3 Commits

Author	SHA1	Message	Date
Jason Woltje	6de631cd07	feat(#313): Implement FastAPI and agent tracing instrumentation ... Add comprehensive OpenTelemetry distributed tracing to the coordinator FastAPI service with automatic request tracing and custom decorators. Implementation: - Created src/telemetry.py: OTEL SDK initialization with OTLP exporter - Created src/tracing_decorators.py: @trace_agent_operation and @trace_tool_execution decorators with sync/async support - Integrated FastAPI auto-instrumentation in src/main.py - Added tracing to coordinator operations in src/coordinator.py - Environment-based configuration (OTEL_ENABLED, endpoint, sampling) Features: - Automatic HTTP request/response tracing via FastAPIInstrumentor - Custom span enrichment with agent context (issue_id, agent_type) - Graceful degradation when telemetry disabled - Proper exception recording and status management - Resource attributes (service.name, service.version, deployment.env) - Configurable sampling ratio (0.0-1.0, defaults to 1.0) Testing: - 25 comprehensive tests (17 telemetry, 8 decorators) - Coverage: 90-91% (exceeds 85% requirement) - All tests passing, no regressions Quality: - Zero linting errors (ruff) - Zero type checking errors (mypy) - Security review approved (no vulnerabilities) - Follows OTEL semantic conventions - Proper error handling and resource cleanup Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-02-04 14:25:48 -06:00
Jason Woltje	88953fc998	feat(#160): Implement basic orchestration loop ... Implements the Coordinator class with main orchestration loop: - Async loop architecture with configurable poll interval - process_queue() method gets next ready issue and spawns agent (stub) - Graceful shutdown handling with stop() method - Error handling that allows loop to continue after failures - Logging for all actions (start, stop, processing, errors) - Integration with QueueManager from #159 - Active agent tracking for future agent management Configuration settings added: - COORDINATOR_POLL_INTERVAL (default: 5.0s) - COORDINATOR_MAX_CONCURRENT_AGENTS (default: 10) - COORDINATOR_ENABLED (default: true) Tests: 27 new tests covering all acceptance criteria Coverage: 92% overall (100% for coordinator.py) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-01 18:03:12 -06:00
Jason Woltje	dad4b68f66	feat(#158): Implement issue parser agent ... Add AI-powered issue metadata parser using Anthropic Sonnet model. - Parse issue markdown to extract: estimated_context, difficulty, assigned_agent, blocks, blocked_by - Implement in-memory caching to avoid duplicate API calls - Graceful fallback to defaults on parse failures - Add comprehensive test suite (9 test cases) - 95% test coverage (exceeds 85% requirement) - Add ANTHROPIC_API_KEY to config - Update documentation and add .env.example Fixes #158 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-02-01 17:50:35 -06:00