Add batch closure ladder analytics and runner (sprint 253)

This commit is contained in:
Bill
2026-02-26 15:48:33 -07:00
parent 28b29dfd30
commit b6c91c9d64
8 changed files with 158 additions and 2 deletions

View File

@@ -150,7 +150,7 @@ Parallel planning tranche (active):
- `logs/taskitem_runs/TEST_ONLY_spec_planning_baseline_20260226/deterministic_spec_readiness.json`
Planning runtime controls (active):
- `sprint232_plan.md` to `sprint252_plan.md`
- `sprint232_plan.md` to `sprint253_plan.md`
- semantic bridge + intake augmentation + requirement injection + expansion gating are wired into:
- `tools/mcp/run_sprint_taskitem_pipeline.sh`
- current policy default is native-first semantic fallback:
@@ -207,3 +207,6 @@ Planning runtime controls (active):
- closure ladder can route around historically ineffective raw-only mode:
- `tools/mcp/analyze_raw_candidate_uplift_history.py`
- `WSTONE_CLOSURE_LADDER_SKIP_RAW_WHEN_NO_UPLIFT`
- closure ladder outcomes can be aggregated in batch:
- `tools/mcp/run_native_profile_closure_ladder_batch.sh`
- `tools/mcp/analyze_closure_ladder_outcomes.py`