Conversation
- README: lead with "Track AI contributions in your git history" - getting-started: show AI trailers first, Claude Code hooks as extra feature - Update config references from .git-mem.json to .git-mem/.git-mem.yaml - CHANGELOG: consolidate post-0.3.0 work into 0.4.0 release - Bump version to 0.4.0 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> AI-Agent: Claude-Code/2.1.42 AI-Model: claude-opus-4-5-20251101 AI-Decision: The project has repositioned its messaging to lead with AI metadata tracking rather than memory extraction, suggesting the primary value prop is tracking AI contributions in git history. AI-Confidence: verified AI-Tags: documentation, product-positioning, ai-metadata, configuration, yaml, migration, breaking-change, versioning, changelog, feature-consolidation, hooks, error-handling, config, reliability, git-trailers, commit-format, timeout, claude-code AI-Lifecycle: project AI-Memory-Id: 56f52b0b AI-Source: llm-enrichment
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
📝 WalkthroughWalkthroughUpdates release notes, docs, and README for version 0.4.0; migrates config from top-level JSON to Changes
Sequence Diagram(s)sequenceDiagram
participant Dev as Developer (commit)
participant Hook as Git Hook
participant Intent as IntentExtractor
participant Loader as MemoryContextLoader
participant LLM as LLM/Enrichment
participant Repo as Repository (commit-msg)
Dev->>Hook: create/prepare commit
Hook->>Intent: extract intent (IIntentExtractor)
Intent->>Loader: loadWithQuery (targeted recall)
Loader->>LLM: provide context (optional enrichment)
LLM-->>Hook: enriched metadata / intent
Hook->>Repo: attach AI metadata trailers to commit
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 3 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches🧪 Generate unit tests (beta)
⚔️ Resolve merge conflicts (beta)
No actionable comments were generated in the recent review. 🎉 Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Fix all issues with AI agents
In `@CHANGELOG.md`:
- Line 26: Update the phrase "Backwards compatible migration from JSON" to
hyphenate the compound adjective: replace it with "Backwards-compatible
migration from JSON" so the compound modifier correctly modifies "migration".
In `@docs/getting-started.md`:
- Around line 15-22: The fenced code block containing the commit metadata
(starting with "feat: add user authentication" and the AI-Agent/AI-Model lines)
is missing a language tag; update the opening triple-backtick to include a
language identifier (e.g., "text" or "git") so Markdown linting and highlighting
work correctly — locate the code block that wraps the lines "feat: add user
authentication" / "AI-Agent: claude-code" and change the fence from ``` to
```text (or ```git).
In `@README.md`:
- Around line 15-23: The fenced code block in README.md containing the lines
starting with "feat: add user authentication" and the
AI-Agent/AI-Model/AI-Decision/AI-Context metadata should include a language
identifier (e.g., change the opening ``` to ```text or ```git) so Markdown
linters and highlighters recognize it; update that opening fence for the block
that contains "AI-Agent: claude-code" to use a language specifier.
- Hyphenate "Backwards-compatible" in CHANGELOG - Add language identifiers to code blocks in README and getting-started Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> AI-Agent: Claude-Code/2.1.42 AI-Model: claude-opus-4-5-20251101 AI-Convention: Documentation code blocks should include language identifiers for proper syntax highlighting and formatting. AI-Confidence: verified AI-Tags: documentation, markdown, code-blocks, syntax-highlighting, grammar, changelog, technical-writing, code-review, tooling, development-process AI-Lifecycle: project AI-Memory-Id: 5034f6a6 AI-Source: llm-enrichment
There was a problem hiding this comment.
Pull request overview
This PR updates the project’s documentation and release metadata to emphasize AI trailer/metadata tracking as the primary value proposition, aligning docs and changelog with the YAML-based config layout and the 0.4.0 release.
Changes:
- Repositions README + getting-started flow to lead with AI commit trailers/metadata, with “memory” as an additional capability.
- Updates config references to
.git-mem/.git-mem.yamland refreshes Claude Code integration docs. - Consolidates CHANGELOG entries and bumps package version to
0.4.0.
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 9 comments.
Show a summary per file
| File | Description |
|---|---|
| package.json | Bumps npm package version to 0.4.0. |
| docs/getting-started.md | Reorders onboarding docs and updates examples/config references. |
| README.md | Rewrites top-level messaging to focus on AI metadata in git history. |
| CLAUDE.md | Updates internal contributor notes for YAML config and adds workflow references. |
| CHANGELOG.md | Consolidates post-0.3.0 notes into a 0.4.0 section and adds doc-related entries. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| { | ||
| "name": "git-mem", | ||
| "version": "0.3.0", | ||
| "version": "0.4.0", |
There was a problem hiding this comment.
package.json version was bumped to 0.4.0, but package-lock.json still reports 0.3.0. If this repo commits package-lock.json, update it (or regenerate lockfile) so the package metadata stays consistent for installs/publishing.
| "version": "0.4.0", | |
| "version": "0.3.0", |
| AI-Agent: claude-code | ||
| AI-Model: claude-sonnet-4-5-20250929 | ||
| AI-Decision: JWT over sessions — stateless API, scales horizontally | ||
| AI-Context: [pattern/middleware, entity/auth-module] |
There was a problem hiding this comment.
The example commit trailers include AI-Context, but the implementation only defines trailers like AI-Tags, AI-Lifecycle, AI-Memory-Id, etc. Consider replacing AI-Context with a supported trailer (likely AI-Tags) so users don’t look for a non-existent trailer key.
| AI-Context: [pattern/middleware, entity/auth-module] | |
| AI-Tags: pattern/middleware, entity/auth-module |
| - Branch per Linear issue, named with ticket number (e.g. `GIT-15`) | ||
| - Use the SKILL .claude/skills/github/SKILL.md for interacting with GitHub | ||
| - PR workflow use the skill .claude/skills/pr/SKILL.md | ||
| - Create the PR | ||
| - Wait for 120 seconds to allow for review from coderabbit | ||
| - Address comments directly inline to the comment | ||
| - if a fix is applied, mark the comment as resolved | ||
| - wait for another 120 seconds to allow for review from coderabbit | ||
| - repeat the steps until all comments are resolved |
There was a problem hiding this comment.
The new guidance references .claude/skills/github/SKILL.md and .claude/skills/pr/SKILL.md, but there is no .claude/skills/ directory in this repo. Either commit those skill docs or update/remove these bullets so the workflow instructions are actionable.
| ### Changed | ||
|
|
||
| - **Documentation repositioning** — README and getting-started now lead with AI metadata tracking, memory as "level up" | ||
|
|
There was a problem hiding this comment.
This PR appears to ship 0.4.0 (version bump + 0.4.0 section), but “Documentation repositioning” is still listed under [Unreleased]. Move it into the 0.4.0 section (likely under “Changed”) or remove it from Unreleased to avoid double-counting.
| - `loadWithQuery` method on `MemoryContextLoader` for targeted recall | ||
| - Configurable via `promptSubmit.extractIntent` in config | ||
| - **Commit message bodies** — memory context now includes full commit message bodies, not just subjects | ||
| - **YAML configuration** — `.git-mem.yaml` replaces `.git-mem.json`: |
There was a problem hiding this comment.
Changelog says “.git-mem.yaml replaces .git-mem.json”, but the actual config path is .git-mem/.git-mem.yaml (file inside the .git-mem/ directory). Consider updating the changelog wording to the full path to avoid confusion.
| - **YAML configuration** — `.git-mem.yaml` replaces `.git-mem.json`: | |
| - **YAML configuration** — `.git-mem/.git-mem.yaml` replaces `.git-mem.json`: |
| ## What `init` sets up | ||
|
|
||
| git-mem stores knowledge in two ways: | ||
| 1. **Git hooks** — `prepare-commit-msg` and `commit-msg` add AI trailers to every commit |
There was a problem hiding this comment.
Docs say init sets up only prepare-commit-msg and commit-msg, but init also installs a post-commit hook. Update this list to include post-commit (and briefly what it does) to match actual behavior.
| 1. **Git hooks** — `prepare-commit-msg` and `commit-msg` add AI trailers to every commit | |
| 1. **Git hooks** — `prepare-commit-msg`, `commit-msg`, and `post-commit` add and record AI trailers for every commit |
| ### extract | ||
|
|
||
| Scan commit history, score commits by interest, and extract decisions/gotchas/conventions as memories. | ||
| Scans commit history, scores commits by interest, and extract decisions/gotchas/conventions as memories for AI context. |
There was a problem hiding this comment.
Grammar: “Scans commit history, scores commits by interest, and extract …” should be “extracts …” (subject/verb agreement).
| Scans commit history, scores commits by interest, and extract decisions/gotchas/conventions as memories for AI context. | |
| Scans commit history, scores commits by interest, and extracts decisions/gotchas/conventions as memories for AI context. |
| AI-Agent: claude-code | ||
| AI-Model: claude-sonnet-4-5-20250929 | ||
| AI-Decision: JWT over sessions — stateless API, scales horizontally | ||
| AI-Context: [pattern/middleware, entity/auth-module] |
There was a problem hiding this comment.
The README example includes an AI-Context trailer, but there’s no AI-Context trailer key in the codebase (the closest concept is AI-Tags). Update the example to use a supported trailer name so it matches what the hooks actually write.
| AI-Context: [pattern/middleware, entity/auth-module] | |
| AI-Tags: [pattern/middleware, entity/auth-module] |
| - `code-quality-rules.md` - TypeScript/ESLint configuration, error prevention | ||
| - `git-rules.md` - Commit workflow, PR creation, memory milestones | ||
| - `testing-principles.md` - Testing pyramid, mocking strategies | ||
| - `memory-rules.md` - Handling session memory | ||
|
|
There was a problem hiding this comment.
These new references to .claude/rules/memory-rules.md (and the .claude/rules/ directory) don’t exist in the repository. Either add the referenced rule file(s) or update CLAUDE.md to point at a path that actually exists so contributors can follow the guidance.
Summary
.git-mem.jsonto.git-mem/.git-mem.yamlTest plan
Closes GIT-106
🤖 Generated with Claude Code
Summary by CodeRabbit
New Features
Changed
Documentation