Adam Moussa
71edeb3f3f
_review_round_index counted EVERY review_verdicts entry, including the synthetic human-gate verdict graph._apply_plan_decision folds in on a "request changes" (reviewer == "human_plan_gate"). That inflated the count so a revised plan could escalate prematurely without a fresh adversarial review. Now counts only reviewer-authored verdicts: a new _is_reviewer_verdict excludes entries tagged reviewer=="human_plan_gate" (read from the verdict dict's own field — no graph.py import). A human request_changes now grants the revised plan a fresh reviewer-round budget. Termination still bounded by MAX_PLAN_GATE_VISITS (each request_changes consumes one gate visit). 1490 passed. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| build_verify_subgraph.py | ||
| builders.py | ||
| builders_llm.py | ||
| clarifier.py | ||
| clarifier_llm.py | ||
| dispatch_invoker.py | ||
| fixer.py | ||
| handbook.py | ||
| planner.py | ||
| review_loop.py | ||
| review_loop_llm.py | ||
| verifier.py | ||
| verifier_llm.py | ||