Add intrinsic prompt-pack intervention for raw generation (sprint 261)

tools/mcp/run_sprint_taskitem_pipeline.sh

@@ -60,6 +60,8 @@ 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}"
 NATIVE_RAW_TOP_GAP_REQUIREMENTS="${WSTONE_NATIVE_RAW_TOP_GAP_REQUIREMENTS:-0}"
 NATIVE_RAW_TOP_GAP_MAX_SIGNALS="${WSTONE_NATIVE_RAW_TOP_GAP_MAX_SIGNALS:-5}"
+NATIVE_RAW_INTRINSIC_PROMPT_PACK="${WSTONE_NATIVE_RAW_INTRINSIC_PROMPT_PACK:-0}"
+NATIVE_RAW_INTRINSIC_PROMPT_MAX_SIGNALS="${WSTONE_NATIVE_RAW_INTRINSIC_PROMPT_MAX_SIGNALS:-8}"
 NATIVE_RAW_TOP_GAP_ADAPTIVE_RETRY="${WSTONE_NATIVE_RAW_TOP_GAP_ADAPTIVE_RETRY:-0}"
 NATIVE_RAW_TOP_GAP_RETRY_SIGNALS="${WSTONE_NATIVE_RAW_TOP_GAP_RETRY_SIGNALS:-10}"
 EXTRA_NORMALIZED_REQUIREMENTS_FILE="${WSTONE_EXTRA_NORMALIZED_REQUIREMENTS_FILE:-}"
@@ -127,6 +129,7 @@ NATIVE_RAW_CANDIDATE_SEARCH_JSON='{}'
 NATIVE_RAW_HARDENING_JSON='{}'
 NATIVE_RAW_SIGNAL_TARGETED_VARIANTS_JSON='{}'
 NATIVE_RAW_TOP_GAP_REQUIREMENTS_JSON='{}'
+NATIVE_RAW_INTRINSIC_PROMPT_PACK_JSON='{}'
 NATIVE_RAW_ADAPTIVE_RETRY_JSON='{}'
 INTRINSIC_REQS_JSON='[]'
 EXTRA_NORMALIZED_REQUIREMENTS_JSON='[]'
@@ -359,6 +362,22 @@ if [[ "$NATIVE_RAW_TOP_GAP_REQUIREMENTS" == "1" && -n "$NATIVE_RAW_TOP_GAP_BACKL
 else
   NATIVE_RAW_TOP_GAP_REQUIREMENTS_JSON='{"enabled":false}'
 fi
+if [[ "$NATIVE_RAW_INTRINSIC_PROMPT_PACK" == "1" && -n "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" && -f "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" ]]; then
+  python3 "$ROOT_DIR/tools/mcp/synthesize_raw_intrinsic_prompt_pack.py" \
+    --top-gaps "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" \
+    --max-signals "$NATIVE_RAW_INTRINSIC_PROMPT_MAX_SIGNALS" \
+    --out "$OUT_DIR/01f_raw_intrinsic_prompt_pack_requirements.json" \
+    --out-report "$OUT_DIR/01f_raw_intrinsic_prompt_pack_report.json" >/dev/null
+  RAW_INTRINSIC_PROMPT_REQS_JSON="$(cat "$OUT_DIR/01f_raw_intrinsic_prompt_pack_requirements.json")"
+  NORMALIZED_REQS="$(jq -nc --argjson base "$NORMALIZED_REQS" --argjson extra "$RAW_INTRINSIC_PROMPT_REQS_JSON" '$base + $extra')"
+  NATIVE_RAW_INTRINSIC_PROMPT_PACK_JSON="$(jq -nc \
+    --argjson enabled true \
+    --arg backlog_file "$NATIVE_RAW_TOP_GAP_BACKLOG_FILE" \
+    --argjson report "$(cat "$OUT_DIR/01f_raw_intrinsic_prompt_pack_report.json")" \
+    '{enabled:$enabled, backlog_file:$backlog_file, report:$report}')"
+else
+  NATIVE_RAW_INTRINSIC_PROMPT_PACK_JSON='{"enabled":false}'
+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:($strict == "1")}')"
@@ -956,6 +975,7 @@ SUMMARY_JSON="$(jq -nc \
   --argjson native_profile_autofill "$NATIVE_PROFILE_AUTOFILL_JSON" \
   --argjson native_intrinsic_boost "$NATIVE_INTRINSIC_BOOST_JSON" \
   --argjson native_raw_top_gap_requirements "$NATIVE_RAW_TOP_GAP_REQUIREMENTS_JSON" \
+  --argjson native_raw_intrinsic_prompt_pack "$NATIVE_RAW_INTRINSIC_PROMPT_PACK_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 "$NATIVE_RAW_ADAPTIVE_RETRY_JSON" \
@@ -988,6 +1008,7 @@ SUMMARY_JSON="$(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_intrinsic_prompt_pack: $native_raw_intrinsic_prompt_pack,
     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,

tools/mcp/synthesize_raw_intrinsic_prompt_pack.py

@@ -0,0 +1,80 @@
+#!/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 main() -> int:
+    p = argparse.ArgumentParser(description="Build intrinsic prompt-pack requirements from top-gap missing-signal classes.")
+    p.add_argument("--top-gaps", required=True)
+    p.add_argument("--max-signals", type=int, default=8)
+    p.add_argument("--out", required=True)
+    p.add_argument("--out-report", required=True)
+    args = p.parse_args()
+
+    backlog = load_json(Path(args.top_gaps))
+    prioritized = list(backlog.get("prioritized_missing") or [])[: max(0, args.max_signals)]
+
+    required_ops: List[str] = []
+    required_contracts: List[str] = []
+    required_reasons: List[str] = []
+    for row in prioritized:
+        signal = str(row.get("missing", ""))
+        if signal.startswith("missing_prerequisite_op:"):
+            required_ops.append(signal.split(":", 1)[1])
+        elif signal.startswith("missing_execution_contract:"):
+            required_contracts.append(signal.split(":", 1)[1])
+        elif signal.startswith("missing_reason_keyword:"):
+            required_reasons.append(signal.split(":", 1)[1])
+
+    required_ops = sorted(set(required_ops))
+    required_contracts = sorted(set(required_contracts))
+    required_reasons = sorted(set(required_reasons))
+
+    prompt_text = (
+        "intrinsic raw generation contract: emit concrete taskitems only; "
+        "for each task include taskId/title/prerequisiteOps/reasons/executionContract/dependencyTaskIds; "
+        f"ensure prerequisiteOps include: {', '.join(required_ops) if required_ops else 'none'}; "
+        f"ensure executionContract true fields include: {', '.join(required_contracts) if required_contracts else 'deterministic,rollbackRequired,replayValidationRequired'}; "
+        f"ensure reasons contain keywords: {', '.join(required_reasons) if required_reasons else 'risk,contract,replay'}; "
+        "forbid umbrella tasks like 'implement everything' and require at least one verifiable operation per task."
+    )
+
+    reqs = [
+        {
+            "requirementId": "raw-intrinsic-prompt-pack",
+            "kind": "constraint",
+            "normalizedText": prompt_text,
+            "anchor": "raw_intrinsic_prompt_pack",
+            "sourceLine": 0,
+            "ambiguous": False,
+        }
+    ]
+    report = {
+        "status": "ok",
+        "selected_signal_count": len(prioritized),
+        "required_ops": required_ops,
+        "required_contract_fields": required_contracts,
+        "required_reason_keywords": required_reasons,
+    }
+
+    write_json(Path(args.out), reqs)
+    write_json(Path(args.out_report), report)
+    print(json.dumps({"status": "ok", "selected_signal_count": len(prioritized), "out": args.out}, sort_keys=True))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())