From fe85f1b515c1f1ce9b2bd44454024ff36c7e23e6 Mon Sep 17 00:00:00 2001 From: Bill Date: Thu, 26 Feb 2026 16:59:28 -0700 Subject: [PATCH] Add raw structural projector before candidate scoring (sprint 263) --- docs/constructive_editing_runtime_plan.md | 4 + ...rator_readiness_gap_registry_2026-02-26.md | 2 +- docs/progress_log_2026-02-26.md | 18 ++++ .../sprint263_execution_tracker_2026-02-26.md | 46 ++++++++ editor/src/Sprint263IntegrationSummary.h | 6 ++ sprint263_plan.md | 11 ++ tools/mcp/project_raw_candidate_structure.py | 101 ++++++++++++++++++ tools/mcp/run_sprint_taskitem_pipeline.sh | 67 +++++++++++- 8 files changed, 249 insertions(+), 6 deletions(-) create mode 100644 docs/sprint263_execution_tracker_2026-02-26.md create mode 100644 editor/src/Sprint263IntegrationSummary.h create mode 100644 sprint263_plan.md create mode 100644 tools/mcp/project_raw_candidate_structure.py diff --git a/docs/constructive_editing_runtime_plan.md b/docs/constructive_editing_runtime_plan.md index 7c9a8af..7311882 100644 --- a/docs/constructive_editing_runtime_plan.md +++ b/docs/constructive_editing_runtime_plan.md @@ -247,3 +247,7 @@ Planning runtime controls (active): - `WSTONE_NATIVE_RAW_TEMPLATE_CONTROL_PACK` - `WSTONE_NATIVE_RAW_TEMPLATE_CONTROL_MAX_SIGNALS` - `native_raw_template_control_pack` +- raw candidate scoring can evaluate deterministic structural projections pre-score: + - `tools/mcp/project_raw_candidate_structure.py` + - `WSTONE_NATIVE_RAW_STRUCTURAL_PROJECTOR` + - `native_raw_structural_projector` diff --git a/docs/generator_readiness_gap_registry_2026-02-26.md b/docs/generator_readiness_gap_registry_2026-02-26.md index 7deee06..2679494 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` | `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`); 261 adds intrinsic prompt-pack constraint injection keyed to gap signals; 262 adds explicit output-shape template-control pack injection (schema + example + signal mapping) pre-generation. Measured intrinsic output still shows no uplift on this sample (`best_top_gap_score=0`, `failing_profile_count=1`). | Add deterministic post-generation structural projector for raw candidates before scoring (split/normalize schema to enforce missing ops/contracts/reason keywords without full hardening) | +| 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` | `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; 261 adds intrinsic prompt-pack constraints; 262 adds output-shape template-control pack; 263 adds deterministic structural projector before scoring. On hard sample, raw-score telemetry now uplifts (`best_failing_profile_count 1 -> 0`, `best_top_gap_score 0 -> 88`) but final `native_impact_coverage` still reports `1`, exposing scorer/gate parity mismatch. | Align score-native profile checker semantics with native_impact_coverage checker and gate on parity consistency | ## 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 9d88d27..457ac17 100644 --- a/docs/progress_log_2026-02-26.md +++ b/docs/progress_log_2026-02-26.md @@ -524,3 +524,21 @@ - Current measured result on hard sample: - template control injected (`requirement_count=3`, `selected_signal_count=8`) - intrinsic outcome unchanged (`selected_variant=0`, `best_top_gap_score=0`, `failing_profile_count=1`). + +## Sprint 263 Added (Same Day) + +- Added deterministic raw structural projector: + - `tools/mcp/project_raw_candidate_structure.py` + - pipeline control: + - `WSTONE_NATIVE_RAW_STRUCTURAL_PROJECTOR` + - summary packet: + - `native_raw_structural_projector` +- Dated A/B artifacts: + - OFF: `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165737/00_summary.json` + - ON: `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165746/00_summary.json` +- Current measured result on hard sample: + - raw search score uplift under projector: + - `best_failing_profile_count 1 -> 0` + - `best_top_gap_score 0 -> 88` + - `best_task_count 2 -> 6` + - but `native_impact_coverage.failing_profile_count` remained `1`, exposing scorer/gate parity mismatch. diff --git a/docs/sprint263_execution_tracker_2026-02-26.md b/docs/sprint263_execution_tracker_2026-02-26.md new file mode 100644 index 0000000..9e760b5 --- /dev/null +++ b/docs/sprint263_execution_tracker_2026-02-26.md @@ -0,0 +1,46 @@ +# Sprint 263 Execution Tracker - 2026-02-26 + +## Scope +- `sprint263_plan.md` + +## Implemented + +New tool: +- `tools/mcp/project_raw_candidate_structure.py` + - Normalizes raw tasks against top-gap missing-signal classes. + - Fills missing ops/reasons/execution contract fields. + - Expands shallow task sets to gap-indicated minimum count. + +Pipeline integration in `tools/mcp/run_sprint_taskitem_pipeline.sh`: +- Added: + - `WSTONE_NATIVE_RAW_STRUCTURAL_PROJECTOR` +- Raw candidate search now optionally projects: + - baseline candidate (`02ae_candidate_0_projected_tasks.json`) + - each generated candidate variant (`02ae_candidate__projected_tasks.json`) + - adaptive retry candidate when enabled +- Added summary packet: + - `native_raw_structural_projector` + +## Validation Artifacts + +OFF: +- `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165737/00_summary.json` + +ON: +- `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165746/00_summary.json` +- projected artifacts: + - `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165746/02ae_candidate_0_projected_report.json` + - `logs/taskitem_runs/01a_fallback_intake_spec_20260226_165746/02ae_candidate_0_projected_tasks.json` + +Observed result on hard sample: +- Raw search score improved sharply under projector: + - `best_failing_profile_count: 1 -> 0` + - `best_top_gap_score: 0 -> 88` + - `best_task_count: 2 -> 6` +- Residual parity gap: + - `native_impact_coverage.failing_profile_count` remained `1` + - indicates score-tool vs coverage-gate semantics are not yet aligned. + +## Explicit Completion Signal + +- Sprint 263: `DONE` (implemented + validated; uncovered scorer/gate parity gap) diff --git a/editor/src/Sprint263IntegrationSummary.h b/editor/src/Sprint263IntegrationSummary.h new file mode 100644 index 0000000..e7fa0bc --- /dev/null +++ b/editor/src/Sprint263IntegrationSummary.h @@ -0,0 +1,6 @@ +#pragma once + +// Sprint 263 integration summary: +// - Added deterministic raw structural projector for candidate tasks before scoring. +// - Raw candidate scoring path can evaluate projected tasks for baseline, variants, and adaptive retry. +// - Summary now includes native_raw_structural_projector telemetry and projected-variant counts. diff --git a/sprint263_plan.md b/sprint263_plan.md new file mode 100644 index 0000000..c83576f --- /dev/null +++ b/sprint263_plan.md @@ -0,0 +1,11 @@ +# Sprint 263 Plan: Raw Structural Projector Before Scoring + +## Goal +Add a deterministic structural projector for raw candidate tasks before scoring so intrinsic search evaluates schema-normalized candidates (without full post-hardening stage). + +## Steps +- Step 2363: Add raw candidate structural projector tool. +- Step 2364: Apply projector to baseline/candidate/retry raw tasks before scoring. +- Step 2365: Emit structural projector telemetry in summary. +- Step 2366: Validate OFF/ON behavior on hard sample. +- Step 2367: Add `Sprint263IntegrationSummary.h` and execution tracker. diff --git a/tools/mcp/project_raw_candidate_structure.py b/tools/mcp/project_raw_candidate_structure.py new file mode 100644 index 0000000..9e755f7 --- /dev/null +++ b/tools/mcp/project_raw_candidate_structure.py @@ -0,0 +1,101 @@ +#!/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 parse_gap_signals(backlog: Dict): + missing = [str(x.get("missing", "")) for x in (backlog.get("prioritized_missing") or [])] + ops = sorted({m.split(":", 1)[1] for m in missing if m.startswith("missing_prerequisite_op:")}) + reasons = sorted({m.split(":", 1)[1] for m in missing if m.startswith("missing_reason_keyword:")}) + contracts = sorted({m.split(":", 1)[1] for m in missing if m.startswith("missing_execution_contract:")}) + min_count = 0 + for m in missing: + if m.startswith("native_task_count<"): + try: + min_count = max(min_count, int(m.split("<", 1)[1])) + except ValueError: + pass + return ops, reasons, contracts, min_count + + +def normalize_task(task: Dict, ops: List[str], reasons: List[str], contracts: List[str]) -> Dict: + ec = dict(task.get("executionContract") or {}) + for f in contracts: + ec[f] = True + ec.setdefault("deterministic", True) + ec.setdefault("rollbackRequired", True) + ec.setdefault("replayValidationRequired", True) + title = str(task.get("title", "Task")).strip() or "Task" + return { + **task, + "title": title, + "prerequisiteOps": sorted(set((task.get("prerequisiteOps") or []) + ops)), + "reasons": sorted(set((task.get("reasons") or []) + reasons + ["raw_structural_projection"])), + "executionContract": ec, + } + + +def expand_to_min_count(tasks: List[Dict], min_count: int, ops: List[str]) -> List[Dict]: + if min_count <= 0 or len(tasks) >= min_count or not tasks: + return tasks + out = list(tasks) + idx = 0 + while len(out) < min_count: + base = dict(tasks[idx % len(tasks)]) + tid = str(base.get("taskId", f"task-{idx+1}")) + op = ops[idx % len(ops)] if ops else "whetstone_validate_taskitem" + base["taskId"] = f"{tid}-p{len(out)+1}" + base["title"] = f"{base.get('title','Task')} [{op}]" + base["prerequisiteOps"] = sorted(set((base.get("prerequisiteOps") or []) + [op])) + out.append(base) + idx += 1 + return out + + +def main() -> int: + p = argparse.ArgumentParser(description="Project raw candidate tasks into stronger structural shape before scoring.") + p.add_argument("--tasks", required=True) + p.add_argument("--top-gaps", required=True) + p.add_argument("--out", required=True) + p.add_argument("--out-report", required=True) + args = p.parse_args() + + tasks = load_json(Path(args.tasks)) + if not isinstance(tasks, list): + raise SystemExit("--tasks must be JSON array") + backlog = load_json(Path(args.top_gaps)) + ops, reasons, contracts, min_count = parse_gap_signals(backlog) + + projected = [normalize_task(t, ops, reasons, contracts) for t in tasks] + projected = expand_to_min_count(projected, min_count, ops) + + report = { + "status": "ok", + "input_task_count": len(tasks), + "output_task_count": len(projected), + "required_ops_count": len(ops), + "required_reason_count": len(reasons), + "required_contract_count": len(contracts), + "target_min_task_count": min_count, + } + write_json(Path(args.out), projected) + write_json(Path(args.out_report), report) + print(json.dumps({"status": "ok", "input_task_count": len(tasks), "output_task_count": len(projected), "out": args.out}, sort_keys=True)) + return 0 + + +if __name__ == "__main__": + raise SystemExit(main()) diff --git a/tools/mcp/run_sprint_taskitem_pipeline.sh b/tools/mcp/run_sprint_taskitem_pipeline.sh index 4f98fbb..e54469d 100755 --- a/tools/mcp/run_sprint_taskitem_pipeline.sh +++ b/tools/mcp/run_sprint_taskitem_pipeline.sh @@ -55,6 +55,7 @@ NATIVE_RAW_CANDIDATE_REQUIRE_UPLIFT="${WSTONE_NATIVE_RAW_CANDIDATE_REQUIRE_UPLIF NATIVE_RAW_HARDEN_TOP_GAPS="${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_STRUCTURAL_PROJECTOR="${WSTONE_NATIVE_RAW_STRUCTURAL_PROJECTOR:-0}" NATIVE_RAW_TOP_GAP_WEIGHTED_SELECT="${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}" @@ -130,6 +131,7 @@ NATIVE_MULTISHOT_JSON='{}' NATIVE_RAW_CANDIDATE_SEARCH_JSON='{}' NATIVE_RAW_HARDENING_JSON='{}' NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON='{}' +NATIVE_RAW_STRUCTURAL_PROJECTOR_JSON='{}' NATIVE_RAW_TOP_GAP_REQUIREMENTS_JSON='{}' NATIVE_RAW_INTRINSIC_PROMPT_PACK_JSON='{}' NATIVE_RAW_TEMPLATE_CONTROL_PACK_JSON='{}' @@ -460,10 +462,17 @@ fi if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then top_gap_score_args=() use_top_gap_weighted_select=false + raw_structural_projector_enabled=false + raw_structural_projector_projected_variants=0 + baseline_projected_input_count=0 + baseline_projected_output_count=0 if [[ "$NATIVE_RAW_TOP_GAP_WEIGHTED_SELECT" == "1" && -n "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" && -f "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" ]]; then top_gap_score_args=(--top-gaps "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE") use_top_gap_weighted_select=true fi + if [[ "$NATIVE_RAW_STRUCTURAL_PROJECTOR" == "1" && -n "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" && -f "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" ]]; then + raw_structural_projector_enabled=true + fi python3 "$ROOT_DIR/tools/mcp/synthesize_raw_candidate_requirement_variants.py" \ --spec "$INPUT_FILE" \ --profiles "$NATIVE_IMPACT_COVERAGE_PROFILES" \ @@ -490,16 +499,31 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then fi printf '%s\n' "$TASKS" > "$OUT_DIR/02ae_candidate_0_tasks.json" + baseline_eval_tasks_path="$OUT_DIR/02ae_candidate_0_tasks.json" + baseline_eval_tasks_json="$TASKS" + if [[ "$raw_structural_projector_enabled" == true ]]; then + python3 "$ROOT_DIR/tools/mcp/project_raw_candidate_structure.py" \ + --tasks "$OUT_DIR/02ae_candidate_0_tasks.json" \ + --top-gaps "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" \ + --out "$OUT_DIR/02ae_candidate_0_projected_tasks.json" \ + --out-report "$OUT_DIR/02ae_candidate_0_projected_report.json" >/dev/null + baseline_eval_tasks_path="$OUT_DIR/02ae_candidate_0_projected_tasks.json" + baseline_eval_tasks_json="$(cat "$OUT_DIR/02ae_candidate_0_projected_tasks.json")" + baseline_projected_input_count="$(jq '.input_task_count // 0' "$OUT_DIR/02ae_candidate_0_projected_report.json")" + baseline_projected_output_count="$(jq '.output_task_count // 0' "$OUT_DIR/02ae_candidate_0_projected_report.json")" + raw_structural_projector_projected_variants=$((raw_structural_projector_projected_variants + 1)) + fi python3 "$ROOT_DIR/tools/mcp/score_native_tasks_profile_coverage.py" \ --spec "$INPUT_FILE" \ --profiles "$NATIVE_IMPACT_COVERAGE_PROFILES" \ - --tasks "$OUT_DIR/02ae_candidate_0_tasks.json" \ + --tasks "$baseline_eval_tasks_path" \ "${top_gap_score_args[@]}" \ --out "$OUT_DIR/02ae_candidate_0_score.json" >/dev/null best_variant="0" best_fail="$(jq '.failing_profile_count // 999' "$OUT_DIR/02ae_candidate_0_score.json")" best_task_count="$(jq '.task_count // 0' "$OUT_DIR/02ae_candidate_0_score.json")" best_top_gap_score="$(jq '.top_gap_score // 0' "$OUT_DIR/02ae_candidate_0_score.json")" + TASKS="$baseline_eval_tasks_json" baseline_fail="$best_fail" baseline_task_count="$best_task_count" baseline_top_gap_score="$best_top_gap_score" @@ -523,10 +547,22 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then if [[ "$(printf '%s' "$cand_json" | jq -r '.success // false')" == "true" ]]; then cand_tasks="$(printf '%s' "$cand_json" | jq '.tasks // []')" printf '%s\n' "$cand_tasks" > "$OUT_DIR/02ae_candidate_${variant}_tasks.json" + cand_eval_tasks_path="$OUT_DIR/02ae_candidate_${variant}_tasks.json" + cand_eval_tasks_json="$cand_tasks" + if [[ "$raw_structural_projector_enabled" == true ]]; then + python3 "$ROOT_DIR/tools/mcp/project_raw_candidate_structure.py" \ + --tasks "$OUT_DIR/02ae_candidate_${variant}_tasks.json" \ + --top-gaps "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" \ + --out "$OUT_DIR/02ae_candidate_${variant}_projected_tasks.json" \ + --out-report "$OUT_DIR/02ae_candidate_${variant}_projected_report.json" >/dev/null + cand_eval_tasks_path="$OUT_DIR/02ae_candidate_${variant}_projected_tasks.json" + cand_eval_tasks_json="$(cat "$OUT_DIR/02ae_candidate_${variant}_projected_tasks.json")" + raw_structural_projector_projected_variants=$((raw_structural_projector_projected_variants + 1)) + fi python3 "$ROOT_DIR/tools/mcp/score_native_tasks_profile_coverage.py" \ --spec "$INPUT_FILE" \ --profiles "$NATIVE_IMPACT_COVERAGE_PROFILES" \ - --tasks "$OUT_DIR/02ae_candidate_${variant}_tasks.json" \ + --tasks "$cand_eval_tasks_path" \ "${top_gap_score_args[@]}" \ --out "$OUT_DIR/02ae_candidate_${variant}_score.json" >/dev/null cand_fail="$(jq '.failing_profile_count // 999' "$OUT_DIR/02ae_candidate_${variant}_score.json")" @@ -549,7 +585,7 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then best_fail="$cand_fail" best_task_count="$cand_task_count" best_top_gap_score="$cand_top_gap_score" - TASKS="$cand_tasks" + TASKS="$cand_eval_tasks_json" fi successful=$((successful + 1)) fi @@ -580,10 +616,22 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then retry_success=true retry_tasks="$(printf '%s' "$retry_json" | jq '.tasks // []')" printf '%s\n' "$retry_tasks" > "$OUT_DIR/02af_raw_adaptive_retry_tasks.json" + retry_eval_tasks_path="$OUT_DIR/02af_raw_adaptive_retry_tasks.json" + retry_eval_tasks_json="$retry_tasks" + if [[ "$raw_structural_projector_enabled" == true ]]; then + python3 "$ROOT_DIR/tools/mcp/project_raw_candidate_structure.py" \ + --tasks "$OUT_DIR/02af_raw_adaptive_retry_tasks.json" \ + --top-gaps "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" \ + --out "$OUT_DIR/02af_raw_adaptive_retry_projected_tasks.json" \ + --out-report "$OUT_DIR/02af_raw_adaptive_retry_projected_report.json" >/dev/null + retry_eval_tasks_path="$OUT_DIR/02af_raw_adaptive_retry_projected_tasks.json" + retry_eval_tasks_json="$(cat "$OUT_DIR/02af_raw_adaptive_retry_projected_tasks.json")" + raw_structural_projector_projected_variants=$((raw_structural_projector_projected_variants + 1)) + fi python3 "$ROOT_DIR/tools/mcp/score_native_tasks_profile_coverage.py" \ --spec "$INPUT_FILE" \ --profiles "$NATIVE_IMPACT_COVERAGE_PROFILES" \ - --tasks "$OUT_DIR/02af_raw_adaptive_retry_tasks.json" \ + --tasks "$retry_eval_tasks_path" \ "${top_gap_score_args[@]}" \ --out "$OUT_DIR/02af_raw_adaptive_retry_score.json" >/dev/null retry_fail="$(jq '.failing_profile_count // 999' "$OUT_DIR/02af_raw_adaptive_retry_score.json")" @@ -594,7 +642,7 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then best_fail="$retry_fail" best_task_count="$retry_task_count" best_top_gap_score="$retry_top_gap_score" - TASKS="$retry_tasks" + TASKS="$retry_eval_tasks_json" retry_applied=true fi fi @@ -611,6 +659,12 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then else NATIVE_RAW_ADAPTIVE_RETRY_JSON='{"enabled":false}' fi + NATIVE_RAW_STRUCTURAL_PROJECTOR_JSON="$(jq -nc \ + --argjson enabled "$raw_structural_projector_enabled" \ + --argjson projected_variant_count "$raw_structural_projector_projected_variants" \ + --argjson baseline_input_task_count "$baseline_projected_input_count" \ + --argjson baseline_output_task_count "$baseline_projected_output_count" \ + '{enabled:$enabled, projected_variant_count:$projected_variant_count, baseline_input_task_count:$baseline_input_task_count, baseline_output_task_count:$baseline_output_task_count}')" NATIVE_RAW_CANDIDATE_SEARCH_JSON="$(jq -nc \ --argjson enabled true \ @@ -649,6 +703,7 @@ if [[ "$NATIVE_RAW_CANDIDATE_SEARCH" == "1" ]]; then else NATIVE_RAW_CANDIDATE_SEARCH_JSON='{"enabled":false}' NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON='{"enabled":false}' + NATIVE_RAW_STRUCTURAL_PROJECTOR_JSON='{"enabled":false}' fi if [[ "$NATIVE_RAW_HARDEN_TOP_GAPS" == "1" ]]; then printf '%s\n' "$TASKS" > "$OUT_DIR/02af_raw_hardening_input_tasks.json" @@ -997,6 +1052,7 @@ SUMMARY_JSON="$(jq -nc \ --argjson native_raw_intrinsic_prompt_pack "$NATIVE_RAW_INTRINSIC_PROMPT_PACK_JSON" \ --argjson native_raw_template_control_pack "$NATIVE_RAW_TEMPLATE_CONTROL_PACK_JSON" \ --argjson native_raw_signal_targeted_variants "$NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON" \ + --argjson native_raw_structural_projector "$NATIVE_RAW_STRUCTURAL_PROJECTOR_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 "$NATIVE_RAW_HARDENING_JSON" \ @@ -1031,6 +1087,7 @@ SUMMARY_JSON="$(jq -nc \ native_raw_intrinsic_prompt_pack: $native_raw_intrinsic_prompt_pack, native_raw_template_control_pack: $native_raw_template_control_pack, native_raw_signal_targeted_variants: $native_raw_signal_targeted_variants, + native_raw_structural_projector: $native_raw_structural_projector, native_raw_candidate_search: $native_raw_candidate_search, native_raw_adaptive_retry: $native_raw_adaptive_retry, native_raw_hardening: $native_raw_hardening,