From 597fe4ededcdbefc31cad4ba43e9b55422741273 Mon Sep 17 00:00:00 2001 From: Bill Date: Thu, 26 Feb 2026 17:04:24 -0700 Subject: [PATCH] Add raw score/gate parity packet and enforcement (sprint 265) --- docs/constructive_editing_runtime_plan.md | 3 ++ ...rator_readiness_gap_registry_2026-02-26.md | 2 +- docs/progress_log_2026-02-26.md | 12 +++++++ .../sprint265_execution_tracker_2026-02-26.md | 33 +++++++++++++++++++ editor/src/Sprint265IntegrationSummary.h | 6 ++++ sprint265_plan.md | 10 ++++++ tools/mcp/run_sprint_taskitem_pipeline.sh | 27 +++++++++++++++ 7 files changed, 92 insertions(+), 1 deletion(-) create mode 100644 docs/sprint265_execution_tracker_2026-02-26.md create mode 100644 editor/src/Sprint265IntegrationSummary.h create mode 100644 sprint265_plan.md diff --git a/docs/constructive_editing_runtime_plan.md b/docs/constructive_editing_runtime_plan.md index 2a67dd2..9cfcf82 100644 --- a/docs/constructive_editing_runtime_plan.md +++ b/docs/constructive_editing_runtime_plan.md @@ -253,3 +253,6 @@ Planning runtime controls (active): - `native_raw_structural_projector` - raw candidate selection now persists selected tasks into generation artifacts for gate parity: - keeps `native_raw_candidate_search` and `native_impact_coverage` on the same task set +- raw score/gate parity can be emitted and hard-enforced: + - `native_raw_score_gate_parity` + - `WSTONE_NATIVE_RAW_SCORE_GATE_PARITY_ENFORCE` diff --git a/docs/generator_readiness_gap_registry_2026-02-26.md b/docs/generator_readiness_gap_registry_2026-02-26.md index aa006de..d11669a 100644 --- 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`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162633/02ae_raw_candidate_search.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162924/01e_raw_top_gap_requirements_report.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163148/02af_raw_adaptive_retry_score.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163556/02ae_raw_signal_targeted_variants.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163855/01f_raw_intrinsic_prompt_pack_report.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165430/01g_raw_template_control_pack_report.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165746/02ae_candidate_0_projected_report.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_170014/06_native_impact_coverage.json` | `partial` | Sprint 241-262 established profile gating plus multiple intrinsic guidance paths; sprint 263 added deterministic structural projection before scoring and showed uplift in score telemetry; sprint 264 aligned score/gate parity by persisting selected raw candidate tasks into generation artifacts. On the hard sample with projector ON, both score and gate now pass consistently (`best_failing_profile_count=0`, `native_impact_coverage.failing_profile_count=0`, task_count `6`). Residual risk is breadth: closure is validated on this hard sample path, not yet proven across broader hard catalogs. | Batch-validate structural projector + parity path across challenging catalogs and add hard fail when score/gate diverge | +| 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`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_162924/01e_raw_top_gap_requirements_report.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163148/02af_raw_adaptive_retry_score.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163556/02ae_raw_signal_targeted_variants.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163855/01f_raw_intrinsic_prompt_pack_report.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165430/01g_raw_template_control_pack_report.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165746/02ae_candidate_0_projected_report.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_170014/06_native_impact_coverage.json`, `logs/taskitem_runs/01a_fallback_intake_spec_20260226_170301/00_summary.json` | `partial` | Sprint 241-262 established profile gating plus multiple intrinsic guidance paths; sprint 263 added deterministic structural projection before scoring; sprint 264 aligned score/gate parity by persisting selected raw candidate tasks into generation artifacts; sprint 265 added explicit `native_raw_score_gate_parity` packet and enforcement mode. On the hard sample with projector ON, score and gate both pass and parity packet reports `pass=true` under enforce mode. Residual risk is breadth: this closure is proven on the hard sample path but not yet validated across broader challenging catalogs. | Batch-validate projector+parity path across challenging catalogs and promote parity enforcement to default when stability is confirmed | ## What Was Covered Today (Sprints 175-184) diff --git a/docs/progress_log_2026-02-26.md b/docs/progress_log_2026-02-26.md index fef706c..3150388 100644 --- a/docs/progress_log_2026-02-26.md +++ b/docs/progress_log_2026-02-26.md @@ -556,3 +556,15 @@ - `best_failing_profile_count=0` - `native_impact_coverage.failing_profile_count=0` - scorer and gate are aligned. + +## Sprint 265 Added (Same Day) + +- Added explicit score/gate parity telemetry + enforcement: + - `WSTONE_NATIVE_RAW_SCORE_GATE_PARITY_ENFORCE` + - summary packet: + - `native_raw_score_gate_parity` +- Dated validation artifact: + - `logs/taskitem_runs/01a_fallback_intake_spec_20260226_170301/00_summary.json` +- Current measured result on hard sample: + - parity packet reports `pass=true` + - enforcement enabled and run succeeds (`rc=0`). diff --git a/docs/sprint265_execution_tracker_2026-02-26.md b/docs/sprint265_execution_tracker_2026-02-26.md new file mode 100644 index 0000000..f9e4da8 --- /dev/null +++ b/docs/sprint265_execution_tracker_2026-02-26.md @@ -0,0 +1,33 @@ +# Sprint 265 Execution Tracker - 2026-02-26 + +## Scope +- `sprint265_plan.md` + +## Implemented + +Pipeline parity packet/enforcement in `tools/mcp/run_sprint_taskitem_pipeline.sh`: +- Added: + - `WSTONE_NATIVE_RAW_SCORE_GATE_PARITY_ENFORCE` +- Added summary packet: + - `native_raw_score_gate_parity` + - `enabled` + - `pass` + - `raw_failing_profile_count` + - `gate_failing_profile_count` +- Enforcement behavior: + - when enabled, pipeline exits `19` if raw score and coverage gate diverge. + +## Validation Artifacts + +Parity-enforced run: +- `logs/taskitem_runs/01a_fallback_intake_spec_20260226_170301/00_summary.json` + +Observed result on hard sample: +- `native_raw_candidate_search.best_failing_profile_count=0` +- `native_impact_coverage.failing_profile_count=0` +- `native_raw_score_gate_parity.pass=true` +- enforcement mode enabled and run succeeded (`rc=0`) + +## Explicit Completion Signal + +- Sprint 265: `DONE` (implemented + validated parity enforcement) diff --git a/editor/src/Sprint265IntegrationSummary.h b/editor/src/Sprint265IntegrationSummary.h new file mode 100644 index 0000000..feb9374 --- /dev/null +++ b/editor/src/Sprint265IntegrationSummary.h @@ -0,0 +1,6 @@ +#pragma once + +// Sprint 265 integration summary: +// - Added native_raw_score_gate_parity telemetry packet. +// - Added optional hard-fail policy for score/gate divergence. +// - Parity enforcement now protects against silent drift between raw scorer and coverage gate. diff --git a/sprint265_plan.md b/sprint265_plan.md new file mode 100644 index 0000000..938b776 --- /dev/null +++ b/sprint265_plan.md @@ -0,0 +1,10 @@ +# Sprint 265 Plan: Raw Score/Gate Parity Packet and Enforcement + +## Goal +Make raw-score vs coverage-gate agreement a first-class runtime invariant with explicit telemetry and optional hard-fail enforcement. + +## Steps +- Step 2372: Add native raw score/gate parity packet in pipeline summary. +- Step 2373: Add enforcement control that fails on divergence. +- Step 2374: Validate parity enforcement on hard sample with projector path. +- Step 2375: Add `Sprint265IntegrationSummary.h` and execution tracker. diff --git a/tools/mcp/run_sprint_taskitem_pipeline.sh b/tools/mcp/run_sprint_taskitem_pipeline.sh index c8f8c43..fa8bbfd 100755 --- a/tools/mcp/run_sprint_taskitem_pipeline.sh +++ b/tools/mcp/run_sprint_taskitem_pipeline.sh @@ -42,6 +42,7 @@ NATIVE_DECOMP_TARGET_MIN_TASKS="${WSTONE_NATIVE_DECOMP_TARGET_MIN_TASKS:-5}" NATIVE_IMPACT_COVERAGE_GATE="${WSTONE_NATIVE_IMPACT_COVERAGE_GATE:-0}" NATIVE_IMPACT_COVERAGE_ENFORCE="${WSTONE_NATIVE_IMPACT_COVERAGE_ENFORCE:-0}" NATIVE_IMPACT_COVERAGE_PROFILES="${WSTONE_NATIVE_IMPACT_COVERAGE_PROFILES:-$ROOT_DIR/tools/mcp/profiles/native_decomposition_impact_profiles.json}" +NATIVE_RAW_SCORE_GATE_PARITY_ENFORCE="${WSTONE_NATIVE_RAW_SCORE_GATE_PARITY_ENFORCE:-0}" NATIVE_PROFILE_AUTOFILL="${WSTONE_NATIVE_PROFILE_AUTOFILL:-0}" NATIVE_PROFILE_AUTOFILL_MAX_TASKS="${WSTONE_NATIVE_PROFILE_AUTOFILL_MAX_TASKS:-12}" NATIVE_INTRINSIC_BOOST="${WSTONE_NATIVE_INTRINSIC_BOOST:-0}" @@ -124,6 +125,7 @@ NATIVE_DECOMP_GATE_JSON='{}' NATIVE_REASON_ENRICHMENT_JSON='{}' NATIVE_DECOMP_RETRY_JSON='{}' NATIVE_IMPACT_COVERAGE_JSON='{}' +NATIVE_RAW_SCORE_GATE_PARITY_JSON='{}' NATIVE_PROFILE_AUTOFILL_JSON='{}' NATIVE_INTRINSIC_BOOST_JSON='{}' NATIVE_SINGLESHOT_PROFILE_SHAPE_JSON='{}' @@ -1160,6 +1162,31 @@ if [[ "$NATIVE_IMPACT_COVERAGE_GATE" == "1" ]]; then SUMMARY_JSON="$(printf '%s' "$SUMMARY_JSON" | jq --argjson nic "$NATIVE_IMPACT_COVERAGE_JSON" '.native_impact_coverage = $nic')" fi +if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" && "$NATIVE_IMPACT_COVERAGE_GATE" == "1" ]]; then + raw_fail_count="$(printf '%s' "$NATIVE_RAW_CANDIDATE_SEARCH_JSON" | jq '.best_failing_profile_count // null')" + gate_fail_count="$(printf '%s' "$NATIVE_IMPACT_COVERAGE_JSON" | jq '.failing_profile_count // null')" + parity_pass=false + if [[ "$raw_fail_count" == "$gate_fail_count" ]]; then + parity_pass=true + fi + NATIVE_RAW_SCORE_GATE_PARITY_JSON="$(jq -nc \ + --argjson enabled true \ + --argjson pass "$parity_pass" \ + --argjson raw_failing_profile_count "$raw_fail_count" \ + --argjson gate_failing_profile_count "$gate_fail_count" \ + '{enabled:$enabled, pass:$pass, raw_failing_profile_count:$raw_failing_profile_count, gate_failing_profile_count:$gate_failing_profile_count}')" + SUMMARY_JSON="$(printf '%s' "$SUMMARY_JSON" | jq --argjson p "$NATIVE_RAW_SCORE_GATE_PARITY_JSON" '.native_raw_score_gate_parity = $p')" + if [[ "$NATIVE_RAW_SCORE_GATE_PARITY_ENFORCE" == "1" && "$parity_pass" != "true" ]]; then + printf '%s\n' "$SUMMARY_JSON" > "$OUT_DIR/00_summary.json" + echo "error: raw score/gate parity check failed" >&2 + echo "error: raw_failing_profile_count=$raw_fail_count gate_failing_profile_count=$gate_fail_count" >&2 + exit 19 + fi +else + NATIVE_RAW_SCORE_GATE_PARITY_JSON='{"enabled":false}' + SUMMARY_JSON="$(printf '%s' "$SUMMARY_JSON" | jq --argjson p "$NATIVE_RAW_SCORE_GATE_PARITY_JSON" '.native_raw_score_gate_parity = $p')" +fi + if [[ "$CALIBRATE_AFTER_RUN" == "1" ]]; then CALIBRATION_OUT_DIR="$OUT_DIR/calibration" CALIBRATION_JSON="$(python3 "$ROOT_DIR/tools/mcp/analyze_taskitem_calibration.py" \