bluera-knowledge 0.14.0 → 0.14.2

package/.claude/settings.local.json.example

@@ -1,45 +0,0 @@
-{
-  "permissions": {
-    "allow": [
-      "Bash(osascript:*)",
-      "Bash(bun run lint:*)",
-      "Bash(bun run typecheck:*)",
-      "Bash(npm run lint:*)",
-      "Bash(npm run typecheck:*)",
-      "Bash(bun run precommit:*)"
-    ],
-    "deny": [
-      "Bash(*validate-npm-release*)",
-      "Bash(bun run validate:*)",
-      "Bash(npm run validate:*)"
-    ]
-  },
-  "hooks": {
-    "PostToolUse": [
-      {
-        "matcher": "Write|Edit",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "\"$CLAUDE_PROJECT_DIR/.claude/hooks/post-edit-check.sh\"",
-            "statusMessage": "Validating changes..."
-          }
-        ]
-      }
-    ],
-    "Notification": [
-      {
-        "matcher": "permission_prompt|idle_prompt|elicitation_dialog",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "osascript -e 'display notification \"Claude needs your input\" with title \"Claude Code\" sound name \"Glass\"' 2>/dev/null || true"
-          }
-        ]
-      }
-    ]
-  },
-  "enabledPlugins": {
-    "bluera-knowledge@bluera": true
-  }
-}

package/.claude/skills/atomic-commits/SKILL.md

@@ -1,61 +0,0 @@
----
-name: atomic-commits
-description: Create atomic commits grouped by logical features with README.md and CLAUDE.md awareness.
-version: 1.0.0
----
-
-# Atomic Commits with Documentation Awareness
-
-Guidelines for creating well-organized commits with README.md and CLAUDE.md awareness.
-
-## Documentation Check
-
-Before committing, evaluate if changes need documentation updates.
-
-### README.md (User-facing documentation)
-
-| Change Type | README Section to Update |
-|-------------|-------------------------|
-| MCP tools added/removed/renamed | MCP Tools table, MCP Integration section |
-| New commands or skills | Commands/Skills documentation |
-| CLI interface changes | Usage examples |
-| Configuration changes | Configuration/Environment sections |
-| Breaking API changes | Upgrade/migration notes |
-| New features | Feature documentation |
-| Installation changes | Installation section |
-
-**Trigger files → check README.md:**
-- `src/mcp/server.ts` - MCP tool surface
-- `.claude-plugin/plugin.json` - Plugin metadata
-- `commands/*.md` - Command documentation
-
-### CLAUDE.md (Claude Code memory - hierarchical)
-
-CLAUDE.md stores context that helps future sessions "do the right thing". Update when:
-- You struggled with something and the insight would prevent future mistakes
-- Important patterns or conventions that aren't obvious from code alone
-- Workflows or commands that are non-trivial to discover
-
-CLAUDE.md is hierarchical - use the directory level matching the changed files. Use `@path/to/file` includes to stay DRY.
-
-| Change Scope | Which CLAUDE.md |
-|--------------|-----------------|
-| Project-wide (scripts, CI/CD, build) | Root CLAUDE.md |
-| Directory-specific patterns | Subdirectory CLAUDE.md (create if needed) |
-
-## Grouping Rules
-
-Identify logical features by grouping related files:
-- Same feature = same commit
-- Infrastructure/config = separate commit
-- Tests = with their implementation OR separate if test-only
-
-## Commit Message Format
-
-```
-<type>(<scope>): <description>
-```
-
-Types: `feat`, `fix`, `docs`, `chore`, `refactor`, `test`, `style`, `build`, `ci`, `perf`
-
-**Note:** Commit messages are validated by commitlint (conventional commits format).

package/.claude/skills/code-review-repo/skill.md

@@ -1,62 +0,0 @@
----
-name: code-review-repo
-description: Review local codebase for bugs and CLAUDE.md compliance using multi-agent analysis
-version: 1.0.0
----
-
-# Local Code Review
-
-Review the entire local codebase for bugs, issues, and CLAUDE.md compliance.
-
-## Process
-
-1. **Gather CLAUDE.md files**: Use a Haiku agent to find all CLAUDE.md files in the repository (root and subdirectories)
-
-2. **Identify source files**: Determine which files to review:
-   - Include: `.ts`, `.tsx`, `.js`, `.jsx`, `.py`, `.rs`, `.go` and similar source files
-   - Exclude: `node_modules/`, `dist/`, `.git/`, vendor directories, generated files
-
-3. **Multi-agent review**: Launch 5 parallel Sonnet agents to independently review the codebase. Each agent returns a list of issues with reasons:
-   - **Agent #1**: Audit for CLAUDE.md compliance. Check that code follows guidelines in all relevant CLAUDE.md files.
-   - **Agent #2**: Shallow bug scan. Look for obvious bugs, error handling issues, and logic errors. Focus on significant bugs, not nitpicks.
-   - **Agent #3**: Git history context. Use git blame and history to identify patterns, recent changes, and potential issues in light of historical context.
-   - **Agent #4**: Previous PR comments. Check closed PRs that touched these files for any feedback that might apply.
-   - **Agent #5**: Code comment compliance. Ensure code follows any guidance in TODO, FIXME, NOTE, or other code comments.
-
-4. **Confidence scoring**: For each issue found, launch a parallel Haiku agent to score confidence (0-100):
-   - **0**: False positive, doesn't hold up to scrutiny
-   - **25**: Might be real, but unverified. Stylistic issues not in CLAUDE.md
-   - **50**: Real but minor, rarely hit in practice
-   - **75**: Verified real issue, important, directly impacts functionality or mentioned in CLAUDE.md
-   - **100**: Definitely real, frequently hit, evidence confirms
-
-5. **Filter**: Only report issues with score >= 80
-
-## False Positive Examples
-
-Avoid flagging:
-- Issues that linters/typecheckers catch (imports, types, formatting)
-- General quality issues unless in CLAUDE.md
-- Code with lint-ignore comments for that specific issue
-- Pre-existing issues unrelated to recent changes
-- Pedantic nitpicks a senior engineer wouldn't mention
-
-## Output Format
-
-### Code review
-
-Found N issues:
-
-1. Brief description (CLAUDE.md says "...")
-   `file/path.ts:42`
-
-2. Brief description (bug due to missing error handling)
-   `file/path.ts:88-95`
-
----
-
-Or if no issues:
-
-### Code review
-
-No issues found. Checked for bugs and CLAUDE.md compliance.

package/.editorconfig

@@ -1,15 +0,0 @@
-root = true
-
-[*]
-charset = utf-8
-end_of_line = lf
-insert_final_newline = true
-trim_trailing_whitespace = true
-indent_style = space
-indent_size = 2
-
-[*.md]
-trim_trailing_whitespace = false
-
-[*.ts]
-indent_size = 2

package/.env.example

@@ -1,21 +0,0 @@
-# Required Configuration
-# Copy this file to .env and set all values
-
-# Logging Configuration
-# Valid values: trace, debug, info, warn, error, fatal
-LOG_LEVEL=info
-
-# Search Quality Configuration
-# Test file boost multiplier (lower values penalize test files more)
-SEARCH_TEST_FILE_BOOST=0.5
-
-# Confidence thresholds for raw vector similarity scoring
-# Results with maxRawScore >= high threshold are "high" confidence
-# Results with maxRawScore >= medium threshold are "medium" confidence
-# Results below medium threshold are "low" confidence
-SEARCH_CONFIDENCE_HIGH=0.5
-SEARCH_CONFIDENCE_MEDIUM=0.3
-
-# MCP Server Configuration
-# Project root directory for MCP server
-PROJECT_ROOT=/path/to/project

package/.github/workflows/auto-release.yml

@@ -1,64 +0,0 @@
-name: Auto Release
-
-on:
-  push:
-    branches: [main]
-  workflow_dispatch:
-
-# Prevent parallel tag creation - queue instead of cancel
-concurrency:
-  group: auto-release
-  cancel-in-progress: false
-
-jobs:
-  auto-release:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write  # Required to push tags
-    # Only run after CI completes successfully
-    needs: []
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          token: ${{ secrets.MARKETPLACE_PAT }}  # Use PAT to trigger Release workflow
-
-      - name: Get version from package.json
-        id: package_version
-        run: |
-          VERSION=$(node -p "require('./package.json').version")
-          echo "version=$VERSION" >> $GITHUB_OUTPUT
-          echo "tag=v$VERSION" >> $GITHUB_OUTPUT
-
-      - name: Check if tag exists
-        id: check_tag
-        run: |
-          if git rev-parse "v${{ steps.package_version.outputs.version }}" >/dev/null 2>&1; then
-            echo "exists=true" >> $GITHUB_OUTPUT
-          else
-            echo "exists=false" >> $GITHUB_OUTPUT
-          fi
-
-      # CRITICAL: This is the quality gate for releases.
-      # CI workflow does NOT run on tags (to avoid redundant ~3 min test runs).
-      # This step ensures all CI checks pass on main BEFORE creating a tag.
-      # The Release workflow trusts this guarantee and publishes immediately.
-      # See ci.yml header comment for the full quality guarantee chain.
-      - name: Wait for CI to complete
-        if: steps.check_tag.outputs.exists == 'false'
-        uses: lewagon/wait-on-check-action@v1.3.4
-        with:
-          ref: ${{ github.sha }}
-          check-regexp: '^(lint-and-typecheck|test|build)$'
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-          wait-interval: 10
-          allowed-conclusions: success
-
-      - name: Create and push tag
-        if: steps.check_tag.outputs.exists == 'false'
-        run: |
-          git config user.name "github-actions[bot]"
-          git config user.email "github-actions[bot]@users.noreply.github.com"
-          git tag ${{ steps.package_version.outputs.tag }}
-          git push origin ${{ steps.package_version.outputs.tag }}

package/.github/workflows/ci.yml

@@ -1,168 +0,0 @@
-name: CI
-
-# CI runs on branch pushes and PRs, but NOT on tags.
-#
-# Why no tag trigger?
-# - Auto Release workflow (auto-release.yml) waits for CI to pass on main
-#   before creating a tag (uses wait-on-check-action with lint-and-typecheck,
-#   test, build checks)
-# - The tag contains the exact same code that just passed CI on main
-# - Running CI again on the tag is redundant and wastes ~3 minutes per release
-# - Release workflow (release.yml) trusts this guarantee and publishes immediately
-#
-# Quality guarantee chain:
-#   push to main → CI passes → Auto Release creates tag → Release publishes
-#
-on:
-  push:
-    branches: ['**']
-    # Note: tags intentionally excluded - see comment above
-  pull_request:
-    branches: [main]
-
-# Prevent duplicate runs: cancel in-progress runs for same branch
-# When a PR is open, only run the pull_request event (skip the push)
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  # Fast checks that don't need Python/models (runs in ~30s)
-  lint-and-typecheck:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Setup Bun
-        uses: oven-sh/setup-bun@v2
-        with:
-          bun-version: latest
-
-      - name: Cache Bun dependencies
-        uses: actions/cache@v4
-        with:
-          path: ~/.bun/install/cache
-          key: bun-${{ runner.os }}-${{ hashFiles('**/bun.lock') }}
-          restore-keys: |
-            bun-${{ runner.os }}-
-
-      - name: Install dependencies
-        run: bun install
-
-      - name: Lint
-        run: bun run lint
-
-      - name: Type check
-        run: bun run typecheck
-
-  # Tests with Python dependencies (slower, runs in parallel)
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Setup Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-
-      - name: Cache pip dependencies
-        uses: actions/cache@v4
-        with:
-          path: ~/.cache/pip
-          key: pip-${{ runner.os }}-crawl4ai
-          restore-keys: |
-            pip-${{ runner.os }}-
-
-      - name: Cache Playwright browsers
-        uses: actions/cache@v4
-        with:
-          path: ~/.cache/ms-playwright
-          key: playwright-${{ runner.os }}-chromium
-          restore-keys: |
-            playwright-${{ runner.os }}-
-
-      - name: Install crawl4ai
-        run: |
-          pip install crawl4ai
-          # Only run setup if Playwright not cached (checks for chromium)
-          if [ ! -d ~/.cache/ms-playwright/chromium-* ]; then
-            crawl4ai-setup
-          else
-            echo "Playwright browsers already cached, skipping setup"
-          fi
-
-      - name: Setup Bun
-        uses: oven-sh/setup-bun@v2
-        with:
-          bun-version: latest
-
-      - name: Cache Bun dependencies
-        uses: actions/cache@v4
-        with:
-          path: ~/.bun/install/cache
-          key: bun-${{ runner.os }}-${{ hashFiles('**/bun.lock') }}
-          restore-keys: |
-            bun-${{ runner.os }}-
-
-      - name: Cache Hugging Face models
-        uses: actions/cache@v4
-        with:
-          path: ~/.cache/huggingface-transformers
-          key: huggingface-transformers-${{ runner.os }}-all-MiniLM-L6-v2
-          restore-keys: |
-            huggingface-transformers-${{ runner.os }}-
-
-      - name: Install dependencies
-        run: bun install
-
-      - name: Warm up embedding model
-        run: |
-          # Download embedding model before tests to prevent race conditions
-          # Multiple test files use embeddings - this ensures model is fully cached
-          node -e "
-            import('@huggingface/transformers').then(async ({ pipeline, env }) => {
-              const { homedir } = await import('node:os');
-              const { join } = await import('node:path');
-              env.cacheDir = join(homedir(), '.cache', 'huggingface-transformers');
-              console.log('Downloading embedding model to:', env.cacheDir);
-              await pipeline('feature-extraction', 'Xenova/all-MiniLM-L6-v2', { dtype: 'fp32' });
-              console.log('Model downloaded successfully');
-            });
-          "
-
-      - name: Run tests with coverage
-        run: bun run test:coverage
-
-  # Build (lightweight, runs in parallel)
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Setup Bun
-        uses: oven-sh/setup-bun@v2
-        with:
-          bun-version: latest
-
-      - name: Cache Bun dependencies
-        uses: actions/cache@v4
-        with:
-          path: ~/.bun/install/cache
-          key: bun-${{ runner.os }}-${{ hashFiles('**/bun.lock') }}
-          restore-keys: |
-            bun-${{ runner.os }}-
-
-      - name: Install dependencies
-        run: bun install
-
-      - name: Build
-        run: bun run build
-
-  # Success job - only runs if all parallel jobs pass
-  ci-success:
-    runs-on: ubuntu-latest
-    needs: [lint-and-typecheck, test, build]
-    steps:
-      - name: CI passed
-        run: echo "All CI checks passed!"

package/.github/workflows/release.yml

@@ -1,74 +0,0 @@
-name: Release
-
-# Publishes to npm when a tag is pushed.
-#
-# Quality assumption: Tags are only created by Auto Release workflow AFTER
-# CI passes on main. This workflow trusts that guarantee and does not re-run
-# tests. See ci.yml and auto-release.yml for the full quality chain.
-#
-on:
-  push:
-    tags:
-      - 'v*'
-  workflow_dispatch:
-
-# Prevent parallel releases - queue instead of cancel
-concurrency:
-  group: release
-  cancel-in-progress: false
-
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      id-token: write  # Required for npm trusted publishing (OIDC)
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Generate release notes
-        id: notes
-        run: |
-          # Get commits since last tag
-          PREV_TAG=$(git describe --tags --abbrev=0 HEAD^ 2>/dev/null || echo "")
-          if [ -n "$PREV_TAG" ]; then
-            NOTES=$(git log --pretty=format:"- %s" $PREV_TAG..HEAD)
-          else
-            NOTES=$(git log --pretty=format:"- %s" -20)
-          fi
-          echo "notes<<EOF" >> $GITHUB_OUTPUT
-          echo "$NOTES" >> $GITHUB_OUTPUT
-          echo "EOF" >> $GITHUB_OUTPUT
-
-      - name: Create GitHub Release
-        uses: softprops/action-gh-release@v2
-        with:
-          generate_release_notes: true
-          body: |
-            ## Changes
-            ${{ steps.notes.outputs.notes }}
-
-      - name: Setup Bun
-        uses: oven-sh/setup-bun@v2
-        with:
-          bun-version: latest
-
-      - name: Setup Node.js (for npm publish)
-        uses: actions/setup-node@v4
-        with:
-          node-version: '22'
-          registry-url: 'https://registry.npmjs.org'
-
-      - name: Update npm for trusted publishing
-        run: npm install -g npm@latest
-
-      - name: Install dependencies
-        run: bun install
-
-      - name: Build
-        run: bun run build
-
-      - name: Publish to npm
-        run: npm publish --provenance --access public

package/.github/workflows/update-marketplace.yml

@@ -1,96 +0,0 @@
-name: Update Marketplace
-
-on:
-  workflow_run:
-    workflows: ["Release"]
-    types: [completed]
-
-# Prevent parallel marketplace updates - queue instead of cancel
-concurrency:
-  group: update-marketplace
-  cancel-in-progress: false
-
-jobs:
-  update-marketplace:
-    runs-on: ubuntu-latest
-    # Only run if Release workflow succeeded
-    if: ${{ github.event.workflow_run.conclusion == 'success' }}
-
-    steps:
-      # Wait for CI to complete successfully
-      - name: Wait for CI to complete
-        uses: lewagon/wait-on-check-action@v1.3.4
-        with:
-          ref: ${{ github.event.workflow_run.head_sha }}
-          check-regexp: '^(lint-and-typecheck|test|build)$'
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-          wait-interval: 10
-          allowed-conclusions: success
-
-      # Get the tag name from the workflow run
-      - name: Get tag name
-        id: get_tag
-        env:
-          HEAD_BRANCH: ${{ github.event.workflow_run.head_branch }}
-        run: |
-          # Get the tag that triggered the Release workflow
-          # head_branch could be "v0.9.15" or "refs/tags/v0.9.15"
-          TAG_NAME=$(echo "$HEAD_BRANCH" | grep -oE 'v[0-9]+\.[0-9]+\.[0-9]+' || echo "")
-          if [ -z "$TAG_NAME" ]; then
-            echo "::error::Could not extract tag from head_branch: $HEAD_BRANCH"
-            exit 1
-          fi
-          echo "tag=${TAG_NAME}" >> $GITHUB_OUTPUT
-          echo "Tag: ${TAG_NAME}"
-
-      # Extract version from tag (v0.9.9 -> 0.9.9)
-      - name: Extract version
-        id: version
-        run: |
-          TAG_NAME=${{ steps.get_tag.outputs.tag }}
-          VERSION=${TAG_NAME#v}
-          echo "version=${VERSION}" >> $GITHUB_OUTPUT
-          echo "Extracted version: ${VERSION}"
-
-      # Checkout marketplace repo
-      - name: Checkout marketplace repo
-        uses: actions/checkout@v4
-        with:
-          repository: blueraai/bluera-marketplace
-          token: ${{ secrets.MARKETPLACE_PAT }}
-          path: marketplace
-
-      # Update marketplace.json
-      - name: Update marketplace version
-        working-directory: marketplace
-        run: |
-          VERSION="${{ steps.version.outputs.version }}"
-
-          jq --arg version "$VERSION" \
-            '(.plugins[] | select(.name == "bluera-knowledge") | .version) = $version' \
-            .claude-plugin/marketplace.json > .claude-plugin/marketplace.json.tmp
-
-          mv .claude-plugin/marketplace.json.tmp .claude-plugin/marketplace.json
-
-          echo "Updated marketplace.json to version $VERSION"
-
-      # Commit and push
-      - name: Commit and push marketplace update
-        working-directory: marketplace
-        run: |
-          VERSION="${{ steps.version.outputs.version }}"
-
-          git config user.name "github-actions[bot]"
-          git config user.email "github-actions[bot]@users.noreply.github.com"
-
-          git add .claude-plugin/marketplace.json
-
-          if git diff --staged --quiet; then
-            echo "No changes - marketplace already up to date"
-            exit 0
-          fi
-
-          git commit -m "chore: update bluera-knowledge to v$VERSION"
-          git push
-
-          echo "✅ Successfully updated marketplace to v$VERSION"

package/.husky/pre-commit

@@ -1,48 +0,0 @@
-#!/bin/sh
-
-# Get list of staged files
-STAGED_FILES=$(git diff --cached --name-only --diff-filter=ACM)
-
-# Categorize changes
-HAS_SRC_CHANGES=$(echo "$STAGED_FILES" | grep -E '^src/.*\.(ts|js)$' || true)
-HAS_TEST_CHANGES=$(echo "$STAGED_FILES" | grep -E '\.(test|spec)\.(ts|js)$' || true)
-HAS_CONFIG_CHANGES=$(echo "$STAGED_FILES" | grep -E '^(package\.json|tsconfig\.json|tsup\.config\.ts|vitest\.config\.ts|\.eslintrc|knip\.json|\.prettierrc|commitlint\.config\.js)' || true)
-HAS_DOC_CHANGES=$(echo "$STAGED_FILES" | grep -E '\.(md|txt)$|^LICENSE|^NOTICE' || true)
-HAS_DIST_CHANGES=$(echo "$STAGED_FILES" | grep -E '^dist/' || true)
-
-# If only documentation changed (and no code/config), skip all checks
-if [ -n "$HAS_DOC_CHANGES" ] && [ -z "$HAS_SRC_CHANGES" ] && [ -z "$HAS_TEST_CHANGES" ] && [ -z "$HAS_CONFIG_CHANGES" ]; then
-  echo "ℹ️  Only documentation changed, skipping code validation"
-  exit 0
-fi
-
-# If only dist/ changed (shouldn't happen, but handle it), skip checks
-if [ -n "$HAS_DIST_CHANGES" ] && [ -z "$HAS_SRC_CHANGES" ] && [ -z "$HAS_TEST_CHANGES" ] && [ -z "$HAS_CONFIG_CHANGES" ]; then
-  echo "ℹ️  Only dist/ changed, skipping validation"
-  exit 0
-fi
-
-# Run checks based on what changed
-echo "🔍 Running validation checks..."
-
-# Always run format check, lint and typecheck for code/config changes
-if [ -n "$HAS_SRC_CHANGES" ] || [ -n "$HAS_TEST_CHANGES" ] || [ -n "$HAS_CONFIG_CHANGES" ]; then
-  bun run format:check || exit 1
-  bun run lint || exit 1
-  bun run lint:deadcode || exit 1
-  bun run typecheck || exit 1
-fi
-
-# Run tests only if source or test files changed
-if [ -n "$HAS_SRC_CHANGES" ] || [ -n "$HAS_TEST_CHANGES" ]; then
-  bun run test:changed || exit 1
-fi
-
-# Build only if source or config changed
-if [ -n "$HAS_SRC_CHANGES" ] || [ -n "$HAS_CONFIG_CHANGES" ]; then
-  bun run build || exit 1
-  # Auto-stage dist/ after build (required for Claude Code plugin distribution)
-  git add dist/
-fi
-
-echo "✅ All checks passed"