Merge remote-tracking branch 'origin/next' into fix/set-task-status

- Closes #412

.changeset/beige-doodles-type.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Resolve all issues related to MCP

.changeset/beige-rats-accept.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-- Add support for Google Gemini models via Vercel AI SDK integration.

.changeset/blue-spies-kick.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Add xAI provider and Grok models support

.changeset/cuddly-zebras-matter.md

@@ -1,8 +0,0 @@
----
-'task-master-ai': minor
----
-
-feat(expand): Enhance `expand` and `expand-all` commands
-
-- Integrate `task-complexity-report.json` to automatically determine the number of subtasks and use tailored prompts for expansion based on prior analysis. You no longer need to try copy-pasting the recommended prompt. If it exists, it will use it for you. You can just run `task-master update --id=[id of task] --research` and it will use that prompt automatically. No extra prompt needed. 
-- Change default behavior to *append* new subtasks to existing ones. Use the `--force` flag to clear existing subtasks before expanding. This is helpful if you need to add more subtasks to a task but you want to do it by the batch from a given prompt. Use force if you want to start fresh with a task's subtasks.

.changeset/curvy-candies-eat.md

@@ -1,9 +0,0 @@
----
-'task-master-ai': patch
----
-
-Better support for file paths on Windows, Linux & WSL.
-
-- Standardizes handling of different path formats (URI encoded, Windows, Linux, WSL).
-- Ensures tools receive a clean, absolute path suitable for the server OS.
-- Simplifies tool implementation by centralizing normalization logic.

.changeset/easy-toys-wash.md

@@ -1,7 +0,0 @@
----
-'task-master-ai': minor
----
-
-Adds support for the OpenRouter AI provider. Users can now configure models available through OpenRouter (requiring an `OPENROUTER_API_KEY`) via the `task-master models` command, granting access to a wide range of additional LLMs.
-    - IMPORTANT FYI ABOUT OPENROUTER: Taskmaster relies on AI SDK, which itself relies on tool use. It looks like **free** models sometimes do not include tool use. For example, Gemini 2.5 pro (free) failed via OpenRouter (no tool use) but worked fine on the paid version of the model. Custom model support for Open Router is considered experimental and likely will not be further improved for some time.
-

.changeset/every-stars-sell.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Add integration for Roo Code

.changeset/fine-monkeys-eat.md

@@ -1,8 +0,0 @@
----
-'task-master-ai': patch
----
-
-Improved update-subtask
-    - Now it has context about the parent task details
-    - It also has context about the subtask before it and the subtask after it (if they exist)
-    - Not passing all subtasks to stay token efficient

.changeset/fine-signs-add.md

@@ -1,13 +0,0 @@
----
-'task-master-ai': patch
----
-
-Improve and adjust `init` command for robustness and updated dependencies.
-
-- **Update Initialization Dependencies:** Ensure newly initialized projects (`task-master init`) include all required AI SDK dependencies (`@ai-sdk/*`, `ai`, provider wrappers) in their `package.json` for out-of-the-box AI feature compatibility. Remove unnecessary dependencies (e.g., `uuid`) from the init template.
-- **Silence `npm install` during `init`:** Prevent `npm install` output from interfering with non-interactive/MCP initialization by suppressing its stdio in silent mode.
-- **Improve Conditional Model Setup:** Reliably skip interactive `models --setup` during non-interactive `init` runs (e.g., `init -y` or MCP) by checking `isSilentMode()` instead of passing flags.
-- **Refactor `init.js`:** Remove internal `isInteractive` flag logic.
-- **Update `init` Instructions:** Tweak the "Getting Started" text displayed after `init`.
-- **Fix MCP Server Launch:** Update `.cursor/mcp.json` template to use `node ./mcp-server/server.js` instead of `npx task-master-mcp`.
-- **Update Default Model:** Change the default main model in the `.taskmasterconfig` template.

.changeset/floppy-plants-marry.md

@@ -0,0 +1,9 @@
+---
+'task-master-ai': patch
+---
+
+Fix CLI --force flag for parse-prd command
+
+Previously, the --force flag was not respected when running `parse-prd`, causing the command to prompt for confirmation or fail even when --force was provided. This patch ensures that the flag is correctly passed and handled, allowing users to overwrite existing tasks.json files as intended.
+
+- Fixes #477

.changeset/forty-plums-stay.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': minor
+---
+
+.taskmasterconfig now supports a baseUrl field per model role (main, research, fallback), allowing endpoint overrides for any provider.

.changeset/gentle-views-jump.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Fixes an issue with add-task which did not use the manually defined properties and still needlessly hit the AI endpoint.

.changeset/many-wasps-sell.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Task Master no longer tells you to update when you're already up to date

.changeset/mighty-mirrors-watch.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': minor
----
-
-Adds model management and new configuration file .taskmasterconfig which houses the models used for main, research and fallback. Adds models command and setter flags. Adds a --setup flag with an interactive setup. We should be calling this during init. Shows a table of active and available models when models is called without flags. Includes SWE scores and token costs, which are manually entered into the supported_models.json, the new place where models are defined for support. Config-manager.js is the core module responsible for managing the new config."

.changeset/neat-donkeys-shave.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Fixes an issue that prevented remove-subtask with comma separated tasks/subtasks from being deleted (only the first ID was being deleted). Closes #140

.changeset/nine-rocks-sink.md

@@ -1,10 +0,0 @@
----
-'task-master-ai': patch
----
-
-Improves next command to be subtask-aware
-    - The logic for determining the "next task" (findNextTask function, used by task-master next and the next_task MCP tool) has been significantly improved. Previously, it only considered top-level tasks, making its recommendation less useful when a parent task containing subtasks was already marked 'in-progress'.
-    - The updated logic now prioritizes finding the next available subtask within any 'in-progress' parent task, considering subtask dependencies and priority. 
-    - If no suitable subtask is found within active parent tasks, it falls back to recommending the next eligible top-level task based on the original criteria (status, dependencies, priority). 
-    
-This change makes the next command much more relevant and helpful during the implementation phase of complex tasks.

.changeset/ninety-ghosts-relax.md

@@ -1,11 +0,0 @@
----
-'task-master-ai': minor
----
-
-Adds custom model ID support for Ollama and OpenRouter providers.
-  - Adds the `--ollama` and `--openrouter` flags to `task-master models --set-<role>` command to set models for those providers outside of the support models list.
-  - Updated `task-master models --setup` interactive mode with options to explicitly enter custom Ollama or OpenRouter model IDs.
-  - Implemented live validation against OpenRouter API (`/api/v1/models`) when setting a custom OpenRouter model ID (via flag or setup).
-  - Refined logic to prioritize explicit provider flags/choices over internal model list lookups in case of ID conflicts.
-  - Added warnings when setting custom/unvalidated models.
-  - We obviously don't recommend going with a custom, unproven model. If you do and find performance is good, please let us know so we can add it to the list of supported models.

.changeset/ninety-wombats-pull.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Add `--status` flag to `show` command to filter displayed subtasks.

.changeset/pre.json

@@ -1,29 +1,12 @@
 {
-  "mode": "pre",
+  "mode": "exit",
   "tag": "rc",
   "initialVersions": {
-    "task-master-ai": "0.12.1"
+    "task-master-ai": "0.13.2"
   },
   "changesets": [
-    "beige-rats-accept",
-    "blue-spies-kick",
-    "cuddly-zebras-matter",
-    "curvy-candies-eat",
-    "easy-toys-wash",
-    "every-stars-sell",
-    "fine-monkeys-eat",
-    "fine-signs-add",
-    "gentle-views-jump",
-    "mighty-mirrors-watch",
-    "neat-donkeys-shave",
-    "nine-rocks-sink",
-    "ninety-ghosts-relax",
-    "ninety-wombats-pull",
-    "public-cooks-fetch",
+    "beige-doodles-type",
     "red-oranges-attend",
-    "red-suns-wash",
-    "tricky-papayas-hang",
-    "violet-papayas-see",
-    "violet-parrots-march"
+    "red-suns-wash"
   ]
 }

.changeset/public-cooks-fetch.md

@@ -1,7 +0,0 @@
----
-'task-master-ai': minor
----
-
-Integrate OpenAI as a new AI provider.
-    - Enhance `models` command/tool to display API key status.
-    - Implement model-specific `maxTokens` override based on `supported-models.json` to save you if you use an incorrect max token value.

.changeset/sharp-dingos-melt.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix the error handling of task status settings

.changeset/slow-singers-swim.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix for issue #409 LOG_LEVEL Pydantic validation error

.changeset/soft-zoos-flow.md

@@ -0,0 +1,7 @@
+---
+'task-master-ai': patch
+---
+
+Fix initial .env.example to work out of the box
+
+- Closes #419

.changeset/ten-ways-mate.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix default fallback model and maxTokens in Taskmaster initialization

.changeset/tricky-papayas-hang.md

@@ -1,9 +0,0 @@
----
-'task-master-ai': minor
----
-Tweaks Perplexity AI calls for research mode to max out input tokens and get day-fresh information
-    - Forces temp at 0.1 for highly deterministic output, no variations
-    - Adds a system prompt to further improve the output
-    - Correctly uses the maximum input tokens (8,719, used 8,700) for perplexity
-    - Specificies to use a high degree of research across the web
-    - Specifies to use information that is as fresh as today; this support stuff like capturing brand new announcements like new GPT models and being able to query for those in research. 🔥

.changeset/tricky-wombats-spend.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix bug when updating tasks on the MCP server (#412)

.changeset/violet-papayas-see.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Fix --task to --num-tasks in ui + related tests - issue #324

.changeset/violet-parrots-march.md

@@ -1,9 +0,0 @@
----
-'task-master-ai': patch
----
-
-Adds a 'models' CLI and MCP command to get the current model configuration, available models, and gives the ability to set main/research/fallback models." 
-    - In the CLI, `task-master models` shows the current models config. Using the `--setup` flag launches an interactive set up that allows you to easily select the models you want to use for each of the three roles. Use `q` during the interactive setup to cancel the setup.
-    - In the MCP, responses are simplified in RESTful format (instead of the full CLI output). The agent can use the `models` tool with different arguments, including `listAvailableModels` to get available models. Run without arguments, it will return the current configuration. Arguments are available to set the model for each of the three roles. This allows you to manage Taskmaster AI providers and models directly from either the CLI or MCP or both.
-    - Updated the CLI help menu when you run `task-master` to include missing commands and .taskmasterconfig information.
-    - Adds `--research` flag to `add-task` so you can hit up Perplexity right from the add-task flow, rather than having to add a task and then update it.

.changeset/wide-eyes-relax.md

@@ -0,0 +1,11 @@
+---
+'task-master-ai': patch
+---
+
+Fix duplicate output on CLI help screen
+
+- Prevent the Task Master CLI from printing the help screen more than once when using `-h` or `--help`.
+- Removed redundant manual event handlers and guards for help output; now only the Commander `.helpInformation` override is used for custom help.
+- Simplified logic so that help is only shown once for both "no arguments" and help flag flows.
+- Ensures a clean, branded help experience with no repeated content.
+- Fixes #339

.cursor/rules/dev_workflow.mdc

@@ -116,7 +116,7 @@ Taskmaster configuration is managed through two main mechanisms:
     *   For MCP/Cursor integration, configure these keys in the `env` section of `.cursor/mcp.json`.
     *   Available keys/variables: See `assets/env.example` or the Configuration section in the command reference (previously linked to `taskmaster.mdc`).
 
-**Important:** Non-API key settings (like model selections, `MAX_TOKENS`, `LOG_LEVEL`) are **no longer configured via environment variables**. Use the `task-master models` command (or `--setup` for interactive configuration) or the `models` MCP tool.
+**Important:** Non-API key settings (like model selections, `MAX_TOKENS`, `TASKMASTER_LOG_LEVEL`) are **no longer configured via environment variables**. Use the `task-master models` command (or `--setup` for interactive configuration) or the `models` MCP tool.
 **If AI commands FAIL in MCP** verify that the API key for the selected provider is present in the `env` section of `.cursor/mcp.json`.
 **If AI commands FAIL in CLI** verify that the API key for the selected provider is present in the `.env` file in the root of the project.
 

.github/workflows/pre-release.yml

@@ -0,0 +1,62 @@
+name: Pre-Release (RC)
+
+on:
+  workflow_dispatch: # Allows manual triggering from GitHub UI/API
+
+concurrency: pre-release-${{ github.ref }}
+
+jobs:
+  rc:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: 'npm'
+
+      - name: Cache node_modules
+        uses: actions/cache@v4
+        with:
+          path: |
+            node_modules
+            */*/node_modules
+          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
+          restore-keys: |
+            ${{ runner.os }}-node-
+
+      - name: Install dependencies
+        run: npm ci
+        timeout-minutes: 2
+
+      - name: Enter RC mode
+        run: |
+          npx changeset pre exit || true
+          npx changeset pre enter rc
+
+      - name: Version RC packages
+        run: npx changeset version
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+
+      - name: Create Release Candidate Pull Request or Publish Release Candidate to npm
+        uses: changesets/action@v1
+        with:
+          publish: npm run release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+
+      - name: Exit RC mode
+        run: npx changeset pre exit
+
+      - name: Commit & Push changes
+        uses: actions-js/push@master
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          branch: ${{ github.ref }}
+          message: 'chore: rc version bump'

.github/workflows/release.yml

@@ -33,6 +33,9 @@ jobs:
         run: npm ci
         timeout-minutes: 2
 
+      - name: Exit pre-release mode (safety check)
+        run: npx changeset pre exit || true
+
       - name: Create Release Pull Request or Publish to npm
         uses: changesets/action@v1
         with:

CHANGELOG.md

@@ -1,51 +1,54 @@
 # task-master-ai
 
-## 0.13.0-rc.2
+## 0.13.1
 
 ### Patch Changes
 
-- Add src directory to exports
+- [#399](https://github.com/eyaltoledano/claude-task-master/pull/399) [`734a4fd`](https://github.com/eyaltoledano/claude-task-master/commit/734a4fdcfc89c2e089255618cf940561ad13a3c8) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix ERR_MODULE_NOT_FOUND when trying to run MCP Server
 
-## 0.13.0-rc.1
-
-### Patch Changes
-
-- 4cbfe82: Fix ERR_MODULE_NOT_FOUND when trying to run MCP Server
-
-## 0.13.0-rc.0
+## 0.13.0
 
 ### Minor Changes
 
-- ef782ff: feat(expand): Enhance `expand` and `expand-all` commands
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`ef782ff`](https://github.com/eyaltoledano/claude-task-master/commit/ef782ff5bd4ceb3ed0dc9ea82087aae5f79ac933) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - feat(expand): Enhance `expand` and `expand-all` commands
 
   - Integrate `task-complexity-report.json` to automatically determine the number of subtasks and use tailored prompts for expansion based on prior analysis. You no longer need to try copy-pasting the recommended prompt. If it exists, it will use it for you. You can just run `task-master update --id=[id of task] --research` and it will use that prompt automatically. No extra prompt needed.
   - Change default behavior to _append_ new subtasks to existing ones. Use the `--force` flag to clear existing subtasks before expanding. This is helpful if you need to add more subtasks to a task but you want to do it by the batch from a given prompt. Use force if you want to start fresh with a task's subtasks.
 
-- 87d97bb: Adds support for the OpenRouter AI provider. Users can now configure models available through OpenRouter (requiring an `OPENROUTER_API_KEY`) via the `task-master models` command, granting access to a wide range of additional LLMs. - IMPORTANT FYI ABOUT OPENROUTER: Taskmaster relies on AI SDK, which itself relies on tool use. It looks like **free** models sometimes do not include tool use. For example, Gemini 2.5 pro (free) failed via OpenRouter (no tool use) but worked fine on the paid version of the model. Custom model support for Open Router is considered experimental and likely will not be further improved for some time.
-- 1ab836f: Adds model management and new configuration file .taskmasterconfig which houses the models used for main, research and fallback. Adds models command and setter flags. Adds a --setup flag with an interactive setup. We should be calling this during init. Shows a table of active and available models when models is called without flags. Includes SWE scores and token costs, which are manually entered into the supported_models.json, the new place where models are defined for support. Config-manager.js is the core module responsible for managing the new config."
-- c8722b0: Adds custom model ID support for Ollama and OpenRouter providers.
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`87d97bb`](https://github.com/eyaltoledano/claude-task-master/commit/87d97bba00d84e905756d46ef96b2d5b984e0f38) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds support for the OpenRouter AI provider. Users can now configure models available through OpenRouter (requiring an `OPENROUTER_API_KEY`) via the `task-master models` command, granting access to a wide range of additional LLMs. - IMPORTANT FYI ABOUT OPENROUTER: Taskmaster relies on AI SDK, which itself relies on tool use. It looks like **free** models sometimes do not include tool use. For example, Gemini 2.5 pro (free) failed via OpenRouter (no tool use) but worked fine on the paid version of the model. Custom model support for Open Router is considered experimental and likely will not be further improved for some time.
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`1ab836f`](https://github.com/eyaltoledano/claude-task-master/commit/1ab836f191cb8969153593a9a0bd47fc9aa4a831) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds model management and new configuration file .taskmasterconfig which houses the models used for main, research and fallback. Adds models command and setter flags. Adds a --setup flag with an interactive setup. We should be calling this during init. Shows a table of active and available models when models is called without flags. Includes SWE scores and token costs, which are manually entered into the supported_models.json, the new place where models are defined for support. Config-manager.js is the core module responsible for managing the new config."
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`c8722b0`](https://github.com/eyaltoledano/claude-task-master/commit/c8722b0a7a443a73b95d1bcd4a0b68e0fce2a1cd) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds custom model ID support for Ollama and OpenRouter providers.
+
   - Adds the `--ollama` and `--openrouter` flags to `task-master models --set-<role>` command to set models for those providers outside of the support models list.
   - Updated `task-master models --setup` interactive mode with options to explicitly enter custom Ollama or OpenRouter model IDs.
   - Implemented live validation against OpenRouter API (`/api/v1/models`) when setting a custom OpenRouter model ID (via flag or setup).
   - Refined logic to prioritize explicit provider flags/choices over internal model list lookups in case of ID conflicts.
   - Added warnings when setting custom/unvalidated models.
   - We obviously don't recommend going with a custom, unproven model. If you do and find performance is good, please let us know so we can add it to the list of supported models.
-- 2517bc1: Integrate OpenAI as a new AI provider. - Enhance `models` command/tool to display API key status. - Implement model-specific `maxTokens` override based on `supported-models.json` to save you if you use an incorrect max token value.
-- 9a48278: Tweaks Perplexity AI calls for research mode to max out input tokens and get day-fresh information - Forces temp at 0.1 for highly deterministic output, no variations - Adds a system prompt to further improve the output - Correctly uses the maximum input tokens (8,719, used 8,700) for perplexity - Specificies to use a high degree of research across the web - Specifies to use information that is as fresh as today; this support stuff like capturing brand new announcements like new GPT models and being able to query for those in research. 🔥
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`2517bc1`](https://github.com/eyaltoledano/claude-task-master/commit/2517bc112c9a497110f3286ca4bfb4130c9addcb) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Integrate OpenAI as a new AI provider. - Enhance `models` command/tool to display API key status. - Implement model-specific `maxTokens` override based on `supported-models.json` to save you if you use an incorrect max token value.
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`9a48278`](https://github.com/eyaltoledano/claude-task-master/commit/9a482789f7894f57f655fb8d30ba68542bd0df63) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Tweaks Perplexity AI calls for research mode to max out input tokens and get day-fresh information - Forces temp at 0.1 for highly deterministic output, no variations - Adds a system prompt to further improve the output - Correctly uses the maximum input tokens (8,719, used 8,700) for perplexity - Specificies to use a high degree of research across the web - Specifies to use information that is as fresh as today; this support stuff like capturing brand new announcements like new GPT models and being able to query for those in research. 🔥
 
 ### Patch Changes
 
-- 842eaf7: - Add support for Google Gemini models via Vercel AI SDK integration.
-- ed79d4f: Add xAI provider and Grok models support
-- ad89253: Better support for file paths on Windows, Linux & WSL.
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`842eaf7`](https://github.com/eyaltoledano/claude-task-master/commit/842eaf722498ddf7307800b4cdcef4ac4fd7e5b0) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - - Add support for Google Gemini models via Vercel AI SDK integration.
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`ed79d4f`](https://github.com/eyaltoledano/claude-task-master/commit/ed79d4f4735dfab4124fa189214c0bd5e23a6860) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add xAI provider and Grok models support
+
+- [#378](https://github.com/eyaltoledano/claude-task-master/pull/378) [`ad89253`](https://github.com/eyaltoledano/claude-task-master/commit/ad89253e313a395637aa48b9f92cc39b1ef94ad8) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Better support for file paths on Windows, Linux & WSL.
 
   - Standardizes handling of different path formats (URI encoded, Windows, Linux, WSL).
   - Ensures tools receive a clean, absolute path suitable for the server OS.
   - Simplifies tool implementation by centralizing normalization logic.
 
-- 2acba94: Add integration for Roo Code
-- d63964a: Improved update-subtask - Now it has context about the parent task details - It also has context about the subtask before it and the subtask after it (if they exist) - Not passing all subtasks to stay token efficient
-- 5f504fa: Improve and adjust `init` command for robustness and updated dependencies.
+- [#285](https://github.com/eyaltoledano/claude-task-master/pull/285) [`2acba94`](https://github.com/eyaltoledano/claude-task-master/commit/2acba945c0afee9460d8af18814c87e80f747e9f) Thanks [@neno-is-ooo](https://github.com/neno-is-ooo)! - Add integration for Roo Code
+
+- [#378](https://github.com/eyaltoledano/claude-task-master/pull/378) [`d63964a`](https://github.com/eyaltoledano/claude-task-master/commit/d63964a10eed9be17856757661ff817ad6bacfdc) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Improved update-subtask - Now it has context about the parent task details - It also has context about the subtask before it and the subtask after it (if they exist) - Not passing all subtasks to stay token efficient
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`5f504fa`](https://github.com/eyaltoledano/claude-task-master/commit/5f504fafb8bdaa0043c2d20dee8bbb8ec2040d85) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Improve and adjust `init` command for robustness and updated dependencies.
 
   - **Update Initialization Dependencies:** Ensure newly initialized projects (`task-master init`) include all required AI SDK dependencies (`@ai-sdk/*`, `ai`, provider wrappers) in their `package.json` for out-of-the-box AI feature compatibility. Remove unnecessary dependencies (e.g., `uuid`) from the init template.
   - **Silence `npm install` during `init`:** Prevent `npm install` output from interfering with non-interactive/MCP initialization by suppressing its stdio in silent mode.
@@ -55,15 +58,19 @@
   - **Fix MCP Server Launch:** Update `.cursor/mcp.json` template to use `node ./mcp-server/server.js` instead of `npx task-master-mcp`.
   - **Update Default Model:** Change the default main model in the `.taskmasterconfig` template.
 
-- 96aeeff: Fixes an issue with add-task which did not use the manually defined properties and still needlessly hit the AI endpoint.
-- 5aea93d: Fixes an issue that prevented remove-subtask with comma separated tasks/subtasks from being deleted (only the first ID was being deleted). Closes #140
-- 66ac9ab: Improves next command to be subtask-aware - The logic for determining the "next task" (findNextTask function, used by task-master next and the next_task MCP tool) has been significantly improved. Previously, it only considered top-level tasks, making its recommendation less useful when a parent task containing subtasks was already marked 'in-progress'. - The updated logic now prioritizes finding the next available subtask within any 'in-progress' parent task, considering subtask dependencies and priority. - If no suitable subtask is found within active parent tasks, it falls back to recommending the next eligible top-level task based on the original criteria (status, dependencies, priority).
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`96aeeff`](https://github.com/eyaltoledano/claude-task-master/commit/96aeeffc195372722c6a07370540e235bfe0e4d8) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fixes an issue with add-task which did not use the manually defined properties and still needlessly hit the AI endpoint.
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`5aea93d`](https://github.com/eyaltoledano/claude-task-master/commit/5aea93d4c0490c242d7d7042a210611977848e0a) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fixes an issue that prevented remove-subtask with comma separated tasks/subtasks from being deleted (only the first ID was being deleted). Closes #140
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`66ac9ab`](https://github.com/eyaltoledano/claude-task-master/commit/66ac9ab9f66d006da518d6e8a3244e708af2764d) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Improves next command to be subtask-aware - The logic for determining the "next task" (findNextTask function, used by task-master next and the next_task MCP tool) has been significantly improved. Previously, it only considered top-level tasks, making its recommendation less useful when a parent task containing subtasks was already marked 'in-progress'. - The updated logic now prioritizes finding the next available subtask within any 'in-progress' parent task, considering subtask dependencies and priority. - If no suitable subtask is found within active parent tasks, it falls back to recommending the next eligible top-level task based on the original criteria (status, dependencies, priority).
 
   This change makes the next command much more relevant and helpful during the implementation phase of complex tasks.
 
-- ca7b045: Add `--status` flag to `show` command to filter displayed subtasks.
-- 5a2371b: Fix --task to --num-tasks in ui + related tests - issue #324
-- 6cb213e: Adds a 'models' CLI and MCP command to get the current model configuration, available models, and gives the ability to set main/research/fallback models." - In the CLI, `task-master models` shows the current models config. Using the `--setup` flag launches an interactive set up that allows you to easily select the models you want to use for each of the three roles. Use `q` during the interactive setup to cancel the setup. - In the MCP, responses are simplified in RESTful format (instead of the full CLI output). The agent can use the `models` tool with different arguments, including `listAvailableModels` to get available models. Run without arguments, it will return the current configuration. Arguments are available to set the model for each of the three roles. This allows you to manage Taskmaster AI providers and models directly from either the CLI or MCP or both. - Updated the CLI help menu when you run `task-master` to include missing commands and .taskmasterconfig information. - Adds `--research` flag to `add-task` so you can hit up Perplexity right from the add-task flow, rather than having to add a task and then update it.
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`ca7b045`](https://github.com/eyaltoledano/claude-task-master/commit/ca7b0457f1dc65fd9484e92527d9fd6d69db758d) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add `--status` flag to `show` command to filter displayed subtasks.
+
+- [#328](https://github.com/eyaltoledano/claude-task-master/pull/328) [`5a2371b`](https://github.com/eyaltoledano/claude-task-master/commit/5a2371b7cc0c76f5e95d43921c1e8cc8081bf14e) Thanks [@knoxgraeme](https://github.com/knoxgraeme)! - Fix --task to --num-tasks in ui + related tests - issue #324
+
+- [#240](https://github.com/eyaltoledano/claude-task-master/pull/240) [`6cb213e`](https://github.com/eyaltoledano/claude-task-master/commit/6cb213ebbd51116ae0688e35b575d09443d17c3b) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds a 'models' CLI and MCP command to get the current model configuration, available models, and gives the ability to set main/research/fallback models." - In the CLI, `task-master models` shows the current models config. Using the `--setup` flag launches an interactive set up that allows you to easily select the models you want to use for each of the three roles. Use `q` during the interactive setup to cancel the setup. - In the MCP, responses are simplified in RESTful format (instead of the full CLI output). The agent can use the `models` tool with different arguments, including `listAvailableModels` to get available models. Run without arguments, it will return the current configuration. Arguments are available to set the model for each of the three roles. This allows you to manage Taskmaster AI providers and models directly from either the CLI or MCP or both. - Updated the CLI help menu when you run `task-master` to include missing commands and .taskmasterconfig information. - Adds `--research` flag to `add-task` so you can hit up Perplexity right from the add-task flow, rather than having to add a task and then update it.
 
 ## 0.12.1
 

assets/.taskmasterconfig

@@ -14,8 +14,8 @@
 		},
 		"fallback": {
 			"provider": "anthropic",
-			"modelId": "claude-3.5-sonnet-20240620",
-			"maxTokens": 120000,
+			"modelId": "claude-3-5-sonnet-20240620",
+			"maxTokens": 8192,
 			"temperature": 0.1
 		}
 	},

assets/.windsurfrules

@@ -198,7 +198,7 @@ alwaysApply: true
   - **MAX_TOKENS** (Default: `"4000"`): Maximum tokens for responses (Example: `MAX_TOKENS=8000`)
   - **TEMPERATURE** (Default: `"0.7"`): Temperature for model responses (Example: `TEMPERATURE=0.5`)
   - **DEBUG** (Default: `"false"`): Enable debug logging (Example: `DEBUG=true`)
-  - **LOG_LEVEL** (Default: `"info"`): Console output level (Example: `LOG_LEVEL=debug`)
+  - **TASKMASTER_LOG_LEVEL** (Default: `"info"`): Console output level (Example: `TASKMASTER_LOG_LEVEL=debug`)
   - **DEFAULT_SUBTASKS** (Default: `"3"`): Default subtask count (Example: `DEFAULT_SUBTASKS=5`)
   - **DEFAULT_PRIORITY** (Default: `"medium"`): Default priority (Example: `DEFAULT_PRIORITY=high`)
   - **PROJECT_NAME** (Default: `"MCP SaaS MVP"`): Project name in metadata (Example: `PROJECT_NAME=My Awesome Project`)

assets/env.example

@@ -1,8 +1,8 @@
 # API Keys (Required to enable respective provider)
-ANTHROPIC_API_KEY=your_anthropic_api_key_here       # Required: Format: sk-ant-api03-...
-PERPLEXITY_API_KEY=your_perplexity_api_key_here     # Optional: Format: pplx-...
-OPENAI_API_KEY=your_openai_api_key_here             # Optional, for OpenAI/OpenRouter models. Format: sk-proj-...
-GOOGLE_API_KEY=your_google_api_key_here             # Optional, for Google Gemini models.
-MISTRAL_API_KEY=your_mistral_key_here               # Optional, for Mistral AI models.
-XAI_API_KEY=YOUR_XAI_KEY_HERE                       # Optional, for xAI AI models.
-AZURE_OPENAI_API_KEY=your_azure_key_here            # Optional, for Azure OpenAI models (requires endpoint in .taskmasterconfig).
+ANTHROPIC_API_KEY="your_anthropic_api_key_here"       # Required: Format: sk-ant-api03-...
+PERPLEXITY_API_KEY="your_perplexity_api_key_here"     # Optional: Format: pplx-...
+OPENAI_API_KEY="your_openai_api_key_here"             # Optional, for OpenAI/OpenRouter models. Format: sk-proj-...
+GOOGLE_API_KEY="your_google_api_key_here"             # Optional, for Google Gemini models.
+MISTRAL_API_KEY="your_mistral_key_here"               # Optional, for Mistral AI models.
+XAI_API_KEY="YOUR_XAI_KEY_HERE"                       # Optional, for xAI AI models.
+AZURE_OPENAI_API_KEY="your_azure_key_here"            # Optional, for Azure OpenAI models (requires endpoint in .taskmasterconfig).

assets/scripts_README.md

@@ -31,7 +31,7 @@ Task Master configuration is now managed through two primary methods:
     - Create a `.env` file in your project root for CLI usage.
     - See `assets/env.example` for required key names.
 
-**Important:** Settings like `MODEL`, `MAX_TOKENS`, `TEMPERATURE`, `LOG_LEVEL`, etc., are **no longer set via `.env`**. Use `task-master models --setup` instead.
+**Important:** Settings like `MODEL`, `MAX_TOKENS`, `TEMPERATURE`, `TASKMASTER_LOG_LEVEL`, etc., are **no longer set via `.env`**. Use `task-master models --setup` instead.
 
 ## How It Works
 
@@ -42,7 +42,7 @@ Task Master configuration is now managed through two primary methods:
    - Tasks can have `subtasks` for more detailed implementation steps.
    - Dependencies are displayed with status indicators (✅ for completed, ⏱️ for pending) to easily track progress.
 
-2. **CLI Commands**  
+2. **CLI Commands**
    You can run the commands via:
 
    ```bash
@@ -200,7 +200,7 @@ Notes:
 
 ## Logging
 
-The script supports different logging levels controlled by the `LOG_LEVEL` environment variable:
+The script supports different logging levels controlled by the `TASKMASTER_LOG_LEVEL` environment variable:
 
 - `debug`: Detailed information, typically useful for troubleshooting
 - `info`: Confirmation that things are working as expected (default)

docs/configuration.md

@@ -15,13 +15,15 @@ Taskmaster uses two primary methods for configuration:
       			"provider": "anthropic",
       			"modelId": "claude-3-7-sonnet-20250219",
       			"maxTokens": 64000,
-      			"temperature": 0.2
+      			"temperature": 0.2,
+      			"baseUrl": "https://api.anthropic.com/v1"
       		},
       		"research": {
       			"provider": "perplexity",
       			"modelId": "sonar-pro",
       			"maxTokens": 8700,
-      			"temperature": 0.1
+      			"temperature": 0.1,
+      			"baseUrl": "https://api.perplexity.ai/v1"
       		},
       		"fallback": {
       			"provider": "anthropic",
@@ -56,8 +58,9 @@ Taskmaster uses two primary methods for configuration:
       - `AZURE_OPENAI_API_KEY`: Your Azure OpenAI API key (also requires `AZURE_OPENAI_ENDPOINT`).
       - `OPENROUTER_API_KEY`: Your OpenRouter API key.
       - `XAI_API_KEY`: Your X-AI API key.
-    - **Optional Endpoint Overrides (in .taskmasterconfig):**
-      - `AZURE_OPENAI_ENDPOINT`: Required if using Azure OpenAI key.
+    - **Optional Endpoint Overrides:**
+      - **Per-role `baseUrl` in `.taskmasterconfig`:** You can add a `baseUrl` property to any model role (`main`, `research`, `fallback`) to override the default API endpoint for that provider. If omitted, the provider's standard endpoint is used.
+      - `AZURE_OPENAI_ENDPOINT`: Required if using Azure OpenAI key (can also be set as `baseUrl` for the Azure model role).
       - `OLLAMA_BASE_URL`: Override the default Ollama API URL (Default: `http://localhost:11434/api`).
 
 **Important:** Settings like model ID selections (`main`, `research`, `fallback`), `maxTokens`, `temperature`, `logLevel`, `defaultSubtasks`, `defaultPriority`, and `projectName` are **managed in `.taskmasterconfig`**, not environment variables.

mcp-server/src/core/direct-functions/update-tasks.js

@@ -6,6 +6,10 @@
 import path from 'path';
 import { updateTasks } from '../../../../scripts/modules/task-manager.js';
 import { createLogWrapper } from '../../tools/utils.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
 
 /**
  * Direct function wrapper for updating tasks based on new context.

mcp-server/src/tools/set-task-status.js

@@ -11,6 +11,7 @@ import {
 } from './utils.js';
 import { setTaskStatusDirect } from '../core/task-master-core.js';
 import { findTasksJsonPath } from '../core/utils/path-utils.js';
+import { TASK_STATUS_OPTIONS } from '../../../src/constants/task-status.js';
 
 /**
  * Register the setTaskStatus tool with the MCP server
@@ -27,7 +28,7 @@ export function registerSetTaskStatusTool(server) {
 					"Task ID or subtask ID (e.g., '15', '15.2'). Can be comma-separated to update multiple tasks/subtasks at once."
 				),
 			status: z
-				.string()
+				.enum(TASK_STATUS_OPTIONS)
 				.describe(
 					"New status to set (e.g., 'pending', 'done', 'in-progress', 'review', 'deferred', 'cancelled'."
 				),

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "task-master-ai",
-	"version": "0.13.0-rc.1",
+	"version": "0.13.2",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "task-master-ai",
-			"version": "0.13.0-rc.1",
+			"version": "0.13.2",
 			"license": "MIT WITH Commons-Clause",
 			"dependencies": {
 				"@ai-sdk/anthropic": "^1.2.10",

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "task-master-ai",
-	"version": "0.13.0-rc.2",
+	"version": "0.13.2",
 	"description": "A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.",
 	"main": "index.js",
 	"type": "module",
@@ -82,9 +82,7 @@
 		"url": "https://github.com/eyaltoledano/claude-task-master/issues"
 	},
 	"files": [
-		"scripts/init.js",
-		"scripts/dev.js",
-		"scripts/modules/**",
+		"scripts/**",
 		"assets/**",
 		".cursor/**",
 		"README-task-master.md",

scripts/README.md

@@ -32,7 +32,7 @@ The script can be configured through environment variables in a `.env` file at t
 - `PERPLEXITY_API_KEY`: Your Perplexity API key for research-backed subtask generation
 - `PERPLEXITY_MODEL`: Specify which Perplexity model to use (default: "sonar-medium-online")
 - `DEBUG`: Enable debug logging (default: false)
-- `LOG_LEVEL`: Log level - debug, info, warn, error (default: info)
+- `TASKMASTER_LOG_LEVEL`: Log level - debug, info, warn, error (default: info)
 - `DEFAULT_SUBTASKS`: Default number of subtasks when expanding (default: 3)
 - `DEFAULT_PRIORITY`: Default priority for generated tasks (default: medium)
 - `PROJECT_NAME`: Override default project name in tasks.json
@@ -47,7 +47,7 @@ The script can be configured through environment variables in a `.env` file at t
    - Tasks can have `subtasks` for more detailed implementation steps.
    - Dependencies are displayed with status indicators (✅ for completed, ⏱️ for pending) to easily track progress.
 
-2. **Script Commands**  
+2. **Script Commands**
    You can run the script via:
 
    ```bash
@@ -225,7 +225,7 @@ To use the Perplexity integration:
 
 ## Logging
 
-The script supports different logging levels controlled by the `LOG_LEVEL` environment variable:
+The script supports different logging levels controlled by the `TASKMASTER_LOG_LEVEL` environment variable:
 
 - `debug`: Detailed information, typically useful for troubleshooting
 - `info`: Confirmation that things are working as expected (default)

scripts/init.js

@@ -38,10 +38,10 @@ const LOG_LEVELS = {
 	success: 4
 };
 
-// Get log level from environment or default to info
-const LOG_LEVEL = process.env.LOG_LEVEL
-	? LOG_LEVELS[process.env.LOG_LEVEL.toLowerCase()]
-	: LOG_LEVELS.info;
+// Determine log level from environment variable or default to 'info'
+const LOG_LEVEL = process.env.TASKMASTER_LOG_LEVEL
+	? LOG_LEVELS[process.env.TASKMASTER_LOG_LEVEL.toLowerCase()]
+	: LOG_LEVELS.info; // Default to info
 
 // Create a color gradient for the banner
 const coolGradient = gradient(['#00b4d8', '#0077b6', '#03045e']);

scripts/modules/ai-services-unified.js

@@ -14,7 +14,8 @@ import {
 	getResearchModelId,
 	getFallbackProvider,
 	getFallbackModelId,
-	getParametersForRole
+	getParametersForRole,
+	getBaseUrlForRole
 } from './config-manager.js';
 import { log, resolveEnvVariable, findProjectRoot } from './utils.js';
 
@@ -284,7 +285,13 @@ async function _unifiedServiceRunner(serviceType, params) {
 		'AI service call failed for all configured roles.';
 
 	for (const currentRole of sequence) {
-		let providerName, modelId, apiKey, roleParams, providerFnSet, providerApiFn;
+		let providerName,
+			modelId,
+			apiKey,
+			roleParams,
+			providerFnSet,
+			providerApiFn,
+			baseUrl;
 
 		try {
 			log('info', `New AI service call with role: ${currentRole}`);
@@ -325,6 +332,7 @@ async function _unifiedServiceRunner(serviceType, params) {
 
 			// Pass effectiveProjectRoot to getParametersForRole
 			roleParams = getParametersForRole(currentRole, effectiveProjectRoot);
+			baseUrl = getBaseUrlForRole(currentRole, effectiveProjectRoot);
 
 			// 2. Get Provider Function Set
 			providerFnSet = PROVIDER_FUNCTIONS[providerName?.toLowerCase()];
@@ -401,6 +409,7 @@ async function _unifiedServiceRunner(serviceType, params) {
 				maxTokens: roleParams.maxTokens,
 				temperature: roleParams.temperature,
 				messages,
+				baseUrl,
 				...(serviceType === 'generateObject' && { schema, objectName }),
 				...restApiParams
 			};

scripts/modules/commands.js

@@ -73,7 +73,11 @@ import {
 	getApiKeyStatusReport
 } from './task-manager/models.js';
 import { findProjectRoot } from './utils.js';
-
+import {
+	isValidTaskStatus,
+	TASK_STATUS_OPTIONS
+} from '../../src/constants/task-status.js';
+import { getTaskMasterVersion } from '../../src/utils/getVersion.js';
 /**
  * Runs the interactive setup process for model configuration.
  * @param {string|null} projectRoot - The resolved project root directory.
@@ -486,11 +490,6 @@ function registerCommands(programInstance) {
 		process.exit(1);
 	});
 
-	// Default help
-	programInstance.on('--help', function () {
-		displayHelp();
-	});
-
 	// parse-prd command
 	programInstance
 		.command('parse-prd')
@@ -515,7 +514,7 @@ function registerCommands(programInstance) {
 			const outputPath = options.output;
 			const force = options.force || false;
 			const append = options.append || false;
-			let useForce = false;
+			let useForce = force;
 			let useAppend = false;
 
 			// Helper function to check if tasks.json exists and confirm overwrite
@@ -609,7 +608,7 @@ function registerCommands(programInstance) {
 				spinner = ora('Parsing PRD and generating tasks...').start();
 				await parsePRD(inputFile, outputPath, numTasks, {
 					append: useAppend,
-					force: useForce
+					useForce
 				});
 				spinner.succeed('Tasks generated successfully!');
 			} catch (error) {
@@ -1038,7 +1037,7 @@ function registerCommands(programInstance) {
 		)
 		.option(
 			'-s, --status <status>',
-			'New status (todo, in-progress, review, done)'
+			`New status (one of: ${TASK_STATUS_OPTIONS.join(', ')})`
 		)
 		.option('-f, --file <file>', 'Path to the tasks file', 'tasks/tasks.json')
 		.action(async (options) => {
@@ -1051,6 +1050,16 @@ function registerCommands(programInstance) {
 				process.exit(1);
 			}
 
+			if (!isValidTaskStatus(status)) {
+				console.error(
+					chalk.red(
+						`Error: Invalid status value: ${status}. Use one of: ${TASK_STATUS_OPTIONS.join(', ')}`
+					)
+				);
+
+				process.exit(1);
+			}
+
 			console.log(
 				chalk.blue(`Setting status of task(s) ${taskId} to: ${status}`)
 			);
@@ -1278,10 +1287,6 @@ function registerCommands(programInstance) {
 			'--details <details>',
 			'Implementation details (for manual task creation)'
 		)
-		.option(
-			'--test-strategy <testStrategy>',
-			'Test strategy (for manual task creation)'
-		)
 		.option(
 			'--dependencies <dependencies>',
 			'Comma-separated list of task IDs this task depends on'
@@ -1663,6 +1668,7 @@ function registerCommands(programInstance) {
 				}
 			} catch (error) {
 				console.error(chalk.red(`Error: ${error.message}`));
+				showAddSubtaskHelp();
 				process.exit(1);
 			}
 		})
@@ -2366,14 +2372,7 @@ function setupCLI() {
 			return 'unknown'; // Default fallback if package.json fails
 		})
 		.helpOption('-h, --help', 'Display help')
-		.addHelpCommand(false) // Disable default help command
-		.on('--help', () => {
-			displayHelp(); // Use your custom help display instead
-		})
-		.on('-h', () => {
-			displayHelp();
-			process.exit(0);
-		});
+		.addHelpCommand(false); // Disable default help command
 
 	// Modify the help option to use your custom display
 	programInstance.helpInformation = () => {
@@ -2393,28 +2392,7 @@ function setupCLI() {
  */
 async function checkForUpdate() {
 	// Get current version from package.json ONLY
-	let currentVersion = 'unknown'; // Initialize with a default
-	try {
-		// Try to get the version from the installed package (if applicable) or current dir
-		let packageJsonPath = path.join(
-			process.cwd(),
-			'node_modules',
-			'task-master-ai',
-			'package.json'
-		);
-		// Fallback to current directory package.json if not found in node_modules
-		if (!fs.existsSync(packageJsonPath)) {
-			packageJsonPath = path.join(process.cwd(), 'package.json');
-		}
-
-		if (fs.existsSync(packageJsonPath)) {
-			const packageJson = JSON.parse(fs.readFileSync(packageJsonPath, 'utf8'));
-			currentVersion = packageJson.version;
-		}
-	} catch (error) {
-		// Silently fail and use default
-		log('debug', `Error reading current package version: ${error.message}`);
-	}
+	const currentVersion = getTaskMasterVersion();
 
 	return new Promise((resolve) => {
 		// Get the latest version from npm registry

scripts/modules/config-manager.js

@@ -677,6 +677,13 @@ function getAllProviders() {
 	return Object.keys(MODEL_MAP || {});
 }
 
+function getBaseUrlForRole(role, explicitRoot = null) {
+	const roleConfig = getModelConfigForRole(role, explicitRoot);
+	return roleConfig && typeof roleConfig.baseUrl === 'string'
+		? roleConfig.baseUrl
+		: undefined;
+}
+
 export {
 	// Core config access
 	getConfig,
@@ -704,6 +711,7 @@ export {
 	getFallbackModelId,
 	getFallbackMaxTokens,
 	getFallbackTemperature,
+	getBaseUrlForRole,
 
 	// Global setting getters (No env var overrides)
 	getLogLevel,

scripts/modules/task-manager/set-task-status.js

@@ -8,6 +8,10 @@ import { validateTaskDependencies } from '../dependency-manager.js';
 import { getDebugFlag } from '../config-manager.js';
 import updateSingleTaskStatus from './update-single-task-status.js';
 import generateTaskFiles from './generate-task-files.js';
+import {
+	isValidTaskStatus,
+	TASK_STATUS_OPTIONS
+} from '../../../src/constants/task-status.js';
 
 /**
  * Set the status of a task
@@ -19,6 +23,11 @@ import generateTaskFiles from './generate-task-files.js';
  */
 async function setTaskStatus(tasksPath, taskIdInput, newStatus, options = {}) {
 	try {
+		if (!isValidTaskStatus(newStatus)) {
+			throw new Error(
+				`Error: Invalid status value: ${newStatus}. Use one of: ${TASK_STATUS_OPTIONS.join(', ')}`
+			);
+		}
 		// Determine if we're in MCP mode by checking for mcpLog
 		const isMcpMode = !!options?.mcpLog;
 

scripts/modules/task-manager/update-single-task-status.js

@@ -1,6 +1,7 @@
 import chalk from 'chalk';
 
 import { log } from '../utils.js';
+import { isValidTaskStatus } from '../../../src/constants/task-status.js';
 
 /**
  * Update the status of a single task
@@ -17,6 +18,12 @@ async function updateSingleTaskStatus(
 	data,
 	showUi = true
 ) {
+	if (!isValidTaskStatus(newStatus)) {
+		throw new Error(
+			`Error: Invalid status value: ${newStatus}. Use one of: ${TASK_STATUS_OPTIONS.join(', ')}`
+		);
+	}
+
 	// Check if it's a subtask (e.g., "1.2")
 	if (taskIdInput.includes('.')) {
 		const [parentId, subtaskId] = taskIdInput

scripts/modules/ui.js

@@ -16,10 +16,11 @@ import {
 	truncate,
 	isSilentMode
 } from './utils.js';
-import path from 'path';
 import fs from 'fs';
 import { findNextTask, analyzeTaskComplexity } from './task-manager.js';
 import { getProjectName, getDefaultSubtasks } from './config-manager.js';
+import { TASK_STATUS_OPTIONS } from '../../src/constants/task-status.js';
+import { getTaskMasterVersion } from '../../src/utils/getVersion.js';
 
 // Create a color gradient for the banner
 const coolGradient = gradient(['#00b4d8', '#0077b6', '#03045e']);
@@ -46,17 +47,7 @@ function displayBanner() {
 	);
 
 	// Read version directly from package.json
-	let version = 'unknown'; // Initialize with a default
-	try {
-		const packageJsonPath = path.join(process.cwd(), 'package.json');
-		if (fs.existsSync(packageJsonPath)) {
-			const packageJson = JSON.parse(fs.readFileSync(packageJsonPath, 'utf8'));
-			version = packageJson.version;
-		}
-	} catch (error) {
-		// Silently fall back to default version
-		log('warn', 'Could not read package.json for version info.');
-	}
+	const version = getTaskMasterVersion();
 
 	console.log(
 		boxen(
@@ -458,7 +449,7 @@ function displayHelp() {
 				{
 					name: 'set-status',
 					args: '--id=<id> --status=<status>',
-					desc: 'Update task status (done, pending, etc.)'
+					desc: `Update task status (${TASK_STATUS_OPTIONS.join(', ')})`
 				},
 				{
 					name: 'update',
@@ -809,12 +800,7 @@ async function displayNextTask(tasksPath) {
 			'padding-bottom': 0,
 			compact: true
 		},
-		chars: {
-			mid: '',
-			'left-mid': '',
-			'mid-mid': '',
-			'right-mid': ''
-		},
+		chars: { mid: '', 'left-mid': '', 'mid-mid': '', 'right-mid': '' },
 		colWidths: [15, Math.min(75, process.stdout.columns - 20 || 60)],
 		wordWrap: true
 	});
@@ -902,12 +888,7 @@ async function displayNextTask(tasksPath) {
 				'padding-bottom': 0,
 				compact: true
 			},
-			chars: {
-				mid: '',
-				'left-mid': '',
-				'mid-mid': '',
-				'right-mid': ''
-			},
+			chars: { mid: '', 'left-mid': '', 'mid-mid': '', 'right-mid': '' },
 			wordWrap: true
 		});
 

src/ai-providers/anthropic.js

@@ -5,7 +5,7 @@
  * using the Vercel AI SDK.
  */
 import { createAnthropic } from '@ai-sdk/anthropic';
-import { generateText, streamText, generateObject, streamObject } from 'ai';
+import { generateText, streamText, generateObject } from 'ai';
 import { log } from '../../scripts/modules/utils.js'; // Assuming utils is accessible
 
 // TODO: Implement standardized functions for generateText, streamText, generateObject
@@ -17,7 +17,7 @@ import { log } from '../../scripts/modules/utils.js'; // Assuming utils is acces
 // Remove the global variable and caching logic
 // let anthropicClient;
 
-function getClient(apiKey) {
+function getClient(apiKey, baseUrl) {
 	if (!apiKey) {
 		// In a real scenario, this would use the config resolver.
 		// Throwing error here if key isn't passed for simplicity.
@@ -30,14 +30,12 @@ function getClient(apiKey) {
 	// Create and return a new instance directly with standard version header
 	return createAnthropic({
 		apiKey: apiKey,
-		baseURL: 'https://api.anthropic.com/v1',
+		...(baseUrl && { baseURL: baseUrl }),
 		// Use standard version header instead of beta
 		headers: {
 			'anthropic-beta': 'output-128k-2025-02-19'
 		}
 	});
-	// }
-	// return anthropicClient;
 }
 
 // --- Standardized Service Function Implementations ---
@@ -51,6 +49,7 @@ function getClient(apiKey) {
  * @param {Array<object>} params.messages - The messages array (e.g., [{ role: 'user', content: '...' }]).
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
+ * @param {string} [params.baseUrl] - The base URL for the Anthropic API.
  * @returns {Promise<string>} The generated text content.
  * @throws {Error} If the API call fails.
  */
@@ -59,11 +58,12 @@ export async function generateAnthropicText({
 	modelId,
 	messages,
 	maxTokens,
-	temperature
+	temperature,
+	baseUrl
 }) {
 	log('debug', `Generating Anthropic text with model: ${modelId}`);
 	try {
-		const client = getClient(apiKey);
+		const client = getClient(apiKey, baseUrl);
 		const result = await generateText({
 			model: client(modelId),
 			messages: messages,
@@ -93,6 +93,7 @@ export async function generateAnthropicText({
  * @param {Array<object>} params.messages - The messages array.
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
+ * @param {string} [params.baseUrl] - The base URL for the Anthropic API.
  * @returns {Promise<object>} The full stream result object from the Vercel AI SDK.
  * @throws {Error} If the API call fails to initiate the stream.
  */
@@ -101,20 +102,20 @@ export async function streamAnthropicText({
 	modelId,
 	messages,
 	maxTokens,
-	temperature
+	temperature,
+	baseUrl
 }) {
 	log('debug', `Streaming Anthropic text with model: ${modelId}`);
 	try {
-		const client = getClient(apiKey);
+		const client = getClient(apiKey, baseUrl);
 
-		// --- DEBUG LOGGING --- >>
 		log(
 			'debug',
 			'[streamAnthropicText] Parameters received by streamText:',
 			JSON.stringify(
 				{
-					modelId: modelId, // Log modelId being used
-					messages: messages, // Log the messages array
+					modelId: modelId,
+					messages: messages,
 					maxTokens: maxTokens,
 					temperature: temperature
 				},
@@ -122,25 +123,19 @@ export async function streamAnthropicText({
 				2
 			)
 		);
-		// --- << DEBUG LOGGING ---
 
 		const stream = await streamText({
 			model: client(modelId),
 			messages: messages,
 			maxTokens: maxTokens,
 			temperature: temperature
-			// Beta header moved to client initialization
 			// TODO: Add other relevant parameters
 		});
 
 		// *** RETURN THE FULL STREAM OBJECT, NOT JUST stream.textStream ***
 		return stream;
 	} catch (error) {
-		log(
-			'error',
-			`Anthropic streamText failed: ${error.message}`,
-			error.stack // Log stack trace for more details
-		);
+		log('error', `Anthropic streamText failed: ${error.message}`, error.stack);
 		throw error;
 	}
 }
@@ -160,6 +155,7 @@ export async function streamAnthropicText({
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
  * @param {number} [params.maxRetries] - Max retries for validation/generation.
+ * @param {string} [params.baseUrl] - The base URL for the Anthropic API.
  * @returns {Promise<object>} The generated object matching the schema.
  * @throws {Error} If generation or validation fails.
  */
@@ -171,24 +167,22 @@ export async function generateAnthropicObject({
 	objectName = 'generated_object',
 	maxTokens,
 	temperature,
-	maxRetries = 3
+	maxRetries = 3,
+	baseUrl
 }) {
 	log(
 		'debug',
 		`Generating Anthropic object ('${objectName}') with model: ${modelId}`
 	);
 	try {
-		const client = getClient(apiKey);
-
-		// Log basic debug info
+		const client = getClient(apiKey, baseUrl);
 		log(
 			'debug',
 			`Using maxTokens: ${maxTokens}, temperature: ${temperature}, model: ${modelId}`
 		);
-
 		const result = await generateObject({
 			model: client(modelId),
-			mode: 'tool', // Anthropic generally uses 'tool' mode for structured output
+			mode: 'tool',
 			schema: schema,
 			messages: messages,
 			tool: {
@@ -199,14 +193,12 @@ export async function generateAnthropicObject({
 			temperature: temperature,
 			maxRetries: maxRetries
 		});
-
 		log(
 			'debug',
 			`Anthropic generateObject result received. Tokens: ${result.usage.completionTokens}/${result.usage.promptTokens}`
 		);
 		return result.object;
 	} catch (error) {
-		// Simple error logging
 		log(
 			'error',
 			`Anthropic generateObject ('${objectName}') failed: ${error.message}`

src/ai-providers/google.js

@@ -12,6 +12,16 @@ import { log } from '../../scripts/modules/utils.js'; // Import logging utility
 const DEFAULT_MODEL = 'gemini-2.0-pro'; // Or a suitable default
 const DEFAULT_TEMPERATURE = 0.2; // Or a suitable default
 
+function getClient(apiKey, baseUrl) {
+	if (!apiKey) {
+		throw new Error('Google API key is required.');
+	}
+	return createGoogleGenerativeAI({
+		apiKey: apiKey,
+		...(baseUrl && { baseURL: baseUrl })
+	});
+}
+
 /**
  * Generates text using a Google AI model.
  *
@@ -29,7 +39,8 @@ async function generateGoogleText({
 	modelId = DEFAULT_MODEL,
 	temperature = DEFAULT_TEMPERATURE,
 	messages,
-	maxTokens // Note: Vercel SDK might handle this differently, needs verification
+	maxTokens,
+	baseUrl
 }) {
 	if (!apiKey) {
 		throw new Error('Google API key is required.');
@@ -37,28 +48,21 @@ async function generateGoogleText({
 	log('info', `Generating text with Google model: ${modelId}`);
 
 	try {
-		// const google = new GoogleGenerativeAI({ apiKey }); // Incorrect instantiation
-		const googleProvider = createGoogleGenerativeAI({ apiKey }); // Correct instantiation
-		// const model = google.getGenerativeModel({ model: modelId }); // Incorrect model retrieval
-		const model = googleProvider(modelId); // Correct model retrieval
-
-		// Construct payload suitable for Vercel SDK's generateText
-		// Note: The exact structure might depend on how messages are passed
+		const googleProvider = getClient(apiKey, baseUrl);
+		const model = googleProvider(modelId);
 		const result = await generateText({
-			model, // Pass the model instance
-			messages, // Pass the messages array directly
+			model,
+			messages,
 			temperature,
-			maxOutputTokens: maxTokens // Map to correct Vercel SDK param if available
+			maxOutputTokens: maxTokens
 		});
-
-		// Assuming result structure provides text directly or within a property
-		return result.text; // Adjust based on actual SDK response
+		return result.text;
 	} catch (error) {
 		log(
 			'error',
 			`Error generating text with Google (${modelId}): ${error.message}`
 		);
-		throw error; // Re-throw for unified service handler
+		throw error;
 	}
 }
 
@@ -79,7 +83,8 @@ async function streamGoogleText({
 	modelId = DEFAULT_MODEL,
 	temperature = DEFAULT_TEMPERATURE,
 	messages,
-	maxTokens
+	maxTokens,
+	baseUrl
 }) {
 	if (!apiKey) {
 		throw new Error('Google API key is required.');
@@ -87,19 +92,15 @@ async function streamGoogleText({
 	log('info', `Streaming text with Google model: ${modelId}`);
 
 	try {
-		// const google = new GoogleGenerativeAI({ apiKey }); // Incorrect instantiation
-		const googleProvider = createGoogleGenerativeAI({ apiKey }); // Correct instantiation
-		// const model = google.getGenerativeModel({ model: modelId }); // Incorrect model retrieval
-		const model = googleProvider(modelId); // Correct model retrieval
-
+		const googleProvider = getClient(apiKey, baseUrl);
+		const model = googleProvider(modelId);
 		const stream = await streamText({
-			model, // Pass the model instance
+			model,
 			messages,
 			temperature,
 			maxOutputTokens: maxTokens
 		});
-
-		return stream; // Return the stream directly
+		return stream;
 	} catch (error) {
 		log(
 			'error',
@@ -130,7 +131,8 @@ async function generateGoogleObject({
 	messages,
 	schema,
 	objectName, // Note: Vercel SDK might use this differently or not at all
-	maxTokens
+	maxTokens,
+	baseUrl
 }) {
 	if (!apiKey) {
 		throw new Error('Google API key is required.');
@@ -138,23 +140,16 @@ async function generateGoogleObject({
 	log('info', `Generating object with Google model: ${modelId}`);
 
 	try {
-		// const google = new GoogleGenerativeAI({ apiKey }); // Incorrect instantiation
-		const googleProvider = createGoogleGenerativeAI({ apiKey }); // Correct instantiation
-		// const model = google.getGenerativeModel({ model: modelId }); // Incorrect model retrieval
-		const model = googleProvider(modelId); // Correct model retrieval
-
+		const googleProvider = getClient(apiKey, baseUrl);
+		const model = googleProvider(modelId);
 		const { object } = await generateObject({
-			model, // Pass the model instance
+			model,
 			schema,
 			messages,
 			temperature,
 			maxOutputTokens: maxTokens
-			// Note: 'objectName' or 'mode' might not be directly applicable here
-			// depending on how `@ai-sdk/google` handles `generateObject`.
-			// Check SDK docs if specific tool calling/JSON mode needs explicit setup.
 		});
-
-		return object; // Return the parsed object
+		return object;
 	} catch (error) {
 		log(
 			'error',

src/ai-providers/openai.js

@@ -1,16 +1,26 @@
-import { createOpenAI, openai } from '@ai-sdk/openai'; // Using openai provider from Vercel AI SDK
-import { generateText, streamText, generateObject } from 'ai'; // Import necessary functions from 'ai'
+import { createOpenAI } from '@ai-sdk/openai'; // Using openai provider from Vercel AI SDK
+import { generateObject } from 'ai'; // Import necessary functions from 'ai'
 import { log } from '../../scripts/modules/utils.js';
 
+function getClient(apiKey, baseUrl) {
+	if (!apiKey) {
+		throw new Error('OpenAI API key is required.');
+	}
+	return createOpenAI({
+		apiKey: apiKey,
+		...(baseUrl && { baseURL: baseUrl })
+	});
+}
+
 /**
  * Generates text using OpenAI models via Vercel AI SDK.
  *
- * @param {object} params - Parameters including apiKey, modelId, messages, maxTokens, temperature.
+ * @param {object} params - Parameters including apiKey, modelId, messages, maxTokens, temperature, baseUrl.
  * @returns {Promise<string>} The generated text content.
  * @throws {Error} If API call fails.
  */
 export async function generateOpenAIText(params) {
-	const { apiKey, modelId, messages, maxTokens, temperature } = params;
+	const { apiKey, modelId, messages, maxTokens, temperature, baseUrl } = params;
 	log('debug', `generateOpenAIText called with model: ${modelId}`);
 
 	if (!apiKey) {
@@ -23,18 +33,15 @@ export async function generateOpenAIText(params) {
 		throw new Error('Invalid or empty messages array provided for OpenAI.');
 	}
 
-	const openaiClient = createOpenAI({ apiKey });
+	const openaiClient = getClient(apiKey, baseUrl);
 
 	try {
 		const result = await openaiClient.chat(messages, {
-			// Updated: Use openaiClient.chat directly
 			model: modelId,
 			max_tokens: maxTokens,
 			temperature
 		});
 
-		// Adjust based on actual Vercel SDK response structure for openaiClient.chat
-		// This might need refinement based on testing the SDK's output.
 		const textContent = result?.choices?.[0]?.message?.content?.trim();
 
 		if (!textContent) {
@@ -65,12 +72,12 @@ export async function generateOpenAIText(params) {
 /**
  * Streams text using OpenAI models via Vercel AI SDK.
  *
- * @param {object} params - Parameters including apiKey, modelId, messages, maxTokens, temperature.
+ * @param {object} params - Parameters including apiKey, modelId, messages, maxTokens, temperature, baseUrl.
  * @returns {Promise<ReadableStream>} A readable stream of text deltas.
  * @throws {Error} If API call fails.
  */
 export async function streamOpenAIText(params) {
-	const { apiKey, modelId, messages, maxTokens, temperature } = params;
+	const { apiKey, modelId, messages, maxTokens, temperature, baseUrl } = params;
 	log('debug', `streamOpenAIText called with model: ${modelId}`);
 
 	if (!apiKey) {
@@ -85,12 +92,10 @@ export async function streamOpenAIText(params) {
 		);
 	}
 
-	const openaiClient = createOpenAI({ apiKey });
+	const openaiClient = getClient(apiKey, baseUrl);
 
 	try {
-		// Use the streamText function from Vercel AI SDK core
 		const stream = await openaiClient.chat.stream(messages, {
-			// Updated: Use openaiClient.chat.stream
 			model: modelId,
 			max_tokens: maxTokens,
 			temperature
@@ -100,7 +105,6 @@ export async function streamOpenAIText(params) {
 			'debug',
 			`OpenAI streamText initiated successfully for model: ${modelId}`
 		);
-		// The Vercel SDK's streamText should directly return the stream object
 		return stream;
 	} catch (error) {
 		log(
@@ -117,7 +121,7 @@ export async function streamOpenAIText(params) {
 /**
  * Generates structured objects using OpenAI models via Vercel AI SDK.
  *
- * @param {object} params - Parameters including apiKey, modelId, messages, schema, objectName, maxTokens, temperature.
+ * @param {object} params - Parameters including apiKey, modelId, messages, schema, objectName, maxTokens, temperature, baseUrl.
  * @returns {Promise<object>} The generated object matching the schema.
  * @throws {Error} If API call fails or object generation fails.
  */
@@ -129,7 +133,8 @@ export async function generateOpenAIObject(params) {
 		schema,
 		objectName,
 		maxTokens,
-		temperature
+		temperature,
+		baseUrl
 	} = params;
 	log(
 		'debug',
@@ -145,10 +150,9 @@ export async function generateOpenAIObject(params) {
 	if (!objectName)
 		throw new Error('Object name is required for OpenAI object generation.');
 
-	const openaiClient = createOpenAI({ apiKey });
+	const openaiClient = getClient(apiKey, baseUrl);
 
 	try {
-		// Use the imported generateObject function from 'ai' package
 		const result = await generateObject({
 			model: openaiClient(modelId),
 			schema: schema,

src/ai-providers/openrouter.js

@@ -2,6 +2,14 @@ import { createOpenRouter } from '@openrouter/ai-sdk-provider';
 import { generateText, streamText, generateObject } from 'ai';
 import { log } from '../../scripts/modules/utils.js'; // Assuming utils.js is in scripts/modules
 
+function getClient(apiKey, baseUrl) {
+	if (!apiKey) throw new Error('OpenRouter API key is required.');
+	return createOpenRouter({
+		apiKey,
+		...(baseUrl && { baseURL: baseUrl })
+	});
+}
+
 /**
  * Generates text using an OpenRouter chat model.
  *
@@ -11,6 +19,7 @@ import { log } from '../../scripts/modules/utils.js'; // Assuming utils.js is in
  * @param {Array<object>} params.messages - Array of message objects (system, user, assistant).
  * @param {number} [params.maxTokens] - Maximum tokens to generate.
  * @param {number} [params.temperature] - Sampling temperature.
+ * @param {string} [params.baseUrl] - Base URL for the OpenRouter API.
  * @returns {Promise<string>} The generated text content.
  * @throws {Error} If the API call fails.
  */
@@ -20,6 +29,7 @@ async function generateOpenRouterText({
 	messages,
 	maxTokens,
 	temperature,
+	baseUrl,
 	...rest // Capture any other Vercel AI SDK compatible parameters
 }) {
 	if (!apiKey) throw new Error('OpenRouter API key is required.');
@@ -28,7 +38,7 @@ async function generateOpenRouterText({
 		throw new Error('Messages array cannot be empty.');
 
 	try {
-		const openrouter = createOpenRouter({ apiKey });
+		const openrouter = getClient(apiKey, baseUrl);
 		const model = openrouter.chat(modelId); // Assuming chat model
 
 		const { text } = await generateText({
@@ -58,6 +68,7 @@ async function generateOpenRouterText({
  * @param {Array<object>} params.messages - Array of message objects (system, user, assistant).
  * @param {number} [params.maxTokens] - Maximum tokens to generate.
  * @param {number} [params.temperature] - Sampling temperature.
+ * @param {string} [params.baseUrl] - Base URL for the OpenRouter API.
  * @returns {Promise<ReadableStream<string>>} A readable stream of text deltas.
  * @throws {Error} If the API call fails.
  */
@@ -67,6 +78,7 @@ async function streamOpenRouterText({
 	messages,
 	maxTokens,
 	temperature,
+	baseUrl,
 	...rest
 }) {
 	if (!apiKey) throw new Error('OpenRouter API key is required.');
@@ -75,7 +87,7 @@ async function streamOpenRouterText({
 		throw new Error('Messages array cannot be empty.');
 
 	try {
-		const openrouter = createOpenRouter({ apiKey });
+		const openrouter = getClient(apiKey, baseUrl);
 		const model = openrouter.chat(modelId);
 
 		// Directly return the stream from the Vercel AI SDK function
@@ -108,6 +120,7 @@ async function streamOpenRouterText({
  * @param {number} [params.maxRetries=3] - Max retries for object generation.
  * @param {number} [params.maxTokens] - Maximum tokens.
  * @param {number} [params.temperature] - Temperature.
+ * @param {string} [params.baseUrl] - Base URL for the OpenRouter API.
  * @returns {Promise<object>} The generated object matching the schema.
  * @throws {Error} If the API call fails or validation fails.
  */
@@ -120,6 +133,7 @@ async function generateOpenRouterObject({
 	maxRetries = 3,
 	maxTokens,
 	temperature,
+	baseUrl,
 	...rest
 }) {
 	if (!apiKey) throw new Error('OpenRouter API key is required.');
@@ -129,7 +143,7 @@ async function generateOpenRouterObject({
 		throw new Error('Messages array cannot be empty.');
 
 	try {
-		const openrouter = createOpenRouter({ apiKey });
+		const openrouter = getClient(apiKey, baseUrl);
 		const model = openrouter.chat(modelId);
 
 		const { object } = await generateObject({

src/ai-providers/perplexity.js

@@ -10,13 +10,13 @@ import { log } from '../../scripts/modules/utils.js';
 
 // --- Client Instantiation ---
 // Similar to Anthropic, this expects the resolved API key to be passed in.
-function getClient(apiKey) {
+function getClient(apiKey, baseUrl) {
 	if (!apiKey) {
 		throw new Error('Perplexity API key is required.');
 	}
-	// Create and return a new instance directly
 	return createPerplexity({
-		apiKey: apiKey
+		apiKey: apiKey,
+		...(baseUrl && { baseURL: baseUrl })
 	});
 }
 
@@ -31,6 +31,7 @@ function getClient(apiKey) {
  * @param {Array<object>} params.messages - The messages array.
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
+ * @param {string} [params.baseUrl] - Base URL for the Perplexity API.
  * @returns {Promise<string>} The generated text content.
  * @throws {Error} If the API call fails.
  */
@@ -39,11 +40,12 @@ export async function generatePerplexityText({
 	modelId,
 	messages,
 	maxTokens,
-	temperature
+	temperature,
+	baseUrl
 }) {
 	log('debug', `Generating Perplexity text with model: ${modelId}`);
 	try {
-		const client = getClient(apiKey);
+		const client = getClient(apiKey, baseUrl);
 		const result = await generateText({
 			model: client(modelId),
 			messages: messages,
@@ -70,6 +72,7 @@ export async function generatePerplexityText({
  * @param {Array<object>} params.messages - The messages array.
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
+ * @param {string} [params.baseUrl] - Base URL for the Perplexity API.
  * @returns {Promise<object>} The full stream result object from the Vercel AI SDK.
  * @throws {Error} If the API call fails to initiate the stream.
  */
@@ -78,11 +81,12 @@ export async function streamPerplexityText({
 	modelId,
 	messages,
 	maxTokens,
-	temperature
+	temperature,
+	baseUrl
 }) {
 	log('debug', `Streaming Perplexity text with model: ${modelId}`);
 	try {
-		const client = getClient(apiKey);
+		const client = getClient(apiKey, baseUrl);
 		const stream = await streamText({
 			model: client(modelId),
 			messages: messages,
@@ -112,6 +116,7 @@ export async function streamPerplexityText({
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
  * @param {number} [params.maxRetries] - Max retries for validation/generation.
+ * @param {string} [params.baseUrl] - Base URL for the Perplexity API.
  * @returns {Promise<object>} The generated object matching the schema.
  * @throws {Error} If generation or validation fails or is unsupported.
  */
@@ -123,7 +128,8 @@ export async function generatePerplexityObject({
 	objectName = 'generated_object',
 	maxTokens,
 	temperature,
-	maxRetries = 1 // Lower retries as support might be limited
+	maxRetries = 1,
+	baseUrl
 }) {
 	log(
 		'debug',
@@ -134,8 +140,7 @@ export async function generatePerplexityObject({
 		'generateObject support for Perplexity might be limited or experimental.'
 	);
 	try {
-		const client = getClient(apiKey);
-		// Attempt using generateObject, but be prepared for potential issues
+		const client = getClient(apiKey, baseUrl);
 		const result = await generateObject({
 			model: client(modelId),
 			schema: schema,

src/ai-providers/xai.js

@@ -9,14 +9,13 @@ import { generateText, streamText, generateObject } from 'ai'; // Only import wh
 import { log } from '../../scripts/modules/utils.js'; // Assuming utils is accessible
 
 // --- Client Instantiation ---
-function getClient(apiKey) {
+function getClient(apiKey, baseUrl) {
 	if (!apiKey) {
 		throw new Error('xAI API key is required.');
 	}
-	// Create and return a new instance directly
 	return createXai({
-		apiKey: apiKey
-		// Add baseURL or other options if needed later
+		apiKey: apiKey,
+		...(baseUrl && { baseURL: baseUrl })
 	});
 }
 
@@ -31,6 +30,7 @@ function getClient(apiKey) {
  * @param {Array<object>} params.messages - The messages array (e.g., [{ role: 'user', content: '...' }]).
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
+ * @param {string} [params.baseUrl] - The base URL for the xAI API.
  * @returns {Promise<string>} The generated text content.
  * @throws {Error} If the API call fails.
  */
@@ -39,13 +39,14 @@ export async function generateXaiText({
 	modelId,
 	messages,
 	maxTokens,
-	temperature
+	temperature,
+	baseUrl
 }) {
 	log('debug', `Generating xAI text with model: ${modelId}`);
 	try {
-		const client = getClient(apiKey);
+		const client = getClient(apiKey, baseUrl);
 		const result = await generateText({
-			model: client(modelId), // Correct model invocation
+			model: client(modelId),
 			messages: messages,
 			maxTokens: maxTokens,
 			temperature: temperature
@@ -70,6 +71,7 @@ export async function generateXaiText({
  * @param {Array<object>} params.messages - The messages array.
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
+ * @param {string} [params.baseUrl] - The base URL for the xAI API.
  * @returns {Promise<object>} The full stream result object from the Vercel AI SDK.
  * @throws {Error} If the API call fails to initiate the stream.
  */
@@ -78,18 +80,19 @@ export async function streamXaiText({
 	modelId,
 	messages,
 	maxTokens,
-	temperature
+	temperature,
+	baseUrl
 }) {
 	log('debug', `Streaming xAI text with model: ${modelId}`);
 	try {
-		const client = getClient(apiKey);
+		const client = getClient(apiKey, baseUrl);
 		const stream = await streamText({
-			model: client(modelId), // Correct model invocation
+			model: client(modelId),
 			messages: messages,
 			maxTokens: maxTokens,
 			temperature: temperature
 		});
-		return stream; // Return the full stream object
+		return stream;
 	} catch (error) {
 		log('error', `xAI streamText failed: ${error.message}`, error.stack);
 		throw error;
@@ -110,6 +113,7 @@ export async function streamXaiText({
  * @param {number} [params.maxTokens] - Maximum tokens for the response.
  * @param {number} [params.temperature] - Temperature for generation.
  * @param {number} [params.maxRetries] - Max retries for validation/generation.
+ * @param {string} [params.baseUrl] - The base URL for the xAI API.
  * @returns {Promise<object>} The generated object matching the schema.
  * @throws {Error} If generation or validation fails.
  */
@@ -121,16 +125,17 @@ export async function generateXaiObject({
 	objectName = 'generated_xai_object',
 	maxTokens,
 	temperature,
-	maxRetries = 3
+	maxRetries = 3,
+	baseUrl
 }) {
 	log(
-		'warn', // Log warning as this is likely unsupported
+		'warn',
 		`Attempting to generate xAI object ('${objectName}') with model: ${modelId}. This may not be supported by the provider.`
 	);
 	try {
-		const client = getClient(apiKey);
+		const client = getClient(apiKey, baseUrl);
 		const result = await generateObject({
-			model: client(modelId), // Correct model invocation
+			model: client(modelId),
 			// Note: mode might need adjustment if xAI ever supports object generation differently
 			mode: 'tool',
 			schema: schema,
@@ -153,6 +158,6 @@ export async function generateXaiObject({
 			'error',
 			`xAI generateObject ('${objectName}') failed: ${error.message}. (Likely unsupported by provider)`
 		);
-		throw error; // Re-throw the error
+		throw error;
 	}
 }

src/constants/task-status.js

@@ -0,0 +1,32 @@
+/**
+ * @typedef {'pending' | 'done' | 'in-progress' | 'review' | 'deferred' | 'cancelled'} TaskStatus
+ */
+
+/**
+ * Task status options list
+ * @type {TaskStatus[]}
+ * @description Defines possible task statuses:
+ * - pending: Task waiting to start
+ * - done: Task completed
+ * - in-progress: Task in progress
+ * - review: Task completed and waiting for review
+ * - deferred: Task postponed or paused
+ * - cancelled: Task cancelled and will not be completed
+ */
+export const TASK_STATUS_OPTIONS = [
+	'pending',
+	'done',
+	'in-progress',
+	'review',
+	'deferred',
+	'cancelled'
+];
+
+/**
+ * Check if a given status is a valid task status
+ * @param {string} status - The status to check
+ * @returns {boolean} True if the status is valid, false otherwise
+ */
+export function isValidTaskStatus(status) {
+	return TASK_STATUS_OPTIONS.includes(status);
+}

src/utils/getVersion.js

@@ -0,0 +1,35 @@
+import fs from 'fs';
+import path from 'path';
+import { fileURLToPath } from 'url';
+import { log } from '../../scripts/modules/utils.js';
+
+/**
+ * Reads the version from the nearest package.json relative to this file.
+ * Returns 'unknown' if not found or on error.
+ * @returns {string} The version string or 'unknown'.
+ */
+export function getTaskMasterVersion() {
+	let version = 'unknown';
+	try {
+		// Get the directory of the current module (getPackageVersion.js)
+		const currentModuleFilename = fileURLToPath(import.meta.url);
+		const currentModuleDirname = path.dirname(currentModuleFilename);
+		// Construct the path to package.json relative to this file (../../package.json)
+		const packageJsonPath = path.join(
+			currentModuleDirname,
+			'..',
+			'..',
+			'package.json'
+		);
+
+		if (fs.existsSync(packageJsonPath)) {
+			const packageJsonContent = fs.readFileSync(packageJsonPath, 'utf8');
+			const packageJson = JSON.parse(packageJsonContent);
+			version = packageJson.version;
+		}
+	} catch (error) {
+		// Silently fall back to default version
+		log('warn', 'Could not read own package.json for version info.', error);
+	}
+	return version;
+}

tests/setup.js

@@ -9,7 +9,7 @@ process.env.MODEL = 'sonar-pro';
 process.env.MAX_TOKENS = '64000';
 process.env.TEMPERATURE = '0.2';
 process.env.DEBUG = 'false';
-process.env.LOG_LEVEL = 'error'; // Set to error to reduce noise in tests
+process.env.TASKMASTER_LOG_LEVEL = 'error'; // Set to error to reduce noise in tests
 process.env.DEFAULT_SUBTASKS = '5';
 process.env.DEFAULT_PRIORITY = 'medium';
 process.env.PROJECT_NAME = 'Test Project';

tests/unit/ai-services-unified.test.js

@@ -8,6 +8,7 @@ const mockGetResearchModelId = jest.fn();
 const mockGetFallbackProvider = jest.fn();
 const mockGetFallbackModelId = jest.fn();
 const mockGetParametersForRole = jest.fn();
+const mockGetBaseUrlForRole = jest.fn();
 
 jest.unstable_mockModule('../../scripts/modules/config-manager.js', () => ({
 	getMainProvider: mockGetMainProvider,
@@ -16,7 +17,8 @@ jest.unstable_mockModule('../../scripts/modules/config-manager.js', () => ({
 	getResearchModelId: mockGetResearchModelId,
 	getFallbackProvider: mockGetFallbackProvider,
 	getFallbackModelId: mockGetFallbackModelId,
-	getParametersForRole: mockGetParametersForRole
+	getParametersForRole: mockGetParametersForRole,
+	getBaseUrlForRole: mockGetBaseUrlForRole
 }));
 
 // Mock AI Provider Modules

tests/unit/task-manager.test.js

@@ -199,6 +199,12 @@ const testSetTaskStatus = (tasksData, taskIdInput, newStatus) => {
 
 // Simplified version of updateSingleTaskStatus for testing
 const testUpdateSingleTaskStatus = (tasksData, taskIdInput, newStatus) => {
+	if (!isValidTaskStatus(newStatus)) {
+		throw new Error(
+			`Error: Invalid status value: ${newStatus}. Use one of: ${TASK_STATUS_OPTIONS.join(', ')}`
+		);
+	}
+
 	// Check if it's a subtask (e.g., "1.2")
 	if (taskIdInput.includes('.')) {
 		const [parentId, subtaskId] = taskIdInput
@@ -329,6 +335,10 @@ const testAddTask = (
 import * as taskManager from '../../scripts/modules/task-manager.js';
 import { sampleClaudeResponse } from '../fixtures/sample-claude-response.js';
 import { sampleTasks, emptySampleTasks } from '../fixtures/sample-tasks.js';
+import {
+	isValidTaskStatus,
+	TASK_STATUS_OPTIONS
+} from '../../src/constants/task-status.js';
 
 // Destructure the required functions for convenience
 const { findNextTask, generateTaskFiles, clearSubtasks, updateTaskById } =
@@ -1165,6 +1175,16 @@ describe('Task Manager Module', () => {
 			expect(testTasksData.tasks[1].status).toBe('done');
 		});
 
+		test('should throw error for invalid status', async () => {
+			// Arrange
+			const testTasksData = JSON.parse(JSON.stringify(sampleTasks));
+
+			// Assert
+			expect(() =>
+				testUpdateSingleTaskStatus(testTasksData, '2', 'Done')
+			).toThrow(/Error: Invalid status value: Done./);
+		});
+
 		test('should update subtask status', async () => {
 			// Arrange
 			const testTasksData = JSON.parse(JSON.stringify(sampleTasks));