From 42c53da5c6f910327733155f181e3581a129af4e Mon Sep 17 00:00:00 2001 From: Bill Date: Thu, 26 Feb 2026 16:37:57 -0700 Subject: [PATCH] Add signal-targeted intrinsic raw variant expansion (sprint 260) --- docs/constructive_editing_runtime_plan.md | 5 + ...rator_readiness_gap_registry_2026-02-26.md | 2 +- docs/progress_log_2026-02-26.md | 16 +++ .../sprint260_execution_tracker_2026-02-26.md | 40 ++++++++ editor/src/Sprint260IntegrationSummary.h | 6 ++ sprint260_plan.md | 12 +++ tools/mcp/run_sprint_taskitem_pipeline.sh | 24 +++++ ...synthesize_raw_signal_targeted_variants.py | 97 +++++++++++++++++++ 8 files changed, 201 insertions(+), 1 deletion(-) create mode 100644 docs/sprint260_execution_tracker_2026-02-26.md create mode 100644 editor/src/Sprint260IntegrationSummary.h create mode 100644 sprint260_plan.md create mode 100644 tools/mcp/synthesize_raw_signal_targeted_variants.py diff --git a/docs/constructive_editing_runtime_plan.md b/docs/constructive_editing_runtime_plan.md index 2010d73..fd59551 100644 --- a/docs/constructive_editing_runtime_plan.md +++ b/docs/constructive_editing_runtime_plan.md @@ -232,3 +232,8 @@ Planning runtime controls (active): - `WSTONE_NATIVE_RAW_TOP_GAP_ADAPTIVE_RETRY` - `WSTONE_NATIVE_RAW_TOP_GAP_RETRY_SIGNALS` - `native_raw_adaptive_retry` +- raw candidate search can expand intrinsic exploration with signal-targeted variants: + - `tools/mcp/synthesize_raw_signal_targeted_variants.py` + - `WSTONE_NATIVE_RAW_SIGNAL_TARGETED_VARIANTS` + - `WSTONE_NATIVE_RAW_SIGNAL_TARGETED_MAX_VARIANTS` + - `native_raw_signal_targeted_variants` diff --git a/docs/generator_readiness_gap_registry_2026-02-26.md b/docs/generator_readiness_gap_registry_2026-02-26.md index 913c770..e2957ef 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` | `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`); 258 injects backlog-driven top-gap normalized requirements before raw generation; 259 adds adaptive retry with expanded top-gap requirements and deterministic retry scoring. Measured intrinsic output still shows no uplift on this sample (`retry_top_gap_score=0`, `retry_fail=1`, `applied=false`). | Add model/prompt-level intrinsic generation intervention keyed by missing-signal classes (beyond requirement text injection alone) | +| 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` | `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`); 258 injects backlog-driven top-gap normalized requirements before raw generation; 259 adds adaptive retry with expanded top-gap requirements and deterministic retry scoring; 260 adds signal-targeted variant expansion keyed to missing-signal classes and increases intrinsic search breadth (`available_variants 2 -> 8`). Measured intrinsic output still shows no uplift on this sample (`best_top_gap_score=0`, `failing_profile_count=1`). | Add model/prompt-level intrinsic generation intervention keyed by missing-signal classes (beyond requirement text injection alone) | ## 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 02b701a..e41756a 100644 --- a/docs/progress_log_2026-02-26.md +++ b/docs/progress_log_2026-02-26.md @@ -474,3 +474,19 @@ - Current measured result on hard sample: - retry attempted and succeeded operationally - no intrinsic uplift (`retry_top_gap_score=0`, `retry_fail=1`, `applied=false`). + +## Sprint 260 Added (Same Day) + +- Added signal-targeted intrinsic variant expansion: + - `tools/mcp/synthesize_raw_signal_targeted_variants.py` + - pipeline controls: + - `WSTONE_NATIVE_RAW_SIGNAL_TARGETED_VARIANTS` + - `WSTONE_NATIVE_RAW_SIGNAL_TARGETED_MAX_VARIANTS` + - summary packet: + - `native_raw_signal_targeted_variants` +- Dated A/B artifacts: + - OFF: `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163629/00_summary.json` + - ON: `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163556/00_summary.json` +- Current measured result on hard sample: + - search breadth increased (`available_variants 2 -> 8`) + - intrinsic outcome unchanged (`selected_variant=0`, `best_top_gap_score=0`, `failing_profile_count=1`). diff --git a/docs/sprint260_execution_tracker_2026-02-26.md b/docs/sprint260_execution_tracker_2026-02-26.md new file mode 100644 index 0000000..f8b34e6 --- /dev/null +++ b/docs/sprint260_execution_tracker_2026-02-26.md @@ -0,0 +1,40 @@ +# Sprint 260 Execution Tracker - 2026-02-26 + +## Scope +- `sprint260_plan.md` + +## Implemented + +New tool: +- `tools/mcp/synthesize_raw_signal_targeted_variants.py` + - Reads prioritized missing signals from raw backlog. + - Emits focused and bundled normalized-requirement variants keyed to signal class. + +Pipeline integration in `tools/mcp/run_sprint_taskitem_pipeline.sh`: +- Added: + - `WSTONE_NATIVE_RAW_SIGNAL_TARGETED_VARIANTS` + - `WSTONE_NATIVE_RAW_SIGNAL_TARGETED_MAX_VARIANTS` +- Raw search now optionally merges: + - profile variants (`synthesize_raw_candidate_requirement_variants.py`) + - signal-targeted variants (`synthesize_raw_signal_targeted_variants.py`) +- Added summary packet: + - `native_raw_signal_targeted_variants` + +## Validation Artifacts + +OFF: +- `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163629/00_summary.json` + +ON: +- `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163556/00_summary.json` +- generated signal variant payload: + - `logs/taskitem_runs/01a_fallback_intake_spec_20260226_163556/02ae_raw_signal_targeted_variants.json` + +Observed result on hard sample: +- OFF: `available_variants=2`, `attempted_variants=3`, `selected_variant=0` +- ON: `available_variants=8`, `attempted_variants=8`, `selected_variant=0` +- `best_top_gap_score` remained `0` and `failing_profile_count` remained `1` + +## Explicit Completion Signal + +- Sprint 260: `DONE` (implemented + validated; intrinsic uplift still pending) diff --git a/editor/src/Sprint260IntegrationSummary.h b/editor/src/Sprint260IntegrationSummary.h new file mode 100644 index 0000000..46aa5b9 --- /dev/null +++ b/editor/src/Sprint260IntegrationSummary.h @@ -0,0 +1,6 @@ +#pragma once + +// Sprint 260 integration summary: +// - Added signal-targeted raw variant synthesis from prioritized missing backlog classes. +// - Raw candidate search can merge profile variants with signal-targeted variants. +// - Summary now exposes native_raw_signal_targeted_variants telemetry for intrinsic search analysis. diff --git a/sprint260_plan.md b/sprint260_plan.md new file mode 100644 index 0000000..d5c44c2 --- /dev/null +++ b/sprint260_plan.md @@ -0,0 +1,12 @@ +# Sprint 260 Plan: Signal-Targeted Intrinsic Variant Expansion + +## Goal +Add missing-signal-class-targeted raw requirement variants so intrinsic candidate search explores direct interventions keyed to backlog failure classes. + +## Steps +- Step 2347: Add tool to synthesize raw variants from top missing-signal backlog classes. +- Step 2348: Merge signal-targeted variants with profile-based variants in raw search. +- Step 2349: Add pipeline controls for enabling and sizing signal-targeted variant expansion. +- Step 2350: Emit signal-targeted variant telemetry in summary packet. +- Step 2351: Validate OFF/ON behavior on hard sample. +- Step 2352: Add `Sprint260IntegrationSummary.h` and execution tracker. diff --git a/tools/mcp/run_sprint_taskitem_pipeline.sh b/tools/mcp/run_sprint_taskitem_pipeline.sh index f9f277b..0a41050 100755 --- a/tools/mcp/run_sprint_taskitem_pipeline.sh +++ b/tools/mcp/run_sprint_taskitem_pipeline.sh @@ -53,6 +53,8 @@ NATIVE_RAW_CANDIDATE_SEARCH="${WSTONE_NATIVE_RAW_CANDIDATE_SEARCH:-0}" NATIVE_RAW_CANDIDATE_MAX_VARIANTS="${WSTONE_NATIVE_RAW_CANDIDATE_MAX_VARIANTS:-8}" NATIVE_RAW_CANDIDATE_REQUIRE_UPLIFT="${WSTONE_NATIVE_RAW_CANDIDATE_REQUIRE_UPLIFT:-0}" NATIVE_RAW_HARDEN_TOP_GAPS="${WSTONE_NATIVE_RAW_HARDEN_TOP_GAPS:-0}" +NATIVE_RAW_SIGNAL_TARGETED_VARIANTS="${WSTONE_NATIVE_RAW_SIGNAL_TARGETED_VARIANTS:-0}" +NATIVE_RAW_SIGNAL_TARGETED_MAX_VARIANTS="${WSTONE_NATIVE_RAW_SIGNAL_TARGETED_MAX_VARIANTS:-6}" NATIVE_RAW_TOP_GAP_WEIGHTED_SELECT="${WSTONE_NATIVE_RAW_TOP_GAP_WEIGHTED_SELECT:-0}" NATIVE_RAW_TOP_GAP_BACKLOG_FILE="${WSTONE_NATIVE_RAW_TOP_GAP_BACKLOG_FILE:-}" NATIVE_RAW_TOP_GAP_REQUIRE_UPLIFT="${WSTONE_NATIVE_RAW_TOP_GAP_REQUIRE_UPLIFT:-0}" @@ -123,6 +125,7 @@ NATIVE_SINGLESHOT_PROFILE_SHAPE_JSON='{}' NATIVE_MULTISHOT_JSON='{}' NATIVE_RAW_CANDIDATE_SEARCH_JSON='{}' NATIVE_RAW_HARDENING_JSON='{}' +NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON='{}' NATIVE_RAW_TOP_GAP_REQUIREMENTS_JSON='{}' NATIVE_RAW_ADAPTIVE_RETRY_JSON='{}' INTRINSIC_REQS_JSON='[]' @@ -429,6 +432,24 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then --max-variants "$NATIVE_RAW_CANDIDATE_MAX_VARIANTS" \ --out "$OUT_DIR/02ae_raw_candidate_variants.json" >/dev/null VARIANTS_JSON="$(cat "$OUT_DIR/02ae_raw_candidate_variants.json")" + if [[ "$NATIVE_RAW_SIGNAL_TARGETED_VARIANTS" == "1" && -n "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" && -f "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" ]]; then + python3 "$ROOT_DIR/tools/mcp/synthesize_raw_signal_targeted_variants.py" \ + --top-gaps "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" \ + --max-variants "$NATIVE_RAW_SIGNAL_TARGETED_MAX_VARIANTS" \ + --out "$OUT_DIR/02ae_raw_signal_targeted_variants.json" >/dev/null + signal_variants_count="$(jq '.variant_count // 0' "$OUT_DIR/02ae_raw_signal_targeted_variants.json")" + VARIANTS_JSON="$(jq -nc \ + --argjson base "$VARIANTS_JSON" \ + --argjson sig "$(cat "$OUT_DIR/02ae_raw_signal_targeted_variants.json")" \ + '{status:"ok", active_profile_count:($base.active_profile_count // 0), variant_count:(((($base.variants // [])|length) + (($sig.variants // [])|length))), variants:(($base.variants // []) + ($sig.variants // []))}')" + NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON="$(jq -nc \ + --argjson enabled true \ + --arg backlog_file "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" \ + --argjson variant_count "$signal_variants_count" \ + '{enabled:$enabled, backlog_file:$backlog_file, variant_count:$variant_count}')" + else + NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON='{"enabled":false}' + fi printf '%s\n' "$TASKS" > "$OUT_DIR/02ae_candidate_0_tasks.json" python3 "$ROOT_DIR/tools/mcp/score_native_tasks_profile_coverage.py" \ @@ -589,6 +610,7 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then fi else NATIVE_RAW_CANDIDATE_SEARCH_JSON='{"enabled":false}' + NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON='{"enabled":false}' fi if [[ "$NATIVE_RAW_HARDEN_TOP_GAPS" == "1" ]]; then printf '%s\n' "$TASKS" > "$OUT_DIR/02af_raw_hardening_input_tasks.json" @@ -934,6 +956,7 @@ SUMMARY_JSON="$(jq -nc \ --argjson native_profile_autofill "$NATIVE_PROFILE_AUTOFILL_JSON" \ --argjson native_intrinsic_boost "$NATIVE_INTRINSIC_BOOST_JSON" \ --argjson native_raw_top_gap_requirements "$NATIVE_RAW_TOP_GAP_REQUIREMENTS_JSON" \ + --argjson native_raw_signal_targeted_variants "$NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON" \ --argjson native_raw_candidate_search "$NATIVE_RAW_CANDIDATE_SEARCH_JSON" \ --argjson native_raw_adaptive_retry "$NATIVE_RAW_ADAPTIVE_RETRY_JSON" \ --argjson native_raw_hardening "$NATIVE_RAW_HARDENING_JSON" \ @@ -965,6 +988,7 @@ SUMMARY_JSON="$(jq -nc \ native_profile_autofill: $native_profile_autofill, native_intrinsic_boost: $native_intrinsic_boost, native_raw_top_gap_requirements: $native_raw_top_gap_requirements, + native_raw_signal_targeted_variants: $native_raw_signal_targeted_variants, native_raw_candidate_search: $native_raw_candidate_search, native_raw_adaptive_retry: $native_raw_adaptive_retry, native_raw_hardening: $native_raw_hardening, diff --git a/tools/mcp/synthesize_raw_signal_targeted_variants.py b/tools/mcp/synthesize_raw_signal_targeted_variants.py new file mode 100644 index 0000000..79b87a2 --- /dev/null +++ b/tools/mcp/synthesize_raw_signal_targeted_variants.py @@ -0,0 +1,97 @@ +#!/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 req_from_signal(signal: str, idx: int) -> Dict: + if signal.startswith("missing_prerequisite_op:"): + op = signal.split(":", 1)[1] + txt = f"raw signal-targeted policy: include prerequisite operation `{op}` in concrete tasks where applicable." + elif signal.startswith("missing_execution_contract:"): + field = signal.split(":", 1)[1] + txt = f"raw signal-targeted policy: set executionContract.{field}=true for generated tasks requiring safe deterministic execution." + elif signal.startswith("missing_reason_keyword:"): + key = signal.split(":", 1)[1] + txt = f"raw signal-targeted policy: reasons must explicitly include `{key}` risk/contract intent." + elif signal.startswith("native_task_count<"): + min_count = signal.split("<", 1)[1] + txt = f"raw signal-targeted policy: produce at least {min_count} concrete non-generic taskitems." + else: + txt = f"raw signal-targeted policy: address missing signal `{signal}` with concrete task structure." + return { + "requirementId": f"raw-signal-{idx+1}", + "kind": "constraint", + "normalizedText": txt, + "anchor": "raw_signal_targeted_variant", + "sourceLine": 0, + "ambiguous": False, + } + + +def build_variants(prioritized_missing: List[Dict], max_variants: int) -> List[List[Dict]]: + if max_variants <= 0: + return [] + reqs = [req_from_signal(str(row.get("missing", "")), i) for i, row in enumerate(prioritized_missing) if str(row.get("missing", ""))] + if not reqs: + return [] + + variants: List[List[Dict]] = [] + # Single-signal focused variants. + for r in reqs: + variants.append([r]) + # Pair bundles for cross-signal coupling. + for i in range(0, len(reqs), 2): + variants.append(reqs[i:i + 2]) + # One all-signals compact bundle. + variants.append(reqs[: min(6, len(reqs))]) + + out: List[List[Dict]] = [] + seen = set() + for v in variants: + key = tuple(x.get("requirementId", "") for x in v) + if not key or key in seen: + continue + seen.add(key) + out.append(v) + if len(out) >= max_variants: + break + return out + + +def main() -> int: + p = argparse.ArgumentParser(description="Synthesize raw candidate variants targeted to top missing backlog signals.") + p.add_argument("--top-gaps", required=True) + p.add_argument("--max-variants", type=int, default=6) + p.add_argument("--out", required=True) + args = p.parse_args() + + backlog = load_json(Path(args.top_gaps)) + prioritized = list(backlog.get("prioritized_missing") or []) + variants = build_variants(prioritized, args.max_variants) + + payload = { + "status": "ok", + "input_signal_count": len(prioritized), + "variant_count": len(variants), + "variants": variants, + } + write_json(Path(args.out), payload) + print(json.dumps({"status": "ok", "input_signal_count": len(prioritized), "variant_count": len(variants), "out": args.out}, sort_keys=True)) + return 0 + + +if __name__ == "__main__": + raise SystemExit(main())