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. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| builders.py | ||
| builders_llm.py | ||
| clarifier.py | ||
| clarifier_llm.py | ||
| planner.py | ||
| review_loop.py | ||
| review_loop_llm.py | ||
| verifier.py | ||
| verifier_llm.py | ||