chore: prepare 0.5.0 release

[TonyCasey]

Summary

• Bump version from 0.4.0 (never published) to 0.5.0
• Update CHANGELOG.md — merge 0.4.0 entries into 0.5.0, add multi-provider LLM (GIT-110), multi-agent detection (GIT-121), trailers command (GIT-71), and 7 bug fixes
• Update docs/getting-started.md — add trailers command, PostCommit/CommitMsg hooks, full env vars table, LLM config YAML section
• Update CLAUDE.md — fix command count (8) and hook handler count (5)
• Fix flaky CLAUDECODE integration test — use GIT_MEM_MODEL instead of ANTHROPIC_MODEL to avoid session file interference
• Update package.json description to match new positioning
• Add README image

Test plan

• npm run type-check — clean
• npm run lint — clean
• npm test — 650/650 pass (previously 649/650)

🤖 Generated with Claude Code

Summary by CodeRabbit

• New Features

  • Multi-provider LLM enrichment now available (OpenAI, Gemini, Ollama) with automatic detection
  • Multi-agent detection support for Claude Code and Codex
  • New trailers command to inspect and query AI metadata across commit history

• Bug Fixes

  • Improved robustness and Windows compatibility
  • Fixed configuration handling and git root resolution

• Documentation

  • Updated getting started guide with new features and configuration options
  • Added LLM provider setup and environment variable documentation

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

---

📝 Walkthrough

Walkthrough

Release 0.5.0 introduces multi-provider LLM enrichment (OpenAI, Gemini, Ollama), multi-agent detection (Claude, Codex), new trailers and hook CLI commands, expanded EventBus hook handlers, and robustness improvements across configuration, initialization, and Windows compatibility.

Changes

Cohort / File(s)	Summary
Release & Version CHANGELOG.md, package.json	Version bumped from 0.4.0 to 0.5.0; added multi-provider LLM enrichment, multi-agent detection, trailers and hook commands; fixed config passthrough, MCP resolution, push semantics, error handling, and Windows compatibility.
Documentation README.md, docs/getting-started.md	Added image asset reference; expanded with new trailers command guidance, multi-LLM provider environment variables (OPENAI_API_KEY, GEMINI_API_KEY, OLLAMA_HOST), YAML configuration example for LLM settings, and updated Claude hooks table with PostCommit/CommitMsg hooks.
Architecture & Public API CLAUDE.md	CLI expanded from 6 to 8 commands (added trailers, hook); EventBus hook handler registration increased from 3 to 5 handlers (session:start, session:stop, prompt:submit, commit:msg, post:commit).
Integration Tests tests/integration/hooks/hook-commit-msg.test.ts	Updated model environment variable priority from ANTHROPIC_MODEL to GIT_MEM_MODEL for Claude Code detection; added explanatory comments.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related PRs

• feat: multi-agent detection with config-based model resolution (GIT-121) #82 — Extends agent/model auto-detection logic with multi-provider resolution and config file model handling, directly supporting the multi-agent detection feature.
• feat: git mem trailers CLI command for inspection (GIT-71) #42 — Adds the git mem trailers CLI command and related trailer-handling modules that are exposed in this release.
• feat: handle edge cases in commit-msg hook (GIT-85) #56 — Modifies the commit-msg hook/handler surface, directly connected to the new commit:msg hook registration in EventBus.

🚥 Pre-merge checks | ✅ 4

✅ Passed checks (4 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title 'chore: prepare 0.5.0 release' clearly summarizes the main change: version bumping and release preparation across all files.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Merge Conflict Detection	✅ Passed	✅ No merge conflicts detected when merging into main

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

• 📝 Generate docstrings

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch release-prep

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[Copilot]

Pull request overview

This PR prepares the 0.5.0 release by bumping the version, consolidating CHANGELOG entries, updating documentation to reflect new features, and fixing a flaky integration test.

Changes:

• Version bump from 0.4.0 to 0.5.0 with updated package description
• CHANGELOG consolidation merging 0.4.0 into 0.5.0 with 3 new features and 7 bug fixes
• Documentation updates for trailers command, hooks, and multi-provider LLM support
• Test fix to prevent CLAUDECODE session file interference using GIT_MEM_MODEL

Reviewed changes

Copilot reviewed 6 out of 7 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
package.json	Version bump to 0.5.0 and updated description to emphasize AI metadata tracking
CHANGELOG.md	Merged 0.4.0 into 0.5.0 release dated 2026-02-16, added multi-provider LLM, multi-agent detection, trailers command, and 7 bug fixes
docs/getting-started.md	Added trailers command documentation, PostCommit/CommitMsg hooks, expanded environment variables table, and LLM configuration YAML section
CLAUDE.md	Updated CLI command count (6→8) and hook handler count (3→5) to reflect current state
tests/integration/hooks/hook-commit-msg.test.ts	Fixed flaky test by using GIT_MEM_MODEL instead of ANTHROPIC_MODEL to avoid session file interference
README.md	Added git-mem.png image to showcase AI commit metadata

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.