The provenance guide already documented the guard semantics and A/B harness, but its example command used the script path that fails from the repo root because package imports do not resolve there. Document the module invocation instead so verification can reproduce the harness without ad hoc path fixes. Constraint: Keep documentation aligned with the current harness without changing runtime behavior or the default debate path Rejected: Add PYTHONPATH=. to the examples | less ergonomic and easier to drift from normal repo-root usage Confidence: high Scope-risk: narrow Directive: Keep profiling examples runnable from the repo root; update the docs if the harness entrypoint changes again Tested: python -m orchestrator.profile_stage_chain --help Tested: python -m pytest tradingagents/tests/test_research_guard.py orchestrator/tests/test_llm_runner.py orchestrator/tests/test_live_mode.py orchestrator/tests/test_contract_v1alpha1.py orchestrator/tests/test_trading_graph_config.py Tested: lsp_diagnostics_directory (0 errors, 0 warnings) Not-tested: end-to-end profile run against a live LLM backend |
||
|---|---|---|
| .. | ||
| application-boundary.md | ||
| research-provenance.md | ||