17ba5d723b
Python rewrite of the agent harness on top of deepagents 0.6.1 + langchain 1.x, replacing the abandoned TS attempt in packages/. 388 unit/integration tests pass. Steps ----- 0. Scaffolding — uv workspace, ruff/mypy/pre-commit/alembic, src/tests/docs trees with docs/schemas/ seeded from my-deepagent-seed/. 1. Core — config (pydantic-settings with MYDEEPAGENT_ env prefix and TOML source), enums (Backend, Capability, RiskLevel, ApprovalDecisionAction, ApprovalState, RunState, RunPhaseState, SessionState, ErrorClass), errors (MyDeepAgentError + BudgetExhaustedError with PEP-3134 cause + context suppression), hash (canonical JSON + sha256). 2. Persona/Workflow/Binding — pydantic v2 schemas with tuple-based deep immutability (post-construction hash drift prevented), YAML loaders, deterministic auto-select (preferred_backends → version → name → hash), override resolution with ineligibility diagnostics, PersonaConsentStore with fcntl.flock + tmp+fsync+rename atomic write. 3. Artifact schema registry — Draft202012Validator, multi-root resolution, structured ValidationFinding output. 4. Persistence — 18 SQLAlchemy 2.0 async ORM models with FK CASCADE/RESTRICT, WAL + busy_timeout + foreign_keys PRAGMA, alembic baseline + ux_active_run_repo_base partial unique index, LangGraph SqliteSaver as context manager only (lifecycle safety). 5. DeepAgent session — build_agent wires Persona → create_deep_agent with LocalShellBackend / FilesystemBackend / StateBackend / CompositeBackend, ChatOpenAI(base_url=openrouter) for openrouter: model strings, and 4 middleware classes (cost / audit-tool / safety-shell / fallback-model). Critical workarounds -------------------- - deepagents 0.6.1 rejects FilesystemPermission together with backends that implement SandboxBackendProtocol (LocalShellBackend). SafetyShellMiddleware enforces destructive-command and secret-path policy at the tool layer instead, and build_agent strips the permissions kwarg when the persona's deepagents_backend is local_shell. - FilesystemOperation in deepagents is Literal['read', 'write'] only; _map_operations collapses our richer schema (read/write/edit/ls) safely. Real OpenRouter smoke --------------------- test_openrouter_deepagents_local_shell_smoke calls DeepSeek via deepagents + LocalShellBackend + SafetyShellMiddleware end-to-end. PASS, ~$0.000001 cost, input=9 / output=1 tokens with content "OK". Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
77 lines
2.4 KiB
YAML
77 lines
2.4 KiB
YAML
name: spec-and-review
|
|
version: 1
|
|
description: "요구사항 → spec → 리뷰 → verifier 검증"
|
|
roles:
|
|
- id: spec_writer
|
|
required_capabilities:
|
|
- spec_write
|
|
- phase_planning
|
|
preferred_backends:
|
|
- openrouter
|
|
fallback_personas:
|
|
- "openrouter-claude-spec-writer@1"
|
|
- id: reviewer
|
|
required_capabilities:
|
|
- code_review
|
|
- evidence_check
|
|
preferred_backends:
|
|
- openrouter
|
|
fallback_personas:
|
|
- "openrouter-claude-code-reviewer@1"
|
|
- id: verifier
|
|
required_capabilities:
|
|
- evidence_check
|
|
- objective_eval
|
|
preferred_backends:
|
|
- openrouter
|
|
fallback_personas:
|
|
- "openrouter-deepseek-verifier@1"
|
|
phases:
|
|
- key: spec
|
|
title: "요구사항 분석 및 Spec 작성"
|
|
risk: low
|
|
role: spec_writer
|
|
expected_artifact:
|
|
path: artifacts/spec.json
|
|
schema: dev/spec@1
|
|
gates:
|
|
- spec_approved
|
|
timeout_seconds: 300
|
|
instructions: |
|
|
사용자 요구사항을 분석해 dev/spec@1 schema에 맞는 spec.json을 작성하세요.
|
|
기존 코드는 read_file/glob/grep으로 탐색합니다.
|
|
완성된 spec.json은 write_file로 artifacts/spec.json에 저장합니다.
|
|
max_budget_usd: 0.50
|
|
- key: review
|
|
title: "Spec 리뷰"
|
|
risk: low
|
|
role: reviewer
|
|
expected_artifact:
|
|
path: artifacts/review.json
|
|
schema: dev/review-finding-batch@1
|
|
gates:
|
|
- review_approved
|
|
timeout_seconds: 300
|
|
instructions: |
|
|
artifacts/spec.json을 read_file로 읽고 dev/review-finding-batch@1 형식으로 review.json을 작성하세요.
|
|
각 finding은 severity, category, summary를 반드시 포함합니다.
|
|
완성된 review.json은 write_file로 artifacts/review.json에 저장합니다.
|
|
max_budget_usd: 0.50
|
|
- key: verify
|
|
title: "리뷰 결과 검증"
|
|
risk: low
|
|
role: verifier
|
|
expected_artifact:
|
|
path: artifacts/verification.json
|
|
schema: dev/review-finding-batch@1
|
|
gates:
|
|
- verify_approved
|
|
timeout_seconds: 180
|
|
instructions: |
|
|
artifacts/review.json을 read_file로 읽고 각 finding을 코드에서 직접 확인합니다.
|
|
verifierStatus를 confirmed 또는 rejected로 판정하고 근거를 evidence 필드에 기록합니다.
|
|
결과를 write_file로 artifacts/verification.json에 저장합니다.
|
|
max_budget_usd: 0.10
|
|
default_gates: []
|
|
max_total_budget_usd: 2.0
|