섹터 플로우 진척도 추적 추가

docs/ROADMAP_WBS.md

@@ -36,7 +36,7 @@
 | **D2 공식 결정론** | 149개 공식 ID 전부 lifecycle 등록 | 269개 등록 (100%) ✅ |
 | **D3 리스크 제어** | Core/Satellite/Cash 버킷 밴드 위반 0건 | RISK_ON 밴드 내 유지 중 |
 | **D4 알파 피드백** | 예측→실현 수익 루프 30건 이상 누적 | 0건 (DATA_GATED ~2026-07-15) |
-| **D5 실행 자동화** | run_all 1회 실행으로 전체 파이프라인 완결 | 96단계 DAG 구축 완료 ✅ |
+| **D5 실행 자동화** | run_all 1회 실행으로 전체 파이프라인 완결 | 98단계 DAG 구축 완료 ✅ |
 
 ---
 
@@ -586,7 +586,7 @@ CI 게이트:
   honest_proof_score: 50.95 →  목표: ≥70 (T+20 30건 → 70.95 자동 달성 예상)
 
 자동화:
-  run_all 성공률:      96단계 DAG PASS →  목표: ≥95% ✅ (step_count=96, wave_0~9)
+  run_all 성공률:      98단계 DAG PASS →  목표: ≥95% ✅ (step_count=98, wave_0~9)
   CI/CD 커버리지:      100%   →  목표: 100% ✅ (Synology act_runner 온라인, 4게이트 PASS)
   수동 개입 횟수:      매일   →  목표: ≤1회/주 (setupDailyRunAllTrigger 설정 후)
 ```

package.json

@@ -19,11 +19,13 @@
     "build-prediction-accuracy-harness": "python tools/build_prediction_accuracy_harness_v2.py",
     "build-alpha-feedback-loop": "python tools/build_alpha_feedback_loop_v2.py",
     "build-operational-alpha-calibration": "python tools/build_operational_alpha_calibration_v2.py",
+    "build-sector-flow-history-progress": "python tools/build_sector_flow_history_progress_v1.py",
     "build-realized-performance": "python tools/build_realized_performance_v1.py",
     "validate-completion-harness": "python tools/validate_completion_harness_instructions_v1.py",
     "validate-prediction-accuracy-harness": "python tools/validate_prediction_accuracy_harness_v2.py",
     "validate-alpha-feedback-loop": "python tools/validate_alpha_feedback_loop_v2.py",
     "validate-operational-alpha-calibration": "python tools/validate_operational_alpha_calibration_v2.py",
+    "validate-sector-flow-history-progress": "python tools/validate_sector_flow_history_progress_v1.py",
     "validate-realized-performance": "python tools/validate_realized_performance_v1.py",
     "validate-gas-recovery": "python tools/validate_gas_orchestration_recovery_v1.py",
     "ops:clean": "python tools/clean_temp_artifacts_v1.py",

runtime/refactor_baseline_v1.yaml

@@ -1,9 +1,9 @@
 {
   "formula_id": "AUDIT_REPOSITORY_ENTROPY_V2",
   "gate": "PASS",
-  "total_file_count": 1890,
+  "total_file_count": 1894,
-  "package_script_count": 29,
+  "package_script_count": 31,
-  "temp_json_count": 191,
+  "temp_json_count": 193,
   "budget": {
     "schema_version": "repository_entropy_budget.v1",
     "max_total_files": 2200,
@@ -15,5 +15,5 @@
       "keep package scripts within release envelope"
     ]
   },
-  "source_zip_sha256": "1b582cc260c09b41dfd2c361bdd40705ac003b88ad8a09b42bbba615189cbf2b"
+  "source_zip_sha256": "ce6afd425a6dbabb4bc4876703080a9dd639077ed52a8bca9ffa39452982c309"
 }

spec/41_release_dag.yaml

@@ -1,5 +1,5 @@
 schema_version: release_dag.v3
-step_count: 96
+step_count: 98
 goal: Linearize package.json scripts into a validated DAG execution graph.
 execution_order:
   # 토폴로지 정렬 기준 병렬 실행 wave (의존성 없는 노드들을 동시에 실행 가능)
@@ -42,6 +42,7 @@ execution_order:
     - build_etf_representative_monitor
     - build_factor_shadow_eligibility
     - build_formula_outputs
+    - build_sector_flow_history_progress
     - build_realized_performance
     - build_missing_formula_bridge
     - build_ratchet_trailing_general
@@ -89,6 +90,7 @@ execution_order:
     - build_honest_proof_gap_analyzer
     - build_operational_alpha_calibration
     - build_prediction_accuracy_harness
+    - validate_sector_flow_history_progress
     - validate_json_generator_outputs
     - validate_alpha_feedback_loop
     - validate_llm_copy_only
@@ -157,6 +159,18 @@ dag:
       artifact_policy: "keep"
       note: "DATA_GATED 항목별 실측 진척도 — non-blocking diagnostic"
 
+    build_sector_flow_history_progress:
+      id: build_sector_flow_history_progress
+      command: ["python", "tools/build_sector_flow_history_progress_v1.py"]
+      inputs: ["tools/build_sector_flow_history_progress_v1.py", "GatherTradingData.json"]
+      outputs: ["Temp/sector_flow_history_progress_v1.json"]
+      depends_on: ["build_data_gated_progress"]
+      timeout_sec: 30
+      cache_key: "build_sector_flow_history_progress_v1"
+      strict: false
+      artifact_policy: "keep"
+      note: "WBS-2.5 sector_flow_history 30일 누적 진척도 — non-blocking diagnostic"
+
     build_realized_performance:
       id: build_realized_performance
       command: ["python", "tools/build_realized_performance_v1.py"]
@@ -634,6 +648,17 @@ dag:
       strict: true
       artifact_policy: "keep"
 
+    validate_sector_flow_history_progress:
+      id: validate_sector_flow_history_progress
+      command: ["python", "tools/validate_sector_flow_history_progress_v1.py"]
+      inputs: ["tools/validate_sector_flow_history_progress_v1.py", "Temp/sector_flow_history_progress_v1.json"]
+      outputs: ["Temp/validate_sector_flow_history_progress_v1.json"]
+      depends_on: ["build_sector_flow_history_progress"]
+      timeout_sec: 30
+      cache_key: "validate_sector_flow_history_progress_v1"
+      strict: true
+      artifact_policy: "keep"
+
     validate_alpha_feedback_loop:
       id: validate_alpha_feedback_loop
       command: ["python", "tools/validate_alpha_feedback_loop_v2.py"]
@@ -1289,7 +1314,7 @@ dag:
       command: ["python", "tools/prepare_upload_zip.py", "--skip-validate", "--skip-convert", "--validation-mode", "package-only"]
       inputs: ["tools/prepare_upload_zip.py"]
       outputs: []
-      depends_on: ["audit_entropy", "validate_specs", "validate_active_manifest", "validate_report_sync", "validate_report_numeric_consistency", "validate_field_dict", "validate_provenance", "validate_low_capability", "validate_golden_coverage", "validate_calibration", "validate_schema_model", "validate_gas_adapter", "validate_agents_shrink", "validate_no_replay_live_mix", "validate_prediction_accuracy_harness", "validate_alpha_feedback_loop", "validate_operational_alpha_calibration", "validate_realized_performance", "validate_runtime_source_whitelist", "validate_cash_ledger", "validate_factor_lifecycle", "validate_factor_lifecycle_completeness", "validate_metric_alias_collision", "validate_architecture_boundaries", "validate_module_io_coverage", "validate_artifact_chain_hash", "validate_artifact_sync", "validate_renderer_no_calc", "validate_packaged_refs", "validate_property_invariants", "validate_anti_late_entry", "validate_rule_lifecycle", "validate_change_requests", "validate_completion_harness_instructions", "validate_engine_health_card", "validate_llm_regression", "validate_llm_copy_only", "build_final_decision", "build_final_context", "build_provenance_ledger", "build_live_replay_separation", "build_late_chase_attribution", "build_profit_giveback_ratchet", "build_shadow_ledger", "build_operating_cadence_signal", "build_engine_health_card", "build_module_io_coverage", "build_artifact_chain_hash", "build_report", "build_bundle", "build_schema_models", "build_architecture_boundaries", "validate_decision_trace", "validate_factor_conflicts", "validate_no_lookahead", "validate_execution_sim", "validate_render_diff", "build_shadow_promotion", "validate_llm_determinism", "build_time_stop_forecast", "validate_live_activation", "build_rebalance_sheet", "build_prediction_accuracy_harness", "build_alpha_feedback_loop", "build_operational_alpha_calibration"]
+      depends_on: ["audit_entropy", "validate_specs", "validate_active_manifest", "validate_report_sync", "validate_report_numeric_consistency", "validate_field_dict", "validate_provenance", "validate_low_capability", "validate_golden_coverage", "validate_calibration", "validate_schema_model", "validate_gas_adapter", "validate_agents_shrink", "validate_no_replay_live_mix", "validate_prediction_accuracy_harness", "validate_alpha_feedback_loop", "validate_operational_alpha_calibration", "validate_realized_performance", "validate_sector_flow_history_progress", "validate_runtime_source_whitelist", "validate_cash_ledger", "validate_factor_lifecycle", "validate_factor_lifecycle_completeness", "validate_metric_alias_collision", "validate_architecture_boundaries", "validate_module_io_coverage", "validate_artifact_chain_hash", "validate_artifact_sync", "validate_renderer_no_calc", "validate_packaged_refs", "validate_property_invariants", "validate_anti_late_entry", "validate_rule_lifecycle", "validate_change_requests", "validate_completion_harness_instructions", "validate_engine_health_card", "validate_llm_regression", "validate_llm_copy_only", "build_final_decision", "build_final_context", "build_provenance_ledger", "build_live_replay_separation", "build_late_chase_attribution", "build_profit_giveback_ratchet", "build_shadow_ledger", "build_operating_cadence_signal", "build_engine_health_card", "build_module_io_coverage", "build_artifact_chain_hash", "build_report", "build_bundle", "build_schema_models", "build_architecture_boundaries", "validate_decision_trace", "validate_factor_conflicts", "validate_no_lookahead", "validate_execution_sim", "validate_render_diff", "build_shadow_promotion", "validate_llm_determinism", "build_time_stop_forecast", "validate_live_activation", "build_rebalance_sheet", "build_prediction_accuracy_harness", "build_alpha_feedback_loop", "build_operational_alpha_calibration", "build_sector_flow_history_progress"]
       timeout_sec: 60
       cache_key: "prepare_zip_v1"
       strict: true

src/quant_engine/prepare_upload_zip.py

@@ -94,6 +94,8 @@ TEMP_KEEP_FILES = {
     "validate_alpha_feedback_loop_v2.json",
     "operational_alpha_calibration_v2.json",
     "validate_operational_alpha_calibration_v2.json",
+    "sector_flow_history_progress_v1.json",
+    "validate_sector_flow_history_progress_v1.json",
     "realized_performance_v1.json",
     "validate_realized_performance_v1.json",
     "single_truth_ledger_v2.json",

tools/build_sector_flow_history_progress_v1.py

@@ -0,0 +1,91 @@
+"""build_sector_flow_history_progress_v1.py — SECTOR_FLOW_HISTORY_PROGRESS_V1
+
+WBS-2.5 진척도를 실데이터로 요약한다.
+sector_flow_history 누적 일수와 Flow_Credit 커버리지를 정직하게 노출한다.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+from collections import defaultdict
+from pathlib import Path
+from typing import Any
+
+ROOT = Path(__file__).resolve().parents[1]
+DEFAULT_JSON = ROOT / "GatherTradingData.json"
+DEFAULT_OUT = ROOT / "Temp" / "sector_flow_history_progress_v1.json"
+FORMULA_ID = "SECTOR_FLOW_HISTORY_PROGRESS_V1"
+
+
+def _load(path: Path) -> dict[str, Any]:
+    if not path.exists():
+        return {}
+    try:
+        obj = json.loads(path.read_text(encoding="utf-8"))
+    except Exception:
+        return {}
+    return obj if isinstance(obj, dict) else {}
+
+
+def _rows(data: dict[str, Any], key: str) -> list[dict[str, Any]]:
+    rows = (data.get("data") or {}).get(key) or []
+    return [r for r in rows if isinstance(r, dict)]
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--json", default=str(DEFAULT_JSON))
+    ap.add_argument("--out", default=str(DEFAULT_OUT))
+    args = ap.parse_args()
+
+    json_path = Path(args.json)
+    json_path = json_path if json_path.is_absolute() else ROOT / json_path
+    out_path = Path(args.out)
+    out_path = out_path if out_path.is_absolute() else ROOT / out_path
+
+    payload = _load(json_path)
+    sector_rows = _rows(payload, "sector_flow_history")
+    data_feed_rows = _rows(payload, "data_feed")
+
+    by_date: dict[str, int] = defaultdict(int)
+    for row in sector_rows:
+        snap = row.get("Snapshot_Date") or row.get("snapshot_date") or ""
+        day = str(snap)[:10]
+        if day:
+            by_date[day] += 1
+
+    distinct_dates = len(by_date)
+    row_count = len(sector_rows)
+    target_dates = 30
+    status = "DONE" if distinct_dates >= target_dates else "DATA_GATED"
+    coverage = round(min(100.0, distinct_dates / target_dates * 100.0), 2)
+
+    flow_credit_values = [row.get("Flow_Credit") for row in data_feed_rows]
+    nonnull_flow_credit = sum(1 for v in flow_credit_values if v is not None)
+    flow_credit_coverage = round((nonnull_flow_credit / len(flow_credit_values) * 100.0), 2) if flow_credit_values else 0.0
+
+    result = {
+        "formula_id": FORMULA_ID,
+        "status": status,
+        "current_dates": distinct_dates,
+        "target_dates": target_dates,
+        "coverage_pct": coverage,
+        "row_count": row_count,
+        "rows_per_date": sorted(by_date.items()),
+        "flow_credit_coverage_pct": flow_credit_coverage,
+        "flow_credit_nonnull_count": nonnull_flow_credit,
+        "flow_credit_total_count": len(flow_credit_values),
+        "source": "GatherTradingData.json:data.sector_flow_history + data.data_feed",
+    }
+
+    out_path.parent.mkdir(parents=True, exist_ok=True)
+    out_path.write_text(json.dumps(result, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    print(
+        f"[{FORMULA_ID}] status={status} dates={distinct_dates}/{target_dates} "
+        f"rows={row_count} flow_credit={nonnull_flow_credit}/{len(flow_credit_values)}"
+    )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

tools/validate_sector_flow_history_progress_v1.py

@@ -0,0 +1,79 @@
+"""validate_sector_flow_history_progress_v1.py — SECTOR_FLOW_HISTORY_PROGRESS_VALIDATE_V1
+
+sector_flow_history 진척도 산출물의 기본 계약을 검증한다.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+from typing import Any
+
+ROOT = Path(__file__).resolve().parents[1]
+DEFAULT_INPUT = ROOT / "Temp" / "sector_flow_history_progress_v1.json"
+DEFAULT_OUT = ROOT / "Temp" / "validate_sector_flow_history_progress_v1.json"
+FORMULA_ID = "SECTOR_FLOW_HISTORY_PROGRESS_VALIDATE_V1"
+
+
+def _load(path: Path) -> Any:
+    if not path.exists():
+        return {}
+    try:
+        return json.loads(path.read_text(encoding="utf-8"))
+    except Exception:
+        return {}
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--input", default=str(DEFAULT_INPUT))
+    ap.add_argument("--out", default=str(DEFAULT_OUT))
+    args = ap.parse_args()
+
+    input_path = Path(args.input)
+    input_path = input_path if input_path.is_absolute() else ROOT / input_path
+    out_path = Path(args.out)
+    out_path = out_path if out_path.is_absolute() else ROOT / out_path
+
+    payload = _load(input_path)
+    errors: list[str] = []
+
+    if not isinstance(payload, dict) or not payload:
+        errors.append("payload must be object")
+    else:
+        if payload.get("formula_id") != "SECTOR_FLOW_HISTORY_PROGRESS_V1":
+            errors.append("formula_id mismatch")
+        if payload.get("status") not in {"DONE", "DATA_GATED"}:
+            errors.append(f"status={payload.get('status')}")
+        for key in [
+            "current_dates",
+            "target_dates",
+            "coverage_pct",
+            "row_count",
+            "rows_per_date",
+            "flow_credit_coverage_pct",
+        ]:
+            if key not in payload:
+                errors.append(f"missing field: {key}")
+
+        current_dates = payload.get("current_dates")
+        target_dates = payload.get("target_dates")
+        if isinstance(current_dates, int) and isinstance(target_dates, int):
+            if current_dates < target_dates and payload.get("status") != "DATA_GATED":
+                errors.append("current_dates < target_dates requires DATA_GATED")
+            if current_dates >= target_dates and payload.get("status") != "DONE":
+                errors.append("current_dates >= target_dates requires DONE")
+
+    result = {
+        "formula_id": FORMULA_ID,
+        "gate": "PASS" if not errors else "FAIL",
+        "checked_file": str(Path(args.input).as_posix()),
+        "errors": errors,
+    }
+    out_path.write_text(json.dumps(result, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    print(json.dumps(result, ensure_ascii=False, indent=2))
+    return 0 if not errors else 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())