diff --git a/docs/constructive_editing_runtime_plan.md b/docs/constructive_editing_runtime_plan.md index 03974a0..d17d72f 100644 --- a/docs/constructive_editing_runtime_plan.md +++ b/docs/constructive_editing_runtime_plan.md @@ -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 `sprint244_plan.md` +- `sprint232_plan.md` to `sprint245_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: @@ -185,3 +185,6 @@ Planning runtime controls (active): - `WSTONE_NATIVE_PROFILE_AUTOFILL` - `WSTONE_NATIVE_PROFILE_AUTOFILL_MAX_TASKS` - `tools/mcp/synthesize_native_profile_autofill_tasks.py` +- intrinsic first-pass boost can inject profile-derived decomposition constraints: + - `WSTONE_NATIVE_INTRINSIC_BOOST` + - `tools/mcp/synthesize_native_intrinsic_boost_requirements.py` diff --git a/docs/generator_readiness_gap_registry_2026-02-26.md b/docs/generator_readiness_gap_registry_2026-02-26.md index 38ac373..f54e6a3 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` | `partial` | Sprint 241 added one-by-one impact profiles and native impact coverage gate. Sprint 242-243 added remediation synthesis and task-bundle closure loop (`7 -> 0` in one rerun on hard sample). Sprint 244 added first-pass profile autofill in the main pipeline; hard fullstack sample now passes impact coverage in first pass with autofill enabled (`failing_profile_count=0`), and enforced gate fails when autofill is disabled (`failing_profile_count=7`). Remaining gap is intrinsic native generator depth without scaffolding assistance. | Improve intrinsic first-pass native decomposition quality so profile closure does not rely on synthetic autofill tasks | +| 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` | `partial` | Sprint 241 added one-by-one impact profiles and native impact coverage gate. Sprint 242-243 added remediation synthesis and task-bundle closure loop (`7 -> 0` in one rerun on hard sample). Sprint 244 added first-pass profile autofill in the main pipeline; hard sample passes with autofill (`failing_profile_count=0`) and fails without it (`7`). Sprint 245 added intrinsic first-pass boost constraints, but no uplift was observed on hard sample (`7 -> 7`, task count `2 -> 2`). Remaining gap is intrinsic native decomposition quality without synthetic task scaffolding. | Improve intrinsic first-pass native decomposition quality so profile closure does not rely on synthetic autofill tasks | ## 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 2ea9387..6a2b2be 100644 --- a/docs/progress_log_2026-02-26.md +++ b/docs/progress_log_2026-02-26.md @@ -248,3 +248,17 @@ - Enforced gate behavior verified: - pass with autofill ON: `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151709/00_summary.json` - fail with autofill OFF: `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151710/06_native_impact_coverage.json` + +## Sprint 245 Added (Same Day) + +- Added intrinsic first-pass decomposition boost path: + - `tools/mcp/synthesize_native_intrinsic_boost_requirements.py` + - `WSTONE_NATIVE_INTRINSIC_BOOST` + - summary packet: `native_intrinsic_boost` +- A/B with autofill disabled on hard fullstack sample: + - OFF: `logs/taskitem_runs/TEST_ONLY_sprint245_intrinsic_20260226_151834/00_summary.json` + - ON: `logs/taskitem_runs/TEST_ONLY_sprint245_intrinsic_20260226_151835/00_summary.json` +- Current measured result: + - `failing_profile_count 7 -> 7` + - `task_count 2 -> 2` + - no intrinsic uplift on this sample (signal retained for next tranche). diff --git a/docs/sprint245_execution_tracker_2026-02-26.md b/docs/sprint245_execution_tracker_2026-02-26.md new file mode 100644 index 0000000..05c61e2 --- /dev/null +++ b/docs/sprint245_execution_tracker_2026-02-26.md @@ -0,0 +1,33 @@ +# Sprint 245 Execution Tracker - 2026-02-26 + +## Scope +- `sprint245_plan.md` + +## Implemented + +New tool: +- `tools/mcp/synthesize_native_intrinsic_boost_requirements.py` + - Builds profile-derived intrinsic decomposition constraints from active profiles. + +Pipeline integration in `tools/mcp/run_sprint_taskitem_pipeline.sh`: +- Added `WSTONE_NATIVE_INTRINSIC_BOOST` (default `0`). +- Writes intrinsic requirements artifact when enabled: + - `01d_native_intrinsic_boost_requirements.json` +- Appends intrinsic requirements into `NORMALIZED_REQS` pre-generation. +- Summary now includes: + - `native_intrinsic_boost` + +## A/B Validation (autofill disabled) + +- intrinsic OFF: + - `logs/taskitem_runs/TEST_ONLY_sprint245_intrinsic_20260226_151834/00_summary.json` +- intrinsic ON: + - `logs/taskitem_runs/TEST_ONLY_sprint245_intrinsic_20260226_151835/00_summary.json` + +Observed result on hard fullstack sample: +- `native_impact_coverage.failing_profile_count: 7 -> 7` +- `taskitems.task_count: 2 -> 2` + +## Explicit Completion Signal + +- Sprint 245: `DONE` (implemented + measured; no closure uplift on this sample) diff --git a/editor/src/Sprint245IntegrationSummary.h b/editor/src/Sprint245IntegrationSummary.h new file mode 100644 index 0000000..57cd5bf --- /dev/null +++ b/editor/src/Sprint245IntegrationSummary.h @@ -0,0 +1,6 @@ +#pragma once + +// Sprint 245 integration summary: +// - Added intrinsic first-pass decomposition boost requirement synthesis. +// - Pipeline can inject profile-derived intrinsic constraints before generation. +// - A/B evidence currently shows no first-pass closure improvement on hard fullstack sample. diff --git a/sprint245_plan.md b/sprint245_plan.md new file mode 100644 index 0000000..99f57f5 --- /dev/null +++ b/sprint245_plan.md @@ -0,0 +1,11 @@ +# Sprint 245 Plan: Intrinsic First-Pass Decomposition Boost + +## Goal +Improve native first-pass decomposition without synthetic task injection by adding profile-derived intrinsic decomposition constraints before generation. + +## Steps +- Step 2269: Add intrinsic boost requirement synthesizer from active impact profiles. +- Step 2270: Integrate optional intrinsic boost requirement injection into pipeline pre-generation path. +- Step 2271: Emit intrinsic boost telemetry in summary. +- Step 2272: Run A/B with autofill disabled to measure intrinsic-only effect. +- Step 2273: Add `Sprint245IntegrationSummary.h` and execution tracker. diff --git a/tools/mcp/run_sprint_taskitem_pipeline.sh b/tools/mcp/run_sprint_taskitem_pipeline.sh index 528e7ed..004b0b8 100755 --- a/tools/mcp/run_sprint_taskitem_pipeline.sh +++ b/tools/mcp/run_sprint_taskitem_pipeline.sh @@ -44,6 +44,7 @@ NATIVE_IMPACT_COVERAGE_ENFORCE="${WSTONE_NATIVE_IMPACT_COVERAGE_ENFORCE:-0}" NATIVE_IMPACT_COVERAGE_PROFILES="${WSTONE_NATIVE_IMPACT_COVERAGE_PROFILES:-$ROOT_DIR/tools/mcp/profiles/native_decomposition_impact_profiles.json}" NATIVE_PROFILE_AUTOFILL="${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}" EXTRA_NORMALIZED_REQUIREMENTS_FILE="${WSTONE_EXTRA_NORMALIZED_REQUIREMENTS_FILE:-}" EXTRA_TASKS_FILE="${WSTONE_EXTRA_TASKS_FILE:-}" CAPABILITY_SIGNALS_JSON="${WSTONE_CAPABILITY_SIGNALS_JSON:-}" @@ -102,6 +103,7 @@ NATIVE_REASON_ENRICHMENT_JSON='{}' NATIVE_DECOMP_RETRY_JSON='{}' NATIVE_IMPACT_COVERAGE_JSON='{}' NATIVE_PROFILE_AUTOFILL_JSON='{}' +NATIVE_INTRINSIC_BOOST_JSON='{}' EXTRA_NORMALIZED_REQUIREMENTS_JSON='[]' EXTRA_TASKS_JSON='[]' if [[ "$SEMANTIC_PLANNING_BRIDGE" == "1" ]]; then @@ -305,6 +307,17 @@ if [[ -n "$EXTRA_NORMALIZED_REQUIREMENTS_FILE" ]]; then EXTRA_NORMALIZED_REQUIREMENTS_JSON="$(cat "$EXTRA_NORMALIZED_REQUIREMENTS_FILE")" NORMALIZED_REQS="$(jq -nc --argjson base "$NORMALIZED_REQS" --argjson extra "$EXTRA_NORMALIZED_REQUIREMENTS_JSON" '$base + $extra')" fi +if [[ "$NATIVE_INTRINSIC_BOOST" == "1" ]]; then + python3 "$ROOT_DIR/tools/mcp/synthesize_native_intrinsic_boost_requirements.py" \ + --spec "$INPUT_FILE" \ + --profiles "$NATIVE_IMPACT_COVERAGE_PROFILES" \ + --out "$OUT_DIR/01d_native_intrinsic_boost_requirements.json" >/dev/null + INTRINSIC_REQS_JSON="$(cat "$OUT_DIR/01d_native_intrinsic_boost_requirements.json")" + NORMALIZED_REQS="$(jq -nc --argjson base "$NORMALIZED_REQS" --argjson intrinsic "$INTRINSIC_REQS_JSON" '$base + $intrinsic')" + NATIVE_INTRINSIC_BOOST_JSON="$(jq -nc --argjson reqs "$INTRINSIC_REQS_JSON" '{enabled:true, requirement_count:($reqs|length)}')" +else + NATIVE_INTRINSIC_BOOST_JSON='{"enabled":false,"requirement_count":0}' +fi CONFLICTS="$(printf '%s' "$INTAKE_JSON" | jq '.conflicts // []')" GEN_ARGS="$(jq -nc --argjson nr "$NORMALIZED_REQS" --argjson cf "$CONFLICTS" --arg strict "$STRICT_EXECUTION_CONTRACT" \ '{normalizedRequirements:$nr,conflicts:$cf,strictExecutionContract:($strict == "1")}')" @@ -567,6 +580,7 @@ SUMMARY_JSON="$(jq -nc \ --argjson native_reason_enrichment "$NATIVE_REASON_ENRICHMENT_JSON" \ --argjson native_decomposition_retry "$NATIVE_DECOMP_RETRY_JSON" \ --argjson native_profile_autofill "$NATIVE_PROFILE_AUTOFILL_JSON" \ + --argjson native_intrinsic_boost "$NATIVE_INTRINSIC_BOOST_JSON" \ --argjson extra_normalized_requirements "$EXTRA_NORMALIZED_REQUIREMENTS_JSON" \ --argjson extra_tasks "$EXTRA_TASKS_JSON" \ --argjson intake "$INTAKE_JSON" \ @@ -590,6 +604,7 @@ SUMMARY_JSON="$(jq -nc \ native_reason_enrichment: $native_reason_enrichment, native_decomposition_retry: $native_decomposition_retry, native_profile_autofill: $native_profile_autofill, + native_intrinsic_boost: $native_intrinsic_boost, extra_normalized_requirements: $extra_normalized_requirements, extra_tasks: $extra_tasks, intake: { diff --git a/tools/mcp/synthesize_native_intrinsic_boost_requirements.py b/tools/mcp/synthesize_native_intrinsic_boost_requirements.py new file mode 100755 index 0000000..dccb0b0 --- /dev/null +++ b/tools/mcp/synthesize_native_intrinsic_boost_requirements.py @@ -0,0 +1,70 @@ +#!/usr/bin/env python3 +import argparse +import json +from pathlib import Path +from typing import Dict, List + + +def load_json(path: Path): + with path.open("r", encoding="utf-8") as f: + return json.load(f) + + +def write_json(path: Path, obj) -> None: + with path.open("w", encoding="utf-8") as f: + json.dump(obj, f, indent=2, sort_keys=True) + f.write("\n") + + +def activate_profiles(profiles: List[Dict], spec_text: str) -> List[Dict]: + s = spec_text.lower() + out = [] + for p in profiles: + keys = [str(k).lower() for k in (p.get("trigger_keywords") or [])] + if keys and any(k in s for k in keys): + out.append(p) + return out + + +def mk_req(profile: Dict, idx: int) -> Dict: + pid = str(profile.get("id", f"profile_{idx}")) + min_tasks = int(profile.get("min_native_task_count", 0) or 0) + reason_keys = [str(x) for x in (profile.get("required_reason_keywords") or [])] + ops = [str(x) for x in (profile.get("required_prerequisite_ops") or [])] + contract = [str(x) for x in (profile.get("required_execution_contract") or [])] + text = ( + f"intrinsic decomposition policy for {pid}: produce at least {min_tasks} concrete taskitems; " + f"ensure reasons include {', '.join(reason_keys) if reason_keys else 'none'}; " + f"ensure prerequisiteOps include {', '.join(ops) if ops else 'none'}; " + f"ensure executionContract includes {', '.join(contract) if contract else 'none'}." + ) + return { + "requirementId": f"intrinsic-boost-{pid}", + "kind": "constraint", + "normalizedText": text, + "anchor": "native_intrinsic_boost", + "sourceLine": 0, + "ambiguous": False, + } + + +def main() -> int: + p = argparse.ArgumentParser(description="Synthesize intrinsic decomposition boost requirements from active impact profiles.") + p.add_argument("--spec", required=True) + p.add_argument("--profiles", required=True) + p.add_argument("--out", required=True) + args = p.parse_args() + + spec_text = Path(args.spec).read_text(encoding="utf-8", errors="ignore") + profiles_doc = load_json(Path(args.profiles)) + profiles = list(profiles_doc.get("profiles") or []) + active = activate_profiles(profiles, spec_text) + + reqs = [mk_req(pf, i) for i, pf in enumerate(active)] + write_json(Path(args.out), reqs) + print(json.dumps({"status": "ok", "active_profile_count": len(active), "requirement_count": len(reqs), "out": args.out}, sort_keys=True)) + return 0 + + +if __name__ == "__main__": + raise SystemExit(main())