fix(my-deepagent): v0.3 plan-conformance — 18-item gap fix across PR #2-#9

1차 v0.3 구현 후 plan-v0.3 와 대조해 발견된 18건 누락/명세 위반을 보강.
자기 리뷰 3 라운드 (누락·미완 / 오류·엣지케이스 / 과최적화) 모두 PASS.

PR #5 plan-mode (3건):
- BLOCKED_TOOLS_IN_PLAN_MODE 에 write_todos 추가
- /plan 시 system message inject (_PLAN_MODE_SYSTEM_PROMPT)
- /approve 시 마지막 assistant 메시지를 "approved plan" system 으로 inject
- InteractiveSession._pending_system_messages 인프라 신설

PR #2 compaction (1건):
- CompactionResult.summary_text 추가, 다음 thread 첫 ainvoke 에 inject

PR #3 auto-memory (6건):
- global memory dir + bootstrap
- frontmatter name/description/type 정식 도입 + MemoryEntry/MemoryType
- _infer_memory_type (keyword heuristic, no LLM)
- _scrub_secrets (OpenRouter/Anthropic/OpenAI/AWS/Bearer redaction)
- /memory show <name> 서브명령
- /remember [--global] / /forget [--global] 스코프 토글

PR #4 skills (3건):
- project_skills_dir + 두 스코프 (global / project) merge with last-wins
- /skill <name> 본문 inject (queue_system_message) — 이전엔 REPL 출력만
- /skills show <name> 별도 서브명령

PR #6 sub-agent (4건):
- budget.py `session:<uuid>` scope + CostMiddleware 자동 전달
- resolve_root_session_id walk-up (cycle guard) + sub-agent root 에 charge
- run_subagent_to_completion 실제 ainvoke + 결과 push to parent
- /agents 서브명령 구조 (list / spawn / show) + spawn 시 parent system msg

PR #7 governance (1건):
- bootstrap_user_dirs — instructions + global/memory + skills + projects 한
  호출로 idempotent 부트스트랩

PR #8 Web GUI (1건):
- index.html → 세션 목록, runs.html (신설) → workflow archive
- conversation.html ?session=<id> deep-link

PR #9 workflow integration (2건):
- /workflow 백그라운드 WorkflowEngine.run + 진행 메시지 stream 누적
- /binding show <workflow-name[@version]> 인자 지원

테스트 (+17, 685 → 702 passed):
- test_plan_mode: write_todos 차단 + blocklist sanity
- test_memory: scrub + type 추론 + override
- test_skills: project override + find_skill + resolve_skill_sources(pk)
- test_subagents: resolve_root_session_id chain + missing fallback
- test_budget: session: scope accumulation
- test_instructions: governance bootstrap + idempotency
- test_api_static: runs.html 신설 + index.html 재구성

게이트:
- ruff check / format --check / mypy: PASS (141 source files)
- pytest -q --ignore=tests/integration/test_e2e_workflow.py
  --ignore=tests/integration/test_openrouter_smoke.py: 702 passed

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
chungyeong
2026-05-18 00:03:08 +09:00
parent 361d6d7636
commit 96c8849e2c
24 changed files with 1687 additions and 304 deletions

View File

@@ -72,9 +72,7 @@ async def test_plan_mode_active_blocks_write_file() -> None:
@pytest.mark.asyncio
async def test_plan_mode_active_blocks_execute() -> None:
mw = PlanModeMiddleware(is_active=lambda: True)
req = _FakeToolRequest(
tool_call={"name": "execute", "id": "exec1", "args": {"command": "ls"}}
)
req = _FakeToolRequest(tool_call={"name": "execute", "id": "exec1", "args": {"command": "ls"}})
result = await mw.awrap_tool_call(req, _passthrough_handler)
assert isinstance(result, ToolMessage)
assert result.status == "error"
@@ -84,9 +82,7 @@ async def test_plan_mode_active_blocks_execute() -> None:
@pytest.mark.asyncio
async def test_plan_mode_active_blocks_task_subagent_spawn() -> None:
mw = PlanModeMiddleware(is_active=lambda: True)
req = _FakeToolRequest(
tool_call={"name": "task", "id": "task1", "args": {"description": "x"}}
)
req = _FakeToolRequest(tool_call={"name": "task", "id": "task1", "args": {"description": "x"}})
result = await mw.awrap_tool_call(req, _passthrough_handler)
assert isinstance(result, ToolMessage)
assert result.status == "error"
@@ -101,13 +97,24 @@ async def test_plan_mode_active_blocks_task_subagent_spawn() -> None:
@pytest.mark.asyncio
async def test_plan_mode_active_allows_read_only_tools() -> None:
mw = PlanModeMiddleware(is_active=lambda: True)
for name in ["read_file", "glob", "grep", "ls", "write_todos"]:
for name in ["read_file", "glob", "grep", "ls"]:
req = _FakeToolRequest(tool_call={"name": name, "id": "t1", "args": {}})
result = await mw.awrap_tool_call(req, _passthrough_handler)
assert result.content == "EXECUTED", f"{name} should not be blocked"
assert result.status != "error"
@pytest.mark.asyncio
async def test_plan_mode_blocks_write_todos() -> None:
"""`write_todos` is part of the plan markdown — must be blocked."""
mw = PlanModeMiddleware(is_active=lambda: True)
req = _FakeToolRequest(tool_call={"name": "write_todos", "id": "wt1", "args": {"todos": []}})
result = await mw.awrap_tool_call(req, _passthrough_handler)
assert isinstance(result, ToolMessage)
assert result.status == "error"
assert "write_todos" in result.content
# ---------------------------------------------------------------------------
# Closure-toggle behavior — flip without rebuild
# ---------------------------------------------------------------------------
@@ -165,6 +172,10 @@ def test_blocklist_includes_all_known_write_tools() -> None:
assert "task" in BLOCKED_TOOLS_IN_PLAN_MODE
def test_blocklist_excludes_read_only_and_planning_tools() -> None:
for name in ("read_file", "glob", "grep", "ls", "write_todos"):
def test_blocklist_excludes_read_only_tools() -> None:
for name in ("read_file", "glob", "grep", "ls"):
assert name not in BLOCKED_TOOLS_IN_PLAN_MODE
def test_blocklist_includes_write_todos() -> None:
assert "write_todos" in BLOCKED_TOOLS_IN_PLAN_MODE