feat: Complete Repomix integration with bootstrap --repomix flag #32
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ration Implements comprehensive Repomix integration as specified in coldstart prompt 008-repomix-integration.md. This feature enables automated repository context generation for AI consumption and improves AI-assisted development workflows. ## Features Added ### Core Components - **RepomixService** (`src/agentready/services/repomix.py`) - Configuration generation (repomix.config.json) - Ignore file generation (.repomixignore) - Repomix execution wrapper with error handling - Freshness checking (7-day default staleness threshold) - Output file management and discovery - **CLI Command** (`src/agentready/cli/repomix.py`) - `agentready repomix-generate` - Main command - `--init` - Initialize Repomix configuration - `--format` - Output format selection (markdown/xml/json/plain) - `--check` - Verify output freshness without regeneration - `--max-age` - Configurable staleness threshold - **Bootstrap Integration** (`src/agentready/cli/bootstrap.py`) - Added `--repomix` flag to bootstrap command - Auto-generates repomix.config.json and .repomixignore - Creates GitHub Actions workflow for automation - **GitHub Actions Workflow** (`src/agentready/templates/bootstrap/workflows/repomix-update.yml.j2`) - Auto-regenerates on push to main and PRs - Weekly scheduled runs (Mondays 9 AM UTC) - Manual trigger support via workflow_dispatch - PR comments when Repomix output changes - **Repomix Assessor** (`src/agentready/assessors/repomix.py`) - Tier 3 attribute (weight: 0.02) - Checks for configuration file existence - Validates output freshness (< 7 days) - Provides detailed remediation guidance ### Testing - Comprehensive unit tests (21 test cases) - RepomixService tests with mocking - Installation detection - Config/ignore generation - Freshness checks - Command execution - RepomixConfigAssessor tests - Multiple assessment scenarios - Pass/fail/partial compliance ### Documentation - Updated repomix-output.md (1.8M, 420k tokens, 156 files) - AgentReady self-assessment: **80.0/100 (Gold)** 🥇 ## Technical Details ### Architecture - Follows existing AgentReady patterns - Strategy pattern for assessor - Service layer for business logic - Template-based workflow generation ### Integration Points - Registered in main CLI (`src/agentready/cli/main.py`) - Added to bootstrap generator (`src/agentready/services/bootstrap.py`) - Included in assessor list (Tier 3 Important) ### Configuration Management - Smart defaults for Python projects - Customizable ignore patterns - Aligned with existing .gitignore patterns - Security scanning enabled by default ## Use Cases ```bash # Initialize Repomix for repository agentready repomix-generate --init # Generate AI-friendly context agentready repomix-generate # Bootstrap new repo with Repomix agentready bootstrap --repomix # Check if output is fresh agentready repomix-generate --check ``` ## Related - Coldstart Prompt: `coldstart-prompts/08-repomix-integration.md` - Priority: P4 (Enhancement) - Category: AI-Assisted Development Tools 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
## [1.1.2](v1.1.1...v1.1.2) (2025-11-21) ### Bug Fixes * correct GitHub repository link in site navigation ([5492278](5492278))
* feat: Add automated demo command for AgentReady Implements P0 feature to showcase AgentReady capabilities with a single command. Features: - agentready demo command creates sample repository and runs assessment - Supports Python (default) and JavaScript demo repositories - Real-time progress indicators with color-coded output (✓/✗/⊘) - Auto-opens HTML report in browser (optional --no-browser flag) - Generates HTML, Markdown, and JSON reports in .agentready-demo/ - Options: --language, --no-browser, --keep-repo Implementation: - Created src/agentready/cli/demo.py with demo command logic - Registered demo command in CLI main.py - Added comprehensive unit tests in tests/unit/test_demo.py - Demo completes in ~3-5 seconds with 25 attribute assessments Perfect for presentations, stakeholder demos, and user onboarding. Closes #1 🤖 Generated with [Claude Code](https://claude.ai/code) Co-authored-by: Jeremy Eder <jeremyeder@users.noreply.github.com> * fix: install AgentReady from source in CI workflow The workflow was attempting to install agentready from PyPI, but the package has never been published. Changed to install from checked-out repository source using 'pip install -e .' instead. This ensures CI tests the actual code in the PR rather than a potentially stale PyPI version. Fixes GitHub Actions workflow failure on PR #24. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: add manual PyPI publishing workflow Added workflow_dispatch workflow for manual PyPI publishing with: - Dry run mode (publishes to TestPyPI for testing) - Production mode (publishes to PyPI) - Optional version override - Automatic GitHub release creation - Built-in validation with twine check - Secure: Uses environment variables to prevent command injection Usage: 1. Configure TEST_PYPI_TOKEN and PYPI_TOKEN secrets 2. Go to Actions → "Publish to PyPI" → Run workflow 3. Choose dry run (TestPyPI) or production (PyPI) Future enhancement tracked in issue #25 for automated integration with semantic-release workflow. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat: implement continuous learning loop with LLM-powered skill extraction Add comprehensive learning system that extracts high-quality skills from assessments: - New 'learn' CLI command with heuristic and LLM enrichment modes - Claude API integration for detailed skill analysis and instruction generation - LLM response caching system (7-day TTL) to reduce API costs - Code sampling for real repository examples - Pattern extraction from high-scoring assessment attributes - Support for multiple output formats (JSON, SKILL.md, GitHub issues) Technical additions: - src/agentready/cli/learn.py - Main learning command implementation - src/agentready/learners/ - Pattern extraction and LLM enrichment modules - src/agentready/services/llm_cache.py - LLM response caching - src/agentready/models/discovered_skill.py - Skill data model - tests/unit/learners/ - Unit tests for learning modules - .github/workflows/continuous-learning.yml - CI workflow - .github/CLAUDE_INTEGRATION.md - Integration documentation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Jeremy Eder <jeremyeder@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com>
# [1.2.0](v1.1.2...v1.2.0) (2025-11-21) ### Features * Add automated demo command for AgentReady ([#24](#24)) ([f4e89d9](f4e89d9)), closes [#1](#1) [#25](#25) [hi#quality](https://github.com/hi/issues/quality) [hi#scoring](https://github.com/hi/issues/scoring)
#26) Add 32 tests (19 unit, 13 integration) for bootstrap functionality: - BootstrapGenerator service: 100% coverage (101/101 lines) - Bootstrap CLI: 92% coverage (37/40 lines) - Tests cover dry-run mode, file generation, language detection, template rendering, error handling, and edge cases Also fix ambiguous variable name linting error in code_quality.py (line 300: l → line for better readability) All tests passing, all linters clean. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude <noreply@anthropic.com>
Add prominent report header showing repository context and assessment metadata to all report formats (HTML, Markdown, JSON). Changes: - Create AssessmentMetadata model to capture execution context - AgentReady version from package metadata - Assessment timestamp (ISO 8601 and human-readable) - Executed by (username@hostname) - CLI command used - Working directory - Update Assessment model with optional metadata field - Implement metadata collection in Scanner service - Get version from importlib.metadata - Reconstruct command from sys.argv - Capture user and hostname from environment - Update all reporters to display metadata - HTML: Two-column header (repo info + meta info) - Markdown: Prominent header with all metadata fields - JSON: Metadata object at top level - Add comprehensive unit tests (4 new tests, all passing) - All 37 tests passing (34 unit + 3 integration) Acceptance criteria met: ✅ User can identify repository assessed (name, path, branch, commit) ✅ Timestamp shows when assessment was run ✅ Git context visible in all reports ✅ AgentReady version tracked for reproducibility ✅ Execution context captured (user@host, command, cwd) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude <noreply@anthropic.com>
# [1.3.0](v1.2.0...v1.3.0) (2025-11-21) ### Features * add report header with repository metadata ([#28](#28)) ([7a8b34a](7a8b34a))
This commit implements issue #8 by adding comprehensive Repomix integration: - Added RepomixConfigAssessor to assess Repomix configuration and freshness - Added --repomix flag to bootstrap command to optionally enable Repomix - Integrated RepomixService into BootstrapGenerator for setup automation - Created GitHub Actions workflow template for automatic Repomix updates - Added comprehensive integration and unit tests for Repomix functionality - Fixed Jinja2 template escaping issues in repomix-update.yml workflow - Updated Finding constructors in RepomixConfigAssessor to match API - Fixed unused imports across multiple files (ruff auto-fix) The --repomix flag allows users to optionally include Repomix configuration when bootstrapping a repository: agentready bootstrap --repomix This creates: - repomix.config.json (Repomix configuration) - .repomixignore (ignore patterns) - .github/workflows/repomix-update.yml (auto-update workflow) All tests passing (95/95). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Contributor
Author
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Comment on lines
+71
to
+74
| # Format timestamps | ||
| iso_timestamp = timestamp.isoformat() | ||
| human_timestamp = timestamp.strftime("%B %d, %Y at %-I:%M %p") | ||
|
|
There was a problem hiding this comment.
AssessmentMetadata now formats the human-readable timestamp with strftime("%B %d, %Y at %-I:%M %p"), but the %-I directive is unsupported on Windows and raises ValueError. That means agentready assess will crash during metadata creation on Windows before any findings are produced. Consider using a portable format (e.g., %I with lstrip('0')) so the assessment runs on Windows as well.
Useful? React with 👍 / 👎.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
This PR implements issue #8 by adding comprehensive Repomix integration to AgentReady.
What's New
--repomixflag foragentready bootstrapcommandKey Changes
CLI & Bootstrap:
--repomixoption tobootstrapcommandAssessor:
GitHub Actions:
Code Quality:
Usage Example
Test Results
✅ All 95 tests passing
bootstrap --repomixTest plan
agentready bootstrap --repomixRelated
Closes #8
🤖 Generated with Claude Code