5 Commits

Author	SHA1	Message	Date
HAL9000	876a2c6916	fix(data-integrity): Replace unconditional commit with flush in LLMTraceRepository.save() ... Implement dual-path session management in LLMTraceRepository.save(): - UoW mode (explicit session provided): flush only, caller controls commit - Standalone mode (no session): flush + commit + close for durable persistence This resolves three data-integrity violations: 1. Premature commit of outer UoW transactions 2. Loss of rollback capability for subsequent failures 3. Mismatch between class docstring and implementation Also adds: - Input validation: trace must not be None - Updated BDD step definitions to pass session explicitly in UoW scenarios - close() method to _BrokenSession mock for proper cleanup path coverage - CHANGELOG.md entry for issue #7505 - CONTRIBUTORS.md credit for HAL 9000 ISSUES CLOSED: #7505	2026-05-05 09:57:46 +00:00
HAL9000	1b515d529c	fix(tests): align LLM trace test session factory with flush-based save ... Use a shared session in test setup so that data flushed (but not committed) by LLMTraceRepository.save() remains visible to subsequent read operations within the same test scenario. This matches the production UnitOfWork pattern where a single session is shared across repository calls. Also fixes ruff format violations (single quotes, string concatenation) that caused the CI lint gate to fail. ISSUES CLOSED: #10034	2026-04-26 11:19:10 +00:00
HAL9000	2a5a37d774	fix: remove type: ignore comments and use proper method assignment ... Removed type: ignore[method-assign] comments from spy function assignments in test code. Replaced direct method assignment with object.__setattr__ to properly handle method replacement without type suppression, maintaining code quality standards.	2026-04-26 11:19:10 +00:00
HAL9000	b4b6fe6484	fix: replace session.commit() with session.flush() in LLMTraceRepository.save() ... Refactor: replace session.commit() with session.flush() in LLMTraceRepository.save() to ensure changes are persisted within the UnitOfWork without prematurely committing the database transaction. - Updated LLMTraceRepository.save() to call session.flush() instead of session.commit() in src/cleveragents/infrastructure/database/llm_trace_repository.py. - Added two new BDD scenarios to features/llm_trace.feature: - 'Repository save() calls flush not commit' to verify save() uses flush not commit. - 'LLM trace rolled back when UnitOfWork transaction rolls back' to verify rollback. - Added corresponding step definitions to features/steps/llm_trace_steps.py. ISSUES CLOSED: #10034	2026-04-26 11:19:10 +00:00
freemo	3f14cbbf7e	feat(observability): add LLMTrace model and operational metrics ... Add LLMTrace Pydantic v2 domain model with all required fields (trace_id, plan_id, decision_id, actor, provider, model, prompt_tokens, completion_tokens, cost_usd, latency_ms, tool_calls, context_hash, streaming, retry_count, error). Define 14 OperationalMetricKey values (PLAN_DURATION_MS, PLAN_TOTAL_COST_USD, PLAN_DECISION_COUNT, ACTOR_INVOCATION_COUNT, ACTOR_LATENCY_MS, TOOL_INVOCATION_COUNT, TOOL_ERROR_RATE, CONTEXT_BUILD_TIME_MS, CONTEXT_TOKEN_COUNT, LLM_CALL_COUNT, LLM_TOTAL_TOKENS, LLM_TOTAL_COST_USD, LLM_AVG_LATENCY_MS, SUBPLAN_COUNT) with MetricEntry model and MetricCollector. Add llm_traces database table (LLMTraceModel) with LLMTraceRepository for persistence. TraceService provides recording, querying, metric computation, plan lifecycle hooks, and optional LangSmith forwarding when LANGCHAIN_TRACING_V2=true. Wired into DI container as trace_service. Includes 28 Behave BDD scenarios, 6 Robot Framework smoke tests, 3 ASV benchmark suites, and reference documentation. Fix pre-existing cli_core server_mode test flake by mocking resolve_server_mode in test steps to avoid stale config file interference. Closes #500	2026-03-03 17:04:17 -05:00