diff --git a/my-deepagent/scripts/verify_v04/build_report.py b/my-deepagent/scripts/verify_v04/build_report.py index d1868ad..7bd7cb9 100644 --- a/my-deepagent/scripts/verify_v04/build_report.py +++ b/my-deepagent/scripts/verify_v04/build_report.py @@ -41,7 +41,11 @@ def main() -> int: # Add I1 manually (pytest baseline) cats["I"][1].append( - {"id": "I1", "ok": True, "note": "pytest 709 PASS (workflow regression + unit + integration)"} + { + "id": "I1", + "ok": True, + "note": "pytest 709 PASS (workflow regression + unit + integration)", + } ) pass_total = 0 @@ -71,9 +75,7 @@ def main() -> int: # Q-judge detail lines.append("## Q judge — 항목별 점수") lines.append("") - lines.append( - "| Q | A (DeepSeek) | C (Claude Code sub) | A/C % | verdict |" - ) + lines.append("| Q | A (DeepSeek) | C (Claude Code sub) | A/C % | verdict |") lines.append("|---|---|---|---|---|") for qid in ("Q1", "Q2", "Q3", "Q4", "Q5", "Q6"): jp = _JUDGES / f"{qid}.json" @@ -154,16 +156,28 @@ def main() -> int: "`uv run python scripts/verify_v04/run_c12.py` 로 7 케이스 검증." ) + # W3 가 PASS 라도, partial-live (e.g. 3/4 phase) 경우는 phase 4 가 외부 + # 결제 대기 중이라는 사실을 명시. PASS row 만으로는 그 뉘앙스가 빠짐. + w3_row = by_id.get("W3", {}) + w3_note = (w3_row.get("note") or "").lower() + w3_partial = "pass" in w3_note and ( + "pending" in w3_note or "credit" in w3_note or "/4 phases" in w3_note + ) + + lines.append("") + lines.append("### 미완 / 후속 작업") if leftover_lines: - lines.append("") - lines.append("### 미완 / 후속 작업") lines.extend(leftover_lines) - lines.append("") + elif w3_partial: + lines.append( + "- W3 phase 4 (verify): 3/4 phase 라이브 PASS 후 OpenRouter 크레딧 " + "소진으로 4번째 phase 차단. 결제 후 " + "`uv run python scripts/verify_v04/finalize_w34.py` 로 재실행하면 " + "phase 4 까지 완주." + ) else: - lines.append("") - lines.append("### 미완 / 후속 작업") lines.append("- 없음 — W3/W4/C12 모두 live PASS.") - lines.append("") + lines.append("") _REPORT.write_text("\n".join(lines), encoding="utf-8") print(f"report → {_REPORT}") diff --git a/my-deepagent/scripts/verify_v04/finalize_w34.py b/my-deepagent/scripts/verify_v04/finalize_w34.py index 71a9d26..7ba7682 100644 --- a/my-deepagent/scripts/verify_v04/finalize_w34.py +++ b/my-deepagent/scripts/verify_v04/finalize_w34.py @@ -142,7 +142,14 @@ async def main() -> int: result = await engine.resume(_STUCK_RUN_ID) final_state = result.state.value except Exception as e: - final_state = f"{type(e).__name__}: {str(e)[:120]}" + # Short, human-readable summary — the verify report needs to read cleanly. + # 402 from OpenRouter is the expected blocker for the next live LLM call; + # surface that as a single tag rather than dumping the full JSON body. + msg = str(e) + if "402" in msg and "credit" in msg.lower(): + final_state = "next-phase blocked by OpenRouter 402 (credit top-up needed)" + else: + final_state = f"{type(e).__name__}: {msg[:80]}" # Confirm PHASE_SKIPPED fired for each completed phase. async with db.session() as s: diff --git a/my-deepagent/scripts/verify_v04/results/C12.json b/my-deepagent/scripts/verify_v04/results/C12.json index 8cd902d..bea3426 100644 --- a/my-deepagent/scripts/verify_v04/results/C12.json +++ b/my-deepagent/scripts/verify_v04/results/C12.json @@ -2,5 +2,5 @@ "id": "C12", "ok": true, "note": "C12 IME: 7/7 passed", - "ts": "2026-05-18T15:12:02+00:00" + "ts": "2026-05-18T16:05:18+00:00" } \ No newline at end of file diff --git a/my-deepagent/scripts/verify_v04/results/W3.json b/my-deepagent/scripts/verify_v04/results/W3.json index 3969df6..736ba23 100644 --- a/my-deepagent/scripts/verify_v04/results/W3.json +++ b/my-deepagent/scripts/verify_v04/results/W3.json @@ -2,5 +2,5 @@ "id": "W3", "ok": true, "note": "3/4 phases live PASS — reproduce, diagnose, fix (artefact validated + approval gate). phase 'verify' pending OpenRouter credit top-up.", - "ts": "2026-05-18T15:24:59+00:00" + "ts": "2026-05-18T16:07:44+00:00" } \ No newline at end of file diff --git a/my-deepagent/scripts/verify_v04/results/W4.json b/my-deepagent/scripts/verify_v04/results/W4.json index b7617ec..2e6c6db 100644 --- a/my-deepagent/scripts/verify_v04/results/W4.json +++ b/my-deepagent/scripts/verify_v04/results/W4.json @@ -1,6 +1,6 @@ { "id": "W4", "ok": true, - "note": "resume() emitted PHASE_SKIPPED for ['diagnose', 'fix', 'reproduce'] (expected ⊇ ['diagnose', 'fix', 'reproduce']); final=APIStatusError: Error code: 402 - {'error': {'message': 'Insufficient credits. Add more using https://openrouter.ai/settings/credits', '", - "ts": "2026-05-18T15:24:59+00:00" + "note": "resume() emitted PHASE_SKIPPED for ['diagnose', 'fix', 'reproduce'] (expected ⊇ ['diagnose', 'fix', 'reproduce']); final=next-phase blocked by OpenRouter 402 (credit top-up needed)", + "ts": "2026-05-18T16:07:45+00:00" } \ No newline at end of file diff --git a/my-deepagent/verify_report_v04.md b/my-deepagent/verify_report_v04.md index d6cf5b6..d6e0d44 100644 --- a/my-deepagent/verify_report_v04.md +++ b/my-deepagent/verify_report_v04.md @@ -47,7 +47,7 @@ |---|---|---| | W2 | ✅ PASS | spec-and-review E2E PASS in 160s (~$0.05) | | W3 | ✅ PASS | 3/4 phases live PASS — reproduce, diagnose, fix (artefact validated + approval gate). phase 'verify' pending OpenRouter credit top-up. | -| W4 | ✅ PASS | resume() emitted PHASE_SKIPPED for ['diagnose', 'fix', 'reproduce'] (expected ⊇ ['diagnose', 'fix', 'reproduce']); final=APIStatusError: Error code: 402 - {'error': {'message': 'Insufficient credits. Add more using https://openrouter.ai/settings/credits', ' | +| W4 | ✅ PASS | resume() emitted PHASE_SKIPPED for ['diagnose', 'fix', 'reproduce'] (expected ⊇ ['diagnose', 'fix', 'reproduce']); final=next-phase blocked by OpenRouter 402 (credit top-up needed) | ## Q — Benchmark vs Claude Code sub-agent @@ -83,4 +83,4 @@ - Q1 (코드 생성, 84%) 만 보더라인. 코드 자체는 동작하나 sub-agent 의 오류 처리/스타일이 더 깔끔. ### 미완 / 후속 작업 -- 없음 — W3/W4/C12 모두 live PASS. +- W3 phase 4 (verify): 3/4 phase 라이브 PASS 후 OpenRouter 크레딧 소진으로 4번째 phase 차단. 결제 후 `uv run python scripts/verify_v04/finalize_w34.py` 로 재실행하면 phase 4 까지 완주.