feat(hooks): auto-reindex after git commit with embeddings preservation
Add PostToolUse hook that re-runs `gitnexus analyze` after git commit/merge,
automatically detecting and preserving embeddings via meta.json stats.
- Persist embeddings count in meta.json stats.embeddings field
- Add PostToolUse handler to both hook variants (cjs + plugin)
- Register PostToolUse hook in setup.ts for Claude Code
- Add "Keeping the Index Fresh" section to generated CLAUDE.md/AGENTS.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
revert running gitanalyz
fix: address code review findings for auto-reindex hooks
- Fix hook timeout units: seconds not milliseconds (8000->8, 120000->120)
- Remove unused execFileSync import from gitnexus-hook.cjs
- Remove unused `output` variable in PostToolUse handler
- Remove spurious template interpolation in ai-context.ts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
refactor: clean up gitnexus-hook.cjs per review feedback
- Hoist spawnSync import to module scope
- Add shell: isWin for npx fallback on Windows
- Extract findGitNexusDir helper, reuse in both PreToolUse and PostToolUse
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
fix(hooks): stricter git regex, proper spawnSync error handling, embeddings in recovery commands
- Tighten commit/merge regex to not match git merge-base (require \s|$ after subcommand)
- Replace try/catch with child.error/signal inspection for spawnSync timeout detection
- Include --embeddings in manual recovery commands when embeddings were detected
- Extract emitPostToolContext helper to reduce duplication
- Apply all fixes to both hook variants (cjs + plugin)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
fix(hooks): single-launch CLI resolution, guard PreToolUse stderr on failure
- Plugin: detect gitnexus binary via which/where once, then run exactly once
(prevents double execution when binary exists but command fails)
- Both hooks: only forward augment stderr as additionalContext when exit code
is 0, preventing CLI error output from leaking into agent context
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
docs: update README and CLI skill for PostToolUse auto-reindex
- README: editor support table now shows PreToolUse + PostToolUse
- README: description mentions auto-reindex after commits
- gitnexus-cli skill: document auto-reindex in "When to run" section
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Skill descriptions were too tool-centric ("using knowledge graph", "blast
radius") which prevented Claude Code from matching them to user intent.
Rewritten to user-intent-driven format with "Use when..." phrasing and
example trigger phrases so Claude can semantically match user requests.
Updated across all 3 sources: gitnexus/skills/, gitnexus-claude-plugin/skills/,
.claude/skills/, and the ai-context.ts fallback generator.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Skill folder names determine invocation paths in Claude Code plugins
(e.g. plugin:gitnexus:gitnexus-cli). Generic names like "cli" or
"debugging" could collide with other plugins, so prefix them all with
gitnexus- for clarity.
Updated across plugin dirs, main package source files, ai-context.ts
generator, setup.ts installer, and all CLAUDE.md/AGENTS.md routing tables.
Skill names should match folder names since the plugin namespace
(gitnexus:) already provides context. Avoids redundant display like
gitnexus:gitnexus-cli → now gitnexus:cli.
Bundle MCP server config (.mcp.json), fix hook to use spawnSync with npx
fallback and read stderr (KuzuDB stdout workaround), wire plugin.json with
hooks/mcpServers paths, add guide skill with tools/resources/schema reference,
add AMP-compatible mcp.json to all skill dirs, and slim CLAUDE.md generator
by moving reference content into the guide skill.
