jpmschweitzerandClaude
62edb111bd
Remove confusing references to unimplemented features and clarify what's currently working vs prepared for future integration. README.md Changes: - Update title to reflect mock API (not "with Ollama Backend") - Remove architecture diagram showing Ollama/PydanticAI integration - Clarify current status section (mock API, integration prepared) - Fix uvicorn command: main:app → src.main:app - Update model examples: llama2 → mistral-nemo:latest - Mark Ollama requirements as future (not currently needed) - Update environment variables (Ollama config commented out) - Clarify API endpoints return mock responses - Update CVE check date: 2025-12-05 → 2025-12-06 - Fix testing section to use requirements-dev.txt - Remove Ollama troubleshooting (not connected yet) - Mark production Ollama considerations as future - Remove redundant changelog section (use CHANGELOG.md) AGENTS.md Changes: - Clarify project overview (mock API, not integrated) - Add status indicators to components section - Mark PydanticAI section as "for future implementation" - Mark Ollama section as "ready for future integration" - Add target model: mistral-nemo:latest - Update OpenAI compatibility section with implemented status - Fix Pydantic version: 2.10+ → 2.11+ (matches requirements) - Add implementation status to development guidelines - Mark common patterns as implemented vs future reference - Update CVE check date: 2025-12-05 → 2025-12-06 CHANGELOG.md Changes: - Clarify PydanticAI line: "for LLM integration" → "dependency (ready for future integration)" Key Improvements: - Clear distinction between implemented vs prepared features - No misleading references to Ollama/PydanticAI integration - Accurate model names (mistral-nemo:latest) - Correct command examples (src.main:app) - Proper date stamps (2025-12-06) - Removed confusing troubleshooting for unconnected services Status: Documentation now accurately reflects v0.1.0 mock API 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
46 lines
1.6 KiB
Markdown
46 lines
1.6 KiB
Markdown
# Changelog
|
|
|
|
All notable changes to this project will be documented in this file.
|
|
|
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
|
|
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
|
|
## [Unreleased]
|
|
|
|
### Added
|
|
- Initial project structure with domain-based organization
|
|
- OpenAI-compatible `/v1/chat/completions` endpoint with streaming support
|
|
- OpenAI-compatible `/v1/models` endpoint
|
|
- Health check and root endpoints
|
|
- Comprehensive test suite with 62% coverage
|
|
- Security-focused dependency management with CVE checking
|
|
- FastAPI best practices implementation
|
|
- SSE streaming with 20-second timeout protection
|
|
- Custom Pydantic base models for consistent serialization
|
|
- Application factory pattern for testability
|
|
- Async Ollama client (ready for integration)
|
|
- Complete documentation (README, AGENTS.md)
|
|
|
|
### Security
|
|
- Minor version locking for all dependencies
|
|
- All packages CVE-checked (as of 2025-12-06)
|
|
- Environment variable protection via .gitignore
|
|
- No known vulnerabilities in dependency tree
|
|
|
|
## [0.1.0] - 2025-12-06
|
|
|
|
### Added
|
|
- Project initialization
|
|
- Python 3.12.11 environment
|
|
- FastAPI 0.123.9 web framework
|
|
- PydanticAI 1.27.0 dependency (ready for future integration)
|
|
- Mock chat completions (lorem ipsum responses)
|
|
- Mock model listing (mistral-nemo:latest)
|
|
- Testing infrastructure (pytest, coverage, ruff, mypy)
|
|
- Configuration management with pydantic-settings
|
|
- CORS middleware
|
|
- Exception handlers (OpenAI-compatible error format)
|
|
|
|
[Unreleased]: https://github.com/yourusername/tatlock/compare/v0.1.0...HEAD
|
|
[0.1.0]: https://github.com/yourusername/tatlock/releases/tag/v0.1.0
|