Compare commits

..

13 Commits

Author SHA1 Message Date
Manfred Riem
f5f8311415 fix: correct PresetError docstring from template to preset 2026-03-10 17:20:54 -05:00
Manfred Riem
6da1375396 fix: address Copilot PR review comments (round 3)
- Fix PS Resolve-Template fallback to skip dot-prefixed dirs (.cache)
- Rename _catalog to _catalog_name for consistency with extension system
- Enforce install_allowed policy in CLI preset add and download_pack()
- Fix shell injection: pass registry path via env var instead of string interpolation
2026-03-10 17:06:34 -05:00
Manfred Riem
1c143e64b1 fix: remove self-test from catalog.json (local-only preset) 2026-03-10 16:39:07 -05:00
Manfred Riem
da6e7d2283 fix: address Copilot PR review comments (round 2)
- Fix init --preset error masking: distinguish "not found" from real errors
- Fix bash resolve_template: skip hidden dirs in extensions (match Python/PS)
- Fix temp dir leaks in tests: use temp_dir fixture instead of mkdtemp
- Fix self-test catalog entry: add note that it's local-only (no download_url)
- Fix Windows path issue in resolve_with_source: use Path.relative_to()
- Fix skill restore path: use project's .specify/templates/commands/ not source tree
- Add encoding="utf-8" to all file read/write in agents.py
- Update test to set up core command templates for skill restoration
2026-03-10 16:35:17 -05:00
Manfred Riem
3ffef55954 fix: narrow empty except blocks and add explanatory comments 2026-03-10 15:16:43 -05:00
Manfred Riem
52f137ce84 fix: address Copilot PR review comments
- Move save_init_options() before preset install so skills propagation
  works during 'specify init --preset --ai-skills'
- Clean up downloaded ZIP after successful preset install during init
- Validate --from URL scheme (require HTTPS, HTTP only for localhost)
- Expose unregister_commands() on extensions.py CommandRegistrar wrapper
  instead of reaching into private _registrar field
- Use _get_merged_packs() for search() and get_pack_info() so all
  active catalogs are searched, not just the highest-priority one
- Fix fetch_catalog() cache to verify cached URL matches current URL
- Fix PresetResolver: script resolution uses .sh extension, consistent
  file extensions throughout resolve(), and resolve_with_source()
  delegates to resolve() to honor template_type parameter
- Fix bash common.sh: fall through to directory scan when python3
  returns empty preset list
- Fix PowerShell Resolve-Template: filter out dot-folders and sort
  extensions deterministically
2026-03-10 15:11:31 -05:00
Manfred Riem
445eefe5ba fix: address PR check failures (ruff F541, CodeQL URL substring)
- Remove extraneous f-prefix from two f-strings without placeholders
- Replace substring URL check in test with startswith/endswith assertions
  to satisfy CodeQL incomplete URL substring sanitization rule
2026-03-10 14:45:16 -05:00
Manfred Riem
35ced30747 feat(presets): propagate command overrides to skills via init-options
- Add save_init_options() / load_init_options() helpers that persist
  CLI flags from 'specify init' to .specify/init-options.json
- PresetManager._register_skills() overwrites SKILL.md files when
  --ai-skills was used during init and corresponding skill dirs exist
- PresetManager._unregister_skills() restores core template content
  on preset removal
- registered_skills stored in preset registry metadata
- 8 new tests covering skill override, skip conditions, and restore
2026-03-10 14:31:17 -05:00
Manfred Riem
914a06a89f Merge remote-tracking branch 'upstream/main' into pr-1787
# Conflicts:
#	CHANGELOG.md
#	src/specify_cli/extensions.py
2026-03-10 14:20:38 -05:00
Manfred Riem
abf4aebdb3 feat(presets): pluggable preset system with template/command overrides, catalog, and resolver
- Rename 'template packs' to 'presets' to avoid naming collision with core templates
- PresetManifest, PresetRegistry, PresetManager, PresetCatalog, PresetResolver in presets.py
- Extract CommandRegistrar to agents.py as shared infrastructure
- CLI: specify preset list/add/remove/search/resolve/info
- CLI: specify preset catalog list/add/remove
- --preset option on specify init
- Priority-based preset stacking (--priority, lower = higher precedence)
- Command overrides registered into all detected agent directories (17+ agents)
- Extension command safety: skip registration if target extension not installed
- Multi-catalog support: env var, project config, user config, built-in defaults
- resolve_template() / Resolve-Template in bash/PowerShell scripts
- Self-test preset: overrides all 6 core templates + 1 command
- Scaffold with 4 examples: core/extension template and command overrides
- Preset catalog (catalog.json, catalog.community.json)
- Documentation: README.md, ARCHITECTURE.md, PUBLISHING.md
- 110 preset tests, 253 total tests passing
2026-03-10 14:17:44 -05:00
copilot-swe-agent[bot]
6003a232d8 test(templates): add comprehensive unit tests for template pack system
Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>
2026-03-09 21:05:27 +00:00
copilot-swe-agent[bot]
2e8a4d6432 feat(templates): add pluggable template system with packs, catalog, resolver, and CLI commands
Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>
2026-03-09 21:02:52 +00:00
copilot-swe-agent[bot]
65ecaa9fe4 Initial plan 2026-03-09 20:53:50 +00:00
33 changed files with 600 additions and 2320 deletions

View File

@@ -53,7 +53,7 @@ echo "✅ Done"
echo -e "\n🤖 Installing Kiro CLI..." echo -e "\n🤖 Installing Kiro CLI..."
# https://kiro.dev/docs/cli/ # https://kiro.dev/docs/cli/
KIRO_INSTALLER_URL="https://kiro.dev/install.sh" KIRO_INSTALLER_URL="https://cli.kiro.dev/install"
KIRO_INSTALLER_SHA256="7487a65cf310b7fb59b357c4b5e6e3f3259d383f4394ecedb39acf70f307cffb" KIRO_INSTALLER_SHA256="7487a65cf310b7fb59b357c4b5e6e3f3259d383f4394ecedb39acf70f307cffb"
KIRO_INSTALLER_PATH="$(mktemp)" KIRO_INSTALLER_PATH="$(mktemp)"
@@ -80,11 +80,6 @@ fi
run_command "$kiro_binary --help > /dev/null" run_command "$kiro_binary --help > /dev/null"
echo "✅ Done" echo "✅ Done"
echo -e "\n🤖 Installing Kimi CLI..."
# https://code.kimi.com
run_command "pipx install kimi-cli"
echo "✅ Done"
echo -e "\n🤖 Installing CodeBuddy CLI..." echo -e "\n🤖 Installing CodeBuddy CLI..."
run_command "npm install -g @tencent-ai/codebuddy-code@latest" run_command "npm install -g @tencent-ai/codebuddy-code@latest"
echo "✅ Done" echo "✅ Done"

2
.github/workflows/scripts/create-github-release.sh vendored Executable file → Normal file
View File

@@ -56,8 +56,6 @@ gh release create "$VERSION" \
.genreleases/spec-kit-template-bob-ps-"$VERSION".zip \ .genreleases/spec-kit-template-bob-ps-"$VERSION".zip \
.genreleases/spec-kit-template-vibe-sh-"$VERSION".zip \ .genreleases/spec-kit-template-vibe-sh-"$VERSION".zip \
.genreleases/spec-kit-template-vibe-ps-"$VERSION".zip \ .genreleases/spec-kit-template-vibe-ps-"$VERSION".zip \
.genreleases/spec-kit-template-kimi-sh-"$VERSION".zip \
.genreleases/spec-kit-template-kimi-ps-"$VERSION".zip \
.genreleases/spec-kit-template-generic-sh-"$VERSION".zip \ .genreleases/spec-kit-template-generic-sh-"$VERSION".zip \
.genreleases/spec-kit-template-generic-ps-"$VERSION".zip \ .genreleases/spec-kit-template-generic-ps-"$VERSION".zip \
--title "Spec Kit Templates - $VERSION_NO_V" \ --title "Spec Kit Templates - $VERSION_NO_V" \

View File

@@ -14,7 +14,7 @@
.PARAMETER Agents .PARAMETER Agents
Comma or space separated subset of agents to build (default: all) Comma or space separated subset of agents to build (default: all)
Valid agents: claude, gemini, copilot, cursor-agent, qwen, opencode, windsurf, codex, kilocode, auggie, roo, codebuddy, amp, kiro-cli, bob, qodercli, shai, tabnine, agy, vibe, kimi, generic Valid agents: claude, gemini, copilot, cursor-agent, qwen, opencode, windsurf, codex, kilocode, auggie, roo, codebuddy, amp, kiro-cli, bob, qodercli, shai, tabnine, agy, vibe, generic
.PARAMETER Scripts .PARAMETER Scripts
Comma or space separated subset of script types to build (default: both) Comma or space separated subset of script types to build (default: both)
@@ -201,93 +201,6 @@ agent: $basename
} }
} }
# Create Kimi Code skills in .kimi/skills/<name>/SKILL.md format.
# Kimi CLI discovers skills as directories containing a SKILL.md file,
# invoked with /skill:<name> (e.g. /skill:speckit.specify).
function New-KimiSkills {
param(
[string]$SkillsDir,
[string]$ScriptVariant
)
$templates = Get-ChildItem -Path "templates/commands/*.md" -File -ErrorAction SilentlyContinue
foreach ($template in $templates) {
$name = [System.IO.Path]::GetFileNameWithoutExtension($template.Name)
$skillName = "speckit.$name"
$skillDir = Join-Path $SkillsDir $skillName
New-Item -ItemType Directory -Force -Path $skillDir | Out-Null
$fileContent = (Get-Content -Path $template.FullName -Raw) -replace "`r`n", "`n"
# Extract description
$description = "Spec Kit: $name workflow"
if ($fileContent -match '(?m)^description:\s*(.+)$') {
$description = $matches[1]
}
# Extract script command
$scriptCommand = "(Missing script command for $ScriptVariant)"
if ($fileContent -match "(?m)^\s*${ScriptVariant}:\s*(.+)$") {
$scriptCommand = $matches[1]
}
# Extract agent_script command from frontmatter if present
$agentScriptCommand = ""
if ($fileContent -match "(?ms)agent_scripts:.*?^\s*${ScriptVariant}:\s*(.+?)$") {
$agentScriptCommand = $matches[1].Trim()
}
# Replace {SCRIPT}, strip scripts sections, rewrite paths
$body = $fileContent -replace '\{SCRIPT\}', $scriptCommand
if (-not [string]::IsNullOrEmpty($agentScriptCommand)) {
$body = $body -replace '\{AGENT_SCRIPT\}', $agentScriptCommand
}
$lines = $body -split "`n"
$outputLines = @()
$inFrontmatter = $false
$skipScripts = $false
$dashCount = 0
foreach ($line in $lines) {
if ($line -match '^---$') {
$outputLines += $line
$dashCount++
$inFrontmatter = ($dashCount -eq 1)
continue
}
if ($inFrontmatter) {
if ($line -match '^(scripts|agent_scripts):$') { $skipScripts = $true; continue }
if ($line -match '^[a-zA-Z].*:' -and $skipScripts) { $skipScripts = $false }
if ($skipScripts -and $line -match '^\s+') { continue }
}
$outputLines += $line
}
$body = $outputLines -join "`n"
$body = $body -replace '\{ARGS\}', '$ARGUMENTS'
$body = $body -replace '__AGENT__', 'kimi'
$body = Rewrite-Paths -Content $body
# Strip existing frontmatter, keep only body
$templateBody = ""
$fmCount = 0
$inBody = $false
foreach ($line in ($body -split "`n")) {
if ($line -match '^---$') {
$fmCount++
if ($fmCount -eq 2) { $inBody = $true }
continue
}
if ($inBody) { $templateBody += "$line`n" }
}
$skillContent = "---`nname: `"$skillName`"`ndescription: `"$description`"`n---`n`n$templateBody"
Set-Content -Path (Join-Path $skillDir "SKILL.md") -Value $skillContent -NoNewline
}
}
function Build-Variant { function Build-Variant {
param( param(
[string]$Agent, [string]$Agent,
@@ -328,6 +241,7 @@ function Build-Variant {
} }
} }
# Copy any script files that aren't in variant-specific directories
Get-ChildItem -Path "scripts" -File -ErrorAction SilentlyContinue | ForEach-Object { Get-ChildItem -Path "scripts" -File -ErrorAction SilentlyContinue | ForEach-Object {
Copy-Item -Path $_.FullName -Destination $scriptsDestDir -Force Copy-Item -Path $_.FullName -Destination $scriptsDestDir -Force
} }
@@ -367,9 +281,11 @@ function Build-Variant {
$agentsDir = Join-Path $baseDir ".github/agents" $agentsDir = Join-Path $baseDir ".github/agents"
Generate-Commands -Agent 'copilot' -Extension 'agent.md' -ArgFormat '$ARGUMENTS' -OutputDir $agentsDir -ScriptVariant $Script Generate-Commands -Agent 'copilot' -Extension 'agent.md' -ArgFormat '$ARGUMENTS' -OutputDir $agentsDir -ScriptVariant $Script
# Generate companion prompt files
$promptsDir = Join-Path $baseDir ".github/prompts" $promptsDir = Join-Path $baseDir ".github/prompts"
Generate-CopilotPrompts -AgentsDir $agentsDir -PromptsDir $promptsDir Generate-CopilotPrompts -AgentsDir $agentsDir -PromptsDir $promptsDir
# Create VS Code workspace settings
$vscodeDir = Join-Path $baseDir ".vscode" $vscodeDir = Join-Path $baseDir ".vscode"
New-Item -ItemType Directory -Path $vscodeDir -Force | Out-Null New-Item -ItemType Directory -Path $vscodeDir -Force | Out-Null
if (Test-Path "templates/vscode-settings.json") { if (Test-Path "templates/vscode-settings.json") {
@@ -382,7 +298,7 @@ function Build-Variant {
} }
'qwen' { 'qwen' {
$cmdDir = Join-Path $baseDir ".qwen/commands" $cmdDir = Join-Path $baseDir ".qwen/commands"
Generate-Commands -Agent 'qwen' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script Generate-Commands -Agent 'qwen' -Extension 'toml' -ArgFormat '{{args}}' -OutputDir $cmdDir -ScriptVariant $Script
if (Test-Path "agent_templates/qwen/QWEN.md") { if (Test-Path "agent_templates/qwen/QWEN.md") {
Copy-Item -Path "agent_templates/qwen/QWEN.md" -Destination (Join-Path $baseDir "QWEN.md") Copy-Item -Path "agent_templates/qwen/QWEN.md" -Destination (Join-Path $baseDir "QWEN.md")
} }
@@ -442,22 +358,17 @@ function Build-Variant {
if (Test-Path $tabnineTemplate) { Copy-Item $tabnineTemplate (Join-Path $baseDir 'TABNINE.md') } if (Test-Path $tabnineTemplate) { Copy-Item $tabnineTemplate (Join-Path $baseDir 'TABNINE.md') }
} }
'agy' { 'agy' {
$cmdDir = Join-Path $baseDir ".agent/commands" $cmdDir = Join-Path $baseDir ".agent/workflows"
Generate-Commands -Agent 'agy' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script Generate-Commands -Agent 'agy' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
} }
'vibe' {
$cmdDir = Join-Path $baseDir ".vibe/prompts"
Generate-Commands -Agent 'vibe' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
'kimi' {
$skillsDir = Join-Path $baseDir ".kimi/skills"
New-Item -ItemType Directory -Force -Path $skillsDir | Out-Null
New-KimiSkills -SkillsDir $skillsDir -ScriptVariant $Script
}
'generic' { 'generic' {
$cmdDir = Join-Path $baseDir ".speckit/commands" $cmdDir = Join-Path $baseDir ".speckit/commands"
Generate-Commands -Agent 'generic' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script Generate-Commands -Agent 'generic' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
} }
'vibe' {
$cmdDir = Join-Path $baseDir ".vibe/prompts"
Generate-Commands -Agent 'vibe' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
default { default {
throw "Unsupported agent '$Agent'." throw "Unsupported agent '$Agent'."
} }
@@ -470,7 +381,7 @@ function Build-Variant {
} }
# Define all agents and scripts # Define all agents and scripts
$AllAgents = @('claude', 'gemini', 'copilot', 'cursor-agent', 'qwen', 'opencode', 'windsurf', 'codex', 'kilocode', 'auggie', 'roo', 'codebuddy', 'amp', 'kiro-cli', 'bob', 'qodercli', 'shai', 'tabnine', 'agy', 'vibe', 'kimi', 'generic') $AllAgents = @('claude', 'gemini', 'copilot', 'cursor-agent', 'qwen', 'opencode', 'windsurf', 'codex', 'kilocode', 'auggie', 'roo', 'codebuddy', 'amp', 'kiro-cli', 'bob', 'qodercli', 'shai', 'tabnine', 'agy', 'vibe', 'generic')
$AllScripts = @('sh', 'ps') $AllScripts = @('sh', 'ps')
function Normalize-List { function Normalize-List {
@@ -480,6 +391,7 @@ function Normalize-List {
return @() return @()
} }
# Split by comma or space and remove duplicates while preserving order
$items = $Input -split '[,\s]+' | Where-Object { $_ } | Select-Object -Unique $items = $Input -split '[,\s]+' | Where-Object { $_ } | Select-Object -Unique
return $items return $items
} }

View File

@@ -6,7 +6,7 @@ set -euo pipefail
# Usage: .github/workflows/scripts/create-release-packages.sh <version> # Usage: .github/workflows/scripts/create-release-packages.sh <version>
# Version argument should include leading 'v'. # Version argument should include leading 'v'.
# Optionally set AGENTS and/or SCRIPTS env vars to limit what gets built. # Optionally set AGENTS and/or SCRIPTS env vars to limit what gets built.
# AGENTS : space or comma separated subset of: claude gemini copilot cursor-agent qwen opencode windsurf codex kilocode auggie roo codebuddy amp shai tabnine kiro-cli agy bob vibe qodercli kimi generic (default: all) # AGENTS : space or comma separated subset of: claude gemini copilot cursor-agent qwen opencode windsurf codex kilocode auggie roo codebuddy amp shai tabnine kiro-cli agy bob vibe qodercli generic (default: all)
# SCRIPTS : space or comma separated subset of: sh ps (default: both) # SCRIPTS : space or comma separated subset of: sh ps (default: both)
# Examples: # Examples:
# AGENTS=claude SCRIPTS=sh $0 v0.2.0 # AGENTS=claude SCRIPTS=sh $0 v0.2.0
@@ -113,6 +113,7 @@ generate_copilot_prompts() {
local basename=$(basename "$agent_file" .agent.md) local basename=$(basename "$agent_file" .agent.md)
local prompt_file="$prompts_dir/${basename}.prompt.md" local prompt_file="$prompts_dir/${basename}.prompt.md"
# Create prompt file with agent frontmatter
cat > "$prompt_file" <<EOF cat > "$prompt_file" <<EOF
--- ---
agent: ${basename} agent: ${basename}
@@ -121,76 +122,6 @@ EOF
done done
} }
# Create Kimi Code skills in .kimi/skills/<name>/SKILL.md format.
# Kimi CLI discovers skills as directories containing a SKILL.md file,
# invoked with /skill:<name> (e.g. /skill:speckit.specify).
create_kimi_skills() {
local skills_dir="$1"
local script_variant="$2"
for template in templates/commands/*.md; do
[[ -f "$template" ]] || continue
local name
name=$(basename "$template" .md)
local skill_name="speckit.${name}"
local skill_dir="${skills_dir}/${skill_name}"
mkdir -p "$skill_dir"
local file_content
file_content=$(tr -d '\r' < "$template")
# Extract description from frontmatter
local description
description=$(printf '%s\n' "$file_content" | awk '/^description:/ {sub(/^description:[[:space:]]*/, ""); print; exit}')
[[ -z "$description" ]] && description="Spec Kit: ${name} workflow"
# Extract script command
local script_command
script_command=$(printf '%s\n' "$file_content" | awk -v sv="$script_variant" '/^[[:space:]]*'"$script_variant"':[[:space:]]*/ {sub(/^[[:space:]]*'"$script_variant"':[[:space:]]*/, ""); print; exit}')
[[ -z "$script_command" ]] && script_command="(Missing script command for $script_variant)"
# Extract agent_script command from frontmatter if present
local agent_script_command
agent_script_command=$(printf '%s\n' "$file_content" | awk '
/^agent_scripts:$/ { in_agent_scripts=1; next }
in_agent_scripts && /^[[:space:]]*'"$script_variant"':[[:space:]]*/ {
sub(/^[[:space:]]*'"$script_variant"':[[:space:]]*/, "")
print
exit
}
in_agent_scripts && /^[a-zA-Z]/ { in_agent_scripts=0 }
')
# Build body: replace placeholders, strip scripts sections, rewrite paths
local body
body=$(printf '%s\n' "$file_content" | sed "s|{SCRIPT}|${script_command}|g")
if [[ -n $agent_script_command ]]; then
body=$(printf '%s\n' "$body" | sed "s|{AGENT_SCRIPT}|${agent_script_command}|g")
fi
body=$(printf '%s\n' "$body" | awk '
/^---$/ { print; if (++dash_count == 1) in_frontmatter=1; else in_frontmatter=0; next }
in_frontmatter && /^scripts:$/ { skip_scripts=1; next }
in_frontmatter && /^agent_scripts:$/ { skip_scripts=1; next }
in_frontmatter && /^[a-zA-Z].*:/ && skip_scripts { skip_scripts=0 }
in_frontmatter && skip_scripts && /^[[:space:]]/ { next }
{ print }
')
body=$(printf '%s\n' "$body" | sed 's/{ARGS}/\$ARGUMENTS/g' | sed 's/__AGENT__/kimi/g' | rewrite_paths)
# Strip existing frontmatter and prepend Kimi frontmatter
local template_body
template_body=$(printf '%s\n' "$body" | awk '/^---/{p++; if(p==2){found=1; next}} found')
{
printf -- '---\n'
printf 'name: "%s"\n' "$skill_name"
printf 'description: "%s"\n' "$description"
printf -- '---\n\n'
printf '%s\n' "$template_body"
} > "$skill_dir/SKILL.md"
done
}
build_variant() { build_variant() {
local agent=$1 script=$2 local agent=$1 script=$2
local base_dir="$GENRELEASES_DIR/sdd-${agent}-package-${script}" local base_dir="$GENRELEASES_DIR/sdd-${agent}-package-${script}"
@@ -209,10 +140,12 @@ build_variant() {
case $script in case $script in
sh) sh)
[[ -d scripts/bash ]] && { cp -r scripts/bash "$SPEC_DIR/scripts/"; echo "Copied scripts/bash -> .specify/scripts"; } [[ -d scripts/bash ]] && { cp -r scripts/bash "$SPEC_DIR/scripts/"; echo "Copied scripts/bash -> .specify/scripts"; }
# Copy any script files that aren't in variant-specific directories
find scripts -maxdepth 1 -type f -exec cp {} "$SPEC_DIR/scripts/" \; 2>/dev/null || true find scripts -maxdepth 1 -type f -exec cp {} "$SPEC_DIR/scripts/" \; 2>/dev/null || true
;; ;;
ps) ps)
[[ -d scripts/powershell ]] && { cp -r scripts/powershell "$SPEC_DIR/scripts/"; echo "Copied scripts/powershell -> .specify/scripts"; } [[ -d scripts/powershell ]] && { cp -r scripts/powershell "$SPEC_DIR/scripts/"; echo "Copied scripts/powershell -> .specify/scripts"; }
# Copy any script files that aren't in variant-specific directories
find scripts -maxdepth 1 -type f -exec cp {} "$SPEC_DIR/scripts/" \; 2>/dev/null || true find scripts -maxdepth 1 -type f -exec cp {} "$SPEC_DIR/scripts/" \; 2>/dev/null || true
;; ;;
esac esac
@@ -220,6 +153,11 @@ build_variant() {
[[ -d templates ]] && { mkdir -p "$SPEC_DIR/templates"; find templates -type f -not -path "templates/commands/*" -not -name "vscode-settings.json" -exec cp --parents {} "$SPEC_DIR"/ \; ; echo "Copied templates -> .specify/templates"; } [[ -d templates ]] && { mkdir -p "$SPEC_DIR/templates"; find templates -type f -not -path "templates/commands/*" -not -name "vscode-settings.json" -exec cp --parents {} "$SPEC_DIR"/ \; ; echo "Copied templates -> .specify/templates"; }
# NOTE: We substitute {ARGS} internally. Outward tokens differ intentionally:
# * Markdown/prompt (claude, copilot, cursor-agent, opencode): $ARGUMENTS
# * TOML (gemini, qwen, tabnine): {{args}}
# This keeps formats readable without extra abstraction.
case $agent in case $agent in
claude) claude)
mkdir -p "$base_dir/.claude/commands" mkdir -p "$base_dir/.claude/commands"
@@ -231,7 +169,9 @@ build_variant() {
copilot) copilot)
mkdir -p "$base_dir/.github/agents" mkdir -p "$base_dir/.github/agents"
generate_commands copilot agent.md "\$ARGUMENTS" "$base_dir/.github/agents" "$script" generate_commands copilot agent.md "\$ARGUMENTS" "$base_dir/.github/agents" "$script"
# Generate companion prompt files
generate_copilot_prompts "$base_dir/.github/agents" "$base_dir/.github/prompts" generate_copilot_prompts "$base_dir/.github/agents" "$base_dir/.github/prompts"
# Create VS Code workspace settings
mkdir -p "$base_dir/.vscode" mkdir -p "$base_dir/.vscode"
[[ -f templates/vscode-settings.json ]] && cp templates/vscode-settings.json "$base_dir/.vscode/settings.json" [[ -f templates/vscode-settings.json ]] && cp templates/vscode-settings.json "$base_dir/.vscode/settings.json"
;; ;;
@@ -240,7 +180,7 @@ build_variant() {
generate_commands cursor-agent md "\$ARGUMENTS" "$base_dir/.cursor/commands" "$script" ;; generate_commands cursor-agent md "\$ARGUMENTS" "$base_dir/.cursor/commands" "$script" ;;
qwen) qwen)
mkdir -p "$base_dir/.qwen/commands" mkdir -p "$base_dir/.qwen/commands"
generate_commands qwen md "\$ARGUMENTS" "$base_dir/.qwen/commands" "$script" generate_commands qwen toml "{{args}}" "$base_dir/.qwen/commands" "$script"
[[ -f agent_templates/qwen/QWEN.md ]] && cp agent_templates/qwen/QWEN.md "$base_dir/QWEN.md" ;; [[ -f agent_templates/qwen/QWEN.md ]] && cp agent_templates/qwen/QWEN.md "$base_dir/QWEN.md" ;;
opencode) opencode)
mkdir -p "$base_dir/.opencode/command" mkdir -p "$base_dir/.opencode/command"
@@ -280,17 +220,14 @@ build_variant() {
mkdir -p "$base_dir/.kiro/prompts" mkdir -p "$base_dir/.kiro/prompts"
generate_commands kiro-cli md "\$ARGUMENTS" "$base_dir/.kiro/prompts" "$script" ;; generate_commands kiro-cli md "\$ARGUMENTS" "$base_dir/.kiro/prompts" "$script" ;;
agy) agy)
mkdir -p "$base_dir/.agent/commands" mkdir -p "$base_dir/.agent/workflows"
generate_commands agy md "\$ARGUMENTS" "$base_dir/.agent/commands" "$script" ;; generate_commands agy md "\$ARGUMENTS" "$base_dir/.agent/workflows" "$script" ;;
bob) bob)
mkdir -p "$base_dir/.bob/commands" mkdir -p "$base_dir/.bob/commands"
generate_commands bob md "\$ARGUMENTS" "$base_dir/.bob/commands" "$script" ;; generate_commands bob md "\$ARGUMENTS" "$base_dir/.bob/commands" "$script" ;;
vibe) vibe)
mkdir -p "$base_dir/.vibe/prompts" mkdir -p "$base_dir/.vibe/prompts"
generate_commands vibe md "\$ARGUMENTS" "$base_dir/.vibe/prompts" "$script" ;; generate_commands vibe md "\$ARGUMENTS" "$base_dir/.vibe/prompts" "$script" ;;
kimi)
mkdir -p "$base_dir/.kimi/skills"
create_kimi_skills "$base_dir/.kimi/skills" "$script" ;;
generic) generic)
mkdir -p "$base_dir/.speckit/commands" mkdir -p "$base_dir/.speckit/commands"
generate_commands generic md "\$ARGUMENTS" "$base_dir/.speckit/commands" "$script" ;; generate_commands generic md "\$ARGUMENTS" "$base_dir/.speckit/commands" "$script" ;;
@@ -300,10 +237,11 @@ build_variant() {
} }
# Determine agent list # Determine agent list
ALL_AGENTS=(claude gemini copilot cursor-agent qwen opencode windsurf codex kilocode auggie roo codebuddy amp shai tabnine kiro-cli agy bob vibe qodercli kimi generic) ALL_AGENTS=(claude gemini copilot cursor-agent qwen opencode windsurf codex kilocode auggie roo codebuddy amp shai tabnine kiro-cli agy bob vibe qodercli generic)
ALL_SCRIPTS=(sh ps) ALL_SCRIPTS=(sh ps)
norm_list() { norm_list() {
# convert comma+space separated -> line separated unique while preserving order of first occurrence
tr ',\n' ' ' | awk '{for(i=1;i<=NF;i++){if(!seen[$i]++){printf((out?"\n":"") $i);out=1}}}END{printf("\n")}' tr ',\n' ' ' | awk '{for(i=1;i<=NF;i++){if(!seen[$i]++){printf((out?"\n":"") $i);out=1}}}END{printf("\n")}'
} }

View File

@@ -10,6 +10,10 @@ The toolkit supports multiple AI coding assistants, allowing teams to use their
--- ---
## General practices
- Any changes to `__init__.py` for the Specify CLI require a version rev in `pyproject.toml` and addition of entries to `CHANGELOG.md`.
## Adding New Agent Support ## Adding New Agent Support
This section explains how to add support for new AI agents/assistants to the Specify CLI. Use this guide as a reference when integrating new AI tools into the Spec-Driven Development workflow. This section explains how to add support for new AI agents/assistants to the Specify CLI. Use this guide as a reference when integrating new AI tools into the Spec-Driven Development workflow.
@@ -31,7 +35,7 @@ Specify supports multiple AI agents by generating agent-specific command files a
| **Gemini CLI** | `.gemini/commands/` | TOML | `gemini` | Google's Gemini CLI | | **Gemini CLI** | `.gemini/commands/` | TOML | `gemini` | Google's Gemini CLI |
| **GitHub Copilot** | `.github/agents/` | Markdown | N/A (IDE-based) | GitHub Copilot in VS Code | | **GitHub Copilot** | `.github/agents/` | Markdown | N/A (IDE-based) | GitHub Copilot in VS Code |
| **Cursor** | `.cursor/commands/` | Markdown | `cursor-agent` | Cursor CLI | | **Cursor** | `.cursor/commands/` | Markdown | `cursor-agent` | Cursor CLI |
| **Qwen Code** | `.qwen/commands/` | Markdown | `qwen` | Alibaba's Qwen Code CLI | | **Qwen Code** | `.qwen/commands/` | TOML | `qwen` | Alibaba's Qwen Code CLI |
| **opencode** | `.opencode/command/` | Markdown | `opencode` | opencode CLI | | **opencode** | `.opencode/command/` | Markdown | `opencode` | opencode CLI |
| **Codex CLI** | `.codex/commands/` | Markdown | `codex` | Codex CLI | | **Codex CLI** | `.codex/commands/` | Markdown | `codex` | Codex CLI |
| **Windsurf** | `.windsurf/workflows/` | Markdown | N/A (IDE-based) | Windsurf IDE workflows | | **Windsurf** | `.windsurf/workflows/` | Markdown | N/A (IDE-based) | Windsurf IDE workflows |
@@ -44,7 +48,6 @@ Specify supports multiple AI agents by generating agent-specific command files a
| **Amp** | `.agents/commands/` | Markdown | `amp` | Amp CLI | | **Amp** | `.agents/commands/` | Markdown | `amp` | Amp CLI |
| **SHAI** | `.shai/commands/` | Markdown | `shai` | SHAI CLI | | **SHAI** | `.shai/commands/` | Markdown | `shai` | SHAI CLI |
| **Tabnine CLI** | `.tabnine/agent/commands/` | TOML | `tabnine` | Tabnine CLI | | **Tabnine CLI** | `.tabnine/agent/commands/` | TOML | `tabnine` | Tabnine CLI |
| **Kimi Code** | `.kimi/skills/` | Markdown | `kimi` | Kimi Code CLI (Moonshot AI) |
| **IBM Bob** | `.bob/commands/` | Markdown | N/A (IDE-based) | IBM Bob IDE | | **IBM Bob** | `.bob/commands/` | Markdown | N/A (IDE-based) | IBM Bob IDE |
| **Generic** | User-specified via `--ai-commands-dir` | Markdown | N/A | Bring your own agent | | **Generic** | User-specified via `--ai-commands-dir` | Markdown | N/A | Bring your own agent |
@@ -84,7 +87,7 @@ This eliminates the need for special-case mappings throughout the codebase.
- `folder`: Directory where agent-specific files are stored (relative to project root) - `folder`: Directory where agent-specific files are stored (relative to project root)
- `commands_subdir`: Subdirectory name within the agent folder where command/prompt files are stored (default: `"commands"`) - `commands_subdir`: Subdirectory name within the agent folder where command/prompt files are stored (default: `"commands"`)
- Most agents use `"commands"` (e.g., `.claude/commands/`) - Most agents use `"commands"` (e.g., `.claude/commands/`)
- Some agents use alternative names: `"agents"` (copilot), `"workflows"` (windsurf, kilocode), `"prompts"` (codex, kiro-cli), `"command"` (opencode - singular) - Some agents use alternative names: `"agents"` (copilot), `"workflows"` (windsurf, kilocode, agy), `"prompts"` (codex, kiro-cli), `"command"` (opencode - singular)
- This field enables `--ai-skills` to locate command templates correctly for skill generation - This field enables `--ai-skills` to locate command templates correctly for skill generation
- `install_url`: Installation documentation URL (set to `None` for IDE-based agents) - `install_url`: Installation documentation URL (set to `None` for IDE-based agents)
- `requires_cli`: Whether the agent requires a CLI tool check during initialization - `requires_cli`: Whether the agent requires a CLI tool check during initialization
@@ -321,7 +324,6 @@ Require a command-line tool to be installed:
- **Amp**: `amp` CLI - **Amp**: `amp` CLI
- **SHAI**: `shai` CLI - **SHAI**: `shai` CLI
- **Tabnine CLI**: `tabnine` CLI - **Tabnine CLI**: `tabnine` CLI
- **Kimi Code**: `kimi` CLI
### IDE-Based Agents ### IDE-Based Agents
@@ -335,7 +337,7 @@ Work within integrated development environments:
### Markdown Format ### Markdown Format
Used by: Claude, Cursor, opencode, Windsurf, Kiro CLI, Amp, SHAI, IBM Bob, Kimi Code, Qwen Used by: Claude, Cursor, opencode, Windsurf, Kiro CLI, Amp, SHAI, IBM Bob
**Standard format:** **Standard format:**
@@ -360,7 +362,7 @@ Command content with {SCRIPT} and $ARGUMENTS placeholders.
### TOML Format ### TOML Format
Used by: Gemini, Tabnine Used by: Gemini, Qwen, Tabnine
```toml ```toml
description = "Command description" description = "Command description"

View File

@@ -7,63 +7,7 @@ Recent changes to the Specify CLI and templates are documented here.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [0.3.0] - 2026-03-13 ## [0.2.1] - 2026-03-10
### Changed
- feat(presets): Pluggable preset system with catalog, resolver, and skills propagation (#1787)
- fix: match 'Last updated' timestamp with or without bold markers (#1836)
- Add specify doctor command for project health diagnostics (#1828)
- fix: harden bash scripts against shell injection and improve robustness (#1809)
- fix: clean up command templates (specify, analyze) (#1810)
- fix: migrate Qwen Code CLI from TOML to Markdown format (#1589) (#1730)
- fix(cli): deprecate explicit command support for agy (#1798) (#1808)
- Add /selftest.extension core extension to test other extensions (#1758)
- feat(extensions): Quality of life improvements for RFC-aligned catalog integration (#1776)
- Add Java brownfield walkthrough to community walkthroughs (#1820)
- chore: bump version to 0.2.1 (#1813)
- Added February 2026 newsletter (#1812)
- feat: add Kimi Code CLI agent support (#1790)
- docs: fix broken links in quickstart guide (#1759) (#1797)
- docs: add catalog cli help documentation (#1793) (#1794)
- fix: use quiet checkout to avoid exception on git checkout (#1792)
- feat(extensions): support .extensionignore to exclude files during install (#1781)
- feat: add Codex support for extension command registration (#1767)
- chore: bump version to 0.2.0 (#1786)
- fix: sync agent list comments with actual supported agents (#1785)
- feat(extensions): support multiple active catalogs simultaneously (#1720)
- Pavel/add tabnine cli support (#1503)
- Add Understanding extension to community catalog (#1778)
- Add ralph extension to community catalog (#1780)
- Update README with project initialization instructions (#1772)
- feat: add review extension to community catalog (#1775)
- Add fleet extension to community catalog (#1771)
- Integration of Mistral vibe support into speckit (#1725)
- fix: Remove duplicate options in specify.md (#1765)
- fix: use global branch numbering instead of per-short-name detection (#1757)
- Add Community Walkthroughs section to README (#1766)
- feat(extensions): add Jira Integration to community catalog (#1764)
- Add Azure DevOps Integration extension to community catalog (#1734)
- Fix docs: update Antigravity link and add initialization example (#1748)
- fix: wire after_tasks and after_implement hook events into command templates (#1702)
- make c ignores consistent with c++ (#1747)
- chore: bump version to 0.1.13 (#1746)
- feat: add kiro-cli and AGENT_CONFIG consistency coverage (#1690)
- feat: add verify extension to community catalog (#1726)
- Add Retrospective Extension to community catalog README table (#1741)
- fix(scripts): add empty description validation and branch checkout error handling (#1559)
- fix: correct Copilot extension command registration (#1724)
- fix(implement): remove Makefile from C ignore patterns (#1558)
- Add sync extension to community catalog (#1728)
- fix(checklist): clarify file handling behavior for append vs create (#1556)
- fix(clarify): correct conflicting question limit from 10 to 5 (#1557)
- chore: bump version to 0.1.12 (#1737)
- fix: use RELEASE_PAT so tag push triggers release workflow (#1736)
- fix: release-trigger uses release branch + PR instead of direct push to main (#1733)
- fix: Split release process to sync pyproject.toml version with git tags (#1732)
## [Unreleased]
### Added ### Added
@@ -84,55 +28,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- feat: `specify init` persists CLI options to `.specify/init-options.json` for downstream operations - feat: `specify init` persists CLI options to `.specify/init-options.json` for downstream operations
- feat(extensions): support `.extensionignore` to exclude files/folders during `specify extension add` (#1781) - feat(extensions): support `.extensionignore` to exclude files/folders during `specify extension add` (#1781)
## [0.2.1] - 2026-03-11
### Changed
- Added February 2026 newsletter (#1812)
- feat: add Kimi Code CLI agent support (#1790)
- docs: fix broken links in quickstart guide (#1759) (#1797)
- docs: add catalog cli help documentation (#1793) (#1794)
- fix: use quiet checkout to avoid exception on git checkout (#1792)
- feat(extensions): support .extensionignore to exclude files during install (#1781)
- feat: add Codex support for extension command registration (#1767)
- chore: bump version to 0.2.0 (#1786)
- fix: sync agent list comments with actual supported agents (#1785)
- feat(extensions): support multiple active catalogs simultaneously (#1720)
- Pavel/add tabnine cli support (#1503)
- Add Understanding extension to community catalog (#1778)
- Add ralph extension to community catalog (#1780)
- Update README with project initialization instructions (#1772)
- feat: add review extension to community catalog (#1775)
- Add fleet extension to community catalog (#1771)
- Integration of Mistral vibe support into speckit (#1725)
- fix: Remove duplicate options in specify.md (#1765)
- fix: use global branch numbering instead of per-short-name detection (#1757)
- Add Community Walkthroughs section to README (#1766)
- feat(extensions): add Jira Integration to community catalog (#1764)
- Add Azure DevOps Integration extension to community catalog (#1734)
- Fix docs: update Antigravity link and add initialization example (#1748)
- fix: wire after_tasks and after_implement hook events into command templates (#1702)
- make c ignores consistent with c++ (#1747)
- chore: bump version to 0.1.13 (#1746)
- feat: add kiro-cli and AGENT_CONFIG consistency coverage (#1690)
- feat: add verify extension to community catalog (#1726)
- Add Retrospective Extension to community catalog README table (#1741)
- fix(scripts): add empty description validation and branch checkout error handling (#1559)
- fix: correct Copilot extension command registration (#1724)
- fix(implement): remove Makefile from C ignore patterns (#1558)
- Add sync extension to community catalog (#1728)
- fix(checklist): clarify file handling behavior for append vs create (#1556)
- fix(clarify): correct conflicting question limit from 10 to 5 (#1557)
- chore: bump version to 0.1.12 (#1737)
- fix: use RELEASE_PAT so tag push triggers release workflow (#1736)
- fix: release-trigger uses release branch + PR instead of direct push to main (#1733)
- fix: Split release process to sync pyproject.toml version with git tags (#1732)
## [0.2.0] - 2026-03-09 ## [0.2.0] - 2026-03-09
### Changed ### Changed
- feat: add Kimi Code CLI agent support
- fix: sync agent list comments with actual supported agents (#1785) - fix: sync agent list comments with actual supported agents (#1785)
- feat(extensions): support multiple active catalogs simultaneously (#1720) - feat(extensions): support multiple active catalogs simultaneously (#1720)
- Pavel/add tabnine cli support (#1503) - Pavel/add tabnine cli support (#1503)

View File

@@ -154,9 +154,7 @@ See Spec-Driven Development in action across different scenarios with these comm
- **[Greenfield Spring Boot + React platform](https://github.com/mnriem/spec-kit-spring-react-demo)** — Builds an LLM performance analytics platform (REST API, graphs, iteration tracking) from scratch using Spring Boot, embedded React, PostgreSQL, and Docker Compose, with a clarify step and a cross-artifact consistency analysis pass included. - **[Greenfield Spring Boot + React platform](https://github.com/mnriem/spec-kit-spring-react-demo)** — Builds an LLM performance analytics platform (REST API, graphs, iteration tracking) from scratch using Spring Boot, embedded React, PostgreSQL, and Docker Compose, with a clarify step and a cross-artifact consistency analysis pass included.
- **[Brownfield ASP.NET CMS extension](https://github.com/mnriem/spec-kit-aspnet-brownfield-demo)** — Extends an existing open-source .NET CMS (CarrotCakeCMS-Core, ~307,000 lines of C#, Razor, SQL, JavaScript, and config files) with two new features — cross-platform Docker Compose infrastructure and a token-authenticated headless REST API — demonstrating how spec-kit fits into existing codebases without prior specs or a constitution. - **[Brownfield ASP.NET CMS extension](https://github.com/mnriem/spec-kit-aspnet-brownfield-demo)** — Extends an existing open-source .NET CMS (CarrotCakeCMS-Core) with two new features — cross-platform Docker Compose infrastructure and a token-authenticated headless REST API — demonstrating how spec-kit fits into existing codebases without prior specs or a constitution.
- **[Brownfield Java runtime extension](https://github.com/mnriem/spec-kit-java-brownfield-demo)** — Extends an existing open-source Jakarta EE runtime (Piranha, ~420,000 lines of Java, XML, JSP, HTML, and config files across 180 Maven modules) with a password-protected Server Admin Console, demonstrating spec-kit on a large multi-module Java project with no prior specs or constitution.
## 🤖 Supported AI Agents ## 🤖 Supported AI Agents
@@ -181,9 +179,8 @@ See Spec-Driven Development in action across different scenarios with these comm
| [SHAI (OVHcloud)](https://github.com/ovh/shai) | ✅ | | | [SHAI (OVHcloud)](https://github.com/ovh/shai) | ✅ | |
| [Tabnine CLI](https://docs.tabnine.com/main/getting-started/tabnine-cli) | ✅ | | | [Tabnine CLI](https://docs.tabnine.com/main/getting-started/tabnine-cli) | ✅ | |
| [Mistral Vibe](https://github.com/mistralai/mistral-vibe) | ✅ | | | [Mistral Vibe](https://github.com/mistralai/mistral-vibe) | ✅ | |
| [Kimi Code](https://code.kimi.com/) | ✅ | |
| [Windsurf](https://windsurf.com/) | ✅ | | | [Windsurf](https://windsurf.com/) | ✅ | |
| [Antigravity (agy)](https://antigravity.google/) | ✅ | Requires `--ai-skills` | | [Antigravity (agy)](https://antigravity.google/) | ✅ | |
| Generic | ✅ | Bring your own agent — use `--ai generic --ai-commands-dir <path>` for unsupported agents | | Generic | ✅ | Bring your own agent — use `--ai generic --ai-commands-dir <path>` for unsupported agents |
## 🔧 Specify CLI Reference ## 🔧 Specify CLI Reference
@@ -195,14 +192,14 @@ The `specify` command supports the following options:
| Command | Description | | Command | Description |
| ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `init` | Initialize a new Specify project from the latest template | | `init` | Initialize a new Specify project from the latest template |
| `check` | Check for installed tools (`git`, `claude`, `gemini`, `code`/`code-insiders`, `cursor-agent`, `windsurf`, `qwen`, `opencode`, `codex`, `kiro-cli`, `shai`, `qodercli`, `vibe`, `kimi`) | | `check` | Check for installed tools (`git`, `claude`, `gemini`, `code`/`code-insiders`, `cursor-agent`, `windsurf`, `qwen`, `opencode`, `codex`, `kiro-cli`, `shai`, `qodercli`, `vibe`) |
### `specify init` Arguments & Options ### `specify init` Arguments & Options
| Argument/Option | Type | Description | | Argument/Option | Type | Description |
| ---------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ---------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `<project-name>` | Argument | Name for your new project directory (optional if using `--here`, or use `.` for current directory) | | `<project-name>` | Argument | Name for your new project directory (optional if using `--here`, or use `.` for current directory) |
| `--ai` | Option | AI assistant to use: `claude`, `gemini`, `copilot`, `cursor-agent`, `qwen`, `opencode`, `codex`, `windsurf`, `kilocode`, `auggie`, `roo`, `codebuddy`, `amp`, `shai`, `kiro-cli` (`kiro` alias), `agy`, `bob`, `qodercli`, `vibe`, `kimi`, or `generic` (requires `--ai-commands-dir`) | | `--ai` | Option | AI assistant to use: `claude`, `gemini`, `copilot`, `cursor-agent`, `qwen`, `opencode`, `codex`, `windsurf`, `kilocode`, `auggie`, `roo`, `codebuddy`, `amp`, `shai`, `kiro-cli` (`kiro` alias), `agy`, `bob`, `qodercli`, `vibe`, or `generic` (requires `--ai-commands-dir`) |
| `--ai-commands-dir` | Option | Directory for agent command files (required with `--ai generic`, e.g. `.myagent/commands/`) | | `--ai-commands-dir` | Option | Directory for agent command files (required with `--ai generic`, e.g. `.myagent/commands/`) |
| `--script` | Option | Script variant to use: `sh` (bash/zsh) or `ps` (PowerShell) | | `--script` | Option | Script variant to use: `sh` (bash/zsh) or `ps` (PowerShell) |
| `--ignore-agent-tools` | Flag | Skip checks for AI agent tools like Claude Code | | `--ignore-agent-tools` | Flag | Skip checks for AI agent tools like Claude Code |
@@ -248,7 +245,7 @@ specify init my-project --ai vibe
specify init my-project --ai bob specify init my-project --ai bob
# Initialize with Antigravity support # Initialize with Antigravity support
specify init my-project --ai agy --ai-skills specify init my-project --ai agy
# Initialize with an unsupported agent (generic / bring your own agent) # Initialize with an unsupported agent (generic / bring your own agent)
specify init my-project --ai generic --ai-commands-dir .myagent/commands/ specify init my-project --ai generic --ai-commands-dir .myagent/commands/

View File

@@ -173,6 +173,6 @@ Finally, implement the solution:
## Next Steps ## Next Steps
- Read the [complete methodology](https://github.com/github/spec-kit/blob/main/spec-driven.md) for in-depth guidance - Read the [complete methodology](../spec-driven.md) for in-depth guidance
- Check out [more examples](https://github.com/github/spec-kit/tree/main/templates) in the repository - Check out [more examples](../templates) in the repository
- Explore the [source code on GitHub](https://github.com/github/spec-kit) - Explore the [source code on GitHub](https://github.com/github/spec-kit)

View File

@@ -432,26 +432,6 @@ Spec Kit uses a **catalog stack** — an ordered list of catalogs searched simul
specify extension catalog list specify extension catalog list
``` ```
### Managing Catalogs via CLI
You can view the main catalog management commands using `--help`:
```text
specify extension catalog --help
Usage: specify extension catalog [OPTIONS] COMMAND [ARGS]...
Manage extension catalogs
╭─ Options ────────────────────────────────────────────────────────────────────────╮
│ --help Show this message and exit. │
╰──────────────────────────────────────────────────────────────────────────────────╯
╭─ Commands ───────────────────────────────────────────────────────────────────────╮
│ list List all active extension catalogs. │
│ add Add a catalog to .specify/extension-catalogs.yml. │
│ remove Remove a catalog from .specify/extension-catalogs.yml. │
╰──────────────────────────────────────────────────────────────────────────────────╯
```
### Adding a Catalog (Project-scoped) ### Adding a Catalog (Project-scoped)
```bash ```bash

View File

@@ -76,7 +76,6 @@ The following community-contributed extensions are available in [`catalog.commun
| Cleanup Extension | Post-implementation quality gate that reviews changes, fixes small issues (scout rule), creates tasks for medium issues, and generates analysis for large issues | [spec-kit-cleanup](https://github.com/dsrednicki/spec-kit-cleanup) | | Cleanup Extension | Post-implementation quality gate that reviews changes, fixes small issues (scout rule), creates tasks for medium issues, and generates analysis for large issues | [spec-kit-cleanup](https://github.com/dsrednicki/spec-kit-cleanup) |
| Fleet Orchestrator | Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases | [spec-kit-fleet](https://github.com/sharathsatish/spec-kit-fleet) | | Fleet Orchestrator | Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases | [spec-kit-fleet](https://github.com/sharathsatish/spec-kit-fleet) |
| Jira Integration | Create Jira Epics, Stories, and Issues from spec-kit specifications and task breakdowns with configurable hierarchy and custom field support | [spec-kit-jira](https://github.com/mbachorik/spec-kit-jira) | | Jira Integration | Create Jira Epics, Stories, and Issues from spec-kit specifications and task breakdowns with configurable hierarchy and custom field support | [spec-kit-jira](https://github.com/mbachorik/spec-kit-jira) |
| Project Health Check | Diagnose a Spec Kit project and report health issues across structure, agents, features, scripts, extensions, and git | [spec-kit-doctor](https://github.com/KhawarHabibKhan/spec-kit-doctor) |
| Ralph Loop | Autonomous implementation loop using AI agent CLI | [spec-kit-ralph](https://github.com/Rubiss/spec-kit-ralph) | | Ralph Loop | Autonomous implementation loop using AI agent CLI | [spec-kit-ralph](https://github.com/Rubiss/spec-kit-ralph) |
| Retrospective Extension | Post-implementation retrospective with spec adherence scoring, drift analysis, and human-gated spec updates | [spec-kit-retrospective](https://github.com/emi-dm/spec-kit-retrospective) | | Retrospective Extension | Post-implementation retrospective with spec adherence scoring, drift analysis, and human-gated spec updates | [spec-kit-retrospective](https://github.com/emi-dm/spec-kit-retrospective) |
| Review Extension | Post-implementation comprehensive code review with specialized agents for code quality, comments, tests, error handling, type design, and simplification | [spec-kit-review](https://github.com/ismaelJimenez/spec-kit-review) | | Review Extension | Post-implementation comprehensive code review with specialized agents for code quality, comments, tests, error handling, type design, and simplification | [spec-kit-review](https://github.com/ismaelJimenez/spec-kit-review) |

View File

@@ -1,9 +1,9 @@
# RFC: Spec Kit Extension System # RFC: Spec Kit Extension System
**Status**: Implemented **Status**: Draft
**Author**: Stats Perform Engineering **Author**: Stats Perform Engineering
**Created**: 2026-01-28 **Created**: 2026-01-28
**Updated**: 2026-03-11 **Updated**: 2026-01-28
--- ---
@@ -24,9 +24,8 @@
13. [Security Considerations](#security-considerations) 13. [Security Considerations](#security-considerations)
14. [Migration Strategy](#migration-strategy) 14. [Migration Strategy](#migration-strategy)
15. [Implementation Phases](#implementation-phases) 15. [Implementation Phases](#implementation-phases)
16. [Resolved Questions](#resolved-questions) 16. [Open Questions](#open-questions)
17. [Open Questions (Remaining)](#open-questions-remaining) 17. [Appendices](#appendices)
18. [Appendices](#appendices)
--- ---
@@ -1505,225 +1504,203 @@ AI agent registers both names, so old scripts work.
## Implementation Phases ## Implementation Phases
### Phase 1: Core Extension System ✅ COMPLETED ### Phase 1: Core Extension System (Week 1-2)
**Goal**: Basic extension infrastructure **Goal**: Basic extension infrastructure
**Deliverables**: **Deliverables**:
- [x] Extension manifest schema (`extension.yml`) - [ ] Extension manifest schema (`extension.yml`)
- [x] Extension directory structure - [ ] Extension directory structure
- [x] CLI commands: - [ ] CLI commands:
- [x] `specify extension list` - [ ] `specify extension list`
- [x] `specify extension add` (from URL and local `--dev`) - [ ] `specify extension add` (from URL)
- [x] `specify extension remove` - [ ] `specify extension remove`
- [x] Extension registry (`.specify/extensions/.registry`) - [ ] Extension registry (`.specify/extensions/.registry`)
- [x] Command registration (Claude and 15+ other agents) - [ ] Command registration (Claude only initially)
- [x] Basic validation (manifest schema, compatibility) - [ ] Basic validation (manifest schema, compatibility)
- [x] Documentation (extension development guide) - [ ] Documentation (extension development guide)
**Testing**: **Testing**:
- [x] Unit tests for manifest parsing - [ ] Unit tests for manifest parsing
- [x] Integration test: Install dummy extension - [ ] Integration test: Install dummy extension
- [x] Integration test: Register commands with Claude - [ ] Integration test: Register commands with Claude
### Phase 2: Jira Extension ✅ COMPLETED ### Phase 2: Jira Extension (Week 3)
**Goal**: First production extension **Goal**: First production extension
**Deliverables**: **Deliverables**:
- [x] Create `spec-kit-jira` repository - [ ] Create `spec-kit-jira` repository
- [x] Port Jira functionality to extension - [ ] Port Jira functionality to extension
- [x] Create `jira-config.yml` template - [ ] Create `jira-config.yml` template
- [x] Commands: - [ ] Commands:
- [x] `specstoissues.md` - [ ] `specstoissues.md`
- [x] `discover-fields.md` - [ ] `discover-fields.md`
- [x] `sync-status.md` - [ ] `sync-status.md`
- [x] Helper scripts - [ ] Helper scripts
- [x] Documentation (README, configuration guide, examples) - [ ] Documentation (README, configuration guide, examples)
- [x] Release v3.0.0 - [ ] Release v1.0.0
**Testing**: **Testing**:
- [x] Test on `eng-msa-ts` project - [ ] Test on `eng-msa-ts` project
- [x] Verify spec→Epic, phase→Story, task→Issue mapping - [ ] Verify spec→Epic, phase→Story, task→Issue mapping
- [x] Test configuration loading and validation - [ ] Test configuration loading and validation
- [x] Test custom field application - [ ] Test custom field application
### Phase 3: Extension Catalog ✅ COMPLETED ### Phase 3: Extension Catalog (Week 4)
**Goal**: Discovery and distribution **Goal**: Discovery and distribution
**Deliverables**: **Deliverables**:
- [x] Central catalog (`extensions/catalog.json` in spec-kit repo) - [ ] Central catalog (`extensions/catalog.json` in spec-kit repo)
- [x] Community catalog (`extensions/catalog.community.json`) - [ ] Catalog fetch and parsing
- [x] Catalog fetch and parsing with multi-catalog support - [ ] CLI commands:
- [x] CLI commands: - [ ] `specify extension search`
- [x] `specify extension search` - [ ] `specify extension info`
- [x] `specify extension info` - [ ] Catalog publishing process (GitHub Action)
- [x] `specify extension catalog list` - [ ] Documentation (how to publish extensions)
- [x] `specify extension catalog add`
- [x] `specify extension catalog remove`
- [x] Documentation (how to publish extensions)
**Testing**: **Testing**:
- [x] Test catalog fetch - [ ] Test catalog fetch
- [x] Test extension search/filtering - [ ] Test extension search/filtering
- [x] Test catalog caching - [ ] Test catalog caching
- [x] Test multi-catalog merge with priority
### Phase 4: Advanced Features ✅ COMPLETED ### Phase 4: Advanced Features (Week 5-6)
**Goal**: Hooks, updates, multi-agent support **Goal**: Hooks, updates, multi-agent support
**Deliverables**: **Deliverables**:
- [x] Hook system (`hooks` in extension.yml) - [ ] Hook system (`hooks` in extension.yml)
- [x] Hook registration and execution - [ ] Hook registration and execution
- [x] Project extensions config (`.specify/extensions.yml`) - [ ] Project extensions config (`.specify/extensions.yml`)
- [x] CLI commands: - [ ] CLI commands:
- [x] `specify extension update` (with atomic backup/restore) - [ ] `specify extension update`
- [x] `specify extension enable/disable` - [ ] `specify extension enable/disable`
- [x] Command registration for multiple agents (15+ agents including Claude, Copilot, Gemini, Cursor, etc.) - [ ] Command registration for multiple agents (Gemini, Copilot)
- [x] Extension update notifications (version comparison) - [ ] Extension update notifications
- [x] Configuration layer resolution (project, local, env) - [ ] Configuration layer resolution (project, local, env)
**Additional features implemented beyond original RFC**:
- [x] **Display name resolution**: All commands accept extension display names in addition to IDs
- [x] **Ambiguous name handling**: User-friendly tables when multiple extensions match a name
- [x] **Atomic update with rollback**: Full backup of extension dir, commands, hooks, and registry with automatic rollback on failure
- [x] **Pre-install ID validation**: Validates extension ID from ZIP before installing (security)
- [x] **Enabled state preservation**: Disabled extensions stay disabled after update
- [x] **Registry update/restore methods**: Clean API for enable/disable and rollback operations
- [x] **Catalog error fallback**: `extension info` falls back to local info when catalog unavailable
- [x] **`_install_allowed` flag**: Discovery-only catalogs can't be used for installation
- [x] **Cache invalidation**: Cache invalidated when `SPECKIT_CATALOG_URL` changes
**Testing**: **Testing**:
- [x] Test hooks in core commands - [ ] Test hooks in core commands
- [x] Test extension updates (preserve config) - [ ] Test extension updates (preserve config)
- [x] Test multi-agent registration - [ ] Test multi-agent registration
- [x] Test atomic rollback on update failure
- [x] Test enabled state preservation
- [x] Test display name resolution
### Phase 5: Polish & Documentation ✅ COMPLETED ### Phase 5: Polish & Documentation (Week 7)
**Goal**: Production ready **Goal**: Production ready
**Deliverables**: **Deliverables**:
- [x] Comprehensive documentation: - [ ] Comprehensive documentation:
- [x] User guide (EXTENSION-USER-GUIDE.md) - [ ] User guide (installing/using extensions)
- [x] Extension development guide (EXTENSION-DEV-GUIDE.md) - [ ] Extension development guide
- [x] Extension API reference (EXTENSION-API-REFERENCE.md) - [ ] Extension API reference
- [x] Error messages and validation improvements - [ ] Migration guide (core → extension)
- [x] CLI help text updates - [ ] Error messages and validation improvements
- [ ] CLI help text updates
- [ ] Example extension template (cookiecutter)
- [ ] Blog post / announcement
- [ ] Video tutorial
**Testing**: **Testing**:
- [x] End-to-end testing on multiple projects - [ ] End-to-end testing on multiple projects
- [x] 163 unit tests passing - [ ] Community beta testing
- [ ] Performance testing (large projects)
--- ---
## Resolved Questions ## Open Questions
The following questions from the original RFC have been resolved during implementation: ### 1. Extension Namespace
### 1. Extension Namespace ✅ RESOLVED
**Question**: Should extension commands use namespace prefix? **Question**: Should extension commands use namespace prefix?
**Decision**: **Option C** - Both prefixed and aliases are supported. Commands use `speckit.{extension}.{command}` as canonical name, with optional aliases defined in manifest. **Options**:
**Implementation**: The `aliases` field in `extension.yml` allows extensions to register additional command names. - A) Prefixed: `/speckit.jira.specstoissues` (explicit, avoids conflicts)
- B) Short alias: `/jira.specstoissues` (shorter, less verbose)
- C) Both: Register both names, prefer prefixed in docs
**Recommendation**: C (both), prefixed is canonical
--- ---
### 2. Config File Location ✅ RESOLVED ### 2. Config File Location
**Question**: Where should extension configs live? **Question**: Where should extension configs live?
**Decision**: **Option A** - Extension directory (`.specify/extensions/{ext-id}/{ext-id}-config.yml`). This keeps extensions self-contained and easier to manage. **Options**:
**Implementation**: Each extension has its own config file within its directory, with layered resolution (defaults → project → local → env vars). - A) Extension directory: `.specify/extensions/jira/jira-config.yml` (encapsulated)
- B) Root level: `.specify/jira-config.yml` (more visible)
- C) Unified: `.specify/extensions.yml` (all extension configs in one file)
**Recommendation**: A (extension directory), cleaner separation
--- ---
### 3. Command File Format ✅ RESOLVED ### 3. Command File Format
**Question**: Should extensions use universal format or agent-specific? **Question**: Should extensions use universal format or agent-specific?
**Decision**: **Option A** - Universal Markdown format. Extensions write commands once, CLI converts to agent-specific format during registration. **Options**:
**Implementation**: `CommandRegistrar` class handles conversion to 15+ agent formats (Claude, Copilot, Gemini, Cursor, etc.). - A) Universal Markdown: Extensions write once, CLI converts per-agent
- B) Agent-specific: Extensions provide separate files for each agent
- C) Hybrid: Universal default, agent-specific overrides
**Recommendation**: A (universal), reduces duplication
--- ---
### 4. Hook Execution Model ✅ RESOLVED ### 4. Hook Execution Model
**Question**: How should hooks execute? **Question**: How should hooks execute?
**Decision**: **Option A** - Hooks are registered in `.specify/extensions.yml` and executed by the AI agent when it sees the hook trigger. Hook state (enabled/disabled) is managed per-extension. **Options**:
**Implementation**: `HookExecutor` class manages hook registration and state in `extensions.yml`. - A) AI agent interprets: Core commands output `EXECUTE_COMMAND: name`
- B) CLI executes: Core commands call `specify extension hook after_tasks`
- C) Agent built-in: Extension system built into AI agent (Claude SDK)
**Recommendation**: A initially (simpler), move to C long-term
--- ---
### 5. Extension Distribution ✅ RESOLVED ### 5. Extension Distribution
**Question**: How should extensions be packaged? **Question**: How should extensions be packaged?
**Decision**: **Option A** - ZIP archives downloaded from GitHub releases (via catalog `download_url`). Local development uses `--dev` flag with directory path. **Options**:
**Implementation**: `ExtensionManager.install_from_zip()` handles ZIP extraction and validation. - A) ZIP archives: Downloaded from GitHub releases
- B) Git repos: Cloned directly (`git clone`)
- C) Python packages: Installable via `uv tool install`
**Recommendation**: A (ZIP), simpler for non-Python extensions in future
--- ---
### 6. Multi-Version Support ✅ RESOLVED ### 6. Multi-Version Support
**Question**: Can multiple versions of same extension coexist? **Question**: Can multiple versions of same extension coexist?
**Decision**: **Option A** - Single version only. Updates replace the existing version with atomic rollback on failure.
**Implementation**: `extension update` performs atomic backup/restore to ensure safe updates.
---
## Open Questions (Remaining)
### 1. Sandboxing / Permissions (Future)
**Question**: Should extensions declare required permissions?
**Options**: **Options**:
- A) No sandboxing (current): Extensions run with same privileges as AI agent - A) Single version: Only one version installed at a time
- B) Permission declarations: Extensions declare `filesystem:read`, `network:external`, etc. - B) Multi-version: Side-by-side versions (`.specify/extensions/jira@1.0/`, `.specify/extensions/jira@2.0/`)
- C) Opt-in sandboxing: Organizations can enable permission enforcement - C) Per-branch: Different branches use different versions
**Status**: Deferred to future version. Currently using trust-based model where users trust extension authors. **Recommendation**: A initially (simpler), consider B in future if needed
---
### 2. Package Signatures (Future)
**Question**: Should extensions be cryptographically signed?
**Options**:
- A) No signatures (current): Trust based on catalog source
- B) GPG/Sigstore signatures: Verify package integrity
- C) Catalog-level verification: Catalog maintainers verify packages
**Status**: Deferred to future version. `checksum` field is available in catalog schema but not enforced.
--- ---

View File

@@ -1,6 +1,6 @@
{ {
"schema_version": "1.0", "schema_version": "1.0",
"updated_at": "2026-03-13T12:00:00Z", "updated_at": "2026-03-09T00:00:00Z",
"catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json", "catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json",
"extensions": { "extensions": {
"azure-devops": { "azure-devops": {
@@ -74,37 +74,6 @@
"created_at": "2026-02-22T00:00:00Z", "created_at": "2026-02-22T00:00:00Z",
"updated_at": "2026-02-22T00:00:00Z" "updated_at": "2026-02-22T00:00:00Z"
}, },
"doctor": {
"name": "Project Health Check",
"id": "doctor",
"description": "Diagnose a Spec Kit project and report health issues across structure, agents, features, scripts, extensions, and git.",
"author": "KhawarHabibKhan",
"version": "1.0.0",
"download_url": "https://github.com/KhawarHabibKhan/spec-kit-doctor/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/KhawarHabibKhan/spec-kit-doctor",
"homepage": "https://github.com/KhawarHabibKhan/spec-kit-doctor",
"documentation": "https://github.com/KhawarHabibKhan/spec-kit-doctor/blob/main/README.md",
"changelog": "https://github.com/KhawarHabibKhan/spec-kit-doctor/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 1,
"hooks": 0
},
"tags": [
"diagnostics",
"health-check",
"validation",
"project-structure"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-13T00:00:00Z",
"updated_at": "2026-03-13T00:00:00Z"
},
"fleet": { "fleet": {
"name": "Fleet Orchestrator", "name": "Fleet Orchestrator",
"id": "fleet", "id": "fleet",

View File

@@ -1,21 +1,6 @@
{ {
"schema_version": "1.0", "schema_version": "1.0",
"updated_at": "2026-03-10T00:00:00Z", "updated_at": "2026-02-03T00:00:00Z",
"catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.json", "catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.json",
"extensions": { "extensions": {}
"selftest": {
"name": "Spec Kit Self-Test Utility",
"id": "selftest",
"version": "1.0.0",
"description": "Verifies catalog extensions by programmatically walking through the discovery, installation, and registration lifecycle.",
"author": "spec-kit-core",
"repository": "https://github.com/github/spec-kit",
"download_url": "https://github.com/github/spec-kit/releases/download/selftest-v1.0.0/selftest.zip",
"tags": [
"testing",
"core",
"utility"
]
}
}
} }

View File

@@ -1,69 +0,0 @@
---
description: "Validate the lifecycle of an extension from the catalog."
---
# Extension Self-Test: `$ARGUMENTS`
This command drives a self-test simulating the developer experience with the `$ARGUMENTS` extension.
## Goal
Validate the end-to-end lifecycle (discovery, installation, registration) for the extension: `$ARGUMENTS`.
If `$ARGUMENTS` is empty, you must tell the user to provide an extension name, for example: `/speckit.selftest.extension linear`.
## Steps
### Step 1: Catalog Discovery Validation
Check if the extension exists in the Spec Kit catalog.
Execute this command and verify that it completes successfully and that the returned extension ID exactly matches `$ARGUMENTS`. If the command fails or the ID does not match `$ARGUMENTS`, fail the test.
```bash
specify extension info "$ARGUMENTS"
```
### Step 2: Simulate Installation
First, try to add the extension to the current workspace configuration directly. If the catalog provides the extension as `install_allowed: false` (discovery-only), this step is *expected* to fail.
```bash
specify extension add "$ARGUMENTS"
```
Then, simulate adding the extension by installing it from its catalog download URL, which should bypass the restriction.
Obtain the extension's `download_url` from the catalog metadata (for example, via a catalog info command or UI), then run:
```bash
specify extension add "$ARGUMENTS" --from "<download_url>"
```
### Step 3: Registration Verification
Once the `add` command completes, verify the installation by checking the project configuration.
Use terminal tools (like `cat`) to verify that the following file contains a record for `$ARGUMENTS`.
```bash
cat .specify/extensions/.registry/$ARGUMENTS.json
```
### Step 4: Verification Report
Analyze the standard output of the three steps.
Generate a terminal-style test output format detailing the results of discovery, installation, and registration. Return this directly to the user.
Example output format:
```text
============================= test session starts ==============================
collected 3 items
test_selftest_discovery.py::test_catalog_search [PASS/FAIL]
Details: [Provide execution result of specify extension search]
test_selftest_installation.py::test_extension_add [PASS/FAIL]
Details: [Provide execution result of specify extension add]
test_selftest_registration.py::test_config_verification [PASS/FAIL]
Details: [Provide execution result of registry record verification]
============================== [X] passed in ... ==============================
```

View File

@@ -1,16 +0,0 @@
schema_version: "1.0"
extension:
id: selftest
name: Spec Kit Self-Test Utility
version: 1.0.0
description: Verifies catalog extensions by programmatically walking through the discovery, installation, and registration lifecycle.
author: spec-kit-core
repository: https://github.com/github/spec-kit
license: MIT
requires:
speckit_version: ">=0.2.0"
provides:
commands:
- name: speckit.selftest.extension
file: commands/selftest.md
description: Validate the lifecycle of an extension from the catalog.

View File

@@ -1,54 +0,0 @@
# Spec Kit - February 2026 Newsletter
This edition covers Spec Kit activity in February 2026. Versions v0.1.7 through v0.1.13 shipped during the month, addressing bugs and adding features including a dual-catalog extension system and additional agent integrations. Community activity included blog posts, tutorials, and meetup sessions. A category summary is in the table below, followed by details.
| **Spec Kit Core (Feb 2026)** | **Community & Content** | **Roadmap & Next** |
| --- | --- | --- |
| Versions **v0.1.7** through **v0.1.13** shipped with bug fixes and features, including a **dual-catalog extension system** and new agent integrations. Over 300 issues were closed (of ~800 filed). The repo reached 71k stars and 6.4k forks. [\[github.com\]](https://github.com/github/spec-kit/releases) [\[github.com\]](https://github.com/github/spec-kit/issues) [\[rywalker.com\]](https://rywalker.com/research/github-spec-kit) | Eduardo Luz published a LinkedIn article on SDD and Spec Kit [\[linkedin.com\]](https://www.linkedin.com/pulse/specification-driven-development-sdd-github-spec-kit-elevating-luz-tojmc?tl=en). Erick Matsen blogged a walkthrough of building a bioinformatics pipeline with Spec Kit [\[matsen.fredhutch.org\]](https://matsen.fredhutch.org/general/2026/02/10/spec-kit-walkthrough.html). Microsoft MVP [Eric Boyd](https://ericboyd.com/) (not the Microsoft AI Platform VP of the same name) presented at the Cleveland .NET User Group [\[ericboyd.com\]](https://ericboyd.com/events/cleveland-csharp-user-group-february-25-2026-spec-driven-development-sdd-github-spec-kit). | **v0.2.0** was released in early March, consolidating February's work. It added extensions for Jira and Azure DevOps, community plugin support, and agents for Tabnine CLI and Kiro CLI [\[github.com\]](https://github.com/github/spec-kit/releases). Future work includes spec lifecycle management and progress toward a stable 1.0 release [\[martinfowler.com\]](https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html). |
***
## Spec Kit Project Updates
Spec Kit released versions **v0.1.7** through **v0.1.13** during February. Version 0.1.7 (early February) updated documentation for the newly introduced **dual-catalog extension system**, which allows both core and community extension catalogs to coexist. Subsequent patches (0.1.8, 0.1.9, etc.) bumped dependencies such as GitHub Actions versions and resolved minor issues. **v0.1.10** fixed YAML front-matter handling in generated files. By late February, **v0.1.12** and **v0.1.13** shipped with additional fixes in preparation for the next version bump. [\[github.com\]](https://github.com/github/spec-kit/releases)
The main architectural addition was the **modular extension system** with separate "core" and "community" extension catalogs for third-party add-ons. Multiple community-contributed extensions were merged during the month, including a **Jira extension** for issue tracker integration, an **Azure DevOps extension**, and utility extensions for code review, retrospective documentation, and CI/CD sync. The pending 0.2.0 release changelog lists over a dozen changes from February, including the extension additions and support for **multiple agent catalogs concurrently**. [\[github.com\]](https://github.com/github/spec-kit/releases)
By end of February, **over 330 issues/feature requests had been closed on GitHub** (out of ~870 filed to date). External contributors submitted pull requests including the **Tabnine CLI support**, which was merged in late February. The repository reached ~71k stars and crossed 6,000 forks. [\[github.com\]](https://github.com/github/spec-kit/issues) [\[github.com\]](https://github.com/github/spec-kit/releases) [\[rywalker.com\]](https://rywalker.com/research/github-spec-kit)
On the stability side, February's work focused on tightening core workflows and fixing edge-case bugs in the specification, planning, and task-generation commands. The team addressed file-handling issues (e.g., clarifying how output files are created/appended) and improved the reliability of the automated release pipeline. The project also added **Kiro CLI** to the supported agent list and updated integration scripts for Cursor and Code Interpreter, bringing the total number of supported AI coding assistants to over 20. [\[github.com\]](https://github.com/github/spec-kit/releases) [\[github.com\]](https://github.com/github/spec-kit)
## Community & Content
**Eduardo Luz** published a LinkedIn article on Feb 15 titled *"Specification Driven Development (SDD) and the GitHub Spec Kit: Elevating Software Engineering."* The article draws on his experience as a senior engineer to describe common causes of technical debt and inconsistent designs, and how SDD addresses them. It walks through Spec Kit's **four-layer approach** (Constitution, Design, Tasks, Implementation) and discusses treating specifications as a source of truth. The post generated discussion among software architects on LinkedIn about reducing misunderstandings and rework through spec-driven workflows. [\[linkedin.com\]](https://www.linkedin.com/pulse/specification-driven-development-sdd-github-spec-kit-elevating-luz-tojmc?tl=en)
**Erick Matsen** (Fred Hutchinson Cancer Center) posted a detailed walkthrough on Feb 10 titled *"Spec-Driven Development with spec-kit."* He describes building a **bioinformatics pipeline** in a single day using Spec Kit's workflow (from `speckit.constitution` to `speckit.implement`). The post includes command outputs and notes on decisions made along the way, such as refining the spec to add domain-specific requirements. He writes: "I really recommend this approach. This feels like the way software development should be." [\[matsen.fredhutch.org\]](https://matsen.fredhutch.org/general/2026/02/10/spec-kit-walkthrough.html) [\[github.com\]](https://github.com/mnriem/spec-kit-dotnet-cli-demo)
Several other tutorials and guides appeared during the month. An article on *IntuitionLabs* (updated Feb 21) provided a guide to Spec Kit covering the philosophy behind SDD and a walkthrough of the four-phase workflow with examples. A piece by Ry Walker (Feb 22) summarized key aspects of Spec Kit, noting its agent-agnostic design and 71k-star count. Microsoft's Developer Blog post from late 2025 (*"Diving Into Spec-Driven Development with GitHub Spec Kit"* by Den Delimarsky) continued to circulate among new users. [\[intuitionlabs.ai\]](https://intuitionlabs.ai/articles/spec-driven-development-spec-kit) [\[rywalker.com\]](https://rywalker.com/research/github-spec-kit)
On **Feb 25**, the Cleveland C# .NET User Group hosted a session titled *"Spec Driven Development with GitHub Spec Kit."* The talk was delivered by Microsoft MVP **[Eric Boyd](https://ericboyd.com/)** (Cleveland-based .NET developer; not to be confused with the Microsoft AI Platform VP of the same name). Boyd covered how specs change an AI coding assistant's output, patterns for iterating and refining specs over multiple cycles, and moving from ad-hoc prompting to a repeatable spec-driven workflow. Other groups, including GDG Madison, also listed sessions on spec-driven development in late February and early March. [\[ericboyd.com\]](https://ericboyd.com/events/cleveland-csharp-user-group-february-25-2026-spec-driven-development-sdd-github-spec-kit)
On GitHub, the **Spec Kit Discussions forum** saw activity around installation troubleshooting, handling multi-feature projects with Spec Kit's branching model, and feature suggestions. One thread discussed how Spec Kit treats each spec as a short-lived artifact tied to a feature branch, which led to discussion about future support for long-running "spec of record" use cases. [\[martinfowler.com\]](https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html)
## SDD Ecosystem
Other spec-driven development tools also saw activity in February.
AWS **Kiro** released version 0.10 on Feb 18 with two new spec workflows: a **Design-First** mode (starting from architecture/pseudocode to derive requirements) and a **Bugfix** mode (structured root-cause analysis producing a `bugfix.md` spec file). Kiro also added hunk-level code review for AI-generated changes and pre/post task hooks for custom automation. AWS expanded Kiro to GovCloud regions on Feb 17 for government compliance use cases. [\[kiro.dev\]](https://kiro.dev/changelog/)
**OpenSpec** (by Fission AI), a lightweight SDD framework, reached ~29.3k stars and nearly 2k forks. Its community published guides and comparisons during the month, including *"Spec-Driven Development Made Easy: A Practical Guide with OpenSpec."* OpenSpec emphasizes simplicity and flexibility, integrating with multiple AI coding assistants via YAML configs.
**Tessl** remained in private beta. As described by Thoughtworks writer Birgitta Boeckeler, Tessl pursues a **spec-as-source** model where specifications are maintained long-term and directly generate code files one-to-one, with generated code labeled as "do not edit." This contrasts with Spec Kit's current approach of creating specs per feature/branch. [\[martinfowler.com\]](https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html)
An **arXiv preprint** (January 2026) categorized SDD implementations into three levels: *spec-first*, *spec-anchored*, and *spec-as-source*. Spec Kit was identified as primarily spec-first with elements of spec-anchored. Tech media published reviews including a *Vibe Coding* "GitHub Spec Kit Review (2026)" and a blog post titled *"Putting Spec Kit Through Its Paces: Radical Idea or Reinvented Waterfall?"* which concluded that SDD with AI assistance is more iterative than traditional Waterfall. [\[intuitionlabs.ai\]](https://intuitionlabs.ai/articles/spec-driven-development-spec-kit) [\[martinfowler.com\]](https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html)
## Roadmap
**v0.2.0** was released on March 10, 2026, consolidating the month's work. It includes new extensions (Jira, Azure DevOps, review, sync), support for multiple extension catalogs and community plugins, and additional agent integrations (Tabnine CLI, Kiro CLI). [\[github.com\]](https://github.com/github/spec-kit/releases)
Areas under discussion or in progress for future development:
- **Spec lifecycle management** -- supporting longer-lived specifications that can evolve across multiple iterations, rather than being tied to a single feature branch. Users have raised this in GitHub Discussions, and the concept of "spec-anchored" development is under consideration. [\[martinfowler.com\]](https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html)
- **CI/CD integration** -- incorporating Spec Kit verification (e.g., `speckit.checklist` or `speckit.verify`) into pull request workflows and project management tools. February's Jira and Azure DevOps extensions are a step in this direction. [\[github.com\]](https://github.com/github/spec-kit/releases)
- **Continued agent support** -- adding integrations as new AI coding assistants emerge. The project currently supports over 20 agents and has been adding new ones (Kiro CLI, Tabnine CLI) as they become available. [\[github.com\]](https://github.com/github/spec-kit)
- **Community ecosystem** -- the open extension model allows external contributors to add functionality directly. February's Jira and Azure DevOps plugins were community-contributed. The Spec Kit README now links to community walkthrough demos for .NET, Spring Boot, and other stacks. [\[github.com\]](https://github.com/github/spec-kit)

View File

@@ -1,6 +1,6 @@
[project] [project]
name = "specify-cli" name = "specify-cli"
version = "0.3.0" version = "0.2.1"
description = "Specify CLI, part of GitHub Spec Kit. A tool to bootstrap your projects for Spec-Driven Development (SDD)." description = "Specify CLI, part of GitHub Spec Kit. A tool to bootstrap your projects for Spec-Driven Development (SDD)."
requires-python = ">=3.11" requires-python = ">=3.11"
dependencies = [ dependencies = [

View File

@@ -79,28 +79,15 @@ SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/common.sh" source "$SCRIPT_DIR/common.sh"
# Get feature paths and validate branch # Get feature paths and validate branch
_paths_output=$(get_feature_paths) || { echo "ERROR: Failed to resolve feature paths" >&2; exit 1; } eval $(get_feature_paths)
eval "$_paths_output"
unset _paths_output
check_feature_branch "$CURRENT_BRANCH" "$HAS_GIT" || exit 1 check_feature_branch "$CURRENT_BRANCH" "$HAS_GIT" || exit 1
# If paths-only mode, output paths and exit (support JSON + paths-only combined) # If paths-only mode, output paths and exit (support JSON + paths-only combined)
if $PATHS_ONLY; then if $PATHS_ONLY; then
if $JSON_MODE; then if $JSON_MODE; then
# Minimal JSON paths payload (no validation performed) # Minimal JSON paths payload (no validation performed)
if has_jq; then printf '{"REPO_ROOT":"%s","BRANCH":"%s","FEATURE_DIR":"%s","FEATURE_SPEC":"%s","IMPL_PLAN":"%s","TASKS":"%s"}\n' \
jq -cn \ "$REPO_ROOT" "$CURRENT_BRANCH" "$FEATURE_DIR" "$FEATURE_SPEC" "$IMPL_PLAN" "$TASKS"
--arg repo_root "$REPO_ROOT" \
--arg branch "$CURRENT_BRANCH" \
--arg feature_dir "$FEATURE_DIR" \
--arg feature_spec "$FEATURE_SPEC" \
--arg impl_plan "$IMPL_PLAN" \
--arg tasks "$TASKS" \
'{REPO_ROOT:$repo_root,BRANCH:$branch,FEATURE_DIR:$feature_dir,FEATURE_SPEC:$feature_spec,IMPL_PLAN:$impl_plan,TASKS:$tasks}'
else
printf '{"REPO_ROOT":"%s","BRANCH":"%s","FEATURE_DIR":"%s","FEATURE_SPEC":"%s","IMPL_PLAN":"%s","TASKS":"%s"}\n' \
"$(json_escape "$REPO_ROOT")" "$(json_escape "$CURRENT_BRANCH")" "$(json_escape "$FEATURE_DIR")" "$(json_escape "$FEATURE_SPEC")" "$(json_escape "$IMPL_PLAN")" "$(json_escape "$TASKS")"
fi
else else
echo "REPO_ROOT: $REPO_ROOT" echo "REPO_ROOT: $REPO_ROOT"
echo "BRANCH: $CURRENT_BRANCH" echo "BRANCH: $CURRENT_BRANCH"
@@ -154,25 +141,14 @@ fi
# Output results # Output results
if $JSON_MODE; then if $JSON_MODE; then
# Build JSON array of documents # Build JSON array of documents
if has_jq; then if [[ ${#docs[@]} -eq 0 ]]; then
if [[ ${#docs[@]} -eq 0 ]]; then json_docs="[]"
json_docs="[]"
else
json_docs=$(printf '%s\n' "${docs[@]}" | jq -R . | jq -s .)
fi
jq -cn \
--arg feature_dir "$FEATURE_DIR" \
--argjson docs "$json_docs" \
'{FEATURE_DIR:$feature_dir,AVAILABLE_DOCS:$docs}'
else else
if [[ ${#docs[@]} -eq 0 ]]; then json_docs=$(printf '"%s",' "${docs[@]}")
json_docs="[]" json_docs="[${json_docs%,}]"
else
json_docs=$(printf '"%s",' "${docs[@]}")
json_docs="[${json_docs%,}]"
fi
printf '{"FEATURE_DIR":"%s","AVAILABLE_DOCS":%s}\n' "$(json_escape "$FEATURE_DIR")" "$json_docs"
fi fi
printf '{"FEATURE_DIR":"%s","AVAILABLE_DOCS":%s}\n' "$FEATURE_DIR" "$json_docs"
else else
# Text output # Text output
echo "FEATURE_DIR:$FEATURE_DIR" echo "FEATURE_DIR:$FEATURE_DIR"

View File

@@ -120,7 +120,7 @@ find_feature_dir_by_prefix() {
# Multiple matches - this shouldn't happen with proper naming convention # Multiple matches - this shouldn't happen with proper naming convention
echo "ERROR: Multiple spec directories found with prefix '$prefix': ${matches[*]}" >&2 echo "ERROR: Multiple spec directories found with prefix '$prefix': ${matches[*]}" >&2
echo "Please ensure only one spec directory exists per numeric prefix." >&2 echo "Please ensure only one spec directory exists per numeric prefix." >&2
return 1 echo "$specs_dir/$branch_name" # Return something to avoid breaking the script
fi fi
} }
@@ -134,42 +134,21 @@ get_feature_paths() {
fi fi
# Use prefix-based lookup to support multiple branches per spec # Use prefix-based lookup to support multiple branches per spec
local feature_dir local feature_dir=$(find_feature_dir_by_prefix "$repo_root" "$current_branch")
if ! feature_dir=$(find_feature_dir_by_prefix "$repo_root" "$current_branch"); then
echo "ERROR: Failed to resolve feature directory" >&2
return 1
fi
# Use printf '%q' to safely quote values, preventing shell injection cat <<EOF
# via crafted branch names or paths containing special characters REPO_ROOT='$repo_root'
printf 'REPO_ROOT=%q\n' "$repo_root" CURRENT_BRANCH='$current_branch'
printf 'CURRENT_BRANCH=%q\n' "$current_branch" HAS_GIT='$has_git_repo'
printf 'HAS_GIT=%q\n' "$has_git_repo" FEATURE_DIR='$feature_dir'
printf 'FEATURE_DIR=%q\n' "$feature_dir" FEATURE_SPEC='$feature_dir/spec.md'
printf 'FEATURE_SPEC=%q\n' "$feature_dir/spec.md" IMPL_PLAN='$feature_dir/plan.md'
printf 'IMPL_PLAN=%q\n' "$feature_dir/plan.md" TASKS='$feature_dir/tasks.md'
printf 'TASKS=%q\n' "$feature_dir/tasks.md" RESEARCH='$feature_dir/research.md'
printf 'RESEARCH=%q\n' "$feature_dir/research.md" DATA_MODEL='$feature_dir/data-model.md'
printf 'DATA_MODEL=%q\n' "$feature_dir/data-model.md" QUICKSTART='$feature_dir/quickstart.md'
printf 'QUICKSTART=%q\n' "$feature_dir/quickstart.md" CONTRACTS_DIR='$feature_dir/contracts'
printf 'CONTRACTS_DIR=%q\n' "$feature_dir/contracts" EOF
}
# Check if jq is available for safe JSON construction
has_jq() {
command -v jq >/dev/null 2>&1
}
# Escape a string for safe embedding in a JSON value (fallback when jq is unavailable).
# Handles backslash, double-quote, and control characters (newline, tab, carriage return).
json_escape() {
local s="$1"
s="${s//\\/\\\\}"
s="${s//\"/\\\"}"
s="${s//$'\n'/\\n}"
s="${s//$'\t'/\\t}"
s="${s//$'\r'/\\r}"
printf '%s' "$s"
} }
check_file() { [[ -f "$1" ]] && echo "$2" || echo "$2"; } check_file() { [[ -f "$1" ]] && echo "$2" || echo "$2"; }
@@ -246,8 +225,6 @@ except Exception:
local core="$base/${template_name}.md" local core="$base/${template_name}.md"
[ -f "$core" ] && echo "$core" && return 0 [ -f "$core" ] && echo "$core" && return 0
# Return success with empty output so callers using set -e don't abort; return 1
# callers check [ -n "$TEMPLATE" ] to detect "not found".
return 0
} }

View File

@@ -162,17 +162,6 @@ clean_branch_name() {
echo "$name" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/-\+/-/g' | sed 's/^-//' | sed 's/-$//' echo "$name" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/-\+/-/g' | sed 's/^-//' | sed 's/-$//'
} }
# Escape a string for safe embedding in a JSON value (fallback when jq is unavailable).
json_escape() {
local s="$1"
s="${s//\\/\\\\}"
s="${s//\"/\\\"}"
s="${s//$'\n'/\\n}"
s="${s//$'\t'/\\t}"
s="${s//$'\r'/\\r}"
printf '%s' "$s"
}
# Resolve repository root. Prefer git information when available, but fall back # Resolve repository root. Prefer git information when available, but fall back
# to searching for repository markers so the workflow still functions in repositories that # to searching for repository markers so the workflow still functions in repositories that
# were initialised with --no-git. # were initialised with --no-git.
@@ -312,22 +301,14 @@ TEMPLATE=$(resolve_template "spec-template" "$REPO_ROOT")
SPEC_FILE="$FEATURE_DIR/spec.md" SPEC_FILE="$FEATURE_DIR/spec.md"
if [ -n "$TEMPLATE" ] && [ -f "$TEMPLATE" ]; then cp "$TEMPLATE" "$SPEC_FILE"; else touch "$SPEC_FILE"; fi if [ -n "$TEMPLATE" ] && [ -f "$TEMPLATE" ]; then cp "$TEMPLATE" "$SPEC_FILE"; else touch "$SPEC_FILE"; fi
# Inform the user how to persist the feature variable in their own shell # Set the SPECIFY_FEATURE environment variable for the current session
printf '# To persist: export SPECIFY_FEATURE=%q\n' "$BRANCH_NAME" >&2 export SPECIFY_FEATURE="$BRANCH_NAME"
if $JSON_MODE; then if $JSON_MODE; then
if command -v jq >/dev/null 2>&1; then printf '{"BRANCH_NAME":"%s","SPEC_FILE":"%s","FEATURE_NUM":"%s"}\n' "$BRANCH_NAME" "$SPEC_FILE" "$FEATURE_NUM"
jq -cn \
--arg branch_name "$BRANCH_NAME" \
--arg spec_file "$SPEC_FILE" \
--arg feature_num "$FEATURE_NUM" \
'{BRANCH_NAME:$branch_name,SPEC_FILE:$spec_file,FEATURE_NUM:$feature_num}'
else
printf '{"BRANCH_NAME":"%s","SPEC_FILE":"%s","FEATURE_NUM":"%s"}\n' "$(json_escape "$BRANCH_NAME")" "$(json_escape "$SPEC_FILE")" "$(json_escape "$FEATURE_NUM")"
fi
else else
echo "BRANCH_NAME: $BRANCH_NAME" echo "BRANCH_NAME: $BRANCH_NAME"
echo "SPEC_FILE: $SPEC_FILE" echo "SPEC_FILE: $SPEC_FILE"
echo "FEATURE_NUM: $FEATURE_NUM" echo "FEATURE_NUM: $FEATURE_NUM"
printf '# To persist in your shell: export SPECIFY_FEATURE=%q\n' "$BRANCH_NAME" echo "SPECIFY_FEATURE environment variable set to: $BRANCH_NAME"
fi fi

View File

@@ -28,9 +28,7 @@ SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/common.sh" source "$SCRIPT_DIR/common.sh"
# Get all paths and variables from common functions # Get all paths and variables from common functions
_paths_output=$(get_feature_paths) || { echo "ERROR: Failed to resolve feature paths" >&2; exit 1; } eval $(get_feature_paths)
eval "$_paths_output"
unset _paths_output
# Check if we're on a proper feature branch (only for git repos) # Check if we're on a proper feature branch (only for git repos)
check_feature_branch "$CURRENT_BRANCH" "$HAS_GIT" || exit 1 check_feature_branch "$CURRENT_BRANCH" "$HAS_GIT" || exit 1
@@ -51,18 +49,8 @@ fi
# Output results # Output results
if $JSON_MODE; then if $JSON_MODE; then
if has_jq; then printf '{"FEATURE_SPEC":"%s","IMPL_PLAN":"%s","SPECS_DIR":"%s","BRANCH":"%s","HAS_GIT":"%s"}\n' \
jq -cn \ "$FEATURE_SPEC" "$IMPL_PLAN" "$FEATURE_DIR" "$CURRENT_BRANCH" "$HAS_GIT"
--arg feature_spec "$FEATURE_SPEC" \
--arg impl_plan "$IMPL_PLAN" \
--arg specs_dir "$FEATURE_DIR" \
--arg branch "$CURRENT_BRANCH" \
--arg has_git "$HAS_GIT" \
'{FEATURE_SPEC:$feature_spec,IMPL_PLAN:$impl_plan,SPECS_DIR:$specs_dir,BRANCH:$branch,HAS_GIT:$has_git}'
else
printf '{"FEATURE_SPEC":"%s","IMPL_PLAN":"%s","SPECS_DIR":"%s","BRANCH":"%s","HAS_GIT":"%s"}\n' \
"$(json_escape "$FEATURE_SPEC")" "$(json_escape "$IMPL_PLAN")" "$(json_escape "$FEATURE_DIR")" "$(json_escape "$CURRENT_BRANCH")" "$(json_escape "$HAS_GIT")"
fi
else else
echo "FEATURE_SPEC: $FEATURE_SPEC" echo "FEATURE_SPEC: $FEATURE_SPEC"
echo "IMPL_PLAN: $IMPL_PLAN" echo "IMPL_PLAN: $IMPL_PLAN"

View File

@@ -30,12 +30,12 @@
# #
# 5. Multi-Agent Support # 5. Multi-Agent Support
# - Handles agent-specific file paths and naming conventions # - Handles agent-specific file paths and naming conventions
# - Supports: Claude, Gemini, Copilot, Cursor, Qwen, opencode, Codex, Windsurf, Kilo Code, Auggie CLI, Roo Code, CodeBuddy CLI, Qoder CLI, Amp, SHAI, Tabnine CLI, Kiro CLI, Mistral Vibe, Kimi Code, Antigravity or Generic # - Supports: Claude, Gemini, Copilot, Cursor, Qwen, opencode, Codex, Windsurf, Kilo Code, Auggie CLI, Roo Code, CodeBuddy CLI, Qoder CLI, Amp, SHAI, Tabnine CLI, Kiro CLI, Mistral Vibe, Antigravity or Generic
# - Can update single agents or all existing agent files # - Can update single agents or all existing agent files
# - Creates default Claude file if no agent files exist # - Creates default Claude file if no agent files exist
# #
# Usage: ./update-agent-context.sh [agent_type] # Usage: ./update-agent-context.sh [agent_type]
# Agent types: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|kimi|generic # Agent types: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic
# Leave empty to update all existing agent files # Leave empty to update all existing agent files
set -e set -e
@@ -53,9 +53,7 @@ SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/common.sh" source "$SCRIPT_DIR/common.sh"
# Get all paths and variables from common functions # Get all paths and variables from common functions
_paths_output=$(get_feature_paths) || { echo "ERROR: Failed to resolve feature paths" >&2; exit 1; } eval $(get_feature_paths)
eval "$_paths_output"
unset _paths_output
NEW_PLAN="$IMPL_PLAN" # Alias for compatibility with existing code NEW_PLAN="$IMPL_PLAN" # Alias for compatibility with existing code
AGENT_TYPE="${1:-}" AGENT_TYPE="${1:-}"
@@ -73,16 +71,13 @@ AUGGIE_FILE="$REPO_ROOT/.augment/rules/specify-rules.md"
ROO_FILE="$REPO_ROOT/.roo/rules/specify-rules.md" ROO_FILE="$REPO_ROOT/.roo/rules/specify-rules.md"
CODEBUDDY_FILE="$REPO_ROOT/CODEBUDDY.md" CODEBUDDY_FILE="$REPO_ROOT/CODEBUDDY.md"
QODER_FILE="$REPO_ROOT/QODER.md" QODER_FILE="$REPO_ROOT/QODER.md"
# AMP, Kiro CLI, and IBM Bob all share AGENTS.md — use AGENTS_FILE to avoid AMP_FILE="$REPO_ROOT/AGENTS.md"
# updating the same file multiple times.
AMP_FILE="$AGENTS_FILE"
SHAI_FILE="$REPO_ROOT/SHAI.md" SHAI_FILE="$REPO_ROOT/SHAI.md"
TABNINE_FILE="$REPO_ROOT/TABNINE.md" TABNINE_FILE="$REPO_ROOT/TABNINE.md"
KIRO_FILE="$AGENTS_FILE" KIRO_FILE="$REPO_ROOT/AGENTS.md"
AGY_FILE="$REPO_ROOT/.agent/rules/specify-rules.md" AGY_FILE="$REPO_ROOT/.agent/rules/specify-rules.md"
BOB_FILE="$AGENTS_FILE" BOB_FILE="$REPO_ROOT/AGENTS.md"
VIBE_FILE="$REPO_ROOT/.vibe/agents/specify-agents.md" VIBE_FILE="$REPO_ROOT/.vibe/agents/specify-agents.md"
KIMI_FILE="$REPO_ROOT/KIMI.md"
# Template file # Template file
TEMPLATE_FILE="$REPO_ROOT/.specify/templates/agent-file-template.md" TEMPLATE_FILE="$REPO_ROOT/.specify/templates/agent-file-template.md"
@@ -116,8 +111,6 @@ log_warning() {
# Cleanup function for temporary files # Cleanup function for temporary files
cleanup() { cleanup() {
local exit_code=$? local exit_code=$?
# Disarm traps to prevent re-entrant loop
trap - EXIT INT TERM
rm -f /tmp/agent_update_*_$$ rm -f /tmp/agent_update_*_$$
rm -f /tmp/manual_additions_$$ rm -f /tmp/manual_additions_$$
exit $exit_code exit $exit_code
@@ -482,7 +475,7 @@ update_existing_agent_file() {
fi fi
# Update timestamp # Update timestamp
if [[ "$line" =~ (\*\*)?Last\ updated(\*\*)?:.*[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] ]]; then if [[ "$line" =~ \*\*Last\ updated\*\*:.*[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] ]]; then
echo "$line" | sed "s/[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]/$current_date/" >> "$temp_file" echo "$line" | sed "s/[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]/$current_date/" >> "$temp_file"
else else
echo "$line" >> "$temp_file" echo "$line" >> "$temp_file"
@@ -613,74 +606,71 @@ update_specific_agent() {
case "$agent_type" in case "$agent_type" in
claude) claude)
update_agent_file "$CLAUDE_FILE" "Claude Code" || return 1 update_agent_file "$CLAUDE_FILE" "Claude Code"
;; ;;
gemini) gemini)
update_agent_file "$GEMINI_FILE" "Gemini CLI" || return 1 update_agent_file "$GEMINI_FILE" "Gemini CLI"
;; ;;
copilot) copilot)
update_agent_file "$COPILOT_FILE" "GitHub Copilot" || return 1 update_agent_file "$COPILOT_FILE" "GitHub Copilot"
;; ;;
cursor-agent) cursor-agent)
update_agent_file "$CURSOR_FILE" "Cursor IDE" || return 1 update_agent_file "$CURSOR_FILE" "Cursor IDE"
;; ;;
qwen) qwen)
update_agent_file "$QWEN_FILE" "Qwen Code" || return 1 update_agent_file "$QWEN_FILE" "Qwen Code"
;; ;;
opencode) opencode)
update_agent_file "$AGENTS_FILE" "opencode" || return 1 update_agent_file "$AGENTS_FILE" "opencode"
;; ;;
codex) codex)
update_agent_file "$AGENTS_FILE" "Codex CLI" || return 1 update_agent_file "$AGENTS_FILE" "Codex CLI"
;; ;;
windsurf) windsurf)
update_agent_file "$WINDSURF_FILE" "Windsurf" || return 1 update_agent_file "$WINDSURF_FILE" "Windsurf"
;; ;;
kilocode) kilocode)
update_agent_file "$KILOCODE_FILE" "Kilo Code" || return 1 update_agent_file "$KILOCODE_FILE" "Kilo Code"
;; ;;
auggie) auggie)
update_agent_file "$AUGGIE_FILE" "Auggie CLI" || return 1 update_agent_file "$AUGGIE_FILE" "Auggie CLI"
;; ;;
roo) roo)
update_agent_file "$ROO_FILE" "Roo Code" || return 1 update_agent_file "$ROO_FILE" "Roo Code"
;; ;;
codebuddy) codebuddy)
update_agent_file "$CODEBUDDY_FILE" "CodeBuddy CLI" || return 1 update_agent_file "$CODEBUDDY_FILE" "CodeBuddy CLI"
;; ;;
qodercli) qodercli)
update_agent_file "$QODER_FILE" "Qoder CLI" || return 1 update_agent_file "$QODER_FILE" "Qoder CLI"
;; ;;
amp) amp)
update_agent_file "$AMP_FILE" "Amp" || return 1 update_agent_file "$AMP_FILE" "Amp"
;; ;;
shai) shai)
update_agent_file "$SHAI_FILE" "SHAI" || return 1 update_agent_file "$SHAI_FILE" "SHAI"
;; ;;
tabnine) tabnine)
update_agent_file "$TABNINE_FILE" "Tabnine CLI" || return 1 update_agent_file "$TABNINE_FILE" "Tabnine CLI"
;; ;;
kiro-cli) kiro-cli)
update_agent_file "$KIRO_FILE" "Kiro CLI" || return 1 update_agent_file "$KIRO_FILE" "Kiro CLI"
;; ;;
agy) agy)
update_agent_file "$AGY_FILE" "Antigravity" || return 1 update_agent_file "$AGY_FILE" "Antigravity"
;; ;;
bob) bob)
update_agent_file "$BOB_FILE" "IBM Bob" || return 1 update_agent_file "$BOB_FILE" "IBM Bob"
;; ;;
vibe) vibe)
update_agent_file "$VIBE_FILE" "Mistral Vibe" || return 1 update_agent_file "$VIBE_FILE" "Mistral Vibe"
;;
kimi)
update_agent_file "$KIMI_FILE" "Kimi Code" || return 1
;; ;;
generic) generic)
log_info "Generic agent: no predefined context file. Use the agent-specific update script for your agent." log_info "Generic agent: no predefined context file. Use the agent-specific update script for your agent."
;; ;;
*) *)
log_error "Unknown agent type '$agent_type'" log_error "Unknown agent type '$agent_type'"
log_error "Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|kimi|generic" log_error "Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic"
exit 1 exit 1
;; ;;
esac esac
@@ -688,53 +678,101 @@ update_specific_agent() {
update_all_existing_agents() { update_all_existing_agents() {
local found_agent=false local found_agent=false
local _updated_paths=()
# Helper: skip non-existent files and files already updated (dedup by # Check each possible agent file and update if it exists
# realpath so that variables pointing to the same file — e.g. AMP_FILE, if [[ -f "$CLAUDE_FILE" ]]; then
# KIRO_FILE, BOB_FILE all resolving to AGENTS_FILE — are only written once). update_agent_file "$CLAUDE_FILE" "Claude Code"
# Uses a linear array instead of associative array for bash 3.2 compatibility.
update_if_new() {
local file="$1" name="$2"
[[ -f "$file" ]] || return 0
local real_path
real_path=$(realpath "$file" 2>/dev/null || echo "$file")
local p
if [[ ${#_updated_paths[@]} -gt 0 ]]; then
for p in "${_updated_paths[@]}"; do
[[ "$p" == "$real_path" ]] && return 0
done
fi
update_agent_file "$file" "$name" || return 1
_updated_paths+=("$real_path")
found_agent=true found_agent=true
} fi
update_if_new "$CLAUDE_FILE" "Claude Code" if [[ -f "$GEMINI_FILE" ]]; then
update_if_new "$GEMINI_FILE" "Gemini CLI" update_agent_file "$GEMINI_FILE" "Gemini CLI"
update_if_new "$COPILOT_FILE" "GitHub Copilot" found_agent=true
update_if_new "$CURSOR_FILE" "Cursor IDE" fi
update_if_new "$QWEN_FILE" "Qwen Code"
update_if_new "$AGENTS_FILE" "Codex/opencode" if [[ -f "$COPILOT_FILE" ]]; then
update_if_new "$AMP_FILE" "Amp" update_agent_file "$COPILOT_FILE" "GitHub Copilot"
update_if_new "$KIRO_FILE" "Kiro CLI" found_agent=true
update_if_new "$BOB_FILE" "IBM Bob" fi
update_if_new "$WINDSURF_FILE" "Windsurf"
update_if_new "$KILOCODE_FILE" "Kilo Code" if [[ -f "$CURSOR_FILE" ]]; then
update_if_new "$AUGGIE_FILE" "Auggie CLI" update_agent_file "$CURSOR_FILE" "Cursor IDE"
update_if_new "$ROO_FILE" "Roo Code" found_agent=true
update_if_new "$CODEBUDDY_FILE" "CodeBuddy CLI" fi
update_if_new "$SHAI_FILE" "SHAI"
update_if_new "$TABNINE_FILE" "Tabnine CLI" if [[ -f "$QWEN_FILE" ]]; then
update_if_new "$QODER_FILE" "Qoder CLI" update_agent_file "$QWEN_FILE" "Qwen Code"
update_if_new "$AGY_FILE" "Antigravity" found_agent=true
update_if_new "$VIBE_FILE" "Mistral Vibe" fi
update_if_new "$KIMI_FILE" "Kimi Code"
if [[ -f "$AGENTS_FILE" ]]; then
update_agent_file "$AGENTS_FILE" "Codex/opencode"
found_agent=true
fi
if [[ -f "$WINDSURF_FILE" ]]; then
update_agent_file "$WINDSURF_FILE" "Windsurf"
found_agent=true
fi
if [[ -f "$KILOCODE_FILE" ]]; then
update_agent_file "$KILOCODE_FILE" "Kilo Code"
found_agent=true
fi
if [[ -f "$AUGGIE_FILE" ]]; then
update_agent_file "$AUGGIE_FILE" "Auggie CLI"
found_agent=true
fi
if [[ -f "$ROO_FILE" ]]; then
update_agent_file "$ROO_FILE" "Roo Code"
found_agent=true
fi
if [[ -f "$CODEBUDDY_FILE" ]]; then
update_agent_file "$CODEBUDDY_FILE" "CodeBuddy CLI"
found_agent=true
fi
if [[ -f "$SHAI_FILE" ]]; then
update_agent_file "$SHAI_FILE" "SHAI"
found_agent=true
fi
if [[ -f "$TABNINE_FILE" ]]; then
update_agent_file "$TABNINE_FILE" "Tabnine CLI"
found_agent=true
fi
if [[ -f "$QODER_FILE" ]]; then
update_agent_file "$QODER_FILE" "Qoder CLI"
found_agent=true
fi
if [[ -f "$KIRO_FILE" ]]; then
update_agent_file "$KIRO_FILE" "Kiro CLI"
found_agent=true
fi
if [[ -f "$AGY_FILE" ]]; then
update_agent_file "$AGY_FILE" "Antigravity"
found_agent=true
fi
if [[ -f "$BOB_FILE" ]]; then
update_agent_file "$BOB_FILE" "IBM Bob"
found_agent=true
fi
if [[ -f "$VIBE_FILE" ]]; then
update_agent_file "$VIBE_FILE" "Mistral Vibe"
found_agent=true
fi
# If no agent files exist, create a default Claude file # If no agent files exist, create a default Claude file
if [[ "$found_agent" == false ]]; then if [[ "$found_agent" == false ]]; then
log_info "No existing agent files found, creating default Claude file..." log_info "No existing agent files found, creating default Claude file..."
update_agent_file "$CLAUDE_FILE" "Claude Code" || return 1 update_agent_file "$CLAUDE_FILE" "Claude Code"
fi fi
} }
print_summary() { print_summary() {
@@ -754,7 +792,7 @@ print_summary() {
fi fi
echo echo
log_info "Usage: $0 [claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|kimi|generic]" log_info "Usage: $0 [claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic]"
} }
#============================================================================== #==============================================================================

View File

@@ -163,7 +163,7 @@ function Resolve-Template {
$presets = $registryData.presets $presets = $registryData.presets
if ($presets) { if ($presets) {
$sortedPresets = $presets.PSObject.Properties | $sortedPresets = $presets.PSObject.Properties |
Sort-Object { if ($null -ne $_.Value.priority) { $_.Value.priority } else { 10 } } | Sort-Object { if ($_.Value.priority) { $_.Value.priority } else { 10 } } |
ForEach-Object { $_.Name } ForEach-Object { $_.Name }
} }
} catch { } catch {

View File

@@ -253,7 +253,7 @@ if ($branchName.Length -gt $maxBranchLength) {
if ($hasGit) { if ($hasGit) {
$branchCreated = $false $branchCreated = $false
try { try {
git checkout -q -b $branchName 2>$null | Out-Null git checkout -b $branchName 2>$null | Out-Null
if ($LASTEXITCODE -eq 0) { if ($LASTEXITCODE -eq 0) {
$branchCreated = $true $branchCreated = $true
} }

View File

@@ -9,7 +9,7 @@ Mirrors the behavior of scripts/bash/update-agent-context.sh:
2. Plan Data Extraction 2. Plan Data Extraction
3. Agent File Management (create from template or update existing) 3. Agent File Management (create from template or update existing)
4. Content Generation (technology stack, recent changes, timestamp) 4. Content Generation (technology stack, recent changes, timestamp)
5. Multi-Agent Support (claude, gemini, copilot, cursor-agent, qwen, opencode, codex, windsurf, kilocode, auggie, roo, codebuddy, amp, shai, tabnine, kiro-cli, agy, bob, vibe, qodercli, kimi, generic) 5. Multi-Agent Support (claude, gemini, copilot, cursor-agent, qwen, opencode, codex, windsurf, kilocode, auggie, roo, codebuddy, amp, shai, tabnine, kiro-cli, agy, bob, vibe, qodercli, generic)
.PARAMETER AgentType .PARAMETER AgentType
Optional agent key to update a single agent. If omitted, updates all existing agent files (creating a default Claude file if none exist). Optional agent key to update a single agent. If omitted, updates all existing agent files (creating a default Claude file if none exist).
@@ -25,7 +25,7 @@ Relies on common helper functions in common.ps1
#> #>
param( param(
[Parameter(Position=0)] [Parameter(Position=0)]
[ValidateSet('claude','gemini','copilot','cursor-agent','qwen','opencode','codex','windsurf','kilocode','auggie','roo','codebuddy','amp','shai','tabnine','kiro-cli','agy','bob','qodercli','vibe','kimi','generic')] [ValidateSet('claude','gemini','copilot','cursor-agent','qwen','opencode','codex','windsurf','kilocode','auggie','roo','codebuddy','amp','shai','tabnine','kiro-cli','agy','bob','qodercli','vibe','generic')]
[string]$AgentType [string]$AgentType
) )
@@ -63,7 +63,6 @@ $KIRO_FILE = Join-Path $REPO_ROOT 'AGENTS.md'
$AGY_FILE = Join-Path $REPO_ROOT '.agent/rules/specify-rules.md' $AGY_FILE = Join-Path $REPO_ROOT '.agent/rules/specify-rules.md'
$BOB_FILE = Join-Path $REPO_ROOT 'AGENTS.md' $BOB_FILE = Join-Path $REPO_ROOT 'AGENTS.md'
$VIBE_FILE = Join-Path $REPO_ROOT '.vibe/agents/specify-agents.md' $VIBE_FILE = Join-Path $REPO_ROOT '.vibe/agents/specify-agents.md'
$KIMI_FILE = Join-Path $REPO_ROOT 'KIMI.md'
$TEMPLATE_FILE = Join-Path $REPO_ROOT '.specify/templates/agent-file-template.md' $TEMPLATE_FILE = Join-Path $REPO_ROOT '.specify/templates/agent-file-template.md'
@@ -331,7 +330,7 @@ function Update-ExistingAgentFile {
if ($existingChanges -lt 2) { $output.Add($line); $existingChanges++ } if ($existingChanges -lt 2) { $output.Add($line); $existingChanges++ }
continue continue
} }
if ($line -match '(\*\*)?Last updated(\*\*)?: .*\d{4}-\d{2}-\d{2}') { if ($line -match '\*\*Last updated\*\*: .*\d{4}-\d{2}-\d{2}') {
$output.Add(($line -replace '\d{4}-\d{2}-\d{2}',$Date.ToString('yyyy-MM-dd'))) $output.Add(($line -replace '\d{4}-\d{2}-\d{2}',$Date.ToString('yyyy-MM-dd')))
continue continue
} }
@@ -407,9 +406,8 @@ function Update-SpecificAgent {
'agy' { Update-AgentFile -TargetFile $AGY_FILE -AgentName 'Antigravity' } 'agy' { Update-AgentFile -TargetFile $AGY_FILE -AgentName 'Antigravity' }
'bob' { Update-AgentFile -TargetFile $BOB_FILE -AgentName 'IBM Bob' } 'bob' { Update-AgentFile -TargetFile $BOB_FILE -AgentName 'IBM Bob' }
'vibe' { Update-AgentFile -TargetFile $VIBE_FILE -AgentName 'Mistral Vibe' } 'vibe' { Update-AgentFile -TargetFile $VIBE_FILE -AgentName 'Mistral Vibe' }
'kimi' { Update-AgentFile -TargetFile $KIMI_FILE -AgentName 'Kimi Code' }
'generic' { Write-Info 'Generic agent: no predefined context file. Use the agent-specific update script for your agent.' } 'generic' { Write-Info 'Generic agent: no predefined context file. Use the agent-specific update script for your agent.' }
default { Write-Err "Unknown agent type '$Type'"; Write-Err 'Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|kimi|generic'; return $false } default { Write-Err "Unknown agent type '$Type'"; Write-Err 'Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic'; return $false }
} }
} }
@@ -434,7 +432,6 @@ function Update-AllExistingAgents {
if (Test-Path $AGY_FILE) { if (-not (Update-AgentFile -TargetFile $AGY_FILE -AgentName 'Antigravity')) { $ok = $false }; $found = $true } if (Test-Path $AGY_FILE) { if (-not (Update-AgentFile -TargetFile $AGY_FILE -AgentName 'Antigravity')) { $ok = $false }; $found = $true }
if (Test-Path $BOB_FILE) { if (-not (Update-AgentFile -TargetFile $BOB_FILE -AgentName 'IBM Bob')) { $ok = $false }; $found = $true } if (Test-Path $BOB_FILE) { if (-not (Update-AgentFile -TargetFile $BOB_FILE -AgentName 'IBM Bob')) { $ok = $false }; $found = $true }
if (Test-Path $VIBE_FILE) { if (-not (Update-AgentFile -TargetFile $VIBE_FILE -AgentName 'Mistral Vibe')) { $ok = $false }; $found = $true } if (Test-Path $VIBE_FILE) { if (-not (Update-AgentFile -TargetFile $VIBE_FILE -AgentName 'Mistral Vibe')) { $ok = $false }; $found = $true }
if (Test-Path $KIMI_FILE) { if (-not (Update-AgentFile -TargetFile $KIMI_FILE -AgentName 'Kimi Code')) { $ok = $false }; $found = $true }
if (-not $found) { if (-not $found) {
Write-Info 'No existing agent files found, creating default Claude file...' Write-Info 'No existing agent files found, creating default Claude file...'
if (-not (Update-AgentFile -TargetFile $CLAUDE_FILE -AgentName 'Claude Code')) { $ok = $false } if (-not (Update-AgentFile -TargetFile $CLAUDE_FILE -AgentName 'Claude Code')) { $ok = $false }

File diff suppressed because it is too large Load Diff

View File

@@ -48,9 +48,9 @@ class CommandRegistrar:
}, },
"qwen": { "qwen": {
"dir": ".qwen/commands", "dir": ".qwen/commands",
"format": "markdown", "format": "toml",
"args": "$ARGUMENTS", "args": "{{args}}",
"extension": ".md" "extension": ".toml"
}, },
"opencode": { "opencode": {
"dir": ".opencode/command", "dir": ".opencode/command",
@@ -71,19 +71,19 @@ class CommandRegistrar:
"extension": ".md" "extension": ".md"
}, },
"kilocode": { "kilocode": {
"dir": ".kilocode/workflows", "dir": ".kilocode/rules",
"format": "markdown", "format": "markdown",
"args": "$ARGUMENTS", "args": "$ARGUMENTS",
"extension": ".md" "extension": ".md"
}, },
"auggie": { "auggie": {
"dir": ".augment/commands", "dir": ".augment/rules",
"format": "markdown", "format": "markdown",
"args": "$ARGUMENTS", "args": "$ARGUMENTS",
"extension": ".md" "extension": ".md"
}, },
"roo": { "roo": {
"dir": ".roo/commands", "dir": ".roo/rules",
"format": "markdown", "format": "markdown",
"args": "$ARGUMENTS", "args": "$ARGUMENTS",
"extension": ".md" "extension": ".md"
@@ -129,12 +129,6 @@ class CommandRegistrar:
"format": "markdown", "format": "markdown",
"args": "$ARGUMENTS", "args": "$ARGUMENTS",
"extension": ".md" "extension": ".md"
},
"kimi": {
"dir": ".kimi/skills",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": "/SKILL.md"
} }
} }
@@ -324,7 +318,6 @@ class CommandRegistrar:
raise ValueError(f"Unsupported format: {agent_config['format']}") raise ValueError(f"Unsupported format: {agent_config['format']}")
dest_file = commands_dir / f"{cmd_name}{agent_config['extension']}" dest_file = commands_dir / f"{cmd_name}{agent_config['extension']}"
dest_file.parent.mkdir(parents=True, exist_ok=True)
dest_file.write_text(output, encoding="utf-8") dest_file.write_text(output, encoding="utf-8")
if agent_name == "copilot": if agent_name == "copilot":
@@ -334,7 +327,6 @@ class CommandRegistrar:
for alias in cmd_info.get("aliases", []): for alias in cmd_info.get("aliases", []):
alias_file = commands_dir / f"{alias}{agent_config['extension']}" alias_file = commands_dir / f"{alias}{agent_config['extension']}"
alias_file.parent.mkdir(parents=True, exist_ok=True)
alias_file.write_text(output, encoding="utf-8") alias_file.write_text(output, encoding="utf-8")
if agent_name == "copilot": if agent_name == "copilot":
self.write_copilot_prompt(project_root, alias) self.write_copilot_prompt(project_root, alias)

View File

@@ -12,7 +12,6 @@ import os
import tempfile import tempfile
import zipfile import zipfile
import shutil import shutil
import copy
from dataclasses import dataclass from dataclasses import dataclass
from pathlib import Path from pathlib import Path
from typing import Optional, Dict, List, Any, Callable, Set from typing import Optional, Dict, List, Any, Callable, Set
@@ -229,54 +228,6 @@ class ExtensionRegistry:
} }
self._save() self._save()
def update(self, extension_id: str, metadata: dict):
"""Update extension metadata in registry, merging with existing entry.
Merges the provided metadata with the existing entry, preserving any
fields not specified in the new metadata. The installed_at timestamp
is always preserved from the original entry.
Use this method instead of add() when updating existing extension
metadata (e.g., enabling/disabling) to preserve the original
installation timestamp and other existing fields.
Args:
extension_id: Extension ID
metadata: Extension metadata fields to update (merged with existing)
Raises:
KeyError: If extension is not installed
"""
if extension_id not in self.data["extensions"]:
raise KeyError(f"Extension '{extension_id}' is not installed")
# Merge new metadata with existing, preserving original installed_at
existing = self.data["extensions"][extension_id]
# Merge: existing fields preserved, new fields override
merged = {**existing, **metadata}
# Always preserve original installed_at based on key existence, not truthiness,
# to handle cases where the field exists but may be falsy (legacy/corruption)
if "installed_at" in existing:
merged["installed_at"] = existing["installed_at"]
else:
# If not present in existing, explicitly remove from merged if caller provided it
merged.pop("installed_at", None)
self.data["extensions"][extension_id] = merged
self._save()
def restore(self, extension_id: str, metadata: dict):
"""Restore extension metadata to registry without modifying timestamps.
Use this method for rollback scenarios where you have a complete backup
of the registry entry (including installed_at) and want to restore it
exactly as it was.
Args:
extension_id: Extension ID
metadata: Complete extension metadata including installed_at
"""
self.data["extensions"][extension_id] = dict(metadata)
self._save()
def remove(self, extension_id: str): def remove(self, extension_id: str):
"""Remove extension from registry. """Remove extension from registry.
@@ -290,28 +241,21 @@ class ExtensionRegistry:
def get(self, extension_id: str) -> Optional[dict]: def get(self, extension_id: str) -> Optional[dict]:
"""Get extension metadata from registry. """Get extension metadata from registry.
Returns a deep copy to prevent callers from accidentally mutating
nested internal registry state without going through the write path.
Args: Args:
extension_id: Extension ID extension_id: Extension ID
Returns: Returns:
Deep copy of extension metadata, or None if not found Extension metadata or None if not found
""" """
entry = self.data["extensions"].get(extension_id) return self.data["extensions"].get(extension_id)
return copy.deepcopy(entry) if entry is not None else None
def list(self) -> Dict[str, dict]: def list(self) -> Dict[str, dict]:
"""Get all installed extensions. """Get all installed extensions.
Returns a deep copy of the extensions mapping to prevent callers
from accidentally mutating nested internal registry state.
Returns: Returns:
Dictionary of extension_id -> metadata (deep copies) Dictionary of extension_id -> metadata
""" """
return copy.deepcopy(self.data["extensions"]) return self.data["extensions"]
def is_installed(self, extension_id: str) -> bool: def is_installed(self, extension_id: str) -> bool:
"""Check if extension is installed. """Check if extension is installed.
@@ -640,7 +584,7 @@ class ExtensionManager:
result.append({ result.append({
"id": ext_id, "id": ext_id,
"name": manifest.name, "name": manifest.name,
"version": metadata.get("version", "unknown"), "version": metadata["version"],
"description": manifest.description, "description": manifest.description,
"enabled": metadata.get("enabled", True), "enabled": metadata.get("enabled", True),
"installed_at": metadata.get("installed_at"), "installed_at": metadata.get("installed_at"),
@@ -739,10 +683,7 @@ class CommandRegistrar:
return self._registrar.render_frontmatter(frontmatter) + "\n" + context_note + body return self._registrar.render_frontmatter(frontmatter) + "\n" + context_note + body
def _render_toml_command(self, frontmatter, body, ext_id): def _render_toml_command(self, frontmatter, body, ext_id):
# Preserve extension-specific context comments for backward compatibility return self._registrar.render_toml_command(frontmatter, body, ext_id)
base = self._registrar.render_toml_command(frontmatter, body, ext_id)
context_lines = f"# Extension: {ext_id}\n# Config: .specify/extensions/{ext_id}/\n"
return base.rstrip("\n") + "\n" + context_lines
def register_commands_for_agent( def register_commands_for_agent(
self, self,
@@ -838,13 +779,12 @@ class ExtensionCatalog:
config_path: Path to extension-catalogs.yml config_path: Path to extension-catalogs.yml
Returns: Returns:
Ordered list of CatalogEntry objects, or None if file doesn't exist. Ordered list of CatalogEntry objects, or None if file doesn't exist
or contains no valid catalog entries.
Raises: Raises:
ValidationError: If any catalog entry has an invalid URL, ValidationError: If any catalog entry has an invalid URL,
the file cannot be parsed, a priority value is invalid, the file cannot be parsed, or a priority value is invalid.
or the file exists but contains no valid catalog entries
(fail-closed for security).
""" """
if not config_path.exists(): if not config_path.exists():
return None return None
@@ -856,17 +796,12 @@ class ExtensionCatalog:
) )
catalogs_data = data.get("catalogs", []) catalogs_data = data.get("catalogs", [])
if not catalogs_data: if not catalogs_data:
# File exists but has no catalogs key or empty list - fail closed return None
raise ValidationError(
f"Catalog config {config_path} exists but contains no 'catalogs' entries. "
f"Remove the file to use built-in defaults, or add valid catalog entries."
)
if not isinstance(catalogs_data, list): if not isinstance(catalogs_data, list):
raise ValidationError( raise ValidationError(
f"Invalid catalog config: 'catalogs' must be a list, got {type(catalogs_data).__name__}" f"Invalid catalog config: 'catalogs' must be a list, got {type(catalogs_data).__name__}"
) )
entries: List[CatalogEntry] = [] entries: List[CatalogEntry] = []
skipped_entries: List[int] = []
for idx, item in enumerate(catalogs_data): for idx, item in enumerate(catalogs_data):
if not isinstance(item, dict): if not isinstance(item, dict):
raise ValidationError( raise ValidationError(
@@ -874,7 +809,6 @@ class ExtensionCatalog:
) )
url = str(item.get("url", "")).strip() url = str(item.get("url", "")).strip()
if not url: if not url:
skipped_entries.append(idx)
continue continue
self._validate_catalog_url(url) self._validate_catalog_url(url)
try: try:
@@ -897,14 +831,7 @@ class ExtensionCatalog:
description=str(item.get("description", "")), description=str(item.get("description", "")),
)) ))
entries.sort(key=lambda e: e.priority) entries.sort(key=lambda e: e.priority)
if not entries: return entries if entries else None
# All entries were invalid (missing URLs) - fail closed for security
raise ValidationError(
f"Catalog config {config_path} contains {len(catalogs_data)} entries but none have valid URLs "
f"(entries at indices {skipped_entries} were skipped). "
f"Each catalog entry must have a 'url' field."
)
return entries
def get_active_catalogs(self) -> List[CatalogEntry]: def get_active_catalogs(self) -> List[CatalogEntry]:
"""Get the ordered list of active catalogs. """Get the ordered list of active catalogs.

View File

@@ -139,15 +139,6 @@ class PresetManifest:
f"must be one of {sorted(VALID_PRESET_TEMPLATE_TYPES)}" f"must be one of {sorted(VALID_PRESET_TEMPLATE_TYPES)}"
) )
# Validate file path safety: must be relative, no parent traversal
file_path = tmpl["file"]
normalized = os.path.normpath(file_path)
if os.path.isabs(normalized) or normalized.startswith(".."):
raise PresetValidationError(
f"Invalid template file path '{file_path}': "
"must be a relative path within the preset directory"
)
# Validate template name format # Validate template name format
if tmpl["type"] == "command": if tmpl["type"] == "command":
# Commands use dot notation (e.g. speckit.specify) # Commands use dot notation (e.g. speckit.specify)
@@ -373,7 +364,7 @@ class PresetManager:
Scans the preset's templates for type "command", reads each command Scans the preset's templates for type "command", reads each command
file, and writes it to every detected agent directory using the file, and writes it to every detected agent directory using the
CommandRegistrar from the agents module. CommandRegistrar from the extensions module.
Args: Args:
manifest: Preset manifest manifest: Preset manifest
@@ -433,7 +424,7 @@ class PresetManager:
Reads ``.specify/init-options.json`` to determine whether skills Reads ``.specify/init-options.json`` to determine whether skills
are enabled and which agent was selected, then delegates to are enabled and which agent was selected, then delegates to
the module-level ``_get_skills_dir()`` helper for the concrete path. ``_get_skills_dir()`` for the concrete path.
Returns: Returns:
The skills directory ``Path``, or ``None`` if skills were not The skills directory ``Path``, or ``None`` if skills were not
@@ -482,33 +473,15 @@ class PresetManager:
if not command_templates: if not command_templates:
return [] return []
# Filter out extension command overrides if the extension isn't installed,
# matching the same logic used by _register_commands().
extensions_dir = self.project_root / ".specify" / "extensions"
filtered = []
for cmd in command_templates:
parts = cmd["name"].split(".")
if len(parts) >= 3 and parts[0] == "speckit":
ext_id = parts[1]
if not (extensions_dir / ext_id).is_dir():
continue
filtered.append(cmd)
if not filtered:
return []
skills_dir = self._get_skills_dir() skills_dir = self._get_skills_dir()
if not skills_dir: if not skills_dir:
return [] return []
from . import SKILL_DESCRIPTIONS, load_init_options from . import SKILL_DESCRIPTIONS
opts = load_init_options(self.project_root)
selected_ai = opts.get("ai", "")
written: List[str] = [] written: List[str] = []
for cmd_tmpl in filtered: for cmd_tmpl in command_templates:
cmd_name = cmd_tmpl["name"] cmd_name = cmd_tmpl["name"]
cmd_file_rel = cmd_tmpl["file"] cmd_file_rel = cmd_tmpl["file"]
source_file = preset_dir / cmd_file_rel source_file = preset_dir / cmd_file_rel
@@ -519,12 +492,7 @@ class PresetManager:
short_name = cmd_name short_name = cmd_name
if short_name.startswith("speckit."): if short_name.startswith("speckit."):
short_name = short_name[len("speckit."):] short_name = short_name[len("speckit."):]
# Kimi CLI discovers skills by directory name and invokes them as skill_name = f"speckit-{short_name}"
# /skill:<name> — use dot separator to match packaging convention.
if selected_ai == "kimi":
skill_name = f"speckit.{short_name}"
else:
skill_name = f"speckit-{short_name}"
# Only overwrite if the skill already exists (i.e. --ai-skills was used) # Only overwrite if the skill already exists (i.e. --ai-skills was used)
skill_subdir = skills_dir / skill_name skill_subdir = skills_dir / skill_name
@@ -605,8 +573,6 @@ class PresetManager:
short_name = skill_name short_name = skill_name
if short_name.startswith("speckit-"): if short_name.startswith("speckit-"):
short_name = short_name[len("speckit-"):] short_name = short_name[len("speckit-"):]
elif short_name.startswith("speckit."):
short_name = short_name[len("speckit."):]
skill_subdir = skills_dir / skill_name skill_subdir = skills_dir / skill_name
skill_file = skill_subdir / "SKILL.md" skill_file = skill_subdir / "SKILL.md"
@@ -930,10 +896,6 @@ class PresetCatalog:
raise PresetValidationError( raise PresetValidationError(
f"Failed to read catalog config {config_path}: {e}" f"Failed to read catalog config {config_path}: {e}"
) )
if not isinstance(data, dict):
raise PresetValidationError(
f"Invalid catalog config {config_path}: expected a mapping at root, got {type(data).__name__}"
)
catalogs_data = data.get("catalogs", []) catalogs_data = data.get("catalogs", [])
if not catalogs_data: if not catalogs_data:
return None return None
@@ -1364,11 +1326,11 @@ class PresetCatalog:
raise PresetError(f"Failed to save preset ZIP: {e}") raise PresetError(f"Failed to save preset ZIP: {e}")
def clear_cache(self): def clear_cache(self):
"""Clear all catalog cache files, including per-URL hashed caches.""" """Clear the catalog cache."""
if self.cache_dir.exists(): if self.cache_file.exists():
for f in self.cache_dir.iterdir(): self.cache_file.unlink()
if f.is_file() and f.name.startswith("catalog"): if self.cache_metadata_file.exists():
f.unlink(missing_ok=True) self.cache_metadata_file.unlink()
class PresetResolver: class PresetResolver:

View File

@@ -129,7 +129,7 @@ Given that feature description, do this:
c. **Handle Validation Results**: c. **Handle Validation Results**:
- **If all items pass**: Mark checklist complete and proceed to step 7 - **If all items pass**: Mark checklist complete and proceed to step 6
- **If items fail (excluding [NEEDS CLARIFICATION])**: - **If items fail (excluding [NEEDS CLARIFICATION])**:
1. List the failing items and specific issues 1. List the failing items and specific issues
@@ -178,6 +178,8 @@ Given that feature description, do this:
**NOTE:** The script creates and checks out the new branch and initializes the spec file before writing. **NOTE:** The script creates and checks out the new branch and initializes the spec file before writing.
## General Guidelines
## Quick Guidelines ## Quick Guidelines
- Focus on **WHAT** users need and **WHY**. - Focus on **WHAT** users need and **WHY**.

View File

@@ -62,14 +62,7 @@ class TestAgentConfigConsistency:
ps_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.ps1").read_text(encoding="utf-8") ps_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.ps1").read_text(encoding="utf-8")
assert re.search(r"'shai'\s*\{.*?\.shai/commands", ps_text, re.S) is not None assert re.search(r"'shai'\s*\{.*?\.shai/commands", ps_text, re.S) is not None
assert re.search(r"'agy'\s*\{.*?\.agent/commands", ps_text, re.S) is not None assert re.search(r"'agy'\s*\{.*?\.agent/workflows", ps_text, re.S) is not None
def test_release_sh_switch_has_shai_and_agy_generation(self):
"""Bash release builder must generate files for shai and agy agents."""
sh_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.sh").read_text(encoding="utf-8")
assert re.search(r"shai\)\s*\n.*?\.shai/commands", sh_text, re.S) is not None
assert re.search(r"agy\)\s*\n.*?\.agent/commands", sh_text, re.S) is not None
def test_init_ai_help_includes_roo_and_kiro_alias(self): def test_init_ai_help_includes_roo_and_kiro_alias(self):
"""CLI help text for --ai should stay in sync with agent config and alias guidance.""" """CLI help text for --ai should stay in sync with agent config and alias guidance."""
@@ -178,58 +171,3 @@ class TestAgentConfigConsistency:
def test_ai_help_includes_tabnine(self): def test_ai_help_includes_tabnine(self):
"""CLI help text for --ai should include tabnine.""" """CLI help text for --ai should include tabnine."""
assert "tabnine" in AI_ASSISTANT_HELP assert "tabnine" in AI_ASSISTANT_HELP
# --- Kimi Code CLI consistency checks ---
def test_kimi_in_agent_config(self):
"""AGENT_CONFIG should include kimi with correct folder and commands_subdir."""
assert "kimi" in AGENT_CONFIG
assert AGENT_CONFIG["kimi"]["folder"] == ".kimi/"
assert AGENT_CONFIG["kimi"]["commands_subdir"] == "skills"
assert AGENT_CONFIG["kimi"]["requires_cli"] is True
def test_kimi_in_extension_registrar(self):
"""Extension command registrar should include kimi using .kimi/skills and SKILL.md."""
cfg = CommandRegistrar.AGENT_CONFIGS
assert "kimi" in cfg
kimi_cfg = cfg["kimi"]
assert kimi_cfg["dir"] == ".kimi/skills"
assert kimi_cfg["extension"] == "/SKILL.md"
def test_kimi_in_release_agent_lists(self):
"""Bash and PowerShell release scripts should include kimi in agent lists."""
sh_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.sh").read_text(encoding="utf-8")
ps_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.ps1").read_text(encoding="utf-8")
sh_match = re.search(r"ALL_AGENTS=\(([^)]*)\)", sh_text)
assert sh_match is not None
sh_agents = sh_match.group(1).split()
ps_match = re.search(r"\$AllAgents = @\(([^)]*)\)", ps_text)
assert ps_match is not None
ps_agents = re.findall(r"'([^']+)'", ps_match.group(1))
assert "kimi" in sh_agents
assert "kimi" in ps_agents
def test_kimi_in_powershell_validate_set(self):
"""PowerShell update-agent-context script should include 'kimi' in ValidateSet."""
ps_text = (REPO_ROOT / "scripts" / "powershell" / "update-agent-context.ps1").read_text(encoding="utf-8")
validate_set_match = re.search(r"\[ValidateSet\(([^)]*)\)\]", ps_text)
assert validate_set_match is not None
validate_set_values = re.findall(r"'([^']+)'", validate_set_match.group(1))
assert "kimi" in validate_set_values
def test_kimi_in_github_release_output(self):
"""GitHub release script should include kimi template packages."""
gh_release_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-github-release.sh").read_text(encoding="utf-8")
assert "spec-kit-template-kimi-sh-" in gh_release_text
assert "spec-kit-template-kimi-ps-" in gh_release_text
def test_ai_help_includes_kimi(self):
"""CLI help text for --ai should include kimi."""
assert "kimi" in AI_ASSISTANT_HELP

View File

@@ -132,16 +132,6 @@ def commands_dir_gemini(project_dir):
return cmd_dir return cmd_dir
@pytest.fixture
def commands_dir_qwen(project_dir):
"""Create a populated .qwen/commands directory (Markdown format)."""
cmd_dir = project_dir / ".qwen" / "commands"
cmd_dir.mkdir(parents=True, exist_ok=True)
for name in ["speckit.specify.md", "speckit.plan.md", "speckit.tasks.md"]:
(cmd_dir / name).write_text(f"# {name}\nContent here\n")
return cmd_dir
# ===== _get_skills_dir Tests ===== # ===== _get_skills_dir Tests =====
class TestGetSkillsDir: class TestGetSkillsDir:
@@ -400,28 +390,6 @@ class TestInstallAiSkills:
# .toml commands should be untouched # .toml commands should be untouched
assert (cmds_dir / "speckit.specify.toml").exists() assert (cmds_dir / "speckit.specify.toml").exists()
def test_qwen_md_commands_dir_installs_skills(self, project_dir):
"""Qwen now uses Markdown format; skills should install directly from .qwen/commands/."""
cmds_dir = project_dir / ".qwen" / "commands"
cmds_dir.mkdir(parents=True)
(cmds_dir / "speckit.specify.md").write_text(
"---\ndescription: Create or update the feature specification.\n---\n\n# Specify\n\nBody.\n"
)
(cmds_dir / "speckit.plan.md").write_text(
"---\ndescription: Generate implementation plan.\n---\n\n# Plan\n\nBody.\n"
)
result = install_ai_skills(project_dir, "qwen")
assert result is True
skills_dir = project_dir / ".qwen" / "skills"
assert skills_dir.exists()
skill_dirs = [d.name for d in skills_dir.iterdir() if d.is_dir()]
assert len(skill_dirs) >= 1
# .md commands should be untouched
assert (cmds_dir / "speckit.specify.md").exists()
assert (cmds_dir / "speckit.plan.md").exists()
@pytest.mark.parametrize("agent_key", [k for k in AGENT_CONFIG.keys() if k != "generic"]) @pytest.mark.parametrize("agent_key", [k for k in AGENT_CONFIG.keys() if k != "generic"])
def test_skills_install_for_all_agents(self, temp_dir, agent_key): def test_skills_install_for_all_agents(self, temp_dir, agent_key):
"""install_ai_skills should produce skills for every configured agent.""" """install_ai_skills should produce skills for every configured agent."""
@@ -442,11 +410,8 @@ class TestInstallAiSkills:
skills_dir = _get_skills_dir(proj, agent_key) skills_dir = _get_skills_dir(proj, agent_key)
assert skills_dir.exists() assert skills_dir.exists()
skill_dirs = [d.name for d in skills_dir.iterdir() if d.is_dir()] skill_dirs = [d.name for d in skills_dir.iterdir() if d.is_dir()]
# Kimi uses dot-separator (speckit.specify) to match /skill:speckit.* invocation; assert "speckit-specify" in skill_dirs
# all other agents use hyphen-separator (speckit-specify). assert (skills_dir / "speckit-specify" / "SKILL.md").exists()
expected_skill_name = "speckit.specify" if agent_key == "kimi" else "speckit-specify"
assert expected_skill_name in skill_dirs
assert (skills_dir / expected_skill_name / "SKILL.md").exists()
@@ -478,15 +443,6 @@ class TestCommandCoexistence:
remaining = list(commands_dir_gemini.glob("speckit.*")) remaining = list(commands_dir_gemini.glob("speckit.*"))
assert len(remaining) == 3 assert len(remaining) == 3
def test_existing_commands_preserved_qwen(self, project_dir, templates_dir, commands_dir_qwen):
"""install_ai_skills must NOT remove pre-existing .qwen/commands files."""
assert len(list(commands_dir_qwen.glob("speckit.*"))) == 3
install_ai_skills(project_dir, "qwen")
remaining = list(commands_dir_qwen.glob("speckit.*"))
assert len(remaining) == 3
def test_commands_dir_not_removed(self, project_dir, templates_dir, commands_dir_claude): def test_commands_dir_not_removed(self, project_dir, templates_dir, commands_dir_claude):
"""install_ai_skills must not remove the commands directory.""" """install_ai_skills must not remove the commands directory."""
install_ai_skills(project_dir, "claude") install_ai_skills(project_dir, "claude")
@@ -702,59 +658,6 @@ class TestCliValidation:
assert "Usage:" in result.output assert "Usage:" in result.output
assert "--ai" in result.output assert "--ai" in result.output
def test_agy_without_ai_skills_fails(self):
"""--ai agy without --ai-skills should fail with exit code 1."""
from typer.testing import CliRunner
runner = CliRunner()
result = runner.invoke(app, ["init", "test-proj", "--ai", "agy"])
assert result.exit_code == 1
assert "Explicit command support was deprecated in Antigravity version 1.20.5." in result.output
assert "--ai-skills" in result.output
def test_interactive_agy_without_ai_skills_prompts_skills(self, monkeypatch):
"""Interactive selector returning agy without --ai-skills should automatically enable --ai-skills."""
from typer.testing import CliRunner
# Mock select_with_arrows to simulate the user picking 'agy' for AI,
# and return a deterministic default for any other prompts to avoid
# calling the real interactive implementation.
def _fake_select_with_arrows(*args, **kwargs):
options = kwargs.get("options")
if options is None and len(args) >= 1:
options = args[0]
# If the options include 'agy', simulate selecting it.
if isinstance(options, dict) and "agy" in options:
return "agy"
if isinstance(options, (list, tuple)) and "agy" in options:
return "agy"
# For any other prompt, return a deterministic, non-interactive default:
# pick the first option if available.
if isinstance(options, dict) and options:
return next(iter(options.keys()))
if isinstance(options, (list, tuple)) and options:
return options[0]
# If no options are provided, fall back to None (should not occur in normal use).
return None
monkeypatch.setattr("specify_cli.select_with_arrows", _fake_select_with_arrows)
# Mock download_and_extract_template to prevent real HTTP downloads during testing
monkeypatch.setattr("specify_cli.download_and_extract_template", lambda *args, **kwargs: None)
# We need to bypass the `git init` step, wait, it has `--no-git` by default in tests maybe?
runner = CliRunner()
# Create temp dir to avoid directory already exists errors or whatever
with runner.isolated_filesystem():
result = runner.invoke(app, ["init", "test-proj", "--no-git"])
# Interactive selection should NOT raise the deprecation error!
assert result.exit_code == 0
assert "Explicit command support was deprecated" not in result.output
def test_ai_skills_flag_appears_in_help(self): def test_ai_skills_flag_appears_in_help(self):
"""--ai-skills should appear in init --help output.""" """--ai-skills should appear in init --help output."""
from typer.testing import CliRunner from typer.testing import CliRunner

View File

@@ -277,135 +277,6 @@ class TestExtensionRegistry:
assert registry2.is_installed("test-ext") assert registry2.is_installed("test-ext")
assert registry2.get("test-ext")["version"] == "1.0.0" assert registry2.get("test-ext")["version"] == "1.0.0"
def test_update_preserves_installed_at(self, temp_dir):
"""Test that update() preserves the original installed_at timestamp."""
extensions_dir = temp_dir / "extensions"
extensions_dir.mkdir()
registry = ExtensionRegistry(extensions_dir)
registry.add("test-ext", {"version": "1.0.0", "enabled": True})
# Get original installed_at
original_data = registry.get("test-ext")
original_installed_at = original_data["installed_at"]
# Update with new metadata
registry.update("test-ext", {"version": "2.0.0", "enabled": False})
# Verify installed_at is preserved
updated_data = registry.get("test-ext")
assert updated_data["installed_at"] == original_installed_at
assert updated_data["version"] == "2.0.0"
assert updated_data["enabled"] is False
def test_update_merges_with_existing(self, temp_dir):
"""Test that update() merges new metadata with existing fields."""
extensions_dir = temp_dir / "extensions"
extensions_dir.mkdir()
registry = ExtensionRegistry(extensions_dir)
registry.add("test-ext", {
"version": "1.0.0",
"enabled": True,
"registered_commands": {"claude": ["cmd1", "cmd2"]},
})
# Update with partial metadata (only enabled field)
registry.update("test-ext", {"enabled": False})
# Verify existing fields are preserved
updated_data = registry.get("test-ext")
assert updated_data["enabled"] is False
assert updated_data["version"] == "1.0.0" # Preserved
assert updated_data["registered_commands"] == {"claude": ["cmd1", "cmd2"]} # Preserved
def test_update_raises_for_missing_extension(self, temp_dir):
"""Test that update() raises KeyError for non-installed extension."""
extensions_dir = temp_dir / "extensions"
extensions_dir.mkdir()
registry = ExtensionRegistry(extensions_dir)
with pytest.raises(KeyError, match="not installed"):
registry.update("nonexistent-ext", {"enabled": False})
def test_restore_overwrites_completely(self, temp_dir):
"""Test that restore() overwrites the registry entry completely."""
extensions_dir = temp_dir / "extensions"
extensions_dir.mkdir()
registry = ExtensionRegistry(extensions_dir)
registry.add("test-ext", {"version": "2.0.0", "enabled": True})
# Restore with complete backup data
backup_data = {
"version": "1.0.0",
"enabled": False,
"installed_at": "2024-01-01T00:00:00+00:00",
"registered_commands": {"claude": ["old-cmd"]},
}
registry.restore("test-ext", backup_data)
# Verify entry is exactly as restored
restored_data = registry.get("test-ext")
assert restored_data == backup_data
def test_restore_can_recreate_removed_entry(self, temp_dir):
"""Test that restore() can recreate an entry after remove()."""
extensions_dir = temp_dir / "extensions"
extensions_dir.mkdir()
registry = ExtensionRegistry(extensions_dir)
registry.add("test-ext", {"version": "1.0.0"})
# Save backup and remove
backup = registry.get("test-ext").copy()
registry.remove("test-ext")
assert not registry.is_installed("test-ext")
# Restore should recreate the entry
registry.restore("test-ext", backup)
assert registry.is_installed("test-ext")
assert registry.get("test-ext")["version"] == "1.0.0"
def test_get_returns_deep_copy(self, temp_dir):
"""Test that get() returns deep copies for nested structures."""
extensions_dir = temp_dir / "extensions"
extensions_dir.mkdir()
registry = ExtensionRegistry(extensions_dir)
metadata = {
"version": "1.0.0",
"registered_commands": {"claude": ["cmd1"]},
}
registry.add("test-ext", metadata)
fetched = registry.get("test-ext")
fetched["registered_commands"]["claude"].append("cmd2")
# Internal registry must remain unchanged.
internal = registry.data["extensions"]["test-ext"]
assert internal["registered_commands"] == {"claude": ["cmd1"]}
def test_list_returns_deep_copy(self, temp_dir):
"""Test that list() returns deep copies for nested structures."""
extensions_dir = temp_dir / "extensions"
extensions_dir.mkdir()
registry = ExtensionRegistry(extensions_dir)
metadata = {
"version": "1.0.0",
"registered_commands": {"claude": ["cmd1"]},
}
registry.add("test-ext", metadata)
listed = registry.list()
listed["test-ext"]["registered_commands"]["claude"].append("cmd2")
# Internal registry must remain unchanged.
internal = registry.data["extensions"]["test-ext"]
assert internal["registered_commands"] == {"claude": ["cmd1"]}
# ===== ExtensionManager Tests ===== # ===== ExtensionManager Tests =====
@@ -541,15 +412,6 @@ class TestCommandRegistrar:
assert "codex" in CommandRegistrar.AGENT_CONFIGS assert "codex" in CommandRegistrar.AGENT_CONFIGS
assert CommandRegistrar.AGENT_CONFIGS["codex"]["dir"] == ".codex/prompts" assert CommandRegistrar.AGENT_CONFIGS["codex"]["dir"] == ".codex/prompts"
def test_qwen_agent_config_is_markdown(self):
"""Qwen should use Markdown format with $ARGUMENTS (not TOML)."""
assert "qwen" in CommandRegistrar.AGENT_CONFIGS
cfg = CommandRegistrar.AGENT_CONFIGS["qwen"]
assert cfg["dir"] == ".qwen/commands"
assert cfg["format"] == "markdown"
assert cfg["args"] == "$ARGUMENTS"
assert cfg["extension"] == ".md"
def test_parse_frontmatter_valid(self): def test_parse_frontmatter_valid(self):
"""Test parsing valid YAML frontmatter.""" """Test parsing valid YAML frontmatter."""
content = """--- content = """---
@@ -1540,8 +1402,8 @@ class TestCatalogStack:
with pytest.raises(ValidationError, match="HTTPS"): with pytest.raises(ValidationError, match="HTTPS"):
catalog.get_active_catalogs() catalog.get_active_catalogs()
def test_empty_project_config_raises_error(self, temp_dir): def test_empty_project_config_falls_back_to_defaults(self, temp_dir):
"""Empty catalogs list in config raises ValidationError (fail-closed for security).""" """Empty catalogs list in config falls back to default stack."""
import yaml as yaml_module import yaml as yaml_module
project_dir = self._make_project(temp_dir) project_dir = self._make_project(temp_dir)
@@ -1550,32 +1412,11 @@ class TestCatalogStack:
yaml_module.dump({"catalogs": []}, f) yaml_module.dump({"catalogs": []}, f)
catalog = ExtensionCatalog(project_dir) catalog = ExtensionCatalog(project_dir)
entries = catalog.get_active_catalogs()
# Fail-closed: empty config should raise, not fall back to defaults # Falls back to default stack
with pytest.raises(ValidationError) as exc_info: assert len(entries) == 2
catalog.get_active_catalogs() assert entries[0].url == ExtensionCatalog.DEFAULT_CATALOG_URL
assert "contains no 'catalogs' entries" in str(exc_info.value)
def test_catalog_entries_without_urls_raises_error(self, temp_dir):
"""Catalog entries without URLs raise ValidationError (fail-closed for security)."""
import yaml as yaml_module
project_dir = self._make_project(temp_dir)
config_path = project_dir / ".specify" / "extension-catalogs.yml"
with open(config_path, "w") as f:
yaml_module.dump({
"catalogs": [
{"name": "no-url-catalog", "priority": 1},
{"name": "another-no-url", "description": "Also missing URL"},
]
}, f)
catalog = ExtensionCatalog(project_dir)
# Fail-closed: entries without URLs should raise, not fall back to defaults
with pytest.raises(ValidationError) as exc_info:
catalog.get_active_catalogs()
assert "none have valid URLs" in str(exc_info.value)
# --- _load_catalog_config --- # --- _load_catalog_config ---
@@ -2102,238 +1943,3 @@ class TestExtensionIgnore:
assert not (dest / "docs" / "guide.md").exists() assert not (dest / "docs" / "guide.md").exists()
assert not (dest / "docs" / "internal.md").exists() assert not (dest / "docs" / "internal.md").exists()
assert (dest / "docs" / "api.md").exists() assert (dest / "docs" / "api.md").exists()
class TestExtensionAddCLI:
"""CLI integration tests for extension add command."""
def test_add_by_display_name_uses_resolved_id_for_download(self, tmp_path):
"""extension add by display name should use resolved ID for download_extension()."""
from typer.testing import CliRunner
from unittest.mock import patch, MagicMock
from specify_cli import app
runner = CliRunner()
# Create project structure
project_dir = tmp_path / "test-project"
project_dir.mkdir()
(project_dir / ".specify").mkdir()
(project_dir / ".specify" / "extensions").mkdir(parents=True)
# Mock catalog that returns extension by display name
mock_catalog = MagicMock()
mock_catalog.get_extension_info.return_value = None # ID lookup fails
mock_catalog.search.return_value = [
{
"id": "acme-jira-integration",
"name": "Jira Integration",
"version": "1.0.0",
"description": "Jira integration extension",
"_install_allowed": True,
}
]
# Track what ID was passed to download_extension
download_called_with = []
def mock_download(extension_id):
download_called_with.append(extension_id)
# Return a path that will fail install (we just want to verify the ID)
raise ExtensionError("Mock download - checking ID was resolved")
mock_catalog.download_extension.side_effect = mock_download
with patch("specify_cli.extensions.ExtensionCatalog", return_value=mock_catalog), \
patch.object(Path, "cwd", return_value=project_dir):
result = runner.invoke(
app,
["extension", "add", "Jira Integration"],
catch_exceptions=True,
)
assert result.exit_code != 0, (
f"Expected non-zero exit code since mock download raises, got {result.exit_code}"
)
# Verify download_extension was called with the resolved ID, not the display name
assert len(download_called_with) == 1
assert download_called_with[0] == "acme-jira-integration", (
f"Expected download_extension to be called with resolved ID 'acme-jira-integration', "
f"but was called with '{download_called_with[0]}'"
)
class TestExtensionUpdateCLI:
"""CLI integration tests for extension update command."""
@staticmethod
def _create_extension_source(base_dir: Path, version: str, include_config: bool = False) -> Path:
"""Create a minimal extension source directory for install tests."""
import yaml
ext_dir = base_dir / f"test-ext-{version}"
ext_dir.mkdir(parents=True, exist_ok=True)
manifest = {
"schema_version": "1.0",
"extension": {
"id": "test-ext",
"name": "Test Extension",
"version": version,
"description": "A test extension",
},
"requires": {"speckit_version": ">=0.1.0"},
"provides": {
"commands": [
{
"name": "speckit.test.hello",
"file": "commands/hello.md",
"description": "Test command",
}
]
},
"hooks": {
"after_tasks": {
"command": "speckit.test.hello",
"optional": True,
}
},
}
(ext_dir / "extension.yml").write_text(yaml.dump(manifest, sort_keys=False))
commands_dir = ext_dir / "commands"
commands_dir.mkdir(exist_ok=True)
(commands_dir / "hello.md").write_text("---\ndescription: Test\n---\n\n$ARGUMENTS\n")
if include_config:
(ext_dir / "linear-config.yml").write_text("custom: true\nvalue: original\n")
return ext_dir
@staticmethod
def _create_catalog_zip(zip_path: Path, version: str):
"""Create a minimal ZIP that passes extension_update ID validation."""
import zipfile
import yaml
manifest = {
"schema_version": "1.0",
"extension": {
"id": "test-ext",
"name": "Test Extension",
"version": version,
"description": "A test extension",
},
"requires": {"speckit_version": ">=0.1.0"},
"provides": {"commands": [{"name": "speckit.test.hello", "file": "commands/hello.md"}]},
}
with zipfile.ZipFile(zip_path, "w") as zf:
zf.writestr("extension.yml", yaml.dump(manifest, sort_keys=False))
def test_update_success_preserves_installed_at(self, tmp_path):
"""Successful update should keep original installed_at and apply new version."""
from typer.testing import CliRunner
from unittest.mock import patch
from specify_cli import app
runner = CliRunner()
project_dir = tmp_path / "project"
project_dir.mkdir()
(project_dir / ".specify").mkdir()
(project_dir / ".claude" / "commands").mkdir(parents=True)
manager = ExtensionManager(project_dir)
v1_dir = self._create_extension_source(tmp_path, "1.0.0", include_config=True)
manager.install_from_directory(v1_dir, "0.1.0")
original_installed_at = manager.registry.get("test-ext")["installed_at"]
original_config_content = (
project_dir / ".specify" / "extensions" / "test-ext" / "linear-config.yml"
).read_text()
zip_path = tmp_path / "test-ext-update.zip"
self._create_catalog_zip(zip_path, "2.0.0")
v2_dir = self._create_extension_source(tmp_path, "2.0.0")
def fake_install_from_zip(self_obj, _zip_path, speckit_version):
return self_obj.install_from_directory(v2_dir, speckit_version)
with patch.object(Path, "cwd", return_value=project_dir), \
patch.object(ExtensionCatalog, "get_extension_info", return_value={
"id": "test-ext",
"name": "Test Extension",
"version": "2.0.0",
"_install_allowed": True,
}), \
patch.object(ExtensionCatalog, "download_extension", return_value=zip_path), \
patch.object(ExtensionManager, "install_from_zip", fake_install_from_zip):
result = runner.invoke(app, ["extension", "update", "test-ext"], input="y\n", catch_exceptions=True)
assert result.exit_code == 0, result.output
updated = ExtensionManager(project_dir).registry.get("test-ext")
assert updated["version"] == "2.0.0"
assert updated["installed_at"] == original_installed_at
restored_config_content = (
project_dir / ".specify" / "extensions" / "test-ext" / "linear-config.yml"
).read_text()
assert restored_config_content == original_config_content
def test_update_failure_rolls_back_registry_hooks_and_commands(self, tmp_path):
"""Failed update should restore original registry, hooks, and command files."""
from typer.testing import CliRunner
from unittest.mock import patch
from specify_cli import app
import yaml
runner = CliRunner()
project_dir = tmp_path / "project"
project_dir.mkdir()
(project_dir / ".specify").mkdir()
(project_dir / ".claude" / "commands").mkdir(parents=True)
manager = ExtensionManager(project_dir)
v1_dir = self._create_extension_source(tmp_path, "1.0.0")
manager.install_from_directory(v1_dir, "0.1.0")
backup_registry_entry = manager.registry.get("test-ext")
hooks_before = yaml.safe_load((project_dir / ".specify" / "extensions.yml").read_text())
registered_commands = backup_registry_entry.get("registered_commands", {})
command_files = []
registrar = CommandRegistrar()
for agent_name, cmd_names in registered_commands.items():
if agent_name not in registrar.AGENT_CONFIGS:
continue
agent_cfg = registrar.AGENT_CONFIGS[agent_name]
commands_dir = project_dir / agent_cfg["dir"]
for cmd_name in cmd_names:
cmd_path = commands_dir / f"{cmd_name}{agent_cfg['extension']}"
command_files.append(cmd_path)
assert command_files, "Expected at least one registered command file"
for cmd_file in command_files:
assert cmd_file.exists(), f"Expected command file to exist before update: {cmd_file}"
zip_path = tmp_path / "test-ext-update.zip"
self._create_catalog_zip(zip_path, "2.0.0")
with patch.object(Path, "cwd", return_value=project_dir), \
patch.object(ExtensionCatalog, "get_extension_info", return_value={
"id": "test-ext",
"name": "Test Extension",
"version": "2.0.0",
"_install_allowed": True,
}), \
patch.object(ExtensionCatalog, "download_extension", return_value=zip_path), \
patch.object(ExtensionManager, "install_from_zip", side_effect=RuntimeError("install failed")):
result = runner.invoke(app, ["extension", "update", "test-ext"], input="y\n", catch_exceptions=True)
assert result.exit_code == 1, result.output
restored_entry = ExtensionManager(project_dir).registry.get("test-ext")
assert restored_entry == backup_registry_entry
hooks_after = yaml.safe_load((project_dir / ".specify" / "extensions.yml").read_text())
assert hooks_after == hooks_before
for cmd_file in command_files:
assert cmd_file.exists(), f"Expected command file to be restored after rollback: {cmd_file}"