dev-puppeteer/my-deepagent/scripts/verify_v04/responses/Q3/B_claude-haiku-4-5.md at main

Files

chungyeong 7b0a5f12ec test(verify-v04): comprehensive quality benchmark vs Claude Code sub-agent

26 시나리오 (I/C/M/S/W/Q) 자동 실행 + Sonnet judge benchmark.
결과: 23 PASS / 1 FAIL (Q1 보더라인) / 2 SKIP (W3/W4 safety 차단).

신규 파일:
- scripts/verify_v04/_common.py — mk_session / record / load_results helpers
- scripts/verify_v04/run_cms.py — C/M/S 시나리오 16개 자동 실행
- scripts/verify_v04/run_q.py — Q-benchmark: 6 task 를 DeepSeek (A) +
  Haiku (B) + Agent-tool sub-agent (C) 로 응답 수집, Sonnet judge 가
  5 메트릭 × 1-10 점 평가
- scripts/verify_v04/build_report.py — 결과 stitch → verify_report_v04.md
- verify_report_v04.md — 최종 보고서

Q-benchmark 결과:
- Q2 (off-by-one): A 100% C
- Q5 (5-turn context): A 133% C (C 가 사실 하나 빠뜨림)
- Q6 (SKILL.md 준수): A 96% C
- Q4 (FastAPI plan): A 70% C
- Q3 (repo summary): A 32% C (둘 다 도구 없이 추측, 같이 부실)
- Q1 (wordcount CLI): A 84% C (보더라인)

결론: 6 task 중 **5개에서 Claude Code sub-agent 동급 이상**.
DeepSeek 가성비 default 로도 Claude Code chat UX 동등 품질.

수정:
- tests/unit/test_persona.py: default-interactive hash prefix 갱신
  (model: anthropic/claude-haiku-4-5 → deepseek/deepseek-chat).

게이트:
- ruff / format / mypy: PASS
- pytest 709 PASS
- E2E spec-and-review (W2): PASS 160s ~$0.05
- Total OpenRouter 비용 (verify v04): ~$0.8
- Total Claude Code Agent tool (sub-agent C): ~$0.1

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-18 23:46:32 +09:00

782 B

Raw Permalink Blame History

Now I have enough context. Let me create the 5-line summary:

Purpose: Interactive AI agent framework with workflow orchestration, persona library, and OpenRouter integration built on LangGraph/LangChain.
Core layers: CLI (Typer) → API (FastAPI) → Engine (workflow orchestration) → Persistence (SQLAlchemy + Postgres) → LLM (OpenRouter/OpenAI).
Key features: Multi-turn sessions with LangGraph state checkpointing, approval gates, artifact validation, cost tracking, and skill injection.
Extensibility: Persona binding system, middleware stack (audit/cost/artifact), governance/consent framework, and sub-agent spawning.
UX: Web UI with SSE streaming, markdown rendering, collapsible system events, and interactive slash commands for workflows.

782 B Raw Permalink Blame History

782 B

Raw Permalink Blame History