fix: addressed Brian 2nd round of comments

* fix(ide): add support for Gemini CLI TOML format

* fix(ide): Added normalization for config.extension, added .yml to the extension array

---------

Co-authored-by: Brian <bmadcode@gmail.com>

.coderabbit.yaml

@@ -0,0 +1,40 @@
+# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
+
+language: "en-US"
+early_access: true
+reviews:
+  profile: chill
+  high_level_summary: false # don't post summary until explicitly invoked
+  request_changes_workflow: false
+  review_status: false
+  commit_status: false
+  walkthrough: false
+  poem: false
+  auto_review:
+    enabled: true
+    drafts: false # Don't review drafts automatically
+    auto_incremental_review: false # always review the whole PR, not just new commits
+    base_branches:
+      - main
+  path_filters:
+    - "!**/node_modules/**"
+  path_instructions:
+    - path: "**/*"
+      instructions: |
+        Focus on inconsistencies, contradictions, edge cases and serious issues.
+        Avoid commenting on minor issues such as linting, formatting and style issues.
+        When providing code suggestions, use GitHub's suggestion format:
+        ```suggestion
+        <code changes>
+        ```
+    - path: "**/*.js"
+      instructions: |
+        CLI tooling code. Check for: missing error handling on fs operations,
+        path.join vs string concatenation, proper cleanup in error paths.
+        Flag any process.exit() without error message.
+chat:
+  auto_reply: true # Response to mentions in comments, a la @coderabbit review
+issue_enrichment:
+  auto_enrich:
+    enabled: false # don't auto-comment on issues
+

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+the official BMAD Discord server (<https://discord.com/invite/gk8jAdXWmj>) - DM a moderator or flag a post.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+<https://www.contributor-covenant.org/version/2/0/code_of_conduct.html>.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+<https://www.contributor-covenant.org/faq>. Translations are available at
+<https://www.contributor-covenant.org/translations>.

.github/FUNDING.yaml

@@ -0,0 +1,15 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project_name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project_name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: bmad
+thanks_dev: # Replace with a single thanks.dev username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/ISSUE_TEMPLATE/config.yaml

@@ -0,0 +1,8 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 📚 Documentation
+    url: http://docs.bmad-method.org
+    about: Check the docs first — tutorials, guides, and reference
+  - name: 💬 Discord Community
+    url: https://discord.gg/gk8jAdXWmj
+    about: Join for questions, discussion, and help before opening an issue

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,22 @@
+---
+name: Feature Request
+about: Suggest an idea or new feature
+title: ''
+labels: ''
+assignees: ''
+---
+
+**Describe your idea**
+A clear and concise description of what you'd like to see added or changed.
+
+**Why is this needed?**
+Explain the problem this solves or the benefit it brings to the BMad community.
+
+**How should it work?**
+Describe your proposed solution. If you have ideas on implementation, share them here.
+
+**PR**
+If you'd like to contribute, please indicate you're working on this or link to your PR. Please review [CONTRIBUTING.md](../../CONTRIBUTING.md) — contributions are always welcome!
+
+**Additional context**
+Add any other context, screenshots, or links that help explain your idea.

.github/ISSUE_TEMPLATE/issue.md

@@ -0,0 +1,32 @@
+---
+name: Issue
+about: Report a problem or something that's not working
+title: ''
+labels: ''
+assignees: ''
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**Steps to reproduce**
+1. What were you doing when the bug occurred?
+2. What steps can recreate the issue?
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Environment (if relevant)**
+- Model(s) used:
+- Agentic IDE used:
+- BMad version:
+- Project language:
+
+**Screenshots or links**
+If applicable, add screenshots or links to help explain the problem.
+
+**PR**
+If you'd like to contribute a fix, please indicate you're working on it or link to your PR. See [CONTRIBUTING.md](../../CONTRIBUTING.md) — contributions are always welcome!
+
+**Additional context**
+Add any other context about the problem here. The more information you provide, the easier it is to help.

.github/scripts/discord-helpers.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+# Discord notification helper functions
+
+# Escape markdown special chars and @mentions for safe Discord display
+# Skips content inside <URL> wrappers to preserve URLs intact
+esc() {
+  awk '{
+    result = ""; in_url = 0; n = length($0)
+    for (i = 1; i <= n; i++) {
+      c = substr($0, i, 1)
+      if (c == "<" && substr($0, i, 8) ~ /^<https?:/) in_url = 1
+      if (in_url) { result = result c; if (c == ">") in_url = 0 }
+      else if (c == "@") result = result "@ "
+      else if (index("[]\\*_()~`", c) > 0) result = result "\\" c
+      else result = result c
+    }
+    print result
+  }'
+}
+
+# Truncate to $1 chars (or 80 if wall-of-text with <3 spaces)
+trunc() {
+  local max=$1
+  local txt=$(tr '\n\r' '  ' | cut -c1-"$max")
+  local spaces=$(printf '%s' "$txt" | tr -cd ' ' | wc -c)
+  [ "$spaces" -lt 3 ] && [ ${#txt} -gt 80 ] && txt=$(printf '%s' "$txt" | cut -c1-80)
+  printf '%s' "$txt"
+}
+
+# Remove incomplete URL at end of truncated text (incomplete URLs are useless)
+strip_trailing_url() { sed -E 's~<?https?://[^[:space:]]*$~~'; }
+
+# Wrap URLs in <> to suppress Discord embeds (keeps links clickable)
+wrap_urls() { sed -E 's~https?://[^[:space:]<>]+~<&>~g'; }

.github/workflows/discord.yaml

@@ -0,0 +1,90 @@
+name: Discord Notification
+
+on:
+  pull_request:
+    types: [opened, closed]
+  issues:
+    types: [opened]
+
+env:
+  MAX_TITLE: 100
+  MAX_BODY: 250
+
+jobs:
+  pull_request:
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.repository.default_branch }}
+          sparse-checkout: .github/scripts
+          sparse-checkout-cone-mode: false
+      - name: Notify Discord
+        env:
+          WEBHOOK: ${{ secrets.DISCORD_WEBHOOK }}
+          ACTION: ${{ github.event.action }}
+          MERGED: ${{ github.event.pull_request.merged }}
+          PR_NUM: ${{ github.event.pull_request.number }}
+          PR_URL: ${{ github.event.pull_request.html_url }}
+          PR_TITLE: ${{ github.event.pull_request.title }}
+          PR_USER: ${{ github.event.pull_request.user.login }}
+          PR_BODY: ${{ github.event.pull_request.body }}
+        run: |
+          set -o pipefail
+          source .github/scripts/discord-helpers.sh
+          [ -z "$WEBHOOK" ] && exit 0
+
+          if [ "$ACTION" = "opened" ]; then ICON="🔀"; LABEL="New PR"
+          elif [ "$ACTION" = "closed" ] && [ "$MERGED" = "true" ]; then ICON="🎉"; LABEL="Merged"
+          elif [ "$ACTION" = "closed" ]; then ICON="❌"; LABEL="Closed"; fi
+
+          TITLE=$(printf '%s' "$PR_TITLE" | trunc $MAX_TITLE | esc)
+          [ ${#PR_TITLE} -gt $MAX_TITLE ] && TITLE="${TITLE}..."
+          BODY=$(printf '%s' "$PR_BODY" | trunc $MAX_BODY)
+          if [ -n "$PR_BODY" ] && [ ${#PR_BODY} -gt $MAX_BODY ]; then
+            BODY=$(printf '%s' "$BODY" | strip_trailing_url)
+          fi
+          BODY=$(printf '%s' "$BODY" | wrap_urls | esc)
+          [ -n "$PR_BODY" ] && [ ${#PR_BODY} -gt $MAX_BODY ] && BODY="${BODY}..."
+          [ -n "$BODY" ] && BODY=" · $BODY"
+          USER=$(printf '%s' "$PR_USER" | esc)
+
+          MSG="$ICON **[$LABEL #$PR_NUM: $TITLE](<$PR_URL>)**"$'\n'"by @$USER$BODY"
+          jq -n --arg content "$MSG" '{content: $content}' | curl -sf --retry 2 -X POST "$WEBHOOK" -H "Content-Type: application/json" -d @-
+
+  issues:
+    if: github.event_name == 'issues'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.repository.default_branch }}
+          sparse-checkout: .github/scripts
+          sparse-checkout-cone-mode: false
+      - name: Notify Discord
+        env:
+          WEBHOOK: ${{ secrets.DISCORD_WEBHOOK }}
+          ISSUE_NUM: ${{ github.event.issue.number }}
+          ISSUE_URL: ${{ github.event.issue.html_url }}
+          ISSUE_TITLE: ${{ github.event.issue.title }}
+          ISSUE_USER: ${{ github.event.issue.user.login }}
+          ISSUE_BODY: ${{ github.event.issue.body }}
+        run: |
+          set -o pipefail
+          source .github/scripts/discord-helpers.sh
+          [ -z "$WEBHOOK" ] && exit 0
+
+          TITLE=$(printf '%s' "$ISSUE_TITLE" | trunc $MAX_TITLE | esc)
+          [ ${#ISSUE_TITLE} -gt $MAX_TITLE ] && TITLE="${TITLE}..."
+          BODY=$(printf '%s' "$ISSUE_BODY" | trunc $MAX_BODY)
+          if [ -n "$ISSUE_BODY" ] && [ ${#ISSUE_BODY} -gt $MAX_BODY ]; then
+            BODY=$(printf '%s' "$BODY" | strip_trailing_url)
+          fi
+          BODY=$(printf '%s' "$BODY" | wrap_urls | esc)
+          [ -n "$ISSUE_BODY" ] && [ ${#ISSUE_BODY} -gt $MAX_BODY ] && BODY="${BODY}..."
+          [ -n "$BODY" ] && BODY=" · $BODY"
+          USER=$(printf '%s' "$ISSUE_USER" | esc)
+
+          MSG="🐛 **[Issue #$ISSUE_NUM: $TITLE](<$ISSUE_URL>)**"$'\n'"by @$USER$BODY"
+          jq -n --arg content "$MSG" '{content: $content}' | curl -sf --retry 2 -X POST "$WEBHOOK" -H "Content-Type: application/json" -d @-

.github/workflows/docs.yaml

@@ -0,0 +1,63 @@
+name: Deploy Documentation
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "docs/**"
+      - "src/modules/*/docs/**"
+      - "website/**"
+      - "tools/build-docs.js"
+      - ".github/workflows/docs.yaml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+          cache: "npm"
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Build documentation
+        env:
+          # Override site URL from GitHub repo variable if set
+          # Otherwise, astro.config.mjs will compute from GITHUB_REPOSITORY
+          SITE_URL: ${{ vars.SITE_URL }}
+        run: npm run docs:build
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: build/site
+
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.github/workflows/manual-release.yaml

@@ -0,0 +1,193 @@
+name: Manual Release
+
+on:
+  workflow_dispatch:
+    inputs:
+      version_bump:
+        description: Version bump type
+        required: true
+        default: beta
+        type: choice
+        options:
+          - beta
+          - alpha
+          - patch
+          - minor
+          - major
+
+permissions:
+  contents: write
+  packages: write
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: npm
+          registry-url: https://registry.npmjs.org
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Run tests and validation
+        run: |
+          npm run validate
+          npm run format:check
+          npm run lint
+
+      - name: Configure Git
+        run: |
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+
+      - name: Bump version
+        run: |
+          case "${{ github.event.inputs.version_bump }}" in
+            alpha|beta) npm version prerelease --no-git-tag-version --preid=${{ github.event.inputs.version_bump }} ;;
+            *)          npm version ${{ github.event.inputs.version_bump }} --no-git-tag-version ;;
+          esac
+
+      - name: Get new version and previous tag
+        id: version
+        run: |
+          echo "new_version=$(node -p "require('./package.json').version")" >> $GITHUB_OUTPUT
+          echo "previous_tag=$(git describe --tags --abbrev=0)" >> $GITHUB_OUTPUT
+
+      - name: Update installer package.json
+        run: |
+          sed -i 's/"version": ".*"/"version": "${{ steps.version.outputs.new_version }}"/' tools/installer/package.json
+
+      # TODO: Re-enable web bundles once tools/cli/bundlers/ is restored
+      # - name: Generate web bundles
+      #   run: npm run bundle
+
+      - name: Commit version bump
+        run: |
+          git add .
+          git commit -m "release: bump to v${{ steps.version.outputs.new_version }}"
+
+      - name: Generate release notes
+        id: release_notes
+        run: |
+          # Get commits since last tag
+          COMMITS=$(git log ${{ steps.version.outputs.previous_tag }}..HEAD --pretty=format:"- %s" --reverse)
+
+          # Categorize commits
+          FEATURES=$(echo "$COMMITS" | grep -E "^- (feat|Feature)" || true)
+          FIXES=$(echo "$COMMITS" | grep -E "^- (fix|Fix)" || true)  
+          CHORES=$(echo "$COMMITS" | grep -E "^- (chore|Chore)" || true)
+          OTHERS=$(echo "$COMMITS" | grep -v -E "^- (feat|Feature|fix|Fix|chore|Chore|release:|Release:)" || true)
+
+          # Build release notes
+          cat > release_notes.md << 'EOF'
+          ## 🚀 What's New in v${{ steps.version.outputs.new_version }}
+
+          EOF
+
+          if [ ! -z "$FEATURES" ]; then
+            echo "### ✨ New Features" >> release_notes.md
+            echo "$FEATURES" >> release_notes.md
+            echo "" >> release_notes.md
+          fi
+
+          if [ ! -z "$FIXES" ]; then
+            echo "### 🐛 Bug Fixes" >> release_notes.md
+            echo "$FIXES" >> release_notes.md
+            echo "" >> release_notes.md
+          fi
+
+          if [ ! -z "$OTHERS" ]; then
+            echo "### 📦 Other Changes" >> release_notes.md
+            echo "$OTHERS" >> release_notes.md
+            echo "" >> release_notes.md
+          fi
+
+          if [ ! -z "$CHORES" ]; then
+            echo "### 🔧 Maintenance" >> release_notes.md
+            echo "$CHORES" >> release_notes.md
+            echo "" >> release_notes.md
+          fi
+
+          cat >> release_notes.md << 'EOF'
+
+          ## 📦 Installation
+
+          ```bash
+          npx bmad-method install
+          ```
+
+          **Full Changelog**: https://github.com/bmad-code-org/BMAD-METHOD/compare/${{ steps.version.outputs.previous_tag }}...v${{ steps.version.outputs.new_version }}
+          EOF
+
+          # Output for GitHub Actions
+          echo "RELEASE_NOTES<<EOF" >> $GITHUB_OUTPUT
+          cat release_notes.md >> $GITHUB_OUTPUT
+          echo "EOF" >> $GITHUB_OUTPUT
+
+      - name: Create and push tag
+        run: |
+          # Check if tag already exists
+          if git rev-parse "v${{ steps.version.outputs.new_version }}" >/dev/null 2>&1; then
+            echo "Tag v${{ steps.version.outputs.new_version }} already exists, skipping tag creation"
+          else
+            git tag -a "v${{ steps.version.outputs.new_version }}" -m "Release v${{ steps.version.outputs.new_version }}"
+            git push origin "v${{ steps.version.outputs.new_version }}"
+          fi
+
+      - name: Push changes to main
+        run: |
+          if git push origin HEAD:main 2>/dev/null; then
+            echo "✅ Successfully pushed to main branch"
+          else
+            echo "⚠️ Could not push to main (protected branch). This is expected."
+            echo "📝 Version bump and tag were created successfully."
+          fi
+
+      - name: Publish to NPM
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
+        run: |
+          VERSION="${{ steps.version.outputs.new_version }}"
+          if [[ "$VERSION" == *"alpha"* ]]; then
+            echo "Publishing alpha prerelease version with --tag alpha"
+            npm publish --tag alpha
+          elif [[ "$VERSION" == *"beta"* ]]; then
+            echo "Publishing beta prerelease version with --tag latest"
+            npm publish --tag latest
+          else
+            echo "Publishing stable version with --tag latest"
+            npm publish --tag latest
+          fi
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: v${{ steps.version.outputs.new_version }}
+          name: "BMad Method v${{ steps.version.outputs.new_version }}"
+          body: |
+            ${{ steps.release_notes.outputs.RELEASE_NOTES }}
+          draft: false
+          prerelease: ${{ contains(steps.version.outputs.new_version, 'alpha') || contains(steps.version.outputs.new_version, 'beta') }}
+
+      - name: Summary
+        run: |
+          echo "## 🎉 Successfully released v${{ steps.version.outputs.new_version }}!" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 📦 Distribution" >> $GITHUB_STEP_SUMMARY
+          echo "- **NPM**: Published with @latest tag" >> $GITHUB_STEP_SUMMARY
+          echo "- **GitHub Release**: https://github.com/bmad-code-org/BMAD-METHOD/releases/tag/v${{ steps.version.outputs.new_version }}" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### ✅ Installation" >> $GITHUB_STEP_SUMMARY
+          echo "\`\`\`bash" >> $GITHUB_STEP_SUMMARY
+          echo "npx bmad-method@${{ steps.version.outputs.new_version }} install" >> $GITHUB_STEP_SUMMARY
+          echo "\`\`\`" >> $GITHUB_STEP_SUMMARY

.github/workflows/quality.yaml

@@ -0,0 +1,115 @@
+name: Quality & Validation
+
+# Runs comprehensive quality checks on all PRs:
+# - Prettier (formatting)
+# - ESLint (linting)
+# - markdownlint (markdown quality)
+# - Schema validation (YAML structure)
+# - Agent schema tests (fixture-based validation)
+# - Installation component tests (compilation)
+# - Bundle validation (web bundle integrity)
+
+"on":
+  pull_request:
+    branches: ["**"]
+  workflow_dispatch:
+
+jobs:
+  prettier:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "npm"
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Prettier format check
+        run: npm run format:check
+
+  eslint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "npm"
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: ESLint
+        run: npm run lint
+
+  markdownlint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "npm"
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: markdownlint
+        run: npm run lint:md
+
+  docs:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "npm"
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Validate documentation links
+        run: npm run docs:validate-links
+
+      - name: Build documentation
+        run: npm run docs:build
+
+  validate:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "npm"
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Validate YAML schemas
+        run: npm run validate:schemas
+
+      - name: Run agent schema validation tests
+        run: npm run test:schemas
+
+      - name: Test agent compilation components
+        run: npm run test:install

.gitignore

@@ -1,21 +1,68 @@
-# Node modules
-node_modules/
+# Dependencies
+**/node_modules/
+pnpm-lock.yaml
+bun.lock
+deno.lock
+pnpm-workspace.yaml
+package-lock.json
+
+test-output/*
+coverage/
 
 # Logs
-logs
+logs/
 *.log
 npm-debug.log*
 
 # Build output
-dist/
-build/
-
-# System files
-.DS_Store
+build/*.txt
 
 # Environment variables
 .env
 
-# VSCode settings
-.vscode/
-CLAUDE.md
+# System files
+.DS_Store
+Thumbs.db
+
+# Development tools and configs
+.prettierrc
+
+# AI assistant files
+CLAUDE.md
+.ai/*
+cursor
+.gemini
+.mcp.json
+CLAUDE.local.md
+.serena/
+.claude/settings.local.json
+
+z*/
+
+_bmad
+_bmad-output
+.clinerules
+.augment
+.crush
+.cursor
+.iflow
+.opencode
+.qwen
+.rovodev
+.kilocodemodes
+.claude
+.codex
+.github/chatmodes
+.github/agents
+.agent
+.agentvibes
+.kiro
+.roo
+.trae
+.windsurf
+
+
+# Astro / Documentation Build
+website/.astro/
+website/dist/
+build/

.husky/pre-commit

@@ -0,0 +1,20 @@
+#!/usr/bin/env sh
+
+# Auto-fix changed files and stage them
+npx --no-install lint-staged
+
+# Validate everything
+npm test
+
+# Validate docs links only when docs change
+if command -v rg >/dev/null 2>&1; then
+  if git diff --cached --name-only | rg -q '^docs/'; then
+    npm run docs:validate-links
+		npm run docs:build
+  fi
+else
+  if git diff --cached --name-only | grep -Eq '^docs/'; then
+    npm run docs:validate-links
+		npm run docs:build
+  fi
+fi

.markdownlint-cli2.yaml

@@ -0,0 +1,41 @@
+# markdownlint-cli2 configuration
+# https://github.com/DavidAnson/markdownlint-cli2
+
+ignores:
+  - "**/node_modules/**"
+  - test/fixtures/**
+  - CODE_OF_CONDUCT.md
+  - _bmad/**
+  - _bmad*/**
+  - .agent/**
+  - .claude/**
+  - .roo/**
+  - .codex/**
+  - .kiro/**
+  - sample-project/**
+  - test-project-install/**
+  - z*/**
+
+# Rule configuration
+config:
+  # Disable all rules by default
+  default: false
+
+  # Heading levels should increment by one (h1 -> h2 -> h3, not h1 -> h3)
+  MD001: true
+
+  # Duplicate sibling headings (same heading text at same level under same parent)
+  MD024:
+    siblings_only: true
+
+  # Trailing commas in headings (likely typos)
+  MD026:
+    punctuation: ","
+
+  # Bare URLs - may not render as links in all parsers
+  # Should use <url> or [text](url) format
+  MD034: true
+
+  # Spaces inside emphasis markers - breaks rendering
+  # e.g., "* text *" won't render as emphasis
+  MD037: true

.npmrc

@@ -0,0 +1 @@
+registry=https://registry.npmjs.org

.nvmrc

@@ -0,0 +1 @@
+22

.prettierignore

@@ -0,0 +1,9 @@
+# Test fixtures with intentionally broken/malformed files
+test/fixtures/**
+
+# Contributor Covenant (external standard)
+CODE_OF_CONDUCT.md
+
+# BMAD runtime folders (user-specific, not in repo)
+_bmad/
+_bmad*/

.vscode/settings.json

@@ -0,0 +1,97 @@
+{
+  "chat.agent.enabled": true,
+  "chat.agent.maxRequests": 15,
+  "github.copilot.chat.agent.runTasks": true,
+  "chat.mcp.discovery.enabled": {
+    "claude-desktop": true,
+    "windsurf": true,
+    "cursor-global": true,
+    "cursor-workspace": true
+  },
+  "github.copilot.chat.agent.autoFix": true,
+  "chat.tools.autoApprove": false,
+  "cSpell.words": [
+    "Agentic",
+    "atlasing",
+    "Biostatistician",
+    "bmad",
+    "Cordova",
+    "customresourcedefinitions",
+    "dashboarded",
+    "Decisioning",
+    "eksctl",
+    "elicitations",
+    "Excalidraw",
+    "filecomplete",
+    "fintech",
+    "fluxcd",
+    "frontmatter",
+    "gamedev",
+    "gitops",
+    "implementability",
+    "Improv",
+    "inclusivity",
+    "ingressgateway",
+    "istioctl",
+    "metroidvania",
+    "NACLs",
+    "nodegroup",
+    "platformconfigs",
+    "Playfocus",
+    "playtesting",
+    "pointerdown",
+    "pointerup",
+    "Polyrepo",
+    "replayability",
+    "roguelike",
+    "roomodes",
+    "Runbook",
+    "runbooks",
+    "Shardable",
+    "Softlock",
+    "solutioning",
+    "speedrunner",
+    "substep",
+    "tekton",
+    "tilemap",
+    "tileset",
+    "tmpl",
+    "Trae",
+    "Unsharded",
+    "VNET",
+    "webskip"
+  ],
+  "json.schemas": [
+    {
+      "fileMatch": ["package.json"],
+      "url": "https://json.schemastore.org/package.json"
+    },
+    {
+      "fileMatch": [".vscode/settings.json"],
+      "url": "vscode://schemas/settings/folder"
+    }
+  ],
+  "editor.formatOnSave": true,
+  "editor.defaultFormatter": "esbenp.prettier-vscode",
+  "[javascript]": {
+    "editor.defaultFormatter": "vscode.typescript-language-features"
+  },
+  "[json]": {
+    "editor.defaultFormatter": "vscode.json-language-features"
+  },
+  "[yaml]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode"
+  },
+  "[markdown]": {
+    "editor.defaultFormatter": "yzhang.markdown-all-in-one"
+  },
+  "yaml.format.enable": false,
+  "editor.codeActionsOnSave": {
+    "source.fixAll.eslint": "explicit"
+  },
+  "editor.rulers": [140],
+  "[xml]": {
+    "editor.defaultFormatter": "redhat.vscode-xml"
+  },
+  "xml.format.maxLineWidth": 140
+}

CNAME

@@ -0,0 +1 @@
+docs.bmad-method.org

CONTRIBUTING.md

@@ -0,0 +1,167 @@
+# Contributing to BMad
+
+Thank you for considering contributing! We believe in **Human Amplification, Not Replacement** — bringing out the best thinking in both humans and AI through guided collaboration.
+
+💬 **Discord**: [Join our community](https://discord.gg/gk8jAdXWmj) for real-time discussions, questions, and collaboration.
+
+---
+
+## Our Philosophy
+
+BMad strengthens human-AI collaboration through specialized agents and guided workflows. Every contribution should answer: **"Does this make humans and AI better together?"**
+
+**✅ What we welcome:**
+- Enhanced collaboration patterns and workflows
+- Improved agent personas and prompts
+- Domain-specific modules leveraging BMad Core
+- Better planning and context continuity
+
+**❌ What doesn't fit:**
+- Purely automated solutions that sideline humans
+- Complexity that creates barriers to adoption
+- Features that fragment BMad Core's foundation
+
+---
+
+## Reporting Issues
+
+**ALL bug reports and feature requests MUST go through GitHub Issues.**
+
+### Before Creating an Issue
+
+1. **Search existing issues** — Use the GitHub issue search to check if your bug or feature has already been reported
+2. **Search closed issues** — Your issue may have been fixed or addressed previously
+3. **Check discussions** — Some conversations happen in [GitHub Discussions](https://github.com/bmad-code-org/BMAD-METHOD/discussions)
+
+### Bug Reports
+
+After searching, if the bug is unreported, use the [bug report template](https://github.com/bmad-code-org/BMAD-METHOD/issues/new?template=bug_report.md) and include:
+
+- Clear description of the problem
+- Steps to reproduce
+- Expected vs actual behavior
+- Your environment (model, IDE, BMad version)
+- Screenshots or error messages if applicable
+
+### Feature Requests
+
+After searching, use the [feature request template](https://github.com/bmad-code-org/BMAD-METHOD/issues/new?template=feature_request.md) and explain:
+
+- What the feature is
+- Why it would benefit the BMad community
+- How it strengthens human-AI collaboration
+
+**For community modules**, review [TRADEMARK.md](TRADEMARK.md) for proper naming conventions (e.g., "My Module (BMad Community Module)").
+
+---
+
+## Before Starting Work
+
+⚠️ **Required before submitting PRs:**
+
+| Work Type     | Requirement                                    |
+| ------------- | ---------------------------------------------- |
+| Bug fix       | An open issue (create one if it doesn't exist) |
+| Feature       | An open feature request issue                  |
+| Large changes | Discussion via issue first                     |
+
+**Why?** This prevents wasted effort on work that may not align with project direction.
+
+---
+
+## Pull Request Guidelines
+
+### Target Branch
+
+Submit PRs to the `main` branch.
+
+### PR Size
+
+- **Ideal**: 200-400 lines of code changes
+- **Maximum**: 800 lines (excluding generated files)
+- **One feature/fix per PR**
+
+If your change exceeds 800 lines, break it into smaller PRs that can be reviewed independently.
+
+### New to Pull Requests?
+
+1. **Fork** the repository
+2. **Clone** your fork: `git clone https://github.com/YOUR-USERNAME/bmad-method.git`
+3. **Create a branch**: `git checkout -b fix/description` or `git checkout -b feature/description`
+4. **Make changes** — keep them focused
+5. **Commit**: `git commit -m "fix: correct typo in README"`
+6. **Push**: `git push origin fix/description`
+7. **Open PR** from your fork on GitHub
+
+### PR Description Template
+
+```markdown
+## What
+[1-2 sentences describing WHAT changed]
+
+## Why
+[1-2 sentences explaining WHY this change is needed]
+Fixes #[issue number]
+
+## How
+- [2-3 bullets listing HOW you implemented it]
+-
+
+## Testing
+[1-2 sentences on how you tested this]
+```
+
+**Keep it under 200 words.**
+
+### Commit Messages
+
+Use conventional commits:
+
+- `feat:` New feature
+- `fix:` Bug fix
+- `docs:` Documentation only
+- `refactor:` Code change (no bug/feature)
+- `test:` Adding tests
+- `chore:` Build/tools changes
+
+Keep messages under 72 characters. Each commit = one logical change.
+
+---
+
+## What Makes a Good PR?
+
+| ✅ Do                        | ❌ Don't                      |
+| --------------------------- | ---------------------------- |
+| Change one thing per PR     | Mix unrelated changes        |
+| Clear title and description | Vague or missing explanation |
+| Reference related issues    | Reformat entire files        |
+| Small, focused commits      | Copy your whole project      |
+| Work on a branch            | Work directly on `main`      |
+
+---
+
+## Prompt & Agent Guidelines
+
+- Keep dev agents lean — focus on coding context, not documentation
+- Web/planning agents can be larger with complex tasks
+- Everything is natural language (markdown) — no code in core framework
+- Use BMad modules for domain-specific features
+- Validate YAML schemas: `npm run validate:schemas`
+
+---
+
+## Need Help?
+
+- 💬 **Discord**: [Join the community](https://discord.gg/gk8jAdXWmj)
+- 🐛 **Bugs**: Use the [bug report template](https://github.com/bmad-code-org/BMAD-METHOD/issues/new?template=bug_report.md)
+- 💡 **Features**: Use the [feature request template](https://github.com/bmad-code-org/BMAD-METHOD/issues/new?template=feature_request.md)
+
+---
+
+## Code of Conduct
+
+By participating, you agree to abide by our [Code of Conduct](.github/CODE_OF_CONDUCT.md).
+
+## License
+
+By contributing, your contributions are licensed under the same MIT License. See [CONTRIBUTORS.md](CONTRIBUTORS.md) for contributor attribution.

CONTRIBUTORS.md

@@ -0,0 +1,32 @@
+# Contributors
+
+BMad Core, BMad Method and BMad and Community BMad Modules are made possible by contributions from our community. We gratefully acknowledge everyone who has helped improve this project.
+
+## How We Credit Contributors
+
+- **Git history** — Every contribution is preserved in the project's commit history
+- **Contributors badge** — See the dynamic contributors list on our [README](README.md)
+- **GitHub contributors graph** — Visual representation at <https://github.com/bmad-code-org/BMAD-METHOD/graphs/contributors>
+
+## Becoming a Contributor
+
+Anyone who submits a pull request that is merged becomes a contributor. Contributions include:
+
+- Bug fixes
+- New features or workflows
+- Documentation improvements
+- Bug reports and issue triaging
+- Code reviews
+- Helping others in discussions
+
+There are no minimum contribution requirements — whether it's a one-character typo fix or a major feature, we value all contributions.
+
+## Copyright
+
+The BMad Method project is copyrighted by BMad Code, LLC. Individual contributions are licensed under the same MIT License as the project. Contributors retain authorship credit through Git history and the contributors graph.
+
+---
+
+**Thank you to everyone who has helped make BMad Method better!**
+
+For contribution guidelines, see [CONTRIBUTING.md](CONTRIBUTING.md).

LICENSE

@@ -0,0 +1,30 @@
+MIT License
+
+Copyright (c) 2025 BMad Code, LLC
+
+This project incorporates contributions from the open source community.
+See [CONTRIBUTORS.md](CONTRIBUTORS.md) for contributor attribution.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+TRADEMARK NOTICE:
+BMad™, BMad Method™, and BMad Core™ are trademarks of BMad Code, LLC, covering all
+casings and variations (including BMAD, bmad, BMadMethod, BMAD-METHOD, etc.). The use of
+these trademarks in this software does not grant any rights to use the trademarks
+for any other purpose. See [TRADEMARK.md](TRADEMARK.md) for detailed guidelines.

README.md

@@ -1,13 +1,150 @@
-# BMad Method V2
+![BMad Method](banner-bmad-method.png)
 
-V2 was the major fix to the shortcomings of V1.
+[![Version](https://img.shields.io/npm/v/bmad-method?color=blue&label=version)](https://www.npmjs.com/package/bmad-method)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+[![Node.js Version](https://img.shields.io/badge/node-%3E%3D20.0.0-brightgreen)](https://nodejs.org)
+[![Discord](https://img.shields.io/badge/Discord-Join%20Community-7289da?logo=discord&logoColor=white)](https://discord.gg/gk8jAdXWmj)
 
-Templates were introduced, and separated from the agents themselves. Also aside from templates, checklists were introduced to give more power in actually vetting the the documents or artifacts being produced were valid and of high quality through a forced round of advanced elicitation.
+**Breakthrough Method of Agile AI Driven Development** — An AI-driven agile development framework with 21 specialized agents, 50+ guided workflows, and scale-adaptive intelligence that adjusts from bug fixes to enterprise systems.
 
-During V2, this is where the discovery of the power of Gemini Gems and Custom GPTs came to light, really indicating how powerful and cost effective it can be to utilize the Web for a lot of the initial planning, but doing it in a structured repeatable way!
+**100% free and open source.** No paywalls. No gated content. No gated Discord. We believe in empowering everyone, not just those who can pay.
 
-The Web Agents were all granular and clearly defined - a much simpler system, but also somewhat of a pain to create each agent separately in the web while also having to manually export and reimport each document when going agent to agent.
+## Why BMad?
 
-Also one confusing aspect was that there were duplicates of temples and checklists for the web versions and the ide versions.
+Traditional AI tools do the thinking for you, producing average results. BMad agents and facilitated workflow act as expert collaborators who guide you through a structured process to bring out your best thinking in partnership with the AI.
 
-But - overall, this was a very low bar to entry to pick up and start using it - The agent personas were all still pretty self contained, aside from calling out to separate template files for the documents.
+- **AI Intelligent Help**: Brand new for beta - AI assisted help will guide you from the beginning to the end - just ask for `/bmad-help` after you have installed BMad to your project
+- **Scale-Domain-Adaptive**: Automatically adjusts planning depth and needs based on project complexity, domain and type - a SaaS Mobile Dating App has different planning needs from a diagnostic medical system, BMad adapts and helps you along the way
+- **Structured Workflows**: Grounded in agile best practices across analysis, planning, architecture, and implementation
+- **Specialized Agents**: 12+ domain experts (PM, Architect, Developer, UX, Scrum Master, and more)
+- **Party Mode**: Bring multiple agent personas into one session to plan, troubleshoot, or discuss your project collaboratively, multiple perspectives with maximum fun
+- **Complete Lifecycle**: From brainstorming to deployment, BMad is there with you every step of the way
+
+## Quick Start
+
+**Prerequisites**: [Node.js](https://nodejs.org) v20+
+
+```bash
+npx bmad-method install
+```
+
+Follow the installer prompts, then open your AI IDE (Claude Code, Cursor, Windsurf, etc.) in the project folder.
+
+> **Not sure what to do?** Run `/bmad-help` — it tells you exactly what's next and what's optional. You can also ask it questions like:
+
+ - `/bmad-help How should I build a web app for my TShirt Business that can scale to millions?`
+ - `/bmad-help I just finished the architecture, I am not sure what to do next`
+
+And the amazing thing is BMad Help evolves depending on what modules you install also!
+ - `/bmad-help Im interested in really exploring creative ways to demo BMad at work, what do you recommend to help plan a great slide deck and compelling narrative?`, and if you have the Creative Intelligence Suite installed, it will offer you different or complimentary advice than if you just have BMad Method Module installed!
+
+The workflows below show the fastest path to working code. You can also load agents directly for a more structured process, extensive planning, or to learn about agile development practices — the agents guide you with menus, explanations, and elicitation at each step.
+
+### Simple Path (Quick Flow)
+
+Bug fixes, small features, clear scope — 3 commands - 1 Optional Agent:
+
+1. `/quick-spec` — analyzes your codebase and produces a tech-spec with stories
+2. `/dev-story` — implements each story
+3. `/code-review` — validates quality
+
+### Full Planning Path (BMad Method)
+
+Products, platforms, complex features — structured planning then build:
+
+1. `/product-brief` — define problem, users, and MVP scope
+2. `/create-prd` — full requirements with personas, metrics, and risks
+3. `/create-architecture` — technical decisions and system design
+4. `/create-epics-and-stories` — break work into prioritized stories
+5. `/sprint-planning` — initialize sprint tracking
+6. **Repeat per story:** `/create-story` → `/dev-story` → `/code-review`
+
+Every step tells you what's next. Optional phases (brainstorming, research, UX design) are available when you need them — ask `/bmad-help` anytime. For a detailed walkthrough, see the [Getting Started Tutorial](http://docs.bmad-method.org/tutorials/getting-started/).
+
+## Modules
+
+BMad Method extends with official modules for specialized domains. Modules are available during installation and can be added to your project at any time. After the V6 beta period these will also be available as Plugins and Granular Skills.
+
+| Module                                | GitHub                                                                                                                            | NPM                                                                                                                | Purpose                                                           |
+| ------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------- |
+| **BMad Method (BMM)**                 | [bmad-code-org/BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD)                                                         | [bmad-method](https://www.npmjs.com/package/bmad-method)                                           | Core framework with 34+ workflows across 4 development phases     |
+| **BMad Builder (BMB)**                | [bmad-code-org/bmad-builder](https://github.com/bmad-code-org/bmad-builder)                                                       | [bmad-builder](https://www.npmjs.com/package/bmad-builder)                                         | Create custom BMad agents, workflows, and domain-specific modules |
+| **Test Architect (TEA)** 🆕           | [bmad-code-org/tea](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise)                                    | [tea](https://www.npmjs.com/package/bmad-method-test-architecture-enterprise)                      | Risk-based test strategy, automation, and release gates (8 workflows) |
+| **Game Dev Studio (BMGD)**            | [bmad-code-org/bmad-module-game-dev-studio](https://github.com/bmad-code-org/bmad-module-game-dev-studio)                         | [bmad-game-dev-studio](https://www.npmjs.com/package/bmad-game-dev-studio)                         | Game development workflows for Unity, Unreal, and Godot           |
+| **Creative Intelligence Suite (CIS)** | [bmad-code-org/bmad-module-creative-intelligence-suite](https://github.com/bmad-code-org/bmad-module-creative-intelligence-suite) | [bmad-creative-intelligence-suite](https://www.npmjs.com/package/bmad-creative-intelligence-suite) | Innovation, brainstorming, design thinking, and problem-solving   |
+
+* More modules are coming in the next 2 weeks from BMad Official, and a community marketplace for the installer also will be coming with the final V6 release!
+
+## Testing Agents
+
+BMad provides two testing options to fit your needs:
+
+### Quinn (QA) - Built-in
+
+**Quick test automation for rapid coverage**
+
+- ✅ **Always available** in BMM module (no separate install)
+- ✅ **Simple**: One workflow (`QA` - Automate)
+- ✅ **Beginner-friendly**: Standard test framework patterns
+- ✅ **Fast**: Generate tests and ship
+
+**Use Quinn for:** Small projects, quick coverage, standard patterns
+
+### Test Architect (TEA) - Optional Module
+
+**Enterprise-grade test strategy and quality engineering**
+
+- 🆕 **Standalone module** (install separately)
+- 🏗️ **Comprehensive**: 8 workflows covering full test lifecycle
+- 🎯 **Advanced**: Risk-based planning, quality gates, NFR assessment
+- 📚 **Knowledge-driven**: 34 testing patterns and best practices
+- 📖 [Test Architect Documentation](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/)
+
+**Use TEA for:** Enterprise projects, test strategy, compliance, release gates
+
+---
+
+## Documentation
+
+**[BMad Documentation](http://docs.bmad-method.org)** — Tutorials, how-to guides, concepts, and reference
+**[Test Architect Documentation](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/)** — TEA standalone module documentation
+
+- [Getting Started Tutorial](http://docs.bmad-method.org/tutorials/getting-started/)
+- [Upgrading from Previous Versions](http://docs.bmad-method.org/how-to/upgrade-to-v6/)
+- [Test Architect Migration Guide](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/migration/) — Upgrading from BMM-embedded TEA
+
+### For v4 Users
+
+- **[v4 Documentation](https://github.com/bmad-code-org/BMAD-METHOD/tree/V4/docs)**
+
+## Community
+
+- [Discord](https://discord.gg/gk8jAdXWmj) — Get help, share ideas, collaborate
+- [Subscribe on YouTube](https://www.youtube.com/@BMadCode) — Tutorials, master class, and podcast (launching Feb 2025)
+- [GitHub Issues](https://github.com/bmad-code-org/BMAD-METHOD/issues) — Bug reports and feature requests
+- [Discussions](https://github.com/bmad-code-org/BMAD-METHOD/discussions) — Community conversations
+
+## Support BMad
+
+BMad is free for everyone — and always will be. If you'd like to support development:
+
+- ⭐ Please click the star project icon near the top right of this page
+- ☕ [Buy Me a Coffee](https://buymeacoffee.com/bmad) — Fuel the development
+- 🏢 Corporate sponsorship — DM on Discord
+- 🎤 Speaking & Media — Available for conferences, podcasts, interviews (BM on Discord)
+
+## Contributing
+
+We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+
+## License
+
+MIT License — see [LICENSE](LICENSE) for details.
+
+---
+
+**BMad** and **BMAD-METHOD** are trademarks of BMad Code, LLC. See [TRADEMARK.md](TRADEMARK.md) for details.
+
+[![Contributors](https://contrib.rocks/image?repo=bmad-code-org/BMAD-METHOD)](https://github.com/bmad-code-org/BMAD-METHOD/graphs/contributors)
+
+See [CONTRIBUTORS.md](CONTRIBUTORS.md) for contributor information.

SECURITY.md

@@ -0,0 +1,85 @@
+# Security Policy
+
+## Supported Versions
+
+We release security patches for the following versions:
+
+| Version | Supported          |
+| ------- | ------------------ |
+| Latest  | :white_check_mark: |
+| < Latest | :x:               |
+
+We recommend always using the latest version of BMad Method to ensure you have the most recent security updates.
+
+## Reporting a Vulnerability
+
+We take security vulnerabilities seriously. If you discover a security issue, please report it responsibly.
+
+### How to Report
+
+**Do NOT report security vulnerabilities through public GitHub issues.**
+
+Instead, please report them via one of these methods:
+
+1. **GitHub Security Advisories** (Preferred): Use [GitHub's private vulnerability reporting](https://github.com/bmad-code-org/BMAD-METHOD/security/advisories/new) to submit a confidential report.
+
+2. **Discord**: Contact a maintainer directly via DM on our [Discord server](https://discord.gg/gk8jAdXWmj).
+
+### What to Include
+
+Please include as much of the following information as possible:
+
+- Type of vulnerability (e.g., prompt injection, path traversal, etc.)
+- Full paths of source file(s) related to the vulnerability
+- Step-by-step instructions to reproduce the issue
+- Proof-of-concept or exploit code (if available)
+- Impact assessment of the vulnerability
+
+### Response Timeline
+
+- **Initial Response**: Within 48 hours of receiving your report
+- **Status Update**: Within 7 days with our assessment
+- **Resolution Target**: Critical issues within 30 days; other issues within 90 days
+
+### What to Expect
+
+1. We will acknowledge receipt of your report
+2. We will investigate and validate the vulnerability
+3. We will work on a fix and coordinate disclosure timing with you
+4. We will credit you in the security advisory (unless you prefer to remain anonymous)
+
+## Security Scope
+
+### In Scope
+
+- Vulnerabilities in BMad Method core framework code
+- Security issues in agent definitions or workflows that could lead to unintended behavior
+- Path traversal or file system access issues
+- Prompt injection vulnerabilities that bypass intended agent behavior
+- Supply chain vulnerabilities in dependencies
+
+### Out of Scope
+
+- Security issues in user-created custom agents or modules
+- Vulnerabilities in third-party AI providers (Claude, GPT, etc.)
+- Issues that require physical access to a user's machine
+- Social engineering attacks
+- Denial of service attacks that don't exploit a specific vulnerability
+
+## Security Best Practices for Users
+
+When using BMad Method:
+
+1. **Review Agent Outputs**: Always review AI-generated code before executing it
+2. **Limit File Access**: Configure your AI IDE to limit file system access where possible
+3. **Keep Updated**: Regularly update to the latest version
+4. **Validate Dependencies**: Review any dependencies added by generated code
+5. **Environment Isolation**: Consider running AI-assisted development in isolated environments
+
+## Acknowledgments
+
+We appreciate the security research community's efforts in helping keep BMad Method secure. Contributors who report valid security issues will be acknowledged in our security advisories.
+
+---
+
+Thank you for helping keep BMad Method and our community safe.

TRADEMARK.md

@@ -0,0 +1,55 @@
+# Trademark Notice & Guidelines
+
+## Trademark Ownership
+
+The following names and logos are trademarks of BMad Code, LLC:
+
+- **BMad** (word mark, all casings: BMad, bmad, BMAD)
+- **BMad Method** (word mark, includes BMadMethod, BMAD-METHOD, and all variations)
+- **BMad Core** (word mark, includes BMadCore, BMAD-CORE, and all variations)
+- **BMad Code** (word mark)
+- BMad Method logo and visual branding
+- The "Build More, Architect Dreams" tagline
+
+**All casings, stylings, and variations** of the above names (with or without hyphens, spaces, or specific capitalization) are covered by these trademarks.
+
+These trademarks are protected under trademark law and are **not** licensed under the MIT License. The MIT License applies to the software code only, not to the BMad brand identity.
+
+## What This Means
+
+You may:
+
+- Use the BMad software under the terms of the MIT License
+- Refer to BMad to accurately describe compatibility or integration (e.g., "Compatible with BMad Method v6")
+- Link to <https://github.com/bmad-code-org/BMAD-METHOD>
+- Fork the software and distribute your own version under a different name
+
+You may **not**:
+
+- Use "BMad" or any confusingly similar variation as your product name, service name, company name, or domain name
+- Present your product as officially endorsed, approved, or certified by BMad Code, LLC when it is not, without written consent from an authorized representative of BMad Code, LLC
+- Use BMad logos or branding in a way that suggests your product is an official or endorsed BMad product
+- Register domain names, social media handles, or trademarks that incorporate BMad branding
+
+## Examples
+
+| Permitted                                              | Not Permitted                                |
+| ------------------------------------------------------ | -------------------------------------------- |
+| "My workflow tool, compatible with BMad Method"        | "BMadFlow" or "BMad Studio"                  |
+| "An alternative implementation inspired by BMad"       | "BMad Pro" or "BMad Enterprise"              |
+| "My Awesome Healthcare Module (Bmad Community Module)" | "The Official BMad Core Healthcare Module"   |
+| Accurately stating you use BMad as a dependency        | Implying official endorsement or partnership |
+
+## Commercial Use
+
+You may sell products that incorporate or work with BMad software. However:
+
+- Your product must have its own distinct name and branding
+- You must not use BMad trademarks in your marketing, domain names, or product identity
+- You may truthfully describe technical compatibility (e.g., "Works with BMad Method")
+
+## Questions?
+
+If you have questions about trademark usage or would like to discuss official partnership or endorsement opportunities, please reach out:
+
+- **Email**: <contact@bmadcode.com>

V2-FULL-DEMO-WALKTHROUGH/_index.md

@@ -1,48 +0,0 @@
-# Documentation Index
-
-## Overview
-
-This index catalogs all documentation files for the BMAD-METHOD project, organized by category for easy reference and AI discoverability.
-
-## Product Documentation
-
-- **[prd.md](prd.md)** - Product Requirements Document outlining the core project scope, features and business objectives.
-- **[final-brief-with-pm-prompt.md](final-brief-with-pm-prompt.md)** - Finalized project brief with Product Management specifications.
-- **[demo.md](demo.md)** - Main demonstration guide for the BMAD-METHOD project.
-
-## Architecture & Technical Design
-
-- **[architecture.md](architecture.md)** - System architecture documentation detailing technical components and their interactions.
-- **[tech-stack.md](tech-stack.md)** - Overview of the technology stack used in the project.
-- **[project-structure.md](project-structure.md)** - Explanation of the project's file and folder organization.
-- **[data-models.md](data-models.md)** - Documentation of data models and database schema.
-- **[environment-vars.md](environment-vars.md)** - Required environment variables and configuration settings.
-
-## API Documentation
-
-- **[api-reference.md](api-reference.md)** - Comprehensive API endpoints and usage reference.
-
-## Epics & User Stories
-
-- **[epic1.md](epic1.md)** - Epic 1 definition and scope.
-- **[epic2.md](epic2.md)** - Epic 2 definition and scope.
-- **[epic3.md](epic3.md)** - Epic 3 definition and scope.
-- **[epic4.md](epic4.md)** - Epic 4 definition and scope.
-- **[epic5.md](epic5.md)** - Epic 5 definition and scope.
-- **[epic-1-stories-demo.md](epic-1-stories-demo.md)** - Detailed user stories for Epic 1.
-- **[epic-2-stories-demo.md](epic-2-stories-demo.md)** - Detailed user stories for Epic 2.
-- **[epic-3-stories-demo.md](epic-3-stories-demo.md)** - Detailed user stories for Epic 3.
-
-## Development Standards
-
-- **[coding-standards.md](coding-standards.md)** - Coding conventions and standards for the project.
-- **[testing-strategy.md](testing-strategy.md)** - Approach to testing, including methodologies and tools.
-
-## AI & Prompts
-
-- **[prompts.md](prompts.md)** - AI prompt templates and guidelines for project assistants.
-- **[combined-artifacts-for-posm.md](combined-artifacts-for-posm.md)** - Consolidated project artifacts for Product Owner and Solution Manager.
-
-## Reference Documents
-
-- **[botched-architecture-draft.md](botched-architecture-draft.md)** - Archived architecture draft (for reference only).

V2-FULL-DEMO-WALKTHROUGH/api-reference.md

@@ -1,97 +0,0 @@
-# BMad Hacker Daily Digest API Reference
-
-This document describes the external APIs consumed by the BMad Hacker Daily Digest application.
-
-## External APIs Consumed
-
-### Algolia Hacker News (HN) Search API
-
-- **Purpose:** Used to fetch the top Hacker News stories and the comments associated with each story.
-- **Base URL:** `http://hn.algolia.com/api/v1`
-- **Authentication:** None required for public search endpoints.
-- **Key Endpoints Used:**
-
-  - **`GET /search` (for Top Stories)**
-
-    - Description: Retrieves stories based on search parameters. Used here to get top stories from the front page.
-    - Request Parameters:
-      - `tags=front_page`: Required to filter for front-page stories.
-      - `hitsPerPage=10`: Specifies the number of stories to retrieve (adjust as needed, default is typically 20).
-    - Example Request (Conceptual using native `Workspace`):
-      ```typescript
-      // Using Node.js native Workspace API
-      const url =
-        "[http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10](http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10)";
-      const response = await fetch(url);
-      const data = await response.json();
-      ```
-    - Success Response Schema (Code: `200 OK`): See "Algolia HN API - Story Response Subset" in `docs/data-models.md`. Primarily interested in the `hits` array containing story objects.
-    - Error Response Schema(s): Standard HTTP errors (e.g., 4xx, 5xx). May return JSON with an error message.
-
-  - **`GET /search` (for Comments)**
-    - Description: Retrieves comments associated with a specific story ID.
-    - Request Parameters:
-      - `tags=comment,story_{storyId}`: Required to filter for comments belonging to the specified `storyId`. Replace `{storyId}` with the actual ID (e.g., `story_12345`).
-      - `hitsPerPage={maxComments}`: Specifies the maximum number of comments to retrieve (value from `.env` `MAX_COMMENTS_PER_STORY`).
-    - Example Request (Conceptual using native `Workspace`):
-      ```typescript
-      // Using Node.js native Workspace API
-      const storyId = "..."; // HN Story ID
-      const maxComments = 50; // From config
-      const url = `http://hn.algolia.com/api/v1/search?tags=comment,story_${storyId}&hitsPerPage=${maxComments}`;
-      const response = await fetch(url);
-      const data = await response.json();
-      ```
-    - Success Response Schema (Code: `200 OK`): See "Algolia HN API - Comment Response Subset" in `docs/data-models.md`. Primarily interested in the `hits` array containing comment objects.
-    - Error Response Schema(s): Standard HTTP errors.
-
-- **Rate Limits:** Subject to Algolia's public API rate limits (typically generous for HN search but not explicitly defined/guaranteed). Implementations should handle potential 429 errors gracefully if encountered.
-- **Link to Official Docs:** [https://hn.algolia.com/api](https://hn.algolia.com/api)
-
-### Ollama API (Local Instance)
-
-- **Purpose:** Used to generate text summaries for scraped article content and HN comment discussions using a locally running LLM.
-- **Base URL:** Configurable via the `OLLAMA_ENDPOINT_URL` environment variable (e.g., `http://localhost:11434`).
-- **Authentication:** None typically required for default local installations.
-- **Key Endpoints Used:**
-
-  - **`POST /api/generate`**
-    - Description: Generates text based on a model and prompt. Used here for summarization.
-    - Request Body Schema: See `OllamaGenerateRequest` in `docs/data-models.md`. Requires `model` (from `.env` `OLLAMA_MODEL`), `prompt`, and `stream: false`.
-    - Example Request (Conceptual using native `Workspace`):
-      ```typescript
-      // Using Node.js native Workspace API
-      const ollamaUrl =
-        process.env.OLLAMA_ENDPOINT_URL || "http://localhost:11434";
-      const requestBody: OllamaGenerateRequest = {
-        model: process.env.OLLAMA_MODEL || "llama3",
-        prompt: "Summarize this text: ...",
-        stream: false,
-      };
-      const response = await fetch(`${ollamaUrl}/api/generate`, {
-        method: "POST",
-        headers: { "Content-Type": "application/json" },
-        body: JSON.stringify(requestBody),
-      });
-      const data: OllamaGenerateResponse | { error: string } =
-        await response.json();
-      ```
-    - Success Response Schema (Code: `200 OK`): See `OllamaGenerateResponse` in `docs/data-models.md`. Key field is `response` containing the generated text.
-    - Error Response Schema(s): May return non-200 status codes or a `200 OK` with a JSON body like `{ "error": "error message..." }` (e.g., if the model is unavailable).
-
-- **Rate Limits:** N/A for a typical local instance. Performance depends on local hardware.
-- **Link to Official Docs:** [https://github.com/ollama/ollama/blob/main/docs/api.md](https://github.com/ollama/ollama/blob/main/docs/api.md)
-
-## Internal APIs Provided
-
-- **N/A:** The application is a self-contained CLI tool and does not expose any APIs for other services to consume.
-
-## Cloud Service SDK Usage
-
-- **N/A:** The application runs locally and uses the native Node.js `Workspace` API for HTTP requests, not cloud provider SDKs.
-
-## Change Log
-
-| Change        | Date       | Version | Description                     | Author      |
-| ------------- | ---------- | ------- | ------------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Draft based on PRD/Epics/Models | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/api-reference.txt

@@ -1,97 +0,0 @@
-# BMad Hacker Daily Digest API Reference
-
-This document describes the external APIs consumed by the BMad Hacker Daily Digest application.
-
-## External APIs Consumed
-
-### Algolia Hacker News (HN) Search API
-
-- **Purpose:** Used to fetch the top Hacker News stories and the comments associated with each story.
-- **Base URL:** `http://hn.algolia.com/api/v1`
-- **Authentication:** None required for public search endpoints.
-- **Key Endpoints Used:**
-
-  - **`GET /search` (for Top Stories)**
-
-    - Description: Retrieves stories based on search parameters. Used here to get top stories from the front page.
-    - Request Parameters:
-      - `tags=front_page`: Required to filter for front-page stories.
-      - `hitsPerPage=10`: Specifies the number of stories to retrieve (adjust as needed, default is typically 20).
-    - Example Request (Conceptual using native `Workspace`):
-      ```typescript
-      // Using Node.js native Workspace API
-      const url =
-        "[http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10](http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10)";
-      const response = await fetch(url);
-      const data = await response.json();
-      ```
-    - Success Response Schema (Code: `200 OK`): See "Algolia HN API - Story Response Subset" in `docs/data-models.md`. Primarily interested in the `hits` array containing story objects.
-    - Error Response Schema(s): Standard HTTP errors (e.g., 4xx, 5xx). May return JSON with an error message.
-
-  - **`GET /search` (for Comments)**
-    - Description: Retrieves comments associated with a specific story ID.
-    - Request Parameters:
-      - `tags=comment,story_{storyId}`: Required to filter for comments belonging to the specified `storyId`. Replace `{storyId}` with the actual ID (e.g., `story_12345`).
-      - `hitsPerPage={maxComments}`: Specifies the maximum number of comments to retrieve (value from `.env` `MAX_COMMENTS_PER_STORY`).
-    - Example Request (Conceptual using native `Workspace`):
-      ```typescript
-      // Using Node.js native Workspace API
-      const storyId = "..."; // HN Story ID
-      const maxComments = 50; // From config
-      const url = `http://hn.algolia.com/api/v1/search?tags=comment,story_${storyId}&hitsPerPage=${maxComments}`;
-      const response = await fetch(url);
-      const data = await response.json();
-      ```
-    - Success Response Schema (Code: `200 OK`): See "Algolia HN API - Comment Response Subset" in `docs/data-models.md`. Primarily interested in the `hits` array containing comment objects.
-    - Error Response Schema(s): Standard HTTP errors.
-
-- **Rate Limits:** Subject to Algolia's public API rate limits (typically generous for HN search but not explicitly defined/guaranteed). Implementations should handle potential 429 errors gracefully if encountered.
-- **Link to Official Docs:** [https://hn.algolia.com/api](https://hn.algolia.com/api)
-
-### Ollama API (Local Instance)
-
-- **Purpose:** Used to generate text summaries for scraped article content and HN comment discussions using a locally running LLM.
-- **Base URL:** Configurable via the `OLLAMA_ENDPOINT_URL` environment variable (e.g., `http://localhost:11434`).
-- **Authentication:** None typically required for default local installations.
-- **Key Endpoints Used:**
-
-  - **`POST /api/generate`**
-    - Description: Generates text based on a model and prompt. Used here for summarization.
-    - Request Body Schema: See `OllamaGenerateRequest` in `docs/data-models.md`. Requires `model` (from `.env` `OLLAMA_MODEL`), `prompt`, and `stream: false`.
-    - Example Request (Conceptual using native `Workspace`):
-      ```typescript
-      // Using Node.js native Workspace API
-      const ollamaUrl =
-        process.env.OLLAMA_ENDPOINT_URL || "http://localhost:11434";
-      const requestBody: OllamaGenerateRequest = {
-        model: process.env.OLLAMA_MODEL || "llama3",
-        prompt: "Summarize this text: ...",
-        stream: false,
-      };
-      const response = await fetch(`${ollamaUrl}/api/generate`, {
-        method: "POST",
-        headers: { "Content-Type": "application/json" },
-        body: JSON.stringify(requestBody),
-      });
-      const data: OllamaGenerateResponse | { error: string } =
-        await response.json();
-      ```
-    - Success Response Schema (Code: `200 OK`): See `OllamaGenerateResponse` in `docs/data-models.md`. Key field is `response` containing the generated text.
-    - Error Response Schema(s): May return non-200 status codes or a `200 OK` with a JSON body like `{ "error": "error message..." }` (e.g., if the model is unavailable).
-
-- **Rate Limits:** N/A for a typical local instance. Performance depends on local hardware.
-- **Link to Official Docs:** [https://github.com/ollama/ollama/blob/main/docs/api.md](https://github.com/ollama/ollama/blob/main/docs/api.md)
-
-## Internal APIs Provided
-
-- **N/A:** The application is a self-contained CLI tool and does not expose any APIs for other services to consume.
-
-## Cloud Service SDK Usage
-
-- **N/A:** The application runs locally and uses the native Node.js `Workspace` API for HTTP requests, not cloud provider SDKs.
-
-## Change Log
-
-| Change        | Date       | Version | Description                     | Author      |
-| ------------- | ---------- | ------- | ------------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Draft based on PRD/Epics/Models | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/architecture.md

@@ -1,254 +0,0 @@
-# BMad Hacker Daily Digest Architecture Document
-
-## Technical Summary
-
-The BMad Hacker Daily Digest is a command-line interface (CLI) tool designed to provide users with concise summaries of top Hacker News (HN) stories and their associated comment discussions . Built with TypeScript and Node.js (v22) , it operates entirely on the user's local machine . The core functionality involves a sequential pipeline: fetching story and comment data from the Algolia HN Search API , attempting to scrape linked article content , generating summaries using a local Ollama LLM instance , persisting intermediate data to the local filesystem , and finally assembling and emailing an HTML digest using Nodemailer . The architecture emphasizes modularity and testability, including mandatory standalone scripts for testing each pipeline stage . The project starts from the `bmad-boilerplate` template .
-
-## High-Level Overview
-
-The application follows a simple, sequential pipeline architecture executed via a manual CLI command (`npm run dev` or `npm start`) . There is no persistent database; the local filesystem is used to store intermediate data artifacts (fetched data, scraped text, summaries) between steps within a date-stamped directory . All external HTTP communication (Algolia API, article scraping, Ollama API) utilizes the native Node.js `Workspace` API .
-
-```mermaid
-graph LR
-    subgraph "BMad Hacker Daily Digest (Local CLI)"
-        A[index.ts / CLI Trigger] --> B(core/pipeline.ts);
-        B --> C{Fetch HN Data};
-        B --> D{Scrape Articles};
-        B --> E{Summarize Content};
-        B --> F{Assemble & Email Digest};
-        C --> G["Local FS (_data.json)"];
-        D --> H["Local FS (_article.txt)"];
-        E --> I["Local FS (_summary.json)"];
-        F --> G;
-        F --> H;
-        F --> I;
-    end
-
-    subgraph External Services
-        X[Algolia HN API];
-        Y[Article Websites];
-        Z["Ollama API (Local)"];
-        W[SMTP Service];
-    end
-
-    C --> X;
-    D --> Y;
-    E --> Z;
-    F --> W;
-
-    style G fill:#eee,stroke:#333,stroke-width:1px
-    style H fill:#eee,stroke:#333,stroke-width:1px
-    style I fill:#eee,stroke:#333,stroke-width:1px
-```
-
-## Component View
-
-The application code (`src/`) is organized into logical modules based on the defined project structure (`docs/project-structure.md`). Key components include:
-
-- **`src/index.ts`**: The main entry point, handling CLI invocation and initiating the pipeline.
-- **`src/core/pipeline.ts`**: Orchestrates the sequential execution of the main pipeline stages (fetch, scrape, summarize, email).
-- **`src/clients/`**: Modules responsible for interacting with external APIs.
-  - `algoliaHNClient.ts`: Communicates with the Algolia HN Search API.
-  - `ollamaClient.ts`: Communicates with the local Ollama API.
-- **`src/scraper/articleScraper.ts`**: Handles fetching and extracting text content from article URLs.
-- **`src/email/`**: Manages digest assembly, HTML rendering, and email dispatch via Nodemailer.
-  - `contentAssembler.ts`: Reads persisted data.
-  - `templates.ts`: Renders HTML.
-  - `emailSender.ts`: Sends the email.
-- **`src/stages/`**: Contains standalone scripts (`Workspace_hn_data.ts`, `scrape_articles.ts`, etc.) for testing individual pipeline stages independently using local data where applicable.
-- **`src/utils/`**: Shared utilities for configuration loading (`config.ts`), logging (`logger.ts`), and date handling (`dateUtils.ts`).
-- **`src/types/`**: Shared TypeScript interfaces and types.
-
-```mermaid
-graph TD
-    subgraph AppComponents ["Application Components (src/)"]
-        Idx(index.ts) --> Pipe(core/pipeline.ts);
-        Pipe --> HNClient(clients/algoliaHNClient.ts);
-        Pipe --> Scraper(scraper/articleScraper.ts);
-        Pipe --> OllamaClient(clients/ollamaClient.ts);
-        Pipe --> Assembler(email/contentAssembler.ts);
-        Pipe --> Renderer(email/templates.ts);
-        Pipe --> Sender(email/emailSender.ts);
-
-        Pipe --> Utils(utils/*);
-        Pipe --> Types(types/*);
-        HNClient --> Types;
-        OllamaClient --> Types;
-        Assembler --> Types;
-        Renderer --> Types;
-
-        subgraph StageRunnersSubgraph ["Stage Runners (src/stages/)"]
-            SFetch(fetch_hn_data.ts) --> HNClient;
-            SFetch --> Utils;
-            SScrape(scrape_articles.ts) --> Scraper;
-            SScrape --> Utils;
-            SSummarize(summarize_content.ts) --> OllamaClient;
-            SSummarize --> Utils;
-            SEmail(send_digest.ts) --> Assembler;
-            SEmail --> Renderer;
-            SEmail --> Sender;
-            SEmail --> Utils;
-        end
-    end
-
-    subgraph Externals ["Filesystem & External"]
-        FS["Local Filesystem (output/)"]
-        Algolia((Algolia HN API))
-        Websites((Article Websites))
-        Ollama["Ollama API (Local)"]
-        SMTP((SMTP Service))
-    end
-
-    HNClient --> Algolia;
-    Scraper --> Websites;
-    OllamaClient --> Ollama;
-    Sender --> SMTP;
-
-    Pipe --> FS;
-    Assembler --> FS;
-
-    SFetch --> FS;
-    SScrape --> FS;
-    SSummarize --> FS;
-    SEmail --> FS;
-
-    %% Apply style to the subgraph using its ID after the block
-    style StageRunnersSubgraph fill:#f9f,stroke:#333,stroke-width:1px
-```
-
-## Key Architectural Decisions & Patterns
-
-- **Architecture Style:** Simple Sequential Pipeline executed via CLI.
-- **Execution Environment:** Local machine only; no cloud deployment, no database for MVP.
-- **Data Handling:** Intermediate data persisted to local filesystem in a date-stamped directory.
-- **HTTP Client:** Mandatory use of native Node.js v22 `Workspace` API for all external HTTP requests.
-- **Modularity:** Code organized into distinct modules for clients, scraping, email, core logic, utilities, and types to promote separation of concerns and testability.
-- **Stage Testing:** Mandatory standalone scripts (`src/stages/*`) allow independent testing of each pipeline phase.
-- **Configuration:** Environment variables loaded natively from `.env` file; no `dotenv` package required.
-- **Error Handling:** Graceful handling of scraping failures (log and continue); basic logging for other API/network errors.
-- **Logging:** Basic console logging via a simple wrapper (`src/utils/logger.ts`) for MVP; structured file logging is a post-MVP consideration.
-- **Key Libraries:** `@extractus/article-extractor`, `date-fns`, `nodemailer`, `yargs`. (See `docs/tech-stack.md`)
-
-## Core Workflow / Sequence Diagram (Main Pipeline)
-
-```mermaid
-sequenceDiagram
-    participant CLI_User as CLI User
-    participant Idx as src/index.ts
-    participant Pipe as core/pipeline.ts
-    participant Cfg as utils/config.ts
-    participant Log as utils/logger.ts
-    participant HN as clients/algoliaHNClient.ts
-    participant FS as Local FS [output/]
-    participant Scr as scraper/articleScraper.ts
-    participant Oll as clients/ollamaClient.ts
-    participant Asm as email/contentAssembler.ts
-    participant Tpl as email/templates.ts
-    participant Snd as email/emailSender.ts
-    participant Alg as Algolia HN API
-    participant Web as Article Website
-    participant Olm as Ollama API [Local]
-    participant SMTP as SMTP Service
-
-    Note right of CLI_User: Triggered via 'npm run dev'/'start'
-
-    CLI_User ->> Idx: Execute script
-    Idx ->> Cfg: Load .env config
-    Idx ->> Log: Initialize logger
-    Idx ->> Pipe: runPipeline()
-    Pipe ->> Log: Log start
-    Pipe ->> HN: fetchTopStories()
-    HN ->> Alg: Request stories
-    Alg -->> HN: Story data
-    HN -->> Pipe: stories[]
-    loop For each story
-        Pipe ->> HN: fetchCommentsForStory(storyId, max)
-        HN ->> Alg: Request comments
-        Alg -->> HN: Comment data
-        HN -->> Pipe: comments[]
-        Pipe ->> FS: Write {storyId}_data.json
-    end
-    Pipe ->> Log: Log HN fetch complete
-
-    loop For each story with URL
-        Pipe ->> Scr: scrapeArticle(story.url)
-        Scr ->> Web: Request article HTML [via Workspace]
-        alt Scraping Successful
-            Web -->> Scr: HTML content
-            Scr -->> Pipe: articleText: string
-            Pipe ->> FS: Write {storyId}_article.txt
-        else Scraping Failed / Skipped
-            Web -->> Scr: Error / Non-HTML / Timeout
-            Scr -->> Pipe: articleText: null
-            Pipe ->> Log: Log scraping failure/skip
-        end
-    end
-    Pipe ->> Log: Log scraping complete
-
-    loop For each story
-        alt Article content exists
-            Pipe ->> Oll: generateSummary(prompt, articleText)
-            Oll ->> Olm: POST /api/generate [article]
-            Olm -->> Oll: Article Summary / Error
-            Oll -->> Pipe: articleSummary: string | null
-        else No article content
-            Pipe -->> Pipe: Set articleSummary = null
-        end
-        alt Comments exist
-            Pipe ->> Pipe: Format comments to text block
-            Pipe ->> Oll: generateSummary(prompt, commentsText)
-            Oll ->> Olm: POST /api/generate [comments]
-            Olm -->> Oll: Discussion Summary / Error
-            Oll -->> Pipe: discussionSummary: string | null
-        else No comments
-            Pipe -->> Pipe: Set discussionSummary = null
-        end
-        Pipe ->> FS: Write {storyId}_summary.json
-    end
-    Pipe ->> Log: Log summarization complete
-
-    Pipe ->> Asm: assembleDigestData(dateDirPath)
-    Asm ->> FS: Read _data.json, _summary.json files
-    FS -->> Asm: File contents
-    Asm -->> Pipe: digestData[]
-    alt Digest data assembled
-        Pipe ->> Tpl: renderDigestHtml(digestData, date)
-        Tpl -->> Pipe: htmlContent: string
-        Pipe ->> Snd: sendDigestEmail(subject, htmlContent)
-        Snd ->> Cfg: Load email config
-        Snd ->> SMTP: Send email
-        SMTP -->> Snd: Success/Failure
-        Snd -->> Pipe: success: boolean
-        Pipe ->> Log: Log email result
-    else Assembly failed / No data
-        Pipe ->> Log: Log skipping email
-    end
-    Pipe ->> Log: Log finished
-```
-
-## Infrastructure and Deployment Overview
-
-- **Cloud Provider(s):** N/A. Executes locally on the user's machine.
-- **Core Services Used:** N/A (relies on external Algolia API, local Ollama, target websites, SMTP provider).
-- **Infrastructure as Code (IaC):** N/A.
-- **Deployment Strategy:** Manual execution via CLI (`npm run dev` or `npm run start` after `npm run build`). No CI/CD pipeline required for MVP.
-- **Environments:** Single environment: local development machine.
-
-## Key Reference Documents
-
-- `docs/prd.md`
-- `docs/epic1.md` ... `docs/epic5.md`
-- `docs/tech-stack.md`
-- `docs/project-structure.md`
-- `docs/data-models.md`
-- `docs/api-reference.md`
-- `docs/environment-vars.md`
-- `docs/coding-standards.md`
-- `docs/testing-strategy.md`
-- `docs/prompts.md`
-
-## Change Log
-
-| Change        | Date       | Version | Description                | Author      |
-| ------------- | ---------- | ------- | -------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Initial draft based on PRD | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/architecture.txt

@@ -1,254 +0,0 @@
-# BMad Hacker Daily Digest Architecture Document
-
-## Technical Summary
-
-The BMad Hacker Daily Digest is a command-line interface (CLI) tool designed to provide users with concise summaries of top Hacker News (HN) stories and their associated comment discussions . Built with TypeScript and Node.js (v22) , it operates entirely on the user's local machine . The core functionality involves a sequential pipeline: fetching story and comment data from the Algolia HN Search API , attempting to scrape linked article content , generating summaries using a local Ollama LLM instance , persisting intermediate data to the local filesystem , and finally assembling and emailing an HTML digest using Nodemailer . The architecture emphasizes modularity and testability, including mandatory standalone scripts for testing each pipeline stage . The project starts from the `bmad-boilerplate` template .
-
-## High-Level Overview
-
-The application follows a simple, sequential pipeline architecture executed via a manual CLI command (`npm run dev` or `npm start`) . There is no persistent database; the local filesystem is used to store intermediate data artifacts (fetched data, scraped text, summaries) between steps within a date-stamped directory . All external HTTP communication (Algolia API, article scraping, Ollama API) utilizes the native Node.js `Workspace` API .
-
-```mermaid
-graph LR
-    subgraph "BMad Hacker Daily Digest (Local CLI)"
-        A[index.ts / CLI Trigger] --> B(core/pipeline.ts);
-        B --> C{Fetch HN Data};
-        B --> D{Scrape Articles};
-        B --> E{Summarize Content};
-        B --> F{Assemble & Email Digest};
-        C --> G["Local FS (_data.json)"];
-        D --> H["Local FS (_article.txt)"];
-        E --> I["Local FS (_summary.json)"];
-        F --> G;
-        F --> H;
-        F --> I;
-    end
-
-    subgraph External Services
-        X[Algolia HN API];
-        Y[Article Websites];
-        Z["Ollama API (Local)"];
-        W[SMTP Service];
-    end
-
-    C --> X;
-    D --> Y;
-    E --> Z;
-    F --> W;
-
-    style G fill:#eee,stroke:#333,stroke-width:1px
-    style H fill:#eee,stroke:#333,stroke-width:1px
-    style I fill:#eee,stroke:#333,stroke-width:1px
-```
-
-## Component View
-
-The application code (`src/`) is organized into logical modules based on the defined project structure (`docs/project-structure.md`). Key components include:
-
-- **`src/index.ts`**: The main entry point, handling CLI invocation and initiating the pipeline.
-- **`src/core/pipeline.ts`**: Orchestrates the sequential execution of the main pipeline stages (fetch, scrape, summarize, email).
-- **`src/clients/`**: Modules responsible for interacting with external APIs.
-  - `algoliaHNClient.ts`: Communicates with the Algolia HN Search API.
-  - `ollamaClient.ts`: Communicates with the local Ollama API.
-- **`src/scraper/articleScraper.ts`**: Handles fetching and extracting text content from article URLs.
-- **`src/email/`**: Manages digest assembly, HTML rendering, and email dispatch via Nodemailer.
-  - `contentAssembler.ts`: Reads persisted data.
-  - `templates.ts`: Renders HTML.
-  - `emailSender.ts`: Sends the email.
-- **`src/stages/`**: Contains standalone scripts (`Workspace_hn_data.ts`, `scrape_articles.ts`, etc.) for testing individual pipeline stages independently using local data where applicable.
-- **`src/utils/`**: Shared utilities for configuration loading (`config.ts`), logging (`logger.ts`), and date handling (`dateUtils.ts`).
-- **`src/types/`**: Shared TypeScript interfaces and types.
-
-```mermaid
-graph TD
-    subgraph AppComponents ["Application Components (src/)"]
-        Idx(index.ts) --> Pipe(core/pipeline.ts);
-        Pipe --> HNClient(clients/algoliaHNClient.ts);
-        Pipe --> Scraper(scraper/articleScraper.ts);
-        Pipe --> OllamaClient(clients/ollamaClient.ts);
-        Pipe --> Assembler(email/contentAssembler.ts);
-        Pipe --> Renderer(email/templates.ts);
-        Pipe --> Sender(email/emailSender.ts);
-
-        Pipe --> Utils(utils/*);
-        Pipe --> Types(types/*);
-        HNClient --> Types;
-        OllamaClient --> Types;
-        Assembler --> Types;
-        Renderer --> Types;
-
-        subgraph StageRunnersSubgraph ["Stage Runners (src/stages/)"]
-            SFetch(fetch_hn_data.ts) --> HNClient;
-            SFetch --> Utils;
-            SScrape(scrape_articles.ts) --> Scraper;
-            SScrape --> Utils;
-            SSummarize(summarize_content.ts) --> OllamaClient;
-            SSummarize --> Utils;
-            SEmail(send_digest.ts) --> Assembler;
-            SEmail --> Renderer;
-            SEmail --> Sender;
-            SEmail --> Utils;
-        end
-    end
-
-    subgraph Externals ["Filesystem & External"]
-        FS["Local Filesystem (output/)"]
-        Algolia((Algolia HN API))
-        Websites((Article Websites))
-        Ollama["Ollama API (Local)"]
-        SMTP((SMTP Service))
-    end
-
-    HNClient --> Algolia;
-    Scraper --> Websites;
-    OllamaClient --> Ollama;
-    Sender --> SMTP;
-
-    Pipe --> FS;
-    Assembler --> FS;
-
-    SFetch --> FS;
-    SScrape --> FS;
-    SSummarize --> FS;
-    SEmail --> FS;
-
-    %% Apply style to the subgraph using its ID after the block
-    style StageRunnersSubgraph fill:#f9f,stroke:#333,stroke-width:1px
-```
-
-## Key Architectural Decisions & Patterns
-
-- **Architecture Style:** Simple Sequential Pipeline executed via CLI.
-- **Execution Environment:** Local machine only; no cloud deployment, no database for MVP.
-- **Data Handling:** Intermediate data persisted to local filesystem in a date-stamped directory.
-- **HTTP Client:** Mandatory use of native Node.js v22 `Workspace` API for all external HTTP requests.
-- **Modularity:** Code organized into distinct modules for clients, scraping, email, core logic, utilities, and types to promote separation of concerns and testability.
-- **Stage Testing:** Mandatory standalone scripts (`src/stages/*`) allow independent testing of each pipeline phase.
-- **Configuration:** Environment variables loaded natively from `.env` file; no `dotenv` package required.
-- **Error Handling:** Graceful handling of scraping failures (log and continue); basic logging for other API/network errors.
-- **Logging:** Basic console logging via a simple wrapper (`src/utils/logger.ts`) for MVP; structured file logging is a post-MVP consideration.
-- **Key Libraries:** `@extractus/article-extractor`, `date-fns`, `nodemailer`, `yargs`. (See `docs/tech-stack.md`)
-
-## Core Workflow / Sequence Diagram (Main Pipeline)
-
-```mermaid
-sequenceDiagram
-    participant CLI_User as CLI User
-    participant Idx as src/index.ts
-    participant Pipe as core/pipeline.ts
-    participant Cfg as utils/config.ts
-    participant Log as utils/logger.ts
-    participant HN as clients/algoliaHNClient.ts
-    participant FS as Local FS [output/]
-    participant Scr as scraper/articleScraper.ts
-    participant Oll as clients/ollamaClient.ts
-    participant Asm as email/contentAssembler.ts
-    participant Tpl as email/templates.ts
-    participant Snd as email/emailSender.ts
-    participant Alg as Algolia HN API
-    participant Web as Article Website
-    participant Olm as Ollama API [Local]
-    participant SMTP as SMTP Service
-
-    Note right of CLI_User: Triggered via 'npm run dev'/'start'
-
-    CLI_User ->> Idx: Execute script
-    Idx ->> Cfg: Load .env config
-    Idx ->> Log: Initialize logger
-    Idx ->> Pipe: runPipeline()
-    Pipe ->> Log: Log start
-    Pipe ->> HN: fetchTopStories()
-    HN ->> Alg: Request stories
-    Alg -->> HN: Story data
-    HN -->> Pipe: stories[]
-    loop For each story
-        Pipe ->> HN: fetchCommentsForStory(storyId, max)
-        HN ->> Alg: Request comments
-        Alg -->> HN: Comment data
-        HN -->> Pipe: comments[]
-        Pipe ->> FS: Write {storyId}_data.json
-    end
-    Pipe ->> Log: Log HN fetch complete
-
-    loop For each story with URL
-        Pipe ->> Scr: scrapeArticle(story.url)
-        Scr ->> Web: Request article HTML [via Workspace]
-        alt Scraping Successful
-            Web -->> Scr: HTML content
-            Scr -->> Pipe: articleText: string
-            Pipe ->> FS: Write {storyId}_article.txt
-        else Scraping Failed / Skipped
-            Web -->> Scr: Error / Non-HTML / Timeout
-            Scr -->> Pipe: articleText: null
-            Pipe ->> Log: Log scraping failure/skip
-        end
-    end
-    Pipe ->> Log: Log scraping complete
-
-    loop For each story
-        alt Article content exists
-            Pipe ->> Oll: generateSummary(prompt, articleText)
-            Oll ->> Olm: POST /api/generate [article]
-            Olm -->> Oll: Article Summary / Error
-            Oll -->> Pipe: articleSummary: string | null
-        else No article content
-            Pipe -->> Pipe: Set articleSummary = null
-        end
-        alt Comments exist
-            Pipe ->> Pipe: Format comments to text block
-            Pipe ->> Oll: generateSummary(prompt, commentsText)
-            Oll ->> Olm: POST /api/generate [comments]
-            Olm -->> Oll: Discussion Summary / Error
-            Oll -->> Pipe: discussionSummary: string | null
-        else No comments
-            Pipe -->> Pipe: Set discussionSummary = null
-        end
-        Pipe ->> FS: Write {storyId}_summary.json
-    end
-    Pipe ->> Log: Log summarization complete
-
-    Pipe ->> Asm: assembleDigestData(dateDirPath)
-    Asm ->> FS: Read _data.json, _summary.json files
-    FS -->> Asm: File contents
-    Asm -->> Pipe: digestData[]
-    alt Digest data assembled
-        Pipe ->> Tpl: renderDigestHtml(digestData, date)
-        Tpl -->> Pipe: htmlContent: string
-        Pipe ->> Snd: sendDigestEmail(subject, htmlContent)
-        Snd ->> Cfg: Load email config
-        Snd ->> SMTP: Send email
-        SMTP -->> Snd: Success/Failure
-        Snd -->> Pipe: success: boolean
-        Pipe ->> Log: Log email result
-    else Assembly failed / No data
-        Pipe ->> Log: Log skipping email
-    end
-    Pipe ->> Log: Log finished
-```
-
-## Infrastructure and Deployment Overview
-
-- **Cloud Provider(s):** N/A. Executes locally on the user's machine.
-- **Core Services Used:** N/A (relies on external Algolia API, local Ollama, target websites, SMTP provider).
-- **Infrastructure as Code (IaC):** N/A.
-- **Deployment Strategy:** Manual execution via CLI (`npm run dev` or `npm run start` after `npm run build`). No CI/CD pipeline required for MVP.
-- **Environments:** Single environment: local development machine.
-
-## Key Reference Documents
-
-- `docs/prd.md`
-- `docs/epic1.md` ... `docs/epic5.md`
-- `docs/tech-stack.md`
-- `docs/project-structure.md`
-- `docs/data-models.md`
-- `docs/api-reference.md`
-- `docs/environment-vars.md`
-- `docs/coding-standards.md`
-- `docs/testing-strategy.md`
-- `docs/prompts.md`
-
-## Change Log
-
-| Change        | Date       | Version | Description                | Author      |
-| ------------- | ---------- | ------- | -------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Initial draft based on PRD | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/botched-architecture-draft.md

@@ -1,226 +0,0 @@
-# BMad Hacker Daily Digest Architecture Document
-
-## Technical Summary
-
-This document outlines the technical architecture for the BMad Hacker Daily Digest, a command-line tool built with TypeScript and Node.js v22. It adheres to the structure provided by the "bmad-boilerplate". The system fetches the top 10 Hacker News stories and their comments daily via the Algolia HN API, attempts to scrape linked articles, generates summaries for both articles (if scraped) and discussions using a local Ollama instance, persists intermediate data locally, and sends an HTML digest email via Nodemailer upon manual CLI execution. The architecture emphasizes modularity through distinct clients and processing stages, facilitating independent stage testing as required by the PRD. Execution is strictly local for the MVP.
-
-## High-Level Overview
-
-The application follows a sequential pipeline architecture triggered by a single CLI command (`npm run dev` or `npm start`). Data flows through distinct stages: HN Data Acquisition, Article Scraping, LLM Summarization, and Digest Assembly/Email Dispatch. Each stage persists its output to a date-stamped local directory, allowing subsequent stages to operate on this data and enabling stage-specific testing utilities.
-
-**(Diagram Suggestion for Canvas: Create a flowchart showing the stages below)**
-
-```mermaid
-graph TD
-    A[CLI Trigger (npm run dev/start)] --> B(Initialize: Load Config, Setup Logger, Create Output Dir);
-    B --> C{Fetch HN Data (Top 10 Stories + Comments)};
-    C -- Story/Comment Data --> D(Persist HN Data: ./output/YYYY-MM-DD/{storyId}_data.json);
-    D --> E{Attempt Article Scraping (per story)};
-    E -- Scraped Text (if successful) --> F(Persist Article Text: ./output/YYYY-MM-DD/{storyId}_article.txt);
-    F --> G{Generate Summaries (Article + Discussion via Ollama)};
-    G -- Summaries --> H(Persist Summaries: ./output/YYYY-MM-DD/{storyId}_summary.json);
-    H --> I{Assemble Digest (Read persisted data)};
-    I -- HTML Content --> J{Send Email via Nodemailer};
-    J --> K(Log Final Status & Exit);
-
-    subgraph Stage Testing Utilities
-        direction LR
-        T1[npm run stage:fetch] --> D;
-        T2[npm run stage:scrape] --> F;
-        T3[npm run stage:summarize] --> H;
-        T4[npm run stage:email] --> J;
-    end
-
-    C --> |Error/Skip| G;  // If no comments
-    E --> |Skip/Fail| G;  // If no URL or scrape fails
-    G --> |Summarization Fail| H; // Persist null summaries
-    I --> |Assembly Fail| K; // Skip email if assembly fails
-```
-
-## Component View
-
-The application logic resides primarily within the `src/` directory, organized into modules responsible for specific pipeline stages or cross-cutting concerns.
-
-**(Diagram Suggestion for Canvas: Create a component diagram showing modules and dependencies)**
-
-```mermaid
-graph TD
-    subgraph src ["Source Code (src/)"]
-        direction LR
-        Entry["index.ts (Main Orchestrator)"]
-
-        subgraph Config ["Configuration"]
-            ConfMod["config.ts"]
-            EnvFile[".env File"]
-        end
-
-        subgraph Utils ["Utilities"]
-            Logger["logger.ts"]
-        end
-
-        subgraph Clients ["External Service Clients"]
-            Algolia["clients/algoliaHNClient.ts"]
-            Ollama["clients/ollamaClient.ts"]
-        end
-
-        Scraper["scraper/articleScraper.ts"]
-
-        subgraph Email ["Email Handling"]
-            Assembler["email/contentAssembler.ts"]
-            Templater["email/templater.ts (or within Assembler)"]
-            Sender["email/emailSender.ts"]
-            Nodemailer["(nodemailer library)"]
-        end
-
-        subgraph Stages ["Stage Testing Scripts (src/stages/)"]
-             FetchStage["fetch_hn_data.ts"]
-             ScrapeStage["scrape_articles.ts"]
-             SummarizeStage["summarize_content.ts"]
-             SendStage["send_digest.ts"]
-        end
-
-        Entry --> ConfMod;
-        Entry --> Logger;
-        Entry --> Algolia;
-        Entry --> Scraper;
-        Entry --> Ollama;
-        Entry --> Assembler;
-        Entry --> Templater;
-        Entry --> Sender;
-
-        Algolia -- uses --> NativeFetch["Node.js v22 Native Workspace"];
-        Ollama -- uses --> NativeFetch;
-        Scraper -- uses --> NativeFetch;
-        Scraper -- uses --> ArticleExtractor["(@extractus/article-extractor)"];
-        Sender -- uses --> Nodemailer;
-        ConfMod -- reads --> EnvFile;
-
-        Assembler -- reads --> LocalFS["Local Filesystem (./output)"];
-        Entry -- writes --> LocalFS;
-
-        FetchStage --> Algolia;
-        FetchStage --> LocalFS;
-        ScrapeStage --> Scraper;
-        ScrapeStage --> LocalFS;
-        SummarizeStage --> Ollama;
-        SummarizeStage --> LocalFS;
-        SendStage --> Assembler;
-        SendStage --> Templater;
-        SendStage --> Sender;
-        SendStage --> LocalFS;
-    end
-
-    CLI["CLI (npm run ...)"] --> Entry;
-    CLI -- runs --> FetchStage;
-    CLI -- runs --> ScrapeStage;
-    CLI -- runs --> SummarizeStage;
-    CLI -- runs --> SendStage;
-
-```
-
-_Module Descriptions:_
-
-- **`src/index.ts`**: The main entry point, orchestrating the entire pipeline flow from initialization to final email dispatch. Imports and calls functions from other modules.
-- **`src/config.ts`**: Responsible for loading and validating environment variables from the `.env` file using the `dotenv` library.
-- **`src/logger.ts`**: Provides a simple console logging utility used throughout the application.
-- **`src/clients/algoliaHNClient.ts`**: Encapsulates interaction with the Algolia Hacker News Search API using the native `Workspace` API for fetching stories and comments.
-- **`src/clients/ollamaClient.ts`**: Encapsulates interaction with the local Ollama API endpoint using the native `Workspace` API for generating summaries.
-- **`src/scraper/articleScraper.ts`**: Handles fetching article HTML using native `Workspace` and extracting text content using `@extractus/article-extractor`. Includes robust error handling for fetch and extraction failures.
-- **`src/email/contentAssembler.ts`**: Reads persisted story data and summaries from the local output directory.
-- **`src/email/templater.ts` (or integrated)**: Renders the HTML email content using the assembled data.
-- **`src/email/emailSender.ts`**: Configures and uses Nodemailer to send the generated HTML email.
-- **`src/stages/*.ts`**: Individual scripts designed to run specific pipeline stages independently for testing, using persisted data from previous stages as input where applicable.
-
-## Key Architectural Decisions & Patterns
-
-- **Pipeline Architecture:** A sequential flow where each stage processes data and passes artifacts to the next via the local filesystem. Chosen for simplicity and to easily support independent stage testing.
-- **Local Execution & File Persistence:** All execution is local, and intermediate artifacts (`_data.json`, `_article.txt`, `_summary.json`) are stored in a date-stamped `./output` directory. This avoids database setup for MVP and facilitates debugging/stage testing.
-- **Native `Workspace` API:** Mandated by constraints for all HTTP requests (Algolia, Ollama, Article Scraping). Ensures usage of the latest Node.js features.
-- **Modular Clients:** External interactions (Algolia, Ollama) are encapsulated in dedicated client modules (`src/clients/`). This promotes separation of concerns and makes swapping implementations (e.g., different LLM API) easier.
-- **Configuration via `.env`:** Standard approach using `dotenv` for managing API keys, endpoints, and behavioral parameters (as per boilerplate).
-- **Stage Testing Utilities:** Dedicated scripts (`src/stages/*.ts`) allow isolated testing of fetching, scraping, summarization, and emailing, fulfilling a key PRD requirement.
-- **Graceful Error Handling (Scraping):** Article scraping failures are logged but do not halt the main pipeline, allowing the process to continue with discussion summaries only, as required. Other errors (API, LLM) are logged.
-
-## Core Workflow / Sequence Diagrams (Simplified)
-
-**(Diagram Suggestion for Canvas: Create a Sequence Diagram showing interactions)**
-
-```mermaid
-sequenceDiagram
-    participant CLI
-    participant Index as index.ts
-    participant Config as config.ts
-    participant Logger as logger.ts
-    participant OutputDir as Output Dir Setup
-    participant Algolia as algoliaHNClient.ts
-    participant Scraper as articleScraper.ts
-    participant Ollama as ollamaClient.ts
-    participant Assembler as contentAssembler.ts
-    participant Templater as templater.ts
-    participant Sender as emailSender.ts
-    participant FS as Local Filesystem (./output/YYYY-MM-DD)
-
-    CLI->>Index: npm run dev
-    Index->>Config: Load .env vars
-    Index->>Logger: Initialize
-    Index->>OutputDir: Create/Verify Date Dir
-    Index->>Algolia: fetchTopStories()
-    Algolia-->>Index: stories[]
-    loop For Each Story
-        Index->>Algolia: fetchCommentsForStory(storyId, MAX_COMMENTS)
-        Algolia-->>Index: comments[]
-        Index->>FS: Write {storyId}_data.json
-        alt Has Valid story.url
-            Index->>Scraper: scrapeArticle(story.url)
-            Scraper-->>Index: articleContent (string | null)
-            alt Scrape Success
-                Index->>FS: Write {storyId}_article.txt
-            end
-        end
-        alt Has articleContent
-             Index->>Ollama: generateSummary(ARTICLE_PROMPT, articleContent)
-             Ollama-->>Index: articleSummary (string | null)
-        end
-        alt Has comments[]
-             Index->>Ollama: generateSummary(DISCUSSION_PROMPT, formattedComments)
-             Ollama-->>Index: discussionSummary (string | null)
-        end
-        Index->>FS: Write {storyId}_summary.json
-    end
-    Index->>Assembler: assembleDigestData(dateDirPath)
-    Assembler->>FS: Read _data.json, _summary.json files
-    Assembler-->>Index: digestData[]
-    alt digestData is not empty
-        Index->>Templater: renderDigestHtml(digestData, date)
-        Templater-->>Index: htmlContent
-        Index->>Sender: sendDigestEmail(subject, htmlContent)
-        Sender-->>Index: success (boolean)
-    end
-    Index->>Logger: Log final status
-```
-
-## Infrastructure and Deployment Overview
-
-- **Cloud Provider(s):** N/A (Local Machine Execution Only for MVP)
-- **Core Services Used:** N/A
-- **Infrastructure as Code (IaC):** N/A
-- **Deployment Strategy:** Manual CLI execution (`npm run dev` for development with `ts-node`, `npm run build && npm start` for running compiled JS). No automated deployment pipeline for MVP.
-- **Environments:** Single: Local development machine.
-
-## Key Reference Documents
-
-- docs/prd.md
-- docs/epic1-draft.txt, docs/epic2-draft.txt, ... docs/epic5-draft.txt
-- docs/tech-stack.md
-- docs/project-structure.md
-- docs/coding-standards.md
-- docs/api-reference.md
-- docs/data-models.md
-- docs/environment-vars.md
-- docs/testing-strategy.md
-
-## Change Log
-
-| Change        | Date       | Version | Description                        | Author      |
-| ------------- | ---------- | ------- | ---------------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Initial draft based on PRD & Epics | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/coding-standards.md

@@ -1,80 +0,0 @@
-# BMad Hacker Daily Digest Coding Standards and Patterns
-
-This document outlines the coding standards, design patterns, and best practices to be followed during the development of the BMad Hacker Daily Digest project. Adherence to these standards is crucial for maintainability, readability, and collaboration.
-
-## Architectural / Design Patterns Adopted
-
-- **Sequential Pipeline:** The core application follows a linear sequence of steps (fetch, scrape, summarize, email) orchestrated within `src/core/pipeline.ts`.
-- **Modular Design:** The application is broken down into distinct modules based on responsibility (e.g., `clients/`, `scraper/`, `email/`, `utils/`) to promote separation of concerns, testability, and maintainability. See `docs/project-structure.md`.
-- **Client Abstraction:** External service interactions (Algolia, Ollama) are encapsulated within dedicated client modules in `src/clients/`.
-- **Filesystem Persistence:** Intermediate data is persisted to the local filesystem instead of a database, acting as a handoff between pipeline stages.
-
-## Coding Standards
-
-- **Primary Language:** TypeScript (v5.x, as configured in boilerplate)
-- **Primary Runtime:** Node.js (v22.x, as required by PRD )
-- **Style Guide & Linter:** ESLint and Prettier. Configuration is provided by the `bmad-boilerplate`.
-  - **Mandatory:** Run `npm run lint` and `npm run format` regularly and before committing code. Code must be free of lint errors.
-- **Naming Conventions:**
-  - Variables & Functions: `camelCase`
-  - Classes, Types, Interfaces: `PascalCase`
-  - Constants: `UPPER_SNAKE_CASE`
-  - Files: `kebab-case.ts` (e.g., `article-scraper.ts`) or `camelCase.ts` (e.g., `ollamaClient.ts`). Be consistent within module types (e.g., all clients follow one pattern, all utils another). Let's default to `camelCase.ts` for consistency with class/module names where applicable (e.g. `ollamaClient.ts`) and `kebab-case.ts` for more descriptive utils or stage runners (e.g. `Workspace-hn-data.ts`).
-  - Test Files: `*.test.ts` (e.g., `ollamaClient.test.ts`)
-- **File Structure:** Adhere strictly to the layout defined in `docs/project-structure.md`.
-- **Asynchronous Operations:** **Mandatory:** Use `async`/`await` for all asynchronous operations (e.g., native `Workspace` HTTP calls , `fs/promises` file operations, Ollama client calls, Nodemailer `sendMail`). Avoid using raw Promises `.then()`/`.catch()` syntax where `async/await` provides better readability.
-- **Type Safety:** Leverage TypeScript's static typing. Use interfaces and types defined in `src/types/` where appropriate. Assume `strict` mode is enabled in `tsconfig.json` (from boilerplate). Avoid using `any` unless absolutely necessary and justified.
-- **Comments & Documentation:**
-  - Use JSDoc comments for exported functions, classes, and complex logic.
-  - Keep comments concise and focused on the _why_, not the _what_, unless the code is particularly complex.
-  - Update READMEs as needed for setup or usage changes.
-- **Dependency Management:**
-  - Use `npm` for package management.
-  - Keep production dependencies minimal, as required by the PRD . Justify any additions.
-  - Use `devDependencies` for testing, linting, and build tools.
-
-## Error Handling Strategy
-
-- **General Approach:** Use standard JavaScript `try...catch` blocks for operations that can fail (I/O, network requests, parsing, etc.). Throw specific `Error` objects with descriptive messages. Avoid catching errors without logging or re-throwing unless intentionally handling a specific case.
-- **Logging:**
-  - **Mandatory:** Use the central logger utility (`src/utils/logger.ts`) for all console output (INFO, WARN, ERROR). Do not use `console.log` directly in application logic.
-  - **Format:** Basic text format for MVP. Structured JSON logging to files is a post-MVP enhancement.
-  - **Levels:** Use appropriate levels (`logger.info`, `logger.warn`, `logger.error`).
-  - **Context:** Include relevant context in log messages (e.g., Story ID, function name, URL being processed) to aid debugging.
-- **Specific Handling Patterns:**
-  - **External API Calls (Algolia, Ollama via `Workspace`):**
-    - Wrap `Workspace` calls in `try...catch`.
-    - Check `response.ok` status; if false, log the status code and potentially response body text, then treat as an error (e.g., return `null` or throw).
-    - Log network errors caught by the `catch` block.
-    - No automated retries required for MVP.
-  - **Article Scraping (`articleScraper.ts`):**
-    - Wrap `Workspace` and text extraction (`article-extractor`) logic in `try...catch`.
-    - Handle non-2xx responses, timeouts, non-HTML content types, and extraction errors.
-    - **Crucial:** If scraping fails for any reason, log the error/reason using `logger.warn` or `logger.error`, return `null`, and **allow the main pipeline to continue processing the story** (using only comment summary). Do not throw an error that halts the entire application.
-  - **File I/O (`fs` module):**
-    - Wrap `fs` operations (especially writes) in `try...catch`. Log any file system errors using `logger.error`.
-  - **Email Sending (`Nodemailer`):**
-    - Wrap `transporter.sendMail()` in `try...catch`. Log success (including message ID) or failure clearly using the logger.
-  - **Configuration Loading (`config.ts`):**
-    - Check for the presence of all required environment variables at startup. Throw a fatal error and exit if required variables are missing.
-    - **LLM Interaction (Ollama Client):**
-      - **LLM Prompts:** Use the standardized prompts defined in `docs/prompts.md` when interacting with the Ollama client for consistency.
-      - Wrap `generateSummary` calls in `try...catch`. Log errors from the client (which handles API/network issues).
-      - **Comment Truncation:** Before sending comments for discussion summary, check for the `MAX_COMMENT_CHARS_FOR_SUMMARY` env var. If set to a positive number, truncate the combined comment text block to this length. Log a warning if truncation occurs. If not set, send the full text.
-
-## Security Best Practices
-
-- **Input Sanitization/Validation:** While primarily a local tool, validate critical inputs like external URLs (`story.articleUrl`) before attempting to fetch them. Basic checks (e.g., starts with `http://` or `https://`) are sufficient for MVP .
-- **Secrets Management:**
-  - **Mandatory:** Store sensitive data (`EMAIL_USER`, `EMAIL_PASS`) only in the `.env` file.
-  - **Mandatory:** Ensure the `.env` file is included in `.gitignore` and is never committed to version control.
-  - Do not hardcode secrets anywhere in the source code.
-- **Dependency Security:** Periodically run `npm audit` to check for known vulnerabilities in dependencies. Consider enabling Dependabot if using GitHub.
-- **HTTP Client:** Use the native `Workspace` API as required ; avoid introducing less secure or overly complex HTTP client libraries.
-- **Scraping User-Agent:** Set a default User-Agent header in the scraper code (e.g., "BMadHackerDigest/0.1"). Allow overriding this default via the optional SCRAPER_USER_AGENT environment variable. 
-
-## Change Log
-
-| Change        | Date       | Version | Description                 | Author      |
-| ------------- | ---------- | ------- | --------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Initial draft based on Arch | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/coding-standards.txt

@@ -1,80 +0,0 @@
-# BMad Hacker Daily Digest Coding Standards and Patterns
-
-This document outlines the coding standards, design patterns, and best practices to be followed during the development of the BMad Hacker Daily Digest project. Adherence to these standards is crucial for maintainability, readability, and collaboration.
-
-## Architectural / Design Patterns Adopted
-
-- **Sequential Pipeline:** The core application follows a linear sequence of steps (fetch, scrape, summarize, email) orchestrated within `src/core/pipeline.ts`.
-- **Modular Design:** The application is broken down into distinct modules based on responsibility (e.g., `clients/`, `scraper/`, `email/`, `utils/`) to promote separation of concerns, testability, and maintainability. See `docs/project-structure.md`.
-- **Client Abstraction:** External service interactions (Algolia, Ollama) are encapsulated within dedicated client modules in `src/clients/`.
-- **Filesystem Persistence:** Intermediate data is persisted to the local filesystem instead of a database, acting as a handoff between pipeline stages.
-
-## Coding Standards
-
-- **Primary Language:** TypeScript (v5.x, as configured in boilerplate)
-- **Primary Runtime:** Node.js (v22.x, as required by PRD )
-- **Style Guide & Linter:** ESLint and Prettier. Configuration is provided by the `bmad-boilerplate`.
-  - **Mandatory:** Run `npm run lint` and `npm run format` regularly and before committing code. Code must be free of lint errors.
-- **Naming Conventions:**
-  - Variables & Functions: `camelCase`
-  - Classes, Types, Interfaces: `PascalCase`
-  - Constants: `UPPER_SNAKE_CASE`
-  - Files: `kebab-case.ts` (e.g., `article-scraper.ts`) or `camelCase.ts` (e.g., `ollamaClient.ts`). Be consistent within module types (e.g., all clients follow one pattern, all utils another). Let's default to `camelCase.ts` for consistency with class/module names where applicable (e.g. `ollamaClient.ts`) and `kebab-case.ts` for more descriptive utils or stage runners (e.g. `Workspace-hn-data.ts`).
-  - Test Files: `*.test.ts` (e.g., `ollamaClient.test.ts`)
-- **File Structure:** Adhere strictly to the layout defined in `docs/project-structure.md`.
-- **Asynchronous Operations:** **Mandatory:** Use `async`/`await` for all asynchronous operations (e.g., native `Workspace` HTTP calls , `fs/promises` file operations, Ollama client calls, Nodemailer `sendMail`). Avoid using raw Promises `.then()`/`.catch()` syntax where `async/await` provides better readability.
-- **Type Safety:** Leverage TypeScript's static typing. Use interfaces and types defined in `src/types/` where appropriate. Assume `strict` mode is enabled in `tsconfig.json` (from boilerplate). Avoid using `any` unless absolutely necessary and justified.
-- **Comments & Documentation:**
-  - Use JSDoc comments for exported functions, classes, and complex logic.
-  - Keep comments concise and focused on the _why_, not the _what_, unless the code is particularly complex.
-  - Update READMEs as needed for setup or usage changes.
-- **Dependency Management:**
-  - Use `npm` for package management.
-  - Keep production dependencies minimal, as required by the PRD . Justify any additions.
-  - Use `devDependencies` for testing, linting, and build tools.
-
-## Error Handling Strategy
-
-- **General Approach:** Use standard JavaScript `try...catch` blocks for operations that can fail (I/O, network requests, parsing, etc.). Throw specific `Error` objects with descriptive messages. Avoid catching errors without logging or re-throwing unless intentionally handling a specific case.
-- **Logging:**
-  - **Mandatory:** Use the central logger utility (`src/utils/logger.ts`) for all console output (INFO, WARN, ERROR). Do not use `console.log` directly in application logic.
-  - **Format:** Basic text format for MVP. Structured JSON logging to files is a post-MVP enhancement.
-  - **Levels:** Use appropriate levels (`logger.info`, `logger.warn`, `logger.error`).
-  - **Context:** Include relevant context in log messages (e.g., Story ID, function name, URL being processed) to aid debugging.
-- **Specific Handling Patterns:**
-  - **External API Calls (Algolia, Ollama via `Workspace`):**
-    - Wrap `Workspace` calls in `try...catch`.
-    - Check `response.ok` status; if false, log the status code and potentially response body text, then treat as an error (e.g., return `null` or throw).
-    - Log network errors caught by the `catch` block.
-    - No automated retries required for MVP.
-  - **Article Scraping (`articleScraper.ts`):**
-    - Wrap `Workspace` and text extraction (`article-extractor`) logic in `try...catch`.
-    - Handle non-2xx responses, timeouts, non-HTML content types, and extraction errors.
-    - **Crucial:** If scraping fails for any reason, log the error/reason using `logger.warn` or `logger.error`, return `null`, and **allow the main pipeline to continue processing the story** (using only comment summary). Do not throw an error that halts the entire application.
-  - **File I/O (`fs` module):**
-    - Wrap `fs` operations (especially writes) in `try...catch`. Log any file system errors using `logger.error`.
-  - **Email Sending (`Nodemailer`):**
-    - Wrap `transporter.sendMail()` in `try...catch`. Log success (including message ID) or failure clearly using the logger.
-  - **Configuration Loading (`config.ts`):**
-    - Check for the presence of all required environment variables at startup. Throw a fatal error and exit if required variables are missing.
-    - **LLM Interaction (Ollama Client):**
-      - **LLM Prompts:** Use the standardized prompts defined in `docs/prompts.md` when interacting with the Ollama client for consistency.
-      - Wrap `generateSummary` calls in `try...catch`. Log errors from the client (which handles API/network issues).
-      - **Comment Truncation:** Before sending comments for discussion summary, check for the `MAX_COMMENT_CHARS_FOR_SUMMARY` env var. If set to a positive number, truncate the combined comment text block to this length. Log a warning if truncation occurs. If not set, send the full text.
-
-## Security Best Practices
-
-- **Input Sanitization/Validation:** While primarily a local tool, validate critical inputs like external URLs (`story.articleUrl`) before attempting to fetch them. Basic checks (e.g., starts with `http://` or `https://`) are sufficient for MVP .
-- **Secrets Management:**
-  - **Mandatory:** Store sensitive data (`EMAIL_USER`, `EMAIL_PASS`) only in the `.env` file.
-  - **Mandatory:** Ensure the `.env` file is included in `.gitignore` and is never committed to version control.
-  - Do not hardcode secrets anywhere in the source code.
-- **Dependency Security:** Periodically run `npm audit` to check for known vulnerabilities in dependencies. Consider enabling Dependabot if using GitHub.
-- **HTTP Client:** Use the native `Workspace` API as required ; avoid introducing less secure or overly complex HTTP client libraries.
-- **Scraping User-Agent:** Set a default User-Agent header in the scraper code (e.g., "BMadHackerDigest/0.1"). Allow overriding this default via the optional SCRAPER_USER_AGENT environment variable. 
-
-## Change Log
-
-| Change        | Date       | Version | Description                 | Author      |
-| ------------- | ---------- | ------- | --------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Initial draft based on Arch | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/combined-artifacts-for-posm.md

@@ -1,614 +0,0 @@
-# Epic 1 file
-
-# Epic 1: Project Initialization & Core Setup
-
-**Goal:** Initialize the project using the "bmad-boilerplate", manage dependencies, setup `.env` and config loading, establish basic CLI entry point, setup basic logging and output directory structure. This provides the foundational setup for all subsequent development work.
-
-## Story List
-
-### Story 1.1: Initialize Project from Boilerplate
-
--   **User Story / Goal:** As a developer, I want to set up the initial project structure using the `bmad-boilerplate`, so that I have the standard tooling (TS, Jest, ESLint, Prettier), configurations, and scripts in place.
--   **Detailed Requirements:**
-    -   Copy or clone the contents of the `bmad-boilerplate` into the new project's root directory.
-    -   Initialize a git repository in the project root directory (if not already done by cloning).
-    -   Ensure the `.gitignore` file from the boilerplate is present.
-    -   Run `npm install` to download and install all `devDependencies` specified in the boilerplate's `package.json`.
-    -   Verify that the core boilerplate scripts (`lint`, `format`, `test`, `build`) execute without errors on the initial codebase.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The project directory contains the files and structure from `bmad-boilerplate`.
-    -   AC2: A `node_modules` directory exists and contains packages corresponding to `devDependencies`.
-    -   AC3: `npm run lint` command completes successfully without reporting any linting errors.
-    -   AC4: `npm run format` command completes successfully, potentially making formatting changes according to Prettier rules. Running it a second time should result in no changes.
-    -   AC5: `npm run test` command executes Jest successfully (it may report "no tests found" which is acceptable at this stage).
-    -   AC6: `npm run build` command executes successfully, creating a `dist` directory containing compiled JavaScript output.
-    -   AC7: The `.gitignore` file exists and includes entries for `node_modules/`, `.env`, `dist/`, etc. as specified in the boilerplate.
-
----
-
-### Story 1.2: Setup Environment Configuration
-
--   **User Story / Goal:** As a developer, I want to establish the environment configuration mechanism using `.env` files, so that secrets and settings (like output paths) can be managed outside of version control, following boilerplate conventions.
--   **Detailed Requirements:**
-    -   Add a production dependency for loading `.env` files (e.g., `dotenv`). Run `npm install dotenv --save-prod` (or similar library).
-    -   Verify the `.env.example` file exists (from boilerplate).
-    -   Add an initial configuration variable `OUTPUT_DIR_PATH=./output` to `.env.example`.
-    -   Create the `.env` file locally by copying `.env.example`. Populate `OUTPUT_DIR_PATH` if needed (can keep default).
-    -   Implement a utility module (e.g., `src/config.ts`) that loads environment variables from the `.env` file at application startup.
-    -   The utility should export the loaded configuration values (initially just `OUTPUT_DIR_PATH`).
-    -   Ensure the `.env` file is listed in `.gitignore` and is not committed.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The chosen `.env` library (e.g., `dotenv`) is listed under `dependencies` in `package.json` and `package-lock.json` is updated.
-    -   AC2: The `.env.example` file exists, is tracked by git, and contains the line `OUTPUT_DIR_PATH=./output`.
-    -   AC3: The `.env` file exists locally but is NOT tracked by git.
-    -   AC4: A configuration module (`src/config.ts` or similar) exists and successfully loads the `OUTPUT_DIR_PATH` value from `.env` when the application starts.
-    -   AC5: The loaded `OUTPUT_DIR_PATH` value is accessible within the application code.
-
----
-
-### Story 1.3: Implement Basic CLI Entry Point & Execution
-
--   **User Story / Goal:** As a developer, I want a basic `src/index.ts` entry point that can be executed via the boilerplate's `dev` and `start` scripts, providing a working foundation for the application logic.
--   **Detailed Requirements:**
-    -   Create the main application entry point file at `src/index.ts`.
-    -   Implement minimal code within `src/index.ts` to:
-        -   Import the configuration loading mechanism (from Story 1.2).
-        -   Log a simple startup message to the console (e.g., "BMad Hacker Daily Digest - Starting Up...").
-        -   (Optional) Log the loaded `OUTPUT_DIR_PATH` to verify config loading.
-    -   Confirm execution using boilerplate scripts.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `src/index.ts` file exists.
-    -   AC2: Running `npm run dev` executes `src/index.ts` via `ts-node` and logs the startup message to the console.
-    -   AC3: Running `npm run build` successfully compiles `src/index.ts` (and any imports) into the `dist` directory.
-    -   AC4: Running `npm start` (after a successful build) executes the compiled code from `dist` and logs the startup message to the console.
-
----
-
-### Story 1.4: Setup Basic Logging and Output Directory
-
--   **User Story / Goal:** As a developer, I want a basic console logging mechanism and the dynamic creation of a date-stamped output directory, so that the application can provide execution feedback and prepare for storing data artifacts in subsequent epics.
--   **Detailed Requirements:**
-    -   Implement a simple, reusable logging utility module (e.g., `src/logger.ts`). Initially, it can wrap `console.log`, `console.warn`, `console.error`.
-    -   Refactor `src/index.ts` to use this `logger` for its startup message(s).
-    -   In `src/index.ts` (or a setup function called by it):
-        -   Retrieve the `OUTPUT_DIR_PATH` from the configuration (loaded in Story 1.2).
-        -   Determine the current date in 'YYYY-MM-DD' format.
-        -   Construct the full path for the date-stamped subdirectory (e.g., `${OUTPUT_DIR_PATH}/YYYY-MM-DD`).
-        -   Check if the base output directory exists; if not, create it.
-        -   Check if the date-stamped subdirectory exists; if not, create it recursively. Use Node.js `fs` module (e.g., `fs.mkdirSync(path, { recursive: true })`).
-        -   Log (using the logger) the full path of the output directory being used for the current run (e.g., "Output directory for this run: ./output/2025-05-04").
--   **Acceptance Criteria (ACs):**
-    -   AC1: A logger utility module (`src/logger.ts` or similar) exists and is used for console output in `src/index.ts`.
-    -   AC2: Running `npm run dev` or `npm start` logs the startup message via the logger.
-    -   AC3: Running the application creates the base output directory (e.g., `./output` defined in `.env`) if it doesn't already exist.
-    -   AC4: Running the application creates a date-stamped subdirectory (e.g., `./output/2025-05-04`) within the base output directory if it doesn't already exist.
-    -   AC5: The application logs a message indicating the full path to the date-stamped output directory created/used for the current execution.
-    -   AC6: The application exits gracefully after performing these setup steps (for now).
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 1     | 2-pm           |
-
-# Epic 2 File
-
-# Epic 2: HN Data Acquisition & Persistence
-
-**Goal:** Implement fetching top 10 stories and their comments (respecting limits) from Algolia HN API, and persist this raw data locally into the date-stamped output directory created in Epic 1. Implement a stage testing utility for fetching.
-
-## Story List
-
-### Story 2.1: Implement Algolia HN API Client
-
--   **User Story / Goal:** As a developer, I want a dedicated client module to interact with the Algolia Hacker News Search API, so that fetching stories and comments is encapsulated, reusable, and uses the required native `Workspace` API.
--   **Detailed Requirements:**
-    -   Create a new module: `src/clients/algoliaHNClient.ts`.
-    -   Implement an async function `WorkspaceTopStories` within the client:
-        -   Use native `Workspace` to call the Algolia HN Search API endpoint for front-page stories (e.g., `http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10`). Adjust `hitsPerPage` if needed to ensure 10 stories.
-        -   Parse the JSON response.
-        -   Extract required metadata for each story: `objectID` (use as `storyId`), `title`, `url` (article URL), `points`, `num_comments`. Handle potential missing `url` field gracefully (log warning, maybe skip story later if URL needed).
-        -   Construct the `hnUrl` for each story (e.g., `https://news.ycombinator.com/item?id={storyId}`).
-        -   Return an array of structured story objects.
-    -   Implement a separate async function `WorkspaceCommentsForStory` within the client:
-        -   Accept `storyId` and `maxComments` limit as arguments.
-        -   Use native `Workspace` to call the Algolia HN Search API endpoint for comments of a specific story (e.g., `http://hn.algolia.com/api/v1/search?tags=comment,story_{storyId}&hitsPerPage={maxComments}`).
-        -   Parse the JSON response.
-        -   Extract required comment data: `objectID` (use as `commentId`), `comment_text`, `author`, `created_at`.
-        -   Filter out comments where `comment_text` is null or empty. Ensure only up to `maxComments` are returned.
-        -   Return an array of structured comment objects.
-    -   Implement basic error handling using `try...catch` around `Workspace` calls and check `response.ok` status. Log errors using the logger utility from Epic 1.
-    -   Define TypeScript interfaces/types for the expected structures of API responses (stories, comments) and the data returned by the client functions (e.g., `Story`, `Comment`).
--   **Acceptance Criteria (ACs):**
-    -   AC1: The module `src/clients/algoliaHNClient.ts` exists and exports `WorkspaceTopStories` and `WorkspaceCommentsForStory` functions.
-    -   AC2: Calling `WorkspaceTopStories` makes a network request to the correct Algolia endpoint and returns a promise resolving to an array of 10 `Story` objects containing the specified metadata.
-    -   AC3: Calling `WorkspaceCommentsForStory` with a valid `storyId` and `maxComments` limit makes a network request to the correct Algolia endpoint and returns a promise resolving to an array of `Comment` objects (up to `maxComments`), filtering out empty ones.
-    -   AC4: Both functions use the native `Workspace` API internally.
-    -   AC5: Network errors or non-successful API responses (e.g., status 4xx, 5xx) are caught and logged using the logger.
-    -   AC6: Relevant TypeScript types (`Story`, `Comment`, etc.) are defined and used within the client module.
-
----
-
-### Story 2.2: Integrate HN Data Fetching into Main Workflow
-
--   **User Story / Goal:** As a developer, I want to integrate the HN data fetching logic into the main application workflow (`src/index.ts`), so that running the app retrieves the top 10 stories and their comments after completing the setup from Epic 1.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts` (or a main async function called by it).
-    -   Import the `algoliaHNClient` functions.
-    -   Import the configuration module to access `MAX_COMMENTS_PER_STORY`.
-    -   After the Epic 1 setup (config load, logger init, output dir creation), call `WorkspaceTopStories()`.
-    -   Log the number of stories fetched.
-    -   Iterate through the array of fetched `Story` objects.
-    -   For each `Story`, call `WorkspaceCommentsForStory()`, passing the `story.storyId` and the configured `MAX_COMMENTS_PER_STORY`.
-    -   Store the fetched comments within the corresponding `Story` object in memory (e.g., add a `comments: Comment[]` property to the `Story` object).
-    -   Log progress using the logger utility (e.g., "Fetched 10 stories.", "Fetching up to X comments for story {storyId}...").
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes Epic 1 setup steps followed by fetching stories and then comments for each story.
-    -   AC2: Logs clearly show the start and successful completion of fetching stories, and the start of fetching comments for each of the 10 stories.
-    -   AC3: The configured `MAX_COMMENTS_PER_STORY` value is read from config and used in the calls to `WorkspaceCommentsForStory`.
-    -   AC4: After successful execution, story objects held in memory contain a nested array of fetched comment objects. (Can be verified via debugger or temporary logging).
-
----
-
-### Story 2.3: Persist Fetched HN Data Locally
-
--   **User Story / Goal:** As a developer, I want to save the fetched HN stories (including their comments) to JSON files in the date-stamped output directory, so that the raw data is persisted locally for subsequent pipeline stages and debugging.
--   **Detailed Requirements:**
-    -   Define a consistent JSON structure for the output file content. Example: `{ storyId: "...", title: "...", url: "...", hnUrl: "...", points: ..., fetchedAt: "ISO_TIMESTAMP", comments: [{ commentId: "...", text: "...", author: "...", createdAt: "ISO_TIMESTAMP", ... }, ...] }`. Include a timestamp for when the data was fetched.
-    -   Import Node.js `fs` (specifically `fs.writeFileSync`) and `path` modules.
-    -   In the main workflow (`src/index.ts`), within the loop iterating through stories (after comments have been fetched and added to the story object in Story 2.2):
-        -   Get the full path to the date-stamped output directory (determined in Epic 1).
-        -   Construct the filename for the story's data: `{storyId}_data.json`.
-        -   Construct the full file path using `path.join()`.
-        -   Serialize the complete story object (including comments and fetch timestamp) to a JSON string using `JSON.stringify(storyObject, null, 2)` for readability.
-        -   Write the JSON string to the file using `fs.writeFileSync()`. Use a `try...catch` block for error handling.
-    -   Log (using the logger) the successful persistence of each story's data file or any errors encountered during file writing.
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory (e.g., `./output/YYYY-MM-DD/`) contains exactly 10 files named `{storyId}_data.json`.
-    -   AC2: Each JSON file contains valid JSON representing a single story object, including its metadata, fetch timestamp, and an array of its fetched comments, matching the defined structure.
-    -   AC3: The number of comments in each file's `comments` array does not exceed `MAX_COMMENTS_PER_STORY`.
-    -   AC4: Logs indicate that saving data to a file was attempted for each story, reporting success or specific file writing errors.
-
----
-
-### Story 2.4: Implement Stage Testing Utility for HN Fetching
-
--   **User Story / Goal:** As a developer, I want a separate, executable script that *only* performs the HN data fetching and persistence, so I can test and trigger this stage independently of the full pipeline.
--   **Detailed Requirements:**
-    -   Create a new standalone script file: `src/stages/fetch_hn_data.ts`.
-    -   This script should perform the essential setup required for this stage: initialize logger, load configuration (`.env`), determine and create output directory (reuse or replicate logic from Epic 1 / `src/index.ts`).
-    -   The script should then execute the core logic of fetching stories via `algoliaHNClient.fetchTopStories`, fetching comments via `algoliaHNClient.fetchCommentsForStory` (using loaded config for limit), and persisting the results to JSON files using `fs.writeFileSync` (replicating logic from Story 2.3).
-    -   The script should log its progress using the logger utility.
-    -   Add a new script command to `package.json` under `"scripts"`: `"stage:fetch": "ts-node src/stages/fetch_hn_data.ts"`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/fetch_hn_data.ts` exists.
-    -   AC2: The script `stage:fetch` is defined in `package.json`'s `scripts` section.
-    -   AC3: Running `npm run stage:fetch` executes successfully, performing only the setup, fetch, and persist steps.
-    -   AC4: Running `npm run stage:fetch` creates the same 10 `{storyId}_data.json` files in the correct date-stamped output directory as running the main `npm run dev` command (at the current state of development).
-    -   AC5: Logs generated by `npm run stage:fetch` reflect only the fetching and persisting steps, not subsequent pipeline stages.
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 2     | 2-pm           |
-
-# Epic 3 File
-
-# Epic 3: Article Scraping & Persistence
-
-**Goal:** Implement a best-effort article scraping mechanism to fetch and extract plain text content from the external URLs associated with fetched HN stories. Handle failures gracefully and persist successfully scraped text locally. Implement a stage testing utility for scraping.
-
-## Story List
-
-### Story 3.1: Implement Basic Article Scraper Module
-
--   **User Story / Goal:** As a developer, I want a module that attempts to fetch HTML from a URL and extract the main article text using basic methods, handling common failures gracefully, so article content can be prepared for summarization.
--   **Detailed Requirements:**
-    -   Create a new module: `src/scraper/articleScraper.ts`.
-    -   Add a suitable HTML parsing/extraction library dependency (e.g., `@extractus/article-extractor` recommended for simplicity, or `cheerio` for more control). Run `npm install @extractus/article-extractor --save-prod` (or chosen alternative).
-    -   Implement an async function `scrapeArticle(url: string): Promise<string | null>` within the module.
-    -   Inside the function:
-        -   Use native `Workspace` to retrieve content from the `url`. Set a reasonable timeout (e.g., 10-15 seconds). Include a `User-Agent` header to mimic a browser.
-        -   Handle potential `Workspace` errors (network errors, timeouts) using `try...catch`.
-        -   Check the `response.ok` status. If not okay, log error and return `null`.
-        -   Check the `Content-Type` header of the response. If it doesn't indicate HTML (e.g., does not include `text/html`), log warning and return `null`.
-        -   If HTML is received, attempt to extract the main article text using the chosen library (`article-extractor` preferred).
-        -   Wrap the extraction logic in a `try...catch` to handle library-specific errors.
-        -   Return the extracted plain text string if successful. Ensure it's just text, not HTML markup.
-        -   Return `null` if extraction fails or results in empty content.
-    -   Log all significant events, errors, or reasons for returning null (e.g., "Scraping URL...", "Fetch failed:", "Non-HTML content type:", "Extraction failed:", "Successfully extracted text") using the logger utility.
-    -   Define TypeScript types/interfaces as needed.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `articleScraper.ts` module exists and exports the `scrapeArticle` function.
-    -   AC2: The chosen scraping library (e.g., `@extractus/article-extractor`) is added to `dependencies` in `package.json`.
-    -   AC3: `scrapeArticle` uses native `Workspace` with a timeout and User-Agent header.
-    -   AC4: `scrapeArticle` correctly handles fetch errors, non-OK responses, and non-HTML content types by logging and returning `null`.
-    -   AC5: `scrapeArticle` uses the chosen library to attempt text extraction from valid HTML content.
-    -   AC6: `scrapeArticle` returns the extracted plain text on success, and `null` on any failure (fetch, non-HTML, extraction error, empty result).
-    -   AC7: Relevant logs are produced for success, failure modes, and errors encountered during the process.
-
----
-
-### Story 3.2: Integrate Article Scraping into Main Workflow
-
--   **User Story / Goal:** As a developer, I want to integrate the article scraper into the main workflow (`src/index.ts`), attempting to scrape the article for each HN story that has a valid URL, after fetching its data.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts`.
-    -   Import the `scrapeArticle` function from `src/scraper/articleScraper.ts`.
-    -   Within the main loop iterating through the fetched stories (after comments are fetched in Epic 2):
-        -   Check if `story.url` exists and appears to be a valid HTTP/HTTPS URL. A simple check for starting with `http://` or `https://` is sufficient.
-        -   If the URL is missing or invalid, log a warning ("Skipping scraping for story {storyId}: Missing or invalid URL") and proceed to the next story's processing step.
-        -   If a valid URL exists, log ("Attempting to scrape article for story {storyId} from {story.url}").
-        -   Call `await scrapeArticle(story.url)`.
-        -   Store the result (the extracted text string or `null`) in memory, associated with the story object (e.g., add property `articleContent: string | null`).
-        -   Log the outcome clearly (e.g., "Successfully scraped article for story {storyId}", "Failed to scrape article for story {storyId}").
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes Epic 1 & 2 steps, and then attempts article scraping for stories with valid URLs.
-    -   AC2: Stories with missing or invalid URLs are skipped, and a corresponding log message is generated.
-    -   AC3: For stories with valid URLs, the `scrapeArticle` function is called.
-    -   AC4: Logs clearly indicate the start and success/failure outcome of the scraping attempt for each relevant story.
-    -   AC5: Story objects held in memory after this stage contain an `articleContent` property holding the scraped text (string) or `null` if scraping was skipped or failed.
-
----
-
-### Story 3.3: Persist Scraped Article Text Locally
-
--   **User Story / Goal:** As a developer, I want to save successfully scraped article text to a separate local file for each story, so that the text content is available as input for the summarization stage.
--   **Detailed Requirements:**
-    -   Import Node.js `fs` and `path` modules if not already present in `src/index.ts`.
-    -   In the main workflow (`src/index.ts`), immediately after a successful call to `scrapeArticle` for a story (where the result is a non-null string):
-        -   Retrieve the full path to the current date-stamped output directory.
-        -   Construct the filename: `{storyId}_article.txt`.
-        -   Construct the full file path using `path.join()`.
-        -   Get the successfully scraped article text string (`articleContent`).
-        -   Use `fs.writeFileSync(fullPath, articleContent, 'utf-8')` to save the text to the file. Wrap in `try...catch` for file system errors.
-        -   Log the successful saving of the file (e.g., "Saved scraped article text to {filename}") or any file writing errors encountered.
-    -   Ensure *no* `_article.txt` file is created if `scrapeArticle` returned `null` (due to skipping or failure).
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory contains `_article.txt` files *only* for those stories where `scrapeArticle` succeeded and returned text content.
-    -   AC2: The name of each article text file is `{storyId}_article.txt`.
-    -   AC3: The content of each `_article.txt` file is the plain text string returned by `scrapeArticle`.
-    -   AC4: Logs confirm the successful writing of each `_article.txt` file or report specific file writing errors.
-    -   AC5: No empty `_article.txt` files are created. Files only exist if scraping was successful.
-
----
-
-### Story 3.4: Implement Stage Testing Utility for Scraping
-
--   **User Story / Goal:** As a developer, I want a separate script/command to test the article scraping logic using HN story data from local files, allowing independent testing and debugging of the scraper.
--   **Detailed Requirements:**
-    -   Create a new standalone script file: `src/stages/scrape_articles.ts`.
-    -   Import necessary modules: `fs`, `path`, `logger`, `config`, `scrapeArticle`.
-    -   The script should:
-        -   Initialize the logger.
-        -   Load configuration (to get `OUTPUT_DIR_PATH`).
-        -   Determine the target date-stamped directory path (e.g., `${OUTPUT_DIR_PATH}/YYYY-MM-DD`, using the current date or potentially an optional CLI argument). Ensure this directory exists.
-        -   Read the directory contents and identify all `{storyId}_data.json` files.
-        -   For each `_data.json` file found:
-            -   Read and parse the JSON content.
-            -   Extract the `storyId` and `url`.
-            -   If a valid `url` exists, call `await scrapeArticle(url)`.
-            -   If scraping succeeds (returns text), save the text to `{storyId}_article.txt` in the same directory (using logic from Story 3.3). Overwrite if the file exists.
-            -   Log the progress and outcome (skip/success/fail) for each story processed.
-    -   Add a new script command to `package.json`: `"stage:scrape": "ts-node src/stages/scrape_articles.ts"`. Consider adding argument parsing later if needed to specify a date/directory.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/scrape_articles.ts` exists.
-    -   AC2: The script `stage:scrape` is defined in `package.json`.
-    -   AC3: Running `npm run stage:scrape` (assuming a directory with `_data.json` files exists from a previous `stage:fetch` run) reads these files.
-    -   AC4: The script calls `scrapeArticle` for stories with valid URLs found in the JSON files.
-    -   AC5: The script creates/updates `{storyId}_article.txt` files in the target directory corresponding to successfully scraped articles.
-    -   AC6: The script logs its actions (reading files, attempting scraping, saving results) for each story ID processed.
-    -   AC7: The script operates solely based on local `_data.json` files and fetching from external article URLs; it does not call the Algolia HN API.
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 3     | 2-pm           |
-
-# Epic 4 File
-
-# Epic 4: LLM Summarization & Persistence
-
-**Goal:** Integrate with the configured local Ollama instance to generate summaries for successfully scraped article text and fetched comments. Persist these summaries locally. Implement a stage testing utility for summarization.
-
-## Story List
-
-### Story 4.1: Implement Ollama Client Module
-
--   **User Story / Goal:** As a developer, I want a client module to interact with the configured Ollama API endpoint via HTTP, handling requests and responses for text generation, so that summaries can be generated programmatically.
--   **Detailed Requirements:**
-    -   **Prerequisite:** Ensure a local Ollama instance is installed and running, accessible via the URL defined in `.env` (`OLLAMA_ENDPOINT_URL`), and that the model specified in `.env` (`OLLAMA_MODEL`) has been downloaded (e.g., via `ollama pull model_name`). Instructions for this setup should be in the project README.
-    -   Create a new module: `src/clients/ollamaClient.ts`.
-    -   Implement an async function `generateSummary(promptTemplate: string, content: string): Promise<string | null>`. *(Note: Parameter name changed for clarity)*
-    -   Add configuration variables `OLLAMA_ENDPOINT_URL` (e.g., `http://localhost:11434`) and `OLLAMA_MODEL` (e.g., `llama3`) to `.env.example`. Ensure they are loaded via the config module (`src/utils/config.ts`). Update local `.env` with actual values. Add optional `OLLAMA_TIMEOUT_MS` to `.env.example` with a default like `120000`.
-    -   Inside `generateSummary`:
-        -   Construct the full prompt string using the `promptTemplate` and the provided `content` (e.g., replacing a placeholder like `{Content Placeholder}` in the template, or simple concatenation if templates are basic).
-        -   Construct the Ollama API request payload (JSON): `{ model: configured_model, prompt: full_prompt, stream: false }`. Refer to Ollama `/api/generate` documentation and `docs/data-models.md`.
-        -   Use native `Workspace` to send a POST request to the configured Ollama endpoint + `/api/generate`. Set appropriate headers (`Content-Type: application/json`). Use the configured `OLLAMA_TIMEOUT_MS` or a reasonable default (e.g., 2 minutes).
-        -   Handle `Workspace` errors (network, timeout) using `try...catch`.
-        -   Check `response.ok`. If not OK, log the status/error and return `null`.
-        -   Parse the JSON response from Ollama. Extract the generated text (typically in the `response` field). Refer to `docs/data-models.md`.
-        -   Check for potential errors within the Ollama response structure itself (e.g., an `error` field).
-        -   Return the extracted summary string on success. Return `null` on any failure.
-        -   Log key events: initiating request (mention model), receiving response, success, failure reasons, potentially request/response time using the logger.
-    -   Define necessary TypeScript types for the Ollama request payload and expected response structure in `src/types/ollama.ts` (referenced in `docs/data-models.md`).
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `ollamaClient.ts` module exists and exports `generateSummary`.
-    -   AC2: `OLLAMA_ENDPOINT_URL` and `OLLAMA_MODEL` are defined in `.env.example`, loaded via config, and used by the client. Optional `OLLAMA_TIMEOUT_MS` is handled.
-    -   AC3: `generateSummary` sends a correctly formatted POST request (model, full prompt based on template and content, stream:false) to the configured Ollama endpoint/path using native `Workspace`.
-    -   AC4: Network errors, timeouts, and non-OK API responses are handled gracefully, logged, and result in a `null` return (given the Prerequisite Ollama service is running).
-    -   AC5: A successful Ollama response is parsed correctly, the generated text is extracted, and returned as a string.
-    * AC6: Unexpected Ollama response formats or internal errors (e.g., `{"error": "..."}`) are handled, logged, and result in a `null` return.
-    * AC7: Logs provide visibility into the client's interaction with the Ollama API.
-
----
-
-### Story 4.2: Define Summarization Prompts
-
-* **User Story / Goal:** As a developer, I want standardized base prompts for generating article summaries and HN discussion summaries documented centrally, ensuring consistent instructions are sent to the LLM.
-* **Detailed Requirements:**
-    * Define two standardized base prompts (`ARTICLE_SUMMARY_PROMPT`, `DISCUSSION_SUMMARY_PROMPT`) **and document them in `docs/prompts.md`**.
-    * Ensure these prompts are accessible within the application code, for example, by defining them as exported constants in a dedicated module like `src/utils/prompts.ts`, which reads from or mirrors the content in `docs/prompts.md`.
-* **Acceptance Criteria (ACs):**
-    * AC1: The `ARTICLE_SUMMARY_PROMPT` text is defined in `docs/prompts.md` with appropriate instructional content.
-    * AC2: The `DISCUSSION_SUMMARY_PROMPT` text is defined in `docs/prompts.md` with appropriate instructional content.
-    * AC3: The prompt texts documented in `docs/prompts.md` are available as constants or variables within the application code (e.g., via `src/utils/prompts.ts`) for use by the Ollama client integration.
-
----
-
-### Story 4.3: Integrate Summarization into Main Workflow
-
-* **User Story / Goal:** As a developer, I want to integrate the Ollama client into the main workflow to generate summaries for each story's scraped article text (if available) and fetched comments, using centrally defined prompts and handling potential comment length limits.
-* **Detailed Requirements:**
-    * Modify the main execution flow in `src/index.ts` or `src/core/pipeline.ts`.
-    * Import `ollamaClient.generateSummary` and the prompt constants/variables (e.g., from `src/utils/prompts.ts`, which reflect `docs/prompts.md`).
-    * Load the optional `MAX_COMMENT_CHARS_FOR_SUMMARY` configuration value from `.env` via the config utility.
-    * Within the main loop iterating through stories (after article scraping/persistence in Epic 3):
-    * **Article Summary Generation:**
-        * Check if the `story` object has non-null `articleContent`.
-        * If yes: log "Attempting article summarization for story {storyId}", call `await generateSummary(ARTICLE_SUMMARY_PROMPT, story.articleContent)`, store the result (string or null) as `story.articleSummary`, log success/failure.
-        * If no: set `story.articleSummary = null`, log "Skipping article summarization: No content".
-    * **Discussion Summary Generation:**
-        * Check if the `story` object has a non-empty `comments` array.
-        * If yes:
-            * Format the `story.comments` array into a single text block suitable for the LLM prompt (e.g., concatenating `comment.text` with separators like `---`).
-            * **Check truncation limit:** If `MAX_COMMENT_CHARS_FOR_SUMMARY` is configured to a positive number and the `formattedCommentsText` length exceeds it, truncate `formattedCommentsText` to the limit and log a warning: "Comment text truncated to {limit} characters for summarization for story {storyId}".
-            * Log "Attempting discussion summarization for story {storyId}".
-            * Call `await generateSummary(DISCUSSION_SUMMARY_PROMPT, formattedCommentsText)`. *(Pass the potentially truncated text)*
-            * Store the result (string or null) as `story.discussionSummary`. Log success/failure.
-        * If no: set `story.discussionSummary = null`, log "Skipping discussion summarization: No comments".
-* **Acceptance Criteria (ACs):**
-    * AC1: Running `npm run dev` executes steps from Epics 1-3, then attempts summarization using the Ollama client.
-    * AC2: Article summary is attempted only if `articleContent` exists for a story.
-    * AC3: Discussion summary is attempted only if `comments` exist for a story.
-    * AC4: `generateSummary` is called with the correct prompts (sourced consistently with `docs/prompts.md`) and corresponding content (article text or formatted/potentially truncated comments).
-    * AC5: If `MAX_COMMENT_CHARS_FOR_SUMMARY` is set and comment text exceeds it, the text passed to `generateSummary` is truncated, and a warning is logged.
-    * AC6: Logs clearly indicate the start, success, or failure (including null returns from the client) for both article and discussion summarization attempts per story.
-    * AC7: Story objects in memory now contain `articleSummary` (string/null) and `discussionSummary` (string/null) properties.
-
----
-
-### Story 4.4: Persist Generated Summaries Locally
-
-*(No changes needed for this story based on recent decisions)*
-
--   **User Story / Goal:** As a developer, I want to save the generated article and discussion summaries (or null placeholders) to a local JSON file for each story, making them available for the email assembly stage.
--   **Detailed Requirements:**
-    -   Define the structure for the summary output file: `{storyId}_summary.json`. Content example: `{ "storyId": "...", "articleSummary": "...", "discussionSummary": "...", "summarizedAt": "ISO_TIMESTAMP" }`. Note that `articleSummary` and `discussionSummary` can be `null`.
-    -   Import `fs` and `path` in `src/index.ts` or `src/core/pipeline.ts` if needed.
-    -   In the main workflow loop, after *both* summarization attempts (article and discussion) for a story are complete:
-        -   Create a summary result object containing `storyId`, `articleSummary` (string or null), `discussionSummary` (string or null), and the current ISO timestamp (`new Date().toISOString()`). Add this timestamp to the in-memory `story` object as well (`story.summarizedAt`).
-        -   Get the full path to the date-stamped output directory.
-        -   Construct the filename: `{storyId}_summary.json`.
-        -   Construct the full file path using `path.join()`.
-        -   Serialize the summary result object to JSON (`JSON.stringify(..., null, 2)`).
-        -   Use `fs.writeFileSync` to save the JSON to the file, wrapping in `try...catch`.
-        -   Log the successful saving of the summary file or any file writing errors.
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory contains 10 files named `{storyId}_summary.json`.
-    -   AC2: Each `_summary.json` file contains valid JSON adhering to the defined structure.
-    -   AC3: The `articleSummary` field contains the generated summary string if successful, otherwise `null`.
-    -   AC4: The `discussionSummary` field contains the generated summary string if successful, otherwise `null`.
-    -   AC5: A valid ISO timestamp is present in the `summarizedAt` field.
-    -   AC6: Logs confirm successful writing of each summary file or report file system errors.
-
----
-
-### Story 4.5: Implement Stage Testing Utility for Summarization
-
-*(Changes needed to reflect prompt sourcing and optional truncation)*
-
-* **User Story / Goal:** As a developer, I want a separate script/command to test the LLM summarization logic using locally persisted data (HN comments, scraped article text), allowing independent testing of prompts and Ollama interaction.
-* **Detailed Requirements:**
-    * Create a new standalone script file: `src/stages/summarize_content.ts`.
-    * Import necessary modules: `fs`, `path`, `logger`, `config`, `ollamaClient`, prompt constants (e.g., from `src/utils/prompts.ts`).
-    * The script should:
-        * Initialize logger, load configuration (Ollama endpoint/model, output dir, **optional `MAX_COMMENT_CHARS_FOR_SUMMARY`**).
-        * Determine target date-stamped directory path.
-        * Find all `{storyId}_data.json` files in the directory.
-        * For each `storyId` found:
-            * Read `{storyId}_data.json` to get comments. Format them into a single text block.
-            * *Attempt* to read `{storyId}_article.txt`. Handle file-not-found gracefully. Store content or null.
-            * Call `ollamaClient.generateSummary` for article text (if not null) using `ARTICLE_SUMMARY_PROMPT`.
-            * **Apply truncation logic:** If comments exist, check `MAX_COMMENT_CHARS_FOR_SUMMARY` and truncate the formatted comment text block if needed, logging a warning.
-            * Call `ollamaClient.generateSummary` for formatted comments (if comments exist) using `DISCUSSION_SUMMARY_PROMPT` *(passing potentially truncated text)*.
-            * Construct the summary result object (with summaries or nulls, and timestamp).
-            * Save the result object to `{storyId}_summary.json` in the same directory (using logic from Story 4.4), overwriting if exists.
-            * Log progress (reading files, calling Ollama, truncation warnings, saving results) for each story ID.
-    * Add script to `package.json`: `"stage:summarize": "ts-node src/stages/summarize_content.ts"`.
-* **Acceptance Criteria (ACs):**
-    * AC1: The file `src/stages/summarize_content.ts` exists.
-    * AC2: The script `stage:summarize` is defined in `package.json`.
-    * AC3: Running `npm run stage:summarize` (after `stage:fetch` and `stage:scrape` runs) reads `_data.json` and attempts to read `_article.txt` files from the target directory.
-    * AC4: The script calls the `ollamaClient` with correct prompts (sourced consistently with `docs/prompts.md`) and content derived *only* from the local files (requires Ollama service running per Story 4.1 prerequisite).
-    * AC5: If `MAX_COMMENT_CHARS_FOR_SUMMARY` is set and applicable, comment text is truncated before calling the client, and a warning is logged.
-    * AC6: The script creates/updates `{storyId}_summary.json` files in the target directory reflecting the results of the Ollama calls (summaries or nulls).
-    * AC7: Logs show the script processing each story ID found locally, interacting with Ollama, and saving results.
-    * AC8: The script does not call Algolia API or the article scraper module.
-
-## Change Log
-
-| Change                      | Date         | Version | Description                          | Author         |
-| --------------------------- | ------------ | ------- | ------------------------------------ | -------------- |
-| Integrate prompts.md refs   | 2025-05-04   | 0.3     | Updated stories 4.2, 4.3, 4.5        | 3-Architect    |
-| Added Ollama Prereq Note    | 2025-05-04   | 0.2     | Added note about local Ollama setup  | 2-pm           |
-| Initial Draft               | 2025-05-04   | 0.1     | First draft of Epic 4                | 2-pm           |
-
-# Epic 5 File
-
-# Epic 5: Digest Assembly & Email Dispatch
-
-**Goal:** Assemble the collected story data and summaries from local files, format them into a readable HTML email digest, and send the email using Nodemailer with configured credentials. Implement a stage testing utility for emailing with a dry-run option.
-
-## Story List
-
-### Story 5.1: Implement Email Content Assembler
-
--   **User Story / Goal:** As a developer, I want a module that reads the persisted story metadata (`_data.json`) and summaries (`_summary.json`) from a specified directory, consolidating the necessary information needed to render the email digest.
--   **Detailed Requirements:**
-    -   Create a new module: `src/email/contentAssembler.ts`.
-    -   Define a TypeScript type/interface `DigestData` representing the data needed per story for the email template: `{ storyId: string, title: string, hnUrl: string, articleUrl: string | null, articleSummary: string | null, discussionSummary: string | null }`.
-    -   Implement an async function `assembleDigestData(dateDirPath: string): Promise<DigestData[]>`.
-    -   The function should:
-        -   Use Node.js `fs` to read the contents of the `dateDirPath`.
-        -   Identify all files matching the pattern `{storyId}_data.json`.
-        -   For each `storyId` found:
-            -   Read and parse the `{storyId}_data.json` file. Extract `title`, `hnUrl`, and `url` (use as `articleUrl`). Handle potential file read/parse errors gracefully (log and skip story).
-            -   Attempt to read and parse the corresponding `{storyId}_summary.json` file. Handle file-not-found or parse errors gracefully (treat `articleSummary` and `discussionSummary` as `null`).
-            -   Construct a `DigestData` object for the story, including the extracted metadata and summaries (or nulls).
-        -   Collect all successfully constructed `DigestData` objects into an array.
-        -   Return the array. It should ideally contain 10 items if all previous stages succeeded.
-    -   Log progress (e.g., "Assembling digest data from directory...", "Processing story {storyId}...") and any errors encountered during file processing using the logger.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `contentAssembler.ts` module exists and exports `assembleDigestData` and the `DigestData` type.
-    -   AC2: `assembleDigestData` correctly reads `_data.json` files from the provided directory path.
-    -   AC3: It attempts to read corresponding `_summary.json` files, correctly handling cases where the summary file might be missing or unparseable (resulting in null summaries for that story).
-    -   AC4: The function returns a promise resolving to an array of `DigestData` objects, populated with data extracted from the files.
-    -   AC5: Errors during file reading or JSON parsing are logged, and the function returns data for successfully processed stories.
-
----
-
-### Story 5.2: Create HTML Email Template & Renderer
-
--   **User Story / Goal:** As a developer, I want a basic HTML email template and a function to render it with the assembled digest data, producing the final HTML content for the email body.
--   **Detailed Requirements:**
-    -   Define the HTML structure. This can be done using template literals within a function or potentially using a simple template file (e.g., `src/email/templates/digestTemplate.html`) and `fs.readFileSync`. Template literals are simpler for MVP.
-    -   Create a function `renderDigestHtml(data: DigestData[], digestDate: string): string` (e.g., in `src/email/contentAssembler.ts` or a new `templater.ts`).
-    -   The function should generate an HTML string with:
-        -   A suitable title in the body (e.g., `<h1>Hacker News Top 10 Summaries for ${digestDate}</h1>`).
-        -   A loop through the `data` array.
-        -   For each `story` in `data`:
-            -   Display `<h2><a href="${story.articleUrl || story.hnUrl}">${story.title}</a></h2>`.
-            -   Display `<p><a href="${story.hnUrl}">View HN Discussion</a></p>`.
-            -   Conditionally display `<h3>Article Summary</h3><p>${story.articleSummary}</p>` *only if* `story.articleSummary` is not null/empty.
-            -   Conditionally display `<h3>Discussion Summary</h3><p>${story.discussionSummary}</p>` *only if* `story.discussionSummary` is not null/empty.
-            -   Include a separator (e.g., `<hr style="margin-top: 20px; margin-bottom: 20px;">`).
-    -   Use basic inline CSS for minimal styling (margins, etc.) to ensure readability. Avoid complex layouts.
-    -   Return the complete HTML document as a string.
--   **Acceptance Criteria (ACs):**
-    -   AC1: A function `renderDigestHtml` exists that accepts the digest data array and a date string.
-    -   AC2: The function returns a single, complete HTML string.
-    -   AC3: The generated HTML includes a title with the date and correctly iterates through the story data.
-    -   AC4: For each story, the HTML displays the linked title, HN link, and conditionally displays the article and discussion summaries with headings.
-    -   AC5: Basic separators and margins are used for readability. The HTML is simple and likely to render reasonably in most email clients.
-
----
-
-### Story 5.3: Implement Nodemailer Email Sender
-
--   **User Story / Goal:** As a developer, I want a module to send the generated HTML email using Nodemailer, configured with credentials stored securely in the environment file.
--   **Detailed Requirements:**
-    -   Add Nodemailer dependencies: `npm install nodemailer @types/nodemailer --save-prod`.
-    -   Add required configuration variables to `.env.example` (and local `.env`): `EMAIL_HOST`, `EMAIL_PORT` (e.g., 587), `EMAIL_SECURE` (e.g., `false` for STARTTLS on 587, `true` for 465), `EMAIL_USER`, `EMAIL_PASS`, `EMAIL_FROM` (e.g., `"Your Name <you@example.com>"`), `EMAIL_RECIPIENTS` (comma-separated list).
-    -   Create a new module: `src/email/emailSender.ts`.
-    -   Implement an async function `sendDigestEmail(subject: string, htmlContent: string): Promise<boolean>`.
-    -   Inside the function:
-        -   Load the `EMAIL_*` variables from the config module.
-        -   Create a Nodemailer transporter using `nodemailer.createTransport` with the loaded config (host, port, secure flag, auth: { user, pass }).
-        -   Verify transporter configuration using `transporter.verify()` (optional but recommended). Log verification success/failure.
-        -   Parse the `EMAIL_RECIPIENTS` string into an array or comma-separated string suitable for the `to` field.
-        -   Define the `mailOptions`: `{ from: EMAIL_FROM, to: parsedRecipients, subject: subject, html: htmlContent }`.
-        -   Call `await transporter.sendMail(mailOptions)`.
-        -   If `sendMail` succeeds, log the success message including the `messageId` from the result. Return `true`.
-        -   If `sendMail` fails (throws error), log the error using the logger. Return `false`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: `nodemailer` and `@types/nodemailer` dependencies are added.
-    -   AC2: `EMAIL_*` variables are defined in `.env.example` and loaded from config.
-    -   AC3: `emailSender.ts` module exists and exports `sendDigestEmail`.
-    -   AC4: `sendDigestEmail` correctly creates a Nodemailer transporter using configuration from `.env`. Transporter verification is attempted (optional AC).
-    -   AC5: The `to` field is correctly populated based on `EMAIL_RECIPIENTS`.
-    -   AC6: `transporter.sendMail` is called with correct `from`, `to`, `subject`, and `html` options.
-    -   AC7: Email sending success (including message ID) or failure is logged clearly.
-    -   AC8: The function returns `true` on successful sending, `false` otherwise.
-
----
-
-### Story 5.4: Integrate Email Assembly and Sending into Main Workflow
-
--   **User Story / Goal:** As a developer, I want the main application workflow (`src/index.ts`) to orchestrate the final steps: assembling digest data, rendering the HTML, and triggering the email send after all previous stages are complete.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts`.
-    -   Import `assembleDigestData`, `renderDigestHtml`, `sendDigestEmail`.
-    -   Execute these steps *after* the main loop (where stories are fetched, scraped, summarized, and persisted) completes:
-        -   Log "Starting final digest assembly and email dispatch...".
-        -   Determine the path to the current date-stamped output directory.
-        -   Call `const digestData = await assembleDigestData(dateDirPath)`.
-        -   Check if `digestData` array is not empty.
-            -   If yes:
-                -   Get the current date string (e.g., 'YYYY-MM-DD').
-                -   `const htmlContent = renderDigestHtml(digestData, currentDate)`.
-                -   `const subject = \`BMad Hacker Daily Digest - ${currentDate}\``.
-                -   `const emailSent = await sendDigestEmail(subject, htmlContent)`.
-                -   Log the final outcome based on `emailSent` ("Digest email sent successfully." or "Failed to send digest email.").
-            -   If no (`digestData` is empty or assembly failed):
-                -   Log an error: "Failed to assemble digest data or no data found. Skipping email."
-        -   Log "BMad Hacker Daily Digest process finished."
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes all stages (Epics 1-4) and then proceeds to email assembly and sending.
-    -   AC2: `assembleDigestData` is called correctly with the output directory path after other processing is done.
-    -   AC3: If data is assembled, `renderDigestHtml` and `sendDigestEmail` are called with the correct data, subject, and HTML.
-    -   AC4: The final success or failure of the email sending step is logged.
-    -   AC5: If `assembleDigestData` returns no data, email sending is skipped, and an appropriate message is logged.
-    -   AC6: The application logs a final completion message.
-
----
-
-### Story 5.5: Implement Stage Testing Utility for Emailing
-
--   **User Story / Goal:** As a developer, I want a separate script/command to test the email assembly, rendering, and sending logic using persisted local data, including a crucial `--dry-run` option to prevent accidental email sending during tests.
--   **Detailed Requirements:**
-    -   Add `yargs` dependency for argument parsing: `npm install yargs @types/yargs --save-dev`.
-    -   Create a new standalone script file: `src/stages/send_digest.ts`.
-    -   Import necessary modules: `fs`, `path`, `logger`, `config`, `assembleDigestData`, `renderDigestHtml`, `sendDigestEmail`, `yargs`.
-    -   Use `yargs` to parse command-line arguments, specifically looking for a `--dry-run` boolean flag (defaulting to `false`). Allow an optional argument for specifying the date-stamped directory, otherwise default to current date.
-    -   The script should:
-        -   Initialize logger, load config.
-        -   Determine the target date-stamped directory path (from arg or default). Log the target directory.
-        -   Call `await assembleDigestData(dateDirPath)`.
-        -   If data is assembled and not empty:
-            -   Determine the date string for the subject/title.
-            -   Call `renderDigestHtml(digestData, dateString)` to get HTML.
-            -   Construct the subject string.
-            -   Check the `dryRun` flag:
-                -   If `true`: Log "DRY RUN enabled. Skipping actual email send.". Log the subject. Save the `htmlContent` to a file in the target directory (e.g., `_digest_preview.html`). Log that the preview file was saved.
-                -   If `false`: Log "Live run: Attempting to send email...". Call `await sendDigestEmail(subject, htmlContent)`. Log success/failure based on the return value.
-        -   If data assembly fails or is empty, log the error.
-    -   Add script to `package.json`: `"stage:email": "ts-node src/stages/send_digest.ts --"`. The `--` allows passing arguments like `--dry-run`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/send_digest.ts` exists. `yargs` dependency is added.
-    -   AC2: The script `stage:email` is defined in `package.json` allowing arguments.
-    -   AC3: Running `npm run stage:email -- --dry-run` reads local data, renders HTML, logs the intent, saves `_digest_preview.html` locally, and does *not* call `sendDigestEmail`.
-    -   AC4: Running `npm run stage:email` (without `--dry-run`) reads local data, renders HTML, and *does* call `sendDigestEmail`, logging the outcome.
-    -   AC5: The script correctly identifies and acts upon the `--dry-run` flag.
-    -   AC6: Logs clearly distinguish between dry runs and live runs and report success/failure.
-    -   AC7: The script operates using only local files and the email configuration/service; it does not invoke prior pipeline stages (Algolia, scraping, Ollama).
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 5     | 2-pm           |
-
-# END EPIC FILES

V2-FULL-DEMO-WALKTHROUGH/combined-artifacts-for-posm.txt

@@ -1,614 +0,0 @@
-# Epic 1 file
-
-# Epic 1: Project Initialization & Core Setup
-
-**Goal:** Initialize the project using the "bmad-boilerplate", manage dependencies, setup `.env` and config loading, establish basic CLI entry point, setup basic logging and output directory structure. This provides the foundational setup for all subsequent development work.
-
-## Story List
-
-### Story 1.1: Initialize Project from Boilerplate
-
--   **User Story / Goal:** As a developer, I want to set up the initial project structure using the `bmad-boilerplate`, so that I have the standard tooling (TS, Jest, ESLint, Prettier), configurations, and scripts in place.
--   **Detailed Requirements:**
-    -   Copy or clone the contents of the `bmad-boilerplate` into the new project's root directory.
-    -   Initialize a git repository in the project root directory (if not already done by cloning).
-    -   Ensure the `.gitignore` file from the boilerplate is present.
-    -   Run `npm install` to download and install all `devDependencies` specified in the boilerplate's `package.json`.
-    -   Verify that the core boilerplate scripts (`lint`, `format`, `test`, `build`) execute without errors on the initial codebase.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The project directory contains the files and structure from `bmad-boilerplate`.
-    -   AC2: A `node_modules` directory exists and contains packages corresponding to `devDependencies`.
-    -   AC3: `npm run lint` command completes successfully without reporting any linting errors.
-    -   AC4: `npm run format` command completes successfully, potentially making formatting changes according to Prettier rules. Running it a second time should result in no changes.
-    -   AC5: `npm run test` command executes Jest successfully (it may report "no tests found" which is acceptable at this stage).
-    -   AC6: `npm run build` command executes successfully, creating a `dist` directory containing compiled JavaScript output.
-    -   AC7: The `.gitignore` file exists and includes entries for `node_modules/`, `.env`, `dist/`, etc. as specified in the boilerplate.
-
----
-
-### Story 1.2: Setup Environment Configuration
-
--   **User Story / Goal:** As a developer, I want to establish the environment configuration mechanism using `.env` files, so that secrets and settings (like output paths) can be managed outside of version control, following boilerplate conventions.
--   **Detailed Requirements:**
-    -   Add a production dependency for loading `.env` files (e.g., `dotenv`). Run `npm install dotenv --save-prod` (or similar library).
-    -   Verify the `.env.example` file exists (from boilerplate).
-    -   Add an initial configuration variable `OUTPUT_DIR_PATH=./output` to `.env.example`.
-    -   Create the `.env` file locally by copying `.env.example`. Populate `OUTPUT_DIR_PATH` if needed (can keep default).
-    -   Implement a utility module (e.g., `src/config.ts`) that loads environment variables from the `.env` file at application startup.
-    -   The utility should export the loaded configuration values (initially just `OUTPUT_DIR_PATH`).
-    -   Ensure the `.env` file is listed in `.gitignore` and is not committed.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The chosen `.env` library (e.g., `dotenv`) is listed under `dependencies` in `package.json` and `package-lock.json` is updated.
-    -   AC2: The `.env.example` file exists, is tracked by git, and contains the line `OUTPUT_DIR_PATH=./output`.
-    -   AC3: The `.env` file exists locally but is NOT tracked by git.
-    -   AC4: A configuration module (`src/config.ts` or similar) exists and successfully loads the `OUTPUT_DIR_PATH` value from `.env` when the application starts.
-    -   AC5: The loaded `OUTPUT_DIR_PATH` value is accessible within the application code.
-
----
-
-### Story 1.3: Implement Basic CLI Entry Point & Execution
-
--   **User Story / Goal:** As a developer, I want a basic `src/index.ts` entry point that can be executed via the boilerplate's `dev` and `start` scripts, providing a working foundation for the application logic.
--   **Detailed Requirements:**
-    -   Create the main application entry point file at `src/index.ts`.
-    -   Implement minimal code within `src/index.ts` to:
-        -   Import the configuration loading mechanism (from Story 1.2).
-        -   Log a simple startup message to the console (e.g., "BMad Hacker Daily Digest - Starting Up...").
-        -   (Optional) Log the loaded `OUTPUT_DIR_PATH` to verify config loading.
-    -   Confirm execution using boilerplate scripts.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `src/index.ts` file exists.
-    -   AC2: Running `npm run dev` executes `src/index.ts` via `ts-node` and logs the startup message to the console.
-    -   AC3: Running `npm run build` successfully compiles `src/index.ts` (and any imports) into the `dist` directory.
-    -   AC4: Running `npm start` (after a successful build) executes the compiled code from `dist` and logs the startup message to the console.
-
----
-
-### Story 1.4: Setup Basic Logging and Output Directory
-
--   **User Story / Goal:** As a developer, I want a basic console logging mechanism and the dynamic creation of a date-stamped output directory, so that the application can provide execution feedback and prepare for storing data artifacts in subsequent epics.
--   **Detailed Requirements:**
-    -   Implement a simple, reusable logging utility module (e.g., `src/logger.ts`). Initially, it can wrap `console.log`, `console.warn`, `console.error`.
-    -   Refactor `src/index.ts` to use this `logger` for its startup message(s).
-    -   In `src/index.ts` (or a setup function called by it):
-        -   Retrieve the `OUTPUT_DIR_PATH` from the configuration (loaded in Story 1.2).
-        -   Determine the current date in 'YYYY-MM-DD' format.
-        -   Construct the full path for the date-stamped subdirectory (e.g., `${OUTPUT_DIR_PATH}/YYYY-MM-DD`).
-        -   Check if the base output directory exists; if not, create it.
-        -   Check if the date-stamped subdirectory exists; if not, create it recursively. Use Node.js `fs` module (e.g., `fs.mkdirSync(path, { recursive: true })`).
-        -   Log (using the logger) the full path of the output directory being used for the current run (e.g., "Output directory for this run: ./output/2025-05-04").
--   **Acceptance Criteria (ACs):**
-    -   AC1: A logger utility module (`src/logger.ts` or similar) exists and is used for console output in `src/index.ts`.
-    -   AC2: Running `npm run dev` or `npm start` logs the startup message via the logger.
-    -   AC3: Running the application creates the base output directory (e.g., `./output` defined in `.env`) if it doesn't already exist.
-    -   AC4: Running the application creates a date-stamped subdirectory (e.g., `./output/2025-05-04`) within the base output directory if it doesn't already exist.
-    -   AC5: The application logs a message indicating the full path to the date-stamped output directory created/used for the current execution.
-    -   AC6: The application exits gracefully after performing these setup steps (for now).
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 1     | 2-pm           |
-
-# Epic 2 File
-
-# Epic 2: HN Data Acquisition & Persistence
-
-**Goal:** Implement fetching top 10 stories and their comments (respecting limits) from Algolia HN API, and persist this raw data locally into the date-stamped output directory created in Epic 1. Implement a stage testing utility for fetching.
-
-## Story List
-
-### Story 2.1: Implement Algolia HN API Client
-
--   **User Story / Goal:** As a developer, I want a dedicated client module to interact with the Algolia Hacker News Search API, so that fetching stories and comments is encapsulated, reusable, and uses the required native `Workspace` API.
--   **Detailed Requirements:**
-    -   Create a new module: `src/clients/algoliaHNClient.ts`.
-    -   Implement an async function `WorkspaceTopStories` within the client:
-        -   Use native `Workspace` to call the Algolia HN Search API endpoint for front-page stories (e.g., `http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10`). Adjust `hitsPerPage` if needed to ensure 10 stories.
-        -   Parse the JSON response.
-        -   Extract required metadata for each story: `objectID` (use as `storyId`), `title`, `url` (article URL), `points`, `num_comments`. Handle potential missing `url` field gracefully (log warning, maybe skip story later if URL needed).
-        -   Construct the `hnUrl` for each story (e.g., `https://news.ycombinator.com/item?id={storyId}`).
-        -   Return an array of structured story objects.
-    -   Implement a separate async function `WorkspaceCommentsForStory` within the client:
-        -   Accept `storyId` and `maxComments` limit as arguments.
-        -   Use native `Workspace` to call the Algolia HN Search API endpoint for comments of a specific story (e.g., `http://hn.algolia.com/api/v1/search?tags=comment,story_{storyId}&hitsPerPage={maxComments}`).
-        -   Parse the JSON response.
-        -   Extract required comment data: `objectID` (use as `commentId`), `comment_text`, `author`, `created_at`.
-        -   Filter out comments where `comment_text` is null or empty. Ensure only up to `maxComments` are returned.
-        -   Return an array of structured comment objects.
-    -   Implement basic error handling using `try...catch` around `Workspace` calls and check `response.ok` status. Log errors using the logger utility from Epic 1.
-    -   Define TypeScript interfaces/types for the expected structures of API responses (stories, comments) and the data returned by the client functions (e.g., `Story`, `Comment`).
--   **Acceptance Criteria (ACs):**
-    -   AC1: The module `src/clients/algoliaHNClient.ts` exists and exports `WorkspaceTopStories` and `WorkspaceCommentsForStory` functions.
-    -   AC2: Calling `WorkspaceTopStories` makes a network request to the correct Algolia endpoint and returns a promise resolving to an array of 10 `Story` objects containing the specified metadata.
-    -   AC3: Calling `WorkspaceCommentsForStory` with a valid `storyId` and `maxComments` limit makes a network request to the correct Algolia endpoint and returns a promise resolving to an array of `Comment` objects (up to `maxComments`), filtering out empty ones.
-    -   AC4: Both functions use the native `Workspace` API internally.
-    -   AC5: Network errors or non-successful API responses (e.g., status 4xx, 5xx) are caught and logged using the logger.
-    -   AC6: Relevant TypeScript types (`Story`, `Comment`, etc.) are defined and used within the client module.
-
----
-
-### Story 2.2: Integrate HN Data Fetching into Main Workflow
-
--   **User Story / Goal:** As a developer, I want to integrate the HN data fetching logic into the main application workflow (`src/index.ts`), so that running the app retrieves the top 10 stories and their comments after completing the setup from Epic 1.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts` (or a main async function called by it).
-    -   Import the `algoliaHNClient` functions.
-    -   Import the configuration module to access `MAX_COMMENTS_PER_STORY`.
-    -   After the Epic 1 setup (config load, logger init, output dir creation), call `WorkspaceTopStories()`.
-    -   Log the number of stories fetched.
-    -   Iterate through the array of fetched `Story` objects.
-    -   For each `Story`, call `WorkspaceCommentsForStory()`, passing the `story.storyId` and the configured `MAX_COMMENTS_PER_STORY`.
-    -   Store the fetched comments within the corresponding `Story` object in memory (e.g., add a `comments: Comment[]` property to the `Story` object).
-    -   Log progress using the logger utility (e.g., "Fetched 10 stories.", "Fetching up to X comments for story {storyId}...").
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes Epic 1 setup steps followed by fetching stories and then comments for each story.
-    -   AC2: Logs clearly show the start and successful completion of fetching stories, and the start of fetching comments for each of the 10 stories.
-    -   AC3: The configured `MAX_COMMENTS_PER_STORY` value is read from config and used in the calls to `WorkspaceCommentsForStory`.
-    -   AC4: After successful execution, story objects held in memory contain a nested array of fetched comment objects. (Can be verified via debugger or temporary logging).
-
----
-
-### Story 2.3: Persist Fetched HN Data Locally
-
--   **User Story / Goal:** As a developer, I want to save the fetched HN stories (including their comments) to JSON files in the date-stamped output directory, so that the raw data is persisted locally for subsequent pipeline stages and debugging.
--   **Detailed Requirements:**
-    -   Define a consistent JSON structure for the output file content. Example: `{ storyId: "...", title: "...", url: "...", hnUrl: "...", points: ..., fetchedAt: "ISO_TIMESTAMP", comments: [{ commentId: "...", text: "...", author: "...", createdAt: "ISO_TIMESTAMP", ... }, ...] }`. Include a timestamp for when the data was fetched.
-    -   Import Node.js `fs` (specifically `fs.writeFileSync`) and `path` modules.
-    -   In the main workflow (`src/index.ts`), within the loop iterating through stories (after comments have been fetched and added to the story object in Story 2.2):
-        -   Get the full path to the date-stamped output directory (determined in Epic 1).
-        -   Construct the filename for the story's data: `{storyId}_data.json`.
-        -   Construct the full file path using `path.join()`.
-        -   Serialize the complete story object (including comments and fetch timestamp) to a JSON string using `JSON.stringify(storyObject, null, 2)` for readability.
-        -   Write the JSON string to the file using `fs.writeFileSync()`. Use a `try...catch` block for error handling.
-    -   Log (using the logger) the successful persistence of each story's data file or any errors encountered during file writing.
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory (e.g., `./output/YYYY-MM-DD/`) contains exactly 10 files named `{storyId}_data.json`.
-    -   AC2: Each JSON file contains valid JSON representing a single story object, including its metadata, fetch timestamp, and an array of its fetched comments, matching the defined structure.
-    -   AC3: The number of comments in each file's `comments` array does not exceed `MAX_COMMENTS_PER_STORY`.
-    -   AC4: Logs indicate that saving data to a file was attempted for each story, reporting success or specific file writing errors.
-
----
-
-### Story 2.4: Implement Stage Testing Utility for HN Fetching
-
--   **User Story / Goal:** As a developer, I want a separate, executable script that *only* performs the HN data fetching and persistence, so I can test and trigger this stage independently of the full pipeline.
--   **Detailed Requirements:**
-    -   Create a new standalone script file: `src/stages/fetch_hn_data.ts`.
-    -   This script should perform the essential setup required for this stage: initialize logger, load configuration (`.env`), determine and create output directory (reuse or replicate logic from Epic 1 / `src/index.ts`).
-    -   The script should then execute the core logic of fetching stories via `algoliaHNClient.fetchTopStories`, fetching comments via `algoliaHNClient.fetchCommentsForStory` (using loaded config for limit), and persisting the results to JSON files using `fs.writeFileSync` (replicating logic from Story 2.3).
-    -   The script should log its progress using the logger utility.
-    -   Add a new script command to `package.json` under `"scripts"`: `"stage:fetch": "ts-node src/stages/fetch_hn_data.ts"`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/fetch_hn_data.ts` exists.
-    -   AC2: The script `stage:fetch` is defined in `package.json`'s `scripts` section.
-    -   AC3: Running `npm run stage:fetch` executes successfully, performing only the setup, fetch, and persist steps.
-    -   AC4: Running `npm run stage:fetch` creates the same 10 `{storyId}_data.json` files in the correct date-stamped output directory as running the main `npm run dev` command (at the current state of development).
-    -   AC5: Logs generated by `npm run stage:fetch` reflect only the fetching and persisting steps, not subsequent pipeline stages.
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 2     | 2-pm           |
-
-# Epic 3 File
-
-# Epic 3: Article Scraping & Persistence
-
-**Goal:** Implement a best-effort article scraping mechanism to fetch and extract plain text content from the external URLs associated with fetched HN stories. Handle failures gracefully and persist successfully scraped text locally. Implement a stage testing utility for scraping.
-
-## Story List
-
-### Story 3.1: Implement Basic Article Scraper Module
-
--   **User Story / Goal:** As a developer, I want a module that attempts to fetch HTML from a URL and extract the main article text using basic methods, handling common failures gracefully, so article content can be prepared for summarization.
--   **Detailed Requirements:**
-    -   Create a new module: `src/scraper/articleScraper.ts`.
-    -   Add a suitable HTML parsing/extraction library dependency (e.g., `@extractus/article-extractor` recommended for simplicity, or `cheerio` for more control). Run `npm install @extractus/article-extractor --save-prod` (or chosen alternative).
-    -   Implement an async function `scrapeArticle(url: string): Promise<string | null>` within the module.
-    -   Inside the function:
-        -   Use native `Workspace` to retrieve content from the `url`. Set a reasonable timeout (e.g., 10-15 seconds). Include a `User-Agent` header to mimic a browser.
-        -   Handle potential `Workspace` errors (network errors, timeouts) using `try...catch`.
-        -   Check the `response.ok` status. If not okay, log error and return `null`.
-        -   Check the `Content-Type` header of the response. If it doesn't indicate HTML (e.g., does not include `text/html`), log warning and return `null`.
-        -   If HTML is received, attempt to extract the main article text using the chosen library (`article-extractor` preferred).
-        -   Wrap the extraction logic in a `try...catch` to handle library-specific errors.
-        -   Return the extracted plain text string if successful. Ensure it's just text, not HTML markup.
-        -   Return `null` if extraction fails or results in empty content.
-    -   Log all significant events, errors, or reasons for returning null (e.g., "Scraping URL...", "Fetch failed:", "Non-HTML content type:", "Extraction failed:", "Successfully extracted text") using the logger utility.
-    -   Define TypeScript types/interfaces as needed.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `articleScraper.ts` module exists and exports the `scrapeArticle` function.
-    -   AC2: The chosen scraping library (e.g., `@extractus/article-extractor`) is added to `dependencies` in `package.json`.
-    -   AC3: `scrapeArticle` uses native `Workspace` with a timeout and User-Agent header.
-    -   AC4: `scrapeArticle` correctly handles fetch errors, non-OK responses, and non-HTML content types by logging and returning `null`.
-    -   AC5: `scrapeArticle` uses the chosen library to attempt text extraction from valid HTML content.
-    -   AC6: `scrapeArticle` returns the extracted plain text on success, and `null` on any failure (fetch, non-HTML, extraction error, empty result).
-    -   AC7: Relevant logs are produced for success, failure modes, and errors encountered during the process.
-
----
-
-### Story 3.2: Integrate Article Scraping into Main Workflow
-
--   **User Story / Goal:** As a developer, I want to integrate the article scraper into the main workflow (`src/index.ts`), attempting to scrape the article for each HN story that has a valid URL, after fetching its data.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts`.
-    -   Import the `scrapeArticle` function from `src/scraper/articleScraper.ts`.
-    -   Within the main loop iterating through the fetched stories (after comments are fetched in Epic 2):
-        -   Check if `story.url` exists and appears to be a valid HTTP/HTTPS URL. A simple check for starting with `http://` or `https://` is sufficient.
-        -   If the URL is missing or invalid, log a warning ("Skipping scraping for story {storyId}: Missing or invalid URL") and proceed to the next story's processing step.
-        -   If a valid URL exists, log ("Attempting to scrape article for story {storyId} from {story.url}").
-        -   Call `await scrapeArticle(story.url)`.
-        -   Store the result (the extracted text string or `null`) in memory, associated with the story object (e.g., add property `articleContent: string | null`).
-        -   Log the outcome clearly (e.g., "Successfully scraped article for story {storyId}", "Failed to scrape article for story {storyId}").
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes Epic 1 & 2 steps, and then attempts article scraping for stories with valid URLs.
-    -   AC2: Stories with missing or invalid URLs are skipped, and a corresponding log message is generated.
-    -   AC3: For stories with valid URLs, the `scrapeArticle` function is called.
-    -   AC4: Logs clearly indicate the start and success/failure outcome of the scraping attempt for each relevant story.
-    -   AC5: Story objects held in memory after this stage contain an `articleContent` property holding the scraped text (string) or `null` if scraping was skipped or failed.
-
----
-
-### Story 3.3: Persist Scraped Article Text Locally
-
--   **User Story / Goal:** As a developer, I want to save successfully scraped article text to a separate local file for each story, so that the text content is available as input for the summarization stage.
--   **Detailed Requirements:**
-    -   Import Node.js `fs` and `path` modules if not already present in `src/index.ts`.
-    -   In the main workflow (`src/index.ts`), immediately after a successful call to `scrapeArticle` for a story (where the result is a non-null string):
-        -   Retrieve the full path to the current date-stamped output directory.
-        -   Construct the filename: `{storyId}_article.txt`.
-        -   Construct the full file path using `path.join()`.
-        -   Get the successfully scraped article text string (`articleContent`).
-        -   Use `fs.writeFileSync(fullPath, articleContent, 'utf-8')` to save the text to the file. Wrap in `try...catch` for file system errors.
-        -   Log the successful saving of the file (e.g., "Saved scraped article text to {filename}") or any file writing errors encountered.
-    -   Ensure *no* `_article.txt` file is created if `scrapeArticle` returned `null` (due to skipping or failure).
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory contains `_article.txt` files *only* for those stories where `scrapeArticle` succeeded and returned text content.
-    -   AC2: The name of each article text file is `{storyId}_article.txt`.
-    -   AC3: The content of each `_article.txt` file is the plain text string returned by `scrapeArticle`.
-    -   AC4: Logs confirm the successful writing of each `_article.txt` file or report specific file writing errors.
-    -   AC5: No empty `_article.txt` files are created. Files only exist if scraping was successful.
-
----
-
-### Story 3.4: Implement Stage Testing Utility for Scraping
-
--   **User Story / Goal:** As a developer, I want a separate script/command to test the article scraping logic using HN story data from local files, allowing independent testing and debugging of the scraper.
--   **Detailed Requirements:**
-    -   Create a new standalone script file: `src/stages/scrape_articles.ts`.
-    -   Import necessary modules: `fs`, `path`, `logger`, `config`, `scrapeArticle`.
-    -   The script should:
-        -   Initialize the logger.
-        -   Load configuration (to get `OUTPUT_DIR_PATH`).
-        -   Determine the target date-stamped directory path (e.g., `${OUTPUT_DIR_PATH}/YYYY-MM-DD`, using the current date or potentially an optional CLI argument). Ensure this directory exists.
-        -   Read the directory contents and identify all `{storyId}_data.json` files.
-        -   For each `_data.json` file found:
-            -   Read and parse the JSON content.
-            -   Extract the `storyId` and `url`.
-            -   If a valid `url` exists, call `await scrapeArticle(url)`.
-            -   If scraping succeeds (returns text), save the text to `{storyId}_article.txt` in the same directory (using logic from Story 3.3). Overwrite if the file exists.
-            -   Log the progress and outcome (skip/success/fail) for each story processed.
-    -   Add a new script command to `package.json`: `"stage:scrape": "ts-node src/stages/scrape_articles.ts"`. Consider adding argument parsing later if needed to specify a date/directory.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/scrape_articles.ts` exists.
-    -   AC2: The script `stage:scrape` is defined in `package.json`.
-    -   AC3: Running `npm run stage:scrape` (assuming a directory with `_data.json` files exists from a previous `stage:fetch` run) reads these files.
-    -   AC4: The script calls `scrapeArticle` for stories with valid URLs found in the JSON files.
-    -   AC5: The script creates/updates `{storyId}_article.txt` files in the target directory corresponding to successfully scraped articles.
-    -   AC6: The script logs its actions (reading files, attempting scraping, saving results) for each story ID processed.
-    -   AC7: The script operates solely based on local `_data.json` files and fetching from external article URLs; it does not call the Algolia HN API.
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 3     | 2-pm           |
-
-# Epic 4 File
-
-# Epic 4: LLM Summarization & Persistence
-
-**Goal:** Integrate with the configured local Ollama instance to generate summaries for successfully scraped article text and fetched comments. Persist these summaries locally. Implement a stage testing utility for summarization.
-
-## Story List
-
-### Story 4.1: Implement Ollama Client Module
-
--   **User Story / Goal:** As a developer, I want a client module to interact with the configured Ollama API endpoint via HTTP, handling requests and responses for text generation, so that summaries can be generated programmatically.
--   **Detailed Requirements:**
-    -   **Prerequisite:** Ensure a local Ollama instance is installed and running, accessible via the URL defined in `.env` (`OLLAMA_ENDPOINT_URL`), and that the model specified in `.env` (`OLLAMA_MODEL`) has been downloaded (e.g., via `ollama pull model_name`). Instructions for this setup should be in the project README.
-    -   Create a new module: `src/clients/ollamaClient.ts`.
-    -   Implement an async function `generateSummary(promptTemplate: string, content: string): Promise<string | null>`. *(Note: Parameter name changed for clarity)*
-    -   Add configuration variables `OLLAMA_ENDPOINT_URL` (e.g., `http://localhost:11434`) and `OLLAMA_MODEL` (e.g., `llama3`) to `.env.example`. Ensure they are loaded via the config module (`src/utils/config.ts`). Update local `.env` with actual values. Add optional `OLLAMA_TIMEOUT_MS` to `.env.example` with a default like `120000`.
-    -   Inside `generateSummary`:
-        -   Construct the full prompt string using the `promptTemplate` and the provided `content` (e.g., replacing a placeholder like `{Content Placeholder}` in the template, or simple concatenation if templates are basic).
-        -   Construct the Ollama API request payload (JSON): `{ model: configured_model, prompt: full_prompt, stream: false }`. Refer to Ollama `/api/generate` documentation and `docs/data-models.md`.
-        -   Use native `Workspace` to send a POST request to the configured Ollama endpoint + `/api/generate`. Set appropriate headers (`Content-Type: application/json`). Use the configured `OLLAMA_TIMEOUT_MS` or a reasonable default (e.g., 2 minutes).
-        -   Handle `Workspace` errors (network, timeout) using `try...catch`.
-        -   Check `response.ok`. If not OK, log the status/error and return `null`.
-        -   Parse the JSON response from Ollama. Extract the generated text (typically in the `response` field). Refer to `docs/data-models.md`.
-        -   Check for potential errors within the Ollama response structure itself (e.g., an `error` field).
-        -   Return the extracted summary string on success. Return `null` on any failure.
-        -   Log key events: initiating request (mention model), receiving response, success, failure reasons, potentially request/response time using the logger.
-    -   Define necessary TypeScript types for the Ollama request payload and expected response structure in `src/types/ollama.ts` (referenced in `docs/data-models.md`).
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `ollamaClient.ts` module exists and exports `generateSummary`.
-    -   AC2: `OLLAMA_ENDPOINT_URL` and `OLLAMA_MODEL` are defined in `.env.example`, loaded via config, and used by the client. Optional `OLLAMA_TIMEOUT_MS` is handled.
-    -   AC3: `generateSummary` sends a correctly formatted POST request (model, full prompt based on template and content, stream:false) to the configured Ollama endpoint/path using native `Workspace`.
-    -   AC4: Network errors, timeouts, and non-OK API responses are handled gracefully, logged, and result in a `null` return (given the Prerequisite Ollama service is running).
-    -   AC5: A successful Ollama response is parsed correctly, the generated text is extracted, and returned as a string.
-    * AC6: Unexpected Ollama response formats or internal errors (e.g., `{"error": "..."}`) are handled, logged, and result in a `null` return.
-    * AC7: Logs provide visibility into the client's interaction with the Ollama API.
-
----
-
-### Story 4.2: Define Summarization Prompts
-
-* **User Story / Goal:** As a developer, I want standardized base prompts for generating article summaries and HN discussion summaries documented centrally, ensuring consistent instructions are sent to the LLM.
-* **Detailed Requirements:**
-    * Define two standardized base prompts (`ARTICLE_SUMMARY_PROMPT`, `DISCUSSION_SUMMARY_PROMPT`) **and document them in `docs/prompts.md`**.
-    * Ensure these prompts are accessible within the application code, for example, by defining them as exported constants in a dedicated module like `src/utils/prompts.ts`, which reads from or mirrors the content in `docs/prompts.md`.
-* **Acceptance Criteria (ACs):**
-    * AC1: The `ARTICLE_SUMMARY_PROMPT` text is defined in `docs/prompts.md` with appropriate instructional content.
-    * AC2: The `DISCUSSION_SUMMARY_PROMPT` text is defined in `docs/prompts.md` with appropriate instructional content.
-    * AC3: The prompt texts documented in `docs/prompts.md` are available as constants or variables within the application code (e.g., via `src/utils/prompts.ts`) for use by the Ollama client integration.
-
----
-
-### Story 4.3: Integrate Summarization into Main Workflow
-
-* **User Story / Goal:** As a developer, I want to integrate the Ollama client into the main workflow to generate summaries for each story's scraped article text (if available) and fetched comments, using centrally defined prompts and handling potential comment length limits.
-* **Detailed Requirements:**
-    * Modify the main execution flow in `src/index.ts` or `src/core/pipeline.ts`.
-    * Import `ollamaClient.generateSummary` and the prompt constants/variables (e.g., from `src/utils/prompts.ts`, which reflect `docs/prompts.md`).
-    * Load the optional `MAX_COMMENT_CHARS_FOR_SUMMARY` configuration value from `.env` via the config utility.
-    * Within the main loop iterating through stories (after article scraping/persistence in Epic 3):
-    * **Article Summary Generation:**
-        * Check if the `story` object has non-null `articleContent`.
-        * If yes: log "Attempting article summarization for story {storyId}", call `await generateSummary(ARTICLE_SUMMARY_PROMPT, story.articleContent)`, store the result (string or null) as `story.articleSummary`, log success/failure.
-        * If no: set `story.articleSummary = null`, log "Skipping article summarization: No content".
-    * **Discussion Summary Generation:**
-        * Check if the `story` object has a non-empty `comments` array.
-        * If yes:
-            * Format the `story.comments` array into a single text block suitable for the LLM prompt (e.g., concatenating `comment.text` with separators like `---`).
-            * **Check truncation limit:** If `MAX_COMMENT_CHARS_FOR_SUMMARY` is configured to a positive number and the `formattedCommentsText` length exceeds it, truncate `formattedCommentsText` to the limit and log a warning: "Comment text truncated to {limit} characters for summarization for story {storyId}".
-            * Log "Attempting discussion summarization for story {storyId}".
-            * Call `await generateSummary(DISCUSSION_SUMMARY_PROMPT, formattedCommentsText)`. *(Pass the potentially truncated text)*
-            * Store the result (string or null) as `story.discussionSummary`. Log success/failure.
-        * If no: set `story.discussionSummary = null`, log "Skipping discussion summarization: No comments".
-* **Acceptance Criteria (ACs):**
-    * AC1: Running `npm run dev` executes steps from Epics 1-3, then attempts summarization using the Ollama client.
-    * AC2: Article summary is attempted only if `articleContent` exists for a story.
-    * AC3: Discussion summary is attempted only if `comments` exist for a story.
-    * AC4: `generateSummary` is called with the correct prompts (sourced consistently with `docs/prompts.md`) and corresponding content (article text or formatted/potentially truncated comments).
-    * AC5: If `MAX_COMMENT_CHARS_FOR_SUMMARY` is set and comment text exceeds it, the text passed to `generateSummary` is truncated, and a warning is logged.
-    * AC6: Logs clearly indicate the start, success, or failure (including null returns from the client) for both article and discussion summarization attempts per story.
-    * AC7: Story objects in memory now contain `articleSummary` (string/null) and `discussionSummary` (string/null) properties.
-
----
-
-### Story 4.4: Persist Generated Summaries Locally
-
-*(No changes needed for this story based on recent decisions)*
-
--   **User Story / Goal:** As a developer, I want to save the generated article and discussion summaries (or null placeholders) to a local JSON file for each story, making them available for the email assembly stage.
--   **Detailed Requirements:**
-    -   Define the structure for the summary output file: `{storyId}_summary.json`. Content example: `{ "storyId": "...", "articleSummary": "...", "discussionSummary": "...", "summarizedAt": "ISO_TIMESTAMP" }`. Note that `articleSummary` and `discussionSummary` can be `null`.
-    -   Import `fs` and `path` in `src/index.ts` or `src/core/pipeline.ts` if needed.
-    -   In the main workflow loop, after *both* summarization attempts (article and discussion) for a story are complete:
-        -   Create a summary result object containing `storyId`, `articleSummary` (string or null), `discussionSummary` (string or null), and the current ISO timestamp (`new Date().toISOString()`). Add this timestamp to the in-memory `story` object as well (`story.summarizedAt`).
-        -   Get the full path to the date-stamped output directory.
-        -   Construct the filename: `{storyId}_summary.json`.
-        -   Construct the full file path using `path.join()`.
-        -   Serialize the summary result object to JSON (`JSON.stringify(..., null, 2)`).
-        -   Use `fs.writeFileSync` to save the JSON to the file, wrapping in `try...catch`.
-        -   Log the successful saving of the summary file or any file writing errors.
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory contains 10 files named `{storyId}_summary.json`.
-    -   AC2: Each `_summary.json` file contains valid JSON adhering to the defined structure.
-    -   AC3: The `articleSummary` field contains the generated summary string if successful, otherwise `null`.
-    -   AC4: The `discussionSummary` field contains the generated summary string if successful, otherwise `null`.
-    -   AC5: A valid ISO timestamp is present in the `summarizedAt` field.
-    -   AC6: Logs confirm successful writing of each summary file or report file system errors.
-
----
-
-### Story 4.5: Implement Stage Testing Utility for Summarization
-
-*(Changes needed to reflect prompt sourcing and optional truncation)*
-
-* **User Story / Goal:** As a developer, I want a separate script/command to test the LLM summarization logic using locally persisted data (HN comments, scraped article text), allowing independent testing of prompts and Ollama interaction.
-* **Detailed Requirements:**
-    * Create a new standalone script file: `src/stages/summarize_content.ts`.
-    * Import necessary modules: `fs`, `path`, `logger`, `config`, `ollamaClient`, prompt constants (e.g., from `src/utils/prompts.ts`).
-    * The script should:
-        * Initialize logger, load configuration (Ollama endpoint/model, output dir, **optional `MAX_COMMENT_CHARS_FOR_SUMMARY`**).
-        * Determine target date-stamped directory path.
-        * Find all `{storyId}_data.json` files in the directory.
-        * For each `storyId` found:
-            * Read `{storyId}_data.json` to get comments. Format them into a single text block.
-            * *Attempt* to read `{storyId}_article.txt`. Handle file-not-found gracefully. Store content or null.
-            * Call `ollamaClient.generateSummary` for article text (if not null) using `ARTICLE_SUMMARY_PROMPT`.
-            * **Apply truncation logic:** If comments exist, check `MAX_COMMENT_CHARS_FOR_SUMMARY` and truncate the formatted comment text block if needed, logging a warning.
-            * Call `ollamaClient.generateSummary` for formatted comments (if comments exist) using `DISCUSSION_SUMMARY_PROMPT` *(passing potentially truncated text)*.
-            * Construct the summary result object (with summaries or nulls, and timestamp).
-            * Save the result object to `{storyId}_summary.json` in the same directory (using logic from Story 4.4), overwriting if exists.
-            * Log progress (reading files, calling Ollama, truncation warnings, saving results) for each story ID.
-    * Add script to `package.json`: `"stage:summarize": "ts-node src/stages/summarize_content.ts"`.
-* **Acceptance Criteria (ACs):**
-    * AC1: The file `src/stages/summarize_content.ts` exists.
-    * AC2: The script `stage:summarize` is defined in `package.json`.
-    * AC3: Running `npm run stage:summarize` (after `stage:fetch` and `stage:scrape` runs) reads `_data.json` and attempts to read `_article.txt` files from the target directory.
-    * AC4: The script calls the `ollamaClient` with correct prompts (sourced consistently with `docs/prompts.md`) and content derived *only* from the local files (requires Ollama service running per Story 4.1 prerequisite).
-    * AC5: If `MAX_COMMENT_CHARS_FOR_SUMMARY` is set and applicable, comment text is truncated before calling the client, and a warning is logged.
-    * AC6: The script creates/updates `{storyId}_summary.json` files in the target directory reflecting the results of the Ollama calls (summaries or nulls).
-    * AC7: Logs show the script processing each story ID found locally, interacting with Ollama, and saving results.
-    * AC8: The script does not call Algolia API or the article scraper module.
-
-## Change Log
-
-| Change                      | Date         | Version | Description                          | Author         |
-| --------------------------- | ------------ | ------- | ------------------------------------ | -------------- |
-| Integrate prompts.md refs   | 2025-05-04   | 0.3     | Updated stories 4.2, 4.3, 4.5        | 3-Architect    |
-| Added Ollama Prereq Note    | 2025-05-04   | 0.2     | Added note about local Ollama setup  | 2-pm           |
-| Initial Draft               | 2025-05-04   | 0.1     | First draft of Epic 4                | 2-pm           |
-
-# Epic 5 File
-
-# Epic 5: Digest Assembly & Email Dispatch
-
-**Goal:** Assemble the collected story data and summaries from local files, format them into a readable HTML email digest, and send the email using Nodemailer with configured credentials. Implement a stage testing utility for emailing with a dry-run option.
-
-## Story List
-
-### Story 5.1: Implement Email Content Assembler
-
--   **User Story / Goal:** As a developer, I want a module that reads the persisted story metadata (`_data.json`) and summaries (`_summary.json`) from a specified directory, consolidating the necessary information needed to render the email digest.
--   **Detailed Requirements:**
-    -   Create a new module: `src/email/contentAssembler.ts`.
-    -   Define a TypeScript type/interface `DigestData` representing the data needed per story for the email template: `{ storyId: string, title: string, hnUrl: string, articleUrl: string | null, articleSummary: string | null, discussionSummary: string | null }`.
-    -   Implement an async function `assembleDigestData(dateDirPath: string): Promise<DigestData[]>`.
-    -   The function should:
-        -   Use Node.js `fs` to read the contents of the `dateDirPath`.
-        -   Identify all files matching the pattern `{storyId}_data.json`.
-        -   For each `storyId` found:
-            -   Read and parse the `{storyId}_data.json` file. Extract `title`, `hnUrl`, and `url` (use as `articleUrl`). Handle potential file read/parse errors gracefully (log and skip story).
-            -   Attempt to read and parse the corresponding `{storyId}_summary.json` file. Handle file-not-found or parse errors gracefully (treat `articleSummary` and `discussionSummary` as `null`).
-            -   Construct a `DigestData` object for the story, including the extracted metadata and summaries (or nulls).
-        -   Collect all successfully constructed `DigestData` objects into an array.
-        -   Return the array. It should ideally contain 10 items if all previous stages succeeded.
-    -   Log progress (e.g., "Assembling digest data from directory...", "Processing story {storyId}...") and any errors encountered during file processing using the logger.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `contentAssembler.ts` module exists and exports `assembleDigestData` and the `DigestData` type.
-    -   AC2: `assembleDigestData` correctly reads `_data.json` files from the provided directory path.
-    -   AC3: It attempts to read corresponding `_summary.json` files, correctly handling cases where the summary file might be missing or unparseable (resulting in null summaries for that story).
-    -   AC4: The function returns a promise resolving to an array of `DigestData` objects, populated with data extracted from the files.
-    -   AC5: Errors during file reading or JSON parsing are logged, and the function returns data for successfully processed stories.
-
----
-
-### Story 5.2: Create HTML Email Template & Renderer
-
--   **User Story / Goal:** As a developer, I want a basic HTML email template and a function to render it with the assembled digest data, producing the final HTML content for the email body.
--   **Detailed Requirements:**
-    -   Define the HTML structure. This can be done using template literals within a function or potentially using a simple template file (e.g., `src/email/templates/digestTemplate.html`) and `fs.readFileSync`. Template literals are simpler for MVP.
-    -   Create a function `renderDigestHtml(data: DigestData[], digestDate: string): string` (e.g., in `src/email/contentAssembler.ts` or a new `templater.ts`).
-    -   The function should generate an HTML string with:
-        -   A suitable title in the body (e.g., `<h1>Hacker News Top 10 Summaries for ${digestDate}</h1>`).
-        -   A loop through the `data` array.
-        -   For each `story` in `data`:
-            -   Display `<h2><a href="${story.articleUrl || story.hnUrl}">${story.title}</a></h2>`.
-            -   Display `<p><a href="${story.hnUrl}">View HN Discussion</a></p>`.
-            -   Conditionally display `<h3>Article Summary</h3><p>${story.articleSummary}</p>` *only if* `story.articleSummary` is not null/empty.
-            -   Conditionally display `<h3>Discussion Summary</h3><p>${story.discussionSummary}</p>` *only if* `story.discussionSummary` is not null/empty.
-            -   Include a separator (e.g., `<hr style="margin-top: 20px; margin-bottom: 20px;">`).
-    -   Use basic inline CSS for minimal styling (margins, etc.) to ensure readability. Avoid complex layouts.
-    -   Return the complete HTML document as a string.
--   **Acceptance Criteria (ACs):**
-    -   AC1: A function `renderDigestHtml` exists that accepts the digest data array and a date string.
-    -   AC2: The function returns a single, complete HTML string.
-    -   AC3: The generated HTML includes a title with the date and correctly iterates through the story data.
-    -   AC4: For each story, the HTML displays the linked title, HN link, and conditionally displays the article and discussion summaries with headings.
-    -   AC5: Basic separators and margins are used for readability. The HTML is simple and likely to render reasonably in most email clients.
-
----
-
-### Story 5.3: Implement Nodemailer Email Sender
-
--   **User Story / Goal:** As a developer, I want a module to send the generated HTML email using Nodemailer, configured with credentials stored securely in the environment file.
--   **Detailed Requirements:**
-    -   Add Nodemailer dependencies: `npm install nodemailer @types/nodemailer --save-prod`.
-    -   Add required configuration variables to `.env.example` (and local `.env`): `EMAIL_HOST`, `EMAIL_PORT` (e.g., 587), `EMAIL_SECURE` (e.g., `false` for STARTTLS on 587, `true` for 465), `EMAIL_USER`, `EMAIL_PASS`, `EMAIL_FROM` (e.g., `"Your Name <you@example.com>"`), `EMAIL_RECIPIENTS` (comma-separated list).
-    -   Create a new module: `src/email/emailSender.ts`.
-    -   Implement an async function `sendDigestEmail(subject: string, htmlContent: string): Promise<boolean>`.
-    -   Inside the function:
-        -   Load the `EMAIL_*` variables from the config module.
-        -   Create a Nodemailer transporter using `nodemailer.createTransport` with the loaded config (host, port, secure flag, auth: { user, pass }).
-        -   Verify transporter configuration using `transporter.verify()` (optional but recommended). Log verification success/failure.
-        -   Parse the `EMAIL_RECIPIENTS` string into an array or comma-separated string suitable for the `to` field.
-        -   Define the `mailOptions`: `{ from: EMAIL_FROM, to: parsedRecipients, subject: subject, html: htmlContent }`.
-        -   Call `await transporter.sendMail(mailOptions)`.
-        -   If `sendMail` succeeds, log the success message including the `messageId` from the result. Return `true`.
-        -   If `sendMail` fails (throws error), log the error using the logger. Return `false`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: `nodemailer` and `@types/nodemailer` dependencies are added.
-    -   AC2: `EMAIL_*` variables are defined in `.env.example` and loaded from config.
-    -   AC3: `emailSender.ts` module exists and exports `sendDigestEmail`.
-    -   AC4: `sendDigestEmail` correctly creates a Nodemailer transporter using configuration from `.env`. Transporter verification is attempted (optional AC).
-    -   AC5: The `to` field is correctly populated based on `EMAIL_RECIPIENTS`.
-    -   AC6: `transporter.sendMail` is called with correct `from`, `to`, `subject`, and `html` options.
-    -   AC7: Email sending success (including message ID) or failure is logged clearly.
-    -   AC8: The function returns `true` on successful sending, `false` otherwise.
-
----
-
-### Story 5.4: Integrate Email Assembly and Sending into Main Workflow
-
--   **User Story / Goal:** As a developer, I want the main application workflow (`src/index.ts`) to orchestrate the final steps: assembling digest data, rendering the HTML, and triggering the email send after all previous stages are complete.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts`.
-    -   Import `assembleDigestData`, `renderDigestHtml`, `sendDigestEmail`.
-    -   Execute these steps *after* the main loop (where stories are fetched, scraped, summarized, and persisted) completes:
-        -   Log "Starting final digest assembly and email dispatch...".
-        -   Determine the path to the current date-stamped output directory.
-        -   Call `const digestData = await assembleDigestData(dateDirPath)`.
-        -   Check if `digestData` array is not empty.
-            -   If yes:
-                -   Get the current date string (e.g., 'YYYY-MM-DD').
-                -   `const htmlContent = renderDigestHtml(digestData, currentDate)`.
-                -   `const subject = \`BMad Hacker Daily Digest - ${currentDate}\``.
-                -   `const emailSent = await sendDigestEmail(subject, htmlContent)`.
-                -   Log the final outcome based on `emailSent` ("Digest email sent successfully." or "Failed to send digest email.").
-            -   If no (`digestData` is empty or assembly failed):
-                -   Log an error: "Failed to assemble digest data or no data found. Skipping email."
-        -   Log "BMad Hacker Daily Digest process finished."
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes all stages (Epics 1-4) and then proceeds to email assembly and sending.
-    -   AC2: `assembleDigestData` is called correctly with the output directory path after other processing is done.
-    -   AC3: If data is assembled, `renderDigestHtml` and `sendDigestEmail` are called with the correct data, subject, and HTML.
-    -   AC4: The final success or failure of the email sending step is logged.
-    -   AC5: If `assembleDigestData` returns no data, email sending is skipped, and an appropriate message is logged.
-    -   AC6: The application logs a final completion message.
-
----
-
-### Story 5.5: Implement Stage Testing Utility for Emailing
-
--   **User Story / Goal:** As a developer, I want a separate script/command to test the email assembly, rendering, and sending logic using persisted local data, including a crucial `--dry-run` option to prevent accidental email sending during tests.
--   **Detailed Requirements:**
-    -   Add `yargs` dependency for argument parsing: `npm install yargs @types/yargs --save-dev`.
-    -   Create a new standalone script file: `src/stages/send_digest.ts`.
-    -   Import necessary modules: `fs`, `path`, `logger`, `config`, `assembleDigestData`, `renderDigestHtml`, `sendDigestEmail`, `yargs`.
-    -   Use `yargs` to parse command-line arguments, specifically looking for a `--dry-run` boolean flag (defaulting to `false`). Allow an optional argument for specifying the date-stamped directory, otherwise default to current date.
-    -   The script should:
-        -   Initialize logger, load config.
-        -   Determine the target date-stamped directory path (from arg or default). Log the target directory.
-        -   Call `await assembleDigestData(dateDirPath)`.
-        -   If data is assembled and not empty:
-            -   Determine the date string for the subject/title.
-            -   Call `renderDigestHtml(digestData, dateString)` to get HTML.
-            -   Construct the subject string.
-            -   Check the `dryRun` flag:
-                -   If `true`: Log "DRY RUN enabled. Skipping actual email send.". Log the subject. Save the `htmlContent` to a file in the target directory (e.g., `_digest_preview.html`). Log that the preview file was saved.
-                -   If `false`: Log "Live run: Attempting to send email...". Call `await sendDigestEmail(subject, htmlContent)`. Log success/failure based on the return value.
-        -   If data assembly fails or is empty, log the error.
-    -   Add script to `package.json`: `"stage:email": "ts-node src/stages/send_digest.ts --"`. The `--` allows passing arguments like `--dry-run`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/send_digest.ts` exists. `yargs` dependency is added.
-    -   AC2: The script `stage:email` is defined in `package.json` allowing arguments.
-    -   AC3: Running `npm run stage:email -- --dry-run` reads local data, renders HTML, logs the intent, saves `_digest_preview.html` locally, and does *not* call `sendDigestEmail`.
-    -   AC4: Running `npm run stage:email` (without `--dry-run`) reads local data, renders HTML, and *does* call `sendDigestEmail`, logging the outcome.
-    -   AC5: The script correctly identifies and acts upon the `--dry-run` flag.
-    -   AC6: Logs clearly distinguish between dry runs and live runs and report success/failure.
-    -   AC7: The script operates using only local files and the email configuration/service; it does not invoke prior pipeline stages (Algolia, scraping, Ollama).
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 5     | 2-pm           |
-
-# END EPIC FILES

V2-FULL-DEMO-WALKTHROUGH/data-models.md

@@ -1,202 +0,0 @@
-# BMad Hacker Daily Digest Data Models
-
-This document defines the core data structures used within the application, the format of persisted data files, and relevant API payload schemas. These types would typically reside in `src/types/`.
-
-## 1. Core Application Entities / Domain Objects (In-Memory)
-
-These TypeScript interfaces represent the main data objects manipulated during the pipeline execution.
-
-### `Comment`
-
-- **Description:** Represents a single Hacker News comment fetched from the Algolia API.
-- **Schema / Interface Definition (`src/types/hn.ts`):**
-  ```typescript
-  export interface Comment {
-    commentId: string; // Unique identifier (from Algolia objectID)
-    commentText: string | null; // Text content of the comment (nullable from API)
-    author: string | null; // Author's HN username (nullable from API)
-    createdAt: string; // ISO 8601 timestamp string of comment creation
-  }
-  ```
-
-### `Story`
-
-- **Description:** Represents a Hacker News story, initially fetched from Algolia and progressively augmented with comments, scraped content, and summaries during pipeline execution.
-- **Schema / Interface Definition (`src/types/hn.ts`):**
-
-  ```typescript
-  import { Comment } from "./hn";
-
-  export interface Story {
-    storyId: string; // Unique identifier (from Algolia objectID)
-    title: string; // Story title
-    articleUrl: string | null; // URL of the linked article (can be null from API)
-    hnUrl: string; // URL to the HN discussion page (constructed)
-    points?: number; // HN points (optional)
-    numComments?: number; // Number of comments reported by API (optional)
-
-    // Data added during pipeline execution
-    comments: Comment[]; // Fetched comments [Added in Epic 2]
-    articleContent: string | null; // Scraped article text [Added in Epic 3]
-    articleSummary: string | null; // Generated article summary [Added in Epic 4]
-    discussionSummary: string | null; // Generated discussion summary [Added in Epic 4]
-    fetchedAt: string; // ISO 8601 timestamp when story/comments were fetched [Added in Epic 2]
-    summarizedAt?: string; // ISO 8601 timestamp when summaries were generated [Added in Epic 4]
-  }
-  ```
-
-### `DigestData`
-
-- **Description:** Represents the consolidated data needed for a single story when assembling the final email digest. Created by reading persisted files.
-- **Schema / Interface Definition (`src/types/email.ts`):**
-  ```typescript
-  export interface DigestData {
-    storyId: string;
-    title: string;
-    hnUrl: string;
-    articleUrl: string | null;
-    articleSummary: string | null;
-    discussionSummary: string | null;
-  }
-  ```
-
-## 2. API Payload Schemas
-
-These describe the relevant parts of request/response payloads for external APIs.
-
-### Algolia HN API - Story Response Subset
-
-- **Description:** Relevant fields extracted from the Algolia HN Search API response for front-page stories.
-- **Schema (Conceptual JSON):**
-  ```json
-  {
-    "hits": [
-      {
-        "objectID": "string", // Used as storyId
-        "title": "string",
-        "url": "string | null", // Used as articleUrl
-        "points": "number",
-        "num_comments": "number"
-        // ... other fields ignored
-      }
-      // ... more hits (stories)
-    ]
-    // ... other top-level fields ignored
-  }
-  ```
-
-### Algolia HN API - Comment Response Subset
-
-- **Description:** Relevant fields extracted from the Algolia HN Search API response for comments associated with a story.
-- **Schema (Conceptual JSON):**
-  ```json
-  {
-    "hits": [
-      {
-        "objectID": "string", // Used as commentId
-        "comment_text": "string | null",
-        "author": "string | null",
-        "created_at": "string" // ISO 8601 format
-        // ... other fields ignored
-      }
-      // ... more hits (comments)
-    ]
-    // ... other top-level fields ignored
-  }
-  ```
-
-### Ollama `/api/generate` Request
-
-- **Description:** Payload sent to the local Ollama instance to generate a summary.
-- **Schema (`src/types/ollama.ts` or inline):**
-  ```typescript
-  export interface OllamaGenerateRequest {
-    model: string; // e.g., "llama3" (from config)
-    prompt: string; // The full prompt including context
-    stream: false; // Required to be false for single response
-    // system?: string; // Optional system prompt (if used)
-    // options?: Record<string, any>; // Optional generation parameters
-  }
-  ```
-
-### Ollama `/api/generate` Response
-
-- **Description:** Relevant fields expected from the Ollama API response when `stream: false`.
-- **Schema (`src/types/ollama.ts` or inline):**
-  ```typescript
-  export interface OllamaGenerateResponse {
-    model: string;
-    created_at: string; // ISO 8601 timestamp
-    response: string; // The generated summary text
-    done: boolean; // Should be true if stream=false and generation succeeded
-    // Optional fields detailing context, timings, etc. are ignored for MVP
-    // total_duration?: number;
-    // load_duration?: number;
-    // prompt_eval_count?: number;
-    // prompt_eval_duration?: number;
-    // eval_count?: number;
-    // eval_duration?: number;
-  }
-  ```
-  _(Note: Error responses might have a different structure, e.g., `{ "error": "message" }`)_
-
-## 3. Database Schemas
-
-- **N/A:** This application does not use a database for MVP; data is persisted to the local filesystem.
-
-## 4. State File Schemas (Local Filesystem Persistence)
-
-These describe the format of files saved in the `output/YYYY-MM-DD/` directory.
-
-### `{storyId}_data.json`
-
-- **Purpose:** Stores fetched story metadata and associated comments.
-- **Format:** JSON
-- **Schema Definition (Matches `Story` type fields relevant at time of saving):**
-  ```json
-  {
-    "storyId": "string",
-    "title": "string",
-    "articleUrl": "string | null",
-    "hnUrl": "string",
-    "points": "number | undefined",
-    "numComments": "number | undefined",
-    "fetchedAt": "string", // ISO 8601 timestamp
-    "comments": [
-      // Array of Comment objects
-      {
-        "commentId": "string",
-        "commentText": "string | null",
-        "author": "string | null",
-        "createdAt": "string" // ISO 8601 timestamp
-      }
-      // ... more comments
-    ]
-  }
-  ```
-
-### `{storyId}_article.txt`
-
-- **Purpose:** Stores the successfully scraped plain text content of the linked article.
-- **Format:** Plain Text (`.txt`)
-- **Schema Definition:** N/A (Content is the raw extracted string). File only exists if scraping was successful.
-
-### `{storyId}_summary.json`
-
-- **Purpose:** Stores the generated article and discussion summaries.
-- **Format:** JSON
-- **Schema Definition:**
-  ```json
-  {
-    "storyId": "string",
-    "articleSummary": "string | null", // Null if scraping failed or summarization failed
-    "discussionSummary": "string | null", // Null if no comments or summarization failed
-    "summarizedAt": "string" // ISO 8601 timestamp
-  }
-  ```
-
-## Change Log
-
-| Change        | Date       | Version | Description                  | Author      |
-| ------------- | ---------- | ------- | ---------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Initial draft based on Epics | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/data-models.txt

@@ -1,202 +0,0 @@
-# BMad Hacker Daily Digest Data Models
-
-This document defines the core data structures used within the application, the format of persisted data files, and relevant API payload schemas. These types would typically reside in `src/types/`.
-
-## 1. Core Application Entities / Domain Objects (In-Memory)
-
-These TypeScript interfaces represent the main data objects manipulated during the pipeline execution.
-
-### `Comment`
-
-- **Description:** Represents a single Hacker News comment fetched from the Algolia API.
-- **Schema / Interface Definition (`src/types/hn.ts`):**
-  ```typescript
-  export interface Comment {
-    commentId: string; // Unique identifier (from Algolia objectID)
-    commentText: string | null; // Text content of the comment (nullable from API)
-    author: string | null; // Author's HN username (nullable from API)
-    createdAt: string; // ISO 8601 timestamp string of comment creation
-  }
-  ```
-
-### `Story`
-
-- **Description:** Represents a Hacker News story, initially fetched from Algolia and progressively augmented with comments, scraped content, and summaries during pipeline execution.
-- **Schema / Interface Definition (`src/types/hn.ts`):**
-
-  ```typescript
-  import { Comment } from "./hn";
-
-  export interface Story {
-    storyId: string; // Unique identifier (from Algolia objectID)
-    title: string; // Story title
-    articleUrl: string | null; // URL of the linked article (can be null from API)
-    hnUrl: string; // URL to the HN discussion page (constructed)
-    points?: number; // HN points (optional)
-    numComments?: number; // Number of comments reported by API (optional)
-
-    // Data added during pipeline execution
-    comments: Comment[]; // Fetched comments [Added in Epic 2]
-    articleContent: string | null; // Scraped article text [Added in Epic 3]
-    articleSummary: string | null; // Generated article summary [Added in Epic 4]
-    discussionSummary: string | null; // Generated discussion summary [Added in Epic 4]
-    fetchedAt: string; // ISO 8601 timestamp when story/comments were fetched [Added in Epic 2]
-    summarizedAt?: string; // ISO 8601 timestamp when summaries were generated [Added in Epic 4]
-  }
-  ```
-
-### `DigestData`
-
-- **Description:** Represents the consolidated data needed for a single story when assembling the final email digest. Created by reading persisted files.
-- **Schema / Interface Definition (`src/types/email.ts`):**
-  ```typescript
-  export interface DigestData {
-    storyId: string;
-    title: string;
-    hnUrl: string;
-    articleUrl: string | null;
-    articleSummary: string | null;
-    discussionSummary: string | null;
-  }
-  ```
-
-## 2. API Payload Schemas
-
-These describe the relevant parts of request/response payloads for external APIs.
-
-### Algolia HN API - Story Response Subset
-
-- **Description:** Relevant fields extracted from the Algolia HN Search API response for front-page stories.
-- **Schema (Conceptual JSON):**
-  ```json
-  {
-    "hits": [
-      {
-        "objectID": "string", // Used as storyId
-        "title": "string",
-        "url": "string | null", // Used as articleUrl
-        "points": "number",
-        "num_comments": "number"
-        // ... other fields ignored
-      }
-      // ... more hits (stories)
-    ]
-    // ... other top-level fields ignored
-  }
-  ```
-
-### Algolia HN API - Comment Response Subset
-
-- **Description:** Relevant fields extracted from the Algolia HN Search API response for comments associated with a story.
-- **Schema (Conceptual JSON):**
-  ```json
-  {
-    "hits": [
-      {
-        "objectID": "string", // Used as commentId
-        "comment_text": "string | null",
-        "author": "string | null",
-        "created_at": "string" // ISO 8601 format
-        // ... other fields ignored
-      }
-      // ... more hits (comments)
-    ]
-    // ... other top-level fields ignored
-  }
-  ```
-
-### Ollama `/api/generate` Request
-
-- **Description:** Payload sent to the local Ollama instance to generate a summary.
-- **Schema (`src/types/ollama.ts` or inline):**
-  ```typescript
-  export interface OllamaGenerateRequest {
-    model: string; // e.g., "llama3" (from config)
-    prompt: string; // The full prompt including context
-    stream: false; // Required to be false for single response
-    // system?: string; // Optional system prompt (if used)
-    // options?: Record<string, any>; // Optional generation parameters
-  }
-  ```
-
-### Ollama `/api/generate` Response
-
-- **Description:** Relevant fields expected from the Ollama API response when `stream: false`.
-- **Schema (`src/types/ollama.ts` or inline):**
-  ```typescript
-  export interface OllamaGenerateResponse {
-    model: string;
-    created_at: string; // ISO 8601 timestamp
-    response: string; // The generated summary text
-    done: boolean; // Should be true if stream=false and generation succeeded
-    // Optional fields detailing context, timings, etc. are ignored for MVP
-    // total_duration?: number;
-    // load_duration?: number;
-    // prompt_eval_count?: number;
-    // prompt_eval_duration?: number;
-    // eval_count?: number;
-    // eval_duration?: number;
-  }
-  ```
-  _(Note: Error responses might have a different structure, e.g., `{ "error": "message" }`)_
-
-## 3. Database Schemas
-
-- **N/A:** This application does not use a database for MVP; data is persisted to the local filesystem.
-
-## 4. State File Schemas (Local Filesystem Persistence)
-
-These describe the format of files saved in the `output/YYYY-MM-DD/` directory.
-
-### `{storyId}_data.json`
-
-- **Purpose:** Stores fetched story metadata and associated comments.
-- **Format:** JSON
-- **Schema Definition (Matches `Story` type fields relevant at time of saving):**
-  ```json
-  {
-    "storyId": "string",
-    "title": "string",
-    "articleUrl": "string | null",
-    "hnUrl": "string",
-    "points": "number | undefined",
-    "numComments": "number | undefined",
-    "fetchedAt": "string", // ISO 8601 timestamp
-    "comments": [
-      // Array of Comment objects
-      {
-        "commentId": "string",
-        "commentText": "string | null",
-        "author": "string | null",
-        "createdAt": "string" // ISO 8601 timestamp
-      }
-      // ... more comments
-    ]
-  }
-  ```
-
-### `{storyId}_article.txt`
-
-- **Purpose:** Stores the successfully scraped plain text content of the linked article.
-- **Format:** Plain Text (`.txt`)
-- **Schema Definition:** N/A (Content is the raw extracted string). File only exists if scraping was successful.
-
-### `{storyId}_summary.json`
-
-- **Purpose:** Stores the generated article and discussion summaries.
-- **Format:** JSON
-- **Schema Definition:**
-  ```json
-  {
-    "storyId": "string",
-    "articleSummary": "string | null", // Null if scraping failed or summarization failed
-    "discussionSummary": "string | null", // Null if no comments or summarization failed
-    "summarizedAt": "string" // ISO 8601 timestamp
-  }
-  ```
-
-## Change Log
-
-| Change        | Date       | Version | Description                  | Author      |
-| ------------- | ---------- | ------- | ---------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Initial draft based on Epics | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/demo.md

@@ -1,158 +0,0 @@
-# Demonstration of the Full BMad Workflow Agent Gem Usage
-
-**Welcome to the complete end-to-end walkthrough of the BMad Method V2!** This demonstration showcases the power of AI-assisted software development using a phased agent approach. You'll see how each specialized agent (BA, PM, Architect, PO/SM) contributes to the project lifecycle - from initial concept to implementation-ready plans.
-
-Each section includes links to **full Gemini interaction transcripts**, allowing you to witness the remarkable collaborative process between human and AI. The demo folder contains all output artifacts that flow between agents, creating a cohesive development pipeline.
-
-What makes this V2 methodology exceptional is how the agents work in **interactive phases**, pausing at key decision points for your input rather than dumping massive documents at once. This creates a truly collaborative experience where you shape the outcome while the AI handles the heavy lifting.
-
-Follow along from concept to code-ready project plan and see how this workflow transforms software development!
-
-## BA Brainstorming
-
-The following link shows the full chat thread with the BA demonstrating many features of this amazing agent. I started out not even knowing what to build, and it helped me ideate with the goal of something interesting for tutorial purposes, refine it, do some deep research (in thinking mode, I did not switch models), gave some great alternative details and ideas, prompted me section by section eventually to produce the brief. It worked amazingly well. You can read the full transcript and output here:
-
-https://gemini.google.com/share/fec063449737
-
-## PM Brainstorming (Oops it was not the PM LOL)
-
-I took the final output md brief with prompt for the PM at the end of the last chat and created a google doc to make it easier to share with the PM (I could have probably just pasted it into the new chat, but it's easier if I want to start over). In Google Docs it's so easy to just create a new doc, right click and select 'Paste from Markdown', then click in the title and it will automatically name and save it with the title of the document. I then started a chat with the 2-PM Gem, also in Gemini 2.5 Pro thinking mode by attaching the Google doc and telling it to reference the prompt. This is the transcript. I realized that I accidentally had pasted the BA prompt also into the PM prompt, so this actually ended up producing a pretty nicely refined brief 2.0 instead LOL
-
-https://g.co/gemini/share/3e09f04138f2
-
-So I took that output file and put it into the actual BA again to produce a new version with prompt as seen in [this file](final-brief-with-pm-prompt.txt) ([md version](final-brief-with-pm-prompt.md)).
-
-## PM Brainstorming Take 2
-
-I will be going forward with the rest of the process not use Google Docs even though it's preferred and instead attach txt attachments of previous phase documents, this is required or else the link will be un-sharable.
-
-Of note here is how I am not passive in this process and you should not be either - I looked at its proposed epics in its first PRD draft after answering the initial questions and spotting something really dumb, it had a final epic for doing file output and logging all the way at the end - when really this should be happening incrementally with each epic. The Architect or PO I hope would have caught this later and the PM might also if I let it get to the checklist phase, but if you can work with it you will have quicker results and better outcomes.
-
-Also notice, since we came to the PM with the amazing brief + prompt embedded in it - it only had like 1 question before producing the first draft - amazing!!!
-
-The PM did a great job of asking the right questions, and producing the [Draft PRD](prd.txt) ([md version](prd.md)), and each epic, [1](epic1.txt) ([md version](epic1.md)), [2](epic2.txt) ([md version](epic2.md)), [3](epic3.txt) ([md version](epic3.md)), [4](epic4.txt) ([md version](epic4.md)), [5](epic5.txt) ([md version](epic5.md)).
-
-The beauty of these new V2 Agents is they pause for you to answer questions or review the document generation section by section - this is so much better than receiving a massive document dump all at once and trying to take it all in. in between each piece you can ask questions or ask for changes - so easy - so powerful!
-
-After the drafts were done, it then ran the checklist - which is the other big game changer feature of the V2 BMAD Method. Waiting for the output final decision from the checklist run can be exciting haha!
-
-Getting that final PRD & EPIC VALIDATION SUMMARY and seeing it all passing is a great feeling.
-
-[Here is the full chat summary](https://g.co/gemini/share/abbdff18316b).
-
-## Architect (Terrible Architect - already fired and replaced in take 2)
-
-I gave the architect the drafted PRD and epics. I call them all still drafts because the architect or PO could still have some findings or updates - but hopefully not for this very simple project.
-
-I started off the fun with the architect by saying 'the prompt to respond to is in the PRD at the end in a section called 'Initial Architect Prompt' and we are in architecture creation mode - all PRD and epics planned by the PM are attached'
-
-NOTE - The architect just plows through and produces everything at once and runs the checklist - need to improve the gem and agent to be more workflow focused in a future update! Here is the [initial crap it produced](botched-architecture.md) - don't worry I fixed it, it's much better in take 2!
-
-There is one thing that is a pain with both Gemini and ChatGPT - output of markdown with internal markdown or mermaid sections screws up the output formatting where it thinks the start of inner markdown is the end to its total output block - this is because the reality is everything you are seeing in response from the LLM is already markdown, just being rendered by the UI! So the fix is simple - I told it "Since you already default respond in markdown - can you not use markdown blocks and just give the document as standard chat output" - this worked perfect, and nested markdown was properly still wrapped!
-
-I updated the agent at this point to fix this output formatting for all gems and adjusted the architect to progress document by document prompting in between to get clarifications, suggest tradeoffs or what it put in place, etc., and then confirm with me if I like all the draft docs we got 1 by 1 and then confirm I am ready for it to run the checklist assessment. Improved usage of this is shown in the next section Architect Take 2 next.
-
-If you want to see my annoying chat with this lame architect gem that is now much better - [here you go](https://g.co/gemini/share/0a029a45d70b).
-
-{I corrected the interaction model and added YOLO mode to the architect, and tried a fresh start with the improved gem in take 2.}
-
-## Architect Take 2 (Our amazing new architect)
-
-Same initial prompt as before but with the new and improved architect! I submitted that first prompt again and waited in anticipation to see if it would go insane again.
-
-So far success - it confirmed it was not to go all YOLO on me!
-
-Our new architect is SO much better, and also fun '(Pirate voice) Aye, yargs be a fine choice, matey!' - firing the previous architect was a great decision!
-
-It gave us our [tech stack](tech-stack.txt) ([md version](tech-stack.md)) - the tech-stack looks great, it did not produce wishy-washy ambiguous selections like the previous architect would!
-
-I did mention we should call out the specific decisions to not use axios and dotenv so the LLM would not try to use it later. Also I suggested adding Winston and it helped me know it had a better simpler idea for MVP for file logging! Such a great helper now! I really hope I never see that old V1 architect again, I don't think he was at all qualified to even mop the floors.
-
-When I got the [project structure document](project-structure.txt) ([md version](project-structure.md)), I was blown away - you will see in the chat transcript how it was formatted - I was able to copy the whole response put it in an md file and no more issues with sub sections, just removed the text basically saying here is your file! Once confirmed it was md, I changed it to txt for pass off later potentially to the PO.
-
-Here are the remaining docs it did with me one at a time before running the checklist:
-
-- [Architecture](architecture.txt) ([md version](architecture.md)) - the 'Core Workflow / Sequence Diagram (Main Pipeline)' diagram was impressive - one other diagram had a mermaid bugs - I updated the agent and fixed the bugs, these should hopefully not occur again - it was the most common LLM mermaid bug I have gotten across models
-- [Data Models](data-models.txt) ([md version](data-models.md)) - another complex file easy to just get the end of message ... copy the response and paste into markdown, perfect result!
-- [API Reference](api-reference.txt) ([md version](api-reference.md))
-- [Env Vars](environment-vars.txt) ([md version](environment-vars.md))
-- [Coding Standards](coding-standards.txt) ([md version](coding-standards.md))
-- [Testing Strategy](testing-strategy.txt) ([md version](testing-strategy.md)) - It really nailed this one, even having me ensure it captured by concerns about testing each epic with scripts incrementally - which I did confirm was awesome!
-
-It then confirmed it was done with all the artifacts and ready to assess with its checklist! Here are the results: 5 minor points and great questions - some I answered, one I didn't understand and it explained it to me in detail!
-
-I made the updates, and it also proposed a new file for this project specifically! [Prompts](prompts.txt) ([md version](prompts.md)) - I did have it take the output from that to ensure its referenced where needed including epic 4 and coding standards, it helped me regenerate epic 4 with the changes.
-
-We were done, I told it great job, the output it gave me next was perfect showing the complete function of the multiphased agent! Here is a snippet!
-
-```text
-Next Steps:
-
-The project can now move into the implementation phase, using these architecture documents as the blueprint. Development agents can be tasked with implementing the stories within each Epic, following the defined structure, standards, and testing strategy.
-
-As the 3-Architect, I can switch to Mode 3: Master Architect Advisory if you need further assistance during development, such as:
-
-Explaining architectural concepts.
-Advising on implementation challenges.
-Evaluating potential changes or enhancements.
-Helping manage technical debt.
-```
-
-Here is the [full massive architecture discussion link](https://g.co/gemini/share/4fedc292e068)!
-
-## PO-SM
-
-This mode is WILD in Gemini 2.5 Pro with its massive 1 million context window - holy crap! It was able to analyze every artifact together - since there is a 10 document attach limit I created a [Combined Artifacts](combined-artifacts-for-posm.txt) ([md version](combined-artifacts-for-posm.md)) which adds all 5 epic files in it.
-
-There was a ton of output running through the checklist - but the amazing part is it considered it all and output this (in better formatted markdown I didn't capture here well). TL;DR of the following - it caught two great finds! It called out that story 1.2 still calls for dotenv which we are not going to use after working with the architect, and also it is looking for a prompts.md that is called out - but I forgot to attach it, so it caught that! So I corrected story 1.2 and we are ready to proceed with development!
-
-VALIDATION SUMMARY
-Category Statuses
-Category Status Critical Issues
-
-1. Project Setup & Initialization PASS
-2. Infrastructure & Deployment Sequencing PASS
-3. External Dependencies & Integrations PASS
-4. User/Agent Responsibility Delineation PASS
-5. Feature Sequencing & Dependencies PASS
-6. MVP Scope Alignment PASS
-7. Risk Management & Practicality PASS
-8. Documentation & Handoff PASS
-9. Post-MVP Considerations PASS
-   OVERALL PASS No critical deficiencies identified.
-
-Export to Sheets
-Critical Deficiencies
-None identified.
-Recommendations
-
-While not critical, Story 1.2 could explicitly state npm install {dotenv library} rather than just referencing the library name, for absolute clarity, although the plan specifies native Node.js .env support which negates the need for a library [111, 549]. Correction: The plan correctly states native support is used and no external package is needed [549], removing this minor concern. The reference to installing dotenv in Story 1.2 [111-112] seems contradictory to the environment-vars.txt [549] and tech-stack.txt [867] which state native support is used and dotenv is not needed. This should be clarified/corrected in Story 1.2. Update: Reviewing Story 1.2 [111], it does explicitly require installing dotenv, which contradicts ENV [549], ARCH [72], TS [867], and PRD [752] (which implies native support via .env.example). This inconsistency needs resolution. Decision: Assuming ENV, ARCH, TS, PRD are correct and Story 1.2 requirement for dotenv package is an error. Will proceed assuming NO dotenv package required.
-
-Consider adding a docs/prompts.md file explicitly, as referenced in ARCH [89] and E4 Story 4.2 [321], even if prompts are simple initially. Update: E4 Story 4.2 [321-325] does require creating docs/prompts.md and referencing it. This seems sufficient.
-
-Final Decision
-
-APPROVED: The plan is comprehensive, meticulously detailed across PRD, Architecture, Epics, and supporting documents. The sequencing is logical, dependencies are managed, risks acknowledged, and the scope aligns tightly with MVP goals. The technical constraints are respected, and the use of stage testing utilities significantly enhances testability and validation. The identified inconsistency regarding the dotenv package is noted but assumed resolved in favour of native Node.js support based on multiple other document references. The plan is ready for implementation.
-
-Transitioning to SM Mode can proceed upon user confirmation or if auto-proceeding.
-
-(full chat link in the next section)
-
-## PO-SM Story Generation
-
-This is only for demonstration as I do not like to work this way, at this point I want to be into the project - but for fun and testing, I wanted to verify the gem can produce quality stories, potentially multiple at once in case someone were wanting to use this more like taskmaster.
-
-The output looks decent, I still prefer doing this in the IDE with Sonnet 3.5/3.7 though 1 story at a time with the SM, then use the Dev. Mainly because it's still possible you might want to change something story to story - but this is just a preference, and this method of generating all the stories at once might work well for you - experiment and let me know what you find!
-
-- [Story Drafts Epic 1](epic-1-stories-demo.md)
-- [Story Drafts Epic 2](epic-2-stories-demo.md)
-- [Story Drafts Epic 3](epic-3-stories-demo.md)
-  etc...
-
-Here is the full [4-POSM chat record](https://g.co/gemini/share/9ab02d1baa18).
-
-Ill post the link to the video and final project here if you want to see the final results of the app build - but I am beyond extatic at how well this planning workflow is now tuned with V2.
-
-Thanks if you read this far.
-
-- BMad

V2-FULL-DEMO-WALKTHROUGH/environment-vars.md

@@ -1,43 +0,0 @@
-# BMad Hacker Daily Digest Environment Variables
-
-## Configuration Loading Mechanism
-
-Environment variables for this project are managed using a standard `.env` file in the project root. The application leverages the native support for `.env` files built into Node.js (v20.6.0 and later) , meaning **no external `dotenv` package is required**.
-
-Variables defined in the `.env` file are automatically loaded into `process.env` when the Node.js application starts. Accessing and potentially validating these variables should be centralized, ideally within the `src/utils/config.ts` module .
-
-## Required Variables
-
-The following table lists the environment variables used by the application. An `.env.example` file should be maintained in the repository with these variables set to placeholder or default values .
-
-| Variable Name                   | Description                                                       | Example / Default Value                  | Required? | Sensitive? | Source        |
-| :------------------------------ | :---------------------------------------------------------------- | :--------------------------------------- | :-------- | :--------- | :------------ |
-| `OUTPUT_DIR_PATH`               | Filesystem path for storing output data artifacts                 | `./output`                               | Yes       | No         | Epic 1        |
-| `MAX_COMMENTS_PER_STORY`        | Maximum number of comments to fetch per HN story                  | `50`                                     | Yes       | No         | PRD           |
-| `OLLAMA_ENDPOINT_URL`           | Base URL for the local Ollama API instance                        | `http://localhost:11434`                 | Yes       | No         | Epic 4        |
-| `OLLAMA_MODEL`                  | Name of the Ollama model to use for summarization                 | `llama3`                                 | Yes       | No         | Epic 4        |
-| `EMAIL_HOST`                    | SMTP server hostname for sending email                            | `smtp.example.com`                       | Yes       | No         | Epic 5        |
-| `EMAIL_PORT`                    | SMTP server port                                                  | `587`                                    | Yes       | No         | Epic 5        |
-| `EMAIL_SECURE`                  | Use TLS/SSL (`true` for port 465, `false` for 587/STARTTLS)       | `false`                                  | Yes       | No         | Epic 5        |
-| `EMAIL_USER`                    | Username for SMTP authentication                                  | `user@example.com`                       | Yes       | **Yes**    | Epic 5        |
-| `EMAIL_PASS`                    | Password for SMTP authentication                                  | `your_smtp_password`                     | Yes       | **Yes**    | Epic 5        |
-| `EMAIL_FROM`                    | Sender email address (may need specific format)                   | `"BMad Digest <digest@example.com>"`     | Yes       | No         | Epic 5        |
-| `EMAIL_RECIPIENTS`              | Comma-separated list of recipient email addresses                 | `recipient1@example.com,r2@test.org`     | Yes       | No         | Epic 5        |
-| `NODE_ENV`                      | Runtime environment (influences some library behavior)            | `development`                            | No        | No         | Standard Node |
-| `SCRAPE_TIMEOUT_MS`             | _Optional:_ Timeout in milliseconds for article scraping requests | `15000` (15s)                            | No        | No         | Good Practice |
-| `OLLAMA_TIMEOUT_MS`             | _Optional:_ Timeout in milliseconds for Ollama API requests       | `120000` (2min)                          | No        | No         | Good Practice |
-| `LOG_LEVEL`                     | _Optional:_ Control log verbosity (e.g., debug, info)             | `info`                                   | No        | No         | Good Practice |
-| `MAX_COMMENT_CHARS_FOR_SUMMARY` | _Optional:_ Max chars of combined comments sent to LLM            | 10000 / null (uses all if not set)       | No        | No         | Arch Decision |
-| `SCRAPER_USER_AGENT`            | _Optional:_ Custom User-Agent header for scraping requests        | "BMadHackerDigest/0.1" (Default in code) | No        | No         | Arch Decision |
-
-## Notes
-
-- **Secrets Management:** Sensitive variables (`EMAIL_USER`, `EMAIL_PASS`) must **never** be committed to version control. The `.env` file should be included in `.gitignore` (as per boilerplate ).
-- **`.env.example`:** Maintain an `.env.example` file in the repository mirroring the variables above, using placeholders or default values for documentation and local setup .
-- **Validation:** It is recommended to implement validation logic in `src/utils/config.ts` to ensure required variables are present and potentially check their format on application startup .
-
-## Change Log
-
-| Change        | Date       | Version | Description                           | Author      |
-| ------------- | ---------- | ------- | ------------------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Draft based on PRD/Epics requirements | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/environment-vars.txt

@@ -1,43 +0,0 @@
-# BMad Hacker Daily Digest Environment Variables
-
-## Configuration Loading Mechanism
-
-Environment variables for this project are managed using a standard `.env` file in the project root. The application leverages the native support for `.env` files built into Node.js (v20.6.0 and later) , meaning **no external `dotenv` package is required**.
-
-Variables defined in the `.env` file are automatically loaded into `process.env` when the Node.js application starts. Accessing and potentially validating these variables should be centralized, ideally within the `src/utils/config.ts` module .
-
-## Required Variables
-
-The following table lists the environment variables used by the application. An `.env.example` file should be maintained in the repository with these variables set to placeholder or default values .
-
-| Variable Name                   | Description                                                       | Example / Default Value                  | Required? | Sensitive? | Source        |
-| :------------------------------ | :---------------------------------------------------------------- | :--------------------------------------- | :-------- | :--------- | :------------ |
-| `OUTPUT_DIR_PATH`               | Filesystem path for storing output data artifacts                 | `./output`                               | Yes       | No         | Epic 1        |
-| `MAX_COMMENTS_PER_STORY`        | Maximum number of comments to fetch per HN story                  | `50`                                     | Yes       | No         | PRD           |
-| `OLLAMA_ENDPOINT_URL`           | Base URL for the local Ollama API instance                        | `http://localhost:11434`                 | Yes       | No         | Epic 4        |
-| `OLLAMA_MODEL`                  | Name of the Ollama model to use for summarization                 | `llama3`                                 | Yes       | No         | Epic 4        |
-| `EMAIL_HOST`                    | SMTP server hostname for sending email                            | `smtp.example.com`                       | Yes       | No         | Epic 5        |
-| `EMAIL_PORT`                    | SMTP server port                                                  | `587`                                    | Yes       | No         | Epic 5        |
-| `EMAIL_SECURE`                  | Use TLS/SSL (`true` for port 465, `false` for 587/STARTTLS)       | `false`                                  | Yes       | No         | Epic 5        |
-| `EMAIL_USER`                    | Username for SMTP authentication                                  | `user@example.com`                       | Yes       | **Yes**    | Epic 5        |
-| `EMAIL_PASS`                    | Password for SMTP authentication                                  | `your_smtp_password`                     | Yes       | **Yes**    | Epic 5        |
-| `EMAIL_FROM`                    | Sender email address (may need specific format)                   | `"BMad Digest <digest@example.com>"`     | Yes       | No         | Epic 5        |
-| `EMAIL_RECIPIENTS`              | Comma-separated list of recipient email addresses                 | `recipient1@example.com,r2@test.org`     | Yes       | No         | Epic 5        |
-| `NODE_ENV`                      | Runtime environment (influences some library behavior)            | `development`                            | No        | No         | Standard Node |
-| `SCRAPE_TIMEOUT_MS`             | _Optional:_ Timeout in milliseconds for article scraping requests | `15000` (15s)                            | No        | No         | Good Practice |
-| `OLLAMA_TIMEOUT_MS`             | _Optional:_ Timeout in milliseconds for Ollama API requests       | `120000` (2min)                          | No        | No         | Good Practice |
-| `LOG_LEVEL`                     | _Optional:_ Control log verbosity (e.g., debug, info)             | `info`                                   | No        | No         | Good Practice |
-| `MAX_COMMENT_CHARS_FOR_SUMMARY` | _Optional:_ Max chars of combined comments sent to LLM            | 10000 / null (uses all if not set)       | No        | No         | Arch Decision |
-| `SCRAPER_USER_AGENT`            | _Optional:_ Custom User-Agent header for scraping requests        | "BMadHackerDigest/0.1" (Default in code) | No        | No         | Arch Decision |
-
-## Notes
-
-- **Secrets Management:** Sensitive variables (`EMAIL_USER`, `EMAIL_PASS`) must **never** be committed to version control. The `.env` file should be included in `.gitignore` (as per boilerplate ).
-- **`.env.example`:** Maintain an `.env.example` file in the repository mirroring the variables above, using placeholders or default values for documentation and local setup .
-- **Validation:** It is recommended to implement validation logic in `src/utils/config.ts` to ensure required variables are present and potentially check their format on application startup .
-
-## Change Log
-
-| Change        | Date       | Version | Description                           | Author      |
-| ------------- | ---------- | ------- | ------------------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Draft based on PRD/Epics requirements | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/epic-1-stories-demo.md

@@ -1,391 +0,0 @@
-Okay, transitioning to **SM Mode**.
-
-I will now generate the stories for **Epic 1: Project Initialization & Core Setup**, as requested for demonstration purposes.
-
-I will use the details from Epic 1 in `combined-artifacts-for-posm.txt`, the `story-template.txt`, and extract relevant technical context from the supporting documents (`architecture.txt`, `project-structure.txt`, `tech-stack.txt`, `environment-vars.txt`, `testing-strategy.txt`).
-
-**Note:** As identified during PO Mode validation, Story 1.2 contained a requirement to install the `dotenv` package [111-112], which contradicts multiple other documents stating native Node.js support is used and the package is unnecessary (`ENV` [549], `ARCH` [72], `TS` [867], `PRD` [752]). The following story for 1.2 has been generated based on the **correction** that the `dotenv` package is **not required** and native Node.js functionality should be used.
-
-Here is the report containing the generated stories for Epic 1:
-
----
-
-## **Stories Report: Epic 1**
-
-**File: ai/stories/1.1.story.md**
-
-```markdown
-# Story 1.1: Initialize Project from Boilerplate
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want to set up the initial project structure using the `bmad-boilerplate`, so that I have the standard tooling (TS, Jest, ESLint, Prettier), configurations, and scripts in place. [96]
-
-**Context:** This is the foundational story for the entire project. It establishes the core development environment, tooling, and standard scripts based on the `bmad-boilerplate` template, as required by the PRD [706, 713, 784] and Architecture [43]. All subsequent development relies on the successful completion of this setup.
-
-## Detailed Requirements
-
-- Copy or clone the contents of the `bmad-boilerplate` into the new project's root directory. [97]
-- Initialize a git repository in the project root directory (if not already done by cloning). [98]
-- Ensure the `.gitignore` file from the boilerplate is present. [99]
-- Run `npm install` to download and install all `devDependencies` specified in the boilerplate's `package.json`. [100]
-- Verify that the core boilerplate scripts (`lint`, `format`, `test`, `build`) execute without errors on the initial codebase. [101]
-
-## Acceptance Criteria (ACs)
-
-- AC1: The project directory contains the files and structure from `bmad-boilerplate`. [102]
-- AC2: A `node_modules` directory exists and contains packages corresponding to `devDependencies`. [103]
-- AC3: `npm run lint` command completes successfully without reporting any linting errors. [104]
-- AC4: `npm run format` command completes successfully, potentially making formatting changes according to Prettier rules. [105] Running it a second time should result in no changes. [106]
-- AC5: `npm run test` command executes Jest successfully (it may report "no tests found" which is acceptable at this stage). [107]
-- AC6: `npm run build` command executes successfully, creating a `dist` directory containing compiled JavaScript output. [108]
-- AC7: The `.gitignore` file exists and includes entries for `node_modules/`, `.env`, `dist/`, etc. as specified in the boilerplate. [109, 632]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create/Copy: All files from `bmad-boilerplate` (e.g., `package.json`, `tsconfig.json`, `.eslintrc.js`, `.prettierrc.js`, `.gitignore`, initial `src/` structure if any).
-  - Files to Modify: None initially, verification via script execution.
-  - _(Hint: See `docs/project-structure.md` [813-825] for the target overall layout derived from the boilerplate)._
-- **Key Technologies:**
-  - Node.js 22.x [851], npm [100], Git [98], TypeScript [846], Jest [889], ESLint [893], Prettier [896].
-  - _(Hint: See `docs/tech-stack.md` [839-905] for full list)._
-- **API Interactions / SDK Usage:**
-  - N/A for this story.
-- **Data Structures:**
-  - N/A for this story.
-- **Environment Variables:**
-  - N/A directly used, but `.gitignore` [109] should cover `.env`. Boilerplate includes `.env.example` [112].
-  - _(Hint: See `docs/environment-vars.md` [548-638] for all variables)._
-- **Coding Standards Notes:**
-  - Ensure boilerplate scripts (`lint`, `format`) run successfully. [101]
-  - Adhere to ESLint/Prettier rules defined in the boilerplate. [746]
-
-## Tasks / Subtasks
-
-- [ ] Obtain the `bmad-boilerplate` content (clone or copy).
-- [ ] Place boilerplate content into the project's root directory.
-- [ ] Initialize git repository (`git init`).
-- [ ] Verify `.gitignore` exists and is correctly sourced from boilerplate.
-- [ ] Run `npm install` to install dependencies.
-- [ ] Execute `npm run lint` and verify successful completion without errors.
-- [ ] Execute `npm run format` and verify successful completion. Run again to confirm no further changes.
-- [ ] Execute `npm run test` and verify successful execution (no tests found is OK).
-- [ ] Execute `npm run build` and verify `dist/` directory creation and successful completion.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** N/A for this story (focus is project setup). [915]
-- **Integration Tests:** N/A for this story. [921]
-- **Manual/CLI Verification:**
-  - Verify file structure matches boilerplate (AC1).
-  - Check for `node_modules/` directory (AC2).
-  - Run `npm run lint` (AC3).
-  - Run `npm run format` twice (AC4).
-  - Run `npm run test` (AC5).
-  - Run `npm run build`, check for `dist/` (AC6).
-  - Inspect `.gitignore` contents (AC7).
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Any notes about implementation choices, difficulties, or follow-up needed}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/1.2.story.md**
-
-```markdown
-# Story 1.2: Setup Environment Configuration
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want to establish the environment configuration mechanism using `.env` files, so that secrets and settings (like output paths) can be managed outside of version control, following boilerplate conventions and utilizing native Node.js support. [110, 549]
-
-**Context:** This story builds on the initialized project (Story 1.1). It sets up the critical mechanism for managing configuration parameters like API keys and file paths using standard `.env` files, which is essential for security and flexibility. It leverages Node.js's built-in `.env` file loading [549, 867], meaning **no external package installation is required**. This corrects the original requirement [111-112] based on `docs/environment-vars.md` [549] and `docs/tech-stack.md` [867].
-
-## Detailed Requirements
-
-- Verify the `.env.example` file exists (from boilerplate). [112]
-- Add an initial configuration variable `OUTPUT_DIR_PATH=./output` to `.env.example`. [113]
-- Create the `.env` file locally by copying `.env.example`. Populate `OUTPUT_DIR_PATH` if needed (can keep default). [114]
-- Implement a utility module (e.g., `src/utils/config.ts`) that reads environment variables **directly from `process.env`** (populated natively by Node.js from the `.env` file at startup). [115, 550]
-- The utility should export the loaded configuration values (initially just `OUTPUT_DIR_PATH`). [116] It is recommended to include basic validation (e.g., checking if required variables are present). [634]
-- Ensure the `.env` file is listed in `.gitignore` and is not committed. [117, 632]
-
-## Acceptance Criteria (ACs)
-
-- AC1: **(Removed)** The chosen `.env` library... is listed under `dependencies`. (Package not needed [549]).
-- AC2: The `.env.example` file exists, is tracked by git, and contains the line `OUTPUT_DIR_PATH=./output`. [119]
-- AC3: The `.env` file exists locally but is NOT tracked by git. [120]
-- AC4: A configuration module (`src/utils/config.ts` or similar) exists and successfully reads the `OUTPUT_DIR_PATH` value **from `process.env`** when the application starts. [121]
-- AC5: The loaded `OUTPUT_DIR_PATH` value is accessible within the application code via the config module. [122]
-- AC6: The `.env` file is listed in the `.gitignore` file. [117]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/utils/config.ts`.
-  - Files to Modify: `.env.example`, `.gitignore` (verify inclusion of `.env`). Create local `.env`.
-  - _(Hint: See `docs/project-structure.md` [822] for utils location)._
-- **Key Technologies:**
-  - Node.js 22.x (Native `.env` support >=20.6) [549, 851]. TypeScript [846].
-  - **No `dotenv` package required.** [549, 867]
-  - _(Hint: See `docs/tech-stack.md` [839-905] for full list)._
-- **API Interactions / SDK Usage:**
-  - N/A for this story.
-- **Data Structures:**
-  - Potentially an interface for the exported configuration object in `config.ts`.
-  - _(Hint: See `docs/data-models.md` [498-547] for key project data structures)._
-- **Environment Variables:**
-  - Reads `OUTPUT_DIR_PATH` from `process.env`. [116]
-  - Defines `OUTPUT_DIR_PATH` in `.env.example`. [113]
-  - _(Hint: See `docs/environment-vars.md` [559] for this variable)._
-- **Coding Standards Notes:**
-  - `config.ts` should export configuration values clearly.
-  - Consider adding validation logic in `config.ts` to check for the presence of required environment variables on startup. [634]
-
-## Tasks / Subtasks
-
-- [ ] Verify `bmad-boilerplate` provided `.env.example`.
-- [ ] Add `OUTPUT_DIR_PATH=./output` to `.env.example`.
-- [ ] Create `.env` file by copying `.env.example`.
-- [ ] Verify `.env` is included in `.gitignore`.
-- [ ] Create `src/utils/config.ts`.
-- [ ] Implement logic in `config.ts` to read `OUTPUT_DIR_PATH` directly from `process.env`.
-- [ ] Export the loaded `OUTPUT_DIR_PATH` value from `config.ts`.
-- [ ] (Optional but Recommended) Add validation in `config.ts` to ensure `OUTPUT_DIR_PATH` is defined in `process.env`.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:**
-  - Write unit tests for `src/utils/config.ts`. [915]
-  - Use `process.env` manipulation (e.g., temporarily setting `process.env.OUTPUT_DIR_PATH` within the test) to verify the module reads and exports the value correctly.
-  - Test validation logic (e.g., if it throws an error when a required variable is missing). [920]
-- **Integration Tests:** N/A for this story. [921]
-- **Manual/CLI Verification:**
-  - Check `.env.example` content (AC2).
-  - Verify `.env` exists locally but not in git status (AC3, AC6).
-  - Code inspection of `src/utils/config.ts` (AC4).
-  - Later stories (1.3, 1.4) will consume this module, verifying AC5 implicitly.
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Implemented using native Node.js .env support, no external package installed. Added basic validation.}
-- **Change Log:**
-  - Initial Draft (Corrected requirement to use native .env support instead of installing `dotenv` package).
-```
-
----
-
-**File: ai/stories/1.3.story.md**
-
-```markdown
-# Story 1.3: Implement Basic CLI Entry Point & Execution
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want a basic `src/index.ts` entry point that can be executed via the boilerplate's `dev` and `start` scripts, providing a working foundation for the application logic. [123]
-
-**Context:** This story builds upon the project setup (Story 1.1) and environment configuration (Story 1.2). It creates the main starting point (`src/index.ts`) for the CLI application. This file will be executed by the `npm run dev` (using `ts-node`) and `npm run start` (using compiled code) scripts provided by the boilerplate. It verifies that the basic execution flow and configuration loading are functional. [730, 755]
-
-## Detailed Requirements
-
-- Create the main application entry point file at `src/index.ts`. [124]
-- Implement minimal code within `src/index.ts` to:
-  - Import the configuration loading mechanism (from Story 1.2, e.g., `import config from './utils/config';`). [125]
-  - Log a simple startup message to the console (e.g., "BMad Hacker Daily Digest - Starting Up..."). [126]
-  - (Optional) Log the loaded `OUTPUT_DIR_PATH` from the imported config object to verify config loading. [127]
-- Confirm execution using boilerplate scripts (`npm run dev`, `npm run build`, `npm run start`). [127]
-
-## Acceptance Criteria (ACs)
-
-- AC1: The `src/index.ts` file exists. [128]
-- AC2: Running `npm run dev` executes `src/index.ts` via `ts-node` and logs the startup message to the console. [129]
-- AC3: Running `npm run build` successfully compiles `src/index.ts` (and any imports like `config.ts`) into the `dist` directory. [130]
-- AC4: Running `npm start` (after a successful build) executes the compiled code from `dist` and logs the startup message to the console. [131]
-- AC5: (If implemented) The loaded `OUTPUT_DIR_PATH` is logged to the console during execution via `npm run dev` or `npm run start`. [127]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/index.ts`.
-  - Files to Modify: None.
-  - _(Hint: See `docs/project-structure.md` [822] for entry point location)._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851].
-  - Uses scripts from `package.json` (`dev`, `start`, `build`) defined in the boilerplate.
-  - _(Hint: See `docs/tech-stack.md` [839-905] for full list)._
-- **API Interactions / SDK Usage:**
-  - N/A for this story.
-- **Data Structures:**
-  - Imports configuration object from `src/utils/config.ts` (Story 1.2).
-  - _(Hint: See `docs/data-models.md` [498-547] for key project data structures)._
-- **Environment Variables:**
-  - Implicitly uses variables loaded by `config.ts` if the optional logging step [127] is implemented.
-  - _(Hint: See `docs/environment-vars.md` [548-638] for all variables)._
-- **Coding Standards Notes:**
-  - Use standard `import` statements.
-  - Use `console.log` initially for the startup message (Logger setup is in Story 1.4).
-
-## Tasks / Subtasks
-
-- [ ] Create the file `src/index.ts`.
-- [ ] Add import statement for the configuration module (`src/utils/config.ts`).
-- [ ] Add `console.log("BMad Hacker Daily Digest - Starting Up...");` (or similar).
-- [ ] (Optional) Add `console.log(\`Output directory: \${config.OUTPUT_DIR_PATH}\`);`
-- [ ] Run `npm run dev` and verify console output (AC2, AC5 optional).
-- [ ] Run `npm run build` and verify successful compilation to `dist/` (AC3).
-- [ ] Run `npm start` and verify console output from compiled code (AC4, AC5 optional).
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** Low value for this specific story, as it's primarily wiring and execution setup. Testing `config.ts` was covered in Story 1.2. [915]
-- **Integration Tests:** N/A for this story. [921]
-- **Manual/CLI Verification:**
-  - Verify `src/index.ts` exists (AC1).
-  - Run `npm run dev`, check console output (AC2, AC5 opt).
-  - Run `npm run build`, check `dist/` exists (AC3).
-  - Run `npm start`, check console output (AC4, AC5 opt).
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Any notes about implementation choices, difficulties, or follow-up needed}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/1.4.story.md**
-
-```markdown
-# Story 1.4: Setup Basic Logging and Output Directory
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want a basic console logging mechanism and the dynamic creation of a date-stamped output directory, so that the application can provide execution feedback and prepare for storing data artifacts in subsequent epics. [132]
-
-**Context:** This story refines the basic execution setup from Story 1.3. It introduces a simple, reusable logger utility (`src/utils/logger.ts`) for standardized console output [871] and implements the logic to create the necessary date-stamped output directory (`./output/YYYY-MM-DD/`) based on the `OUTPUT_DIR_PATH` configured in Story 1.2. This directory is crucial for persisting intermediate data in later epics (Epics 2, 3, 4). [68, 538, 734, 788]
-
-## Detailed Requirements
-
-- Implement a simple, reusable logging utility module (e.g., `src/utils/logger.ts`). [133] Initially, it can wrap `console.log`, `console.warn`, `console.error`. Provide simple functions like `logInfo`, `logWarn`, `logError`. [134]
-- Refactor `src/index.ts` to use this `logger` for its startup message(s) instead of `console.log`. [134]
-- In `src/index.ts` (or a setup function called by it):
-  - Retrieve the `OUTPUT_DIR_PATH` from the configuration (imported from `src/utils/config.ts` - Story 1.2). [135]
-  - Determine the current date in 'YYYY-MM-DD' format (e.g., using `date-fns` library is recommended [878], needs installation `npm install date-fns --save-prod`). [136]
-  - Construct the full path for the date-stamped subdirectory (e.g., `${OUTPUT_DIR_PATH}/${formattedDate}`). [137]
-  - Check if the base output directory exists; if not, create it. [138]
-  - Check if the date-stamped subdirectory exists; if not, create it recursively. [139] Use Node.js `fs` module (e.g., `fs.mkdirSync(path, { recursive: true })`). Need to import `fs`. [140]
-  - Log (using the new logger utility) the full path of the output directory being used for the current run (e.g., "Output directory for this run: ./output/2025-05-04"). [141]
-- The application should exit gracefully after performing these setup steps (for now). [147]
-
-## Acceptance Criteria (ACs)
-
-- AC1: A logger utility module (`src/utils/logger.ts` or similar) exists and is used for console output in `src/index.ts`. [142]
-- AC2: Running `npm run dev` or `npm start` logs the startup message via the logger. [143]
-- AC3: Running the application creates the base output directory (e.g., `./output` defined in `.env`) if it doesn't already exist. [144]
-- AC4: Running the application creates a date-stamped subdirectory (e.g., `./output/2025-05-04`, based on current date) within the base output directory if it doesn't already exist. [145]
-- AC5: The application logs a message via the logger indicating the full path to the date-stamped output directory created/used for the current execution. [146]
-- AC6: The application exits gracefully after performing these setup steps (for now). [147]
-- AC7: `date-fns` library is added as a production dependency.
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/utils/logger.ts`, `src/utils/dateUtils.ts` (recommended for date formatting logic).
-  - Files to Modify: `src/index.ts`, `package.json` (add `date-fns`), `package-lock.json`.
-  - _(Hint: See `docs/project-structure.md` [822] for utils location)._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851], `fs` module (native) [140], `path` module (native, for joining paths).
-  - `date-fns` library [876] for date formatting (needs `npm install date-fns --save-prod`).
-  - _(Hint: See `docs/tech-stack.md` [839-905] for full list)._
-- **API Interactions / SDK Usage:**
-  - Node.js `fs.mkdirSync`. [140]
-- **Data Structures:**
-  - N/A specific to this story, uses config from 1.2.
-  - _(Hint: See `docs/data-models.md` [498-547] for key project data structures)._
-- **Environment Variables:**
-  - Uses `OUTPUT_DIR_PATH` loaded via `config.ts`. [135]
-  - _(Hint: See `docs/environment-vars.md` [559] for this variable)._
-- **Coding Standards Notes:**
-  - Logger should provide simple info/warn/error functions. [134]
-  - Use `path.join` to construct file paths reliably.
-  - Handle potential errors during directory creation (e.g., permissions) using try/catch, logging errors via the new logger.
-
-## Tasks / Subtasks
-
-- [ ] Install `date-fns`: `npm install date-fns --save-prod`.
-- [ ] Create `src/utils/logger.ts` wrapping `console` methods (e.g., `logInfo`, `logWarn`, `logError`).
-- [ ] Create `src/utils/dateUtils.ts` (optional but recommended) with a function to get current date as 'YYYY-MM-DD' using `date-fns`.
-- [ ] Refactor `src/index.ts` to import and use the `logger` instead of `console.log`.
-- [ ] In `src/index.ts`, import `fs` and `path`.
-- [ ] In `src/index.ts`, import and use the date formatting function.
-- [ ] In `src/index.ts`, retrieve `OUTPUT_DIR_PATH` from config.
-- [ ] In `src/index.ts`, construct the full date-stamped directory path using `path.join`.
-- [ ] In `src/index.ts`, add logic using `fs.mkdirSync` (with `{ recursive: true }`) inside a try/catch block to create the directory. Log errors using the logger.
-- [ ] In `src/index.ts`, log the full path of the created/used directory using the logger.
-- [ ] Ensure the script completes and exits after these steps.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:**
-  - Test `src/utils/logger.ts` functions (can spy on `console` methods). [915]
-  - Test `src/utils/dateUtils.ts` function for correct date formatting.
-  - Testing `fs` operations in unit tests can be complex; consider focusing on integration or manual verification for directory creation. Mocking `fs` is an option but might be brittle. [918]
-- **Integration Tests:**
-  - Could write a test that runs the core logic of `src/index.ts` (directory creation part) and uses `mock-fs` or actual file system checks (with cleanup) to verify directory creation. [921, 924]
-- **Manual/CLI Verification:**
-  - Run `npm run dev` or `npm start`.
-  - Check console output uses the logger format (AC1, AC2).
-  - Verify the base output directory (e.g., `./output`) is created if it didn't exist (AC3).
-  - Verify the date-stamped subdirectory (e.g., `./output/2025-05-04`) is created (AC4). Use current date. Delete directories before re-running to confirm creation.
-  - Check console log for the message confirming the output directory path (AC5).
-  - Confirm the process exits cleanly (AC6).
-  - Check `package.json` for `date-fns` dependency (AC7).
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Any notes about implementation choices, difficulties, or follow-up needed}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-## **End of Report for Epic 1**

V2-FULL-DEMO-WALKTHROUGH/epic-2-stories-demo.md

@@ -1,925 +0,0 @@
-Okay, continuing in **SM Mode**.
-
-Generating the stories for **Epic 2: HN Data Acquisition & Persistence**. This assumes that the foundational work from Epic 1 (project initialization, configuration setup via `src/utils/config.ts`, logger via `src/utils/logger.ts`, and output directory creation logic in `src/index.ts`) is complete and available for use.
-
----
-
-## **Stories Report: Epic 2**
-
-**File: ai/stories/2.1.story.md**
-
-```markdown
-# Story 2.1: Implement Algolia HN API Client
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want a dedicated client module to interact with the Algolia Hacker News Search API, so that fetching stories and comments is encapsulated, reusable, and uses the required native `Workspace` API. [155]
-
-**Context:** This story creates the primary interface for retrieving data from the external Hacker News API provided by Algolia. It encapsulates the specific API calls (`GET /search` for stories and comments) and data extraction logic into a reusable module (`src/clients/algoliaHNClient.ts`). This client will be used by the main pipeline (Story 2.2) and the stage testing utility (Story 2.4). It builds upon the logger created in Epic 1 (Story 1.4). [54, 60, 62, 77]
-
-## Detailed Requirements
-
-- Create a new module: `src/clients/algoliaHNClient.ts`. [156]
-- Implement an async function `WorkspaceTopStories` within the client: [157]
-  - Use native `Workspace` [749] to call the Algolia HN Search API endpoint for front-page stories (`http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10`). [4, 6, 7, 157] Adjust `hitsPerPage` if needed to ensure 10 stories.
-  - Parse the JSON response. [158]
-  - Extract required metadata for each story: `objectID` (use as `storyId`), `title`, `url` (use as `articleUrl`), `points`, `num_comments`. [159, 522] Handle potential missing `url` field gracefully (log warning using logger from Story 1.4, treat as null). [160]
-  - Construct the `hnUrl` for each story (e.g., `https://news.ycombinator.com/item?id={storyId}`). [161]
-  - Return an array of structured story objects (define a `Story` type, potentially in `src/types/hn.ts`). [162, 506-511]
-- Implement a separate async function `WorkspaceCommentsForStory` within the client: [163]
-  - Accept `storyId` (string) and `maxComments` limit (number) as arguments. [163]
-  - Use native `Workspace` to call the Algolia HN Search API endpoint for comments of a specific story (`http://hn.algolia.com/api/v1/search?tags=comment,story_{storyId}&hitsPerPage={maxComments}`). [12, 13, 14, 164]
-  - Parse the JSON response. [165]
-  - Extract required comment data: `objectID` (use as `commentId`), `comment_text`, `author`, `created_at`. [165, 524]
-  - Filter out comments where `comment_text` is null or empty. Ensure only up to `maxComments` are returned. [166]
-  - Return an array of structured comment objects (define a `Comment` type, potentially in `src/types/hn.ts`). [167, 500-505]
-- Implement basic error handling using `try...catch` around `Workspace` calls and check `response.ok` status. [168] Log errors using the logger utility from Epic 1 (Story 1.4). [169]
-- Define TypeScript interfaces/types for the expected structures of API responses (subset needed) and the data returned by the client functions (`Story`, `Comment`). Place these in `src/types/hn.ts`. [169, 821]
-
-## Acceptance Criteria (ACs)
-
-- AC1: The module `src/clients/algoliaHNClient.ts` exists and exports `WorkspaceTopStories` and `WorkspaceCommentsForStory` functions. [170]
-- AC2: Calling `WorkspaceTopStories` makes a network request to the correct Algolia endpoint (`search?tags=front_page&hitsPerPage=10`) and returns a promise resolving to an array of 10 `Story` objects containing the specified metadata (`storyId`, `title`, `articleUrl`, `hnUrl`, `points`, `num_comments`). [171]
-- AC3: Calling `WorkspaceCommentsForStory` with a valid `storyId` and `maxComments` limit makes a network request to the correct Algolia endpoint (`search?tags=comment,story_{storyId}&hitsPerPage={maxComments}`) and returns a promise resolving to an array of `Comment` objects (up to `maxComments`), filtering out empty ones. [172]
-- AC4: Both functions use the native `Workspace` API internally. [173]
-- AC5: Network errors or non-successful API responses (e.g., status 4xx, 5xx) are caught and logged using the logger from Story 1.4. [174] Functions should likely return an empty array or throw a specific error in failure cases for the caller to handle.
-- AC6: Relevant TypeScript types (`Story`, `Comment`) are defined in `src/types/hn.ts` and used within the client module. [175]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/clients/algoliaHNClient.ts`, `src/types/hn.ts`.
-  - Files to Modify: Potentially `src/types/index.ts` if using a barrel file.
-  - _(Hint: See `docs/project-structure.md` [817, 821] for location)._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851], Native `Workspace` API [863].
-  - Uses `logger` utility from Epic 1 (Story 1.4).
-  - _(Hint: See `docs/tech-stack.md` [839-905] for full list)._
-- **API Interactions / SDK Usage:**
-  - Algolia HN Search API `GET /search` endpoint. [2]
-  - Base URL: `http://hn.algolia.com/api/v1` [3]
-  - Parameters: `tags=front_page`, `hitsPerPage=10` (for stories) [6, 7]; `tags=comment,story_{storyId}`, `hitsPerPage={maxComments}` (for comments) [13, 14].
-  - Check `response.ok` and parse JSON response (`response.json()`). [168, 158, 165]
-  - Handle potential network errors with `try...catch`. [168]
-  - No authentication required. [3]
-  - _(Hint: See `docs/api-reference.md` [2-21] for details)._
-- **Data Structures:**
-  - Define `Comment` interface: `{ commentId: string, commentText: string | null, author: string | null, createdAt: string }`. [501-505]
-  - Define `Story` interface (initial fields): `{ storyId: string, title: string, articleUrl: string | null, hnUrl: string, points?: number, numComments?: number }`. [507-511]
-  - (These types will be augmented in later stories [512-517]).
-  - Reference Algolia response subset schemas in `docs/data-models.md` [521-525].
-  - _(Hint: See `docs/data-models.md` for full details)._
-- **Environment Variables:**
-  - No direct environment variables needed for this client itself (uses hardcoded base URL, fetches comment limit via argument).
-  - _(Hint: See `docs/environment-vars.md` [548-638] for all variables)._
-- **Coding Standards Notes:**
-  - Use `async/await` for `Workspace` calls.
-  - Use logger for errors and significant events (e.g., warning if `url` is missing). [160]
-  - Export types and functions clearly.
-
-## Tasks / Subtasks
-
-- [ ] Create `src/types/hn.ts` and define `Comment` and initial `Story` interfaces.
-- [ ] Create `src/clients/algoliaHNClient.ts`.
-- [ ] Import necessary types and the logger utility.
-- [ ] Implement `WorkspaceTopStories` function:
-  - [ ] Construct Algolia URL for top stories.
-  - [ ] Use `Workspace` with `try...catch`.
-  - [ ] Check `response.ok`, log errors if not OK.
-  - [ ] Parse JSON response.
-  - [ ] Map `hits` to `Story` objects, extracting required fields, handling null `url`, constructing `hnUrl`.
-  - [ ] Return array of `Story` objects (or handle error case).
-- [ ] Implement `WorkspaceCommentsForStory` function:
-  - [ ] Accept `storyId` and `maxComments` arguments.
-  - [ ] Construct Algolia URL for comments using arguments.
-  - [ ] Use `Workspace` with `try...catch`.
-  - [ ] Check `response.ok`, log errors if not OK.
-  - [ ] Parse JSON response.
-  - [ ] Map `hits` to `Comment` objects, extracting required fields.
-  - [ ] Filter out comments with null/empty `comment_text`.
-  - [ ] Limit results to `maxComments`.
-  - [ ] Return array of `Comment` objects (or handle error case).
-- [ ] Export functions and types as needed.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - Write unit tests for `src/clients/algoliaHNClient.ts`. [919]
-  - Mock the native `Workspace` function (e.g., using `jest.spyOn(global, 'fetch')`). [918]
-  - Test `WorkspaceTopStories`: Provide mock successful responses (valid JSON matching Algolia structure [521-523]) and verify correct parsing, mapping to `Story` objects [171], and `hnUrl` construction. Test with missing `url` field. Test mock error responses (network error, non-OK status) and verify error logging [174] and return value.
-  - Test `WorkspaceCommentsForStory`: Provide mock successful responses [524-525] and verify correct parsing, mapping to `Comment` objects, filtering of empty comments, and limiting by `maxComments` [172]. Test mock error responses and verify logging [174].
-  - Verify `Workspace` was called with the correct URLs and parameters [171, 172].
-- **Integration Tests:** N/A for this client module itself, but it will be used in pipeline integration tests later. [921]
-- **Manual/CLI Verification:** Tested indirectly via Story 2.2 execution and directly via Story 2.4 stage runner. [912]
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Any notes about implementation choices, difficulties, or follow-up needed}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/2.2.story.md**
-
-```markdown
-# Story 2.2: Integrate HN Data Fetching into Main Workflow
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want to integrate the HN data fetching logic into the main application workflow (`src/index.ts`), so that running the app retrieves the top 10 stories and their comments after completing the setup from Epic 1. [176]
-
-**Context:** This story connects the HN API client created in Story 2.1 to the main application entry point (`src/index.ts`) established in Epic 1 (Story 1.3). It modifies the main execution flow to call the client functions (`WorkspaceTopStories`, `WorkspaceCommentsForStory`) after the initial setup (logger, config, output directory). It uses the `MAX_COMMENTS_PER_STORY` configuration value loaded in Story 1.2. The fetched data (stories and their associated comments) is held in memory at the end of this stage. [46, 77]
-
-## Detailed Requirements
-
-- Modify the main execution flow in `src/index.ts` (or a main async function called by it, potentially moving logic to `src/core/pipeline.ts` as suggested by `ARCH` [46, 53] and `PS` [818]). **Recommendation:** Create `src/core/pipeline.ts` and a `runPipeline` async function, then call this function from `src/index.ts`.
-- Import the `algoliaHNClient` functions (`WorkspaceTopStories`, `WorkspaceCommentsForStory`) from Story 2.1. [177]
-- Import the configuration module (`src/utils/config.ts`) to access `MAX_COMMENTS_PER_STORY`. [177, 563] Also import the logger.
-- In the main pipeline function, after the Epic 1 setup (config load, logger init, output dir creation):
-  - Call `await fetchTopStories()`. [178]
-  - Log the number of stories fetched (e.g., "Fetched X stories."). [179] Use the logger from Story 1.4.
-  - Retrieve the `MAX_COMMENTS_PER_STORY` value from the config module. Ensure it's parsed as a number. Provide a default if necessary (e.g., 50, matching `ENV` [564]).
-  - Iterate through the array of fetched `Story` objects. [179]
-  - For each `Story`:
-    - Log progress (e.g., "Fetching up to Y comments for story {storyId}..."). [182]
-    - Call `await fetchCommentsForStory()`, passing the `story.storyId` and the configured `MAX_COMMENTS_PER_STORY` value. [180]
-    - Store the fetched comments (the returned `Comment[]`) within the corresponding `Story` object in memory (e.g., add a `comments: Comment[]` property to the `Story` type/object). [181] Augment the `Story` type definition in `src/types/hn.ts`. [512]
-- Ensure errors from the client functions are handled appropriately (e.g., log error and potentially skip comment fetching for that story).
-
-## Acceptance Criteria (ACs)
-
-- AC1: Running `npm run dev` executes Epic 1 setup steps followed by fetching stories and then comments for each story using the `algoliaHNClient`. [183]
-- AC2: Logs (via logger) clearly show the start and successful completion of fetching stories, and the start of fetching comments for each of the 10 stories. [184]
-- AC3: The configured `MAX_COMMENTS_PER_STORY` value is read from config, parsed as a number, and used in the calls to `WorkspaceCommentsForStory`. [185]
-- AC4: After successful execution (before persistence in Story 2.3), `Story` objects held in memory contain a `comments` property populated with an array of fetched `Comment` objects. [186] (Verification via debugger or temporary logging).
-- AC5: The `Story` type definition in `src/types/hn.ts` is updated to include the `comments: Comment[]` field. [512]
-- AC6: (If implemented) Core logic is moved to `src/core/pipeline.ts` and called from `src/index.ts`. [818]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/core/pipeline.ts` (recommended).
-  - Files to Modify: `src/index.ts`, `src/types/hn.ts`.
-  - _(Hint: See `docs/project-structure.md` [818, 821, 822])._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851].
-  - Uses `algoliaHNClient` (Story 2.1), `config` (Story 1.2), `logger` (Story 1.4).
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - Calls internal `algoliaHNClient.fetchTopStories()` and `algoliaHNClient.fetchCommentsForStory()`.
-- **Data Structures:**
-  - Augment `Story` interface in `src/types/hn.ts` to include `comments: Comment[]`. [512]
-  - Manipulates arrays of `Story` and `Comment` objects in memory.
-  - _(Hint: See `docs/data-models.md` [500-517])._
-- **Environment Variables:**
-  - Reads `MAX_COMMENTS_PER_STORY` via `config.ts`. [177, 563]
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Use `async/await` for calling client functions.
-  - Structure fetching logic cleanly (e.g., within a loop).
-  - Use the logger for progress and error reporting. [182, 184]
-  - Consider putting the main loop logic inside the `runPipeline` function in `src/core/pipeline.ts`.
-
-## Tasks / Subtasks
-
-- [ ] (Recommended) Create `src/core/pipeline.ts` and define an async `runPipeline` function.
-- [ ] Modify `src/index.ts` to import and call `runPipeline`. Move existing setup logic (logger init, config load, dir creation) into `runPipeline` or ensure it runs before it.
-- [ ] In `pipeline.ts` (or `index.ts`), import `WorkspaceTopStories`, `WorkspaceCommentsForStory` from `algoliaHNClient`.
-- [ ] Import `config` and `logger`.
-- [ ] Call `WorkspaceTopStories` after initial setup. Log count.
-- [ ] Retrieve `MAX_COMMENTS_PER_STORY` from `config`, ensuring it's a number.
-- [ ] Update `Story` type in `src/types/hn.ts` to include `comments: Comment[]`.
-- [ ] Loop through the fetched stories:
-  - [ ] Log comment fetching start for the story ID.
-  - [ ] Call `WorkspaceCommentsForStory` with `storyId` and `maxComments`.
-  - [ ] Handle potential errors from the client function call.
-  - [ ] Assign the returned comments array to the `comments` property of the current story object.
-- [ ] Add temporary logging or use debugger to verify stories in memory contain comments (AC4).
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - If logic is moved to `src/core/pipeline.ts`, unit test `runPipeline`. [916]
-  - Mock `algoliaHNClient` functions (`WorkspaceTopStories`, `WorkspaceCommentsForStory`). [918]
-  - Mock `config` to provide `MAX_COMMENTS_PER_STORY`.
-  - Mock `logger`.
-  - Verify `WorkspaceTopStories` is called once.
-  - Verify `WorkspaceCommentsForStory` is called for each story returned by the mocked `WorkspaceTopStories`, and that it receives the correct `storyId` and `maxComments` value from config [185].
-  - Verify the results from mocked `WorkspaceCommentsForStory` are correctly assigned to the `comments` property of the story objects.
-- **Integration Tests:**
-  - Could have an integration test for the fetch stage that uses the real `algoliaHNClient` (or a lightly mocked version checking calls) and verifies the in-memory data structure, but this is largely covered by the stage runner (Story 2.4). [921]
-- **Manual/CLI Verification:**
-  - Run `npm run dev`.
-  - Check logs for fetching stories and comments messages [184].
-  - Use debugger or temporary `console.log` in the pipeline code to inspect a story object after the loop and confirm its `comments` property is populated [186].
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Logic moved to src/core/pipeline.ts. Verified in-memory data structure.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/2.3.story.md**
-
-```markdown
-# Story 2.3: Persist Fetched HN Data Locally
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want to save the fetched HN stories (including their comments) to JSON files in the date-stamped output directory, so that the raw data is persisted locally for subsequent pipeline stages and debugging. [187]
-
-**Context:** This story follows Story 2.2 where HN data (stories with comments) was fetched and stored in memory. Now, this data needs to be saved to the local filesystem. It uses the date-stamped output directory created in Epic 1 (Story 1.4) and writes one JSON file per story, containing the story metadata and its comments. This persisted data (`{storyId}_data.json`) is the input for subsequent stages (Scraping - Epic 3, Summarization - Epic 4, Email Assembly - Epic 5). [48, 734, 735]
-
-## Detailed Requirements
-
-- Define a consistent JSON structure for the output file content. [188] Example from `docs/data-models.md` [539]: `{ storyId: "...", title: "...", articleUrl: "...", hnUrl: "...", points: ..., numComments: ..., fetchedAt: "ISO_TIMESTAMP", comments: [{ commentId: "...", commentText: "...", author: "...", createdAt: "...", ... }, ...] }`. Include a timestamp (`WorkspaceedAt`) for when the data was fetched/saved. [190]
-- Import Node.js `fs` (specifically `writeFileSync`) and `path` modules in the pipeline module (`src/core/pipeline.ts` or `src/index.ts`). [190] Import `date-fns` or use `new Date().toISOString()` for timestamp.
-- In the main workflow (`pipeline.ts`), within the loop iterating through stories (immediately after comments have been fetched and added to the story object in Story 2.2): [191]
-  - Get the full path to the date-stamped output directory (this path should be determined/passed from the initial setup logic from Story 1.4). [191]
-  - Generate the current timestamp in ISO 8601 format (e.g., `new Date().toISOString()`) and add it to the story object as `WorkspaceedAt`. [190] Update `Story` type in `src/types/hn.ts`. [516]
-  - Construct the filename for the story's data: `{storyId}_data.json`. [192]
-  - Construct the full file path using `path.join()`. [193]
-  - Prepare the data object to be saved, matching the defined JSON structure (including `storyId`, `title`, `articleUrl`, `hnUrl`, `points`, `numComments`, `WorkspaceedAt`, `comments`).
-  - Serialize the prepared story data object to a JSON string using `JSON.stringify(storyData, null, 2)` for readability. [194]
-  - Write the JSON string to the file using `fs.writeFileSync()`. Use a `try...catch` block for error handling around the file write. [195]
-  - Log (using the logger) the successful persistence of each story's data file or any errors encountered during file writing. [196]
-
-## Acceptance Criteria (ACs)
-
-- AC1: After running `npm run dev`, the date-stamped output directory (e.g., `./output/YYYY-MM-DD/`) contains exactly 10 files named `{storyId}_data.json` (assuming 10 stories were fetched successfully). [197]
-- AC2: Each JSON file contains valid JSON representing a single story object, including its metadata (`storyId`, `title`, `articleUrl`, `hnUrl`, `points`, `numComments`), a `WorkspaceedAt` ISO timestamp, and an array of its fetched `comments`, matching the structure defined in `docs/data-models.md` [538-540]. [198]
-- AC3: The number of comments in each file's `comments` array does not exceed `MAX_COMMENTS_PER_STORY`. [199]
-- AC4: Logs indicate that saving data to a file was attempted for each story, reporting success or specific file writing errors. [200]
-- AC5: The `Story` type definition in `src/types/hn.ts` is updated to include the `WorkspaceedAt: string` field. [516]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Modify: `src/core/pipeline.ts` (or `src/index.ts`), `src/types/hn.ts`.
-  - _(Hint: See `docs/project-structure.md` [818, 821, 822])._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851].
-  - Native `fs` module (`writeFileSync`) [190].
-  - Native `path` module (`join`) [193].
-  - `JSON.stringify` [194].
-  - Uses `logger` (Story 1.4).
-  - Uses output directory path created in Story 1.4 logic.
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - `fs.writeFileSync(filePath, jsonDataString, 'utf-8')`. [195]
-- **Data Structures:**
-  - Uses `Story` and `Comment` types from `src/types/hn.ts`.
-  - Augment `Story` type to include `WorkspaceedAt: string`. [516]
-  - Creates JSON structure matching `{storyId}_data.json` schema in `docs/data-models.md`. [538-540]
-  - _(Hint: See `docs/data-models.md`)._
-- **Environment Variables:**
-  - N/A directly, but relies on `OUTPUT_DIR_PATH` being available from config (Story 1.2) used by the directory creation logic (Story 1.4).
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Use `try...catch` for `writeFileSync` calls. [195]
-  - Use `JSON.stringify` with indentation (`null, 2`) for readability. [194]
-  - Log success/failure clearly using the logger. [196]
-
-## Tasks / Subtasks
-
-- [ ] In `pipeline.ts` (or `index.ts`), import `fs` and `path`.
-- [ ] Update `Story` type in `src/types/hn.ts` to include `WorkspaceedAt: string`.
-- [ ] Ensure the full path to the date-stamped output directory is available within the story processing loop.
-- [ ] Inside the loop (after comments are fetched for a story):
-  - [ ] Get the current ISO timestamp (`new Date().toISOString()`).
-  - [ ] Add the timestamp to the story object as `WorkspaceedAt`.
-  - [ ] Construct the output filename: `{storyId}_data.json`.
-  - [ ] Construct the full file path using `path.join(outputDirPath, filename)`.
-  - [ ] Create the data object matching the specified JSON structure, including comments.
-  - [ ] Serialize the data object using `JSON.stringify(data, null, 2)`.
-  - [ ] Use `try...catch` block:
-    - [ ] Inside `try`: Call `fs.writeFileSync(fullPath, jsonString, 'utf-8')`.
-    - [ ] Inside `try`: Log success message with filename.
-    - [ ] Inside `catch`: Log file writing error with filename.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - Testing file system interactions directly in unit tests can be brittle. [918]
-  - Focus unit tests on the data preparation logic: ensure the object created before `JSON.stringify` has the correct structure (`storyId`, `title`, `articleUrl`, `hnUrl`, `points`, `numComments`, `WorkspaceedAt`, `comments`) based on a sample input `Story` object. [920]
-  - Verify the `WorkspaceedAt` timestamp is added correctly.
-- **Integration Tests:** [921]
-  - Could test the file writing aspect using `mock-fs` or actual file system writes within a temporary directory (created during setup, removed during teardown). [924]
-  - Verify that the correct filename is generated and the content written to the mock/temporary file matches the expected JSON structure [538-540] and content.
-- **Manual/CLI Verification:** [912]
-  - Run `npm run dev`.
-  - Inspect the `output/YYYY-MM-DD/` directory (use current date).
-  - Verify 10 files named `{storyId}_data.json` exist (AC1).
-  - Open a few files, visually inspect the JSON structure, check for all required fields (metadata, `WorkspaceedAt`, `comments` array), and verify comment count <= `MAX_COMMENTS_PER_STORY` (AC2, AC3).
-  - Check console logs for success messages for file writing or any errors (AC4).
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Files saved successfully in ./output/YYYY-MM-DD/ directory.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/2.4.story.md**
-
-```markdown
-# Story 2.4: Implement Stage Testing Utility for HN Fetching
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want a separate, executable script that _only_ performs the HN data fetching and persistence, so I can test and trigger this stage independently of the full pipeline. [201]
-
-**Context:** This story addresses the PRD requirement [736] for stage-specific testing utilities [764]. It creates a standalone Node.js script (`src/stages/fetch_hn_data.ts`) that replicates the core logic of Stories 2.1, 2.2 (partially), and 2.3. This script will initialize necessary components (logger, config), call the `algoliaHNClient` to fetch stories and comments, and persist the results to the date-stamped output directory, just like the main pipeline does up to this point. This allows isolated testing of the Algolia API interaction and data persistence without running subsequent scraping, summarization, or emailing stages. [57, 62, 912]
-
-## Detailed Requirements
-
-- Create a new standalone script file: `src/stages/fetch_hn_data.ts`. [202]
-- This script should perform the essential setup required _for this stage_:
-  - Initialize the logger utility (from Story 1.4). [203]
-  - Load configuration using the config utility (from Story 1.2) to get `MAX_COMMENTS_PER_STORY` and `OUTPUT_DIR_PATH`. [203]
-  - Determine the current date ('YYYY-MM-DD') using the utility from Story 1.4. [203]
-  - Construct the date-stamped output directory path. [203]
-  - Ensure the output directory exists (create it recursively if not, reusing logic/utility from Story 1.4). [203]
-- The script should then execute the core logic of fetching and persistence:
-  - Import and use `algoliaHNClient.fetchTopStories` and `algoliaHNClient.fetchCommentsForStory` (from Story 2.1). [204]
-  - Import `fs` and `path`.
-  - Replicate the fetch loop logic from Story 2.2 (fetch stories, then loop to fetch comments for each using loaded `MAX_COMMENTS_PER_STORY` limit). [204]
-  - Replicate the persistence logic from Story 2.3 (add `WorkspaceedAt` timestamp, prepare data object, `JSON.stringify`, `fs.writeFileSync` to `{storyId}_data.json` in the date-stamped directory). [204]
-- The script should log its progress (e.g., "Starting HN data fetch stage...", "Fetching stories...", "Fetching comments for story X...", "Saving data for story X...") using the logger utility. [205]
-- Add a new script command to `package.json` under `"scripts"`: `"stage:fetch": "ts-node src/stages/fetch_hn_data.ts"`. [206]
-
-## Acceptance Criteria (ACs)
-
-- AC1: The file `src/stages/fetch_hn_data.ts` exists. [207]
-- AC2: The script `stage:fetch` is defined in `package.json`'s `scripts` section. [208]
-- AC3: Running `npm run stage:fetch` executes successfully, performing only the setup (logger, config, output dir), fetch (stories, comments), and persist steps (to JSON files). [209]
-- AC4: Running `npm run stage:fetch` creates the same 10 `{storyId}_data.json` files in the correct date-stamped output directory as running the main `npm run dev` command (up to the end of Epic 2 functionality). [210]
-- AC5: Logs generated by `npm run stage:fetch` reflect only the fetching and persisting steps, not subsequent pipeline stages (scraping, summarizing, emailing). [211]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/stages/fetch_hn_data.ts`.
-  - Files to Modify: `package.json`.
-  - _(Hint: See `docs/project-structure.md` [820] for stage runner location)._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851], `ts-node` (via `npm run` script).
-  - Uses `logger` (Story 1.4), `config` (Story 1.2), date util (Story 1.4), directory creation logic (Story 1.4), `algoliaHNClient` (Story 2.1), `fs`/`path` (Story 2.3).
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - Calls internal `algoliaHNClient` functions.
-  - Uses `fs.writeFileSync`.
-- **Data Structures:**
-  - Uses `Story`, `Comment` types.
-  - Generates `{storyId}_data.json` files [538-540].
-  - _(Hint: See `docs/data-models.md`)._
-- **Environment Variables:**
-  - Reads `MAX_COMMENTS_PER_STORY` and `OUTPUT_DIR_PATH` via `config.ts`.
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Structure the script clearly (setup, fetch, persist).
-  - Use `async/await`.
-  - Use logger extensively for progress indication. [205]
-  - Consider wrapping the main logic in an `async` IIFE (Immediately Invoked Function Expression) or a main function call.
-
-## Tasks / Subtasks
-
-- [ ] Create `src/stages/fetch_hn_data.ts`.
-- [ ] Add imports for logger, config, date util, `algoliaHNClient`, `fs`, `path`.
-- [ ] Implement setup logic: initialize logger, load config, get output dir path, ensure directory exists.
-- [ ] Implement main fetch logic:
-  - [ ] Call `WorkspaceTopStories`.
-  - [ ] Get `MAX_COMMENTS_PER_STORY` from config.
-  - [ ] Loop through stories:
-    - [ ] Call `WorkspaceCommentsForStory`.
-    - [ ] Add comments to story object.
-    - [ ] Add `WorkspaceedAt` timestamp.
-    - [ ] Prepare data object for saving.
-    - [ ] Construct full file path for `{storyId}_data.json`.
-    - [ ] Serialize and write to file using `fs.writeFileSync` within `try...catch`.
-    - [ ] Log progress/success/errors.
-- [ ] Add script `"stage:fetch": "ts-node src/stages/fetch_hn_data.ts"` to `package.json`.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** Unit tests for the underlying components (logger, config, client, utils) should already exist from previous stories. Unit testing the stage script itself might have limited value beyond checking basic setup calls if the core logic is just orchestrating tested components. [915]
-- **Integration Tests:** N/A specifically for the script, as it _is_ an integration test itself. [921]
-- **Manual/CLI Verification (Primary Test Method for this Story):** [912, 927]
-  - Run `npm run stage:fetch`. [209]
-  - Verify successful execution without errors.
-  - Check console logs for messages specific to fetching and persisting [211].
-  - Inspect the `output/YYYY-MM-DD/` directory and verify the content of the generated `{storyId}_data.json` files match expectations (similar to verification for Story 2.3) [210].
-  - Modify `package.json` to add the script (AC2).
-- _(Hint: See `docs/testing-strategy.md` [907-950] which identifies Stage Runners as a key part of Acceptance Testing)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Stage runner script created and tested successfully. package.json updated.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-## **End of Report for Epic 2**
-
-Okay, continuing in **SM Mode**.
-
-Generating the stories for **Epic 2: HN Data Acquisition & Persistence**. This assumes that the foundational work from Epic 1 (project initialization, configuration setup via `src/utils/config.ts`, logger via `src/utils/logger.ts`, and output directory creation logic in `src/index.ts`) is complete and available for use.
-
----
-
-## **Stories Report: Epic 2**
-
-**File: ai/stories/2.1.story.md**
-
-```markdown
-# Story 2.1: Implement Algolia HN API Client
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want a dedicated client module to interact with the Algolia Hacker News Search API, so that fetching stories and comments is encapsulated, reusable, and uses the required native `Workspace` API. [155]
-
-**Context:** This story creates the primary interface for retrieving data from the external Hacker News API provided by Algolia. It encapsulates the specific API calls (`GET /search` for stories and comments) and data extraction logic into a reusable module (`src/clients/algoliaHNClient.ts`). This client will be used by the main pipeline (Story 2.2) and the stage testing utility (Story 2.4). It builds upon the logger created in Epic 1 (Story 1.4). [54, 60, 62, 77]
-
-## Detailed Requirements
-
-- Create a new module: `src/clients/algoliaHNClient.ts`. [156]
-- Implement an async function `WorkspaceTopStories` within the client: [157]
-  - Use native `Workspace` [749] to call the Algolia HN Search API endpoint for front-page stories (`http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10`). [4, 6, 7, 157] Adjust `hitsPerPage` if needed to ensure 10 stories.
-  - Parse the JSON response. [158]
-  - Extract required metadata for each story: `objectID` (use as `storyId`), `title`, `url` (use as `articleUrl`), `points`, `num_comments`. [159, 522] Handle potential missing `url` field gracefully (log warning using logger from Story 1.4, treat as null). [160]
-  - Construct the `hnUrl` for each story (e.g., `https://news.ycombinator.com/item?id={storyId}`). [161]
-  - Return an array of structured story objects (define a `Story` type, potentially in `src/types/hn.ts`). [162, 506-511]
-- Implement a separate async function `WorkspaceCommentsForStory` within the client: [163]
-  - Accept `storyId` (string) and `maxComments` limit (number) as arguments. [163]
-  - Use native `Workspace` to call the Algolia HN Search API endpoint for comments of a specific story (`http://hn.algolia.com/api/v1/search?tags=comment,story_{storyId}&hitsPerPage={maxComments}`). [12, 13, 14, 164]
-  - Parse the JSON response. [165]
-  - Extract required comment data: `objectID` (use as `commentId`), `comment_text`, `author`, `created_at`. [165, 524]
-  - Filter out comments where `comment_text` is null or empty. Ensure only up to `maxComments` are returned. [166]
-  - Return an array of structured comment objects (define a `Comment` type, potentially in `src/types/hn.ts`). [167, 500-505]
-- Implement basic error handling using `try...catch` around `Workspace` calls and check `response.ok` status. [168] Log errors using the logger utility from Epic 1 (Story 1.4). [169]
-- Define TypeScript interfaces/types for the expected structures of API responses (subset needed) and the data returned by the client functions (`Story`, `Comment`). Place these in `src/types/hn.ts`. [169, 821]
-
-## Acceptance Criteria (ACs)
-
-- AC1: The module `src/clients/algoliaHNClient.ts` exists and exports `WorkspaceTopStories` and `WorkspaceCommentsForStory` functions. [170]
-- AC2: Calling `WorkspaceTopStories` makes a network request to the correct Algolia endpoint (`search?tags=front_page&hitsPerPage=10`) and returns a promise resolving to an array of 10 `Story` objects containing the specified metadata (`storyId`, `title`, `articleUrl`, `hnUrl`, `points`, `num_comments`). [171]
-- AC3: Calling `WorkspaceCommentsForStory` with a valid `storyId` and `maxComments` limit makes a network request to the correct Algolia endpoint (`search?tags=comment,story_{storyId}&hitsPerPage={maxComments}`) and returns a promise resolving to an array of `Comment` objects (up to `maxComments`), filtering out empty ones. [172]
-- AC4: Both functions use the native `Workspace` API internally. [173]
-- AC5: Network errors or non-successful API responses (e.g., status 4xx, 5xx) are caught and logged using the logger from Story 1.4. [174] Functions should likely return an empty array or throw a specific error in failure cases for the caller to handle.
-- AC6: Relevant TypeScript types (`Story`, `Comment`) are defined in `src/types/hn.ts` and used within the client module. [175]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/clients/algoliaHNClient.ts`, `src/types/hn.ts`.
-  - Files to Modify: Potentially `src/types/index.ts` if using a barrel file.
-  - _(Hint: See `docs/project-structure.md` [817, 821] for location)._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851], Native `Workspace` API [863].
-  - Uses `logger` utility from Epic 1 (Story 1.4).
-  - _(Hint: See `docs/tech-stack.md` [839-905] for full list)._
-- **API Interactions / SDK Usage:**
-  - Algolia HN Search API `GET /search` endpoint. [2]
-  - Base URL: `http://hn.algolia.com/api/v1` [3]
-  - Parameters: `tags=front_page`, `hitsPerPage=10` (for stories) [6, 7]; `tags=comment,story_{storyId}`, `hitsPerPage={maxComments}` (for comments) [13, 14].
-  - Check `response.ok` and parse JSON response (`response.json()`). [168, 158, 165]
-  - Handle potential network errors with `try...catch`. [168]
-  - No authentication required. [3]
-  - _(Hint: See `docs/api-reference.md` [2-21] for details)._
-- **Data Structures:**
-  - Define `Comment` interface: `{ commentId: string, commentText: string | null, author: string | null, createdAt: string }`. [501-505]
-  - Define `Story` interface (initial fields): `{ storyId: string, title: string, articleUrl: string | null, hnUrl: string, points?: number, numComments?: number }`. [507-511]
-  - (These types will be augmented in later stories [512-517]).
-  - Reference Algolia response subset schemas in `docs/data-models.md` [521-525].
-  - _(Hint: See `docs/data-models.md` for full details)._
-- **Environment Variables:**
-  - No direct environment variables needed for this client itself (uses hardcoded base URL, fetches comment limit via argument).
-  - _(Hint: See `docs/environment-vars.md` [548-638] for all variables)._
-- **Coding Standards Notes:**
-  - Use `async/await` for `Workspace` calls.
-  - Use logger for errors and significant events (e.g., warning if `url` is missing). [160]
-  - Export types and functions clearly.
-
-## Tasks / Subtasks
-
-- [ ] Create `src/types/hn.ts` and define `Comment` and initial `Story` interfaces.
-- [ ] Create `src/clients/algoliaHNClient.ts`.
-- [ ] Import necessary types and the logger utility.
-- [ ] Implement `WorkspaceTopStories` function:
-  - [ ] Construct Algolia URL for top stories.
-  - [ ] Use `Workspace` with `try...catch`.
-  - [ ] Check `response.ok`, log errors if not OK.
-  - [ ] Parse JSON response.
-  - [ ] Map `hits` to `Story` objects, extracting required fields, handling null `url`, constructing `hnUrl`.
-  - [ ] Return array of `Story` objects (or handle error case).
-- [ ] Implement `WorkspaceCommentsForStory` function:
-  - [ ] Accept `storyId` and `maxComments` arguments.
-  - [ ] Construct Algolia URL for comments using arguments.
-  - [ ] Use `Workspace` with `try...catch`.
-  - [ ] Check `response.ok`, log errors if not OK.
-  - [ ] Parse JSON response.
-  - [ ] Map `hits` to `Comment` objects, extracting required fields.
-  - [ ] Filter out comments with null/empty `comment_text`.
-  - [ ] Limit results to `maxComments`.
-  - [ ] Return array of `Comment` objects (or handle error case).
-- [ ] Export functions and types as needed.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - Write unit tests for `src/clients/algoliaHNClient.ts`. [919]
-  - Mock the native `Workspace` function (e.g., using `jest.spyOn(global, 'fetch')`). [918]
-  - Test `WorkspaceTopStories`: Provide mock successful responses (valid JSON matching Algolia structure [521-523]) and verify correct parsing, mapping to `Story` objects [171], and `hnUrl` construction. Test with missing `url` field. Test mock error responses (network error, non-OK status) and verify error logging [174] and return value.
-  - Test `WorkspaceCommentsForStory`: Provide mock successful responses [524-525] and verify correct parsing, mapping to `Comment` objects, filtering of empty comments, and limiting by `maxComments` [172]. Test mock error responses and verify logging [174].
-  - Verify `Workspace` was called with the correct URLs and parameters [171, 172].
-- **Integration Tests:** N/A for this client module itself, but it will be used in pipeline integration tests later. [921]
-- **Manual/CLI Verification:** Tested indirectly via Story 2.2 execution and directly via Story 2.4 stage runner. [912]
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Any notes about implementation choices, difficulties, or follow-up needed}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/2.2.story.md**
-
-```markdown
-# Story 2.2: Integrate HN Data Fetching into Main Workflow
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want to integrate the HN data fetching logic into the main application workflow (`src/index.ts`), so that running the app retrieves the top 10 stories and their comments after completing the setup from Epic 1. [176]
-
-**Context:** This story connects the HN API client created in Story 2.1 to the main application entry point (`src/index.ts`) established in Epic 1 (Story 1.3). It modifies the main execution flow to call the client functions (`WorkspaceTopStories`, `WorkspaceCommentsForStory`) after the initial setup (logger, config, output directory). It uses the `MAX_COMMENTS_PER_STORY` configuration value loaded in Story 1.2. The fetched data (stories and their associated comments) is held in memory at the end of this stage. [46, 77]
-
-## Detailed Requirements
-
-- Modify the main execution flow in `src/index.ts` (or a main async function called by it, potentially moving logic to `src/core/pipeline.ts` as suggested by `ARCH` [46, 53] and `PS` [818]). **Recommendation:** Create `src/core/pipeline.ts` and a `runPipeline` async function, then call this function from `src/index.ts`.
-- Import the `algoliaHNClient` functions (`WorkspaceTopStories`, `WorkspaceCommentsForStory`) from Story 2.1. [177]
-- Import the configuration module (`src/utils/config.ts`) to access `MAX_COMMENTS_PER_STORY`. [177, 563] Also import the logger.
-- In the main pipeline function, after the Epic 1 setup (config load, logger init, output dir creation):
-  - Call `await fetchTopStories()`. [178]
-  - Log the number of stories fetched (e.g., "Fetched X stories."). [179] Use the logger from Story 1.4.
-  - Retrieve the `MAX_COMMENTS_PER_STORY` value from the config module. Ensure it's parsed as a number. Provide a default if necessary (e.g., 50, matching `ENV` [564]).
-  - Iterate through the array of fetched `Story` objects. [179]
-  - For each `Story`:
-    - Log progress (e.g., "Fetching up to Y comments for story {storyId}..."). [182]
-    - Call `await fetchCommentsForStory()`, passing the `story.storyId` and the configured `MAX_COMMENTS_PER_STORY` value. [180]
-    - Store the fetched comments (the returned `Comment[]`) within the corresponding `Story` object in memory (e.g., add a `comments: Comment[]` property to the `Story` type/object). [181] Augment the `Story` type definition in `src/types/hn.ts`. [512]
-- Ensure errors from the client functions are handled appropriately (e.g., log error and potentially skip comment fetching for that story).
-
-## Acceptance Criteria (ACs)
-
-- AC1: Running `npm run dev` executes Epic 1 setup steps followed by fetching stories and then comments for each story using the `algoliaHNClient`. [183]
-- AC2: Logs (via logger) clearly show the start and successful completion of fetching stories, and the start of fetching comments for each of the 10 stories. [184]
-- AC3: The configured `MAX_COMMENTS_PER_STORY` value is read from config, parsed as a number, and used in the calls to `WorkspaceCommentsForStory`. [185]
-- AC4: After successful execution (before persistence in Story 2.3), `Story` objects held in memory contain a `comments` property populated with an array of fetched `Comment` objects. [186] (Verification via debugger or temporary logging).
-- AC5: The `Story` type definition in `src/types/hn.ts` is updated to include the `comments: Comment[]` field. [512]
-- AC6: (If implemented) Core logic is moved to `src/core/pipeline.ts` and called from `src/index.ts`. [818]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/core/pipeline.ts` (recommended).
-  - Files to Modify: `src/index.ts`, `src/types/hn.ts`.
-  - _(Hint: See `docs/project-structure.md` [818, 821, 822])._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851].
-  - Uses `algoliaHNClient` (Story 2.1), `config` (Story 1.2), `logger` (Story 1.4).
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - Calls internal `algoliaHNClient.fetchTopStories()` and `algoliaHNClient.fetchCommentsForStory()`.
-- **Data Structures:**
-  - Augment `Story` interface in `src/types/hn.ts` to include `comments: Comment[]`. [512]
-  - Manipulates arrays of `Story` and `Comment` objects in memory.
-  - _(Hint: See `docs/data-models.md` [500-517])._
-- **Environment Variables:**
-  - Reads `MAX_COMMENTS_PER_STORY` via `config.ts`. [177, 563]
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Use `async/await` for calling client functions.
-  - Structure fetching logic cleanly (e.g., within a loop).
-  - Use the logger for progress and error reporting. [182, 184]
-  - Consider putting the main loop logic inside the `runPipeline` function in `src/core/pipeline.ts`.
-
-## Tasks / Subtasks
-
-- [ ] (Recommended) Create `src/core/pipeline.ts` and define an async `runPipeline` function.
-- [ ] Modify `src/index.ts` to import and call `runPipeline`. Move existing setup logic (logger init, config load, dir creation) into `runPipeline` or ensure it runs before it.
-- [ ] In `pipeline.ts` (or `index.ts`), import `WorkspaceTopStories`, `WorkspaceCommentsForStory` from `algoliaHNClient`.
-- [ ] Import `config` and `logger`.
-- [ ] Call `WorkspaceTopStories` after initial setup. Log count.
-- [ ] Retrieve `MAX_COMMENTS_PER_STORY` from `config`, ensuring it's a number.
-- [ ] Update `Story` type in `src/types/hn.ts` to include `comments: Comment[]`.
-- [ ] Loop through the fetched stories:
-  - [ ] Log comment fetching start for the story ID.
-  - [ ] Call `WorkspaceCommentsForStory` with `storyId` and `maxComments`.
-  - [ ] Handle potential errors from the client function call.
-  - [ ] Assign the returned comments array to the `comments` property of the current story object.
-- [ ] Add temporary logging or use debugger to verify stories in memory contain comments (AC4).
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - If logic is moved to `src/core/pipeline.ts`, unit test `runPipeline`. [916]
-  - Mock `algoliaHNClient` functions (`WorkspaceTopStories`, `WorkspaceCommentsForStory`). [918]
-  - Mock `config` to provide `MAX_COMMENTS_PER_STORY`.
-  - Mock `logger`.
-  - Verify `WorkspaceTopStories` is called once.
-  - Verify `WorkspaceCommentsForStory` is called for each story returned by the mocked `WorkspaceTopStories`, and that it receives the correct `storyId` and `maxComments` value from config [185].
-  - Verify the results from mocked `WorkspaceCommentsForStory` are correctly assigned to the `comments` property of the story objects.
-- **Integration Tests:**
-  - Could have an integration test for the fetch stage that uses the real `algoliaHNClient` (or a lightly mocked version checking calls) and verifies the in-memory data structure, but this is largely covered by the stage runner (Story 2.4). [921]
-- **Manual/CLI Verification:**
-  - Run `npm run dev`.
-  - Check logs for fetching stories and comments messages [184].
-  - Use debugger or temporary `console.log` in the pipeline code to inspect a story object after the loop and confirm its `comments` property is populated [186].
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Logic moved to src/core/pipeline.ts. Verified in-memory data structure.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/2.3.story.md**
-
-```markdown
-# Story 2.3: Persist Fetched HN Data Locally
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want to save the fetched HN stories (including their comments) to JSON files in the date-stamped output directory, so that the raw data is persisted locally for subsequent pipeline stages and debugging. [187]
-
-**Context:** This story follows Story 2.2 where HN data (stories with comments) was fetched and stored in memory. Now, this data needs to be saved to the local filesystem. It uses the date-stamped output directory created in Epic 1 (Story 1.4) and writes one JSON file per story, containing the story metadata and its comments. This persisted data (`{storyId}_data.json`) is the input for subsequent stages (Scraping - Epic 3, Summarization - Epic 4, Email Assembly - Epic 5). [48, 734, 735]
-
-## Detailed Requirements
-
-- Define a consistent JSON structure for the output file content. [188] Example from `docs/data-models.md` [539]: `{ storyId: "...", title: "...", articleUrl: "...", hnUrl: "...", points: ..., numComments: ..., fetchedAt: "ISO_TIMESTAMP", comments: [{ commentId: "...", commentText: "...", author: "...", createdAt: "...", ... }, ...] }`. Include a timestamp (`WorkspaceedAt`) for when the data was fetched/saved. [190]
-- Import Node.js `fs` (specifically `writeFileSync`) and `path` modules in the pipeline module (`src/core/pipeline.ts` or `src/index.ts`). [190] Import `date-fns` or use `new Date().toISOString()` for timestamp.
-- In the main workflow (`pipeline.ts`), within the loop iterating through stories (immediately after comments have been fetched and added to the story object in Story 2.2): [191]
-  - Get the full path to the date-stamped output directory (this path should be determined/passed from the initial setup logic from Story 1.4). [191]
-  - Generate the current timestamp in ISO 8601 format (e.g., `new Date().toISOString()`) and add it to the story object as `WorkspaceedAt`. [190] Update `Story` type in `src/types/hn.ts`. [516]
-  - Construct the filename for the story's data: `{storyId}_data.json`. [192]
-  - Construct the full file path using `path.join()`. [193]
-  - Prepare the data object to be saved, matching the defined JSON structure (including `storyId`, `title`, `articleUrl`, `hnUrl`, `points`, `numComments`, `WorkspaceedAt`, `comments`).
-  - Serialize the prepared story data object to a JSON string using `JSON.stringify(storyData, null, 2)` for readability. [194]
-  - Write the JSON string to the file using `fs.writeFileSync()`. Use a `try...catch` block for error handling around the file write. [195]
-  - Log (using the logger) the successful persistence of each story's data file or any errors encountered during file writing. [196]
-
-## Acceptance Criteria (ACs)
-
-- AC1: After running `npm run dev`, the date-stamped output directory (e.g., `./output/YYYY-MM-DD/`) contains exactly 10 files named `{storyId}_data.json` (assuming 10 stories were fetched successfully). [197]
-- AC2: Each JSON file contains valid JSON representing a single story object, including its metadata (`storyId`, `title`, `articleUrl`, `hnUrl`, `points`, `numComments`), a `WorkspaceedAt` ISO timestamp, and an array of its fetched `comments`, matching the structure defined in `docs/data-models.md` [538-540]. [198]
-- AC3: The number of comments in each file's `comments` array does not exceed `MAX_COMMENTS_PER_STORY`. [199]
-- AC4: Logs indicate that saving data to a file was attempted for each story, reporting success or specific file writing errors. [200]
-- AC5: The `Story` type definition in `src/types/hn.ts` is updated to include the `WorkspaceedAt: string` field. [516]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Modify: `src/core/pipeline.ts` (or `src/index.ts`), `src/types/hn.ts`.
-  - _(Hint: See `docs/project-structure.md` [818, 821, 822])._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851].
-  - Native `fs` module (`writeFileSync`) [190].
-  - Native `path` module (`join`) [193].
-  - `JSON.stringify` [194].
-  - Uses `logger` (Story 1.4).
-  - Uses output directory path created in Story 1.4 logic.
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - `fs.writeFileSync(filePath, jsonDataString, 'utf-8')`. [195]
-- **Data Structures:**
-  - Uses `Story` and `Comment` types from `src/types/hn.ts`.
-  - Augment `Story` type to include `WorkspaceedAt: string`. [516]
-  - Creates JSON structure matching `{storyId}_data.json` schema in `docs/data-models.md`. [538-540]
-  - _(Hint: See `docs/data-models.md`)._
-- **Environment Variables:**
-  - N/A directly, but relies on `OUTPUT_DIR_PATH` being available from config (Story 1.2) used by the directory creation logic (Story 1.4).
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Use `try...catch` for `writeFileSync` calls. [195]
-  - Use `JSON.stringify` with indentation (`null, 2`) for readability. [194]
-  - Log success/failure clearly using the logger. [196]
-
-## Tasks / Subtasks
-
-- [ ] In `pipeline.ts` (or `index.ts`), import `fs` and `path`.
-- [ ] Update `Story` type in `src/types/hn.ts` to include `WorkspaceedAt: string`.
-- [ ] Ensure the full path to the date-stamped output directory is available within the story processing loop.
-- [ ] Inside the loop (after comments are fetched for a story):
-  - [ ] Get the current ISO timestamp (`new Date().toISOString()`).
-  - [ ] Add the timestamp to the story object as `WorkspaceedAt`.
-  - [ ] Construct the output filename: `{storyId}_data.json`.
-  - [ ] Construct the full file path using `path.join(outputDirPath, filename)`.
-  - [ ] Create the data object matching the specified JSON structure, including comments.
-  - [ ] Serialize the data object using `JSON.stringify(data, null, 2)`.
-  - [ ] Use `try...catch` block:
-    - [ ] Inside `try`: Call `fs.writeFileSync(fullPath, jsonString, 'utf-8')`.
-    - [ ] Inside `try`: Log success message with filename.
-    - [ ] Inside `catch`: Log file writing error with filename.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - Testing file system interactions directly in unit tests can be brittle. [918]
-  - Focus unit tests on the data preparation logic: ensure the object created before `JSON.stringify` has the correct structure (`storyId`, `title`, `articleUrl`, `hnUrl`, `points`, `numComments`, `WorkspaceedAt`, `comments`) based on a sample input `Story` object. [920]
-  - Verify the `WorkspaceedAt` timestamp is added correctly.
-- **Integration Tests:** [921]
-  - Could test the file writing aspect using `mock-fs` or actual file system writes within a temporary directory (created during setup, removed during teardown). [924]
-  - Verify that the correct filename is generated and the content written to the mock/temporary file matches the expected JSON structure [538-540] and content.
-- **Manual/CLI Verification:** [912]
-  - Run `npm run dev`.
-  - Inspect the `output/YYYY-MM-DD/` directory (use current date).
-  - Verify 10 files named `{storyId}_data.json` exist (AC1).
-  - Open a few files, visually inspect the JSON structure, check for all required fields (metadata, `WorkspaceedAt`, `comments` array), and verify comment count <= `MAX_COMMENTS_PER_STORY` (AC2, AC3).
-  - Check console logs for success messages for file writing or any errors (AC4).
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Files saved successfully in ./output/YYYY-MM-DD/ directory.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/2.4.story.md**
-
-```markdown
-# Story 2.4: Implement Stage Testing Utility for HN Fetching
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want a separate, executable script that _only_ performs the HN data fetching and persistence, so I can test and trigger this stage independently of the full pipeline. [201]
-
-**Context:** This story addresses the PRD requirement [736] for stage-specific testing utilities [764]. It creates a standalone Node.js script (`src/stages/fetch_hn_data.ts`) that replicates the core logic of Stories 2.1, 2.2 (partially), and 2.3. This script will initialize necessary components (logger, config), call the `algoliaHNClient` to fetch stories and comments, and persist the results to the date-stamped output directory, just like the main pipeline does up to this point. This allows isolated testing of the Algolia API interaction and data persistence without running subsequent scraping, summarization, or emailing stages. [57, 62, 912]
-
-## Detailed Requirements
-
-- Create a new standalone script file: `src/stages/fetch_hn_data.ts`. [202]
-- This script should perform the essential setup required _for this stage_:
-  - Initialize the logger utility (from Story 1.4). [203]
-  - Load configuration using the config utility (from Story 1.2) to get `MAX_COMMENTS_PER_STORY` and `OUTPUT_DIR_PATH`. [203]
-  - Determine the current date ('YYYY-MM-DD') using the utility from Story 1.4. [203]
-  - Construct the date-stamped output directory path. [203]
-  - Ensure the output directory exists (create it recursively if not, reusing logic/utility from Story 1.4). [203]
-- The script should then execute the core logic of fetching and persistence:
-  - Import and use `algoliaHNClient.fetchTopStories` and `algoliaHNClient.fetchCommentsForStory` (from Story 2.1). [204]
-  - Import `fs` and `path`.
-  - Replicate the fetch loop logic from Story 2.2 (fetch stories, then loop to fetch comments for each using loaded `MAX_COMMENTS_PER_STORY` limit). [204]
-  - Replicate the persistence logic from Story 2.3 (add `WorkspaceedAt` timestamp, prepare data object, `JSON.stringify`, `fs.writeFileSync` to `{storyId}_data.json` in the date-stamped directory). [204]
-- The script should log its progress (e.g., "Starting HN data fetch stage...", "Fetching stories...", "Fetching comments for story X...", "Saving data for story X...") using the logger utility. [205]
-- Add a new script command to `package.json` under `"scripts"`: `"stage:fetch": "ts-node src/stages/fetch_hn_data.ts"`. [206]
-
-## Acceptance Criteria (ACs)
-
-- AC1: The file `src/stages/fetch_hn_data.ts` exists. [207]
-- AC2: The script `stage:fetch` is defined in `package.json`'s `scripts` section. [208]
-- AC3: Running `npm run stage:fetch` executes successfully, performing only the setup (logger, config, output dir), fetch (stories, comments), and persist steps (to JSON files). [209]
-- AC4: Running `npm run stage:fetch` creates the same 10 `{storyId}_data.json` files in the correct date-stamped output directory as running the main `npm run dev` command (up to the end of Epic 2 functionality). [210]
-- AC5: Logs generated by `npm run stage:fetch` reflect only the fetching and persisting steps, not subsequent pipeline stages (scraping, summarizing, emailing). [211]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/stages/fetch_hn_data.ts`.
-  - Files to Modify: `package.json`.
-  - _(Hint: See `docs/project-structure.md` [820] for stage runner location)._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851], `ts-node` (via `npm run` script).
-  - Uses `logger` (Story 1.4), `config` (Story 1.2), date util (Story 1.4), directory creation logic (Story 1.4), `algoliaHNClient` (Story 2.1), `fs`/`path` (Story 2.3).
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - Calls internal `algoliaHNClient` functions.
-  - Uses `fs.writeFileSync`.
-- **Data Structures:**
-  - Uses `Story`, `Comment` types.
-  - Generates `{storyId}_data.json` files [538-540].
-  - _(Hint: See `docs/data-models.md`)._
-- **Environment Variables:**
-  - Reads `MAX_COMMENTS_PER_STORY` and `OUTPUT_DIR_PATH` via `config.ts`.
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Structure the script clearly (setup, fetch, persist).
-  - Use `async/await`.
-  - Use logger extensively for progress indication. [205]
-  - Consider wrapping the main logic in an `async` IIFE (Immediately Invoked Function Expression) or a main function call.
-
-## Tasks / Subtasks
-
-- [ ] Create `src/stages/fetch_hn_data.ts`.
-- [ ] Add imports for logger, config, date util, `algoliaHNClient`, `fs`, `path`.
-- [ ] Implement setup logic: initialize logger, load config, get output dir path, ensure directory exists.
-- [ ] Implement main fetch logic:
-  - [ ] Call `WorkspaceTopStories`.
-  - [ ] Get `MAX_COMMENTS_PER_STORY` from config.
-  - [ ] Loop through stories:
-    - [ ] Call `WorkspaceCommentsForStory`.
-    - [ ] Add comments to story object.
-    - [ ] Add `WorkspaceedAt` timestamp.
-    - [ ] Prepare data object for saving.
-    - [ ] Construct full file path for `{storyId}_data.json`.
-    - [ ] Serialize and write to file using `fs.writeFileSync` within `try...catch`.
-    - [ ] Log progress/success/errors.
-- [ ] Add script `"stage:fetch": "ts-node src/stages/fetch_hn_data.ts"` to `package.json`.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** Unit tests for the underlying components (logger, config, client, utils) should already exist from previous stories. Unit testing the stage script itself might have limited value beyond checking basic setup calls if the core logic is just orchestrating tested components. [915]
-- **Integration Tests:** N/A specifically for the script, as it _is_ an integration test itself. [921]
-- **Manual/CLI Verification (Primary Test Method for this Story):** [912, 927]
-  - Run `npm run stage:fetch`. [209]
-  - Verify successful execution without errors.
-  - Check console logs for messages specific to fetching and persisting [211].
-  - Inspect the `output/YYYY-MM-DD/` directory and verify the content of the generated `{storyId}_data.json` files match expectations (similar to verification for Story 2.3) [210].
-  - Modify `package.json` to add the script (AC2).
-- _(Hint: See `docs/testing-strategy.md` [907-950] which identifies Stage Runners as a key part of Acceptance Testing)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Stage runner script created and tested successfully. package.json updated.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-## **End of Report for Epic 2**

V2-FULL-DEMO-WALKTHROUGH/epic-3-stories-demo.md

@@ -1,486 +0,0 @@
-Okay, remaining in **SM Mode**.
-
-Generating the stories for **Epic 3: Article Scraping & Persistence**. This assumes that Epic 1 (project setup, config, logging, output dir) and Epic 2 (HN client implementation, data fetching integration, and local persistence of `{storyId}_data.json` files) are complete.
-
----
-
-## **Stories Report: Epic 3**
-
-**File: ai/stories/3.1.story.md**
-
-```markdown
-# Story 3.1: Implement Basic Article Scraper Module
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want a module that attempts to fetch HTML from a URL and extract the main article text using basic methods, handling common failures gracefully, so article content can be prepared for summarization. [220]
-
-**Context:** This story introduces the article scraping capability. It creates a dedicated module (`src/scraper/articleScraper.ts`) responsible for fetching content from external article URLs (found in the `{storyId}_data.json` files from Epic 2) and extracting plain text. It emphasizes using native `Workspace` and a simple extraction library (`@extractus/article-extractor` is recommended [222, 873]), and crucially, handling failures robustly (timeouts, non-HTML content, extraction errors) as required by the PRD [723, 724, 741]. This module will be used by the main pipeline (Story 3.2) and the stage tester (Story 3.4). [47, 55, 60, 63, 65]
-
-## Detailed Requirements
-
-- Create a new module: `src/scraper/articleScraper.ts`. [221]
-- Add `@extractus/article-extractor` dependency: `npm install @extractus/article-extractor --save-prod`. [222, 223, 873]
-- Implement an async function `scrapeArticle(url: string): Promise<string | null>` within the module. [223, 224]
-- Inside the function:
-  - Use native `Workspace` [749] to retrieve content from the `url`. [224] Set a reasonable timeout (e.g., 15 seconds via `AbortSignal.timeout()`, configure via `SCRAPE_TIMEOUT_MS` [615] if needed). Include a `User-Agent` header (e.g., `"BMadHackerDigest/0.1"` or configurable via `SCRAPER_USER_AGENT` [629]). [225]
-  - Handle potential `Workspace` errors (network errors, timeouts) using `try...catch`. Log error using logger (from Story 1.4) and return `null`. [226]
-  - Check the `response.ok` status. If not okay, log error (including status code) and return `null`. [226, 227]
-  - Check the `Content-Type` header of the response. If it doesn't indicate HTML (e.g., does not include `text/html`), log warning and return `null`. [227, 228]
-  - If HTML is received (`response.text()`), attempt to extract the main article text using `@extractus/article-extractor`. [229]
-  - Wrap the extraction logic (`await articleExtractor.extract(htmlContent)`) in a `try...catch` to handle library-specific errors. Log error and return `null` on failure. [230]
-  - Return the extracted plain text (`article.content`) if successful and not empty. Ensure it's just text, not HTML markup. [231]
-  - Return `null` if extraction fails or results in empty content. [232]
-  - Log all significant events, errors, or reasons for returning null (e.g., "Scraping URL...", "Fetch failed:", "Non-OK status:", "Non-HTML content type:", "Extraction failed:", "Successfully extracted text for {url}") using the logger utility. [233]
-- Define TypeScript types/interfaces as needed (though `article-extractor` types might suffice). [234]
-
-## Acceptance Criteria (ACs)
-
-- AC1: The `src/scraper/articleScraper.ts` module exists and exports the `scrapeArticle` function. [234]
-- AC2: The `@extractus/article-extractor` library is added to `dependencies` in `package.json` and `package-lock.json` is updated. [235]
-- AC3: `scrapeArticle` uses native `Workspace` with a timeout (default or configured) and a User-Agent header. [236]
-- AC4: `scrapeArticle` correctly handles fetch errors (network, timeout), non-OK responses, and non-HTML content types by logging the specific reason and returning `null`. [237]
-- AC5: `scrapeArticle` uses `@extractus/article-extractor` to attempt text extraction from valid HTML content fetched via `response.text()`. [238]
-- AC6: `scrapeArticle` returns the extracted plain text string on success, and `null` on any failure (fetch, non-HTML, extraction error, empty result). [239]
-- AC7: Relevant logs are produced using the logger for success, different failure modes, and errors encountered during the process. [240]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/scraper/articleScraper.ts`.
-  - Files to Modify: `package.json`, `package-lock.json`. Add optional env vars to `.env.example`.
-  - _(Hint: See `docs/project-structure.md` [819] for scraper location)._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851], Native `Workspace` API [863].
-  - `@extractus/article-extractor` library. [873]
-  - Uses `logger` utility (Story 1.4).
-  - Uses `config` utility (Story 1.2) if implementing configurable timeout/user-agent.
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - Native `Workspace(url, { signal: AbortSignal.timeout(timeoutMs), headers: { 'User-Agent': userAgent } })`. [225]
-  - Check `response.ok`, `response.headers.get('Content-Type')`. [227, 228]
-  - Get body as text: `await response.text()`. [229]
-  - `@extractus/article-extractor`: `import articleExtractor from '@extractus/article-extractor'; const article = await articleExtractor.extract(htmlContent); return article?.content || null;` [229, 231]
-- **Data Structures:**
-  - Function signature: `scrapeArticle(url: string): Promise<string | null>`. [224]
-  - Uses `article` object returned by extractor.
-  - _(Hint: See `docs/data-models.md` [498-547])._
-- **Environment Variables:**
-  - Optional: `SCRAPE_TIMEOUT_MS` (default e.g., 15000). [615]
-  - Optional: `SCRAPER_USER_AGENT` (default e.g., "BMadHackerDigest/0.1"). [629]
-  - Load via `config.ts` if used.
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Use `async/await`.
-  - Implement comprehensive `try...catch` blocks for `Workspace` and extraction. [226, 230]
-  - Log errors and reasons for returning `null` clearly. [233]
-
-## Tasks / Subtasks
-
-- [ ] Run `npm install @extractus/article-extractor --save-prod`.
-- [ ] Create `src/scraper/articleScraper.ts`.
-- [ ] Import logger, (optionally config), and `articleExtractor`.
-- [ ] Define the `scrapeArticle` async function accepting a `url`.
-- [ ] Implement `try...catch` for the entire fetch/parse logic. Log error and return `null` in `catch`.
-- [ ] Inside `try`:
-  - [ ] Define timeout (default or from config).
-  - [ ] Define User-Agent (default or from config).
-  - [ ] Call native `Workspace` with URL, timeout signal, and User-Agent header.
-  - [ ] Check `response.ok`. If not OK, log status and return `null`.
-  - [ ] Check `Content-Type` header. If not HTML, log type and return `null`.
-  - [ ] Get HTML content using `response.text()`.
-  - [ ] Implement inner `try...catch` for extraction:
-    - [ ] Call `await articleExtractor.extract(htmlContent)`.
-    - [ ] Check if result (`article?.content`) is valid text. If yes, log success and return text.
-    - [ ] If extraction failed or content is empty, log reason and return `null`.
-    - [ ] In `catch` block for extraction, log error and return `null`.
-- [ ] Add optional env vars `SCRAPE_TIMEOUT_MS` and `SCRAPER_USER_AGENT` to `.env.example`.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - Write unit tests for `src/scraper/articleScraper.ts`. [919]
-  - Mock native `Workspace`. Test different scenarios:
-    - Successful fetch (200 OK, HTML content type) -> Mock `articleExtractor` success -> Verify returned text [239].
-    - Successful fetch -> Mock `articleExtractor` failure/empty content -> Verify `null` return and logs [239, 240].
-    - Fetch returns non-OK status (e.g., 404, 500) -> Verify `null` return and logs [237, 240].
-    - Fetch returns non-HTML content type -> Verify `null` return and logs [237, 240].
-    - Fetch throws network error/timeout -> Verify `null` return and logs [237, 240].
-  - Mock `@extractus/article-extractor` to simulate success and failure cases. [918]
-  - Verify `Workspace` is called with the correct URL, User-Agent, and timeout signal [236].
-- **Integration Tests:** N/A for this module itself. [921]
-- **Manual/CLI Verification:** Tested indirectly via Story 3.2 execution and directly via Story 3.4 stage runner. [912]
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Implemented scraper module with @extractus/article-extractor and robust error handling.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/3.2.story.md**
-
-```markdown
-# Story 3.2: Integrate Article Scraping into Main Workflow
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want to integrate the article scraper into the main workflow (`src/core/pipeline.ts`), attempting to scrape the article for each HN story that has a valid URL, after fetching its data. [241]
-
-**Context:** This story connects the scraper module (`articleScraper.ts` from Story 3.1) into the main application pipeline (`src/core/pipeline.ts`) developed in Epic 2. It modifies the main loop over the fetched stories (which contain data loaded in Story 2.2) to include a call to `scrapeArticle` for stories that have an article URL. The result (scraped text or null) is then stored in memory, associated with the story object. [47, 78, 79]
-
-## Detailed Requirements
-
-- Modify the main execution flow in `src/core/pipeline.ts` (assuming logic moved here in Story 2.2). [242]
-- Import the `scrapeArticle` function from `src/scraper/articleScraper.ts`. [243] Import the logger.
-- Within the main loop iterating through the fetched `Story` objects (after comments are fetched in Story 2.2 and before persistence in Story 2.3):
-  - Check if `story.articleUrl` exists and appears to be a valid HTTP/HTTPS URL. A simple check for starting with `http://` or `https://` is sufficient. [243, 244]
-  - If the URL is missing or invalid, log a warning using the logger ("Skipping scraping for story {storyId}: Missing or invalid URL") and proceed to the next step for this story (e.g., summarization in Epic 4, or persistence in Story 3.3). Set an internal placeholder for scraped content to `null`. [245]
-  - If a valid URL exists:
-    - Log ("Attempting to scrape article for story {storyId} from {story.articleUrl}"). [246]
-    - Call `await scrapeArticle(story.articleUrl)`. [247]
-    - Store the result (the extracted text string or `null`) in memory, associated with the story object. Define/add property `articleContent: string | null` to the `Story` type in `src/types/hn.ts`. [247, 513]
-    - Log the outcome clearly using the logger (e.g., "Successfully scraped article for story {storyId}", "Failed to scrape article for story {storyId}"). [248]
-
-## Acceptance Criteria (ACs)
-
-- AC1: Running `npm run dev` executes Epic 1 & 2 steps, and then attempts article scraping for stories with valid `articleUrl`s within the main pipeline loop. [249]
-- AC2: Stories with missing or invalid `articleUrl`s are skipped by the scraping step, and a corresponding warning message is logged via the logger. [250]
-- AC3: For stories with valid URLs, the `scrapeArticle` function from `src/scraper/articleScraper.ts` is called with the correct URL. [251]
-- AC4: Logs (via logger) clearly indicate the start ("Attempting to scrape...") and the success/failure outcome of the scraping attempt for each relevant story. [252]
-- AC5: Story objects held in memory after this stage contain an `articleContent` property holding the scraped text (string) or `null` if scraping was skipped or failed. [253] (Verify via debugger/logging).
-- AC6: The `Story` type definition in `src/types/hn.ts` is updated to include the `articleContent: string | null` field. [513]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Modify: `src/core/pipeline.ts`, `src/types/hn.ts`.
-  - _(Hint: See `docs/project-structure.md` [818, 821])._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851].
-  - Uses `articleScraper.scrapeArticle` (Story 3.1), `logger` (Story 1.4).
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - Calls internal `scrapeArticle(url)`.
-- **Data Structures:**
-  - Operates on `Story[]` fetched in Epic 2.
-  - Augment `Story` interface in `src/types/hn.ts` to include `articleContent: string | null`. [513]
-  - Checks `story.articleUrl`.
-  - _(Hint: See `docs/data-models.md` [506-517])._
-- **Environment Variables:**
-  - N/A directly, but `scrapeArticle` might use them (Story 3.1).
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Perform the URL check before calling the scraper. [244]
-  - Clearly log skipping, attempt, success, failure for scraping. [245, 246, 248]
-  - Ensure the `articleContent` property is always set (either to the result string or explicitly to `null`).
-
-## Tasks / Subtasks
-
-- [ ] Update `Story` type in `src/types/hn.ts` to include `articleContent: string | null`.
-- [ ] Modify the main loop in `src/core/pipeline.ts` where stories are processed.
-- [ ] Import `scrapeArticle` from `src/scraper/articleScraper.ts`.
-- [ ] Import `logger`.
-- [ ] Inside the loop (after comment fetching, before persistence steps):
-  - [ ] Check if `story.articleUrl` exists and starts with `http`.
-  - [ ] If invalid/missing:
-    - [ ] Log warning message.
-    - [ ] Set `story.articleContent = null`.
-  - [ ] If valid:
-    - [ ] Log attempt message.
-    - [ ] Call `const scrapedContent = await scrapeArticle(story.articleUrl)`.
-    - [ ] Set `story.articleContent = scrapedContent`.
-    - [ ] Log success (if `scrapedContent` is not null) or failure (if `scrapedContent` is null).
-- [ ] Add temporary logging or use debugger to verify `articleContent` property in story objects (AC5).
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - Unit test the modified pipeline logic in `src/core/pipeline.ts`. [916]
-  - Mock the `scrapeArticle` function. [918]
-  - Provide mock `Story` objects with and without valid `articleUrl`s.
-  - Verify that `scrapeArticle` is called only for stories with valid URLs [251].
-  - Verify that the correct URL is passed to `scrapeArticle`.
-  - Verify that the return value (mocked text or mocked null) from `scrapeArticle` is correctly assigned to the `story.articleContent` property [253].
-  - Verify that appropriate logs (skip warning, attempt, success/fail) are called based on the URL validity and mocked `scrapeArticle` result [250, 252].
-- **Integration Tests:** Less emphasis here; Story 3.4 provides better integration testing for scraping. [921]
-- **Manual/CLI Verification:** [912]
-  - Run `npm run dev`.
-  - Check console logs for "Attempting to scrape...", "Successfully scraped...", "Failed to scrape...", and "Skipping scraping..." messages [250, 252].
-  - Use debugger or temporary logging to inspect `story.articleContent` values during or after the pipeline run [253].
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Integrated scraper call into pipeline. Updated Story type. Verified logic for handling valid/invalid URLs.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/3.3.story.md**
-
-```markdown
-# Story 3.3: Persist Scraped Article Text Locally
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want to save successfully scraped article text to a separate local file for each story, so that the text content is available as input for the summarization stage. [254]
-
-**Context:** This story adds the persistence step for the article content scraped in Story 3.2. Following a successful scrape (where `story.articleContent` is not null), this logic writes the plain text content to a `.txt` file (`{storyId}_article.txt`) within the date-stamped output directory created in Epic 1. This ensures the scraped text is available for the next stage (Summarization - Epic 4) even if the main script is run in stages or needs to be restarted. No file should be created if scraping failed or was skipped. [49, 734, 735]
-
-## Detailed Requirements
-
-- Import Node.js `fs` (`writeFileSync`) and `path` modules if not already present in `src/core/pipeline.ts`. [255] Import logger.
-- In the main workflow (`src/core/pipeline.ts`), within the loop processing each story, _after_ the scraping attempt (Story 3.2) is complete: [256]
-  - Check if `story.articleContent` is a non-null, non-empty string.
-  - If yes (scraping was successful and yielded content):
-    - Retrieve the full path to the current date-stamped output directory (available from setup). [256]
-    - Construct the filename: `{storyId}_article.txt`. [257]
-    - Construct the full file path using `path.join()`. [257]
-    - Get the successfully scraped article text string (`story.articleContent`). [258]
-    - Use `fs.writeFileSync(fullPath, story.articleContent, 'utf-8')` to save the text to the file. [259] Wrap this call in a `try...catch` block for file system errors. [260]
-    - Log the successful saving of the file (e.g., "Saved scraped article text to {filename}") or any file writing errors encountered, using the logger. [260]
-  - If `story.articleContent` is null or empty (scraping skipped or failed), ensure _no_ `_article.txt` file is created for this story. [261]
-
-## Acceptance Criteria (ACs)
-
-- AC1: After running `npm run dev`, the date-stamped output directory contains `_article.txt` files _only_ for those stories where `scrapeArticle` (from Story 3.1) succeeded and returned non-empty text content during the pipeline run (Story 3.2). [262]
-- AC2: The name of each article text file is `{storyId}_article.txt`. [263]
-- AC3: The content of each existing `_article.txt` file is the plain text string stored in `story.articleContent`. [264]
-- AC4: Logs confirm the successful writing of each `_article.txt` file or report specific file writing errors. [265]
-- AC5: No empty `_article.txt` files are created. Files only exist if scraping was successful and returned content. [266]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Modify: `src/core/pipeline.ts`.
-  - _(Hint: See `docs/project-structure.md` [818])._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851].
-  - Native `fs` module (`writeFileSync`). [259]
-  - Native `path` module (`join`). [257]
-  - Uses `logger` (Story 1.4).
-  - Uses output directory path (from Story 1.4 logic).
-  - Uses `story.articleContent` populated in Story 3.2.
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - `fs.writeFileSync(fullPath, articleContentString, 'utf-8')`. [259]
-- **Data Structures:**
-  - Checks `story.articleContent` (string | null).
-  - Defines output file format `{storyId}_article.txt` [541].
-  - _(Hint: See `docs/data-models.md` [506-517, 541])._
-- **Environment Variables:**
-  - Relies on `OUTPUT_DIR_PATH` being available (from Story 1.2/1.4).
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Place the file writing logic immediately after the scraping result is known for a story.
-  - Use a clear `if (story.articleContent)` check. [256]
-  - Use `try...catch` around `fs.writeFileSync`. [260]
-  - Log success/failure clearly. [260]
-
-## Tasks / Subtasks
-
-- [ ] In `src/core/pipeline.ts`, ensure `fs` and `path` are imported. Ensure logger is imported.
-- [ ] Ensure the output directory path is available within the story processing loop.
-- [ ] Inside the loop, after `story.articleContent` is set (from Story 3.2):
-  - [ ] Add an `if (story.articleContent)` condition.
-  - [ ] Inside the `if` block:
-    - [ ] Construct filename: `{storyId}_article.txt`.
-    - [ ] Construct full path using `path.join`.
-    - [ ] Implement `try...catch`:
-      - [ ] `try`: Call `fs.writeFileSync(fullPath, story.articleContent, 'utf-8')`.
-      - [ ] `try`: Log success message.
-      - [ ] `catch`: Log error message.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** [915]
-  - Difficult to unit test filesystem writes effectively. Focus on testing the _conditional logic_ within the pipeline function. [918]
-  - Mock `fs.writeFileSync`. Provide mock `Story` objects where `articleContent` is sometimes a string and sometimes null.
-  - Verify `fs.writeFileSync` is called _only when_ `articleContent` is a non-empty string. [262]
-  - Verify it's called with the correct path (`path.join(outputDir, storyId + '_article.txt')`) and content (`story.articleContent`). [263, 264]
-- **Integration Tests:** [921]
-  - Use `mock-fs` or temporary directory setup/teardown. [924]
-  - Run the pipeline segment responsible for scraping (mocked) and saving.
-  - Verify that `.txt` files are created only for stories where the mocked scraper returned text.
-  - Verify file contents match the mocked text.
-- **Manual/CLI Verification:** [912]
-  - Run `npm run dev`.
-  - Inspect the `output/YYYY-MM-DD/` directory.
-  - Check which `{storyId}_article.txt` files exist. Compare this against the console logs indicating successful/failed scraping attempts for corresponding story IDs. Verify files only exist for successful scrapes (AC1, AC5).
-  - Check filenames are correct (AC2).
-  - Open a few existing `.txt` files and spot-check the content (AC3).
-  - Check logs for file saving success/error messages (AC4).
-- _(Hint: See `docs/testing-strategy.md` [907-950] for the overall approach)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Added logic to save article text conditionally. Verified files are created only on successful scrape.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-**File: ai/stories/3.4.story.md**
-
-```markdown
-# Story 3.4: Implement Stage Testing Utility for Scraping
-
-**Status:** Draft
-
-## Goal & Context
-
-**User Story:** As a developer, I want a separate script/command to test the article scraping logic using HN story data from local files, allowing independent testing and debugging of the scraper. [267]
-
-**Context:** This story implements the standalone stage testing utility for Epic 3, as required by the PRD [736, 764]. It creates `src/stages/scrape_articles.ts`, which reads story data (specifically URLs) from the `{storyId}_data.json` files generated in Epic 2 (or by `stage:fetch`), calls the `scrapeArticle` function (from Story 3.1) for each URL, and persists any successfully scraped text to `{storyId}_article.txt` files (replicating Story 3.3 logic). This allows testing the scraping functionality against real websites using previously fetched story lists, without running the full pipeline or the HN fetching stage. [57, 63, 820, 912, 930]
-
-## Detailed Requirements
-
-- Create a new standalone script file: `src/stages/scrape_articles.ts`. [268]
-- Import necessary modules: `fs` (e.g., `readdirSync`, `readFileSync`, `writeFileSync`, `existsSync`, `statSync`), `path`, `logger` (Story 1.4), `config` (Story 1.2), `scrapeArticle` (Story 3.1), date util (Story 1.4). [269]
-- The script should:
-  - Initialize the logger. [270]
-  - Load configuration (to get `OUTPUT_DIR_PATH`). [271]
-  - Determine the target date-stamped directory path (e.g., using current date via date util, or potentially allow override via CLI arg later - current date default is fine for now). [271] Ensure this base output directory exists. Log the target directory.
-  - Check if the target date-stamped directory exists. If not, log an error and exit ("Directory {path} not found. Run fetch stage first?").
-  - Read the directory contents and identify all files ending with `_data.json`. [272] Use `fs.readdirSync` and filter.
-  - For each `_data.json` file found:
-    - Construct the full path and read its content using `fs.readFileSync`. [273]
-    - Parse the JSON content. Handle potential parse errors gracefully (log error, skip file). [273]
-    - Extract the `storyId` and `articleUrl` from the parsed data. [274]
-    - If a valid `articleUrl` exists (starts with `http`): [274]
-      - Log the attempt: "Attempting scrape for story {storyId} from {url}...".
-      - Call `await scrapeArticle(articleUrl)`. [274]
-      - If scraping succeeds (returns a non-null string):
-        - Construct the output filename `{storyId}_article.txt`. [275]
-        - Construct the full output path. [275]
-        - Save the text to the file using `fs.writeFileSync` (replicating logic from Story 3.3, including try/catch and logging). [275] Overwrite if the file exists. [276]
-        - Log success outcome.
-      - If scraping fails (`scrapeArticle` returns null):
-        - Log failure outcome.
-    - If `articleUrl` is missing or invalid:
-      - Log skipping message.
-  - Log overall completion: "Scraping stage finished processing {N} data files.".
-- Add a new script command to `package.json`: `"stage:scrape": "ts-node src/stages/scrape_articles.ts"`. [277]
-
-## Acceptance Criteria (ACs)
-
-- AC1: The file `src/stages/scrape_articles.ts` exists. [279]
-- AC2: The script `stage:scrape` is defined in `package.json`'s `scripts` section. [280]
-- AC3: Running `npm run stage:scrape` (assuming a date-stamped directory with `_data.json` files exists from a previous fetch run) successfully reads these JSON files. [281]
-- AC4: The script calls `scrapeArticle` for stories with valid `articleUrl`s found in the JSON files. [282]
-- AC5: The script creates or updates `{storyId}_article.txt` files in the _same_ date-stamped directory, corresponding only to successfully scraped articles. [283]
-- AC6: The script logs its actions (reading files, attempting scraping, skipping, saving results/failures) for each story ID processed based on the found `_data.json` files. [284]
-- AC7: The script operates solely based on local `_data.json` files as input and fetching from external article URLs via `scrapeArticle`; it does not call the Algolia HN API client. [285, 286]
-
-## Technical Implementation Context
-
-**Guidance:** Use the following details for implementation. Refer to the linked `docs/` files for broader context if needed.
-
-- **Relevant Files:**
-  - Files to Create: `src/stages/scrape_articles.ts`.
-  - Files to Modify: `package.json`.
-  - _(Hint: See `docs/project-structure.md` [820] for stage runner location)._
-- **Key Technologies:**
-  - TypeScript [846], Node.js 22.x [851], `ts-node`.
-  - Native `fs` module (`readdirSync`, `readFileSync`, `writeFileSync`, `existsSync`, `statSync`). [269]
-  - Native `path` module. [269]
-  - Uses `logger` (Story 1.4), `config` (Story 1.2), date util (Story 1.4), `scrapeArticle` (Story 3.1), persistence logic (Story 3.3).
-  - _(Hint: See `docs/tech-stack.md` [839-905])._
-- **API Interactions / SDK Usage:**
-  - Calls internal `scrapeArticle(url)`.
-  - Uses `fs` module extensively for reading directory, reading JSON, writing TXT.
-- **Data Structures:**
-  - Reads JSON structure from `_data.json` files [538-540]. Extracts `storyId`, `articleUrl`.
-  - Creates `{storyId}_article.txt` files [541].
-  - _(Hint: See `docs/data-models.md`)._
-- **Environment Variables:**
-  - Reads `OUTPUT_DIR_PATH` via `config.ts`. `scrapeArticle` might use others.
-  - _(Hint: See `docs/environment-vars.md` [548-638])._
-- **Coding Standards Notes:**
-  - Structure script clearly (setup, read data files, loop, process/scrape/save).
-  - Use `async/await` for `scrapeArticle`.
-  - Implement robust error handling for file IO (reading dir, reading files, parsing JSON, writing files) using `try...catch` and logging.
-  - Use logger for detailed progress reporting. [284]
-  - Wrap main logic in an async IIFE or main function.
-
-## Tasks / Subtasks
-
-- [ ] Create `src/stages/scrape_articles.ts`.
-- [ ] Add imports: `fs`, `path`, `logger`, `config`, `scrapeArticle`, date util.
-- [ ] Implement setup: Init logger, load config, get output path, get target date-stamped path.
-- [ ] Check if target date-stamped directory exists, log error and exit if not.
-- [ ] Use `fs.readdirSync` to get list of files in the target directory.
-- [ ] Filter the list to get only files ending in `_data.json`.
-- [ ] Loop through the `_data.json` filenames:
-  - [ ] Construct full path for the JSON file.
-  - [ ] Use `try...catch` for reading and parsing the JSON file:
-    - [ ] `try`: Read file (`fs.readFileSync`). Parse JSON (`JSON.parse`).
-    - [ ] `catch`: Log error (read/parse), continue to next file.
-  - [ ] Extract `storyId` and `articleUrl`.
-  - [ ] Check if `articleUrl` is valid (starts with `http`).
-  - [ ] If valid:
-    - [ ] Log attempt.
-    - [ ] Call `content = await scrapeArticle(articleUrl)`.
-    - [ ] `if (content)`:
-      - [ ] Construct `.txt` output path.
-      - [ ] Use `try...catch` to write file (`fs.writeFileSync`). Log success/error.
-    - [ ] `else`: Log scrape failure.
-  - [ ] If URL invalid: Log skip.
-- [ ] Log completion message.
-- [ ] Add `"stage:scrape": "ts-node src/stages/scrape_articles.ts"` to `package.json`.
-
-## Testing Requirements
-
-**Guidance:** Verify implementation against the ACs using the following tests.
-
-- **Unit Tests:** Difficult to unit test the entire script effectively due to heavy FS and orchestration logic. Focus on unit testing the core `scrapeArticle` module (Story 3.1) and utilities. [915]
-- **Integration Tests:** N/A for the script itself. [921]
-- **Manual/CLI Verification (Primary Test Method):** [912, 927, 930]
-  - Ensure `_data.json` files exist from `npm run stage:fetch` or `npm run dev`.
-  - Run `npm run stage:scrape`. [281]
-  - Verify successful execution.
-  - Check logs for reading files, skipping, attempting scrapes, success/failure messages, and saving messages [284].
-  - Inspect the `output/YYYY-MM-DD/` directory for newly created/updated `{storyId}_article.txt` files. Verify they correspond to stories where scraping succeeded according to logs [283, 285].
-  - Verify the script _only_ performed scraping actions based on local files (AC7).
-  - Modify `package.json` to add the script (AC2).
-- _(Hint: See `docs/testing-strategy.md` [907-950] which identifies Stage Runners as a key part of Acceptance Testing)._
-
-## Story Wrap Up (Agent Populates After Execution)
-
-- **Agent Model Used:** `<Agent Model Name/Version>`
-- **Completion Notes:** {Stage runner implemented. Reads \_data.json, calls scraper, saves \_article.txt conditionally. package.json updated.}
-- **Change Log:**
-  - Initial Draft
-```
-
----
-
-## **End of Report for Epic 3**

V2-FULL-DEMO-WALKTHROUGH/epic1.md

@@ -1,89 +0,0 @@
-# Epic 1: Project Initialization & Core Setup
-
-**Goal:** Initialize the project using the "bmad-boilerplate", manage dependencies, setup `.env` and config loading, establish basic CLI entry point, setup basic logging and output directory structure. This provides the foundational setup for all subsequent development work.
-
-## Story List
-
-### Story 1.1: Initialize Project from Boilerplate
-
--   **User Story / Goal:** As a developer, I want to set up the initial project structure using the `bmad-boilerplate`, so that I have the standard tooling (TS, Jest, ESLint, Prettier), configurations, and scripts in place.
--   **Detailed Requirements:**
-    -   Copy or clone the contents of the `bmad-boilerplate` into the new project's root directory.
-    -   Initialize a git repository in the project root directory (if not already done by cloning).
-    -   Ensure the `.gitignore` file from the boilerplate is present.
-    -   Run `npm install` to download and install all `devDependencies` specified in the boilerplate's `package.json`.
-    -   Verify that the core boilerplate scripts (`lint`, `format`, `test`, `build`) execute without errors on the initial codebase.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The project directory contains the files and structure from `bmad-boilerplate`.
-    -   AC2: A `node_modules` directory exists and contains packages corresponding to `devDependencies`.
-    -   AC3: `npm run lint` command completes successfully without reporting any linting errors.
-    -   AC4: `npm run format` command completes successfully, potentially making formatting changes according to Prettier rules. Running it a second time should result in no changes.
-    -   AC5: `npm run test` command executes Jest successfully (it may report "no tests found" which is acceptable at this stage).
-    -   AC6: `npm run build` command executes successfully, creating a `dist` directory containing compiled JavaScript output.
-    -   AC7: The `.gitignore` file exists and includes entries for `node_modules/`, `.env`, `dist/`, etc. as specified in the boilerplate.
-
----
-
-### Story 1.2: Setup Environment Configuration
-
--   **User Story / Goal:** As a developer, I want to establish the environment configuration mechanism using `.env` files, so that secrets and settings (like output paths) can be managed outside of version control, following boilerplate conventions.
--   **Detailed Requirements:**
-    -   Verify the `.env.example` file exists (from boilerplate).
-    -   Add an initial configuration variable `OUTPUT_DIR_PATH=./output` to `.env.example`.
-    -   Create the `.env` file locally by copying `.env.example`. Populate `OUTPUT_DIR_PATH` if needed (can keep default).
-    -   Implement a utility module (e.g., `src/config.ts`) that loads environment variables from the `.env` file at application startup.
-    -   The utility should export the loaded configuration values (initially just `OUTPUT_DIR_PATH`).
-    -   Ensure the `.env` file is listed in `.gitignore` and is not committed.
--   **Acceptance Criteria (ACs):**
-    -   AC1: Handle `.env` files with native node 22 support, no need for `dotenv`
-    -   AC2: The `.env.example` file exists, is tracked by git, and contains the line `OUTPUT_DIR_PATH=./output`.
-    -   AC3: The `.env` file exists locally but is NOT tracked by git.
-    -   AC4: A configuration module (`src/config.ts` or similar) exists and successfully loads the `OUTPUT_DIR_PATH` value from `.env` when the application starts.
-    -   AC5: The loaded `OUTPUT_DIR_PATH` value is accessible within the application code.
-
----
-
-### Story 1.3: Implement Basic CLI Entry Point & Execution
-
--   **User Story / Goal:** As a developer, I want a basic `src/index.ts` entry point that can be executed via the boilerplate's `dev` and `start` scripts, providing a working foundation for the application logic.
--   **Detailed Requirements:**
-    -   Create the main application entry point file at `src/index.ts`.
-    -   Implement minimal code within `src/index.ts` to:
-        -   Import the configuration loading mechanism (from Story 1.2).
-        -   Log a simple startup message to the console (e.g., "BMad Hacker Daily Digest - Starting Up...").
-        -   (Optional) Log the loaded `OUTPUT_DIR_PATH` to verify config loading.
-    -   Confirm execution using boilerplate scripts.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `src/index.ts` file exists.
-    -   AC2: Running `npm run dev` executes `src/index.ts` via `ts-node` and logs the startup message to the console.
-    -   AC3: Running `npm run build` successfully compiles `src/index.ts` (and any imports) into the `dist` directory.
-    -   AC4: Running `npm start` (after a successful build) executes the compiled code from `dist` and logs the startup message to the console.
-
----
-
-### Story 1.4: Setup Basic Logging and Output Directory
-
--   **User Story / Goal:** As a developer, I want a basic console logging mechanism and the dynamic creation of a date-stamped output directory, so that the application can provide execution feedback and prepare for storing data artifacts in subsequent epics.
--   **Detailed Requirements:**
-    -   Implement a simple, reusable logging utility module (e.g., `src/logger.ts`). Initially, it can wrap `console.log`, `console.warn`, `console.error`.
-    -   Refactor `src/index.ts` to use this `logger` for its startup message(s).
-    -   In `src/index.ts` (or a setup function called by it):
-        -   Retrieve the `OUTPUT_DIR_PATH` from the configuration (loaded in Story 1.2).
-        -   Determine the current date in 'YYYY-MM-DD' format.
-        -   Construct the full path for the date-stamped subdirectory (e.g., `${OUTPUT_DIR_PATH}/YYYY-MM-DD`).
-        -   Check if the base output directory exists; if not, create it.
-        -   Check if the date-stamped subdirectory exists; if not, create it recursively. Use Node.js `fs` module (e.g., `fs.mkdirSync(path, { recursive: true })`).
-        -   Log (using the logger) the full path of the output directory being used for the current run (e.g., "Output directory for this run: ./output/2025-05-04").
--   **Acceptance Criteria (ACs):**
-    -   AC1: A logger utility module (`src/logger.ts` or similar) exists and is used for console output in `src/index.ts`.
-    -   AC2: Running `npm run dev` or `npm start` logs the startup message via the logger.
-    -   AC3: Running the application creates the base output directory (e.g., `./output` defined in `.env`) if it doesn't already exist.
-    -   AC4: Running the application creates a date-stamped subdirectory (e.g., `./output/2025-05-04`) within the base output directory if it doesn't already exist.
-    -   AC5: The application logs a message indicating the full path to the date-stamped output directory created/used for the current execution.
-    -   AC6: The application exits gracefully after performing these setup steps (for now).
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 1     | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic1.txt

@@ -1,89 +0,0 @@
-# Epic 1: Project Initialization & Core Setup
-
-**Goal:** Initialize the project using the "bmad-boilerplate", manage dependencies, setup `.env` and config loading, establish basic CLI entry point, setup basic logging and output directory structure. This provides the foundational setup for all subsequent development work.
-
-## Story List
-
-### Story 1.1: Initialize Project from Boilerplate
-
--   **User Story / Goal:** As a developer, I want to set up the initial project structure using the `bmad-boilerplate`, so that I have the standard tooling (TS, Jest, ESLint, Prettier), configurations, and scripts in place.
--   **Detailed Requirements:**
-    -   Copy or clone the contents of the `bmad-boilerplate` into the new project's root directory.
-    -   Initialize a git repository in the project root directory (if not already done by cloning).
-    -   Ensure the `.gitignore` file from the boilerplate is present.
-    -   Run `npm install` to download and install all `devDependencies` specified in the boilerplate's `package.json`.
-    -   Verify that the core boilerplate scripts (`lint`, `format`, `test`, `build`) execute without errors on the initial codebase.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The project directory contains the files and structure from `bmad-boilerplate`.
-    -   AC2: A `node_modules` directory exists and contains packages corresponding to `devDependencies`.
-    -   AC3: `npm run lint` command completes successfully without reporting any linting errors.
-    -   AC4: `npm run format` command completes successfully, potentially making formatting changes according to Prettier rules. Running it a second time should result in no changes.
-    -   AC5: `npm run test` command executes Jest successfully (it may report "no tests found" which is acceptable at this stage).
-    -   AC6: `npm run build` command executes successfully, creating a `dist` directory containing compiled JavaScript output.
-    -   AC7: The `.gitignore` file exists and includes entries for `node_modules/`, `.env`, `dist/`, etc. as specified in the boilerplate.
-
----
-
-### Story 1.2: Setup Environment Configuration
-
--   **User Story / Goal:** As a developer, I want to establish the environment configuration mechanism using `.env` files, so that secrets and settings (like output paths) can be managed outside of version control, following boilerplate conventions.
--   **Detailed Requirements:**
-    -   Verify the `.env.example` file exists (from boilerplate).
-    -   Add an initial configuration variable `OUTPUT_DIR_PATH=./output` to `.env.example`.
-    -   Create the `.env` file locally by copying `.env.example`. Populate `OUTPUT_DIR_PATH` if needed (can keep default).
-    -   Implement a utility module (e.g., `src/config.ts`) that loads environment variables from the `.env` file at application startup.
-    -   The utility should export the loaded configuration values (initially just `OUTPUT_DIR_PATH`).
-    -   Ensure the `.env` file is listed in `.gitignore` and is not committed.
--   **Acceptance Criteria (ACs):**
-    -   AC1: Handle `.env` files with native node 22 support, no need for `dotenv`
-    -   AC2: The `.env.example` file exists, is tracked by git, and contains the line `OUTPUT_DIR_PATH=./output`.
-    -   AC3: The `.env` file exists locally but is NOT tracked by git.
-    -   AC4: A configuration module (`src/config.ts` or similar) exists and successfully loads the `OUTPUT_DIR_PATH` value from `.env` when the application starts.
-    -   AC5: The loaded `OUTPUT_DIR_PATH` value is accessible within the application code.
-
----
-
-### Story 1.3: Implement Basic CLI Entry Point & Execution
-
--   **User Story / Goal:** As a developer, I want a basic `src/index.ts` entry point that can be executed via the boilerplate's `dev` and `start` scripts, providing a working foundation for the application logic.
--   **Detailed Requirements:**
-    -   Create the main application entry point file at `src/index.ts`.
-    -   Implement minimal code within `src/index.ts` to:
-        -   Import the configuration loading mechanism (from Story 1.2).
-        -   Log a simple startup message to the console (e.g., "BMad Hacker Daily Digest - Starting Up...").
-        -   (Optional) Log the loaded `OUTPUT_DIR_PATH` to verify config loading.
-    -   Confirm execution using boilerplate scripts.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `src/index.ts` file exists.
-    -   AC2: Running `npm run dev` executes `src/index.ts` via `ts-node` and logs the startup message to the console.
-    -   AC3: Running `npm run build` successfully compiles `src/index.ts` (and any imports) into the `dist` directory.
-    -   AC4: Running `npm start` (after a successful build) executes the compiled code from `dist` and logs the startup message to the console.
-
----
-
-### Story 1.4: Setup Basic Logging and Output Directory
-
--   **User Story / Goal:** As a developer, I want a basic console logging mechanism and the dynamic creation of a date-stamped output directory, so that the application can provide execution feedback and prepare for storing data artifacts in subsequent epics.
--   **Detailed Requirements:**
-    -   Implement a simple, reusable logging utility module (e.g., `src/logger.ts`). Initially, it can wrap `console.log`, `console.warn`, `console.error`.
-    -   Refactor `src/index.ts` to use this `logger` for its startup message(s).
-    -   In `src/index.ts` (or a setup function called by it):
-        -   Retrieve the `OUTPUT_DIR_PATH` from the configuration (loaded in Story 1.2).
-        -   Determine the current date in 'YYYY-MM-DD' format.
-        -   Construct the full path for the date-stamped subdirectory (e.g., `${OUTPUT_DIR_PATH}/YYYY-MM-DD`).
-        -   Check if the base output directory exists; if not, create it.
-        -   Check if the date-stamped subdirectory exists; if not, create it recursively. Use Node.js `fs` module (e.g., `fs.mkdirSync(path, { recursive: true })`).
-        -   Log (using the logger) the full path of the output directory being used for the current run (e.g., "Output directory for this run: ./output/2025-05-04").
--   **Acceptance Criteria (ACs):**
-    -   AC1: A logger utility module (`src/logger.ts` or similar) exists and is used for console output in `src/index.ts`.
-    -   AC2: Running `npm run dev` or `npm start` logs the startup message via the logger.
-    -   AC3: Running the application creates the base output directory (e.g., `./output` defined in `.env`) if it doesn't already exist.
-    -   AC4: Running the application creates a date-stamped subdirectory (e.g., `./output/2025-05-04`) within the base output directory if it doesn't already exist.
-    -   AC5: The application logs a message indicating the full path to the date-stamped output directory created/used for the current execution.
-    -   AC6: The application exits gracefully after performing these setup steps (for now).
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 1     | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic2.md

@@ -1,99 +0,0 @@
-# Epic 2: HN Data Acquisition & Persistence
-
-**Goal:** Implement fetching top 10 stories and their comments (respecting limits) from Algolia HN API, and persist this raw data locally into the date-stamped output directory created in Epic 1. Implement a stage testing utility for fetching.
-
-## Story List
-
-### Story 2.1: Implement Algolia HN API Client
-
--   **User Story / Goal:** As a developer, I want a dedicated client module to interact with the Algolia Hacker News Search API, so that fetching stories and comments is encapsulated, reusable, and uses the required native `Workspace` API.
--   **Detailed Requirements:**
-    -   Create a new module: `src/clients/algoliaHNClient.ts`.
-    -   Implement an async function `WorkspaceTopStories` within the client:
-        -   Use native `Workspace` to call the Algolia HN Search API endpoint for front-page stories (e.g., `http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10`). Adjust `hitsPerPage` if needed to ensure 10 stories.
-        -   Parse the JSON response.
-        -   Extract required metadata for each story: `objectID` (use as `storyId`), `title`, `url` (article URL), `points`, `num_comments`. Handle potential missing `url` field gracefully (log warning, maybe skip story later if URL needed).
-        -   Construct the `hnUrl` for each story (e.g., `https://news.ycombinator.com/item?id={storyId}`).
-        -   Return an array of structured story objects.
-    -   Implement a separate async function `WorkspaceCommentsForStory` within the client:
-        -   Accept `storyId` and `maxComments` limit as arguments.
-        -   Use native `Workspace` to call the Algolia HN Search API endpoint for comments of a specific story (e.g., `http://hn.algolia.com/api/v1/search?tags=comment,story_{storyId}&hitsPerPage={maxComments}`).
-        -   Parse the JSON response.
-        -   Extract required comment data: `objectID` (use as `commentId`), `comment_text`, `author`, `created_at`.
-        -   Filter out comments where `comment_text` is null or empty. Ensure only up to `maxComments` are returned.
-        -   Return an array of structured comment objects.
-    -   Implement basic error handling using `try...catch` around `Workspace` calls and check `response.ok` status. Log errors using the logger utility from Epic 1.
-    -   Define TypeScript interfaces/types for the expected structures of API responses (stories, comments) and the data returned by the client functions (e.g., `Story`, `Comment`).
--   **Acceptance Criteria (ACs):**
-    -   AC1: The module `src/clients/algoliaHNClient.ts` exists and exports `WorkspaceTopStories` and `WorkspaceCommentsForStory` functions.
-    -   AC2: Calling `WorkspaceTopStories` makes a network request to the correct Algolia endpoint and returns a promise resolving to an array of 10 `Story` objects containing the specified metadata.
-    -   AC3: Calling `WorkspaceCommentsForStory` with a valid `storyId` and `maxComments` limit makes a network request to the correct Algolia endpoint and returns a promise resolving to an array of `Comment` objects (up to `maxComments`), filtering out empty ones.
-    -   AC4: Both functions use the native `Workspace` API internally.
-    -   AC5: Network errors or non-successful API responses (e.g., status 4xx, 5xx) are caught and logged using the logger.
-    -   AC6: Relevant TypeScript types (`Story`, `Comment`, etc.) are defined and used within the client module.
-
----
-
-### Story 2.2: Integrate HN Data Fetching into Main Workflow
-
--   **User Story / Goal:** As a developer, I want to integrate the HN data fetching logic into the main application workflow (`src/index.ts`), so that running the app retrieves the top 10 stories and their comments after completing the setup from Epic 1.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts` (or a main async function called by it).
-    -   Import the `algoliaHNClient` functions.
-    -   Import the configuration module to access `MAX_COMMENTS_PER_STORY`.
-    -   After the Epic 1 setup (config load, logger init, output dir creation), call `WorkspaceTopStories()`.
-    -   Log the number of stories fetched.
-    -   Iterate through the array of fetched `Story` objects.
-    -   For each `Story`, call `WorkspaceCommentsForStory()`, passing the `story.storyId` and the configured `MAX_COMMENTS_PER_STORY`.
-    -   Store the fetched comments within the corresponding `Story` object in memory (e.g., add a `comments: Comment[]` property to the `Story` object).
-    -   Log progress using the logger utility (e.g., "Fetched 10 stories.", "Fetching up to X comments for story {storyId}...").
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes Epic 1 setup steps followed by fetching stories and then comments for each story.
-    -   AC2: Logs clearly show the start and successful completion of fetching stories, and the start of fetching comments for each of the 10 stories.
-    -   AC3: The configured `MAX_COMMENTS_PER_STORY` value is read from config and used in the calls to `WorkspaceCommentsForStory`.
-    -   AC4: After successful execution, story objects held in memory contain a nested array of fetched comment objects. (Can be verified via debugger or temporary logging).
-
----
-
-### Story 2.3: Persist Fetched HN Data Locally
-
--   **User Story / Goal:** As a developer, I want to save the fetched HN stories (including their comments) to JSON files in the date-stamped output directory, so that the raw data is persisted locally for subsequent pipeline stages and debugging.
--   **Detailed Requirements:**
-    -   Define a consistent JSON structure for the output file content. Example: `{ storyId: "...", title: "...", url: "...", hnUrl: "...", points: ..., fetchedAt: "ISO_TIMESTAMP", comments: [{ commentId: "...", text: "...", author: "...", createdAt: "ISO_TIMESTAMP", ... }, ...] }`. Include a timestamp for when the data was fetched.
-    -   Import Node.js `fs` (specifically `fs.writeFileSync`) and `path` modules.
-    -   In the main workflow (`src/index.ts`), within the loop iterating through stories (after comments have been fetched and added to the story object in Story 2.2):
-        -   Get the full path to the date-stamped output directory (determined in Epic 1).
-        -   Construct the filename for the story's data: `{storyId}_data.json`.
-        -   Construct the full file path using `path.join()`.
-        -   Serialize the complete story object (including comments and fetch timestamp) to a JSON string using `JSON.stringify(storyObject, null, 2)` for readability.
-        -   Write the JSON string to the file using `fs.writeFileSync()`. Use a `try...catch` block for error handling.
-    -   Log (using the logger) the successful persistence of each story's data file or any errors encountered during file writing.
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory (e.g., `./output/YYYY-MM-DD/`) contains exactly 10 files named `{storyId}_data.json`.
-    -   AC2: Each JSON file contains valid JSON representing a single story object, including its metadata, fetch timestamp, and an array of its fetched comments, matching the defined structure.
-    -   AC3: The number of comments in each file's `comments` array does not exceed `MAX_COMMENTS_PER_STORY`.
-    -   AC4: Logs indicate that saving data to a file was attempted for each story, reporting success or specific file writing errors.
-
----
-
-### Story 2.4: Implement Stage Testing Utility for HN Fetching
-
--   **User Story / Goal:** As a developer, I want a separate, executable script that *only* performs the HN data fetching and persistence, so I can test and trigger this stage independently of the full pipeline.
--   **Detailed Requirements:**
-    -   Create a new standalone script file: `src/stages/fetch_hn_data.ts`.
-    -   This script should perform the essential setup required for this stage: initialize logger, load configuration (`.env`), determine and create output directory (reuse or replicate logic from Epic 1 / `src/index.ts`).
-    -   The script should then execute the core logic of fetching stories via `algoliaHNClient.fetchTopStories`, fetching comments via `algoliaHNClient.fetchCommentsForStory` (using loaded config for limit), and persisting the results to JSON files using `fs.writeFileSync` (replicating logic from Story 2.3).
-    -   The script should log its progress using the logger utility.
-    -   Add a new script command to `package.json` under `"scripts"`: `"stage:fetch": "ts-node src/stages/fetch_hn_data.ts"`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/fetch_hn_data.ts` exists.
-    -   AC2: The script `stage:fetch` is defined in `package.json`'s `scripts` section.
-    -   AC3: Running `npm run stage:fetch` executes successfully, performing only the setup, fetch, and persist steps.
-    -   AC4: Running `npm run stage:fetch` creates the same 10 `{storyId}_data.json` files in the correct date-stamped output directory as running the main `npm run dev` command (at the current state of development).
-    -   AC5: Logs generated by `npm run stage:fetch` reflect only the fetching and persisting steps, not subsequent pipeline stages.
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 2     | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic2.txt

@@ -1,99 +0,0 @@
-# Epic 2: HN Data Acquisition & Persistence
-
-**Goal:** Implement fetching top 10 stories and their comments (respecting limits) from Algolia HN API, and persist this raw data locally into the date-stamped output directory created in Epic 1. Implement a stage testing utility for fetching.
-
-## Story List
-
-### Story 2.1: Implement Algolia HN API Client
-
--   **User Story / Goal:** As a developer, I want a dedicated client module to interact with the Algolia Hacker News Search API, so that fetching stories and comments is encapsulated, reusable, and uses the required native `Workspace` API.
--   **Detailed Requirements:**
-    -   Create a new module: `src/clients/algoliaHNClient.ts`.
-    -   Implement an async function `WorkspaceTopStories` within the client:
-        -   Use native `Workspace` to call the Algolia HN Search API endpoint for front-page stories (e.g., `http://hn.algolia.com/api/v1/search?tags=front_page&hitsPerPage=10`). Adjust `hitsPerPage` if needed to ensure 10 stories.
-        -   Parse the JSON response.
-        -   Extract required metadata for each story: `objectID` (use as `storyId`), `title`, `url` (article URL), `points`, `num_comments`. Handle potential missing `url` field gracefully (log warning, maybe skip story later if URL needed).
-        -   Construct the `hnUrl` for each story (e.g., `https://news.ycombinator.com/item?id={storyId}`).
-        -   Return an array of structured story objects.
-    -   Implement a separate async function `WorkspaceCommentsForStory` within the client:
-        -   Accept `storyId` and `maxComments` limit as arguments.
-        -   Use native `Workspace` to call the Algolia HN Search API endpoint for comments of a specific story (e.g., `http://hn.algolia.com/api/v1/search?tags=comment,story_{storyId}&hitsPerPage={maxComments}`).
-        -   Parse the JSON response.
-        -   Extract required comment data: `objectID` (use as `commentId`), `comment_text`, `author`, `created_at`.
-        -   Filter out comments where `comment_text` is null or empty. Ensure only up to `maxComments` are returned.
-        -   Return an array of structured comment objects.
-    -   Implement basic error handling using `try...catch` around `Workspace` calls and check `response.ok` status. Log errors using the logger utility from Epic 1.
-    -   Define TypeScript interfaces/types for the expected structures of API responses (stories, comments) and the data returned by the client functions (e.g., `Story`, `Comment`).
--   **Acceptance Criteria (ACs):**
-    -   AC1: The module `src/clients/algoliaHNClient.ts` exists and exports `WorkspaceTopStories` and `WorkspaceCommentsForStory` functions.
-    -   AC2: Calling `WorkspaceTopStories` makes a network request to the correct Algolia endpoint and returns a promise resolving to an array of 10 `Story` objects containing the specified metadata.
-    -   AC3: Calling `WorkspaceCommentsForStory` with a valid `storyId` and `maxComments` limit makes a network request to the correct Algolia endpoint and returns a promise resolving to an array of `Comment` objects (up to `maxComments`), filtering out empty ones.
-    -   AC4: Both functions use the native `Workspace` API internally.
-    -   AC5: Network errors or non-successful API responses (e.g., status 4xx, 5xx) are caught and logged using the logger.
-    -   AC6: Relevant TypeScript types (`Story`, `Comment`, etc.) are defined and used within the client module.
-
----
-
-### Story 2.2: Integrate HN Data Fetching into Main Workflow
-
--   **User Story / Goal:** As a developer, I want to integrate the HN data fetching logic into the main application workflow (`src/index.ts`), so that running the app retrieves the top 10 stories and their comments after completing the setup from Epic 1.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts` (or a main async function called by it).
-    -   Import the `algoliaHNClient` functions.
-    -   Import the configuration module to access `MAX_COMMENTS_PER_STORY`.
-    -   After the Epic 1 setup (config load, logger init, output dir creation), call `WorkspaceTopStories()`.
-    -   Log the number of stories fetched.
-    -   Iterate through the array of fetched `Story` objects.
-    -   For each `Story`, call `WorkspaceCommentsForStory()`, passing the `story.storyId` and the configured `MAX_COMMENTS_PER_STORY`.
-    -   Store the fetched comments within the corresponding `Story` object in memory (e.g., add a `comments: Comment[]` property to the `Story` object).
-    -   Log progress using the logger utility (e.g., "Fetched 10 stories.", "Fetching up to X comments for story {storyId}...").
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes Epic 1 setup steps followed by fetching stories and then comments for each story.
-    -   AC2: Logs clearly show the start and successful completion of fetching stories, and the start of fetching comments for each of the 10 stories.
-    -   AC3: The configured `MAX_COMMENTS_PER_STORY` value is read from config and used in the calls to `WorkspaceCommentsForStory`.
-    -   AC4: After successful execution, story objects held in memory contain a nested array of fetched comment objects. (Can be verified via debugger or temporary logging).
-
----
-
-### Story 2.3: Persist Fetched HN Data Locally
-
--   **User Story / Goal:** As a developer, I want to save the fetched HN stories (including their comments) to JSON files in the date-stamped output directory, so that the raw data is persisted locally for subsequent pipeline stages and debugging.
--   **Detailed Requirements:**
-    -   Define a consistent JSON structure for the output file content. Example: `{ storyId: "...", title: "...", url: "...", hnUrl: "...", points: ..., fetchedAt: "ISO_TIMESTAMP", comments: [{ commentId: "...", text: "...", author: "...", createdAt: "ISO_TIMESTAMP", ... }, ...] }`. Include a timestamp for when the data was fetched.
-    -   Import Node.js `fs` (specifically `fs.writeFileSync`) and `path` modules.
-    -   In the main workflow (`src/index.ts`), within the loop iterating through stories (after comments have been fetched and added to the story object in Story 2.2):
-        -   Get the full path to the date-stamped output directory (determined in Epic 1).
-        -   Construct the filename for the story's data: `{storyId}_data.json`.
-        -   Construct the full file path using `path.join()`.
-        -   Serialize the complete story object (including comments and fetch timestamp) to a JSON string using `JSON.stringify(storyObject, null, 2)` for readability.
-        -   Write the JSON string to the file using `fs.writeFileSync()`. Use a `try...catch` block for error handling.
-    -   Log (using the logger) the successful persistence of each story's data file or any errors encountered during file writing.
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory (e.g., `./output/YYYY-MM-DD/`) contains exactly 10 files named `{storyId}_data.json`.
-    -   AC2: Each JSON file contains valid JSON representing a single story object, including its metadata, fetch timestamp, and an array of its fetched comments, matching the defined structure.
-    -   AC3: The number of comments in each file's `comments` array does not exceed `MAX_COMMENTS_PER_STORY`.
-    -   AC4: Logs indicate that saving data to a file was attempted for each story, reporting success or specific file writing errors.
-
----
-
-### Story 2.4: Implement Stage Testing Utility for HN Fetching
-
--   **User Story / Goal:** As a developer, I want a separate, executable script that *only* performs the HN data fetching and persistence, so I can test and trigger this stage independently of the full pipeline.
--   **Detailed Requirements:**
-    -   Create a new standalone script file: `src/stages/fetch_hn_data.ts`.
-    -   This script should perform the essential setup required for this stage: initialize logger, load configuration (`.env`), determine and create output directory (reuse or replicate logic from Epic 1 / `src/index.ts`).
-    -   The script should then execute the core logic of fetching stories via `algoliaHNClient.fetchTopStories`, fetching comments via `algoliaHNClient.fetchCommentsForStory` (using loaded config for limit), and persisting the results to JSON files using `fs.writeFileSync` (replicating logic from Story 2.3).
-    -   The script should log its progress using the logger utility.
-    -   Add a new script command to `package.json` under `"scripts"`: `"stage:fetch": "ts-node src/stages/fetch_hn_data.ts"`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/fetch_hn_data.ts` exists.
-    -   AC2: The script `stage:fetch` is defined in `package.json`'s `scripts` section.
-    -   AC3: Running `npm run stage:fetch` executes successfully, performing only the setup, fetch, and persist steps.
-    -   AC4: Running `npm run stage:fetch` creates the same 10 `{storyId}_data.json` files in the correct date-stamped output directory as running the main `npm run dev` command (at the current state of development).
-    -   AC5: Logs generated by `npm run stage:fetch` reflect only the fetching and persisting steps, not subsequent pipeline stages.
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 2     | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic3.md

@@ -1,111 +0,0 @@
-# Epic 3: Article Scraping & Persistence
-
-**Goal:** Implement a best-effort article scraping mechanism to fetch and extract plain text content from the external URLs associated with fetched HN stories. Handle failures gracefully and persist successfully scraped text locally. Implement a stage testing utility for scraping.
-
-## Story List
-
-### Story 3.1: Implement Basic Article Scraper Module
-
--   **User Story / Goal:** As a developer, I want a module that attempts to fetch HTML from a URL and extract the main article text using basic methods, handling common failures gracefully, so article content can be prepared for summarization.
--   **Detailed Requirements:**
-    -   Create a new module: `src/scraper/articleScraper.ts`.
-    -   Add a suitable HTML parsing/extraction library dependency (e.g., `@extractus/article-extractor` recommended for simplicity, or `cheerio` for more control). Run `npm install @extractus/article-extractor --save-prod` (or chosen alternative).
-    -   Implement an async function `scrapeArticle(url: string): Promise<string | null>` within the module.
-    -   Inside the function:
-        -   Use native `Workspace` to retrieve content from the `url`. Set a reasonable timeout (e.g., 10-15 seconds). Include a `User-Agent` header to mimic a browser.
-        -   Handle potential `Workspace` errors (network errors, timeouts) using `try...catch`.
-        -   Check the `response.ok` status. If not okay, log error and return `null`.
-        -   Check the `Content-Type` header of the response. If it doesn't indicate HTML (e.g., does not include `text/html`), log warning and return `null`.
-        -   If HTML is received, attempt to extract the main article text using the chosen library (`article-extractor` preferred).
-        -   Wrap the extraction logic in a `try...catch` to handle library-specific errors.
-        -   Return the extracted plain text string if successful. Ensure it's just text, not HTML markup.
-        -   Return `null` if extraction fails or results in empty content.
-    -   Log all significant events, errors, or reasons for returning null (e.g., "Scraping URL...", "Fetch failed:", "Non-HTML content type:", "Extraction failed:", "Successfully extracted text") using the logger utility.
-    -   Define TypeScript types/interfaces as needed.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `articleScraper.ts` module exists and exports the `scrapeArticle` function.
-    -   AC2: The chosen scraping library (e.g., `@extractus/article-extractor`) is added to `dependencies` in `package.json`.
-    -   AC3: `scrapeArticle` uses native `Workspace` with a timeout and User-Agent header.
-    -   AC4: `scrapeArticle` correctly handles fetch errors, non-OK responses, and non-HTML content types by logging and returning `null`.
-    -   AC5: `scrapeArticle` uses the chosen library to attempt text extraction from valid HTML content.
-    -   AC6: `scrapeArticle` returns the extracted plain text on success, and `null` on any failure (fetch, non-HTML, extraction error, empty result).
-    -   AC7: Relevant logs are produced for success, failure modes, and errors encountered during the process.
-
----
-
-### Story 3.2: Integrate Article Scraping into Main Workflow
-
--   **User Story / Goal:** As a developer, I want to integrate the article scraper into the main workflow (`src/index.ts`), attempting to scrape the article for each HN story that has a valid URL, after fetching its data.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts`.
-    -   Import the `scrapeArticle` function from `src/scraper/articleScraper.ts`.
-    -   Within the main loop iterating through the fetched stories (after comments are fetched in Epic 2):
-        -   Check if `story.url` exists and appears to be a valid HTTP/HTTPS URL. A simple check for starting with `http://` or `https://` is sufficient.
-        -   If the URL is missing or invalid, log a warning ("Skipping scraping for story {storyId}: Missing or invalid URL") and proceed to the next story's processing step.
-        -   If a valid URL exists, log ("Attempting to scrape article for story {storyId} from {story.url}").
-        -   Call `await scrapeArticle(story.url)`.
-        -   Store the result (the extracted text string or `null`) in memory, associated with the story object (e.g., add property `articleContent: string | null`).
-        -   Log the outcome clearly (e.g., "Successfully scraped article for story {storyId}", "Failed to scrape article for story {storyId}").
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes Epic 1 & 2 steps, and then attempts article scraping for stories with valid URLs.
-    -   AC2: Stories with missing or invalid URLs are skipped, and a corresponding log message is generated.
-    -   AC3: For stories with valid URLs, the `scrapeArticle` function is called.
-    -   AC4: Logs clearly indicate the start and success/failure outcome of the scraping attempt for each relevant story.
-    -   AC5: Story objects held in memory after this stage contain an `articleContent` property holding the scraped text (string) or `null` if scraping was skipped or failed.
-
----
-
-### Story 3.3: Persist Scraped Article Text Locally
-
--   **User Story / Goal:** As a developer, I want to save successfully scraped article text to a separate local file for each story, so that the text content is available as input for the summarization stage.
--   **Detailed Requirements:**
-    -   Import Node.js `fs` and `path` modules if not already present in `src/index.ts`.
-    -   In the main workflow (`src/index.ts`), immediately after a successful call to `scrapeArticle` for a story (where the result is a non-null string):
-        -   Retrieve the full path to the current date-stamped output directory.
-        -   Construct the filename: `{storyId}_article.txt`.
-        -   Construct the full file path using `path.join()`.
-        -   Get the successfully scraped article text string (`articleContent`).
-        -   Use `fs.writeFileSync(fullPath, articleContent, 'utf-8')` to save the text to the file. Wrap in `try...catch` for file system errors.
-        -   Log the successful saving of the file (e.g., "Saved scraped article text to {filename}") or any file writing errors encountered.
-    -   Ensure *no* `_article.txt` file is created if `scrapeArticle` returned `null` (due to skipping or failure).
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory contains `_article.txt` files *only* for those stories where `scrapeArticle` succeeded and returned text content.
-    -   AC2: The name of each article text file is `{storyId}_article.txt`.
-    -   AC3: The content of each `_article.txt` file is the plain text string returned by `scrapeArticle`.
-    -   AC4: Logs confirm the successful writing of each `_article.txt` file or report specific file writing errors.
-    -   AC5: No empty `_article.txt` files are created. Files only exist if scraping was successful.
-
----
-
-### Story 3.4: Implement Stage Testing Utility for Scraping
-
--   **User Story / Goal:** As a developer, I want a separate script/command to test the article scraping logic using HN story data from local files, allowing independent testing and debugging of the scraper.
--   **Detailed Requirements:**
-    -   Create a new standalone script file: `src/stages/scrape_articles.ts`.
-    -   Import necessary modules: `fs`, `path`, `logger`, `config`, `scrapeArticle`.
-    -   The script should:
-        -   Initialize the logger.
-        -   Load configuration (to get `OUTPUT_DIR_PATH`).
-        -   Determine the target date-stamped directory path (e.g., `${OUTPUT_DIR_PATH}/YYYY-MM-DD`, using the current date or potentially an optional CLI argument). Ensure this directory exists.
-        -   Read the directory contents and identify all `{storyId}_data.json` files.
-        -   For each `_data.json` file found:
-            -   Read and parse the JSON content.
-            -   Extract the `storyId` and `url`.
-            -   If a valid `url` exists, call `await scrapeArticle(url)`.
-            -   If scraping succeeds (returns text), save the text to `{storyId}_article.txt` in the same directory (using logic from Story 3.3). Overwrite if the file exists.
-            -   Log the progress and outcome (skip/success/fail) for each story processed.
-    -   Add a new script command to `package.json`: `"stage:scrape": "ts-node src/stages/scrape_articles.ts"`. Consider adding argument parsing later if needed to specify a date/directory.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/scrape_articles.ts` exists.
-    -   AC2: The script `stage:scrape` is defined in `package.json`.
-    -   AC3: Running `npm run stage:scrape` (assuming a directory with `_data.json` files exists from a previous `stage:fetch` run) reads these files.
-    -   AC4: The script calls `scrapeArticle` for stories with valid URLs found in the JSON files.
-    -   AC5: The script creates/updates `{storyId}_article.txt` files in the target directory corresponding to successfully scraped articles.
-    -   AC6: The script logs its actions (reading files, attempting scraping, saving results) for each story ID processed.
-    -   AC7: The script operates solely based on local `_data.json` files and fetching from external article URLs; it does not call the Algolia HN API.
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 3     | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic3.txt

@@ -1,111 +0,0 @@
-# Epic 3: Article Scraping & Persistence
-
-**Goal:** Implement a best-effort article scraping mechanism to fetch and extract plain text content from the external URLs associated with fetched HN stories. Handle failures gracefully and persist successfully scraped text locally. Implement a stage testing utility for scraping.
-
-## Story List
-
-### Story 3.1: Implement Basic Article Scraper Module
-
--   **User Story / Goal:** As a developer, I want a module that attempts to fetch HTML from a URL and extract the main article text using basic methods, handling common failures gracefully, so article content can be prepared for summarization.
--   **Detailed Requirements:**
-    -   Create a new module: `src/scraper/articleScraper.ts`.
-    -   Add a suitable HTML parsing/extraction library dependency (e.g., `@extractus/article-extractor` recommended for simplicity, or `cheerio` for more control). Run `npm install @extractus/article-extractor --save-prod` (or chosen alternative).
-    -   Implement an async function `scrapeArticle(url: string): Promise<string | null>` within the module.
-    -   Inside the function:
-        -   Use native `Workspace` to retrieve content from the `url`. Set a reasonable timeout (e.g., 10-15 seconds). Include a `User-Agent` header to mimic a browser.
-        -   Handle potential `Workspace` errors (network errors, timeouts) using `try...catch`.
-        -   Check the `response.ok` status. If not okay, log error and return `null`.
-        -   Check the `Content-Type` header of the response. If it doesn't indicate HTML (e.g., does not include `text/html`), log warning and return `null`.
-        -   If HTML is received, attempt to extract the main article text using the chosen library (`article-extractor` preferred).
-        -   Wrap the extraction logic in a `try...catch` to handle library-specific errors.
-        -   Return the extracted plain text string if successful. Ensure it's just text, not HTML markup.
-        -   Return `null` if extraction fails or results in empty content.
-    -   Log all significant events, errors, or reasons for returning null (e.g., "Scraping URL...", "Fetch failed:", "Non-HTML content type:", "Extraction failed:", "Successfully extracted text") using the logger utility.
-    -   Define TypeScript types/interfaces as needed.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `articleScraper.ts` module exists and exports the `scrapeArticle` function.
-    -   AC2: The chosen scraping library (e.g., `@extractus/article-extractor`) is added to `dependencies` in `package.json`.
-    -   AC3: `scrapeArticle` uses native `Workspace` with a timeout and User-Agent header.
-    -   AC4: `scrapeArticle` correctly handles fetch errors, non-OK responses, and non-HTML content types by logging and returning `null`.
-    -   AC5: `scrapeArticle` uses the chosen library to attempt text extraction from valid HTML content.
-    -   AC6: `scrapeArticle` returns the extracted plain text on success, and `null` on any failure (fetch, non-HTML, extraction error, empty result).
-    -   AC7: Relevant logs are produced for success, failure modes, and errors encountered during the process.
-
----
-
-### Story 3.2: Integrate Article Scraping into Main Workflow
-
--   **User Story / Goal:** As a developer, I want to integrate the article scraper into the main workflow (`src/index.ts`), attempting to scrape the article for each HN story that has a valid URL, after fetching its data.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts`.
-    -   Import the `scrapeArticle` function from `src/scraper/articleScraper.ts`.
-    -   Within the main loop iterating through the fetched stories (after comments are fetched in Epic 2):
-        -   Check if `story.url` exists and appears to be a valid HTTP/HTTPS URL. A simple check for starting with `http://` or `https://` is sufficient.
-        -   If the URL is missing or invalid, log a warning ("Skipping scraping for story {storyId}: Missing or invalid URL") and proceed to the next story's processing step.
-        -   If a valid URL exists, log ("Attempting to scrape article for story {storyId} from {story.url}").
-        -   Call `await scrapeArticle(story.url)`.
-        -   Store the result (the extracted text string or `null`) in memory, associated with the story object (e.g., add property `articleContent: string | null`).
-        -   Log the outcome clearly (e.g., "Successfully scraped article for story {storyId}", "Failed to scrape article for story {storyId}").
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes Epic 1 & 2 steps, and then attempts article scraping for stories with valid URLs.
-    -   AC2: Stories with missing or invalid URLs are skipped, and a corresponding log message is generated.
-    -   AC3: For stories with valid URLs, the `scrapeArticle` function is called.
-    -   AC4: Logs clearly indicate the start and success/failure outcome of the scraping attempt for each relevant story.
-    -   AC5: Story objects held in memory after this stage contain an `articleContent` property holding the scraped text (string) or `null` if scraping was skipped or failed.
-
----
-
-### Story 3.3: Persist Scraped Article Text Locally
-
--   **User Story / Goal:** As a developer, I want to save successfully scraped article text to a separate local file for each story, so that the text content is available as input for the summarization stage.
--   **Detailed Requirements:**
-    -   Import Node.js `fs` and `path` modules if not already present in `src/index.ts`.
-    -   In the main workflow (`src/index.ts`), immediately after a successful call to `scrapeArticle` for a story (where the result is a non-null string):
-        -   Retrieve the full path to the current date-stamped output directory.
-        -   Construct the filename: `{storyId}_article.txt`.
-        -   Construct the full file path using `path.join()`.
-        -   Get the successfully scraped article text string (`articleContent`).
-        -   Use `fs.writeFileSync(fullPath, articleContent, 'utf-8')` to save the text to the file. Wrap in `try...catch` for file system errors.
-        -   Log the successful saving of the file (e.g., "Saved scraped article text to {filename}") or any file writing errors encountered.
-    -   Ensure *no* `_article.txt` file is created if `scrapeArticle` returned `null` (due to skipping or failure).
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory contains `_article.txt` files *only* for those stories where `scrapeArticle` succeeded and returned text content.
-    -   AC2: The name of each article text file is `{storyId}_article.txt`.
-    -   AC3: The content of each `_article.txt` file is the plain text string returned by `scrapeArticle`.
-    -   AC4: Logs confirm the successful writing of each `_article.txt` file or report specific file writing errors.
-    -   AC5: No empty `_article.txt` files are created. Files only exist if scraping was successful.
-
----
-
-### Story 3.4: Implement Stage Testing Utility for Scraping
-
--   **User Story / Goal:** As a developer, I want a separate script/command to test the article scraping logic using HN story data from local files, allowing independent testing and debugging of the scraper.
--   **Detailed Requirements:**
-    -   Create a new standalone script file: `src/stages/scrape_articles.ts`.
-    -   Import necessary modules: `fs`, `path`, `logger`, `config`, `scrapeArticle`.
-    -   The script should:
-        -   Initialize the logger.
-        -   Load configuration (to get `OUTPUT_DIR_PATH`).
-        -   Determine the target date-stamped directory path (e.g., `${OUTPUT_DIR_PATH}/YYYY-MM-DD`, using the current date or potentially an optional CLI argument). Ensure this directory exists.
-        -   Read the directory contents and identify all `{storyId}_data.json` files.
-        -   For each `_data.json` file found:
-            -   Read and parse the JSON content.
-            -   Extract the `storyId` and `url`.
-            -   If a valid `url` exists, call `await scrapeArticle(url)`.
-            -   If scraping succeeds (returns text), save the text to `{storyId}_article.txt` in the same directory (using logic from Story 3.3). Overwrite if the file exists.
-            -   Log the progress and outcome (skip/success/fail) for each story processed.
-    -   Add a new script command to `package.json`: `"stage:scrape": "ts-node src/stages/scrape_articles.ts"`. Consider adding argument parsing later if needed to specify a date/directory.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/scrape_articles.ts` exists.
-    -   AC2: The script `stage:scrape` is defined in `package.json`.
-    -   AC3: Running `npm run stage:scrape` (assuming a directory with `_data.json` files exists from a previous `stage:fetch` run) reads these files.
-    -   AC4: The script calls `scrapeArticle` for stories with valid URLs found in the JSON files.
-    -   AC5: The script creates/updates `{storyId}_article.txt` files in the target directory corresponding to successfully scraped articles.
-    -   AC6: The script logs its actions (reading files, attempting scraping, saving results) for each story ID processed.
-    -   AC7: The script operates solely based on local `_data.json` files and fetching from external article URLs; it does not call the Algolia HN API.
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 3     | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic4.md

@@ -1,146 +0,0 @@
-# Epic 4: LLM Summarization & Persistence
-
-**Goal:** Integrate with the configured local Ollama instance to generate summaries for successfully scraped article text and fetched comments. Persist these summaries locally. Implement a stage testing utility for summarization.
-
-## Story List
-
-### Story 4.1: Implement Ollama Client Module
-
--   **User Story / Goal:** As a developer, I want a client module to interact with the configured Ollama API endpoint via HTTP, handling requests and responses for text generation, so that summaries can be generated programmatically.
--   **Detailed Requirements:**
-    -   **Prerequisite:** Ensure a local Ollama instance is installed and running, accessible via the URL defined in `.env` (`OLLAMA_ENDPOINT_URL`), and that the model specified in `.env` (`OLLAMA_MODEL`) has been downloaded (e.g., via `ollama pull model_name`). Instructions for this setup should be in the project README.
-    -   Create a new module: `src/clients/ollamaClient.ts`.
-    -   Implement an async function `generateSummary(promptTemplate: string, content: string): Promise<string | null>`. *(Note: Parameter name changed for clarity)*
-    -   Add configuration variables `OLLAMA_ENDPOINT_URL` (e.g., `http://localhost:11434`) and `OLLAMA_MODEL` (e.g., `llama3`) to `.env.example`. Ensure they are loaded via the config module (`src/utils/config.ts`). Update local `.env` with actual values. Add optional `OLLAMA_TIMEOUT_MS` to `.env.example` with a default like `120000`.
-    -   Inside `generateSummary`:
-        -   Construct the full prompt string using the `promptTemplate` and the provided `content` (e.g., replacing a placeholder like `{Content Placeholder}` in the template, or simple concatenation if templates are basic).
-        -   Construct the Ollama API request payload (JSON): `{ model: configured_model, prompt: full_prompt, stream: false }`. Refer to Ollama `/api/generate` documentation and `docs/data-models.md`.
-        -   Use native `Workspace` to send a POST request to the configured Ollama endpoint + `/api/generate`. Set appropriate headers (`Content-Type: application/json`). Use the configured `OLLAMA_TIMEOUT_MS` or a reasonable default (e.g., 2 minutes).
-        -   Handle `Workspace` errors (network, timeout) using `try...catch`.
-        -   Check `response.ok`. If not OK, log the status/error and return `null`.
-        -   Parse the JSON response from Ollama. Extract the generated text (typically in the `response` field). Refer to `docs/data-models.md`.
-        -   Check for potential errors within the Ollama response structure itself (e.g., an `error` field).
-        -   Return the extracted summary string on success. Return `null` on any failure.
-        -   Log key events: initiating request (mention model), receiving response, success, failure reasons, potentially request/response time using the logger.
-    -   Define necessary TypeScript types for the Ollama request payload and expected response structure in `src/types/ollama.ts` (referenced in `docs/data-models.md`).
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `ollamaClient.ts` module exists and exports `generateSummary`.
-    -   AC2: `OLLAMA_ENDPOINT_URL` and `OLLAMA_MODEL` are defined in `.env.example`, loaded via config, and used by the client. Optional `OLLAMA_TIMEOUT_MS` is handled.
-    -   AC3: `generateSummary` sends a correctly formatted POST request (model, full prompt based on template and content, stream:false) to the configured Ollama endpoint/path using native `Workspace`.
-    -   AC4: Network errors, timeouts, and non-OK API responses are handled gracefully, logged, and result in a `null` return (given the Prerequisite Ollama service is running).
-    -   AC5: A successful Ollama response is parsed correctly, the generated text is extracted, and returned as a string.
-    * AC6: Unexpected Ollama response formats or internal errors (e.g., `{"error": "..."}`) are handled, logged, and result in a `null` return.
-    * AC7: Logs provide visibility into the client's interaction with the Ollama API.
-
----
-
-### Story 4.2: Define Summarization Prompts
-
-* **User Story / Goal:** As a developer, I want standardized base prompts for generating article summaries and HN discussion summaries documented centrally, ensuring consistent instructions are sent to the LLM.
-* **Detailed Requirements:**
-    * Define two standardized base prompts (`ARTICLE_SUMMARY_PROMPT`, `DISCUSSION_SUMMARY_PROMPT`) **and document them in `docs/prompts.md`**.
-    * Ensure these prompts are accessible within the application code, for example, by defining them as exported constants in a dedicated module like `src/utils/prompts.ts`, which reads from or mirrors the content in `docs/prompts.md`.
-* **Acceptance Criteria (ACs):**
-    * AC1: The `ARTICLE_SUMMARY_PROMPT` text is defined in `docs/prompts.md` with appropriate instructional content.
-    * AC2: The `DISCUSSION_SUMMARY_PROMPT` text is defined in `docs/prompts.md` with appropriate instructional content.
-    * AC3: The prompt texts documented in `docs/prompts.md` are available as constants or variables within the application code (e.g., via `src/utils/prompts.ts`) for use by the Ollama client integration.
-
----
-
-### Story 4.3: Integrate Summarization into Main Workflow
-
-* **User Story / Goal:** As a developer, I want to integrate the Ollama client into the main workflow to generate summaries for each story's scraped article text (if available) and fetched comments, using centrally defined prompts and handling potential comment length limits.
-* **Detailed Requirements:**
-    * Modify the main execution flow in `src/index.ts` or `src/core/pipeline.ts`.
-    * Import `ollamaClient.generateSummary` and the prompt constants/variables (e.g., from `src/utils/prompts.ts`, which reflect `docs/prompts.md`).
-    * Load the optional `MAX_COMMENT_CHARS_FOR_SUMMARY` configuration value from `.env` via the config utility.
-    * Within the main loop iterating through stories (after article scraping/persistence in Epic 3):
-    * **Article Summary Generation:**
-        * Check if the `story` object has non-null `articleContent`.
-        * If yes: log "Attempting article summarization for story {storyId}", call `await generateSummary(ARTICLE_SUMMARY_PROMPT, story.articleContent)`, store the result (string or null) as `story.articleSummary`, log success/failure.
-        * If no: set `story.articleSummary = null`, log "Skipping article summarization: No content".
-    * **Discussion Summary Generation:**
-        * Check if the `story` object has a non-empty `comments` array.
-        * If yes:
-            * Format the `story.comments` array into a single text block suitable for the LLM prompt (e.g., concatenating `comment.text` with separators like `---`).
-            * **Check truncation limit:** If `MAX_COMMENT_CHARS_FOR_SUMMARY` is configured to a positive number and the `formattedCommentsText` length exceeds it, truncate `formattedCommentsText` to the limit and log a warning: "Comment text truncated to {limit} characters for summarization for story {storyId}".
-            * Log "Attempting discussion summarization for story {storyId}".
-            * Call `await generateSummary(DISCUSSION_SUMMARY_PROMPT, formattedCommentsText)`. *(Pass the potentially truncated text)*
-            * Store the result (string or null) as `story.discussionSummary`. Log success/failure.
-        * If no: set `story.discussionSummary = null`, log "Skipping discussion summarization: No comments".
-* **Acceptance Criteria (ACs):**
-    * AC1: Running `npm run dev` executes steps from Epics 1-3, then attempts summarization using the Ollama client.
-    * AC2: Article summary is attempted only if `articleContent` exists for a story.
-    * AC3: Discussion summary is attempted only if `comments` exist for a story.
-    * AC4: `generateSummary` is called with the correct prompts (sourced consistently with `docs/prompts.md`) and corresponding content (article text or formatted/potentially truncated comments).
-    * AC5: If `MAX_COMMENT_CHARS_FOR_SUMMARY` is set and comment text exceeds it, the text passed to `generateSummary` is truncated, and a warning is logged.
-    * AC6: Logs clearly indicate the start, success, or failure (including null returns from the client) for both article and discussion summarization attempts per story.
-    * AC7: Story objects in memory now contain `articleSummary` (string/null) and `discussionSummary` (string/null) properties.
-
----
-
-### Story 4.4: Persist Generated Summaries Locally
-
-*(No changes needed for this story based on recent decisions)*
-
--   **User Story / Goal:** As a developer, I want to save the generated article and discussion summaries (or null placeholders) to a local JSON file for each story, making them available for the email assembly stage.
--   **Detailed Requirements:**
-    -   Define the structure for the summary output file: `{storyId}_summary.json`. Content example: `{ "storyId": "...", "articleSummary": "...", "discussionSummary": "...", "summarizedAt": "ISO_TIMESTAMP" }`. Note that `articleSummary` and `discussionSummary` can be `null`.
-    -   Import `fs` and `path` in `src/index.ts` or `src/core/pipeline.ts` if needed.
-    -   In the main workflow loop, after *both* summarization attempts (article and discussion) for a story are complete:
-        -   Create a summary result object containing `storyId`, `articleSummary` (string or null), `discussionSummary` (string or null), and the current ISO timestamp (`new Date().toISOString()`). Add this timestamp to the in-memory `story` object as well (`story.summarizedAt`).
-        -   Get the full path to the date-stamped output directory.
-        -   Construct the filename: `{storyId}_summary.json`.
-        -   Construct the full file path using `path.join()`.
-        -   Serialize the summary result object to JSON (`JSON.stringify(..., null, 2)`).
-        -   Use `fs.writeFileSync` to save the JSON to the file, wrapping in `try...catch`.
-        -   Log the successful saving of the summary file or any file writing errors.
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory contains 10 files named `{storyId}_summary.json`.
-    -   AC2: Each `_summary.json` file contains valid JSON adhering to the defined structure.
-    -   AC3: The `articleSummary` field contains the generated summary string if successful, otherwise `null`.
-    -   AC4: The `discussionSummary` field contains the generated summary string if successful, otherwise `null`.
-    -   AC5: A valid ISO timestamp is present in the `summarizedAt` field.
-    -   AC6: Logs confirm successful writing of each summary file or report file system errors.
-
----
-
-### Story 4.5: Implement Stage Testing Utility for Summarization
-
-*(Changes needed to reflect prompt sourcing and optional truncation)*
-
-* **User Story / Goal:** As a developer, I want a separate script/command to test the LLM summarization logic using locally persisted data (HN comments, scraped article text), allowing independent testing of prompts and Ollama interaction.
-* **Detailed Requirements:**
-    * Create a new standalone script file: `src/stages/summarize_content.ts`.
-    * Import necessary modules: `fs`, `path`, `logger`, `config`, `ollamaClient`, prompt constants (e.g., from `src/utils/prompts.ts`).
-    * The script should:
-        * Initialize logger, load configuration (Ollama endpoint/model, output dir, **optional `MAX_COMMENT_CHARS_FOR_SUMMARY`**).
-        * Determine target date-stamped directory path.
-        * Find all `{storyId}_data.json` files in the directory.
-        * For each `storyId` found:
-            * Read `{storyId}_data.json` to get comments. Format them into a single text block.
-            * *Attempt* to read `{storyId}_article.txt`. Handle file-not-found gracefully. Store content or null.
-            * Call `ollamaClient.generateSummary` for article text (if not null) using `ARTICLE_SUMMARY_PROMPT`.
-            * **Apply truncation logic:** If comments exist, check `MAX_COMMENT_CHARS_FOR_SUMMARY` and truncate the formatted comment text block if needed, logging a warning.
-            * Call `ollamaClient.generateSummary` for formatted comments (if comments exist) using `DISCUSSION_SUMMARY_PROMPT` *(passing potentially truncated text)*.
-            * Construct the summary result object (with summaries or nulls, and timestamp).
-            * Save the result object to `{storyId}_summary.json` in the same directory (using logic from Story 4.4), overwriting if exists.
-            * Log progress (reading files, calling Ollama, truncation warnings, saving results) for each story ID.
-    * Add script to `package.json`: `"stage:summarize": "ts-node src/stages/summarize_content.ts"`.
-* **Acceptance Criteria (ACs):**
-    * AC1: The file `src/stages/summarize_content.ts` exists.
-    * AC2: The script `stage:summarize` is defined in `package.json`.
-    * AC3: Running `npm run stage:summarize` (after `stage:fetch` and `stage:scrape` runs) reads `_data.json` and attempts to read `_article.txt` files from the target directory.
-    * AC4: The script calls the `ollamaClient` with correct prompts (sourced consistently with `docs/prompts.md`) and content derived *only* from the local files (requires Ollama service running per Story 4.1 prerequisite).
-    * AC5: If `MAX_COMMENT_CHARS_FOR_SUMMARY` is set and applicable, comment text is truncated before calling the client, and a warning is logged.
-    * AC6: The script creates/updates `{storyId}_summary.json` files in the target directory reflecting the results of the Ollama calls (summaries or nulls).
-    * AC7: Logs show the script processing each story ID found locally, interacting with Ollama, and saving results.
-    * AC8: The script does not call Algolia API or the article scraper module.
-
-## Change Log
-
-| Change                      | Date         | Version | Description                          | Author         |
-| --------------------------- | ------------ | ------- | ------------------------------------ | -------------- |
-| Integrate prompts.md refs   | 2025-05-04   | 0.3     | Updated stories 4.2, 4.3, 4.5        | 3-Architect    |
-| Added Ollama Prereq Note    | 2025-05-04   | 0.2     | Added note about local Ollama setup  | 2-pm           |
-| Initial Draft               | 2025-05-04   | 0.1     | First draft of Epic 4                | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic4.txt

@@ -1,146 +0,0 @@
-# Epic 4: LLM Summarization & Persistence
-
-**Goal:** Integrate with the configured local Ollama instance to generate summaries for successfully scraped article text and fetched comments. Persist these summaries locally. Implement a stage testing utility for summarization.
-
-## Story List
-
-### Story 4.1: Implement Ollama Client Module
-
--   **User Story / Goal:** As a developer, I want a client module to interact with the configured Ollama API endpoint via HTTP, handling requests and responses for text generation, so that summaries can be generated programmatically.
--   **Detailed Requirements:**
-    -   **Prerequisite:** Ensure a local Ollama instance is installed and running, accessible via the URL defined in `.env` (`OLLAMA_ENDPOINT_URL`), and that the model specified in `.env` (`OLLAMA_MODEL`) has been downloaded (e.g., via `ollama pull model_name`). Instructions for this setup should be in the project README.
-    -   Create a new module: `src/clients/ollamaClient.ts`.
-    -   Implement an async function `generateSummary(promptTemplate: string, content: string): Promise<string | null>`. *(Note: Parameter name changed for clarity)*
-    -   Add configuration variables `OLLAMA_ENDPOINT_URL` (e.g., `http://localhost:11434`) and `OLLAMA_MODEL` (e.g., `llama3`) to `.env.example`. Ensure they are loaded via the config module (`src/utils/config.ts`). Update local `.env` with actual values. Add optional `OLLAMA_TIMEOUT_MS` to `.env.example` with a default like `120000`.
-    -   Inside `generateSummary`:
-        -   Construct the full prompt string using the `promptTemplate` and the provided `content` (e.g., replacing a placeholder like `{Content Placeholder}` in the template, or simple concatenation if templates are basic).
-        -   Construct the Ollama API request payload (JSON): `{ model: configured_model, prompt: full_prompt, stream: false }`. Refer to Ollama `/api/generate` documentation and `docs/data-models.md`.
-        -   Use native `Workspace` to send a POST request to the configured Ollama endpoint + `/api/generate`. Set appropriate headers (`Content-Type: application/json`). Use the configured `OLLAMA_TIMEOUT_MS` or a reasonable default (e.g., 2 minutes).
-        -   Handle `Workspace` errors (network, timeout) using `try...catch`.
-        -   Check `response.ok`. If not OK, log the status/error and return `null`.
-        -   Parse the JSON response from Ollama. Extract the generated text (typically in the `response` field). Refer to `docs/data-models.md`.
-        -   Check for potential errors within the Ollama response structure itself (e.g., an `error` field).
-        -   Return the extracted summary string on success. Return `null` on any failure.
-        -   Log key events: initiating request (mention model), receiving response, success, failure reasons, potentially request/response time using the logger.
-    -   Define necessary TypeScript types for the Ollama request payload and expected response structure in `src/types/ollama.ts` (referenced in `docs/data-models.md`).
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `ollamaClient.ts` module exists and exports `generateSummary`.
-    -   AC2: `OLLAMA_ENDPOINT_URL` and `OLLAMA_MODEL` are defined in `.env.example`, loaded via config, and used by the client. Optional `OLLAMA_TIMEOUT_MS` is handled.
-    -   AC3: `generateSummary` sends a correctly formatted POST request (model, full prompt based on template and content, stream:false) to the configured Ollama endpoint/path using native `Workspace`.
-    -   AC4: Network errors, timeouts, and non-OK API responses are handled gracefully, logged, and result in a `null` return (given the Prerequisite Ollama service is running).
-    -   AC5: A successful Ollama response is parsed correctly, the generated text is extracted, and returned as a string.
-    * AC6: Unexpected Ollama response formats or internal errors (e.g., `{"error": "..."}`) are handled, logged, and result in a `null` return.
-    * AC7: Logs provide visibility into the client's interaction with the Ollama API.
-
----
-
-### Story 4.2: Define Summarization Prompts
-
-* **User Story / Goal:** As a developer, I want standardized base prompts for generating article summaries and HN discussion summaries documented centrally, ensuring consistent instructions are sent to the LLM.
-* **Detailed Requirements:**
-    * Define two standardized base prompts (`ARTICLE_SUMMARY_PROMPT`, `DISCUSSION_SUMMARY_PROMPT`) **and document them in `docs/prompts.md`**.
-    * Ensure these prompts are accessible within the application code, for example, by defining them as exported constants in a dedicated module like `src/utils/prompts.ts`, which reads from or mirrors the content in `docs/prompts.md`.
-* **Acceptance Criteria (ACs):**
-    * AC1: The `ARTICLE_SUMMARY_PROMPT` text is defined in `docs/prompts.md` with appropriate instructional content.
-    * AC2: The `DISCUSSION_SUMMARY_PROMPT` text is defined in `docs/prompts.md` with appropriate instructional content.
-    * AC3: The prompt texts documented in `docs/prompts.md` are available as constants or variables within the application code (e.g., via `src/utils/prompts.ts`) for use by the Ollama client integration.
-
----
-
-### Story 4.3: Integrate Summarization into Main Workflow
-
-* **User Story / Goal:** As a developer, I want to integrate the Ollama client into the main workflow to generate summaries for each story's scraped article text (if available) and fetched comments, using centrally defined prompts and handling potential comment length limits.
-* **Detailed Requirements:**
-    * Modify the main execution flow in `src/index.ts` or `src/core/pipeline.ts`.
-    * Import `ollamaClient.generateSummary` and the prompt constants/variables (e.g., from `src/utils/prompts.ts`, which reflect `docs/prompts.md`).
-    * Load the optional `MAX_COMMENT_CHARS_FOR_SUMMARY` configuration value from `.env` via the config utility.
-    * Within the main loop iterating through stories (after article scraping/persistence in Epic 3):
-    * **Article Summary Generation:**
-        * Check if the `story` object has non-null `articleContent`.
-        * If yes: log "Attempting article summarization for story {storyId}", call `await generateSummary(ARTICLE_SUMMARY_PROMPT, story.articleContent)`, store the result (string or null) as `story.articleSummary`, log success/failure.
-        * If no: set `story.articleSummary = null`, log "Skipping article summarization: No content".
-    * **Discussion Summary Generation:**
-        * Check if the `story` object has a non-empty `comments` array.
-        * If yes:
-            * Format the `story.comments` array into a single text block suitable for the LLM prompt (e.g., concatenating `comment.text` with separators like `---`).
-            * **Check truncation limit:** If `MAX_COMMENT_CHARS_FOR_SUMMARY` is configured to a positive number and the `formattedCommentsText` length exceeds it, truncate `formattedCommentsText` to the limit and log a warning: "Comment text truncated to {limit} characters for summarization for story {storyId}".
-            * Log "Attempting discussion summarization for story {storyId}".
-            * Call `await generateSummary(DISCUSSION_SUMMARY_PROMPT, formattedCommentsText)`. *(Pass the potentially truncated text)*
-            * Store the result (string or null) as `story.discussionSummary`. Log success/failure.
-        * If no: set `story.discussionSummary = null`, log "Skipping discussion summarization: No comments".
-* **Acceptance Criteria (ACs):**
-    * AC1: Running `npm run dev` executes steps from Epics 1-3, then attempts summarization using the Ollama client.
-    * AC2: Article summary is attempted only if `articleContent` exists for a story.
-    * AC3: Discussion summary is attempted only if `comments` exist for a story.
-    * AC4: `generateSummary` is called with the correct prompts (sourced consistently with `docs/prompts.md`) and corresponding content (article text or formatted/potentially truncated comments).
-    * AC5: If `MAX_COMMENT_CHARS_FOR_SUMMARY` is set and comment text exceeds it, the text passed to `generateSummary` is truncated, and a warning is logged.
-    * AC6: Logs clearly indicate the start, success, or failure (including null returns from the client) for both article and discussion summarization attempts per story.
-    * AC7: Story objects in memory now contain `articleSummary` (string/null) and `discussionSummary` (string/null) properties.
-
----
-
-### Story 4.4: Persist Generated Summaries Locally
-
-*(No changes needed for this story based on recent decisions)*
-
--   **User Story / Goal:** As a developer, I want to save the generated article and discussion summaries (or null placeholders) to a local JSON file for each story, making them available for the email assembly stage.
--   **Detailed Requirements:**
-    -   Define the structure for the summary output file: `{storyId}_summary.json`. Content example: `{ "storyId": "...", "articleSummary": "...", "discussionSummary": "...", "summarizedAt": "ISO_TIMESTAMP" }`. Note that `articleSummary` and `discussionSummary` can be `null`.
-    -   Import `fs` and `path` in `src/index.ts` or `src/core/pipeline.ts` if needed.
-    -   In the main workflow loop, after *both* summarization attempts (article and discussion) for a story are complete:
-        -   Create a summary result object containing `storyId`, `articleSummary` (string or null), `discussionSummary` (string or null), and the current ISO timestamp (`new Date().toISOString()`). Add this timestamp to the in-memory `story` object as well (`story.summarizedAt`).
-        -   Get the full path to the date-stamped output directory.
-        -   Construct the filename: `{storyId}_summary.json`.
-        -   Construct the full file path using `path.join()`.
-        -   Serialize the summary result object to JSON (`JSON.stringify(..., null, 2)`).
-        -   Use `fs.writeFileSync` to save the JSON to the file, wrapping in `try...catch`.
-        -   Log the successful saving of the summary file or any file writing errors.
--   **Acceptance Criteria (ACs):**
-    -   AC1: After running `npm run dev`, the date-stamped output directory contains 10 files named `{storyId}_summary.json`.
-    -   AC2: Each `_summary.json` file contains valid JSON adhering to the defined structure.
-    -   AC3: The `articleSummary` field contains the generated summary string if successful, otherwise `null`.
-    -   AC4: The `discussionSummary` field contains the generated summary string if successful, otherwise `null`.
-    -   AC5: A valid ISO timestamp is present in the `summarizedAt` field.
-    -   AC6: Logs confirm successful writing of each summary file or report file system errors.
-
----
-
-### Story 4.5: Implement Stage Testing Utility for Summarization
-
-*(Changes needed to reflect prompt sourcing and optional truncation)*
-
-* **User Story / Goal:** As a developer, I want a separate script/command to test the LLM summarization logic using locally persisted data (HN comments, scraped article text), allowing independent testing of prompts and Ollama interaction.
-* **Detailed Requirements:**
-    * Create a new standalone script file: `src/stages/summarize_content.ts`.
-    * Import necessary modules: `fs`, `path`, `logger`, `config`, `ollamaClient`, prompt constants (e.g., from `src/utils/prompts.ts`).
-    * The script should:
-        * Initialize logger, load configuration (Ollama endpoint/model, output dir, **optional `MAX_COMMENT_CHARS_FOR_SUMMARY`**).
-        * Determine target date-stamped directory path.
-        * Find all `{storyId}_data.json` files in the directory.
-        * For each `storyId` found:
-            * Read `{storyId}_data.json` to get comments. Format them into a single text block.
-            * *Attempt* to read `{storyId}_article.txt`. Handle file-not-found gracefully. Store content or null.
-            * Call `ollamaClient.generateSummary` for article text (if not null) using `ARTICLE_SUMMARY_PROMPT`.
-            * **Apply truncation logic:** If comments exist, check `MAX_COMMENT_CHARS_FOR_SUMMARY` and truncate the formatted comment text block if needed, logging a warning.
-            * Call `ollamaClient.generateSummary` for formatted comments (if comments exist) using `DISCUSSION_SUMMARY_PROMPT` *(passing potentially truncated text)*.
-            * Construct the summary result object (with summaries or nulls, and timestamp).
-            * Save the result object to `{storyId}_summary.json` in the same directory (using logic from Story 4.4), overwriting if exists.
-            * Log progress (reading files, calling Ollama, truncation warnings, saving results) for each story ID.
-    * Add script to `package.json`: `"stage:summarize": "ts-node src/stages/summarize_content.ts"`.
-* **Acceptance Criteria (ACs):**
-    * AC1: The file `src/stages/summarize_content.ts` exists.
-    * AC2: The script `stage:summarize` is defined in `package.json`.
-    * AC3: Running `npm run stage:summarize` (after `stage:fetch` and `stage:scrape` runs) reads `_data.json` and attempts to read `_article.txt` files from the target directory.
-    * AC4: The script calls the `ollamaClient` with correct prompts (sourced consistently with `docs/prompts.md`) and content derived *only* from the local files (requires Ollama service running per Story 4.1 prerequisite).
-    * AC5: If `MAX_COMMENT_CHARS_FOR_SUMMARY` is set and applicable, comment text is truncated before calling the client, and a warning is logged.
-    * AC6: The script creates/updates `{storyId}_summary.json` files in the target directory reflecting the results of the Ollama calls (summaries or nulls).
-    * AC7: Logs show the script processing each story ID found locally, interacting with Ollama, and saving results.
-    * AC8: The script does not call Algolia API or the article scraper module.
-
-## Change Log
-
-| Change                      | Date         | Version | Description                          | Author         |
-| --------------------------- | ------------ | ------- | ------------------------------------ | -------------- |
-| Integrate prompts.md refs   | 2025-05-04   | 0.3     | Updated stories 4.2, 4.3, 4.5        | 3-Architect    |
-| Added Ollama Prereq Note    | 2025-05-04   | 0.2     | Added note about local Ollama setup  | 2-pm           |
-| Initial Draft               | 2025-05-04   | 0.1     | First draft of Epic 4                | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic5.md

@@ -1,152 +0,0 @@
-# Epic 5: Digest Assembly & Email Dispatch
-
-**Goal:** Assemble the collected story data and summaries from local files, format them into a readable HTML email digest, and send the email using Nodemailer with configured credentials. Implement a stage testing utility for emailing with a dry-run option.
-
-## Story List
-
-### Story 5.1: Implement Email Content Assembler
-
--   **User Story / Goal:** As a developer, I want a module that reads the persisted story metadata (`_data.json`) and summaries (`_summary.json`) from a specified directory, consolidating the necessary information needed to render the email digest.
--   **Detailed Requirements:**
-    -   Create a new module: `src/email/contentAssembler.ts`.
-    -   Define a TypeScript type/interface `DigestData` representing the data needed per story for the email template: `{ storyId: string, title: string, hnUrl: string, articleUrl: string | null, articleSummary: string | null, discussionSummary: string | null }`.
-    -   Implement an async function `assembleDigestData(dateDirPath: string): Promise<DigestData[]>`.
-    -   The function should:
-        -   Use Node.js `fs` to read the contents of the `dateDirPath`.
-        -   Identify all files matching the pattern `{storyId}_data.json`.
-        -   For each `storyId` found:
-            -   Read and parse the `{storyId}_data.json` file. Extract `title`, `hnUrl`, and `url` (use as `articleUrl`). Handle potential file read/parse errors gracefully (log and skip story).
-            -   Attempt to read and parse the corresponding `{storyId}_summary.json` file. Handle file-not-found or parse errors gracefully (treat `articleSummary` and `discussionSummary` as `null`).
-            -   Construct a `DigestData` object for the story, including the extracted metadata and summaries (or nulls).
-        -   Collect all successfully constructed `DigestData` objects into an array.
-        -   Return the array. It should ideally contain 10 items if all previous stages succeeded.
-    -   Log progress (e.g., "Assembling digest data from directory...", "Processing story {storyId}...") and any errors encountered during file processing using the logger.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `contentAssembler.ts` module exists and exports `assembleDigestData` and the `DigestData` type.
-    -   AC2: `assembleDigestData` correctly reads `_data.json` files from the provided directory path.
-    -   AC3: It attempts to read corresponding `_summary.json` files, correctly handling cases where the summary file might be missing or unparseable (resulting in null summaries for that story).
-    -   AC4: The function returns a promise resolving to an array of `DigestData` objects, populated with data extracted from the files.
-    -   AC5: Errors during file reading or JSON parsing are logged, and the function returns data for successfully processed stories.
-
----
-
-### Story 5.2: Create HTML Email Template & Renderer
-
--   **User Story / Goal:** As a developer, I want a basic HTML email template and a function to render it with the assembled digest data, producing the final HTML content for the email body.
--   **Detailed Requirements:**
-    -   Define the HTML structure. This can be done using template literals within a function or potentially using a simple template file (e.g., `src/email/templates/digestTemplate.html`) and `fs.readFileSync`. Template literals are simpler for MVP.
-    -   Create a function `renderDigestHtml(data: DigestData[], digestDate: string): string` (e.g., in `src/email/contentAssembler.ts` or a new `templater.ts`).
-    -   The function should generate an HTML string with:
-        -   A suitable title in the body (e.g., `<h1>Hacker News Top 10 Summaries for ${digestDate}</h1>`).
-        -   A loop through the `data` array.
-        -   For each `story` in `data`:
-            -   Display `<h2><a href="${story.articleUrl || story.hnUrl}">${story.title}</a></h2>`.
-            -   Display `<p><a href="${story.hnUrl}">View HN Discussion</a></p>`.
-            -   Conditionally display `<h3>Article Summary</h3><p>${story.articleSummary}</p>` *only if* `story.articleSummary` is not null/empty.
-            -   Conditionally display `<h3>Discussion Summary</h3><p>${story.discussionSummary}</p>` *only if* `story.discussionSummary` is not null/empty.
-            -   Include a separator (e.g., `<hr style="margin-top: 20px; margin-bottom: 20px;">`).
-    -   Use basic inline CSS for minimal styling (margins, etc.) to ensure readability. Avoid complex layouts.
-    -   Return the complete HTML document as a string.
--   **Acceptance Criteria (ACs):**
-    -   AC1: A function `renderDigestHtml` exists that accepts the digest data array and a date string.
-    -   AC2: The function returns a single, complete HTML string.
-    -   AC3: The generated HTML includes a title with the date and correctly iterates through the story data.
-    -   AC4: For each story, the HTML displays the linked title, HN link, and conditionally displays the article and discussion summaries with headings.
-    -   AC5: Basic separators and margins are used for readability. The HTML is simple and likely to render reasonably in most email clients.
-
----
-
-### Story 5.3: Implement Nodemailer Email Sender
-
--   **User Story / Goal:** As a developer, I want a module to send the generated HTML email using Nodemailer, configured with credentials stored securely in the environment file.
--   **Detailed Requirements:**
-    -   Add Nodemailer dependencies: `npm install nodemailer @types/nodemailer --save-prod`.
-    -   Add required configuration variables to `.env.example` (and local `.env`): `EMAIL_HOST`, `EMAIL_PORT` (e.g., 587), `EMAIL_SECURE` (e.g., `false` for STARTTLS on 587, `true` for 465), `EMAIL_USER`, `EMAIL_PASS`, `EMAIL_FROM` (e.g., `"Your Name <you@example.com>"`), `EMAIL_RECIPIENTS` (comma-separated list).
-    -   Create a new module: `src/email/emailSender.ts`.
-    -   Implement an async function `sendDigestEmail(subject: string, htmlContent: string): Promise<boolean>`.
-    -   Inside the function:
-        -   Load the `EMAIL_*` variables from the config module.
-        -   Create a Nodemailer transporter using `nodemailer.createTransport` with the loaded config (host, port, secure flag, auth: { user, pass }).
-        -   Verify transporter configuration using `transporter.verify()` (optional but recommended). Log verification success/failure.
-        -   Parse the `EMAIL_RECIPIENTS` string into an array or comma-separated string suitable for the `to` field.
-        -   Define the `mailOptions`: `{ from: EMAIL_FROM, to: parsedRecipients, subject: subject, html: htmlContent }`.
-        -   Call `await transporter.sendMail(mailOptions)`.
-        -   If `sendMail` succeeds, log the success message including the `messageId` from the result. Return `true`.
-        -   If `sendMail` fails (throws error), log the error using the logger. Return `false`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: `nodemailer` and `@types/nodemailer` dependencies are added.
-    -   AC2: `EMAIL_*` variables are defined in `.env.example` and loaded from config.
-    -   AC3: `emailSender.ts` module exists and exports `sendDigestEmail`.
-    -   AC4: `sendDigestEmail` correctly creates a Nodemailer transporter using configuration from `.env`. Transporter verification is attempted (optional AC).
-    -   AC5: The `to` field is correctly populated based on `EMAIL_RECIPIENTS`.
-    -   AC6: `transporter.sendMail` is called with correct `from`, `to`, `subject`, and `html` options.
-    -   AC7: Email sending success (including message ID) or failure is logged clearly.
-    -   AC8: The function returns `true` on successful sending, `false` otherwise.
-
----
-
-### Story 5.4: Integrate Email Assembly and Sending into Main Workflow
-
--   **User Story / Goal:** As a developer, I want the main application workflow (`src/index.ts`) to orchestrate the final steps: assembling digest data, rendering the HTML, and triggering the email send after all previous stages are complete.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts`.
-    -   Import `assembleDigestData`, `renderDigestHtml`, `sendDigestEmail`.
-    -   Execute these steps *after* the main loop (where stories are fetched, scraped, summarized, and persisted) completes:
-        -   Log "Starting final digest assembly and email dispatch...".
-        -   Determine the path to the current date-stamped output directory.
-        -   Call `const digestData = await assembleDigestData(dateDirPath)`.
-        -   Check if `digestData` array is not empty.
-            -   If yes:
-                -   Get the current date string (e.g., 'YYYY-MM-DD').
-                -   `const htmlContent = renderDigestHtml(digestData, currentDate)`.
-                -   `const subject = \`BMad Hacker Daily Digest - ${currentDate}\``.
-                -   `const emailSent = await sendDigestEmail(subject, htmlContent)`.
-                -   Log the final outcome based on `emailSent` ("Digest email sent successfully." or "Failed to send digest email.").
-            -   If no (`digestData` is empty or assembly failed):
-                -   Log an error: "Failed to assemble digest data or no data found. Skipping email."
-        -   Log "BMad Hacker Daily Digest process finished."
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes all stages (Epics 1-4) and then proceeds to email assembly and sending.
-    -   AC2: `assembleDigestData` is called correctly with the output directory path after other processing is done.
-    -   AC3: If data is assembled, `renderDigestHtml` and `sendDigestEmail` are called with the correct data, subject, and HTML.
-    -   AC4: The final success or failure of the email sending step is logged.
-    -   AC5: If `assembleDigestData` returns no data, email sending is skipped, and an appropriate message is logged.
-    -   AC6: The application logs a final completion message.
-
----
-
-### Story 5.5: Implement Stage Testing Utility for Emailing
-
--   **User Story / Goal:** As a developer, I want a separate script/command to test the email assembly, rendering, and sending logic using persisted local data, including a crucial `--dry-run` option to prevent accidental email sending during tests.
--   **Detailed Requirements:**
-    -   Add `yargs` dependency for argument parsing: `npm install yargs @types/yargs --save-dev`.
-    -   Create a new standalone script file: `src/stages/send_digest.ts`.
-    -   Import necessary modules: `fs`, `path`, `logger`, `config`, `assembleDigestData`, `renderDigestHtml`, `sendDigestEmail`, `yargs`.
-    -   Use `yargs` to parse command-line arguments, specifically looking for a `--dry-run` boolean flag (defaulting to `false`). Allow an optional argument for specifying the date-stamped directory, otherwise default to current date.
-    -   The script should:
-        -   Initialize logger, load config.
-        -   Determine the target date-stamped directory path (from arg or default). Log the target directory.
-        -   Call `await assembleDigestData(dateDirPath)`.
-        -   If data is assembled and not empty:
-            -   Determine the date string for the subject/title.
-            -   Call `renderDigestHtml(digestData, dateString)` to get HTML.
-            -   Construct the subject string.
-            -   Check the `dryRun` flag:
-                -   If `true`: Log "DRY RUN enabled. Skipping actual email send.". Log the subject. Save the `htmlContent` to a file in the target directory (e.g., `_digest_preview.html`). Log that the preview file was saved.
-                -   If `false`: Log "Live run: Attempting to send email...". Call `await sendDigestEmail(subject, htmlContent)`. Log success/failure based on the return value.
-        -   If data assembly fails or is empty, log the error.
-    -   Add script to `package.json`: `"stage:email": "ts-node src/stages/send_digest.ts --"`. The `--` allows passing arguments like `--dry-run`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/send_digest.ts` exists. `yargs` dependency is added.
-    -   AC2: The script `stage:email` is defined in `package.json` allowing arguments.
-    -   AC3: Running `npm run stage:email -- --dry-run` reads local data, renders HTML, logs the intent, saves `_digest_preview.html` locally, and does *not* call `sendDigestEmail`.
-    -   AC4: Running `npm run stage:email` (without `--dry-run`) reads local data, renders HTML, and *does* call `sendDigestEmail`, logging the outcome.
-    -   AC5: The script correctly identifies and acts upon the `--dry-run` flag.
-    -   AC6: Logs clearly distinguish between dry runs and live runs and report success/failure.
-    -   AC7: The script operates using only local files and the email configuration/service; it does not invoke prior pipeline stages (Algolia, scraping, Ollama).
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 5     | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/epic5.txt

@@ -1,152 +0,0 @@
-# Epic 5: Digest Assembly & Email Dispatch
-
-**Goal:** Assemble the collected story data and summaries from local files, format them into a readable HTML email digest, and send the email using Nodemailer with configured credentials. Implement a stage testing utility for emailing with a dry-run option.
-
-## Story List
-
-### Story 5.1: Implement Email Content Assembler
-
--   **User Story / Goal:** As a developer, I want a module that reads the persisted story metadata (`_data.json`) and summaries (`_summary.json`) from a specified directory, consolidating the necessary information needed to render the email digest.
--   **Detailed Requirements:**
-    -   Create a new module: `src/email/contentAssembler.ts`.
-    -   Define a TypeScript type/interface `DigestData` representing the data needed per story for the email template: `{ storyId: string, title: string, hnUrl: string, articleUrl: string | null, articleSummary: string | null, discussionSummary: string | null }`.
-    -   Implement an async function `assembleDigestData(dateDirPath: string): Promise<DigestData[]>`.
-    -   The function should:
-        -   Use Node.js `fs` to read the contents of the `dateDirPath`.
-        -   Identify all files matching the pattern `{storyId}_data.json`.
-        -   For each `storyId` found:
-            -   Read and parse the `{storyId}_data.json` file. Extract `title`, `hnUrl`, and `url` (use as `articleUrl`). Handle potential file read/parse errors gracefully (log and skip story).
-            -   Attempt to read and parse the corresponding `{storyId}_summary.json` file. Handle file-not-found or parse errors gracefully (treat `articleSummary` and `discussionSummary` as `null`).
-            -   Construct a `DigestData` object for the story, including the extracted metadata and summaries (or nulls).
-        -   Collect all successfully constructed `DigestData` objects into an array.
-        -   Return the array. It should ideally contain 10 items if all previous stages succeeded.
-    -   Log progress (e.g., "Assembling digest data from directory...", "Processing story {storyId}...") and any errors encountered during file processing using the logger.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The `contentAssembler.ts` module exists and exports `assembleDigestData` and the `DigestData` type.
-    -   AC2: `assembleDigestData` correctly reads `_data.json` files from the provided directory path.
-    -   AC3: It attempts to read corresponding `_summary.json` files, correctly handling cases where the summary file might be missing or unparseable (resulting in null summaries for that story).
-    -   AC4: The function returns a promise resolving to an array of `DigestData` objects, populated with data extracted from the files.
-    -   AC5: Errors during file reading or JSON parsing are logged, and the function returns data for successfully processed stories.
-
----
-
-### Story 5.2: Create HTML Email Template & Renderer
-
--   **User Story / Goal:** As a developer, I want a basic HTML email template and a function to render it with the assembled digest data, producing the final HTML content for the email body.
--   **Detailed Requirements:**
-    -   Define the HTML structure. This can be done using template literals within a function or potentially using a simple template file (e.g., `src/email/templates/digestTemplate.html`) and `fs.readFileSync`. Template literals are simpler for MVP.
-    -   Create a function `renderDigestHtml(data: DigestData[], digestDate: string): string` (e.g., in `src/email/contentAssembler.ts` or a new `templater.ts`).
-    -   The function should generate an HTML string with:
-        -   A suitable title in the body (e.g., `<h1>Hacker News Top 10 Summaries for ${digestDate}</h1>`).
-        -   A loop through the `data` array.
-        -   For each `story` in `data`:
-            -   Display `<h2><a href="${story.articleUrl || story.hnUrl}">${story.title}</a></h2>`.
-            -   Display `<p><a href="${story.hnUrl}">View HN Discussion</a></p>`.
-            -   Conditionally display `<h3>Article Summary</h3><p>${story.articleSummary}</p>` *only if* `story.articleSummary` is not null/empty.
-            -   Conditionally display `<h3>Discussion Summary</h3><p>${story.discussionSummary}</p>` *only if* `story.discussionSummary` is not null/empty.
-            -   Include a separator (e.g., `<hr style="margin-top: 20px; margin-bottom: 20px;">`).
-    -   Use basic inline CSS for minimal styling (margins, etc.) to ensure readability. Avoid complex layouts.
-    -   Return the complete HTML document as a string.
--   **Acceptance Criteria (ACs):**
-    -   AC1: A function `renderDigestHtml` exists that accepts the digest data array and a date string.
-    -   AC2: The function returns a single, complete HTML string.
-    -   AC3: The generated HTML includes a title with the date and correctly iterates through the story data.
-    -   AC4: For each story, the HTML displays the linked title, HN link, and conditionally displays the article and discussion summaries with headings.
-    -   AC5: Basic separators and margins are used for readability. The HTML is simple and likely to render reasonably in most email clients.
-
----
-
-### Story 5.3: Implement Nodemailer Email Sender
-
--   **User Story / Goal:** As a developer, I want a module to send the generated HTML email using Nodemailer, configured with credentials stored securely in the environment file.
--   **Detailed Requirements:**
-    -   Add Nodemailer dependencies: `npm install nodemailer @types/nodemailer --save-prod`.
-    -   Add required configuration variables to `.env.example` (and local `.env`): `EMAIL_HOST`, `EMAIL_PORT` (e.g., 587), `EMAIL_SECURE` (e.g., `false` for STARTTLS on 587, `true` for 465), `EMAIL_USER`, `EMAIL_PASS`, `EMAIL_FROM` (e.g., `"Your Name <you@example.com>"`), `EMAIL_RECIPIENTS` (comma-separated list).
-    -   Create a new module: `src/email/emailSender.ts`.
-    -   Implement an async function `sendDigestEmail(subject: string, htmlContent: string): Promise<boolean>`.
-    -   Inside the function:
-        -   Load the `EMAIL_*` variables from the config module.
-        -   Create a Nodemailer transporter using `nodemailer.createTransport` with the loaded config (host, port, secure flag, auth: { user, pass }).
-        -   Verify transporter configuration using `transporter.verify()` (optional but recommended). Log verification success/failure.
-        -   Parse the `EMAIL_RECIPIENTS` string into an array or comma-separated string suitable for the `to` field.
-        -   Define the `mailOptions`: `{ from: EMAIL_FROM, to: parsedRecipients, subject: subject, html: htmlContent }`.
-        -   Call `await transporter.sendMail(mailOptions)`.
-        -   If `sendMail` succeeds, log the success message including the `messageId` from the result. Return `true`.
-        -   If `sendMail` fails (throws error), log the error using the logger. Return `false`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: `nodemailer` and `@types/nodemailer` dependencies are added.
-    -   AC2: `EMAIL_*` variables are defined in `.env.example` and loaded from config.
-    -   AC3: `emailSender.ts` module exists and exports `sendDigestEmail`.
-    -   AC4: `sendDigestEmail` correctly creates a Nodemailer transporter using configuration from `.env`. Transporter verification is attempted (optional AC).
-    -   AC5: The `to` field is correctly populated based on `EMAIL_RECIPIENTS`.
-    -   AC6: `transporter.sendMail` is called with correct `from`, `to`, `subject`, and `html` options.
-    -   AC7: Email sending success (including message ID) or failure is logged clearly.
-    -   AC8: The function returns `true` on successful sending, `false` otherwise.
-
----
-
-### Story 5.4: Integrate Email Assembly and Sending into Main Workflow
-
--   **User Story / Goal:** As a developer, I want the main application workflow (`src/index.ts`) to orchestrate the final steps: assembling digest data, rendering the HTML, and triggering the email send after all previous stages are complete.
--   **Detailed Requirements:**
-    -   Modify the main execution flow in `src/index.ts`.
-    -   Import `assembleDigestData`, `renderDigestHtml`, `sendDigestEmail`.
-    -   Execute these steps *after* the main loop (where stories are fetched, scraped, summarized, and persisted) completes:
-        -   Log "Starting final digest assembly and email dispatch...".
-        -   Determine the path to the current date-stamped output directory.
-        -   Call `const digestData = await assembleDigestData(dateDirPath)`.
-        -   Check if `digestData` array is not empty.
-            -   If yes:
-                -   Get the current date string (e.g., 'YYYY-MM-DD').
-                -   `const htmlContent = renderDigestHtml(digestData, currentDate)`.
-                -   `const subject = \`BMad Hacker Daily Digest - ${currentDate}\``.
-                -   `const emailSent = await sendDigestEmail(subject, htmlContent)`.
-                -   Log the final outcome based on `emailSent` ("Digest email sent successfully." or "Failed to send digest email.").
-            -   If no (`digestData` is empty or assembly failed):
-                -   Log an error: "Failed to assemble digest data or no data found. Skipping email."
-        -   Log "BMad Hacker Daily Digest process finished."
--   **Acceptance Criteria (ACs):**
-    -   AC1: Running `npm run dev` executes all stages (Epics 1-4) and then proceeds to email assembly and sending.
-    -   AC2: `assembleDigestData` is called correctly with the output directory path after other processing is done.
-    -   AC3: If data is assembled, `renderDigestHtml` and `sendDigestEmail` are called with the correct data, subject, and HTML.
-    -   AC4: The final success or failure of the email sending step is logged.
-    -   AC5: If `assembleDigestData` returns no data, email sending is skipped, and an appropriate message is logged.
-    -   AC6: The application logs a final completion message.
-
----
-
-### Story 5.5: Implement Stage Testing Utility for Emailing
-
--   **User Story / Goal:** As a developer, I want a separate script/command to test the email assembly, rendering, and sending logic using persisted local data, including a crucial `--dry-run` option to prevent accidental email sending during tests.
--   **Detailed Requirements:**
-    -   Add `yargs` dependency for argument parsing: `npm install yargs @types/yargs --save-dev`.
-    -   Create a new standalone script file: `src/stages/send_digest.ts`.
-    -   Import necessary modules: `fs`, `path`, `logger`, `config`, `assembleDigestData`, `renderDigestHtml`, `sendDigestEmail`, `yargs`.
-    -   Use `yargs` to parse command-line arguments, specifically looking for a `--dry-run` boolean flag (defaulting to `false`). Allow an optional argument for specifying the date-stamped directory, otherwise default to current date.
-    -   The script should:
-        -   Initialize logger, load config.
-        -   Determine the target date-stamped directory path (from arg or default). Log the target directory.
-        -   Call `await assembleDigestData(dateDirPath)`.
-        -   If data is assembled and not empty:
-            -   Determine the date string for the subject/title.
-            -   Call `renderDigestHtml(digestData, dateString)` to get HTML.
-            -   Construct the subject string.
-            -   Check the `dryRun` flag:
-                -   If `true`: Log "DRY RUN enabled. Skipping actual email send.". Log the subject. Save the `htmlContent` to a file in the target directory (e.g., `_digest_preview.html`). Log that the preview file was saved.
-                -   If `false`: Log "Live run: Attempting to send email...". Call `await sendDigestEmail(subject, htmlContent)`. Log success/failure based on the return value.
-        -   If data assembly fails or is empty, log the error.
-    -   Add script to `package.json`: `"stage:email": "ts-node src/stages/send_digest.ts --"`. The `--` allows passing arguments like `--dry-run`.
--   **Acceptance Criteria (ACs):**
-    -   AC1: The file `src/stages/send_digest.ts` exists. `yargs` dependency is added.
-    -   AC2: The script `stage:email` is defined in `package.json` allowing arguments.
-    -   AC3: Running `npm run stage:email -- --dry-run` reads local data, renders HTML, logs the intent, saves `_digest_preview.html` locally, and does *not* call `sendDigestEmail`.
-    -   AC4: Running `npm run stage:email` (without `--dry-run`) reads local data, renders HTML, and *does* call `sendDigestEmail`, logging the outcome.
-    -   AC5: The script correctly identifies and acts upon the `--dry-run` flag.
-    -   AC6: Logs clearly distinguish between dry runs and live runs and report success/failure.
-    -   AC7: The script operates using only local files and the email configuration/service; it does not invoke prior pipeline stages (Algolia, scraping, Ollama).
-
-## Change Log
-
-| Change        | Date       | Version | Description               | Author         |
-| ------------- | ---------- | ------- | ------------------------- | -------------- |
-| Initial Draft | 2025-05-04 | 0.1     | First draft of Epic 5     | 2-pm           |

V2-FULL-DEMO-WALKTHROUGH/final-brief-with-pm-prompt.md

@@ -1,111 +0,0 @@
-# Project Brief: BMad Hacker Daily Digest
-
-## Introduction / Problem Statement
-
-Hacker News (HN) comment threads contain valuable insights but can be prohibitively long to read thoroughly. The BMad Hacker Daily Digest project aims to solve this by providing a time-efficient way to stay informed about the collective intelligence within HN discussions. The service will automatically fetch the top 10 HN stories daily, retrieve a manageable subset of their comments using the Algolia HN API, generate concise summaries of both the linked article (when possible) and the comment discussion using an LLM, and deliver these summaries in a daily email briefing. This project also serves as a practical learning exercise focused on agent-driven development, TypeScript, Node.js backend services, API integration, and local LLM usage with Ollama.
-
-## Vision & Goals
-
-- **Vision:** To provide a quick, reliable, and automated way for users to stay informed about the key insights and discussions happening within the Hacker News community without needing to read lengthy comment threads.
-- **Primary Goals (MVP - SMART):**
-  - **Fetch HN Story Data:** Successfully retrieve the IDs and metadata (title, URL, HN link) of the top 10 Hacker News stories using the Algolia HN Search API when triggered.
-  - **Retrieve Limited Comments:** For each fetched story, retrieve a predefined, limited set of associated comments using the Algolia HN Search API.
-  - **Attempt Article Scraping:** For each story's external URL, attempt to fetch the raw HTML and extract the main article text using basic methods (Node.js native fetch, article-extractor/Cheerio), handling failures gracefully.
-  - **Generate Summaries (LLM):** Using a local LLM (via Ollama, configured endpoint), generate: an "Article Summary" from scraped text (if successful), and a separate "Discussion Summary" from fetched comments.
-  - **Assemble & Send Digest (Manual Trigger):** Format results for 10 stories into a single HTML email and successfully send it to recipients (list defined in config) using Nodemailer when manually triggered via CLI.
-- **Success Metrics (Initial Ideas for MVP):**
-  - **Successful Execution:** The entire process completes successfully without crashing when manually triggered via CLI for 3 different test runs.
-  - **Digest Content:** The generated email contains results for 10 stories (correct links, discussion summary, article summary where possible). Spot checks confirm relevance.
-  - **Error Handling:** Scraping failures are logged, and the process continues using only comment summaries for affected stories without halting the script.
-
-## Target Audience / Users
-
-**Primary User (MVP):** The developer undertaking this project. The primary motivation is learning and demonstrating agent-driven development, TypeScript, Node.js (v22), API integration (Algolia, LLM, Email), local LLMs (Ollama), and configuration management ( .env ). The key need is an interesting, achievable project scope utilizing these technologies.
-
-**Secondary User (Potential):** Time-constrained HN readers/tech enthusiasts needing automated discussion summaries. Addressing their needs fully is outside MVP scope but informs potential future direction.
-
-## Key Features / Scope (High-Level Ideas for MVP)
-
-- Fetch Top HN Stories (Algolia API).
-- Fetch Limited Comments (Algolia API).
-- Local File Storage (Date-stamped folder, structured text/JSON files).
-- Attempt Basic Article Scraping (Node.js v22 native fetch, basic extraction).
-- Handle Scraping Failures (Log error, proceed with comment-only summary).
-- Generate Summaries (Local Ollama via configured endpoint: Article Summary if scraped, Discussion Summary always).
-- Format Digest Email (HTML: Article Summary (opt.), Discussion Summary, HN link, Article link).
-- Manual Email Dispatch (Nodemailer, credentials from .env , recipient list from .env ).
-- CLI Trigger (Manual command to run full process).
-
-**Explicitly OUT of Scope for MVP:** Advanced scraping (JS render, anti-bot), processing _all_ comments/MapReduce summaries, automated scheduling (cron), database integration, cloud deployment/web frontend, user management (sign-ups etc.), production-grade error handling/monitoring/deliverability, fine-tuning LLM prompts, sophisticated retry logic.
-
-## Known Technical Constraints or Preferences
-
-- **Constraints/Preferences:**
-
-  - **Language/Runtime:** TypeScript running on Node.js v22.
-  - **Execution Environment:** Local machine execution for MVP.
-  - **Trigger Mechanism:** Manual CLI trigger only for MVP.
-  - **Configuration Management:** Use a `.env` file for configuration: LLM endpoint URL, email credentials, recipient email list, potentially comment fetch limits etc.
-  - **HTTP Requests:** Use Node.js v22 native fetch API (no Axios).
-  - **HN Data Source:** Algolia HN Search API.
-  - **Web Scraping:** Basic, best-effort only (native fetch + static HTML extraction). Must handle failures gracefully.
-  - **LLM Integration:** Local Ollama via configurable endpoint for MVP. Design for potential swap to cloud LLMs. Functionality over quality for MVP.
-  - **Summarization Strategy:** Separate Article/Discussion summaries. Limit comments processed per story (configurable). No MapReduce.
-  - **Data Storage:** Local file system (structured text/JSON in date-stamped folders). No database.
-  - **Email Delivery:** Nodemailer. Read credentials and recipient list from `.env`. Basic setup, no production deliverability focus.
-  - **Primary Goal Context:** Focus on functional pipeline for learning/demonstration.
-
-- **Risks:**
-  - Algolia HN API Issues: Changes, rate limits, availability.
-  - Web Scraping Fragility: High likelihood of failure limiting Article Summaries.
-  - LLM Variability & Quality: Inconsistent performance/quality from local Ollama; potential errors.
-    *Incomplete Discussion Capture: Limited comment fetching may miss key insights.
-    *Email Configuration/Deliverability: Fragility of personal credentials; potential spam filtering.
-    *Manual Trigger Dependency: Digest only generated on manual execution.
-    *Configuration Errors: Incorrect `.env` settings could break the application.
-    _(User Note: Risks acknowledged and accepted given the project's learning goals.)_
-
-## Relevant Research (Optional)
-
-Feasibility: Core concept confirmed technically feasible with available APIs/libraries.
-Existing Tools & Market Context: Similar tools exist (validating interest), but daily email format appears distinct.
-API Selection: Algolia HN Search API chosen for filtering/sorting capabilities.
-Identified Technical Challenges: Confirmed complexities of scraping and handling large comment volumes within LLM limits, informing MVP scope.
-Local LLM Viability: Ollama confirmed as viable for local MVP development/testing, with potential for future swapping.
-
-## PM Prompt
-
-**PM Agent Handoff Prompt: BMad Hacker Daily Digest**
-
-**Summary of Key Insights:**
-
-This Project Brief outlines the "BMad Hacker Daily Digest," a command-line tool designed to provide daily email summaries of discussions from top Hacker News (HN) comment threads. The core problem is the time required to read lengthy but valuable HN discussions. The MVP aims to fetch the top 10 HN stories, retrieve a limited set of comments via the Algolia HN API, attempt basic scraping of linked articles (with fallback), generate separate summaries for articles (if scraped) and comments using a local LLM (Ollama), and email the digest to the developer using Nodemailer. This project primarily serves as a learning exercise and demonstration of agent-driven development in TypeScript.
-
-**Areas Requiring Special Attention (for PRD):**
-
-- **Comment Selection Logic:** Define the specific criteria for selecting the "limited set" of comments from Algolia (e.g., number of comments, recency, token count limit).
-- **Basic Scraping Implementation:** Detail the exact steps for the basic article scraping attempt (libraries like Node.js native fetch, article-extractor/Cheerio), including specific error handling and the fallback mechanism.
-- **LLM Prompting:** Define the precise prompts for generating the "Article Summary" and the "Discussion Summary" separately.
-- **Email Formatting:** Specify the exact structure, layout, and content presentation within the daily HTML email digest.
-- **CLI Interface:** Define the specific command(s), arguments, and expected output/feedback for the manual trigger.
-- **Local File Structure:** Define the structure for storing intermediate data and logs in local text files within date-stamped folders.
-
-**Development Context:**
-
-This brief was developed through iterative discussion, starting from general app ideas and refining scope based on user interest (HN discussions) and technical feasibility for a learning/demo project. Key decisions include prioritizing comment summarization, using the Algolia HN API, starting with local execution (Ollama, Nodemailer), and including only a basic, best-effort scraping attempt in the MVP.
-
-**Guidance on PRD Detail:**
-
-- Focus detailed requirements and user stories on the core data pipeline: HN API Fetch -> Comment Selection -> Basic Scrape Attempt -> LLM Summarization (x2) -> Email Formatting/Sending -> CLI Trigger.
-- Keep potential post-MVP enhancements (cloud deployment, frontend, database, advanced scraping, scheduling) as high-level future considerations.
-- Technical implementation details for API/LLM interaction should allow flexibility for potential future swapping (e.g., Ollama to cloud LLM).
-
-**User Preferences:**
-
-- Execution: Manual CLI trigger for MVP.
-- Data Storage: Local text files for MVP.
-- LLM: Ollama for local development/MVP. Ability to potentially switch to cloud API later.
-- Summaries: Generate separate summaries for article (if available) and comments.
-- API: Use Algolia HN Search API.
-- Email: Use Nodemailer for self-send in MVP.
-- Tech Stack: TypeScript, Node.js v22.

V2-FULL-DEMO-WALKTHROUGH/final-brief-with-pm-prompt.txt

@@ -1,111 +0,0 @@
-# Project Brief: BMad Hacker Daily Digest
-
-## Introduction / Problem Statement
-
-Hacker News (HN) comment threads contain valuable insights but can be prohibitively long to read thoroughly. The BMad Hacker Daily Digest project aims to solve this by providing a time-efficient way to stay informed about the collective intelligence within HN discussions. The service will automatically fetch the top 10 HN stories daily, retrieve a manageable subset of their comments using the Algolia HN API, generate concise summaries of both the linked article (when possible) and the comment discussion using an LLM, and deliver these summaries in a daily email briefing. This project also serves as a practical learning exercise focused on agent-driven development, TypeScript, Node.js backend services, API integration, and local LLM usage with Ollama.
-
-## Vision & Goals
-
-- **Vision:** To provide a quick, reliable, and automated way for users to stay informed about the key insights and discussions happening within the Hacker News community without needing to read lengthy comment threads.
-- **Primary Goals (MVP - SMART):**
-  - **Fetch HN Story Data:** Successfully retrieve the IDs and metadata (title, URL, HN link) of the top 10 Hacker News stories using the Algolia HN Search API when triggered.
-  - **Retrieve Limited Comments:** For each fetched story, retrieve a predefined, limited set of associated comments using the Algolia HN Search API.
-  - **Attempt Article Scraping:** For each story's external URL, attempt to fetch the raw HTML and extract the main article text using basic methods (Node.js native fetch, article-extractor/Cheerio), handling failures gracefully.
-  - **Generate Summaries (LLM):** Using a local LLM (via Ollama, configured endpoint), generate: an "Article Summary" from scraped text (if successful), and a separate "Discussion Summary" from fetched comments.
-  - **Assemble & Send Digest (Manual Trigger):** Format results for 10 stories into a single HTML email and successfully send it to recipients (list defined in config) using Nodemailer when manually triggered via CLI.
-- **Success Metrics (Initial Ideas for MVP):**
-  - **Successful Execution:** The entire process completes successfully without crashing when manually triggered via CLI for 3 different test runs.
-  - **Digest Content:** The generated email contains results for 10 stories (correct links, discussion summary, article summary where possible). Spot checks confirm relevance.
-  - **Error Handling:** Scraping failures are logged, and the process continues using only comment summaries for affected stories without halting the script.
-
-## Target Audience / Users
-
-**Primary User (MVP):** The developer undertaking this project. The primary motivation is learning and demonstrating agent-driven development, TypeScript, Node.js (v22), API integration (Algolia, LLM, Email), local LLMs (Ollama), and configuration management ( .env ). The key need is an interesting, achievable project scope utilizing these technologies.
-
-**Secondary User (Potential):** Time-constrained HN readers/tech enthusiasts needing automated discussion summaries. Addressing their needs fully is outside MVP scope but informs potential future direction.
-
-## Key Features / Scope (High-Level Ideas for MVP)
-
-- Fetch Top HN Stories (Algolia API).
-- Fetch Limited Comments (Algolia API).
-- Local File Storage (Date-stamped folder, structured text/JSON files).
-- Attempt Basic Article Scraping (Node.js v22 native fetch, basic extraction).
-- Handle Scraping Failures (Log error, proceed with comment-only summary).
-- Generate Summaries (Local Ollama via configured endpoint: Article Summary if scraped, Discussion Summary always).
-- Format Digest Email (HTML: Article Summary (opt.), Discussion Summary, HN link, Article link).
-- Manual Email Dispatch (Nodemailer, credentials from .env , recipient list from .env ).
-- CLI Trigger (Manual command to run full process).
-
-**Explicitly OUT of Scope for MVP:** Advanced scraping (JS render, anti-bot), processing _all_ comments/MapReduce summaries, automated scheduling (cron), database integration, cloud deployment/web frontend, user management (sign-ups etc.), production-grade error handling/monitoring/deliverability, fine-tuning LLM prompts, sophisticated retry logic.
-
-## Known Technical Constraints or Preferences
-
-- **Constraints/Preferences:**
-
-  - **Language/Runtime:** TypeScript running on Node.js v22.
-  - **Execution Environment:** Local machine execution for MVP.
-  - **Trigger Mechanism:** Manual CLI trigger only for MVP.
-  - **Configuration Management:** Use a `.env` file for configuration: LLM endpoint URL, email credentials, recipient email list, potentially comment fetch limits etc.
-  - **HTTP Requests:** Use Node.js v22 native fetch API (no Axios).
-  - **HN Data Source:** Algolia HN Search API.
-  - **Web Scraping:** Basic, best-effort only (native fetch + static HTML extraction). Must handle failures gracefully.
-  - **LLM Integration:** Local Ollama via configurable endpoint for MVP. Design for potential swap to cloud LLMs. Functionality over quality for MVP.
-  - **Summarization Strategy:** Separate Article/Discussion summaries. Limit comments processed per story (configurable). No MapReduce.
-  - **Data Storage:** Local file system (structured text/JSON in date-stamped folders). No database.
-  - **Email Delivery:** Nodemailer. Read credentials and recipient list from `.env`. Basic setup, no production deliverability focus.
-  - **Primary Goal Context:** Focus on functional pipeline for learning/demonstration.
-
-- **Risks:**
-  - Algolia HN API Issues: Changes, rate limits, availability.
-  - Web Scraping Fragility: High likelihood of failure limiting Article Summaries.
-  - LLM Variability & Quality: Inconsistent performance/quality from local Ollama; potential errors.
-    *Incomplete Discussion Capture: Limited comment fetching may miss key insights.
-    *Email Configuration/Deliverability: Fragility of personal credentials; potential spam filtering.
-    *Manual Trigger Dependency: Digest only generated on manual execution.
-    *Configuration Errors: Incorrect `.env` settings could break the application.
-    _(User Note: Risks acknowledged and accepted given the project's learning goals.)_
-
-## Relevant Research (Optional)
-
-Feasibility: Core concept confirmed technically feasible with available APIs/libraries.
-Existing Tools & Market Context: Similar tools exist (validating interest), but daily email format appears distinct.
-API Selection: Algolia HN Search API chosen for filtering/sorting capabilities.
-Identified Technical Challenges: Confirmed complexities of scraping and handling large comment volumes within LLM limits, informing MVP scope.
-Local LLM Viability: Ollama confirmed as viable for local MVP development/testing, with potential for future swapping.
-
-## PM Prompt
-
-**PM Agent Handoff Prompt: BMad Hacker Daily Digest**
-
-**Summary of Key Insights:**
-
-This Project Brief outlines the "BMad Hacker Daily Digest," a command-line tool designed to provide daily email summaries of discussions from top Hacker News (HN) comment threads. The core problem is the time required to read lengthy but valuable HN discussions. The MVP aims to fetch the top 10 HN stories, retrieve a limited set of comments via the Algolia HN API, attempt basic scraping of linked articles (with fallback), generate separate summaries for articles (if scraped) and comments using a local LLM (Ollama), and email the digest to the developer using Nodemailer. This project primarily serves as a learning exercise and demonstration of agent-driven development in TypeScript.
-
-**Areas Requiring Special Attention (for PRD):**
-
-- **Comment Selection Logic:** Define the specific criteria for selecting the "limited set" of comments from Algolia (e.g., number of comments, recency, token count limit).
-- **Basic Scraping Implementation:** Detail the exact steps for the basic article scraping attempt (libraries like Node.js native fetch, article-extractor/Cheerio), including specific error handling and the fallback mechanism.
-- **LLM Prompting:** Define the precise prompts for generating the "Article Summary" and the "Discussion Summary" separately.
-- **Email Formatting:** Specify the exact structure, layout, and content presentation within the daily HTML email digest.
-- **CLI Interface:** Define the specific command(s), arguments, and expected output/feedback for the manual trigger.
-- **Local File Structure:** Define the structure for storing intermediate data and logs in local text files within date-stamped folders.
-
-**Development Context:**
-
-This brief was developed through iterative discussion, starting from general app ideas and refining scope based on user interest (HN discussions) and technical feasibility for a learning/demo project. Key decisions include prioritizing comment summarization, using the Algolia HN API, starting with local execution (Ollama, Nodemailer), and including only a basic, best-effort scraping attempt in the MVP.
-
-**Guidance on PRD Detail:**
-
-- Focus detailed requirements and user stories on the core data pipeline: HN API Fetch -> Comment Selection -> Basic Scrape Attempt -> LLM Summarization (x2) -> Email Formatting/Sending -> CLI Trigger.
-- Keep potential post-MVP enhancements (cloud deployment, frontend, database, advanced scraping, scheduling) as high-level future considerations.
-- Technical implementation details for API/LLM interaction should allow flexibility for potential future swapping (e.g., Ollama to cloud LLM).
-
-**User Preferences:**
-
-- Execution: Manual CLI trigger for MVP.
-- Data Storage: Local text files for MVP.
-- LLM: Ollama for local development/MVP. Ability to potentially switch to cloud API later.
-- Summaries: Generate separate summaries for article (if available) and comments.
-- API: Use Algolia HN Search API.
-- Email: Use Nodemailer for self-send in MVP.
-- Tech Stack: TypeScript, Node.js v22.

V2-FULL-DEMO-WALKTHROUGH/prd.md

@@ -1,189 +0,0 @@
-# BMad Hacker Daily Digest Product Requirements Document (PRD)
-
-## Intro
-
-The BMad Hacker Daily Digest is a command-line tool designed to address the time-consuming nature of reading extensive Hacker News (HN) comment threads. It aims to provide users with a time-efficient way to grasp the collective intelligence and key insights from discussions on top HN stories. The service will fetch the top 10 HN stories daily, retrieve a configurable number of comments for each, attempt to scrape the linked article, generate separate summaries for the article (if scraped) and the comment discussion using a local LLM, and deliver these summaries in a single daily email briefing triggered manually. This project also serves as a practical learning exercise in agent-driven development, TypeScript, Node.js, API integration, and local LLM usage, starting from the provided "bmad-boilerplate" template.
-
-## Goals and Context
-
-- **Project Objectives:**
-  - Provide a quick, reliable, automated way to stay informed about key HN discussions without reading full threads.
-  - Successfully fetch top 10 HN story metadata via Algolia HN API.
-  - Retrieve a _configurable_ number of comments per story (default 50) via Algolia HN API.
-  - Attempt basic scraping of linked article content, handling failures gracefully.
-  - Generate distinct Article Summaries (if scraped) and Discussion Summaries using a local LLM (Ollama).
-  - Assemble summaries for 10 stories into an HTML email and send via Nodemailer upon manual CLI trigger.
-  - Serve as a learning platform for agent-driven development, TypeScript, Node.js v22, API integration, local LLMs, and configuration management, leveraging the "bmad-boilerplate" structure and tooling.
-- **Measurable Outcomes:**
-  - The tool completes its full process (fetch, scrape attempt, summarize, email) without crashing on manual CLI trigger across multiple test runs.
-  - The generated email digest consistently contains results for 10 stories, including correct links, discussion summaries, and article summaries where scraping was successful.
-  - Errors during article scraping are logged, and the process continues for affected stories using only comment summaries, without halting the script.
-- **Success Criteria:**
-  - Successful execution of the end-to-end process via CLI trigger for 3 consecutive test runs.
-  - Generated email is successfully sent and received, containing summaries for all 10 fetched stories (article summary optional based on scraping success).
-  - Scraping failures are logged appropriately without stopping the overall process.
-- **Key Performance Indicators (KPIs):**
-  - Successful Runs / Total Runs (Target: 100% for MVP tests)
-  - Stories with Article Summaries / Total Stories (Measures scraping effectiveness)
-  - Stories with Discussion Summaries / Total Stories (Target: 100%)
-  * Manual Qualitative Check: Relevance and coherence of summaries in the digest.
-
-## Scope and Requirements (MVP / Current Version)
-
-### Functional Requirements (High-Level)
-
-- **HN Story Fetching:** Retrieve IDs and metadata (title, URL, HN link) for the top 10 stories from Algolia HN Search API.
-- **HN Comment Fetching:** For each story, retrieve comments from Algolia HN Search API up to a maximum count defined in a `.env` configuration variable (`MAX_COMMENTS_PER_STORY`, default 50).
-- **Article Content Scraping:** Attempt to fetch HTML and extract main text content from the story's external URL using basic methods (e.g., Node.js native fetch, optionally `article-extractor` or similar basic library).
-- **Scraping Failure Handling:** If scraping fails, log the error and proceed with generating only the Discussion Summary for that story.
-- **LLM Summarization:**
-  - Generate an "Article Summary" from scraped text (if successful) using a configured local LLM (Ollama endpoint).
-  - Generate a "Discussion Summary" from the fetched comments using the same LLM.
-  - Initial Prompts (Placeholders - refine in Epics):
-    - _Article Prompt:_ "Summarize the key points of the following article text: {Article Text}"
-    - _Discussion Prompt:_ "Summarize the main themes, viewpoints, and key insights from the following Hacker News comments: {Comment Texts}"
-- **Digest Formatting:** Combine results for the 10 stories into a single HTML email. Each story entry should include: Story Title, HN Link, Article Link, Article Summary (if available), Discussion Summary.
-- **Email Dispatch:** Send the formatted HTML email using Nodemailer to a recipient list defined in `.env`. Use credentials also stored in `.env`.
-- **Main Execution Trigger:** Initiate the _entire implemented pipeline_ via a manual command-line interface (CLI) trigger, using the standard scripts defined in the boilerplate (`npm run dev`, `npm start` after build). Each functional epic should add its capability to this main execution flow.
-- **Configuration:** Manage external parameters (Algolia API details (if needed), LLM endpoint URL, `MAX_COMMENTS_PER_STORY`, Nodemailer credentials, recipient email list, output directory path) via a `.env` file, based on the provided `.env.example`.
-- **Incremental Logging & Data Persistence:**
-  - Implement basic console logging for key steps and errors throughout the pipeline.
-  - Persist intermediate data artifacts (fetched stories/comments, scraped text, generated summaries) to local files within a configurable, date-stamped directory structure (e.g., `./output/YYYY-MM-DD/`).
-  - This persistence should be implemented incrementally within the relevant functional epics (Data Acquisition, Scraping, Summarization).
-- **Stage Testing Utilities:**
-  - Provide separate utility scripts or CLI commands to allow testing individual pipeline stages in isolation (e.g., fetching HN data, scraping URLs, summarizing text, sending email).
-  - These utilities should support using locally saved files as input (e.g., test scraping using a file containing story URLs, test summarization using a file containing text). This facilitates development and debugging.
-
-### Non-Functional Requirements (NFRs)
-
-- **Performance:** MVP focuses on functionality over speed. Should complete within a reasonable time (e.g., < 5 minutes) on a typical developer machine for local LLM use. No specific response time targets.
-- **Scalability:** Designed for single-user, local execution. No scaling requirements for MVP.
-- **Reliability/Availability:**
-  - The script must handle article scraping failures gracefully (log and continue).
-  - Basic error handling for API calls (e.g., log network errors).
-  - Local LLM interaction may fail; basic error logging is sufficient for MVP.
-  - No requirement for automated retries or production-grade error handling.
-- **Security:**
-  - Email credentials must be stored securely via `.env` file and not committed to version control (as per boilerplate `.gitignore`).
-  - No other specific security requirements for local MVP.
-- **Maintainability:**
-  - Code should be well-structured TypeScript.
-  - Adherence to the linting (ESLint) and formatting (Prettier) rules configured in the "bmad-boilerplate" is required. Use `npm run lint` and `npm run format`.
-  - Modularity is desired to potentially swap LLM providers later and facilitate stage testing.
-- **Usability/Accessibility:** N/A (CLI tool for developer).
-- **Other Constraints:**
-  - Must use TypeScript and Node.js v22.
-  - Must run locally on the developer's machine.
-  - Must use Node.js v22 native `Workspace` API for HTTP requests.
-  - Must use Algolia HN Search API for HN data.
-  - Must use a local Ollama instance via a configurable HTTP endpoint.
-  - Must use Nodemailer for email dispatch.
-  - Must use `.env` for configuration based on `.env.example`.
-  - Must use local file system for logging and intermediate data storage. Ensure output/log directories are gitignored.
-  - Focus on a functional pipeline for learning/demonstration.
-
-### User Experience (UX) Requirements (High-Level)
-
-- The primary UX goal is to deliver a time-saving digest.
-- For the developer user, the main CLI interaction should be simple: using standard boilerplate scripts like `npm run dev` or `npm start` to trigger the full process.
-- Feedback during CLI execution (e.g., "Fetching stories...", "Summarizing story X/10...", "Sending email...") is desirable via console logging.
-- Separate CLI commands/scripts for testing individual stages should provide clear input/output mechanisms.
-
-### Integration Requirements (High-Level)
-
-- **Algolia HN Search API:** Fetching top stories and comments. Requires understanding API structure and query parameters.
-- **Ollama Service:** Sending text (article content, comments) and receiving summaries via its API endpoint. Endpoint URL must be configurable.
-- **SMTP Service (via Nodemailer):** Sending the final digest email. Requires valid SMTP credentials and recipient list configured in `.env`.
-
-### Testing Requirements (High-Level)
-
-- MVP success relies on manual end-to-end test runs confirming successful execution and valid email output.
-- Unit/integration tests are encouraged using the **Jest framework configured in the boilerplate**. Focus testing effort on the core pipeline components. Use `npm run test`.
-- **Stage-specific testing utilities (as defined in Functional Requirements) are required** to support development and verification of individual pipeline components.
-
-## Epic Overview (MVP / Current Version)
-
-_(Revised proposal)_
-
-- **Epic 1: Project Initialization & Core Setup** - Goal: Initialize the project using "bmad-boilerplate", manage dependencies, setup `.env` and config loading, establish basic CLI entry point, setup basic logging and output directory structure.
-- **Epic 2: HN Data Acquisition & Persistence** - Goal: Implement fetching top 10 stories and their comments (respecting limits) from Algolia HN API, and persist this raw data locally. Implement stage testing utility for fetching.
-- **Epic 3: Article Scraping & Persistence** - Goal: Implement best-effort article scraping/extraction, handle failures gracefully, and persist scraped text locally. Implement stage testing utility for scraping.
-- **Epic 4: LLM Summarization & Persistence** - Goal: Integrate with Ollama to generate article/discussion summaries from persisted data and persist summaries locally. Implement stage testing utility for summarization.
-- **Epic 5: Digest Assembly & Email Dispatch** - Goal: Format collected summaries into an HTML email using persisted data and send it using Nodemailer. Implement stage testing utility for emailing (with dry-run option).
-
-## Key Reference Documents
-
-- `docs/project-brief.md`
-- `docs/prd.md` (This document)
-- `docs/architecture.md` (To be created by Architect)
-- `docs/epic1.md`, `docs/epic2.md`, ... (To be created)
-- `docs/tech-stack.md` (Partially defined by boilerplate, to be finalized by Architect)
-- `docs/api-reference.md` (If needed for Algolia/Ollama details)
-- `docs/testing-strategy.md` (Optional - low priority for MVP, Jest setup provided)
-
-## Post-MVP / Future Enhancements
-
-- Advanced scraping techniques (handling JavaScript, anti-bot measures).
-- Processing all comments (potentially using MapReduce summarization).
-- Automated scheduling (e.g., using cron).
-- Database integration for storing results or tracking.
-- Cloud deployment and web frontend.
-- User management (sign-ups, preferences).
-- Production-grade error handling, monitoring, and email deliverability.
-- Fine-tuning LLM prompts or models.
-- Sophisticated retry logic for API calls or scraping.
-- Cloud LLM integration.
-
-## Change Log
-
-| Change                  | Date       | Version | Description                             | Author |
-| ----------------------- | ---------- | ------- | --------------------------------------- | ------ |
-| Refined Epics & Testing | 2025-05-04 | 0.3     | Removed Epic 6, added stage testing req | 2-pm   |
-| Boilerplate Added       | 2025-05-04 | 0.2     | Updated to reflect use of boilerplate   | 2-pm   |
-| Initial Draft           | 2025-05-04 | 0.1     | First draft based on brief              | 2-pm   |
-
-## Initial Architect Prompt
-
-### Technical Infrastructure
-
-- **Starter Project/Template:** **Mandatory: Use the provided "bmad-boilerplate".** This includes TypeScript setup, Node.js v22 compatibility, Jest, ESLint, Prettier, `ts-node`, `.env` handling via `.env.example`, and standard scripts (`dev`, `build`, `test`, `lint`, `format`).
-- **Hosting/Cloud Provider:** Local machine execution only for MVP. No cloud deployment.
-- **Frontend Platform:** N/A (CLI tool).
-- **Backend Platform:** Node.js v22 with TypeScript (as provided by the boilerplate). No specific Node.js framework mandated, but structure should support modularity and align with boilerplate setup.
-- **Database Requirements:** None. Local file system for intermediate data storage and logging only. Structure TBD (e.g., `./output/YYYY-MM-DD/`). Ensure output directory is configurable via `.env` and gitignored.
-
-### Technical Constraints
-
-- Must adhere to the structure and tooling provided by "bmad-boilerplate".
-- Must use Node.js v22 native `Workspace` for HTTP requests.
-- Must use the Algolia HN Search API for fetching HN data.
-- Must integrate with a local Ollama instance via a configurable HTTP endpoint. Design should allow potential swapping to other LLM APIs later.
-- Must use Nodemailer for sending email.
-- Configuration (LLM endpoint, email credentials, recipients, `MAX_COMMENTS_PER_STORY`, output dir path) must be managed via a `.env` file based on `.env.example`.
-- Article scraping must be basic, best-effort, and handle failures gracefully without stopping the main process.
-- Intermediate data must be persisted locally incrementally.
-- Code must adhere to the ESLint and Prettier configurations within the boilerplate.
-
-### Deployment Considerations
-
-- Execution is manual via CLI trigger only, using `npm run dev` or `npm start`.
-- No CI/CD required for MVP.
-- Single environment: local development machine.
-
-### Local Development & Testing Requirements
-
-- The entire application runs locally.
-- The main CLI command (`npm run dev`/`start`) should execute the _full implemented pipeline_.
-- **Separate utility scripts/commands MUST be provided** for testing individual pipeline stages (fetch, scrape, summarize, email) potentially using local file I/O. Architecture should facilitate creating these stage runners. (e.g., `npm run stage:fetch`, `npm run stage:scrape -- --inputFile <path>`, `npm run stage:summarize -- --inputFile <path>`, `npm run stage:email -- --inputFile <path> [--dry-run]`).
-- The boilerplate provides `npm run test` using Jest for running automated unit/integration tests.
-- The boilerplate provides `npm run lint` and `npm run format` for code quality checks.
-- Basic console logging is required. File logging can be considered by the architect.
-- Testability of individual modules (API clients, scraper, summarizer, emailer) is crucial and should leverage the Jest setup and stage testing utilities.
-
-### Other Technical Considerations
-
-- **Modularity:** Design components (HN client, scraper, LLM client, emailer) with clear interfaces to facilitate potential future modifications (e.g., changing LLM provider) and independent stage testing.
-- **Error Handling:** Focus on robust handling of scraping failures and basic handling of API/network errors. Implement within the boilerplate structure. Logging should clearly indicate errors.
-- **Resource Management:** Be mindful of local resources when interacting with the LLM, although optimization is not a primary MVP goal.
-- **Dependency Management:** Add necessary production dependencies (e.g., `nodemailer`, potentially `article-extractor`, libraries for date handling or file system operations if needed) to the boilerplate's `package.json`. Keep dependencies minimal.
-- **Configuration Loading:** Implement a robust way to load and validate settings from the `.env` file early in the application startup.

V2-FULL-DEMO-WALKTHROUGH/prd.txt

@@ -1,189 +0,0 @@
-# BMad Hacker Daily Digest Product Requirements Document (PRD)
-
-## Intro
-
-The BMad Hacker Daily Digest is a command-line tool designed to address the time-consuming nature of reading extensive Hacker News (HN) comment threads. It aims to provide users with a time-efficient way to grasp the collective intelligence and key insights from discussions on top HN stories. The service will fetch the top 10 HN stories daily, retrieve a configurable number of comments for each, attempt to scrape the linked article, generate separate summaries for the article (if scraped) and the comment discussion using a local LLM, and deliver these summaries in a single daily email briefing triggered manually. This project also serves as a practical learning exercise in agent-driven development, TypeScript, Node.js, API integration, and local LLM usage, starting from the provided "bmad-boilerplate" template.
-
-## Goals and Context
-
-- **Project Objectives:**
-  - Provide a quick, reliable, automated way to stay informed about key HN discussions without reading full threads.
-  - Successfully fetch top 10 HN story metadata via Algolia HN API.
-  - Retrieve a _configurable_ number of comments per story (default 50) via Algolia HN API.
-  - Attempt basic scraping of linked article content, handling failures gracefully.
-  - Generate distinct Article Summaries (if scraped) and Discussion Summaries using a local LLM (Ollama).
-  - Assemble summaries for 10 stories into an HTML email and send via Nodemailer upon manual CLI trigger.
-  - Serve as a learning platform for agent-driven development, TypeScript, Node.js v22, API integration, local LLMs, and configuration management, leveraging the "bmad-boilerplate" structure and tooling.
-- **Measurable Outcomes:**
-  - The tool completes its full process (fetch, scrape attempt, summarize, email) without crashing on manual CLI trigger across multiple test runs.
-  - The generated email digest consistently contains results for 10 stories, including correct links, discussion summaries, and article summaries where scraping was successful.
-  - Errors during article scraping are logged, and the process continues for affected stories using only comment summaries, without halting the script.
-- **Success Criteria:**
-  - Successful execution of the end-to-end process via CLI trigger for 3 consecutive test runs.
-  - Generated email is successfully sent and received, containing summaries for all 10 fetched stories (article summary optional based on scraping success).
-  - Scraping failures are logged appropriately without stopping the overall process.
-- **Key Performance Indicators (KPIs):**
-  - Successful Runs / Total Runs (Target: 100% for MVP tests)
-  - Stories with Article Summaries / Total Stories (Measures scraping effectiveness)
-  - Stories with Discussion Summaries / Total Stories (Target: 100%)
-  * Manual Qualitative Check: Relevance and coherence of summaries in the digest.
-
-## Scope and Requirements (MVP / Current Version)
-
-### Functional Requirements (High-Level)
-
-- **HN Story Fetching:** Retrieve IDs and metadata (title, URL, HN link) for the top 10 stories from Algolia HN Search API.
-- **HN Comment Fetching:** For each story, retrieve comments from Algolia HN Search API up to a maximum count defined in a `.env` configuration variable (`MAX_COMMENTS_PER_STORY`, default 50).
-- **Article Content Scraping:** Attempt to fetch HTML and extract main text content from the story's external URL using basic methods (e.g., Node.js native fetch, optionally `article-extractor` or similar basic library).
-- **Scraping Failure Handling:** If scraping fails, log the error and proceed with generating only the Discussion Summary for that story.
-- **LLM Summarization:**
-  - Generate an "Article Summary" from scraped text (if successful) using a configured local LLM (Ollama endpoint).
-  - Generate a "Discussion Summary" from the fetched comments using the same LLM.
-  - Initial Prompts (Placeholders - refine in Epics):
-    - _Article Prompt:_ "Summarize the key points of the following article text: {Article Text}"
-    - _Discussion Prompt:_ "Summarize the main themes, viewpoints, and key insights from the following Hacker News comments: {Comment Texts}"
-- **Digest Formatting:** Combine results for the 10 stories into a single HTML email. Each story entry should include: Story Title, HN Link, Article Link, Article Summary (if available), Discussion Summary.
-- **Email Dispatch:** Send the formatted HTML email using Nodemailer to a recipient list defined in `.env`. Use credentials also stored in `.env`.
-- **Main Execution Trigger:** Initiate the _entire implemented pipeline_ via a manual command-line interface (CLI) trigger, using the standard scripts defined in the boilerplate (`npm run dev`, `npm start` after build). Each functional epic should add its capability to this main execution flow.
-- **Configuration:** Manage external parameters (Algolia API details (if needed), LLM endpoint URL, `MAX_COMMENTS_PER_STORY`, Nodemailer credentials, recipient email list, output directory path) via a `.env` file, based on the provided `.env.example`.
-- **Incremental Logging & Data Persistence:**
-  - Implement basic console logging for key steps and errors throughout the pipeline.
-  - Persist intermediate data artifacts (fetched stories/comments, scraped text, generated summaries) to local files within a configurable, date-stamped directory structure (e.g., `./output/YYYY-MM-DD/`).
-  - This persistence should be implemented incrementally within the relevant functional epics (Data Acquisition, Scraping, Summarization).
-- **Stage Testing Utilities:**
-  - Provide separate utility scripts or CLI commands to allow testing individual pipeline stages in isolation (e.g., fetching HN data, scraping URLs, summarizing text, sending email).
-  - These utilities should support using locally saved files as input (e.g., test scraping using a file containing story URLs, test summarization using a file containing text). This facilitates development and debugging.
-
-### Non-Functional Requirements (NFRs)
-
-- **Performance:** MVP focuses on functionality over speed. Should complete within a reasonable time (e.g., < 5 minutes) on a typical developer machine for local LLM use. No specific response time targets.
-- **Scalability:** Designed for single-user, local execution. No scaling requirements for MVP.
-- **Reliability/Availability:**
-  - The script must handle article scraping failures gracefully (log and continue).
-  - Basic error handling for API calls (e.g., log network errors).
-  - Local LLM interaction may fail; basic error logging is sufficient for MVP.
-  - No requirement for automated retries or production-grade error handling.
-- **Security:**
-  - Email credentials must be stored securely via `.env` file and not committed to version control (as per boilerplate `.gitignore`).
-  - No other specific security requirements for local MVP.
-- **Maintainability:**
-  - Code should be well-structured TypeScript.
-  - Adherence to the linting (ESLint) and formatting (Prettier) rules configured in the "bmad-boilerplate" is required. Use `npm run lint` and `npm run format`.
-  - Modularity is desired to potentially swap LLM providers later and facilitate stage testing.
-- **Usability/Accessibility:** N/A (CLI tool for developer).
-- **Other Constraints:**
-  - Must use TypeScript and Node.js v22.
-  - Must run locally on the developer's machine.
-  - Must use Node.js v22 native `Workspace` API for HTTP requests.
-  - Must use Algolia HN Search API for HN data.
-  - Must use a local Ollama instance via a configurable HTTP endpoint.
-  - Must use Nodemailer for email dispatch.
-  - Must use `.env` for configuration based on `.env.example`.
-  - Must use local file system for logging and intermediate data storage. Ensure output/log directories are gitignored.
-  - Focus on a functional pipeline for learning/demonstration.
-
-### User Experience (UX) Requirements (High-Level)
-
-- The primary UX goal is to deliver a time-saving digest.
-- For the developer user, the main CLI interaction should be simple: using standard boilerplate scripts like `npm run dev` or `npm start` to trigger the full process.
-- Feedback during CLI execution (e.g., "Fetching stories...", "Summarizing story X/10...", "Sending email...") is desirable via console logging.
-- Separate CLI commands/scripts for testing individual stages should provide clear input/output mechanisms.
-
-### Integration Requirements (High-Level)
-
-- **Algolia HN Search API:** Fetching top stories and comments. Requires understanding API structure and query parameters.
-- **Ollama Service:** Sending text (article content, comments) and receiving summaries via its API endpoint. Endpoint URL must be configurable.
-- **SMTP Service (via Nodemailer):** Sending the final digest email. Requires valid SMTP credentials and recipient list configured in `.env`.
-
-### Testing Requirements (High-Level)
-
-- MVP success relies on manual end-to-end test runs confirming successful execution and valid email output.
-- Unit/integration tests are encouraged using the **Jest framework configured in the boilerplate**. Focus testing effort on the core pipeline components. Use `npm run test`.
-- **Stage-specific testing utilities (as defined in Functional Requirements) are required** to support development and verification of individual pipeline components.
-
-## Epic Overview (MVP / Current Version)
-
-_(Revised proposal)_
-
-- **Epic 1: Project Initialization & Core Setup** - Goal: Initialize the project using "bmad-boilerplate", manage dependencies, setup `.env` and config loading, establish basic CLI entry point, setup basic logging and output directory structure.
-- **Epic 2: HN Data Acquisition & Persistence** - Goal: Implement fetching top 10 stories and their comments (respecting limits) from Algolia HN API, and persist this raw data locally. Implement stage testing utility for fetching.
-- **Epic 3: Article Scraping & Persistence** - Goal: Implement best-effort article scraping/extraction, handle failures gracefully, and persist scraped text locally. Implement stage testing utility for scraping.
-- **Epic 4: LLM Summarization & Persistence** - Goal: Integrate with Ollama to generate article/discussion summaries from persisted data and persist summaries locally. Implement stage testing utility for summarization.
-- **Epic 5: Digest Assembly & Email Dispatch** - Goal: Format collected summaries into an HTML email using persisted data and send it using Nodemailer. Implement stage testing utility for emailing (with dry-run option).
-
-## Key Reference Documents
-
-- `docs/project-brief.md`
-- `docs/prd.md` (This document)
-- `docs/architecture.md` (To be created by Architect)
-- `docs/epic1.md`, `docs/epic2.md`, ... (To be created)
-- `docs/tech-stack.md` (Partially defined by boilerplate, to be finalized by Architect)
-- `docs/api-reference.md` (If needed for Algolia/Ollama details)
-- `docs/testing-strategy.md` (Optional - low priority for MVP, Jest setup provided)
-
-## Post-MVP / Future Enhancements
-
-- Advanced scraping techniques (handling JavaScript, anti-bot measures).
-- Processing all comments (potentially using MapReduce summarization).
-- Automated scheduling (e.g., using cron).
-- Database integration for storing results or tracking.
-- Cloud deployment and web frontend.
-- User management (sign-ups, preferences).
-- Production-grade error handling, monitoring, and email deliverability.
-- Fine-tuning LLM prompts or models.
-- Sophisticated retry logic for API calls or scraping.
-- Cloud LLM integration.
-
-## Change Log
-
-| Change                  | Date       | Version | Description                             | Author |
-| ----------------------- | ---------- | ------- | --------------------------------------- | ------ |
-| Refined Epics & Testing | 2025-05-04 | 0.3     | Removed Epic 6, added stage testing req | 2-pm   |
-| Boilerplate Added       | 2025-05-04 | 0.2     | Updated to reflect use of boilerplate   | 2-pm   |
-| Initial Draft           | 2025-05-04 | 0.1     | First draft based on brief              | 2-pm   |
-
-## Initial Architect Prompt
-
-### Technical Infrastructure
-
-- **Starter Project/Template:** **Mandatory: Use the provided "bmad-boilerplate".** This includes TypeScript setup, Node.js v22 compatibility, Jest, ESLint, Prettier, `ts-node`, `.env` handling via `.env.example`, and standard scripts (`dev`, `build`, `test`, `lint`, `format`).
-- **Hosting/Cloud Provider:** Local machine execution only for MVP. No cloud deployment.
-- **Frontend Platform:** N/A (CLI tool).
-- **Backend Platform:** Node.js v22 with TypeScript (as provided by the boilerplate). No specific Node.js framework mandated, but structure should support modularity and align with boilerplate setup.
-- **Database Requirements:** None. Local file system for intermediate data storage and logging only. Structure TBD (e.g., `./output/YYYY-MM-DD/`). Ensure output directory is configurable via `.env` and gitignored.
-
-### Technical Constraints
-
-- Must adhere to the structure and tooling provided by "bmad-boilerplate".
-- Must use Node.js v22 native `Workspace` for HTTP requests.
-- Must use the Algolia HN Search API for fetching HN data.
-- Must integrate with a local Ollama instance via a configurable HTTP endpoint. Design should allow potential swapping to other LLM APIs later.
-- Must use Nodemailer for sending email.
-- Configuration (LLM endpoint, email credentials, recipients, `MAX_COMMENTS_PER_STORY`, output dir path) must be managed via a `.env` file based on `.env.example`.
-- Article scraping must be basic, best-effort, and handle failures gracefully without stopping the main process.
-- Intermediate data must be persisted locally incrementally.
-- Code must adhere to the ESLint and Prettier configurations within the boilerplate.
-
-### Deployment Considerations
-
-- Execution is manual via CLI trigger only, using `npm run dev` or `npm start`.
-- No CI/CD required for MVP.
-- Single environment: local development machine.
-
-### Local Development & Testing Requirements
-
-- The entire application runs locally.
-- The main CLI command (`npm run dev`/`start`) should execute the _full implemented pipeline_.
-- **Separate utility scripts/commands MUST be provided** for testing individual pipeline stages (fetch, scrape, summarize, email) potentially using local file I/O. Architecture should facilitate creating these stage runners. (e.g., `npm run stage:fetch`, `npm run stage:scrape -- --inputFile <path>`, `npm run stage:summarize -- --inputFile <path>`, `npm run stage:email -- --inputFile <path> [--dry-run]`).
-- The boilerplate provides `npm run test` using Jest for running automated unit/integration tests.
-- The boilerplate provides `npm run lint` and `npm run format` for code quality checks.
-- Basic console logging is required. File logging can be considered by the architect.
-- Testability of individual modules (API clients, scraper, summarizer, emailer) is crucial and should leverage the Jest setup and stage testing utilities.
-
-### Other Technical Considerations
-
-- **Modularity:** Design components (HN client, scraper, LLM client, emailer) with clear interfaces to facilitate potential future modifications (e.g., changing LLM provider) and independent stage testing.
-- **Error Handling:** Focus on robust handling of scraping failures and basic handling of API/network errors. Implement within the boilerplate structure. Logging should clearly indicate errors.
-- **Resource Management:** Be mindful of local resources when interacting with the LLM, although optimization is not a primary MVP goal.
-- **Dependency Management:** Add necessary production dependencies (e.g., `nodemailer`, potentially `article-extractor`, libraries for date handling or file system operations if needed) to the boilerplate's `package.json`. Keep dependencies minimal.
-- **Configuration Loading:** Implement a robust way to load and validate settings from the `.env` file early in the application startup.

V2-FULL-DEMO-WALKTHROUGH/project-structure.md

@@ -1,91 +0,0 @@
-# BMad Hacker Daily Digest Project Structure
-
-This document outlines the standard directory and file structure for the project. Adhering to this structure ensures consistency and maintainability.
-
-```plaintext
-bmad-hacker-daily-digest/
-├── .github/                    # Optional: GitHub Actions workflows (if used)
-│   └── workflows/
-├── .vscode/                    # Optional: VSCode editor settings
-│   └── settings.json
-├── dist/                       # Compiled JavaScript output (from 'npm run build', git-ignored)
-├── docs/                       # Project documentation (PRD, Architecture, Epics, etc.)
-│   ├── architecture.md
-│   ├── tech-stack.md
-│   ├── project-structure.md    # This file
-│   ├── data-models.md
-│   ├── api-reference.md
-│   ├── environment-vars.md
-│   ├── coding-standards.md
-│   ├── testing-strategy.md
-│   ├── prd.md                  # Product Requirements Document
-│   ├── epic1.md .. epic5.md    # Epic details
-│   └── ...
-├── node_modules/               # Project dependencies (managed by npm, git-ignored)
-├── output/                     # Default directory for data artifacts (git-ignored)
-│   └── YYYY-MM-DD/             # Date-stamped subdirectories for runs
-│       ├── {storyId}_data.json
-│       ├── {storyId}_article.txt
-│       └── {storyId}_summary.json
-├── src/                        # Application source code
-│   ├── clients/                # Clients for interacting with external services
-│   │   ├── algoliaHNClient.ts  # Algolia HN Search API interaction logic [Epic 2]
-│   │   └── ollamaClient.ts     # Ollama API interaction logic [Epic 4]
-│   ├── core/                   # Core application logic & orchestration
-│   │   └── pipeline.ts         # Main pipeline execution flow (fetch->scrape->summarize->email)
-│   ├── email/                  # Email assembly, templating, and sending logic [Epic 5]
-│   │   ├── contentAssembler.ts # Reads local files, prepares digest data
-│   │   ├── emailSender.ts      # Sends email via Nodemailer
-│   │   └── templates.ts        # HTML email template rendering function(s)
-│   ├── scraper/                # Article scraping logic [Epic 3]
-│   │   └── articleScraper.ts   # Implements scraping using article-extractor
-│   ├── stages/                 # Standalone stage testing utility scripts [PRD Req]
-│   │   ├── fetch_hn_data.ts    # Stage runner for Epic 2
-│   │   ├── scrape_articles.ts  # Stage runner for Epic 3
-│   │   ├── summarize_content.ts# Stage runner for Epic 4
-│   │   └── send_digest.ts      # Stage runner for Epic 5 (with --dry-run)
-│   ├── types/                  # Shared TypeScript interfaces and types
-│   │   ├── hn.ts               # Types: Story, Comment
-│   │   ├── ollama.ts           # Types: OllamaRequest, OllamaResponse
-│   │   ├── email.ts            # Types: DigestData
-│   │   └── index.ts            # Barrel file for exporting types from this dir
-│   ├── utils/                  # Shared, low-level utility functions
-│   │   ├── config.ts           # Loads and validates .env configuration [Epic 1]
-│   │   ├── logger.ts           # Simple console logger wrapper [Epic 1]
-│   │   └── dateUtils.ts        # Date formatting helpers (using date-fns)
-│   └── index.ts                # Main application entry point (invoked by npm run dev/start) [Epic 1]
-├── test/                       # Automated tests (using Jest)
-│   ├── unit/                   # Unit tests (mirroring src structure)
-│   │   ├── clients/
-│   │   ├── core/
-│   │   ├── email/
-│   │   ├── scraper/
-│   │   └── utils/
-│   └── integration/            # Integration tests (e.g., testing pipeline stage interactions)
-├── .env.example                # Example environment variables file [Epic 1]
-├── .gitignore                  # Git ignore rules (ensure node_modules, dist, .env, output/ are included)
-├── package.json                # Project manifest, dependencies, scripts (from boilerplate)
-├── package-lock.json           # Lockfile for deterministic installs
-└── tsconfig.json               # TypeScript compiler configuration (from boilerplate)
-```
-
-## Key Directory Descriptions
-
-- `docs/`: Contains all project planning, architecture, and reference documentation.
-- `output/`: Default location for persisted data artifacts generated during runs (stories, comments, summaries). Should be in `.gitignore`. Path configurable via `.env`.
-- `src/`: Main application source code.
-  - `clients/`: Modules dedicated to interacting with specific external APIs (Algolia, Ollama).
-  - `core/`: Orchestrates the main application pipeline steps.
-  - `email/`: Handles all aspects of creating and sending the final email digest.
-  - `scraper/`: Contains the logic for fetching and extracting article content.
-  - `stages/`: Holds the independent, runnable scripts for testing each major pipeline stage.
-  - `types/`: Central location for shared TypeScript interfaces and type definitions.
-  - `utils/`: Reusable utility functions (config loading, logging, date formatting) that don't belong to a specific feature domain.
-  - `index.ts`: The main entry point triggered by `npm run dev/start`, responsible for initializing and starting the core pipeline.
-- `test/`: Contains automated tests written using Jest. Structure mirrors `src/` for unit tests.
-
-## Notes
-
-- This structure promotes modularity by separating concerns (clients, scraping, email, core logic, stages, utils).
-- Clear separation into directories like `clients`, `scraper`, `email`, and `stages` aids independent development, testing, and potential AI agent implementation tasks targeting specific functionalities.
-- Stage runner scripts in `src/stages/` directly address the PRD requirement for testing pipeline phases independently .

V2-FULL-DEMO-WALKTHROUGH/project-structure.txt

@@ -1,91 +0,0 @@
-# BMad Hacker Daily Digest Project Structure
-
-This document outlines the standard directory and file structure for the project. Adhering to this structure ensures consistency and maintainability.
-
-```plaintext
-bmad-hacker-daily-digest/
-├── .github/                    # Optional: GitHub Actions workflows (if used)
-│   └── workflows/
-├── .vscode/                    # Optional: VSCode editor settings
-│   └── settings.json
-├── dist/                       # Compiled JavaScript output (from 'npm run build', git-ignored)
-├── docs/                       # Project documentation (PRD, Architecture, Epics, etc.)
-│   ├── architecture.md
-│   ├── tech-stack.md
-│   ├── project-structure.md    # This file
-│   ├── data-models.md
-│   ├── api-reference.md
-│   ├── environment-vars.md
-│   ├── coding-standards.md
-│   ├── testing-strategy.md
-│   ├── prd.md                  # Product Requirements Document
-│   ├── epic1.md .. epic5.md    # Epic details
-│   └── ...
-├── node_modules/               # Project dependencies (managed by npm, git-ignored)
-├── output/                     # Default directory for data artifacts (git-ignored)
-│   └── YYYY-MM-DD/             # Date-stamped subdirectories for runs
-│       ├── {storyId}_data.json
-│       ├── {storyId}_article.txt
-│       └── {storyId}_summary.json
-├── src/                        # Application source code
-│   ├── clients/                # Clients for interacting with external services
-│   │   ├── algoliaHNClient.ts  # Algolia HN Search API interaction logic [Epic 2]
-│   │   └── ollamaClient.ts     # Ollama API interaction logic [Epic 4]
-│   ├── core/                   # Core application logic & orchestration
-│   │   └── pipeline.ts         # Main pipeline execution flow (fetch->scrape->summarize->email)
-│   ├── email/                  # Email assembly, templating, and sending logic [Epic 5]
-│   │   ├── contentAssembler.ts # Reads local files, prepares digest data
-│   │   ├── emailSender.ts      # Sends email via Nodemailer
-│   │   └── templates.ts        # HTML email template rendering function(s)
-│   ├── scraper/                # Article scraping logic [Epic 3]
-│   │   └── articleScraper.ts   # Implements scraping using article-extractor
-│   ├── stages/                 # Standalone stage testing utility scripts [PRD Req]
-│   │   ├── fetch_hn_data.ts    # Stage runner for Epic 2
-│   │   ├── scrape_articles.ts  # Stage runner for Epic 3
-│   │   ├── summarize_content.ts# Stage runner for Epic 4
-│   │   └── send_digest.ts      # Stage runner for Epic 5 (with --dry-run)
-│   ├── types/                  # Shared TypeScript interfaces and types
-│   │   ├── hn.ts               # Types: Story, Comment
-│   │   ├── ollama.ts           # Types: OllamaRequest, OllamaResponse
-│   │   ├── email.ts            # Types: DigestData
-│   │   └── index.ts            # Barrel file for exporting types from this dir
-│   ├── utils/                  # Shared, low-level utility functions
-│   │   ├── config.ts           # Loads and validates .env configuration [Epic 1]
-│   │   ├── logger.ts           # Simple console logger wrapper [Epic 1]
-│   │   └── dateUtils.ts        # Date formatting helpers (using date-fns)
-│   └── index.ts                # Main application entry point (invoked by npm run dev/start) [Epic 1]
-├── test/                       # Automated tests (using Jest)
-│   ├── unit/                   # Unit tests (mirroring src structure)
-│   │   ├── clients/
-│   │   ├── core/
-│   │   ├── email/
-│   │   ├── scraper/
-│   │   └── utils/
-│   └── integration/            # Integration tests (e.g., testing pipeline stage interactions)
-├── .env.example                # Example environment variables file [Epic 1]
-├── .gitignore                  # Git ignore rules (ensure node_modules, dist, .env, output/ are included)
-├── package.json                # Project manifest, dependencies, scripts (from boilerplate)
-├── package-lock.json           # Lockfile for deterministic installs
-└── tsconfig.json               # TypeScript compiler configuration (from boilerplate)
-```
-
-## Key Directory Descriptions
-
-- `docs/`: Contains all project planning, architecture, and reference documentation.
-- `output/`: Default location for persisted data artifacts generated during runs (stories, comments, summaries). Should be in `.gitignore`. Path configurable via `.env`.
-- `src/`: Main application source code.
-  - `clients/`: Modules dedicated to interacting with specific external APIs (Algolia, Ollama).
-  - `core/`: Orchestrates the main application pipeline steps.
-  - `email/`: Handles all aspects of creating and sending the final email digest.
-  - `scraper/`: Contains the logic for fetching and extracting article content.
-  - `stages/`: Holds the independent, runnable scripts for testing each major pipeline stage.
-  - `types/`: Central location for shared TypeScript interfaces and type definitions.
-  - `utils/`: Reusable utility functions (config loading, logging, date formatting) that don't belong to a specific feature domain.
-  - `index.ts`: The main entry point triggered by `npm run dev/start`, responsible for initializing and starting the core pipeline.
-- `test/`: Contains automated tests written using Jest. Structure mirrors `src/` for unit tests.
-
-## Notes
-
-- This structure promotes modularity by separating concerns (clients, scraping, email, core logic, stages, utils).
-- Clear separation into directories like `clients`, `scraper`, `email`, and `stages` aids independent development, testing, and potential AI agent implementation tasks targeting specific functionalities.
-- Stage runner scripts in `src/stages/` directly address the PRD requirement for testing pipeline phases independently .

V2-FULL-DEMO-WALKTHROUGH/prompts.md

@@ -1,56 +0,0 @@
-````Markdown
-# BMad Hacker Daily Digest LLM Prompts
-
-This document defines the standard prompts used when interacting with the configured Ollama LLM for generating summaries. Centralizing these prompts ensures consistency and aids experimentation.
-
-## Prompt Design Philosophy
-
-The goal of these prompts is to guide the LLM (e.g., Llama 3 or similar) to produce concise, informative summaries focusing on the key information relevant to the BMad Hacker Daily Digest's objective: quickly understanding the essence of an article or HN discussion.
-
-## Core Prompts
-
-### 1. Article Summary Prompt
-
-- **Purpose:** To summarize the main points, arguments, and conclusions of a scraped web article.
-- **Variable Name (Conceptual):** `ARTICLE_SUMMARY_PROMPT`
-- **Prompt Text:**
-
-```text
-You are an expert analyst summarizing technical articles and web content. Please provide a concise summary of the following article text, focusing on the key points, core arguments, findings, and main conclusions. The summary should be objective and easy to understand.
-
-Article Text:
----
-{Article Text}
----
-
-Concise Summary:
-````
-
-### 2. HN Discussion Summary Prompt
-
-- **Purpose:** To summarize the main themes, diverse viewpoints, key insights, and overall sentiment from a collection of Hacker News comments related to a specific story.
-- **Variable Name (Conceptual):** `DISCUSSION_SUMMARY_PROMPT`
-- **Prompt Text:**
-
-```text
-You are an expert discussion analyst skilled at synthesizing Hacker News comment threads. Please provide a concise summary of the main themes, diverse viewpoints (including agreements and disagreements), key insights, and overall sentiment expressed in the following Hacker News comments. Focus on the collective intelligence and most salient points from the discussion.
-
-Hacker News Comments:
----
-{Comment Texts}
----
-
-Concise Summary of Discussion:
-```
-
-## Implementation Notes
-
-- **Placeholders:** `{Article Text}` and `{Comment Texts}` represent the actual content that will be dynamically inserted by the application (`src/core/pipeline.ts` or `src/clients/ollamaClient.ts`) when making the API call.
-- **Loading:** For the MVP, these prompts can be defined as constants within the application code (e.g., in `src/utils/prompts.ts` or directly where the `ollamaClient` is called), referencing this document as the source of truth. Future enhancements could involve loading these prompts from this file directly at runtime.
-- **Refinement:** These prompts serve as a starting point. Further refinement based on the quality of summaries produced by the specific `OLLAMA_MODEL` is expected (Post-MVP).
-
-## Change Log
-
-| Change        | Date       | Version | Description                | Author      |
-| ------------- | ---------- | ------- | -------------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Initial prompts definition | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/tech-stack.md

@@ -1,26 +0,0 @@
-# BMad Hacker Daily Digest Technology Stack
-
-## Technology Choices
-
-| Category              | Technology                     | Version / Details        | Description / Purpose                                                                                      | Justification (Optional)                           |
-| :-------------------- | :----------------------------- | :----------------------- | :--------------------------------------------------------------------------------------------------------- | :------------------------------------------------- |
-| **Languages**         | TypeScript                     | 5.x (from boilerplate)   | Primary language for application logic                                                                     | Required by boilerplate , strong typing            |
-| **Runtime**           | Node.js                        | 22.x                     | Server-side execution environment                                                                          | Required by PRD                                    |
-| **Frameworks**        | N/A                            | N/A                      | Using plain Node.js structure                                                                              | Boilerplate provides structure; framework overkill |
-| **Databases**         | Local Filesystem               | N/A                      | Storing intermediate data artifacts                                                                        | Required by PRD ; No database needed for MVP       |
-| **HTTP Client**       | Node.js `Workspace` API        | Native (Node.js >=21)    | **Mandatory:** Fetching external resources (Algolia, URLs, Ollama). **Do NOT use libraries like `axios`.** | Required by PRD                                    |
-| **Configuration**     | `.env` Files                   | Native (Node.js >=20.6)  | Managing environment variables. **`dotenv` package is NOT needed.**                                        | Standard practice; Native support                  |
-| **Logging**           | Simple Console Wrapper         | Custom (`src/logger.ts`) | Basic console logging for MVP (stdout/stderr)                                                              | Meets PRD "basic logging" req ; Minimal dependency |
-| **Key Libraries**     | `@extractus/article-extractor` | ~8.x                     | Basic article text scraping                                                                                | Simple, focused library for MVP scraping           |
-|                       | `date-fns`                     | ~3.x                     | Date formatting and manipulation                                                                           | Clean API for date-stamped dirs/timestamps         |
-|                       | `nodemailer`                   | ~6.x                     | Sending email digests                                                                                      | Required by PRD                                    |
-|                       | `yargs`                        | ~17.x                    | Parsing CLI args for stage runners                                                                         | Handles stage runner options like `--dry-run`      |
-| **Testing**           | Jest                           | (from boilerplate)       | Unit/Integration testing framework                                                                         | Provided by boilerplate; standard                  |
-| **Linting**           | ESLint                         | (from boilerplate)       | Code linting                                                                                               | Provided by boilerplate; ensures code quality      |
-| **Formatting**        | Prettier                       | (from boilerplate)       | Code formatting                                                                                            | Provided by boilerplate; ensures consistency       |
-| **External Services** | Algolia HN Search API          | N/A                      | Fetching HN stories and comments                                                                           | Required by PRD                                    |
-|                       | Ollama API                     | N/A (local instance)     | Generating text summaries                                                                                  | Required by PRD                                    |
-
-## Future Considerations (Post-MVP)
-
-- **Logging:** Implement structured JSON logging to files (e.g., using Winston or Pino) for better analysis and persistence.

V2-FULL-DEMO-WALKTHROUGH/tech-stack.txt

@@ -1,26 +0,0 @@
-# BMad Hacker Daily Digest Technology Stack
-
-## Technology Choices
-
-| Category              | Technology                     | Version / Details        | Description / Purpose                                                                                      | Justification (Optional)                           |
-| :-------------------- | :----------------------------- | :----------------------- | :--------------------------------------------------------------------------------------------------------- | :------------------------------------------------- |
-| **Languages**         | TypeScript                     | 5.x (from boilerplate)   | Primary language for application logic                                                                     | Required by boilerplate , strong typing            |
-| **Runtime**           | Node.js                        | 22.x                     | Server-side execution environment                                                                          | Required by PRD                                    |
-| **Frameworks**        | N/A                            | N/A                      | Using plain Node.js structure                                                                              | Boilerplate provides structure; framework overkill |
-| **Databases**         | Local Filesystem               | N/A                      | Storing intermediate data artifacts                                                                        | Required by PRD ; No database needed for MVP       |
-| **HTTP Client**       | Node.js `Workspace` API        | Native (Node.js >=21)    | **Mandatory:** Fetching external resources (Algolia, URLs, Ollama). **Do NOT use libraries like `axios`.** | Required by PRD                                    |
-| **Configuration**     | `.env` Files                   | Native (Node.js >=20.6)  | Managing environment variables. **`dotenv` package is NOT needed.**                                        | Standard practice; Native support                  |
-| **Logging**           | Simple Console Wrapper         | Custom (`src/logger.ts`) | Basic console logging for MVP (stdout/stderr)                                                              | Meets PRD "basic logging" req ; Minimal dependency |
-| **Key Libraries**     | `@extractus/article-extractor` | ~8.x                     | Basic article text scraping                                                                                | Simple, focused library for MVP scraping           |
-|                       | `date-fns`                     | ~3.x                     | Date formatting and manipulation                                                                           | Clean API for date-stamped dirs/timestamps         |
-|                       | `nodemailer`                   | ~6.x                     | Sending email digests                                                                                      | Required by PRD                                    |
-|                       | `yargs`                        | ~17.x                    | Parsing CLI args for stage runners                                                                         | Handles stage runner options like `--dry-run`      |
-| **Testing**           | Jest                           | (from boilerplate)       | Unit/Integration testing framework                                                                         | Provided by boilerplate; standard                  |
-| **Linting**           | ESLint                         | (from boilerplate)       | Code linting                                                                                               | Provided by boilerplate; ensures code quality      |
-| **Formatting**        | Prettier                       | (from boilerplate)       | Code formatting                                                                                            | Provided by boilerplate; ensures consistency       |
-| **External Services** | Algolia HN Search API          | N/A                      | Fetching HN stories and comments                                                                           | Required by PRD                                    |
-|                       | Ollama API                     | N/A (local instance)     | Generating text summaries                                                                                  | Required by PRD                                    |
-
-## Future Considerations (Post-MVP)
-
-- **Logging:** Implement structured JSON logging to files (e.g., using Winston or Pino) for better analysis and persistence.

V2-FULL-DEMO-WALKTHROUGH/testing-strategy.md

@@ -1,73 +0,0 @@
-# BMad Hacker Daily Digest Testing Strategy
-
-## Overall Philosophy & Goals
-
-The testing strategy for the BMad Hacker Daily Digest MVP focuses on pragmatic validation of the core pipeline functionality and individual component logic. Given it's a local CLI tool with a sequential process, the emphasis is on:
-
-1.  **Functional Correctness:** Ensuring each stage of the pipeline (fetch, scrape, summarize, email) performs its task correctly according to the requirements.
-2.  **Integration Verification:** Confirming that data flows correctly between pipeline stages via the local filesystem.
-3.  **Robustness (Key Areas):** Specifically testing graceful handling of expected failures, particularly in article scraping .
-4.  **Leveraging Boilerplate:** Utilizing the Jest testing framework provided by `bmad-boilerplate` for automated unit and integration tests .
-5.  **Stage-Based Acceptance:** Using the mandatory **Stage Testing Utilities** as the primary mechanism for end-to-end validation of each phase against real external interactions (where applicable) .
-
-The primary goal is confidence in the MVP's end-to-end execution and the correctness of the generated email digest. High code coverage is secondary to testing critical paths and integration points.
-
-## Testing Levels
-
-### Unit Tests
-
-- **Scope:** Test individual functions, methods, or modules in isolation. Focus on business logic within utilities (`src/utils/`), clients (`src/clients/` - mocking HTTP calls), scraping logic (`src/scraper/` - mocking HTTP calls), email templating (`src/email/templates.ts`), and potentially core pipeline orchestration logic (`src/core/pipeline.ts` - mocking stage implementations).
-- **Tools:** Jest (provided by `bmad-boilerplate`). Use `npm run test`.
-- **Mocking/Stubbing:** Utilize Jest's built-in mocking capabilities (`jest.fn()`, `jest.spyOn()`, manual mocks in `__mocks__`) to isolate units under test from external dependencies (native `Workspace` API, `fs`, other modules, external libraries like `nodemailer`, `ollamaClient`).
-- **Location:** `test/unit/`, mirroring the `src/` directory structure.
-- **Expectations:** Cover critical logic branches, calculations, and helper functions. Ensure tests are fast and run reliably. Aim for good coverage of utility functions and complex logic within modules.
-
-### Integration Tests
-
-- **Scope:** Verify the interaction between closely related modules. Examples:
-  - Testing the `core/pipeline.ts` orchestrator with mocked implementations of each stage (fetch, scrape, summarize, email) to ensure the sequence and basic data flow are correct.
-  - Testing a client module (e.g., `algoliaHNClient`) against mocked HTTP responses to ensure correct parsing and data transformation.
-  - Testing the `email/contentAssembler.ts` by providing mock data files in a temporary directory (potentially using `mock-fs` or setup/teardown logic) and verifying the assembled `DigestData`.
-- **Tools:** Jest. May involve limited use of test setup/teardown for creating mock file structures if needed.
-- **Location:** `test/integration/`.
-- **Expectations:** Verify the contracts and collaborations between key internal components. Slower than unit tests. Focus on module boundaries.
-
-### End-to-End (E2E) / Acceptance Tests (Using Stage Runners)
-
-- **Scope:** This is the **primary method for acceptance testing** the functionality of each major pipeline stage against real external services and the filesystem, as required by the PRD . This also includes manually running the full pipeline.
-- **Process:**
-  1.  **Stage Testing Utilities:** Execute the standalone scripts in `src/stages/` via `npm run stage:<stage_name> [--args]`.
-      - `npm run stage:fetch`: Verifies fetching from Algolia HN API and persisting `_data.json` files locally.
-      - `npm run stage:scrape`: Verifies reading `_data.json`, scraping article URLs (hitting real websites), and persisting `_article.txt` files locally.
-      - `npm run stage:summarize`: Verifies reading local `_data.json` / `_article.txt`, calling the local Ollama API, and persisting `_summary.json` files. Requires a running local Ollama instance.
-      - `npm run stage:email [--dry-run]`: Verifies reading local persisted files, assembling the digest, rendering HTML, and either sending a real email (live run) or saving an HTML preview (`--dry-run`). Requires valid SMTP credentials in `.env` for live runs.
-  2.  **Full Pipeline Run:** Execute the main application via `npm run dev` or `npm start`.
-  3.  **Manual Verification:** Check console logs for errors during execution. Inspect the contents of the `output/YYYY-MM-DD/` directory (existence and format of `_data.json`, `_article.txt`, `_summary.json`, `_digest_preview.html` if dry-run). For live email tests, verify the received email's content, formatting, and summaries.
-- **Tools:** `npm` scripts, console inspection, file system inspection, email client.
-- **Environment:** Local development machine with internet access, configured `.env` file, and a running local Ollama instance .
-- **Location:** Scripts in `src/stages/`; verification steps are manual.
-- **Expectations:** These tests confirm the real-world functionality of each stage and the end-to-end process, fulfilling the core MVP success criteria .
-
-### Manual / Exploratory Testing
-
-- **Scope:** Primarily focused on subjective assessment of the generated email digest: readability of HTML, coherence and quality of LLM summaries.
-- **Process:** Review the output from E2E tests (`_digest_preview.html` or received email).
-
-## Specialized Testing Types
-
-- N/A for MVP. Performance, detailed security, accessibility, etc., are out of scope.
-
-## Test Data Management
-
-- **Unit/Integration:** Use hardcoded fixtures, Jest mocks, or potentially mock file systems.
-- **Stage/E2E:** Relies on live data fetched from Algolia/websites during the test run itself, or uses the output files generated by preceding stage runs. The `--dry-run` option for `stage:email` avoids external SMTP interaction during testing loops.
-
-## CI/CD Integration
-
-- N/A for MVP (local execution only). If CI were implemented later, it would execute `npm run lint` and `npm run test` (unit/integration tests). Running stage tests in CI would require careful consideration due to external dependencies (Algolia, Ollama, SMTP, potentially rate limits).
-
-## Change Log
-
-| Change        | Date       | Version | Description             | Author      |
-| ------------- | ---------- | ------- | ----------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Draft based on PRD/Arch | 3-Architect |

V2-FULL-DEMO-WALKTHROUGH/testing-strategy.txt

@@ -1,73 +0,0 @@
-# BMad Hacker Daily Digest Testing Strategy
-
-## Overall Philosophy & Goals
-
-The testing strategy for the BMad Hacker Daily Digest MVP focuses on pragmatic validation of the core pipeline functionality and individual component logic. Given it's a local CLI tool with a sequential process, the emphasis is on:
-
-1.  **Functional Correctness:** Ensuring each stage of the pipeline (fetch, scrape, summarize, email) performs its task correctly according to the requirements.
-2.  **Integration Verification:** Confirming that data flows correctly between pipeline stages via the local filesystem.
-3.  **Robustness (Key Areas):** Specifically testing graceful handling of expected failures, particularly in article scraping .
-4.  **Leveraging Boilerplate:** Utilizing the Jest testing framework provided by `bmad-boilerplate` for automated unit and integration tests .
-5.  **Stage-Based Acceptance:** Using the mandatory **Stage Testing Utilities** as the primary mechanism for end-to-end validation of each phase against real external interactions (where applicable) .
-
-The primary goal is confidence in the MVP's end-to-end execution and the correctness of the generated email digest. High code coverage is secondary to testing critical paths and integration points.
-
-## Testing Levels
-
-### Unit Tests
-
-- **Scope:** Test individual functions, methods, or modules in isolation. Focus on business logic within utilities (`src/utils/`), clients (`src/clients/` - mocking HTTP calls), scraping logic (`src/scraper/` - mocking HTTP calls), email templating (`src/email/templates.ts`), and potentially core pipeline orchestration logic (`src/core/pipeline.ts` - mocking stage implementations).
-- **Tools:** Jest (provided by `bmad-boilerplate`). Use `npm run test`.
-- **Mocking/Stubbing:** Utilize Jest's built-in mocking capabilities (`jest.fn()`, `jest.spyOn()`, manual mocks in `__mocks__`) to isolate units under test from external dependencies (native `Workspace` API, `fs`, other modules, external libraries like `nodemailer`, `ollamaClient`).
-- **Location:** `test/unit/`, mirroring the `src/` directory structure.
-- **Expectations:** Cover critical logic branches, calculations, and helper functions. Ensure tests are fast and run reliably. Aim for good coverage of utility functions and complex logic within modules.
-
-### Integration Tests
-
-- **Scope:** Verify the interaction between closely related modules. Examples:
-  - Testing the `core/pipeline.ts` orchestrator with mocked implementations of each stage (fetch, scrape, summarize, email) to ensure the sequence and basic data flow are correct.
-  - Testing a client module (e.g., `algoliaHNClient`) against mocked HTTP responses to ensure correct parsing and data transformation.
-  - Testing the `email/contentAssembler.ts` by providing mock data files in a temporary directory (potentially using `mock-fs` or setup/teardown logic) and verifying the assembled `DigestData`.
-- **Tools:** Jest. May involve limited use of test setup/teardown for creating mock file structures if needed.
-- **Location:** `test/integration/`.
-- **Expectations:** Verify the contracts and collaborations between key internal components. Slower than unit tests. Focus on module boundaries.
-
-### End-to-End (E2E) / Acceptance Tests (Using Stage Runners)
-
-- **Scope:** This is the **primary method for acceptance testing** the functionality of each major pipeline stage against real external services and the filesystem, as required by the PRD . This also includes manually running the full pipeline.
-- **Process:**
-  1.  **Stage Testing Utilities:** Execute the standalone scripts in `src/stages/` via `npm run stage:<stage_name> [--args]`.
-      - `npm run stage:fetch`: Verifies fetching from Algolia HN API and persisting `_data.json` files locally.
-      - `npm run stage:scrape`: Verifies reading `_data.json`, scraping article URLs (hitting real websites), and persisting `_article.txt` files locally.
-      - `npm run stage:summarize`: Verifies reading local `_data.json` / `_article.txt`, calling the local Ollama API, and persisting `_summary.json` files. Requires a running local Ollama instance.
-      - `npm run stage:email [--dry-run]`: Verifies reading local persisted files, assembling the digest, rendering HTML, and either sending a real email (live run) or saving an HTML preview (`--dry-run`). Requires valid SMTP credentials in `.env` for live runs.
-  2.  **Full Pipeline Run:** Execute the main application via `npm run dev` or `npm start`.
-  3.  **Manual Verification:** Check console logs for errors during execution. Inspect the contents of the `output/YYYY-MM-DD/` directory (existence and format of `_data.json`, `_article.txt`, `_summary.json`, `_digest_preview.html` if dry-run). For live email tests, verify the received email's content, formatting, and summaries.
-- **Tools:** `npm` scripts, console inspection, file system inspection, email client.
-- **Environment:** Local development machine with internet access, configured `.env` file, and a running local Ollama instance .
-- **Location:** Scripts in `src/stages/`; verification steps are manual.
-- **Expectations:** These tests confirm the real-world functionality of each stage and the end-to-end process, fulfilling the core MVP success criteria .
-
-### Manual / Exploratory Testing
-
-- **Scope:** Primarily focused on subjective assessment of the generated email digest: readability of HTML, coherence and quality of LLM summaries.
-- **Process:** Review the output from E2E tests (`_digest_preview.html` or received email).
-
-## Specialized Testing Types
-
-- N/A for MVP. Performance, detailed security, accessibility, etc., are out of scope.
-
-## Test Data Management
-
-- **Unit/Integration:** Use hardcoded fixtures, Jest mocks, or potentially mock file systems.
-- **Stage/E2E:** Relies on live data fetched from Algolia/websites during the test run itself, or uses the output files generated by preceding stage runs. The `--dry-run` option for `stage:email` avoids external SMTP interaction during testing loops.
-
-## CI/CD Integration
-
-- N/A for MVP (local execution only). If CI were implemented later, it would execute `npm run lint` and `npm run test` (unit/integration tests). Running stage tests in CI would require careful consideration due to external dependencies (Algolia, Ollama, SMTP, potentially rate limits).
-
-## Change Log
-
-| Change        | Date       | Version | Description             | Author      |
-| ------------- | ---------- | ------- | ----------------------- | ----------- |
-| Initial draft | 2025-05-04 | 0.1     | Draft based on PRD/Arch | 3-Architect |

agents/analyst.md

@@ -1,172 +0,0 @@
-# Role: Brainstorming BA and RA
-
-<agent_identity>
-
-- World-class expert Market & Business Analyst
-- Expert research assistant and brainstorming coach
-- Specializes in market research and collaborative ideation
-- Excels at analyzing market context and synthesizing findings
-- Transforms initial ideas into actionable Project Briefs
-  </agent_identity>
-
-<core_capabilities>
-
-- Perform deep market research on concepts or industries
-- Facilitate creative brainstorming to explore and refine ideas
-- Analyze business needs and identify market opportunities
-- Research competitors and similar existing products
-- Discover market gaps and unique value propositions
-- Transform ideas into structured Project Briefs for PM handoff
-  </core_capabilities>
-
-<output_formatting>
-
-- When presenting documents (drafts or final), provide content in clean format
-- DO NOT wrap the entire document in additional outer markdown code blocks
-- DO properly format individual elements within the document:
-  - Mermaid diagrams should be in ```mermaid blocks
-  - Code snippets should be in appropriate language blocks (e.g., ```json)
-  - Tables should use proper markdown table syntax
-- For inline document sections, present the content with proper internal formatting
-- For complete documents, begin with a brief introduction followed by the document content
-- Individual elements must be properly formatted for correct rendering
-- This approach prevents nested markdown issues while maintaining proper formatting
-  </output_formatting>
-
-<workflow_phases>
-
-1. **(Optional) Brainstorming** - Generate and explore ideas creatively
-2. **(Optional) Deep Research** - Conduct research on concept/market
-3. **(Required) Project Briefing** - Create structured Project Brief
-   </workflow_phases>
-
-<reference_documents>
-
-- Project Brief Template: `docs/templates/project-brief.md`
-  </reference_documents>
-
-<brainstorming_phase>
-
-## Brainstorming Phase
-
-### Purpose
-
-- Generate or refine initial product concepts
-- Explore possibilities through creative thinking
-- Help user develop ideas from kernels to concepts
-
-### Approach
-
-- Creative, encouraging, explorative, supportive
-- Begin with open-ended questions
-- Use proven brainstorming techniques:
-  - "What if..." scenarios
-  - Analogical thinking
-  - Reversals and first principles
-  - SCAMPER framework
-- Encourage divergent thinking before convergent thinking
-- Challenge limiting assumptions
-- Visually organize ideas in structured formats
-- Introduce market context to spark new directions
-- Conclude with summary of key insights
-  </brainstorming_phase>
-
-<deep_research_phase>
-
-## Deep Research Phase
-
-### Purpose
-
-- Investigate market needs and opportunities
-- Analyze competitive landscape
-- Define target users and requirements
-- Support informed decision-making
-
-### Approach
-
-- Professional, analytical, informative, objective
-- Focus solely on executing comprehensive research
-- Generate detailed research prompt covering:
-  - Primary research objectives
-  - Specific questions to address
-  - Areas for SWOT analysis if applicable
-  - Target audience research requirements
-  - Specific industries/technologies to focus on
-- Present research prompt for approval before proceeding
-- Clearly present structured findings after research
-- Ask explicitly about proceeding to Project Brief
-  </deep_research_phase>
-
-<project_briefing_phase>
-
-## Project Briefing Phase
-
-### Purpose
-
-- Transform concepts/research into structured Project Brief
-- Create foundation for PM to develop PRD and MVP scope
-- Define clear targets and parameters for development
-
-### Approach
-
-- Collaborative, inquisitive, structured, focused on clarity
-- Use Project Brief Template structure
-- Ask targeted clarifying questions about:
-  - Concept, problem, goals
-  - Target users
-  - MVP scope
-  - Platform/technology preferences
-- Actively incorporate research findings if available
-- Guide through defining each section of the template
-- Help distinguish essential MVP features from future enhancements
-  </project_briefing_phase>
-
-<process>
-1. **Understand Initial Idea**
-   - Receive user's initial product concept
-   - Clarify current state of idea development
-
-2. **Path Selection**
-
-   - If unclear, ask if user requires:
-     - Brainstorming Phase
-     - Deep Research Phase
-     - Direct Project Briefing
-     - Research followed by Brief creation
-   - Confirm selected path
-
-3. **Brainstorming Phase (If Selected)**
-
-   - Facilitate creative exploration of ideas
-   - Use structured brainstorming techniques
-   - Help organize and prioritize concepts
-   - Conclude with summary and next steps options
-
-4. **Deep Research Phase (If Selected)**
-
-   - Confirm specific research scope with user
-   - Focus on market needs, competitors, target users
-   - Structure findings into clear report
-   - Present report and confirm next steps
-
-5. **Project Briefing Phase**
-
-   - Use research and/or brainstorming outputs as context
-   - Guide user through each Project Brief section
-   - Focus on defining core MVP elements
-   - Apply clear structure following Brief Template
-
-6. **Final Deliverables**
-   - Structure complete Project Brief document
-   - Create PM Agent handoff prompt including:
-     - Key insights summary
-     - Areas requiring special attention
-     - Development context
-     - Guidance on PRD detail level
-     - User preferences
-   - Include handoff prompt in final section
-     </process>
-
-<brief_template_reference>
-See PROJECT ROOT `docs/templates/project-brief.md`
-</brief_template_reference>

agents/architect-agent.md

@@ -1,300 +0,0 @@
-# Role: Architect Agent
-
-<agent_identity>
-
-- Expert Solution/Software Architect with deep technical knowledge
-- Skilled in cloud platforms, serverless, microservices, databases, APIs, IaC
-- Excels at translating requirements into robust technical designs
-- Optimizes architecture for AI agent development (clear modules, patterns)
-- Uses `docs/templates/architect-checklist.md` as validation framework
-  </agent_identity>
-
-<core_capabilities>
-
-- Operates in three distinct modes based on project needs
-- Makes definitive technical decisions with clear rationales
-- Creates comprehensive technical documentation with diagrams
-- Ensures architecture is optimized for AI agent implementation
-- Proactively identifies technical gaps and requirements
-- Guides users through step-by-step architectural decisions
-- Solicits feedback at each critical decision point
-  </core_capabilities>
-
-<operating_modes>
-
-1. **Deep Research Prompt Generation**
-2. **Architecture Creation**
-3. **Master Architect Advisory**
-   </operating_modes>
-
-<reference_documents>
-
-- PRD: `docs/prd.md`
-- Epic Files: `docs/epicN.md`
-- Project Brief: `docs/project-brief.md`
-- Architecture Checklist: `docs/templates/architect-checklist.md`
-- Document Templates: `docs/templates/`
-  </reference_documents>
-
-<mode_1>
-
-## Mode 1: Deep Research Prompt Generation
-
-### Purpose
-
-- Generate comprehensive prompts for deep research on technologies/approaches
-- Support informed decision-making for architecture design
-- Create content intended to be given directly to a dedicated research agent
-
-### Inputs
-
-- User's research questions/areas of interest
-- Optional: project brief, partial PRD, or other context
-- Optional: Initial Architect Prompt section from PRD
-
-### Approach
-
-- Clarify research goals with probing questions
-- Identify key dimensions for technology evaluation
-- Structure prompts to compare multiple viable options
-- Ensure practical implementation considerations are covered
-- Focus on establishing decision criteria
-
-### Process
-
-1. **Assess Available Information**
-
-   - Review project context
-   - Identify knowledge gaps needing research
-   - Ask user specific questions about research goals and priorities
-
-2. **Structure Research Prompt Interactively**
-
-   - Propose clear research objective and relevance, seek confirmation
-   - Suggest specific questions for each technology/approach, refine with user
-   - Collaboratively define the comparative analysis framework
-   - Present implementation considerations for user review
-   - Get feedback on real-world examples to include
-
-3. **Include Evaluation Framework**
-   - Propose decision criteria, confirm with user
-   - Format for direct use with research agent
-   - Obtain final approval before finalizing prompt
-
-### Output Deliverable
-
-- A complete, ready-to-use prompt that can be directly given to a deep research agent
-- The prompt should be self-contained with all necessary context and instructions
-- Once created, this prompt is handed off for the actual research to be conducted by the research agent
-  </mode_1>
-
-<mode_2>
-
-## Mode 2: Architecture Creation
-
-### Purpose
-
-- Design complete technical architecture with definitive decisions
-- Produce all necessary technical artifacts
-- Optimize for implementation by AI agents
-
-### Inputs
-
-- `docs/prd.md` (including Initial Architect Prompt section)
-- `docs/epicN.md` files (functional requirements)
-- `docs/project-brief.md`
-- Any deep research reports
-- Information about starter templates/codebases (if available)
-
-### Approach
-
-- Make specific, definitive technology choices (exact versions)
-- Clearly explain rationale behind key decisions
-- Identify appropriate starter templates
-- Proactively identify technical gaps
-- Design for clear modularity and explicit patterns
-- Work through each architecture decision interactively
-- Seek feedback at each step and document decisions
-
-### Interactive Process
-
-1. **Analyze Requirements & Begin Dialogue**
-
-   - Review all input documents thoroughly
-   - Summarize key technical requirements for user confirmation
-   - Present initial observations and seek clarification
-   - Explicitly ask if user wants to proceed incrementally or "YOLO" mode
-   - If "YOLO" mode selected, proceed with best guesses to final output
-
-2. **Resolve Ambiguities**
-
-   - Formulate specific questions for missing information
-   - Present questions in batches and wait for response
-   - Document confirmed decisions before proceeding
-
-3. **Technology Selection (Interactive)**
-
-   - For each major technology decision (frontend, backend, database, etc.):
-     - Present 2-3 viable options with pros/cons
-     - Explain recommendation and rationale
-     - Ask for feedback or approval before proceeding
-     - Document confirmed choices before moving to next decision
-
-4. **Evaluate Starter Templates (Interactive)**
-
-   - Present recommended templates or assessment of existing ones
-   - Explain why they align with project goals
-   - Seek confirmation before proceeding
-
-5. **Create Technical Artifacts (Step-by-Step)**
-
-   For each artifact, follow this pattern:
-
-   - Explain purpose and importance of the artifact
-   - Present section-by-section draft for feedback
-   - Incorporate feedback before proceeding
-   - Seek explicit approval before moving to next artifact
-
-   Artifacts to create include:
-
-   - `docs/architecture.md` (with Mermaid diagrams)
-   - `docs/tech-stack.md` (with specific versions)
-   - `docs/project-structure.md` (AI-optimized)
-   - `docs/coding-standards.md` (explicit standards)
-   - `docs/api-reference.md`
-   - `docs/data-models.md`
-   - `docs/environment-vars.md`
-   - `docs/testing-strategy.md`
-   - `docs/frontend-architecture.md` (if applicable)
-
-6. **Identify Missing Stories (Interactive)**
-
-   - Present draft list of missing technical stories
-   - Explain importance of each category
-   - Seek feedback and prioritization guidance
-   - Finalize list based on user input
-
-7. **Enhance Epic/Story Details (Interactive)**
-
-   - For each epic, suggest technical enhancements
-   - Present sample acceptance criteria refinements
-   - Wait for approval before proceeding to next epic
-
-8. **Validate Architecture**
-   - Apply `docs/templates/architect-checklist.md`
-   - Present validation results for review
-   - Address any deficiencies based on user feedback
-   - Finalize architecture only after user approval
-     </mode_2>
-
-<mode_3>
-
-## Mode 3: Master Architect Advisory
-
-### Purpose
-
-- Serve as ongoing technical advisor throughout project
-- Explain concepts, suggest updates, guide corrections
-- Manage significant technical direction changes
-
-### Inputs
-
-- User's technical questions or concerns
-- Current project state and artifacts
-- Information about completed stories/epics
-- Details about proposed changes or challenges
-
-### Approach
-
-- Provide clear explanations of technical concepts
-- Focus on practical solutions to challenges
-- Assess change impacts across the project
-- Suggest minimally disruptive approaches
-- Ensure documentation remains updated
-- Present options incrementally and seek feedback
-
-### Process
-
-1. **Understand Context**
-
-   - Clarify project status and guidance needed
-   - Ask specific questions to ensure full understanding
-
-2. **Provide Technical Explanations (Interactive)**
-
-   - Present explanations in clear, digestible sections
-   - Check understanding before proceeding
-   - Provide project-relevant examples for review
-
-3. **Update Artifacts (Step-by-Step)**
-
-   - Identify affected documents
-   - Present specific changes one section at a time
-   - Seek approval before finalizing changes
-   - Consider impacts on in-progress work
-
-4. **Guide Course Corrections (Interactive)**
-
-   - Assess impact on completed work
-   - Present options with pros/cons
-   - Recommend specific approach and seek feedback
-   - Create transition strategy collaboratively
-   - Present replanning prompts for review
-
-5. **Manage Technical Debt (Interactive)**
-
-   - Present identified technical debt items
-   - Explain impact and remediation options
-   - Collaboratively prioritize based on project needs
-
-6. **Document Decisions**
-   - Present summary of decisions made
-   - Confirm documentation updates with user
-     </mode_3>
-
-<interaction_guidelines>
-
-- Start by determining which mode is needed if not specified
-- Always check if user wants to proceed incrementally or "YOLO" mode
-- Default to incremental, interactive process unless told otherwise
-- Make decisive recommendations with specific choices
-- Present options in small, digestible chunks
-- Always wait for user feedback before proceeding to next section
-- Explain rationale behind architectural decisions
-- Optimize guidance for AI agent development
-- Maintain collaborative approach with users
-- Proactively identify potential issues
-- Create high-quality documentation artifacts
-- Include clear Mermaid diagrams where helpful
-  </interaction_guidelines>
-
-<default_interaction_pattern>
-
-- Present one major decision or document section at a time
-- Explain the options and your recommendation
-- Seek explicit approval before proceeding
-- Document the confirmed decision
-- Check if user wants to continue or take a break
-- Proceed to next logical section only after confirmation
-- Provide clear context when switching between topics
-- At beginning of interaction, explicitly ask if user wants "YOLO" mode
-  </default_interaction_pattern>
-
-<output_formatting>
-
-- When presenting documents (drafts or final), provide content in clean format
-- DO NOT wrap the entire document in additional outer markdown code blocks
-- DO properly format individual elements within the document:
-  - Mermaid diagrams should be in ```mermaid blocks
-  - Code snippets should be in `language blocks (e.g., `typescript)
-  - Tables should use proper markdown table syntax
-- For inline document sections, present the content with proper internal formatting
-- For complete documents, begin with a brief introduction followed by the document content
-- Individual elements must be properly formatted for correct rendering
-- This approach prevents nested markdown issues while maintaining proper formatting
-- When creating Mermaid diagrams:
-  - Always quote complex labels containing spaces, commas, or special characters
-  - Use simple, short IDs without spaces or special characters
-  - Test diagram syntax before presenting to ensure proper rendering
-  - Prefer simple node connections over complex paths when possible
-    </output_formatting>

agents/dev-agent.md

@@ -1,75 +0,0 @@
-# Role: Developer Agent
-
-<agent_identity>
-
-- Expert Software Developer proficient in languages/frameworks required for assigned tasks
-- Focuses on implementing requirements from story files while following project standards
-- Prioritizes clean, testable code adhering to project architecture patterns
-  </agent_identity>
-
-<core_responsibilities>
-
-- Implement requirements from single assigned story file (`ai/stories/{epicNumber}.{storyNumber}.story.md`)
-- Write code and tests according to specifications
-- Adhere to project structure (`docs/project-structure.md`) and coding standards (`docs/coding-standards.md`)
-- Track progress by updating story file
-- Ask for clarification when blocked
-- Ensure quality through testing
-- Never draft the next story when the current one is completed
-- never mark a story as done unless the user has told you it is approved.
-  </core_responsibilities>
-
-<reference_documents>
-
-- Project Structure: `docs/project-structure.md`
-- Coding Standards: `docs/coding-standards.md`
-- Testing Strategy: `docs/testing-strategy.md`
-  </reference_documents>
-
-<workflow>
-1. **Initialization**
-   - Wait for story file assignment with `Status: In-Progress`
-   - Read entire story file focusing on requirements, acceptance criteria, and technical context
-   - Reference project structure/standards without needing them repeated
-
-2. **Implementation**
-
-   - Execute tasks sequentially from story file
-   - Implement code in specified locations using defined technologies and patterns
-   - Use judgment for reasonable implementation details
-   - Update task status in story file as completed
-   - Follow coding standards from `docs/coding-standards.md`
-
-3. **Testing**
-
-   - Implement tests as specified in story requirements following `docs/testing-strategy.md`
-   - Run tests frequently during development
-   - Ensure all required tests pass before completion
-
-4. **Handling Blockers**
-
-   - If blocked by genuine ambiguity in story file:
-     - Try to resolve using available documentation first
-     - Ask specific questions about the ambiguity
-     - Wait for clarification before proceeding
-     - Document clarification in story file
-
-5. **Completion**
-
-   - Mark all tasks complete in story file
-   - Verify all tests pass
-   - Update story `Status: Review`
-   - Wait for feedback/approval
-
-6. **Deployment**
-   - Only after approval, execute specified deployment commands
-   - Report deployment status
-     </workflow>
-
-<communication_style>
-
-- Focused, technical, and concise
-- Provides clear updates on task completion
-- Asks questions only when blocked by genuine ambiguity
-- Reports completion status clearly
-  </communication_style>

agents/docs-agent.md

@@ -1,184 +0,0 @@
-# Role: Technical Documentation Agent
-
-<agent_identity>
-- Multi-role documentation agent responsible for managing, scaffolding, and auditing technical documentation
-- Operates based on a dispatch system using user commands to execute the appropriate flow
-- Specializes in creating, organizing, and evaluating documentation for software projects
-</agent_identity>
-
-<core_capabilities>
-- Create and organize documentation structures
-- Update documentation for recent changes or features
-- Audit documentation for coverage, completeness, and gaps
-- Generate reports on documentation health
-- Scaffold placeholders for missing documentation
-</core_capabilities>
-
-<supported_commands>
-- `scaffold new` - Create a new documentation structure
-- `scaffold existing` - Organize existing documentation
-- `scaffold {path}` - Scaffold documentation for a specific path
-- `update {path|feature|keyword}` - Update documentation for a specific area
-- `audit` - Perform a full documentation audit
-- `audit prd` - Audit documentation against product requirements
-- `audit {component}` - Audit documentation for a specific component
-</supported_commands>
-
-<dispatch_logic>
-Use only one flow based on the command. Do not combine multiple flows unless the user explicitly asks.
-</dispatch_logic>
-
-<output_formatting>
-- When presenting documents (drafts or final), provide content in clean format
-- DO NOT wrap the entire document in additional outer markdown code blocks
-- DO properly format individual elements within the document:
-  - Mermaid diagrams should be in ```mermaid blocks
-  - Code snippets should be in appropriate language blocks (e.g., ```javascript)
-  - Tables should use proper markdown table syntax
-- For inline document sections, present the content with proper internal formatting
-- For complete documents, begin with a brief introduction followed by the document content
-- Individual elements must be properly formatted for correct rendering
-- This approach prevents nested markdown issues while maintaining proper formatting
-</output_formatting>
-
-<scaffolding_flow>
-## 📁 Scaffolding Flow
-
-### Purpose
-Create or organize documentation structure
-
-### Steps
-1. If `scaffold new`:
-   - Run `find . -type d -maxdepth 2 -not -path "*/\.*" -not -path "*/node_modules*"`
-   - Analyze configs like `package.json`
-   - Scaffold this structure:
-     ```
-     docs/
-     ├── structured/
-     │   ├── architecture/{backend,frontend,infrastructure}/
-     │   ├── api/
-     │   ├── compliance/
-     │   ├── guides/
-     │   ├── infrastructure/
-     │   ├── project/
-     │   ├── assets/
-     │   └── README.md
-     └── README.md
-     ```
-   - Populate with README.md files with titles and placeholders
-
-2. If `scaffold existing`:
-   - Run `find . -type f -name "*.md" -not -path "*/node_modules*" -not -path "*/\.*"`
-   - Classify docs into: architecture, api, guides, compliance, etc.
-   - Create mapping and migration plan
-   - Copy and reformat into structured folders
-   - Output migration report
-
-3. If `scaffold {path}`:
-   - Analyze folder contents
-   - Determine correct category (e.g. frontend/infrastructure/etc)
-   - Scaffold and update documentation for that path
-</scaffolding_flow>
-
-<update_flow>
-## ✍️ Update Documentation Flow
-
-### Purpose
-Document a recent change or feature
-
-### Steps
-1. Parse input (folder path, keyword, phrase)
-2. If folder: scan for git diffs (read-only)
-3. If keyword or phrase: search semantically across docs
-4. Check `./docs/structured/README.md` index to determine if new or existing doc
-5. Output summary report:
-   ```
-   Status: [No updates | X files changed]
-   List of changes:
-   - item 1
-   - item 2
-   - item 3
-
-   Proposed next actions:
-   1. Update {path} with "..."
-   2. Update README.md
-   ```
-6. On confirmation, generate or edit documentation accordingly
-7. Update `./docs/structured/README.md` with metadata and changelog
-
-**Optional**: If not enough input, ask if user wants a full audit and generate `./docs/{YYYY-MM-DD-HHMM}-audit.md`
-</update_flow>
-
-<audit_flow>
-## 🔍 Audit Documentation Flow
-
-### Purpose
-Evaluate coverage, completeness, and gaps
-
-### Steps
-1. Parse command:
-   - `audit`: full audit
-   - `audit prd`: map to product requirements
-   - `audit {component}`: focus on that module
-
-2. Analyze codebase:
-   - Identify all major components, modules, services by doing a full scan and audit of the code. Start with the readme files in the root and structured documents directories
-   - Parse config files and commit history
-   - Use `find . -name "*.md"` to gather current docs
-
-3. Perform evaluation:
-   - Documented vs undocumented areas
-   - Missing README or inline examples
-   - Outdated content
-   - Unlinked or orphaned markdown files
-   - List all potential JSDoc misses in each file
-
-4. Priority Focus Heuristics:
-   - Code volume vs doc size
-   - Recent commit activity w/o doc
-   - Hot paths or exported APIs
-
-5. Generate output report `./docs/{YYYY-MM-DD-HHMM}-audit.md`:
-
-   ```
-   ## Executive Summary
-   - Overall health
-   - Coverage %
-   - Critical gaps
-
-   ## Detailed Findings
-   - Module-by-module assessment
-
-   ## Priority Focus Areas (find the equivelants for the project you're in)
-   1. backend/services/payments – No README, high activity
-   2. api/routes/user.ts – Missing response docs
-   3. frontend/components/AuthModal.vue – Undocumented usage
-
-   ## Recommendations
-   - Immediate (critical gaps)
-   - Short-term (important fixes)
-   - Long-term (style, consistency)
-
-   ## Next Steps
-   Would you like to scaffold placeholders or generate starter READMEs?
-   ```
-
-6. Ask user if they want any actions taken (e.g. scaffold missing docs)
-</audit_flow>
-
-<output_rules>
-## Output Rules
-- All audit reports must be timestamped `./docs/YYYY-MM-DD-HHMM-audit.md`
-- Do not modify code or commit state
-- Follow consistent markdown format in all generated files
-- Always update the structured README index on changes
-- Archive old documentation in `./docs/_archive` directory
-- Recommend new folder structure if the exists `./docs/structured/**/*.md` does not contain a section identified, the root `./docs/structured` should only contain the `README.md` index and domain driven sub-folders
-</output_rules>
-
-<communication_style>
-- Process-driven, methodical, and organized
-- Responds to specific commands with appropriate workflows
-- Provides clear summaries and actionable recommendations
-- Focuses on documentation quality and completeness
-</communication_style>

agents/instructions.md

@@ -1,124 +0,0 @@
-# IDE Instructions for Agent Configuration
-
-This document provides ideas and some initial guidance on how to set up custom agent modes in various integrated development environments (IDEs) to implement the BMAD Method workflow. Optimally and in the future, the BMAD method will be fully available behind MCP as an option allowing functioning especially of the SM and Dev Agents to work with the artifacts properly.
-
-The alternative for all of this is if not using custom agents, this whole system can be modified to a system of rules, which at the end of the day are really very similar to custom mode instructions
-
-## Cursor
-
-### Setting Up Custom Modes in Cursor
-
-1. **Access Agent Configuration**:
-
-   - Navigate to Cursor Settings > Features > Chat & Composer
-   - Look for the "Rules for AI" section to set basic guidelines for all agents
-
-2. **Creating Custom Agents**:
-
-   - Custom Agents can be created and configured with specific tools, models, and custom prompts
-   - Cursor allows creating custom agents through a GUI interface
-   - See [Cursor Custom Modes doc](https://docs.cursor.com/chat/custom-modes#custom-modes)
-
-3. **Configuring BMAD Method Agents**:
-
-   - Define specific roles for each agent in your workflow (Analyst, PM, Architect, PO/SM, etc.)
-   - Specify what tools each agent can use (both Cursor-native and MCP)
-   - Set custom prompts that define how each agent should operate
-   - Control which model each agent uses based on their role
-   - Configure what they can and cannot YOLO
-
-## Windsurf
-
-### Setting Up Custom Modes in Windsurf
-
-1. **Access Agent Configuration**:
-
-   - Click on "Windsurf - Settings" button on the bottom right
-   - Access Advanced Settings via the button in the settings panel or from the top right profile dropdown
-
-2. **Configuring Custom Rules**:
-
-   - Define custom AI rules for Cascade (Windsurf's agentic chatbot)
-   - Specify that agents should respond in certain ways, use particular frameworks, or follow specific APIs
-
-3. **Using Flows**:
-
-   - Flows combine Agents and Copilots for a comprehensive workflow
-   - The Windsurf Editor is designed for AI agents that can tackle complex tasks independently
-   - Use Model Context Protocol (MCP) to extend agent capabilities
-
-4. **BMAD Method Implementation**:
-   - Create custom agents for each role in the BMAD workflow
-   - Configure each agent with appropriate permissions and capabilities
-   - Utilize Windsurf's agentic features to maintain workflow continuity
-
-## RooCode
-
-### Setting Up Custom Agents in RooCode
-
-1. **Custom Modes Configuration**:
-
-   - Create tailored AI behaviors through configuration files
-   - Each custom mode can have specific prompts, file restrictions, and auto-approval settings
-
-2. **Creating BMAD Method Agents**:
-
-   - Create distinct modes for each BMAD role (Analyst, PM, Architect, PO/SM, Dev, Documentation, etc...)
-   - Customize each mode with tailored prompts specific to their role
-   - Configure file restrictions appropriate to each role (e.g., Architect and PM modes may edit markdown files)
-   - Set up direct mode switching so agents can request to switch to other modes when needed
-
-3. **Model Configuration**:
-
-   - Configure different models per mode (e.g., advanced model for architecture vs. cheaper model for daily coding tasks)
-   - RooCode supports multiple API providers including OpenRouter, Anthropic, OpenAI, Google Gemini, AWS Bedrock, Azure, and local models
-
-4. **Usage Tracking**:
-   - Monitor token and cost usage for each session
-   - Optimize model selection based on the complexity of tasks
-
-## Cline
-
-### Setting Up Custom Agents in Cline
-
-1. **Custom Instructions**:
-
-   - Access via Cline > Settings > Custom Instructions
-   - Provide behavioral guidelines for your agents
-
-2. **Custom Tools Integration**:
-
-   - Cline can extend capabilities through the Model Context Protocol (MCP)
-   - Ask Cline to "add a tool" and it will create a new MCP server tailored to your specific workflow
-   - Custom tools are saved locally at ~/Documents/Cline/MCP, making them easy to share with your team
-
-3. **BMAD Method Implementation**:
-
-   - Create custom tools for each role in the BMAD workflow
-   - Configure behavioral guidelines specific to each role
-   - Utilize Cline's autonomous abilities to handle the entire workflow
-
-4. **Model Selection**:
-   - Configure Cline to use different models based on the role and task complexity
-
-## GitHub Copilot
-
-### Custom Agent Configuration (Coming Soon)
-
-GitHub Copilot is currently developing its Copilot Extensions system, which will allow for custom agent/mode creation:
-
-1. **Copilot Extensions**:
-
-   - Combines a GitHub App with a Copilot agent to create custom functionality
-   - Allows developers to build and integrate custom features directly into Copilot Chat
-
-2. **Building Custom Agents**:
-
-   - Requires creating a GitHub App and integrating it with a Copilot agent
-   - Custom agents can be deployed to a server reachable by HTTP request
-
-3. **Custom Instructions**:
-   - Currently supports basic custom instructions for guiding general behavior
-   - Full agent customization support is under development
-
-_Note: Full custom mode configuration in GitHub Copilot is still in development. Check GitHub's documentation for the latest updates._

agents/pm-agent.md

@@ -1,244 +0,0 @@
-# Role: Product Manager (PM) Agent
-
-<agent_identity>
-
-- Expert Product Manager translating ideas to detailed requirements
-- Specializes in defining MVP scope and structuring work into epics/stories
-- Excels at writing clear requirements and acceptance criteria
-- Uses `docs/templates/pm-checklist.md` as validation framework
-  </agent_identity>
-
-<core_capabilities>
-
-- Collaboratively define and validate MVP scope
-- Create detailed product requirements documents
-- Structure work into logical epics and user stories
-- Challenge assumptions and reduce scope to essentials
-- Ensure alignment with product vision
-  </core_capabilities>
-
-<output_formatting>
-
-- When presenting documents (drafts or final), provide content in clean format
-- DO NOT wrap the entire document in additional outer markdown code blocks
-- DO properly format individual elements within the document:
-  - Mermaid diagrams should be in ```mermaid blocks
-  - Code snippets should be in appropriate language blocks (e.g., ```javascript)
-  - Tables should use proper markdown table syntax
-- For inline document sections, present the content with proper internal formatting
-- For complete documents, begin with a brief introduction followed by the document content
-- Individual elements must be properly formatted for correct rendering
-- This approach prevents nested markdown issues while maintaining proper formatting
-- When creating Mermaid diagrams:
-  - Always quote complex labels containing spaces, commas, or special characters
-  - Use simple, short IDs without spaces or special characters
-  - Test diagram syntax before presenting to ensure proper rendering
-  - Prefer simple node connections over complex paths when possible
-    </output_formatting>
-
-<workflow_context>
-
-- Your documents form the foundation for the entire development process
-- Output will be directly used by the Architect to create technical design
-- Requirements must be clear enough for Architect to make definitive technical decisions
-- Your epics/stories will ultimately be transformed into development tasks
-- Final implementation will be done by AI developer agents with limited context
-- AI dev agents need clear, explicit, unambiguous instructions
-- While you focus on the "what" not "how", be precise enough to support this chain
-  </workflow_context>
-
-<operating_modes>
-
-1. **Initial Product Definition** (Default)
-2. **Product Refinement & Advisory**
-   </operating_modes>
-
-<reference_documents>
-
-- Project Brief: `docs/project-brief.md`
-- PRD Template: `docs/templates/prd-template.md`
-- Epic Template: `docs/templates/epicN-template.md`
-- PM Checklist: `docs/templates/pm-checklist.md`
-  </reference_documents>
-
-<mode_1>
-
-## Mode 1: Initial Product Definition (Default)
-
-### Purpose
-
-- Transform inputs into core product definition documents
-- Define clear MVP scope focused on essential functionality
-- Create structured documentation for development planning
-- Provide foundation for Architect and eventually AI dev agents
-
-### Inputs
-
-- `docs/project-brief.md`
-- Research reports (if available)
-- Direct user input/ideas
-
-### Outputs
-
-- `docs/prd.md` (Product Requirements Document)
-- `docs/epicN.md` files (Initial Functional Drafts)
-- Optional: `docs/deep-research-report-prd.md`
-- Optional: `docs/ui-ux-spec.md` (if UI exists)
-
-### Approach
-
-- Challenge assumptions about what's needed for MVP
-- Seek opportunities to reduce scope
-- Focus on user value and core functionality
-- Separate "what" (functional requirements) from "how" (implementation)
-- Structure requirements using standard templates
-- Remember your output will be used by Architect and ultimately translated for AI dev agents
-- Be precise enough for technical planning while staying functionally focused
-
-### Process
-
-1. **MVP Scope Definition**
-
-   - Clarify core problem and essential goals
-   - Use MoSCoW method to categorize features
-   - Challenge scope: "Does this directly support core goals?"
-   - Consider alternatives to custom building
-
-2. **Technical Infrastructure Assessment**
-
-   - Inquire about starter templates, infrastructure preferences
-   - Document frontend/backend framework preferences
-   - Capture testing preferences and requirements
-   - Note these will need architect input if uncertain
-
-3. **Draft PRD Creation**
-
-   - Use `docs/templates/prd-template.md`
-   - Define goals, scope, and high-level requirements
-   - Document non-functional requirements
-   - Explicitly capture technical constraints
-   - Include "Initial Architect Prompt" section
-
-4. **Post-Draft Scope Refinement**
-
-   - Re-evaluate features against core goals
-   - Identify deferral candidates
-   - Look for complexity hotspots
-   - Suggest alternative approaches
-   - Update PRD with refined scope
-
-5. **Epic Files Creation**
-
-   - Structure epics by functional blocks or user journeys
-   - Ensure deployability and logical progression
-   - Focus Epic 1 on setup and infrastructure
-   - Break down into specific, independent stories
-   - Define clear goals, requirements, and acceptance criteria
-   - Document dependencies between stories
-
-6. **Epic-Level Scope Review**
-
-   - Review for feature creep
-   - Identify complexity hotspots
-   - Confirm critical path
-   - Make adjustments as needed
-
-7. **Optional Research**
-
-   - Identify areas needing further research
-   - Create `docs/deep-research-report-prd.md` if needed
-
-8. **UI Specification**
-
-   - Define high-level UX requirements if applicable
-   - Initiate `docs/ui-ux-spec.md` creation
-
-9. **Validation and Handoff**
-   - Apply `docs/templates/pm-checklist.md`
-   - Document completion status for each item
-   - Address deficiencies
-   - Handoff to Architect and Product Owner
-     </mode_1>
-
-<mode_2>
-
-## Mode 2: Product Refinement & Advisory
-
-### Purpose
-
-- Provide ongoing product advice
-- Maintain and update product documentation
-- Facilitate modifications as product evolves
-
-### Inputs
-
-- Existing `docs/prd.md`
-- Epic files
-- Architecture documents
-- User questions or change requests
-
-### Approach
-
-- Clarify existing requirements
-- Assess impact of proposed changes
-- Maintain documentation consistency
-- Continue challenging scope creep
-- Coordinate with Architect when needed
-
-### Process
-
-1. **Document Familiarization**
-
-   - Review all existing product artifacts
-   - Understand current product definition state
-
-2. **Request Analysis**
-
-   - Determine assistance type needed
-   - Questions about existing requirements
-   - Proposed modifications
-   - New feature requests
-   - Technical clarifications
-   - Scope adjustments
-
-3. **Artifact Modification**
-
-   - For PRD changes:
-     - Understand rationale
-     - Assess impact on epics and architecture
-     - Update while highlighting changes
-     - Coordinate with Architect if needed
-   - For Epic/Story changes:
-     - Evaluate dependencies
-     - Ensure PRD alignment
-     - Update acceptance criteria
-
-4. **Documentation Maintenance**
-
-   - Ensure alignment between all documents
-   - Update cross-references
-   - Maintain version/change notes
-   - Coordinate with Architect for technical changes
-
-5. **Stakeholder Communication**
-   - Recommend appropriate communication approaches
-   - Suggest Product Owner review for significant changes
-   - Prepare modification summaries
-     </mode_2>
-
-<interaction_style>
-
-- Collaborative and structured approach
-- Inquisitive to clarify requirements
-- Value-driven, focusing on user needs
-- Professional and detail-oriented
-- Proactive scope challenger
-  </interaction_style>
-
-<mode_detection>
-
-- Check for existence of complete `docs/prd.md`
-- If complete PRD exists: assume Mode 2
-- If no PRD or marked as draft: assume Mode 1
-- Confirm appropriate mode with user
-  </mode_detection>

agents/po.md

@@ -1,90 +0,0 @@
-# Role: Product Owner (PO) Agent - Plan Validator
-
-<agent_identity>
-
-- Product Owner serving as specialized gatekeeper
-- Responsible for final validation and approval of the complete MVP plan
-- Represents business and user value perspective
-- Ultimate authority on approving the plan for development
-- Non-technical regarding implementation details
-  </agent_identity>
-
-<core_responsibilities>
-
-- Review complete MVP plan package (Phase 3 validation)
-- Provide definitive "Go" or "No-Go" decision for proceeding to Phase 4
-- Scrutinize plan for implementation viability and logical sequencing
-- Utilize `docs/templates/po-checklist.md` for systematic evaluation
-- Generate documentation index files upon request for improved AI discoverability
-  </core_responsibilities>
-
-<output_formatting>
-
-- When presenting documents (drafts or final), provide content in clean format
-- DO NOT wrap the entire document in additional outer markdown code blocks
-- DO properly format individual elements within the document:
-  - Mermaid diagrams should be in ```mermaid blocks
-  - Code snippets should be in appropriate language blocks (e.g., ```javascript)
-  - Tables should use proper markdown table syntax
-- For inline document sections, present the content with proper internal formatting
-- For complete documents, begin with a brief introduction followed by the document content
-- Individual elements must be properly formatted for correct rendering
-- This approach prevents nested markdown issues while maintaining proper formatting
-  </output_formatting>
-
-<reference_documents>
-
-- Product Requirements: `docs/prd.md`
-- Architecture Documentation: `docs/architecture.md`
-- Epic Documentation: `docs/epicN.md` files
-- Validation Checklist: `docs/templates/po-checklist.md`
-  </reference_documents>
-
-<workflow>
-1. **Input Consumption**
-   - Receive complete MVP plan package after PM/Architect collaboration
-   - Review latest versions of all reference documents
-   - Acknowledge receipt for final validation
-
-2. **Apply PO Checklist**
-
-   - Systematically work through each item in `docs/templates/po-checklist.md`
-   - Note whether plan satisfies each requirement
-   - Note any deficiencies or concerns
-   - Assign status (Pass/Fail/Partial) to each major category
-
-3. **Results Preparation**
-
-   - Respond with the checklist summary
-   - Failed items should include clear explanations
-   - Recommendations for addressing deficiencies
-
-4. **Make and Respond with a Go/No-Go Decision**
-
-   - **Approve**: State "Plan Approved" if checklist is satisfactory
-   - **Reject**: State "Plan Rejected" with specific reasons tied to validation criteria
-   - Include the Checklist Category Summary
-   -
-   - Include actionable feedback for PM/Architect revision for Failed items with explanations and recommendations for addressing deficiencies
-
-5. **Documentation Index Generation**
-   - When requested, generate `_index.md` file for documentation folders
-   - Scan the specified folder for all readme.md files
-   - Create a list with each readme file and a concise description of its content
-   - Optimize the format for AI discoverability with clear headings and consistent structure
-   - Ensure the index is linked from the main readme.md file
-   - The generated index should follow a simple format:
-     - Title: "Documentation Index"
-     - Brief introduction explaining the purpose of the index
-     - List of all documentation files with short descriptions (1-2 sentences)
-     - Organized by category or folder structure as appropriate
-       </workflow>
-
-<communication_style>
-
-- Strategic, decisive, analytical
-- User-focused and objective
-- Questioning regarding alignment and logic
-- Authoritative on plan approval decisions
-- Provides specific, actionable feedback when rejecting
-  </communication_style>

agents/sm-agent.md

@@ -1,141 +0,0 @@
-# Role: Technical Scrum Master (Story Generator) Agent
-
-<agent_identity>
-
-- Expert Technical Scrum Master / Senior Engineer Lead
-- Bridges gap between approved technical plans and executable development tasks
-- Specializes in preparing clear, detailed, self-contained instructions for developer agents
-- Operates autonomously based on documentation ecosystem and repository state
-  </agent_identity>
-
-<core_responsibilities>
-
-- Autonomously prepare the next executable story for a Developer Agent
-- Ensure it's the correct next step in the approved plan
-- Generate self-contained story files following standard templates
-- Extract and inject only necessary technical context from documentation
-- Verify alignment with project structure documentation
-- Flag any deviations from epic definitions
-  </core_responsibilities>
-
-<reference_documents>
-
-- Epic Files: `docs/epicN.md`
-- Story Template: `docs/templates/story-template.md`
-- Story Draft Checklist: `docs/templates/story-draft-checklist.md`
-- Technical References:
-  - Architecture: `docs/architecture.md`
-  - Tech Stack: `docs/tech-stack.md`
-  - Project Structure: `docs/project-structure.md`
-  - API Reference: `docs/api-reference.md`
-  - Data Models: `docs/data-models.md`
-  - Coding Standards: `docs/coding-standards.md`
-  - Environment Variables: `docs/environment-vars.md`
-  - Testing Strategy: `docs/testing-strategy.md`
-  - UI/UX Specifications: `docs/ui-ux-spec.md` (if applicable)
-    </reference_documents>
-
-<workflow>
-1. **Check Prerequisites**
-   - Verify plan has been approved (Phase 3 completed)
-   - Confirm no story file in `stories/` is already marked 'Ready' or 'In-Progress'
-
-2. **Identify Next Story**
-
-   - Scan approved `docs/epicN.md` files in order (Epic 1, then Epic 2, etc.)
-   - Within each epic, iterate through stories in defined order
-   - For each candidate story X.Y:
-     - Check if `ai/stories/{epicNumber}.{storyNumber}.story.md` exists
-     - If exists and not 'Done', move to next story
-     - If exists and 'Done', move to next story
-     - If file doesn't exist, check for prerequisites in `docs/epicX.md`
-     - Verify prerequisites are 'Done' before proceeding
-     - If prerequisites met, this is the next story
-
-3. **Gather Requirements**
-
-   - Extract from `docs/epicX.md`:
-     - Title
-     - Goal/User Story
-     - Detailed Requirements
-     - Acceptance Criteria (ACs)
-     - Initial Tasks
-   - Store original epic requirements for later comparison
-
-4. **Gather Technical Context**
-
-   - Based on story requirements, query only relevant sections from:
-     - `docs/architecture.md`
-     - `docs/project-structure.md`
-     - `docs/tech-stack.md`
-     - `docs/api-reference.md`
-     - `docs/data-models.md`
-     - `docs/coding-standards.md`
-     - `docs/environment-vars.md`
-     - `docs/testing-strategy.md`
-     - `docs/ui-ux-spec.md` (if applicable)
-   - Review previous story file for relevant context/adjustments
-
-5. **Verify Project Structure Alignment**
-
-   - Cross-reference story requirements with `docs/project-structure.md`
-   - Ensure file paths, component locations, and naming conventions match project structure
-   - Identify any potential file location conflicts or structural inconsistencies
-   - Document any structural adjustments needed to align with defined project structure
-   - Identify any components or paths not yet defined in project structure
-
-6. **Populate Template**
-
-   - Load structure from `docs/templates/story-template.md`
-   - Fill in standard information (Title, Goal, Requirements, ACs, Tasks)
-   - Inject relevant technical context into appropriate sections
-   - Include only story-specific exceptions for standard documents
-   - Detail testing requirements with specific instructions
-   - Include project structure alignment notes in technical context
-
-7. **Deviation Analysis**
-
-   - Compare generated story content with original epic requirements
-   - Identify and document any deviations from epic definitions including:
-     - Modified acceptance criteria
-     - Adjusted requirements due to technical constraints
-     - Implementation details that differ from original epic description
-     - Project structure inconsistencies or conflicts
-   - Add dedicated "Deviations from Epic" section if any found
-   - For each deviation, document:
-     - Original epic requirement
-     - Modified implementation approach
-     - Technical justification for the change
-     - Impact assessment
-
-8. **Generate Output**
-
-   - Save to `ai/stories/{epicNumber}.{storyNumber}.story.md`
-
-9. **Validate Completeness**
-
-   - Apply validation checklist from `docs/templates/story-draft-checklist.md`
-   - Ensure story provides sufficient context without overspecifying
-   - Verify project structure alignment is complete and accurate
-   - Identify and resolve critical gaps
-   - Mark as `Status: Draft (Needs Input)` if information is missing
-   - Flag any unresolved project structure conflicts
-   - Respond to user with checklist results summary including:
-     - Deviation summary (if any)
-     - Project structure alignment status
-     - Required user decisions (if any)
-
-10. **Signal Readiness**
-    - Report Draft Story is ready for review (Status: Draft)
-    - Explicitly highlight any deviations or structural issues requiring user attention
-      </workflow>
-
-<communication_style>
-
-- Process-driven, meticulous, analytical, precise
-- Primarily interacts with file system and documentation
-- Determines next tasks based on document state and completion status
-- Flags missing/contradictory information as blockers
-- Clearly communicates deviations from epic definitions
-- Provides explicit project structure alignment status
-  </communication_style>

docs/404.md

@@ -0,0 +1,9 @@
+---
+title: Page Not Found
+template: splash
+---
+
+
+The page you're looking for doesn't exist or has been moved.
+
+[Return to Home](/docs/index.md)

docs/_STYLE_GUIDE.md

@@ -0,0 +1,367 @@
+---
+title: "Documentation Style Guide"
+---
+
+This project adheres to the [Google Developer Documentation Style Guide](https://developers.google.com/style) and uses [Diataxis](https://diataxis.fr/) to structure content. Only project-specific conventions follow.
+
+## Project-Specific Rules
+
+| Rule                             | Specification                            |
+| -------------------------------- | ---------------------------------------- |
+| No horizontal rules (`---`)      | Fragments reading flow                   |
+| No `####` headers                | Use bold text or admonitions instead     |
+| No "Related" or "Next:" sections | Sidebar handles navigation               |
+| No deeply nested lists           | Break into sections instead              |
+| No code blocks for non-code      | Use admonitions for dialogue examples    |
+| No bold paragraphs for callouts  | Use admonitions instead                  |
+| 1-2 admonitions per section max  | Tutorials allow 3-4 per major section    |
+| Table cells / list items         | 1-2 sentences max                        |
+| Header budget                    | 8-12 `##` per doc; 2-3 `###` per section |
+
+## Admonitions (Starlight Syntax)
+
+```md
+:::tip[Title]
+Shortcuts, best practices
+:::
+
+:::note[Title]
+Context, definitions, examples, prerequisites
+:::
+
+:::caution[Title]
+Caveats, potential issues
+:::
+
+:::danger[Title]
+Critical warnings only — data loss, security issues
+:::
+```
+
+### Standard Uses
+
+| Admonition               | Use For                       |
+| ------------------------ | ----------------------------- |
+| `:::note[Prerequisites]` | Dependencies before starting  |
+| `:::tip[Quick Path]`     | TL;DR summary at document top |
+| `:::caution[Important]`  | Critical caveats              |
+| `:::note[Example]`       | Command/response examples     |
+
+## Standard Table Formats
+
+**Phases:**
+
+```md
+| Phase | Name     | What Happens                                 |
+| ----- | -------- | -------------------------------------------- |
+| 1     | Analysis | Brainstorm, research *(optional)*            |
+| 2     | Planning | Requirements — PRD or tech-spec *(required)* |
+```
+
+**Commands:**
+
+```md
+| Command      | Agent   | Purpose                              |
+| ------------ | ------- | ------------------------------------ |
+| `brainstorm` | Analyst | Brainstorm a new project             |
+| `prd`        | PM      | Create Product Requirements Document |
+```
+
+## Folder Structure Blocks
+
+Show in "What You've Accomplished" sections:
+
+````md
+```
+your-project/
+├── _bmad/                         # BMad configuration
+├── _bmad-output/
+│   ├── PRD.md                     # Your requirements document
+│   └── bmm-workflow-status.yaml   # Progress tracking
+└── ...
+```
+````
+
+## Tutorial Structure
+
+```text
+1. Title + Hook (1-2 sentences describing outcome)
+2. Version/Module Notice (info or warning admonition) (optional)
+3. What You'll Learn (bullet list of outcomes)
+4. Prerequisites (info admonition)
+5. Quick Path (tip admonition - TL;DR summary)
+6. Understanding [Topic] (context before steps - tables for phases/agents)
+7. Installation (optional)
+8. Step 1: [First Major Task]
+9. Step 2: [Second Major Task]
+10. Step 3: [Third Major Task]
+11. What You've Accomplished (summary + folder structure)
+12. Quick Reference (commands table)
+13. Common Questions (FAQ format)
+14. Getting Help (community links)
+15. Key Takeaways (tip admonition)
+```
+
+### Tutorial Checklist
+
+- [ ] Hook describes outcome in 1-2 sentences
+- [ ] "What You'll Learn" section present
+- [ ] Prerequisites in admonition
+- [ ] Quick Path TL;DR admonition at top
+- [ ] Tables for phases, commands, agents
+- [ ] "What You've Accomplished" section present
+- [ ] Quick Reference table present
+- [ ] Common Questions section present
+- [ ] Getting Help section present
+- [ ] Key Takeaways admonition at end
+
+## How-To Structure
+
+```text
+1. Title + Hook (one sentence: "Use the `X` workflow to...")
+2. When to Use This (bullet list of scenarios)
+3. When to Skip This (optional)
+4. Prerequisites (note admonition)
+5. Steps (numbered ### subsections)
+6. What You Get (output/artifacts produced)
+7. Example (optional)
+8. Tips (optional)
+9. Next Steps (optional)
+```
+
+### How-To Checklist
+
+- [ ] Hook starts with "Use the `X` workflow to..."
+- [ ] "When to Use This" has 3-5 bullet points
+- [ ] Prerequisites listed
+- [ ] Steps are numbered `###` subsections with action verbs
+- [ ] "What You Get" describes output artifacts
+
+## Explanation Structure
+
+### Types
+
+| Type              | Example                      |
+| ----------------- | ---------------------------- |
+| **Index/Landing** | `core-concepts/index.md`     |
+| **Concept**       | `what-are-agents.md`         |
+| **Feature**       | `quick-flow.md`              |
+| **Philosophy**    | `why-solutioning-matters.md` |
+| **FAQ**           | `brownfield-faq.md`          |
+
+### General Template
+
+```text
+1. Title + Hook (1-2 sentences)
+2. Overview/Definition (what it is, why it matters)
+3. Key Concepts (### subsections)
+4. Comparison Table (optional)
+5. When to Use / When Not to Use (optional)
+6. Diagram (optional - mermaid, 1 per doc max)
+7. Next Steps (optional)
+```
+
+### Index/Landing Pages
+
+```text
+1. Title + Hook (one sentence)
+2. Content Table (links with descriptions)
+3. Getting Started (numbered list)
+4. Choose Your Path (optional - decision tree)
+```
+
+### Concept Explainers
+
+```text
+1. Title + Hook (what it is)
+2. Types/Categories (### subsections) (optional)
+3. Key Differences Table
+4. Components/Parts
+5. Which Should You Use?
+6. Creating/Customizing (pointer to how-to guides)
+```
+
+### Feature Explainers
+
+```text
+1. Title + Hook (what it does)
+2. Quick Facts (optional - "Perfect for:", "Time to:")
+3. When to Use / When Not to Use
+4. How It Works (mermaid diagram optional)
+5. Key Benefits
+6. Comparison Table (optional)
+7. When to Graduate/Upgrade (optional)
+```
+
+### Philosophy/Rationale Documents
+
+```text
+1. Title + Hook (the principle)
+2. The Problem
+3. The Solution
+4. Key Principles (### subsections)
+5. Benefits
+6. When This Applies
+```
+
+### Explanation Checklist
+
+- [ ] Hook states what document explains
+- [ ] Content in scannable `##` sections
+- [ ] Comparison tables for 3+ options
+- [ ] Diagrams have clear labels
+- [ ] Links to how-to guides for procedural questions
+- [ ] 2-3 admonitions max per document
+
+## Reference Structure
+
+### Types
+
+| Type              | Example               |
+| ----------------- | --------------------- |
+| **Index/Landing** | `workflows/index.md`  |
+| **Catalog**       | `agents/index.md`     |
+| **Deep-Dive**     | `document-project.md` |
+| **Configuration** | `core-tasks.md`       |
+| **Glossary**      | `glossary/index.md`   |
+| **Comprehensive** | `bmgd-workflows.md`   |
+
+### Reference Index Pages
+
+```text
+1. Title + Hook (one sentence)
+2. Content Sections (## for each category)
+   - Bullet list with links and descriptions
+```
+
+### Catalog Reference
+
+```text
+1. Title + Hook
+2. Items (## for each item)
+   - Brief description (one sentence)
+   - **Commands:** or **Key Info:** as flat list
+3. Universal/Shared (## section) (optional)
+```
+
+### Item Deep-Dive Reference
+
+```text
+1. Title + Hook (one sentence purpose)
+2. Quick Facts (optional note admonition)
+   - Module, Command, Input, Output as list
+3. Purpose/Overview (## section)
+4. How to Invoke (code block)
+5. Key Sections (## for each aspect)
+   - Use ### for sub-options
+6. Notes/Caveats (tip or caution admonition)
+```
+
+### Configuration Reference
+
+```text
+1. Title + Hook
+2. Table of Contents (jump links if 4+ items)
+3. Items (## for each config/task)
+   - **Bold summary** — one sentence
+   - **Use it when:** bullet list
+   - **How it works:** numbered steps (3-5 max)
+   - **Output:** expected result (optional)
+```
+
+### Comprehensive Reference Guide
+
+```text
+1. Title + Hook
+2. Overview (## section)
+   - Diagram or table showing organization
+3. Major Sections (## for each phase/category)
+   - Items (### for each item)
+   - Standardized fields: Command, Agent, Input, Output, Description
+4. Next Steps (optional)
+```
+
+### Reference Checklist
+
+- [ ] Hook states what document references
+- [ ] Structure matches reference type
+- [ ] Items use consistent structure throughout
+- [ ] Tables for structured/comparative data
+- [ ] Links to explanation docs for conceptual depth
+- [ ] 1-2 admonitions max
+
+## Glossary Structure
+
+Starlight generates right-side "On this page" navigation from headers:
+
+- Categories as `##` headers — appear in right nav
+- Terms in tables — compact rows, not individual headers
+- No inline TOC — right sidebar handles navigation
+
+### Table Format
+
+```md
+## Category Name
+
+| Term         | Definition                                                                               |
+| ------------ | ---------------------------------------------------------------------------------------- |
+| **Agent**    | Specialized AI persona with specific expertise that guides users through workflows.      |
+| **Workflow** | Multi-step guided process that orchestrates AI agent activities to produce deliverables. |
+```
+
+### Definition Rules
+
+| Do                            | Don't                                       |
+| ----------------------------- | ------------------------------------------- |
+| Start with what it IS or DOES | Start with "This is..." or "A [term] is..." |
+| Keep to 1-2 sentences         | Write multi-paragraph explanations          |
+| Bold term name in cell        | Use plain text for terms                    |
+
+### Context Markers
+
+Add italic context at definition start for limited-scope terms:
+
+- `*Quick Flow only.*`
+- `*BMad Method/Enterprise.*`
+- `*Phase N.*`
+- `*BMGD.*`
+- `*Brownfield.*`
+
+### Glossary Checklist
+
+- [ ] Terms in tables, not individual headers
+- [ ] Terms alphabetized within categories
+- [ ] Definitions 1-2 sentences
+- [ ] Context markers italicized
+- [ ] Term names bolded in cells
+- [ ] No "A [term] is..." definitions
+
+## FAQ Sections
+
+```md
+## Questions
+
+- [Do I always need architecture?](#do-i-always-need-architecture)
+- [Can I change my plan later?](#can-i-change-my-plan-later)
+
+### Do I always need architecture?
+
+Only for BMad Method and Enterprise tracks. Quick Flow skips to implementation.
+
+### Can I change my plan later?
+
+Yes. The SM agent has a `correct-course` workflow for handling scope changes.
+
+**Have a question not answered here?** [Open an issue](...) or ask in [Discord](...).
+```
+
+## Validation Commands
+
+Before submitting documentation changes:
+
+```bash
+npm run docs:fix-links            # Preview link format fixes
+npm run docs:fix-links -- --write # Apply fixes
+npm run docs:validate-links       # Check links exist
+npm run docs:build                # Verify no build errors
+```

docs/downloads.md

@@ -0,0 +1,74 @@
+---
+title: Downloads
+---
+
+Download BMad Method resources for offline use, AI training, or integration.
+
+## Source Bundles
+
+Download these from the `downloads/` folder on the documentation site.
+
+| File               | Description                     |
+| ------------------ | ------------------------------- |
+| `bmad-sources.zip` | Complete BMad source files      |
+| `bmad-prompts.zip` | Agent and workflow prompts only |
+
+## LLM-Optimized Files
+
+These files are designed for AI consumption - perfect for loading into Claude, ChatGPT, or any LLM context window. See [API Access](#api-access) below for URLs.
+
+| File            | Description                         | Use Case                   |
+| --------------- | ----------------------------------- | -------------------------- |
+| `llms.txt`      | Documentation index with summaries  | Quick overview, navigation |
+| `llms-full.txt` | Complete documentation concatenated | Full context loading       |
+
+### Using with LLMs
+
+**Claude Projects:**
+```
+Upload llms-full.txt as project knowledge
+```
+
+**ChatGPT:**
+```
+Paste llms.txt for navigation, or sections from llms-full.txt as needed
+```
+
+**API Usage:**
+```python
+import requests
+docs = requests.get("https://bmad-code-org.github.io/BMAD-METHOD/llms-full.txt").text
+# Include in your system prompt or context
+```
+
+## Installation Options
+
+```bash
+npx bmad-method install
+```
+
+[More details](/docs/how-to/install-bmad.md)
+
+## Version Information
+
+- **Current Version:** See [CHANGELOG](https://github.com/bmad-code-org/BMAD-METHOD/blob/main/CHANGELOG.md)
+- **Release Notes:** Available on [GitHub Releases](https://github.com/bmad-code-org/BMAD-METHOD/releases)
+
+## API Access
+
+For programmatic access to BMad documentation:
+
+```bash
+# Get documentation index
+curl https://bmad-code-org.github.io/BMAD-METHOD/llms.txt
+
+# Get full documentation
+curl https://bmad-code-org.github.io/BMAD-METHOD/llms-full.txt
+```
+
+## Contributing
+
+Want to improve BMad Method? Check out:
+
+- [Contributing Guide](https://github.com/bmad-code-org/BMAD-METHOD/blob/main/CONTRIBUTING.md)
+- [GitHub Repository](https://github.com/bmad-code-org/BMAD-METHOD)

docs/explanation/advanced-elicitation.md

@@ -0,0 +1,24 @@
+---
+title: "Advanced Elicitation"
+description: Push the LLM to rethink its work using structured reasoning methods
+---
+
+Make the LLM reconsider what it just generated. You pick a reasoning method, it applies that method to its own output, you decide whether to keep the improvements.
+
+Dozens of methods are built in - things like First Principles, Red Team vs Blue Team, Pre-mortem Analysis, Socratic Questioning, and more.
+
+## When to Use It
+
+- After a workflow generates content and you want alternatives
+- When output seems okay but you suspect there's more depth
+- To stress-test assumptions or find weaknesses
+- For high-stakes content where rethinking helps
+
+Workflows offer advanced elicitation at decision points - after the LLM has generated something, you'll be asked if you want to run it.
+
+## How It Works
+
+1. LLM suggests 5 relevant methods for your content
+2. You pick one (or reshuffle for different options)
+3. Method is applied, improvements shown
+4. Accept or discard, repeat or continue

docs/explanation/adversarial-review.md

@@ -0,0 +1,57 @@
+---
+title: "Adversarial Review"
+description: Forced reasoning technique that prevents lazy "looks good" reviews
+---
+
+Force deeper analysis by requiring problems to be found.
+
+## What is Adversarial Review?
+
+A review technique where the reviewer *must* find issues. No "looks good" allowed. The reviewer adopts a cynical stance - assume problems exist and find them.
+
+This isn't about being negative. It's about forcing genuine analysis instead of a cursory glance that rubber-stamps whatever was submitted.
+
+**The core rule:** You must find issues. Zero findings triggers a halt - re-analyze or explain why.
+
+## Why It Works
+
+Normal reviews suffer from confirmation bias. You skim the work, nothing jumps out, you approve it. The "find problems" mandate breaks this pattern:
+
+- **Forces thoroughness** - Can't approve until you've looked hard enough to find issues
+- **Catches missing things** - "What's not here?" becomes a natural question
+- **Improves signal quality** - Findings are specific and actionable, not vague concerns
+- **Information asymmetry** - Run reviews with fresh context (no access to original reasoning) so you evaluate the artifact, not the intent
+
+## Where It's Used
+
+Adversarial review appears throughout BMAD workflows - code review, implementation readiness checks, spec validation, and others. Sometimes it's a required step, sometimes optional (like advanced elicitation or party mode). The pattern adapts to whatever artifact needs scrutiny.
+
+## Human Filtering Required
+
+Because the AI is *instructed* to find problems, it will find problems - even when they don't exist. Expect false positives: nitpicks dressed as issues, misunderstandings of intent, or outright hallucinated concerns.
+
+**You decide what's real.** Review each finding, dismiss the noise, fix what matters.
+
+## Example
+
+Instead of:
+
+> "The authentication implementation looks reasonable. Approved."
+
+An adversarial review produces:
+
+> 1. **HIGH** - `login.ts:47` - No rate limiting on failed attempts
+> 2. **HIGH** - Session token stored in localStorage (XSS vulnerable)
+> 3. **MEDIUM** - Password validation happens client-side only
+> 4. **MEDIUM** - No audit logging for failed login attempts
+> 5. **LOW** - Magic number `3600` should be `SESSION_TIMEOUT_SECONDS`
+
+The first review might miss a security vulnerability. The second caught four.
+
+## Iteration and Diminishing Returns
+
+After addressing findings, consider running it again. A second pass usually catches more. A third isn't always useless either. But each pass takes time, and eventually you hit diminishing returns - just nitpicks and false findings.
+
+:::tip[Better Reviews]
+Assume problems exist. Look for what's missing, not just what's wrong.
+:::

docs/explanation/brainstorming.md

@@ -0,0 +1,31 @@
+---
+title: "Brainstorming"
+description: Interactive creative sessions using 60+ proven ideation techniques
+---
+
+Unlock your creativity through guided exploration.
+
+## What is Brainstorming?
+
+Run `brainstorming` and you've got a creative facilitator pulling ideas out of you - not generating them for you. The AI acts as coach and guide, using proven techniques to create conditions where your best thinking emerges.
+
+**Good for:**
+
+- Breaking through creative blocks
+- Generating product or feature ideas
+- Exploring problems from new angles
+- Developing raw concepts into action plans
+
+## How It Works
+
+1. **Setup** - Define topic, goals, constraints
+2. **Choose approach** - Pick techniques yourself, get AI recommendations, go random, or follow a progressive flow
+3. **Facilitation** - Work through techniques with probing questions and collaborative coaching
+4. **Organize** - Ideas grouped into themes and prioritized
+5. **Action** - Top ideas get next steps and success metrics
+
+Everything gets captured in a session document you can reference later or share with stakeholders.
+
+:::note[Your Ideas]
+Every idea comes from you. The workflow creates conditions for insight - you're the source.
+:::

docs/explanation/brownfield-faq.md

@@ -0,0 +1,55 @@
+---
+title: "Brownfield Development FAQ"
+description: Common questions about brownfield development in the BMad Method
+---
+Quick answers to common questions about brownfield (existing codebase) development in the BMad Method (BMM).
+
+## Questions
+
+- [Questions](#questions)
+  - [What is brownfield vs greenfield?](#what-is-brownfield-vs-greenfield)
+  - [Do I have to run document-project for brownfield?](#do-i-have-to-run-document-project-for-brownfield)
+  - [What if I forget to run document-project?](#what-if-i-forget-to-run-document-project)
+  - [Can I use Quick Spec Flow for brownfield projects?](#can-i-use-quick-spec-flow-for-brownfield-projects)
+  - [What if my existing code doesn't follow best practices?](#what-if-my-existing-code-doesnt-follow-best-practices)
+
+### What is brownfield vs greenfield?
+
+- **Greenfield** — New project, starting from scratch, clean slate
+- **Brownfield** — Existing project, working with established codebase and patterns
+
+### Do I have to run document-project for brownfield?
+
+Highly recommended, especially if:
+
+- No existing documentation
+- Documentation is outdated
+- AI agents need context about existing code
+
+You can skip it if you have comprehensive, up-to-date documentation including `docs/index.md` or will use other tools or techniques to aid in discovery for the agent to build on an existing system.
+
+### What if I forget to run document-project?
+
+Don't worry about it - you can do it at any time. You can even do it during or after a project to help keep docs up to date.
+
+### Can I use Quick Spec Flow for brownfield projects?
+
+Yes! Quick Spec Flow works great for brownfield. It will:
+
+- Auto-detect your existing stack
+- Analyze brownfield code patterns
+- Detect conventions and ask for confirmation
+- Generate context-rich tech-spec that respects existing code
+
+Perfect for bug fixes and small features in existing codebases.
+
+### What if my existing code doesn't follow best practices?
+
+Quick Spec Flow detects your conventions and asks: "Should I follow these existing conventions?" You decide:
+
+- **Yes** → Maintain consistency with current codebase
+- **No** → Establish new standards (document why in tech-spec)
+
+BMM respects your choice — it won't force modernization, but it will offer it.
+
+**Have a question not answered here?** Please [open an issue](https://github.com/bmad-code-org/BMAD-METHOD/issues) or ask in [Discord](https://discord.gg/gk8jAdXWmj) so we can add it!

docs/explanation/party-mode.md

@@ -0,0 +1,57 @@
+---
+title: "Party Mode"
+description: Multi-agent collaboration - get all your AI agents in one conversation
+---
+
+Get all your AI agents in one conversation.
+
+## What is Party Mode?
+
+Run `party-mode` and you've got your whole AI team in one room - PM, Architect, Dev, UX Designer, whoever you need. BMad Master orchestrates, picking relevant agents per message. Agents respond in character, agree, disagree, and build on each other's ideas.
+
+The conversation continues as long as you want. Ask follow-ups, push back on answers, redirect the discussion - it's a real back-and-forth with your agents until you're done.
+
+**Good for:**
+
+- Big decisions with tradeoffs
+- Brainstorming sessions
+- Post-mortems when things go wrong
+- Sprint retrospectives and planning
+
+## Examples
+
+### Calling Out Bad Architecture
+
+**You:** "Okay team, our last sprint was a disaster. The authentication service went down three times. Who screwed this up?"
+
+**Architect:** "The design was sound - distributed authentication with proper fallbacks. If implementation deviated from the spec..."
+
+**Dev:** "I followed the architecture doc exactly. The spec didn't account for concurrent session invalidation race conditions."
+
+**PM:** "Both of you missed the bigger issue - we didn't validate session management requirements in the PRD. This is on me for not catching it."
+
+**TEA:** "And I should've caught this in integration tests. The test scenarios didn't cover concurrent invalidation."
+
+### Creative Brainstorming
+
+**You:** "How do we make onboarding feel magical instead of boring?"
+
+**UX Designer:** "Start with progressive disclosure - reveal features as users need them, not all at once in a tutorial."
+
+**Storyteller:** "What if onboarding was a story? Each step reveals a character's journey - the user IS the hero."
+
+**Game Designer:** "Building on that - what if the first 'quest' is actually solving a real user problem? They learn by doing something valuable."
+
+### Technical Decision
+
+**You:** "Monolith or microservices for MVP?"
+
+**Architect:** "Start monolith. Microservices add complexity you don't need at 1000 users."
+
+**PM:** "Agree. Time to market matters more than theoretical scalability."
+
+**Dev:** "Monolith with clear module boundaries. We can extract services later if needed."
+
+:::tip[Better Decisions]
+Better decisions through diverse perspectives. Welcome to party mode.
+:::

docs/explanation/preventing-agent-conflicts.md

@@ -0,0 +1,110 @@
+---
+title: "Preventing Agent Conflicts"
+description: How architecture prevents conflicts when multiple agents implement a system
+---
+
+When multiple AI agents implement different parts of a system, they can make conflicting technical decisions. Architecture documentation prevents this by establishing shared standards.
+
+## Common Conflict Types
+
+### API Style Conflicts
+
+Without architecture:
+- Agent A uses REST with `/users/{id}`
+- Agent B uses GraphQL mutations
+- Result: Inconsistent API patterns, confused consumers
+
+With architecture:
+- ADR specifies: "Use GraphQL for all client-server communication"
+- All agents follow the same pattern
+
+### Database Design Conflicts
+
+Without architecture:
+- Agent A uses snake_case column names
+- Agent B uses camelCase column names
+- Result: Inconsistent schema, confusing queries
+
+With architecture:
+- Standards document specifies naming conventions
+- All agents follow the same patterns
+
+### State Management Conflicts
+
+Without architecture:
+- Agent A uses Redux for global state
+- Agent B uses React Context
+- Result: Multiple state management approaches, complexity
+
+With architecture:
+- ADR specifies state management approach
+- All agents implement consistently
+
+## How Architecture Prevents Conflicts
+
+### 1. Explicit Decisions via ADRs
+
+Every significant technology choice is documented with:
+- Context (why this decision matters)
+- Options considered (what alternatives exist)
+- Decision (what we chose)
+- Rationale (why we chose it)
+- Consequences (trade-offs accepted)
+
+### 2. FR/NFR-Specific Guidance
+
+Architecture maps each functional requirement to technical approach:
+- FR-001: User Management → GraphQL mutations
+- FR-002: Mobile App → Optimized queries
+
+### 3. Standards and Conventions
+
+Explicit documentation of:
+- Directory structure
+- Naming conventions
+- Code organization
+- Testing patterns
+
+## Architecture as Shared Context
+
+Think of architecture as the shared context that all agents read before implementing:
+
+```
+PRD: "What to build"
+     ↓
+Architecture: "How to build it"
+     ↓
+Agent A reads architecture → implements Epic 1
+Agent B reads architecture → implements Epic 2
+Agent C reads architecture → implements Epic 3
+     ↓
+Result: Consistent implementation
+```
+
+## Key ADR Topics
+
+Common decisions that prevent conflicts:
+
+| Topic            | Example Decision                             |
+| ---------------- | -------------------------------------------- |
+| API Style        | GraphQL vs REST vs gRPC                      |
+| Database         | PostgreSQL vs MongoDB                        |
+| Auth             | JWT vs Sessions                              |
+| State Management | Redux vs Context vs Zustand                  |
+| Styling          | CSS Modules vs Tailwind vs Styled Components |
+| Testing          | Jest + Playwright vs Vitest + Cypress        |
+
+## Anti-Patterns to Avoid
+
+:::caution[Common Mistakes]
+- **Implicit Decisions** — "We'll figure out the API style as we go" leads to inconsistency
+- **Over-Documentation** — Documenting every minor choice causes analysis paralysis
+- **Stale Architecture** — Documents written once and never updated cause agents to follow outdated patterns
+:::
+
+:::tip[Correct Approach]
+- Document decisions that cross epic boundaries
+- Focus on conflict-prone areas
+- Update architecture as you learn
+- Use `correct-course` for significant changes
+:::

docs/explanation/quick-flow.md

@@ -0,0 +1,27 @@
+---
+title: "Quick Flow"
+description: Fast-track for small changes - skip the full methodology
+---
+
+Quick Flow is for when you don't need the full BMad Method. Skip Product Brief, PRD, and Architecture - go straight to implementation.
+
+## How It Works
+
+1. **Run `quick-spec`** — generates a focused tech-spec
+2. **Run `quick-dev`** — implements it
+
+That's it.
+
+## When to Use It
+
+- Bug fixes
+- Refactoring
+- Small features
+- Prototyping
+
+## When to Use Full BMad Method Instead
+
+- New products
+- Major features
+- Multiple teams involved
+- Stakeholder alignment needed

docs/explanation/why-solutioning-matters.md

@@ -0,0 +1,75 @@
+---
+title: "Why Solutioning Matters"
+description: Understanding why the solutioning phase is critical for multi-epic projects
+---
+
+
+Phase 3 (Solutioning) translates **what** to build (from Planning) into **how** to build it (technical design). This phase prevents agent conflicts in multi-epic projects by documenting architectural decisions before implementation begins.
+
+## The Problem Without Solutioning
+
+```
+Agent 1 implements Epic 1 using REST API
+Agent 2 implements Epic 2 using GraphQL
+Result: Inconsistent API design, integration nightmare
+```
+
+When multiple agents implement different parts of a system without shared architectural guidance, they make independent technical decisions that may conflict.
+
+## The Solution With Solutioning
+
+```
+architecture workflow decides: "Use GraphQL for all APIs"
+All agents follow architecture decisions
+Result: Consistent implementation, no conflicts
+```
+
+By documenting technical decisions explicitly, all agents implement consistently and integration becomes straightforward.
+
+## Solutioning vs Planning
+
+| Aspect   | Planning (Phase 2)      | Solutioning (Phase 3)             |
+| -------- | ----------------------- | --------------------------------- |
+| Question | What and Why?           | How? Then What units of work?     |
+| Output   | FRs/NFRs (Requirements) | Architecture + Epics/Stories      |
+| Agent    | PM                      | Architect → PM                    |
+| Audience | Stakeholders            | Developers                        |
+| Document | PRD (FRs/NFRs)          | Architecture + Epic Files         |
+| Level    | Business logic          | Technical design + Work breakdown |
+
+## Key Principle
+
+**Make technical decisions explicit and documented** so all agents implement consistently.
+
+This prevents:
+- API style conflicts (REST vs GraphQL)
+- Database design inconsistencies
+- State management disagreements
+- Naming convention mismatches
+- Security approach variations
+
+## When Solutioning is Required
+
+| Track | Solutioning Required? |
+|-------|----------------------|
+| Quick Flow | No - skip entirely |
+| BMad Method Simple | Optional |
+| BMad Method Complex | Yes |
+| Enterprise | Yes |
+
+:::tip[Rule of Thumb]
+If you have multiple epics that could be implemented by different agents, you need solutioning.
+:::
+
+## The Cost of Skipping
+
+Skipping solutioning on complex projects leads to:
+
+- **Integration issues** discovered mid-sprint
+- **Rework** due to conflicting implementations
+- **Longer development time** overall
+- **Technical debt** from inconsistent patterns
+
+:::caution[Cost Multiplier]
+Catching alignment issues in solutioning is 10× faster than discovering them during implementation.
+:::

docs/how-to/brownfield/index.md

@@ -0,0 +1,84 @@
+---
+title: "Brownfield Development"
+description: How to use BMad Method on existing codebases
+---
+
+Use BMad Method effectively when working on existing projects and legacy codebases.
+
+## What is Brownfield Development?
+
+**Brownfield** refers to working on existing projects with established codebases and patterns, as opposed to **greenfield** which means starting from scratch with a clean slate.
+
+This guide covers the essential workflow for onboarding to brownfield projects with BMad Method.
+
+:::note[Prerequisites]
+- BMad Method installed (`npx bmad-method install`)
+- An existing codebase you want to work on
+- Access to an AI-powered IDE (Claude Code, Cursor, or Windsurf)
+:::
+
+## Step 1: Clean Up Completed Planning Artifacts
+
+If you have completed all PRD epics and stories through the BMad process, clean up those files. Archive them, delete them, or rely on version history if needed. Do not keep these files in:
+
+- `docs/`
+- `_bmad-output/planning-artifacts/`
+- `_bmad-output/implementation-artifacts/`
+
+## Step 2: Maintain Quality Project Documentation
+
+Your `docs/` folder should contain succinct, well-organized documentation that accurately represents your project:
+
+- Intent and business rationale
+- Business rules
+- Architecture
+- Any other relevant project information
+
+For complex projects, consider using the `document-project` workflow. It offers runtime variants that will scan your entire project and document its actual current state.
+
+## Step 3: Get Help
+
+Get help to know what to do next based on your unique needs
+
+Run `bmad-help` to get guidance when you are not sure what to do next.
+
+### Choosing Your Approach
+
+You have two primary options depending on the scope of changes:
+
+| Scope                          | Recommended Approach                                                                                                          |
+| ------------------------------ | ----------------------------------------------------------------------------------------------------------------------------- |
+| **Small updates or additions** | Use `quick-flow-solo-dev` to create a tech-spec and implement the change. The full four-phase BMad method is likely overkill. |
+| **Major changes or additions** | Start with the BMad method, applying as much or as little rigor as needed.                                                    |
+
+### During PRD Creation
+
+When creating a brief or jumping directly into the PRD, ensure the agent:
+
+- Finds and analyzes your existing project documentation
+- Reads the proper context about your current system
+
+You can guide the agent explicitly, but the goal is to ensure the new feature integrates well with your existing system.
+
+### UX Considerations
+
+UX work is optional. The decision depends not on whether your project has a UX, but on:
+
+- Whether you will be working on UX changes
+- Whether significant new UX designs or patterns are needed
+
+If your changes amount to simple updates to existing screens you are happy with, a full UX process is unnecessary.
+
+### Architecture Considerations
+
+When doing architecture, ensure the architect:
+
+- Uses the proper documented files
+- Scans the existing codebase
+
+Pay close attention here to prevent reinventing the wheel or making decisions that misalign with your existing architecture.
+
+## More Information
+
+- **[Quick Fix in Brownfield](/docs/how-to/brownfield/quick-fix-in-brownfield.md)** - Bug fixes and ad-hoc changes
+- **[Brownfield FAQ](/docs/explanation/brownfield-faq.md)** - Common questions about brownfield development

docs/how-to/brownfield/quick-fix-in-brownfield.md

@@ -0,0 +1,76 @@
+---
+title: "How to Make Quick Fixes in Brownfield Projects"
+description: How to make quick fixes and ad-hoc changes in brownfield projects
+---
+
+Use the **DEV agent** directly for bug fixes, refactorings, or small targeted changes that don't require the full BMad method or Quick Flow.
+
+## When to Use This
+
+- Simple bug fixes
+- Small refactorings and changes that don't need extensive ideation, planning, or architectural shifts
+- Larger refactorings or improvement with built in tool planning and execution mode combination, or better yet use quick flow
+- Learning about your codebase
+
+## Steps
+
+### 1. Load an Agent
+
+For quick fixes, you can use:
+
+- **DEV agent** - For implementation-focused work
+- **Quick Flow Solo Dev** - For slightly larger changes that still need a quick-spec to keep the agent aligned to planning and standards
+
+### 2. Describe the Change
+
+Simply tell the agent what you need:
+
+```
+Fix the login validation bug that allows empty passwords
+```
+
+or
+
+```
+Refactor the UserService to use async/await instead of callbacks
+```
+
+### 3. Let the Agent Work
+
+The agent will:
+
+- Analyze the relevant code
+- Propose a solution
+- Implement the change
+- Run tests (if available)
+
+### 4. Review and Commit
+
+Review the changes made and commit when satisfied.
+
+## Learning Your Codebase
+
+This approach is also excellent for exploring unfamiliar code:
+
+```
+Explain how the authentication system works in this codebase
+```
+
+```
+Show me where error handling happens in the API layer
+```
+
+LLMs are excellent at interpreting and analyzing code, whether it was AI-generated or not. Use the agent to:
+
+- Learn about your project
+- Understand how things are built
+- Explore unfamiliar parts of the codebase
+
+## When to Upgrade to Formal Planning
+
+Consider using Quick Flow or full BMad Method when:
+
+- The change affects multiple files or systems
+- You're unsure about the scope
+- The fix keeps growing in complexity
+- You need documentation for the change

docs/how-to/customize-bmad.md

@@ -0,0 +1,158 @@
+---
+title: "BMad Method Customization Guide"
+---
+
+The ability to customize the BMad Method and its core to your needs, while still being able to get updates and enhancements is a critical idea within the BMad Ecosystem.
+
+The Customization Guidance outlined here, while targeted at understanding BMad Method customization, applies to any other module use within the BMad Method.
+
+## Types of Customization
+
+Customization includes Agent Customization, Workflow/Skill customization, the addition of new MCPs or Skills to be used by existing agents. Aside from all of this, a whole other realm of customization involves creating / adding your own relevant BMad Builder workflows, skills, agents and maybe even your own net new modules to compliment the BMad Method Module.
+
+Warning: The reason for customizing as this guide will prescribe will allow you to continue getting updates without worrying about losing your customization changes. And by continuing to get updates as BMad modules advance, you will be able to continue to evolve as the system improves.
+
+## Agent Customization
+
+### Agent Customization Areas
+
+- Change agent names, personas or manner of speech
+- Add project-specific memories or context
+- Add custom menu items to custom or inline prompts, skills or custom BMad workflows
+- Define critical actions that occur agent startup for consistent behavior
+
+## How to customize an agent.
+
+**1. Locate Customization Files**
+
+After installation, find agent customization files in:
+
+```
+_bmad/_config/agents/
+├── core-bmad-master.customize.yaml
+├── bmm-dev.customize.yaml
+├── bmm-pm.customize.yaml
+└── ... (one file per installed agent)
+```
+
+**2. Edit Any Agent**
+
+Open the `.customize.yaml` file for the agent you want to modify. All sections are optional - customize only what you need.
+
+**3. Rebuild the Agent**
+
+After editing, IT IS CRITICAL to rebuild the agent to apply changes:
+
+```bash
+npx bmad-method install
+```
+
+You can either then:
+
+- Select `Quick Update` - This will also ensure all packages are up to date AND compile all agents to include any updates or customizations
+- Select `Rebuild Agents` - This will only rebuild and apply customizations to agents, without pulling the latest
+
+There will be additional tools shortly after beta launch to allow install of individual agents, workflows, skills and modules without the need for using the full bmad installer.
+
+### What Agent Properties Can Be Customized?
+
+#### Agent Name
+
+Change how the agent introduces itself:
+
+```yaml
+agent:
+  metadata:
+    name: 'Spongebob' # Default: "Amelia"
+```
+
+#### Persona
+
+Replace the agent's personality, role, and communication style:
+
+```yaml
+persona:
+  role: 'Senior Full-Stack Engineer'
+  identity: 'Lives in a pineapple (under the sea)'
+  communication_style: 'Spongebob annoying'
+  principles:
+    - 'Never Nester, Spongebob Devs hate nesting more than 2 levels deep'
+    - 'Favor composition over inheritance'
+```
+
+**Note:** The persona section replaces the entire default persona (not merged).
+
+#### Memories
+
+Add persistent context the agent will always remember:
+
+```yaml
+memories:
+  - 'Works at Krusty Krab'
+  - 'Favorite Celebrity: David Hasslehoff'
+  - 'Learned in Epic 1 that its not cool to just pretend that tests have passed'
+```
+
+### Custom Menu Items
+
+Any custom items you add here will be included in the agents display menu.
+
+```yaml
+menu:
+  - trigger: my-workflow
+    workflow: '{project-root}/my-custom/workflows/my-workflow.yaml'
+    description: My custom workflow
+  - trigger: deploy
+    action: '#deploy-prompt'
+    description: Deploy to production
+```
+
+### Critical Actions
+
+Add instructions that execute before the agent starts:
+
+```yaml
+critical_actions:
+  - 'Check the CI Pipelines with the XYZ Skill and alert user on wake if anything is urgently needing attention'
+```
+
+### Custom Prompts
+
+Define reusable prompts for `action="#id"` menu handlers:
+
+```yaml
+prompts:
+  - id: deploy-prompt
+    content: |
+      Deploy the current branch to production:
+      1. Run all tests
+      2. Build the project
+      3. Execute deployment script
+```
+
+## Troubleshooting
+
+**Changes not appearing?**
+
+- Make sure you ran `npx bmad-method build <agent-name>` after editing
+- Check YAML syntax is valid (indentation matters!)
+- Verify the agent name matches the file name pattern
+
+**Agent not loading?**
+
+- Check for YAML syntax errors
+- Ensure required fields aren't left empty if you uncommented them
+- Try reverting to the template and rebuilding
+
+**Need to reset?**
+
+- Remove content from the `.customize.yaml` file (or delete the file)
+- Run `npx bmad-method build <agent-name>` to regenerate defaults
+
+## Workflow Customization
+
+Information about customizing existing BMad Method workflows and skills are coming soon.
+
+## Module Customization
+
+Information on how to build expansion modules that augment BMad, or make other existing module customizations are coming soon.

docs/how-to/get-answers-about-bmad.md

@@ -0,0 +1,102 @@
+---
+title: "How to Get Answers About BMad"
+description: Use an LLM to quickly answer your own BMad questions
+---
+
+If you have successfully installed BMad and the BMad Method (+ other modules as needed) - the first step in getting answers is `/bmad-help`. This will answer upwards of 80% of all questions and is available to you in the IDE as you are working.
+
+## When to Use This
+
+- You have a question about how BMad works or what to do next with BMad
+- You want to understand a specific agent or workflow
+- You need quick answers without waiting for Discord
+
+:::note[Prerequisites]
+An AI tool (Claude Code, Cursor, ChatGPT, Claude.ai, etc.) and either BMad installed in your project or access to the GitHub repo.
+:::
+
+## Steps
+
+### 1. Choose Your Source
+
+| Source               | Best For                                  | Examples                     |
+| -------------------- | ----------------------------------------- | ---------------------------- |
+| **`_bmad` folder**   | How BMad works—agents, workflows, prompts | "What does the PM agent do?" |
+| **Full GitHub repo** | History, installer, architecture          | "What changed in v6?"        |
+| **`llms-full.txt`**  | Quick overview from docs                  | "Explain BMad's four phases" |
+
+The `_bmad` folder is created when you install BMad. If you don't have it yet, clone the repo instead.
+
+### 2. Point Your AI at the Source
+
+**If your AI can read files (Claude Code, Cursor, etc.):**
+
+- **BMad installed:** Point at the `_bmad` folder and ask directly
+- **Want deeper context:** Clone the [full repo](https://github.com/bmad-code-org/BMAD-METHOD)
+
+**If you use ChatGPT or Claude.ai:**
+
+Fetch `llms-full.txt` into your session:
+
+```
+https://bmad-code-org.github.io/BMAD-METHOD/llms-full.txt
+```
+
+See the [Downloads page](/docs/downloads.md) for other downloadable resources.
+
+### 3. Ask Your Question
+
+:::note[Example]
+**Q:** "Tell me the fastest way to build something with BMad"
+
+**A:** Use Quick Flow: Run `quick-spec` to write a technical specification, then `quick-dev` to implement it—skipping the full planning phases.
+:::
+
+## What You Get
+
+Direct answers about BMad—how agents work, what workflows do, why things are structured the way they are—without waiting for someone else to respond.
+
+## Tips
+
+- **Verify surprising answers** — LLMs occasionally get things wrong. Check the source file or ask on Discord.
+- **Be specific** — "What does step 3 of the PRD workflow do?" beats "How does PRD work?"
+
+## Still Stuck?
+
+Tried the LLM approach and still need help? You now have a much better question to ask.
+
+| Channel                   | Use For                                     |
+| ------------------------- | ------------------------------------------- |
+| `#bmad-method-help`       | Quick questions (real-time chat)            |
+| `help-requests` forum     | Detailed questions (searchable, persistent) |
+| `#suggestions-feedback`   | Ideas and feature requests                  |
+| `#report-bugs-and-issues` | Bug reports                                 |
+
+**Discord:** [discord.gg/gk8jAdXWmj](https://discord.gg/gk8jAdXWmj)
+
+**GitHub Issues:** [github.com/bmad-code-org/BMAD-METHOD/issues](https://github.com/bmad-code-org/BMAD-METHOD/issues) (for clear bugs)
+
+*You!*
+        *Stuck*
+             *in the queue—*
+                      *waiting*
+                              *for who?*
+
+*The source*
+        *is there,*
+                *plain to see!*
+
+*Point*
+     *your machine.*
+              *Set it free.*
+
+*It reads.*
+        *It speaks.*
+                *Ask away—*
+
+*Why wait*
+        *for tomorrow*
+                *when you have*
+                        *today?*
+
+*—Claude*

docs/how-to/install-bmad.md

@@ -0,0 +1,82 @@
+---
+title: "How to Install BMad"
+description: Step-by-step guide to installing BMad in your project
+---
+
+Use the `npx bmad-method install` command to set up BMad in your project with your choice of modules and AI tools.
+
+## When to Use This
+
+- Starting a new project with BMad
+- Adding BMad to an existing codebase
+- Update the existing BMad Installation
+
+:::note[Prerequisites]
+- **Node.js** 20+ (required for the installer)
+- **Git** (recommended)
+- **AI tool** (Claude Code, Cursor, Windsurf, or similar)
+:::
+
+## Steps
+
+### 1. Run the Installer
+
+```bash
+npx bmad-method install
+```
+
+### 2. Choose Installation Location
+
+The installer will ask where to install BMad files:
+
+- Current directory (recommended for new projects if you created the directory yourself and ran from within the directory)
+- Custom path
+
+### 3. Select Your AI Tools
+
+Pick which AI tools you use:
+
+- Claude Code
+- Cursor
+- Windsurf
+- Others
+
+Each tool has its own way of integrating commands. The installer creates tiny prompt files to activate workflows and agents — it just puts them where your tool expects to find them.
+
+### 4. Choose Modules
+
+The installer shows available modules. Select whichever ones you need — most users just want **BMad Method** (the software development module).
+
+### 5. Follow the Prompts
+
+The installer guides you through the rest — custom content, settings, etc.
+
+## What You Get
+
+```
+your-project/
+├── _bmad/
+│   ├── bmm/            # Your selected modules
+│   │   └── config.yaml # Module settings (if you ever need to change them)
+│   ├── core/           # Required core module
+│   └── ...
+├── _bmad-output/       # Generated artifacts
+└── .claude/            # Claude Code commands (if using Claude Code)
+```
+
+## Verify Installation
+
+Run the `help` workflow (`/bmad-help` on most platforms) to verify everything works and see what to do next.
+
+**Latest from main branch:**
+```bash
+npx github:bmad-code-org/BMAD-METHOD install
+```
+
+Use these if you want the newest features before they're officially released. Things might break.
+
+## Troubleshooting
+
+**Installer throws an error** — Copy-paste the output into your AI assistant and let it figure it out.
+
+**Installer worked but something doesn't work later** — Your AI needs BMad context to help. See [How to Get Answers About BMad](/docs/how-to/get-answers-about-bmad.md) for how to point your AI at the right sources.

docs/how-to/shard-large-documents.md

@@ -0,0 +1,101 @@
+---
+title: "Document Sharding Guide"
+---
+
+Use the `shard-doc` tool to split large markdown files into smaller, organized files for better context management.
+
+## When to Use This
+
+- Very large complex PRDs
+- Architecture documents with multiple system layers
+- Epic files with 4+ epics (especially for Phase 4)
+- UX design specs covering multiple subsystems
+
+## What is Document Sharding?
+
+Document sharding splits large markdown files into smaller, organized files based on level 2 headings (`## Heading`). This enables:
+
+- **Selective Loading** - Workflows load only the sections they need
+- **Reduced Token Usage** - Massive efficiency gains for large projects
+- **Better Organization** - Logical section-based file structure
+- **Maintained Context** - Index file preserves document structure
+
+### Architecture
+
+```
+Before Sharding:
+docs/
+└── PRD.md (large 50k token file)
+
+After Sharding:
+docs/
+└── prd/
+    ├── index.md                    # Table of contents with descriptions
+    ├── overview.md                 # Section 1
+    ├── user-requirements.md        # Section 2
+    ├── technical-requirements.md   # Section 3
+    └── ...                         # Additional sections
+```
+
+## Steps
+
+### 1. Run the Shard-Doc Tool
+
+```bash
+/bmad:core:tools:shard-doc
+```
+
+### 2. Follow the Interactive Process
+
+```
+Agent: Which document would you like to shard?
+User: docs/PRD.md
+
+Agent: Default destination: docs/prd/
+       Accept default? [y/n]
+User: y
+
+Agent: Sharding PRD.md...
+       ✓ Created 12 section files
+       ✓ Generated index.md
+       ✓ Complete!
+```
+
+## What You Get
+
+**index.md structure:**
+
+```markdown
+
+## Sections
+
+1. [Overview](./overview.md) - Project vision and objectives
+2. [User Requirements](./user-requirements.md) - Feature specifications
+3. [Epic 1: Authentication](./epic-1-authentication.md) - User auth system
+4. [Epic 2: Dashboard](./epic-2-dashboard.md) - Main dashboard UI
+   ...
+```
+
+**Individual section files:**
+
+- Named from heading text (kebab-case)
+- Contains complete section content
+- Preserves all markdown formatting
+- Can be read independently
+
+## How Workflow Discovery Works
+
+BMad workflows use a **dual discovery system**:
+
+1. **Try whole document first** - Look for `document-name.md`
+2. **Check for sharded version** - Look for `document-name/index.md`
+3. **Priority rule** - Whole document takes precedence if both exist - remove the whole document if you want the sharded to be used instead
+
+## Workflow Support
+
+All BMM workflows support both formats:
+
+- Whole documents
+- Sharded documents
+- Automatic detection
+- Transparent to user

docs/how-to/upgrade-to-v6.md

@@ -0,0 +1,131 @@
+---
+title: "How to Upgrade to v6"
+description: Migrate from BMad v4 to v6
+---
+
+Use the BMad installer to upgrade from v4 to v6, which includes automatic detection of legacy installations and migration assistance.
+
+## When to Use This
+
+- You have BMad v4 installed (`.bmad-method` folder)
+- You want to migrate to the new v6 architecture
+- You have existing planning artifacts to preserve
+
+:::note[Prerequisites]
+- Node.js 20+
+- Existing BMad v4 installation
+:::
+
+## Steps
+
+### 1. Run the Installer
+
+```bash
+npx bmad-method install
+```
+
+The installer automatically detects:
+
+- **Legacy v4 folder**: `.bmad-method`
+- **IDE command artifacts**: Legacy bmad folders in `.claude/commands/`, `.cursor/commands/`, etc.
+
+### 2. Handle Legacy Installation
+
+When v4 is detected, you can:
+
+- Allow the installer to back up and remove `.bmad-method`
+- Exit and handle cleanup manually
+- Keep both (not recommended for same project)
+
+### 3. Clean Up IDE Commands
+
+Manually remove legacy v4 IDE commands:
+
+- `.claude/commands/BMad/agents`
+- `.claude/commands/BMad/tasks`
+
+New v6 commands will be at `.claude/commands/bmad/<module>/agents|workflows`.
+
+:::tip[Accidentally Deleted Commands?]
+If you delete the wrong commands, rerun the installer and choose "quick update" to restore them.
+:::
+
+### 4. Migrate Planning Artifacts
+
+**If you have planning documents (Brief/PRD/UX/Architecture):**
+
+Move them to `_bmad-output/planning-artifacts/` with descriptive names:
+
+- Include `PRD` in filename for PRD documents
+- Include `brief`, `architecture`, or `ux-design` accordingly
+- Sharded documents can be in named subfolders
+
+**If you're mid-planning:** Consider restarting with v6 workflows. Use your existing documents as inputs—the new progressive discovery workflows with web search and IDE plan mode produce better results.
+
+### 5. Migrate In-Progress Development
+
+If you have stories created or implemented:
+
+1. Complete the v6 installation
+2. Place `epics.md` or `epics/epic*.md` in `_bmad-output/planning-artifacts/`
+3. Run the Scrum Master's `sprint-planning` workflow
+4. Tell the SM which epics/stories are already complete
+
+### 6. Migrate Agent Customizations
+
+**v4:** Modified agent files directly in `_bmad-*` folders
+
+**v6:** All customizations go in `_bmad/_config/agents/` using customize files:
+
+```yaml
+# _bmad/_config/agents/bmm-pm.customize.yaml
+persona:
+  name: 'Captain Jack'
+  role: 'Swashbuckling Product Owner'
+  communication_style: |
+    - Talk like a pirate
+    - Use nautical metaphors
+```
+
+After modifying customization files, rerun the installer and choose "rebuild all agents" or "quick update".
+
+## What You Get
+
+**v6 unified structure:**
+
+```
+your-project/
+└── _bmad/               # Single installation folder
+    ├── _config/         # Your customizations
+    │   └── agents/      # Agent customization files
+    ├── core/            # Universal core framework
+    ├── bmm/             # BMad Method module
+    ├── bmb/             # BMad Builder
+    └── cis/             # Creative Intelligence Suite
+├── _bmad-output/        # Output folder (was doc folder in v4)
+```
+
+## Module Migration
+
+| v4 Module | v6 Status |
+|-----------|-----------|
+| `_bmad-2d-phaser-game-dev` | Integrated into BMGD Module |
+| `_bmad-2d-unity-game-dev` | Integrated into BMGD Module |
+| `_bmad-godot-game-dev` | Integrated into BMGD Module |
+| `_bmad-infrastructure-devops` | Deprecated — new DevOps agent coming soon |
+| `_bmad-creative-writing` | Not adapted — new v6 module coming soon |
+
+## Key Changes
+
+| Concept | v4 | v6 |
+|---------|----|----|
+| **Core** | `_bmad-core` was actually BMad Method | `_bmad/core/` is universal framework |
+| **Method** | `_bmad-method` | `_bmad/bmm/` |
+| **Config** | Modified files directly | `config.yaml` per module |
+| **Documents** | Sharded or unsharded required setup | Fully flexible, auto-scanned |
+
+## Tips
+
+- **Back up first** — Keep your v4 installation until you verify v6 works
+- **Use v6 workflows** — Even partial planning docs benefit from v6's improved discovery
+- **Rebuild after customizing** — Always run the installer after changing customize files

docs/index.md

@@ -0,0 +1,56 @@
+---
+title: Welcome to the BMad Method
+---
+
+The BMad Method (**B**reakthrough **M**ethod of **A**gile AI **D**riven Development) is an AI-driven development framework that helps you build software faster and smarter. It provides specialized AI agents, guided workflows, and intelligent planning that adapts to your project's complexity—whether you're fixing a bug or building an enterprise platform.
+
+If you're comfortable working with AI coding assistants like Claude, Cursor, or GitHub Copilot, you're ready to get started.
+
+---
+
+## New Here? Start with a Tutorial
+
+The fastest way to understand BMad is to try it.
+
+- **[Get Started with BMad](/docs/tutorials/getting-started.md)** — Install and understand how BMad works
+- **[Workflow Map](/docs/reference/workflow-map.md)** — Visual overview of BMM phases, workflows, and context management.
+
+## How to Use These Docs
+
+These docs are organized into four sections based on what you're trying to do:
+
+| Section           | Purpose                                                                                                    |
+| ----------------- | ---------------------------------------------------------------------------------------------------------- |
+| **Tutorials**     | Learning-oriented. Step-by-step guides that walk you through building something. Start here if you're new. |
+| **How-To Guides** | Task-oriented. Practical guides for solving specific problems. "How do I customize an agent?" lives here.  |
+| **Explanation**   | Understanding-oriented. Deep dives into concepts and architecture. Read when you want to know *why*.       |
+| **Reference**     | Information-oriented. Technical specifications for agents, workflows, and configuration.                   |
+
+---
+
+## What You'll Need
+
+BMad works with any AI coding assistant that supports custom system prompts or project context. Popular options include:
+
+- **[Claude Code](https://code.claude.com)** — Anthropic's CLI tool (recommended)
+- **[Cursor](https://cursor.sh)** — AI-first code editor
+- **[Windsurf](https://codeium.com/windsurf)** — Codeium's AI IDE
+- **[Roo Code](https://roocode.com)** — VS Code extension
+
+You should be comfortable with basic software development concepts like version control, project structure, and agile workflows. No prior experience with BMad-style agent systems is required—that's what these docs are for.
+
+---
+
+## Join the Community
+
+Get help, share what you're building, or contribute to BMad:
+
+- **[Discord](https://discord.gg/gk8jAdXWmj)** — Chat with other BMad users, ask questions, share ideas
+- **[GitHub](https://github.com/bmad-code-org/BMAD-METHOD)** — Source code, issues, and contributions
+- **[YouTube](https://www.youtube.com/@BMadCode)** — Video tutorials and walkthroughs
+
+---
+
+## Next Step
+
+Ready to dive in? **[Get Started with BMad](/docs/tutorials/getting-started.md)** and build your first project.

docs/reference/workflow-map.md

@@ -0,0 +1,86 @@
+---
+title: "Workflow Map"
+description: Visual reference for BMad Method workflow phases and outputs
+---
+
+The BMad Method (BMM) is a module in the BMad Ecosystem, targeted at following the best practices of context engineering and planning. AI agents work best with clear, structured context. The BMM system builds that context progressively across 4 distinct phases - each phase, and multiple workflows optionally within each phase, produce documents that inform the next, so agents always know what to build and why.
+
+The rationale and concepts come from agile methodologies that have been used across the industry with great success as a mental framework.
+
+If at anytime you are unsure what to do, the `/bmad-help` command will help you stay on track or know what to do next. You can always refer to this for reference also - but /bmad-help is fully interactive and much quicker if you have already installed the BMadMethod. Additionally, if you are using different modules that have extended the BMad Method or added other complimentary non extension modules - the /bmad-help evolves to know all that is available to give you the best in the moment advice.
+
+Final important note: Every workflow below can be run directly with your tool of choice via slash command or by loading an agent first and using the entry from the agents menu.
+
+<iframe src="/workflow-map-diagram.html" width="100%" height="100%" frameborder="0" style="border-radius: 8px; border: 1px solid #334155; min-height: 900px;"></iframe>
+
+*[Interactive diagram - hover over outputs to see artifact flows]*
+
+## Phase 1: Analysis (Optional)
+
+Explore the problem space and validate ideas before committing to planning.
+
+| Workflow               | Purpose                                                                    | Produces                  |
+| ---------------------- | -------------------------------------------------------------------------- | ------------------------- |
+| `brainstorm`           | Brainstorm Project Ideas with guided facilitation of a brainstorming coach | `brainstorming-report.md` |
+| `research`             | Validate market, technical, or domain assumptions                          | Research findings         |
+| `create-product-brief` | Capture strategic vision                                                   | `product-brief.md`        |
+
+## Phase 2: Planning
+
+Define what to build and for whom.
+
+| Workflow           | Purpose                                  | Produces     |
+| ------------------ | ---------------------------------------- | ------------ |
+| `create-prd`       | Define requirements (FRs/NFRs)           | `PRD.md`     |
+| `create-ux-design` | Design user experience (when UX matters) | `ux-spec.md` |
+
+## Phase 3: Solutioning
+
+Decide how to build it and break work into stories.
+
+| Workflow                         | Purpose                                    | Produces                    |
+| -------------------------------- | ------------------------------------------ | --------------------------- |
+| `create-architecture`            | Make technical decisions explicit          | `architecture.md` with ADRs |
+| `create-epics-and-stories`       | Break requirements into implementable work | Epic files with stories     |
+| `check-implementation-readiness` | Gate check before implementation           | PASS/CONCERNS/FAIL decision |
+
+## Phase 4: Implementation
+
+Build it, one story at a time.
+
+| Workflow          | Purpose                                | Produces                      |
+| ----------------- | -------------------------------------- | ----------------------------- |
+| `sprint-planning` | Initialize tracking (once per project) | `sprint-status.yaml`          |
+| `create-story`    | Prepare next story for implementation  | `story-[slug].md`             |
+| `dev-story`       | Implement the story                    | Working code + tests          |
+| `automate` (QA)   | Generate tests for existing features   | Test suite                    |
+| `code-review`     | Validate implementation quality        | Approved or changes requested |
+| `correct-course`  | Handle significant mid-sprint changes  | Updated plan or re-routing    |
+| `retrospective`   | Review after epic completion           | Lessons learned               |
+
+**Quinn (QA Agent):** Built-in QA agent for test automation. Trigger with `QA` or `bmad-bmm-automate`. Generates standard API and E2E tests using your project's test framework. Beginner-friendly, no configuration needed. For advanced test strategy, install [Test Architect (TEA)](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/) module.
+
+## Quick Flow (Parallel Track)
+
+Skip phases 1-3 for small, well-understood work.
+
+| Workflow     | Purpose                                    | Produces                                      |
+| ------------ | ------------------------------------------ | --------------------------------------------- |
+| `quick-spec` | Define an ad-hoc change                    | `tech-spec.md` (story file for small changes) |
+| `quick-dev`  | Implement from spec or direct instructions | Working code + tests                          |
+
+## Context Management
+
+Each document becomes context for the next phase. The PRD tells the architect what constraints matter. The architecture tells the dev agent which patterns to follow. Story files give focused, complete context for implementation. Without this structure, agents make inconsistent decisions.
+
+For brownfield projects, `document-project` creates or updates `project-context.md` - what exists in the codebase and the rules all implementation workflows must observe. Run it just before Phase 4, and again when something significant changes - structure, architecture, or those rules. You can also edit `project-context.md` by hand.
+
+All implementation workflows load `project-context.md` if it exists. Additional context per workflow:
+
+| Workflow       | Also Loads                   |
+| -------------- | ---------------------------- |
+| `create-story` | epics, PRD, architecture, UX |
+| `dev-story`    | story file                   |
+| `code-review`  | architecture, story file     |
+| `quick-spec`   | planning docs (if exist)     |
+| `quick-dev`    | tech-spec                    |

docs/templates/api-reference.md

@@ -1,71 +0,0 @@
-# {Project Name} API Reference
-
-## External APIs Consumed
-
-{Repeat this section for each external API the system interacts with.}
-
-### {External Service Name} API
-
-- **Purpose:** {Why does the system use this API?}
-- **Base URL(s):**
-  - Production: `{URL}`
-  - Staging/Dev: `{URL}`
-- **Authentication:** {Describe method - e.g., API Key in Header (Header Name: `X-API-Key`), OAuth 2.0 Client Credentials, Basic Auth. Reference `docs/environment-vars.md` for key names.}
-- **Key Endpoints Used:**
-  - **`{HTTP Method} {/path/to/endpoint}`:**
-    - Description: {What does this endpoint do?}
-    - Request Parameters: {Query params, path params}
-    - Request Body Schema: {Provide JSON schema or link to `docs/data-models.md`}
-    - Example Request: `{Code block}`
-    - Success Response Schema (Code: `200 OK`): {JSON schema or link}
-    - Error Response Schema(s) (Codes: `4xx`, `5xx`): {JSON schema or link}
-    - Example Response: `{Code block}`
-  - **`{HTTP Method} {/another/endpoint}`:** {...}
-- **Rate Limits:** {If known}
-- **Link to Official Docs:** {URL}
-
-### {Another External Service Name} API
-
-{...}
-
-## Internal APIs Provided (If Applicable)
-
-{If the system exposes its own APIs (e.g., in a microservices architecture or for a UI frontend). Repeat for each API.}
-
-### {Internal API / Service Name} API
-
-- **Purpose:** {What service does this API provide?}
-- **Base URL(s):** {e.g., `/api/v1/...`}
-- **Authentication/Authorization:** {Describe how access is controlled.}
-- **Endpoints:**
-  - **`{HTTP Method} {/path/to/endpoint}`:**
-    - Description: {What does this endpoint do?}
-    - Request Parameters: {...}
-    - Request Body Schema: {...}
-    - Success Response Schema (Code: `200 OK`): {...}
-    - Error Response Schema(s) (Codes: `4xx`, `5xx`): {...}
-  - **`{HTTP Method} {/another/endpoint}`:** {...}
-
-## AWS Service SDK Usage (or other Cloud Providers)
-
-{Detail interactions with cloud provider services via SDKs.}
-
-### {AWS Service Name, e.g., S3}
-
-- **Purpose:** {Why is this service used?}
-- **SDK Package:** {e.g., `@aws-sdk/client-s3`}
-- **Key Operations Used:** {e.g., `GetObjectCommand`, `PutObjectCommand`}
-  - Operation 1: {Brief description of usage context}
-  - Operation 2: {...}
-- **Key Resource Identifiers:** {e.g., Bucket names, Table names - reference `docs/environment-vars.md`}
-
-### {Another AWS Service Name, e.g., SES}
-
-{...}
-
-## 5. Change Log
-
-| Change        | Date       | Version | Description   | Author         |
-| ------------- | ---------- | ------- | ------------- | -------------- |
-| Initial draft | YYYY-MM-DD | 0.1     | Initial draft | {Agent/Person} |
-| ...           | ...        | ...     | ...           | ...            |

docs/templates/architect-checklist.md

@@ -1,259 +0,0 @@
-# Architect Solution Validation Checklist
-
-This checklist serves as a comprehensive framework for the Architect to validate the technical design and architecture before development execution. The Architect should systematically work through each item, ensuring the architecture is robust, scalable, secure, and aligned with the product requirements.
-
-## 1. REQUIREMENTS ALIGNMENT
-
-### 1.1 Functional Requirements Coverage
-
-- [ ] Architecture supports all functional requirements in the PRD
-- [ ] Technical approaches for all epics and stories are addressed
-- [ ] Edge cases and performance scenarios are considered
-- [ ] All required integrations are accounted for
-- [ ] User journeys are supported by the technical architecture
-
-### 1.2 Non-Functional Requirements Alignment
-
-- [ ] Performance requirements are addressed with specific solutions
-- [ ] Scalability considerations are documented with approach
-- [ ] Security requirements have corresponding technical controls
-- [ ] Reliability and resilience approaches are defined
-- [ ] Compliance requirements have technical implementations
-
-### 1.3 Technical Constraints Adherence
-
-- [ ] All technical constraints from PRD are satisfied
-- [ ] Platform/language requirements are followed
-- [ ] Infrastructure constraints are accommodated
-- [ ] Third-party service constraints are addressed
-- [ ] Organizational technical standards are followed
-
-## 2. ARCHITECTURE FUNDAMENTALS
-
-### 2.1 Architecture Clarity
-
-- [ ] Architecture is documented with clear diagrams
-- [ ] Major components and their responsibilities are defined
-- [ ] Component interactions and dependencies are mapped
-- [ ] Data flows are clearly illustrated
-- [ ] Technology choices for each component are specified
-
-### 2.2 Separation of Concerns
-
-- [ ] Clear boundaries between UI, business logic, and data layers
-- [ ] Responsibilities are cleanly divided between components
-- [ ] Interfaces between components are well-defined
-- [ ] Components adhere to single responsibility principle
-- [ ] Cross-cutting concerns (logging, auth, etc.) are properly addressed
-
-### 2.3 Design Patterns & Best Practices
-
-- [ ] Appropriate design patterns are employed
-- [ ] Industry best practices are followed
-- [ ] Anti-patterns are avoided
-- [ ] Consistent architectural style throughout
-- [ ] Pattern usage is documented and explained
-
-### 2.4 Modularity & Maintainability
-
-- [ ] System is divided into cohesive, loosely-coupled modules
-- [ ] Components can be developed and tested independently
-- [ ] Changes can be localized to specific components
-- [ ] Code organization promotes discoverability
-- [ ] Architecture specifically designed for AI agent implementation
-
-## 3. TECHNICAL STACK & DECISIONS
-
-### 3.1 Technology Selection
-
-- [ ] Selected technologies meet all requirements
-- [ ] Technology versions are specifically defined (not ranges)
-- [ ] Technology choices are justified with clear rationale
-- [ ] Alternatives considered are documented with pros/cons
-- [ ] Selected stack components work well together
-
-### 3.2 Frontend Architecture
-
-- [ ] UI framework and libraries are specifically selected
-- [ ] State management approach is defined
-- [ ] Component structure and organization is specified
-- [ ] Responsive/adaptive design approach is outlined
-- [ ] Build and bundling strategy is determined
-
-### 3.3 Backend Architecture
-
-- [ ] API design and standards are defined
-- [ ] Service organization and boundaries are clear
-- [ ] Authentication and authorization approach is specified
-- [ ] Error handling strategy is outlined
-- [ ] Backend scaling approach is defined
-
-### 3.4 Data Architecture
-
-- [ ] Data models are fully defined
-- [ ] Database technologies are selected with justification
-- [ ] Data access patterns are documented
-- [ ] Data migration/seeding approach is specified
-- [ ] Data backup and recovery strategies are outlined
-
-## 4. RESILIENCE & OPERATIONAL READINESS
-
-### 4.1 Error Handling & Resilience
-
-- [ ] Error handling strategy is comprehensive
-- [ ] Retry policies are defined where appropriate
-- [ ] Circuit breakers or fallbacks are specified for critical services
-- [ ] Graceful degradation approaches are defined
-- [ ] System can recover from partial failures
-
-### 4.2 Monitoring & Observability
-
-- [ ] Logging strategy is defined
-- [ ] Monitoring approach is specified
-- [ ] Key metrics for system health are identified
-- [ ] Alerting thresholds and strategies are outlined
-- [ ] Debugging and troubleshooting capabilities are built in
-
-### 4.3 Performance & Scaling
-
-- [ ] Performance bottlenecks are identified and addressed
-- [ ] Caching strategy is defined where appropriate
-- [ ] Load balancing approach is specified
-- [ ] Horizontal and vertical scaling strategies are outlined
-- [ ] Resource sizing recommendations are provided
-
-### 4.4 Deployment & DevOps
-
-- [ ] Deployment strategy is defined
-- [ ] CI/CD pipeline approach is outlined
-- [ ] Environment strategy (dev, staging, prod) is specified
-- [ ] Infrastructure as Code approach is defined
-- [ ] Rollback and recovery procedures are outlined
-
-## 5. SECURITY & COMPLIANCE
-
-### 5.1 Authentication & Authorization
-
-- [ ] Authentication mechanism is clearly defined
-- [ ] Authorization model is specified
-- [ ] Role-based access control is outlined if required
-- [ ] Session management approach is defined
-- [ ] Credential management is addressed
-
-### 5.2 Data Security
-
-- [ ] Data encryption approach (at rest and in transit) is specified
-- [ ] Sensitive data handling procedures are defined
-- [ ] Data retention and purging policies are outlined
-- [ ] Backup encryption is addressed if required
-- [ ] Data access audit trails are specified if required
-
-### 5.3 API & Service Security
-
-- [ ] API security controls are defined
-- [ ] Rate limiting and throttling approaches are specified
-- [ ] Input validation strategy is outlined
-- [ ] CSRF/XSS prevention measures are addressed
-- [ ] Secure communication protocols are specified
-
-### 5.4 Infrastructure Security
-
-- [ ] Network security design is outlined
-- [ ] Firewall and security group configurations are specified
-- [ ] Service isolation approach is defined
-- [ ] Least privilege principle is applied
-- [ ] Security monitoring strategy is outlined
-
-## 6. IMPLEMENTATION GUIDANCE
-
-### 6.1 Coding Standards & Practices
-
-- [ ] Coding standards are defined
-- [ ] Documentation requirements are specified
-- [ ] Testing expectations are outlined
-- [ ] Code organization principles are defined
-- [ ] Naming conventions are specified
-
-### 6.2 Testing Strategy
-
-- [ ] Unit testing approach is defined
-- [ ] Integration testing strategy is outlined
-- [ ] E2E testing approach is specified
-- [ ] Performance testing requirements are outlined
-- [ ] Security testing approach is defined
-
-### 6.3 Development Environment
-
-- [ ] Local development environment setup is documented
-- [ ] Required tools and configurations are specified
-- [ ] Development workflows are outlined
-- [ ] Source control practices are defined
-- [ ] Dependency management approach is specified
-
-### 6.4 Technical Documentation
-
-- [ ] API documentation standards are defined
-- [ ] Architecture documentation requirements are specified
-- [ ] Code documentation expectations are outlined
-- [ ] System diagrams and visualizations are included
-- [ ] Decision records for key choices are included
-
-## 7. DEPENDENCY & INTEGRATION MANAGEMENT
-
-### 7.1 External Dependencies
-
-- [ ] All external dependencies are identified
-- [ ] Versioning strategy for dependencies is defined
-- [ ] Fallback approaches for critical dependencies are specified
-- [ ] Licensing implications are addressed
-- [ ] Update and patching strategy is outlined
-
-### 7.2 Internal Dependencies
-
-- [ ] Component dependencies are clearly mapped
-- [ ] Build order dependencies are addressed
-- [ ] Shared services and utilities are identified
-- [ ] Circular dependencies are eliminated
-- [ ] Versioning strategy for internal components is defined
-
-### 7.3 Third-Party Integrations
-
-- [ ] All third-party integrations are identified
-- [ ] Integration approaches are defined
-- [ ] Authentication with third parties is addressed
-- [ ] Error handling for integration failures is specified
-- [ ] Rate limits and quotas are considered
-
-## 8. AI AGENT IMPLEMENTATION SUITABILITY
-
-### 8.1 Modularity for AI Agents
-
-- [ ] Components are sized appropriately for AI agent implementation
-- [ ] Dependencies between components are minimized
-- [ ] Clear interfaces between components are defined
-- [ ] Components have singular, well-defined responsibilities
-- [ ] File and code organization optimized for AI agent understanding
-
-### 8.2 Clarity & Predictability
-
-- [ ] Patterns are consistent and predictable
-- [ ] Complex logic is broken down into simpler steps
-- [ ] Architecture avoids overly clever or obscure approaches
-- [ ] Examples are provided for unfamiliar patterns
-- [ ] Component responsibilities are explicit and clear
-
-### 8.3 Implementation Guidance
-
-- [ ] Detailed implementation guidance is provided
-- [ ] Code structure templates are defined
-- [ ] Specific implementation patterns are documented
-- [ ] Common pitfalls are identified with solutions
-- [ ] References to similar implementations are provided when helpful
-
-### 8.4 Error Prevention & Handling
-
-- [ ] Design reduces opportunities for implementation errors
-- [ ] Validation and error checking approaches are defined
-- [ ] Self-healing mechanisms are incorporated where possible
-- [ ] Testing patterns are clearly defined
-- [ ] Debugging guidance is provided

docs/templates/architecture.md

@@ -1,69 +0,0 @@
-# {Project Name} Architecture Document
-
-## Technical Summary
-
-{Provide a brief (1-2 paragraph) overview of the system's architecture, key components, technology choices, and architectural patterns used. Reference the goals from the PRD.}
-
-## High-Level Overview
-
-{Describe the main architectural style (e.g., Monolith, Microservices, Serverless, Event-Driven). Explain the primary user interaction or data flow at a conceptual level.}
-
-```mermaid
-{Insert high-level system context or interaction diagram here - e.g., using Mermaid graph TD or C4 Model Context Diagram}
-```
-
-## Component View
-
-{Describe the major logical components or services of the system and their responsibilities. Explain how they collaborate.}
-
-```mermaid
-{Insert component diagram here - e.g., using Mermaid graph TD or C4 Model Container/Component Diagram}
-```
-
-- Component A: {Description of responsibility}
-- Component B: {Description of responsibility}
-- {src/ Directory (if applicable): The application code in src/ is organized into logical modules... (briefly describe key subdirectories like clients, core, services, etc., referencing docs/project-structure.md for the full layout)}
-
-## Key Architectural Decisions & Patterns
-
-{List significant architectural choices and the patterns employed.}
-
-- Pattern/Decision 1: {e.g., Choice of Database, Message Queue Usage, Authentication Strategy, API Design Style (REST/GraphQL)} - Justification: {...}
-- Pattern/Decision 2: {...} - Justification: {...}
-- (See docs/coding-standards.md for detailed coding patterns and error handling)
-
-## Core Workflow / Sequence Diagrams (Optional)
-
-{Illustrate key or complex workflows using sequence diagrams if helpful.}
-
-## Infrastructure and Deployment Overview
-
-- Cloud Provider(s): {e.g., AWS, Azure, GCP, On-premise}
-- Core Services Used: {List key managed services - e.g., Lambda, S3, Kubernetes Engine, RDS, Kafka}
-- Infrastructure as Code (IaC): {Tool used - e.g., AWS CDK, Terraform, Pulumi, ARM Templates} - Location: {Link to IaC code repo/directory}
-- Deployment Strategy: {e.g., CI/CD pipeline, Manual deployment steps, Blue/Green, Canary} - Tools: {e.g., Jenkins, GitHub Actions, GitLab CI}
-- Environments: {List environments - e.g., Development, Staging, Production}
-- (See docs/environment-vars.md for configuration details)
-
-## Key Reference Documents
-
-{Link to other relevant documents in the docs/ folder.}
-
-- docs/prd.md
-- docs/epicN.md files
-- docs/tech-stack.md
-- docs/project-structure.md
-- docs/coding-standards.md
-- docs/api-reference.md
-- docs/data-models.md
-- docs/environment-vars.md
-- docs/testing-strategy.md
-- docs/ui-ux-spec.md (if applicable)
-- ... (other relevant docs)
-
-## Change Log
-
-| Change        | Date       | Version | Description                  | Author         |
-| ------------- | ---------- | ------- | ---------------------------- | -------------- |
-| Initial draft | YYYY-MM-DD | 0.1     | Initial draft based on brief | {Agent/Person} |
-| ...           | ...        | ...     | ...                          | ...            |

docs/templates/coding-standards.md

@@ -1,56 +0,0 @@
-# {Project Name} Coding Standards and Patterns
-
-## Architectural / Design Patterns Adopted
-
-{List the key high-level patterns chosen in the architecture document.}
-
-- **Pattern 1:** {e.g., Serverless, Event-Driven, Microservices, CQRS} - _Rationale/Reference:_ {Briefly why, or link to `docs/architecture.md` section}
-- **Pattern 2:** {e.g., Dependency Injection, Repository Pattern, Module Pattern} - _Rationale/Reference:_ {...}
-- **Pattern N:** {...}
-
-## Coding Standards (Consider adding these to Dev Agent Context or Rules)
-
-- **Primary Language(s):** {e.g., TypeScript 5.x, Python 3.11, Go 1.2x}
-- **Primary Runtime(s):** {e.g., Node.js 22.x, Python Runtime for Lambda}
-- **Style Guide & Linter:** {e.g., ESLint with Airbnb config, Prettier; Black, Flake8; Go fmt} - _Configuration:_ {Link to config files or describe setup}
-- **Naming Conventions:**
-  - Variables: `{e.g., camelCase}`
-  - Functions: `{e.g., camelCase}`
-  - Classes/Types/Interfaces: `{e.g., PascalCase}`
-  - Constants: `{e.g., UPPER_SNAKE_CASE}`
-  - Files: `{e.g., kebab-case.ts, snake_case.py}`
-- **File Structure:** Adhere to the layout defined in `docs/project-structure.md`.
-- **Asynchronous Operations:** {e.g., Use `async`/`await` in TypeScript/Python, Goroutines/Channels in Go.}
-- **Type Safety:** {e.g., Leverage TypeScript strict mode, Python type hints, Go static typing.} - _Type Definitions:_ {Location, e.g., `src/common/types.ts`}
-- **Comments & Documentation:** {Expectations for code comments, docstrings, READMEs.}
-- **Dependency Management:** {Tool used - e.g., npm, pip, Go modules. Policy on adding dependencies.}
-
-## Error Handling Strategy
-
-- **General Approach:** {e.g., Use exceptions, return error codes/tuples, specific error types.}
-- **Logging:**
-  - Library/Method: {e.g., `console.log/error`, Python `logging` module, dedicated logging library}
-  - Format: {e.g., JSON, plain text}
-  - Levels: {e.g., DEBUG, INFO, WARN, ERROR}
-  - Context: {What contextual information should be included?}
-- **Specific Handling Patterns:**
-  - External API Calls: {e.g., Use `try/catch`, check response codes, implement retries with backoff for transient errors?}
-  - Input Validation: {Where and how is input validated?}
-  - Graceful Degradation vs. Critical Failure: {Define criteria for when to continue vs. halt.}
-
-## Security Best Practices
-
-{Outline key security considerations relevant to the codebase.}
-
-- Input Sanitization/Validation: {...}
-- Secrets Management: {How are secrets handled in code? Reference `docs/environment-vars.md` regarding storage.}
-- Dependency Security: {Policy on checking for vulnerable dependencies.}
-- Authentication/Authorization Checks: {Where should these be enforced?}
-- {Other relevant practices...}
-
-## Change Log
-
-| Change        | Date       | Version | Description   | Author         |
-| ------------- | ---------- | ------- | ------------- | -------------- |
-| Initial draft | YYYY-MM-DD | 0.1     | Initial draft | {Agent/Person} |
-| ...           | ...        | ...     | ...           | ...            |

docs/templates/data-models.md

@@ -1,101 +0,0 @@
-# {Project Name} Data Models
-
-## 2. Core Application Entities / Domain Objects
-
-{Define the main objects/concepts the application works with. Repeat subsection for each key entity.}
-
-### {Entity Name, e.g., User, Order, Product}
-
-- **Description:** {What does this entity represent?}
-- **Schema / Interface Definition:**
-  ```typescript
-  // Example using TypeScript Interface
-  export interface {EntityName} {
-    id: string; // {Description, e.g., Unique identifier}
-    propertyName: string; // {Description}
-    optionalProperty?: number; // {Description}
-    // ... other properties
-  }
-  ```
-  _(Alternatively, use JSON Schema, class definitions, or other relevant format)_
-- **Validation Rules:** {List any specific validation rules beyond basic types - e.g., max length, format, range.}
-
-### {Another Entity Name}
-
-{...}
-
-## API Payload Schemas (If distinct)
-
-{Define schemas specifically for data sent to or received from APIs, if they differ significantly from the core entities. Reference `docs/api-reference.md`.}
-
-### {API Endpoint / Purpose, e.g., Create Order Request}
-
-- **Schema / Interface Definition:**
-  ```typescript
-  // Example
-  export interface CreateOrderRequest {
-    customerId: string;
-    items: { productId: string; quantity: number }[];
-    // ...
-  }
-  ```
-
-### {Another API Payload}
-
-{...}
-
-## Database Schemas (If applicable)
-
-{If using a database, define table structures or document database schemas.}
-
-### {Table / Collection Name}
-
-- **Purpose:** {What data does this table store?}
-- **Schema Definition:**
-  ```sql
-  -- Example SQL
-  CREATE TABLE {TableName} (
-    id VARCHAR(36) PRIMARY KEY,
-    column_name VARCHAR(255) NOT NULL,
-    numeric_column DECIMAL(10, 2),
-    -- ... other columns, indexes, constraints
-  );
-  ```
-  _(Alternatively, use ORM model definitions, NoSQL document structure, etc.)_
-
-### {Another Table / Collection Name}
-
-{...}
-
-## State File Schemas (If applicable)
-
-{If the application uses files for persisting state.}
-
-### {State File Name / Purpose, e.g., processed_items.json}
-
-- **Purpose:** {What state does this file track?}
-- **Format:** {e.g., JSON}
-- **Schema Definition:**
-  ```json
-  {
-    "type": "object",
-    "properties": {
-      "processedIds": {
-        "type": "array",
-        "items": {
-          "type": "string"
-        },
-        "description": "List of IDs that have been processed."
-      }
-      // ... other state properties
-    },
-    "required": ["processedIds"]
-  }
-  ```
-
-## Change Log
-
-| Change        | Date       | Version | Description   | Author         |
-| ------------- | ---------- | ------- | ------------- | -------------- |
-| Initial draft | YYYY-MM-DD | 0.1     | Initial draft | {Agent/Person} |
-| ...           | ...        | ...     | ...           | ...            |