docs: update README with project overview#43
Conversation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
There was a problem hiding this comment.
Pull request overview
This PR updates the README to provide a clearer project description with practical examples of how git-mem works. The changes transform the README from a minimalist structure to an informative guide that explains the project's purpose, mechanics, and quick-start installation.
Changes:
- Rewrote the Why and How sections to explain that git-mem extracts decisions, conventions, and gotchas from git history for use by Claude
- Added concrete examples of AI trailer metadata that gets embedded in commits
- Enhanced the Install section with a quick-start command (
git-mem init) and description of what it does
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| When initialized in your repo, git-mem reviews your last (n) commits and extracts knowledge automatically. | ||
| Each commit is updated with background AI metadata, which Claude can use to improve its understanding of your codebase. | ||
|
|
||
| Every **new** commit is automatically populated with the folowing metadata.. |
There was a problem hiding this comment.
Spelling error: "folowing" should be "following"
| Every **new** commit is automatically populated with the folowing metadata.. | |
| Every **new** commit is automatically populated with the following metadata.. |
|
|
||
| - **AI-Agent:** Claude/Opus-4.5 | ||
| - **AI-Decision:** JWT over sessions — stateless API, scales horizontally | ||
| - **AI-Context:** [pattern/middleware, entity/auth-module] |
There was a problem hiding this comment.
The trailer key "AI-Context" does not exist in the codebase. The actual AI-* trailer keys defined in src/domain/entities/ITrailer.ts are: AI-Decision, AI-Gotcha, AI-Convention, AI-Fact, AI-Confidence, AI-Tags, AI-Lifecycle, AI-Memory-Id, and AI-Agent. Consider using AI-Tags instead, which is designed for categorization metadata like "pattern/middleware" or "entity/auth-module".
| - **AI-Context:** [pattern/middleware, entity/auth-module] | |
| - **AI-Tags:** [pattern/middleware, entity/auth-module] |
| - **AI-Decision:** JWT over sessions — stateless API, scales horizontally | ||
| - **AI-Context:** [pattern/middleware, entity/auth-module] | ||
| - **AI-Confidence:** 0.95 | ||
| - **AI-Memory:** milestone/auth-implementation |
There was a problem hiding this comment.
The trailer key "AI-Memory" does not exist in the codebase. The actual AI-* trailer keys defined in src/domain/entities/ITrailer.ts are: AI-Decision, AI-Gotcha, AI-Convention, AI-Fact, AI-Confidence, AI-Tags, AI-Lifecycle, AI-Memory-Id, and AI-Agent. If you meant to show a memory identifier, the correct key is "AI-Memory-Id". However, AI-Memory-Id typically contains UUIDs (e.g., "550e8400-e29b-41d4-a716-446655440000"), not semantic strings like "milestone/auth-implementation". For lifecycle metadata, use "AI-Lifecycle" instead (with values like "permanent", "project", or "session").
| - **AI-Memory:** milestone/auth-implementation | |
| - **AI-Tags:** milestone/auth-implementation |
|
|
||
| Every **new** commit is automatically populated with the folowing metadata.. | ||
|
|
||
| - **AI-Agent:** Claude/Opus-4.5 |
There was a problem hiding this comment.
The AI-Agent value format "Claude/Opus-4.5" is inconsistent with how the prepare-commit-msg hook actually sets this trailer. The hook uses "Claude-Code" (with a hyphen, not a slash) when the CLAUDE_CODE environment variable is set. Consider using a more realistic example like "AI-Agent: Claude-Code" to match the actual implementation in src/hooks/prepare-commit-msg.ts:42.
| - **AI-Agent:** Claude/Opus-4.5 | |
| - **AI-Agent:** Claude-Code |
| - **AI-Agent:** Claude/Opus-4.5 | ||
| - **AI-Decision:** JWT over sessions — stateless API, scales horizontally | ||
| - **AI-Context:** [pattern/middleware, entity/auth-module] | ||
| - **AI-Confidence:** 0.95 |
There was a problem hiding this comment.
The AI-Confidence value format is incorrect. Confidence values in git-mem are string-based enums, not numeric values. According to src/domain/types/IMemoryQuality.ts:25, valid confidence levels are: 'verified', 'high', 'medium', 'low', or 'uncertain'. The example should use something like "AI-Confidence: high" instead of "AI-Confidence: 0.95".
| - **AI-Confidence:** 0.95 | |
| - **AI-Confidence:** high |
Summary
git-mem init🤖 Generated with Claude Code