Adam Moussa
4b17e8ebd4
review_loop_llm -> GPT-4.1 cross_reviewer (orchestrator run.py); builders_llm -> DeepSeek fast_coder (INERT, proposes diff text only); verifier_llm -> ci_gate is sole PASS authority, Claude is fix-proposer only. Hardens review_loop.parse_verdict to word-boundary matching, adds a fail-closed subprocess timeout, and bind_review_node (single-arg, no LangGraph config injection). All fail safe on untrusted model output. |
||
|---|---|---|
| .. | ||
| sim | ||
| __init__.py | ||
| conftest.py | ||
| test_billing.py | ||
| test_builders.py | ||
| test_builders_llm.py | ||
| test_ci_gate.py | ||
| test_ci_gate_workflow.py | ||
| test_clarifier.py | ||
| test_clarifier_llm.py | ||
| test_claude_code_adapter.py | ||
| test_deadline_timer.py | ||
| test_github_adapter.py | ||
| test_graph.py | ||
| test_invoker.py | ||
| test_ledger.py | ||
| test_operator_cli.py | ||
| test_planner.py | ||
| test_recovery.py | ||
| test_responder.py | ||
| test_resume_worker.py | ||
| test_review_loop.py | ||
| test_review_loop_llm.py | ||
| test_run_team.py | ||
| test_schema.py | ||
| test_slack_adapter.py | ||
| test_state_store.py | ||
| test_task_model.py | ||
| test_transport_base.py | ||
| test_verifier.py | ||
| test_verifier_llm.py | ||