Add top-gap uplift hard gate for raw candidate search (sprint 257)

2026-02-26 16:27:39 -07:00
parent 39575cb383
commit fd8d582db7
7 changed files with 83 additions and 2 deletions
--- a/docs/constructive_editing_runtime_plan.md
+++ b/docs/constructive_editing_runtime_plan.md
@@ -220,3 +220,6 @@ Planning runtime controls (active):
  - `WSTONE_NATIVE_RAW_TOP_GAP_WEIGHTED_SELECT`
  - `WSTONE_NATIVE_RAW_TOP_GAP_BACKLOG_FILE`
  - scorer `--top-gaps` telemetry (`top_gap_score`)
+- raw candidate search can enforce top-gap uplift as hard policy:
+  - `WSTONE_NATIVE_RAW_TOP_GAP_REQUIRE_UPLIFT`
+  - failure code `18` when no weighted uplift is achieved
--- a/docs/generator_readiness_gap_registry_2026-02-26.md
+++ b/docs/generator_readiness_gap_registry_2026-02-26.md
@@ -47,7 +47,7 @@ This is the canonical dated registry for "not production-ready" generator gaps.
 | GR-018 | Performance/security/rollout constrained refactor enforcement gap | `docs/gap_hunt_fullstack_multifile_2026-02-26.md`, `logs/taskitem_runs/challenging_fullstack_multifile_20260226_r5/results.jsonl` | `partial` | Hard checks now enforce migration rollback + data-loss policy, security deny-by-default, SLO p95 presence, and rollout staged+abort policy. Enforcement is contract-level; generator capability under these constraints is still weak in C++ AB path. | Constraint-aware generation follow-up |
 | GR-019 | Parity-blocked readiness load (gating without capability closure) | `logs/taskitem_runs/challenging_fullstack_multifile_20260226_r7/summary.json`, `logs/taskitem_runs/challenging_subset_prod_20260226_r7/summary.json`, `docs/sprint225_227_execution_tracker_2026-02-26.md` | `partial` | Sprint 225-227 reduced blocked parity load from `6` to `0` on both tracked hard catalogs while keeping unresolved divergence at `0`. This closes immediate safety debt for current corpora, but robustness is still contingent on pattern-driven repair classes. | Generalize repairs beyond queue-shaped transpile outputs |
 | GR-020 | Semantic fallback overuse masks weak native decomposition | `logs/taskitem_runs/TEST_ONLY_sprint236_semantic_fallback_audit_20260226/semantic_fallback_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint237_semantic_fallback_gate_fail_20260226/semantic_fallback_budget_gate.json`, `logs/taskitem_runs/TEST_ONLY_sprint238_native_gate_fail_20260226.json`, `logs/taskitem_runs/TEST_ONLY_sprint239_semantic_fallback_audit_20260226/semantic_fallback_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint240_retry_20260226_145631/00_summary.json`, `docs/sprint236_execution_tracker_2026-02-26.md`, `docs/sprint237_execution_tracker_2026-02-26.md`, `docs/sprint238_execution_tracker_2026-02-26.md`, `docs/sprint239_execution_tracker_2026-02-26.md`, `docs/sprint240_execution_tracker_2026-02-26.md` | `partial` | Sprint 236 added deterministic fallback-gap auditing with tool + constraint metadata. Sprint 237 added fallback-budget hard gate (`max-fallback-rate`) and produced expected fail/pass artifacts. Sprint 238 added native decomposition hard gate in pipeline (`min task count`, `min semantic signal count`) so weak native generation can be blocked before fallback masking. Sprint 239 added native reason enrichment and improved semantic signal density (`0 -> 6`). Sprint 240 added native decomposition retry with explicit minimum-task policy; on current sample retry attempted but did not improve depth (`2 -> 2`). | Native decomposition task-depth upgrade (increase native task granularity beyond 2) |
-| GR-021 | Impact-specific native decomposition coverage not enforced uniformly | `docs/native_decomposition_impact_list_2026-02-26.md`, `tools/mcp/profiles/native_decomposition_impact_profiles.json`, `logs/taskitem_runs/TEST_ONLY_sprint241_fullstack_impact_20260226_150416/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint241_native_impact_aggregate_20260226/native_impact_coverage_aggregate.json`, `logs/taskitem_runs/TEST_ONLY_sprint242_impact_remediation_loop_20260226/remediation_loop_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint243_impact_remediation_tasks_loop_20260226_r2/remediation_loop_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_20260226_151651/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151709/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint245_intrinsic_20260226_151835/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint246_multishot_20260226_153033/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint246_multishot_enforce_20260226_153045/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint247_singleshot_20260226_153230/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint247_singleshot_enforce_20260226_153241/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint248_rawsearch_20260226_153903/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint249_rawguard_20260226_154028/02ae_raw_candidate_search.json`, `logs/taskitem_runs/TEST_ONLY_sprint250_closure_ladder_20260226/closure_ladder_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint251_rawvariants_20260226_154355/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint252_closure_ladder_policy_skip2_20260226/closure_ladder_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint253_closure_ladder_batch_20260226/closure_ladder_batch_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint254_closure_ladder_batch_20260226_r2/raw_gap_backlog.json`, `logs/taskitem_runs/TEST_ONLY_sprint255_rawharden_20260226_161924/00_summary.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162423/00_summary.json` | `partial` | Sprint 241 introduced impact profiles/gates; 242-243 remediation loops; 244 first-pass autofill; 245 intrinsic constraints only (no uplift); 246 multishot closure; 247 single-shot shaping closure; 248 raw candidate search no uplift; 249 no-uplift guardrail; 250 closure ladder; 251 richer raw variants no uplift; 252 history-aware ladder routing; 253 batch ladder analytics; 254 raw gap backlog synthesis from `raw_only` attempts identifies top missing raw signals; 255 adds first-pass raw top-gap hardening that closes hard-sample profile coverage (`failing_profile_count 7 -> 0`) by injecting missing ops/contracts/reasons and minimum task depth; 256 adds top-gap weighted candidate selection telemetry and tie-break policy, but measured sample still shows no intrinsic raw uplift (`selected_variant=0`). Residual gap remains in intrinsic raw generator quality because coverage is still recovered primarily via post-generation hardening/shaping paths. | Add intrinsic raw generation hard gate requiring minimum top-gap score uplift (or fail fast) before promoting raw-only path |
+| GR-021 | Impact-specific native decomposition coverage not enforced uniformly | `docs/native_decomposition_impact_list_2026-02-26.md`, `tools/mcp/profiles/native_decomposition_impact_profiles.json`, `logs/taskitem_runs/TEST_ONLY_sprint241_fullstack_impact_20260226_150416/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint241_native_impact_aggregate_20260226/native_impact_coverage_aggregate.json`, `logs/taskitem_runs/TEST_ONLY_sprint242_impact_remediation_loop_20260226/remediation_loop_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint243_impact_remediation_tasks_loop_20260226_r2/remediation_loop_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_20260226_151651/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151709/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint245_intrinsic_20260226_151835/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint246_multishot_20260226_153033/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint246_multishot_enforce_20260226_153045/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint247_singleshot_20260226_153230/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint247_singleshot_enforce_20260226_153241/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint248_rawsearch_20260226_153903/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint249_rawguard_20260226_154028/02ae_raw_candidate_search.json`, `logs/taskitem_runs/TEST_ONLY_sprint250_closure_ladder_20260226/closure_ladder_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint251_rawvariants_20260226_154355/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint252_closure_ladder_policy_skip2_20260226/closure_ladder_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint253_closure_ladder_batch_20260226/closure_ladder_batch_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint254_closure_ladder_batch_20260226_r2/raw_gap_backlog.json`, `logs/taskitem_runs/TEST_ONLY_sprint255_rawharden_20260226_161924/00_summary.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162423/00_summary.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162633/02ae_raw_candidate_search.json` | `partial` | Sprint 241 introduced impact profiles/gates; 242-243 remediation loops; 244 first-pass autofill; 245 intrinsic constraints only (no uplift); 246 multishot closure; 247 single-shot shaping closure; 248 raw candidate search no uplift; 249 no-uplift guardrail; 250 closure ladder; 251 richer raw variants no uplift; 252 history-aware ladder routing; 253 batch ladder analytics; 254 raw gap backlog synthesis from `raw_only` attempts identifies top missing raw signals; 255 adds first-pass raw top-gap hardening that closes hard-sample profile coverage (`failing_profile_count 7 -> 0`) by injecting missing ops/contracts/reasons and minimum task depth; 256 adds top-gap weighted candidate selection telemetry and tie-break policy; 257 adds hard fail policy when top-gap uplift is required but absent (`exit 18`). Residual gap remains intrinsic: raw generation still fails to produce uplift on this sample without hardening/shaping overlays. | Add intrinsic raw requirement synthesis loop that explicitly targets top weighted missing signals before raw generation retries |

 ## What Was Covered Today (Sprints 175-184)

--- a/docs/progress_log_2026-02-26.md
+++ b/docs/progress_log_2026-02-26.md
@@ -427,3 +427,17 @@
 - Current measured result on hard sample:
  - no intrinsic raw uplift yet (`selected_variant=0`, `best_failing_profile_count=1`)
  - scorer top-gap telemetry emitted and usable for ranking policy.
+
+## Sprint 257 Added (Same Day)
+
+- Added top-gap uplift hard gate in raw candidate search:
+  - `WSTONE_NATIVE_RAW_TOP_GAP_REQUIRE_UPLIFT`
+  - exit code `18` on missing weighted mode config or no top-gap uplift
+- Raw search summary now includes:
+  - `top_gap_require_uplift`
+- Dated validation artifacts:
+  - pass (gate OFF): `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162632/00_summary.json`
+  - fail (gate ON): `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162633/02ae_raw_candidate_search.json`
+- Current measured result on hard sample:
+  - `baseline_top_gap_score=0`, `best_top_gap_score=0`
+  - run blocked correctly when uplift requirement is enabled.
--- a/docs/sprint257_execution_tracker_2026-02-26.md
+++ b/docs/sprint257_execution_tracker_2026-02-26.md
@@ -0,0 +1,33 @@
+# Sprint 257 Execution Tracker - 2026-02-26
+
+## Scope
+- `sprint257_plan.md`
+
+## Implemented
+
+Pipeline gating enhancement in `tools/mcp/run_sprint_taskitem_pipeline.sh`:
+- Added:
+  - `WSTONE_NATIVE_RAW_TOP_GAP_REQUIRE_UPLIFT`
+- Raw candidate search now hard-fails with exit code `18` when:
+  - uplift is required but weighted top-gap mode is not configured (`WSTONE_NATIVE_RAW_TOP_GAP_WEIGHTED_SELECT=1` + valid backlog file), or
+  - `best_top_gap_score <= baseline_top_gap_score`
+- Raw search summary now emits:
+  - `top_gap_require_uplift`
+
+## Validation Artifacts
+
+Gate OFF (expected pass):
+- `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162632/00_summary.json`
+
+Gate ON (expected fail):
+- `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162633/02ae_raw_candidate_search.json`
+- command exit code: `18`
+
+Observed result on hard sample:
+- `baseline_top_gap_score=0`
+- `best_top_gap_score=0`
+- with required uplift enabled, run blocked as designed.
+
+## Explicit Completion Signal
+
+- Sprint 257: `DONE` (implemented + enforced no-uplift guard for top-gap policy)