mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-05 00:08:24 +00:00
3e6a34297d
Squashes 25 PR commits onto current main. AppConfig becomes a pure value object with no ambient lookup. Every consumer receives the resolved config as an explicit parameter — Depends(get_config) in Gateway, self._app_config in DeerFlowClient, runtime.context.app_config in agent runs, AppConfig.from_file() at the LangGraph Server registration boundary. Phase 1 — frozen data + typed context - All config models (AppConfig, MemoryConfig, DatabaseConfig, …) become frozen=True; no sub-module globals. - AppConfig.from_file() is pure (no side-effect singleton loaders). - Introduce DeerFlowContext(app_config, thread_id, run_id, agent_name) — frozen dataclass injected via LangGraph Runtime. - Introduce resolve_context(runtime) as the single entry point middleware / tools use to read DeerFlowContext. Phase 2 — pure explicit parameter passing - Gateway: app.state.config + Depends(get_config); 7 routers migrated (mcp, memory, models, skills, suggestions, uploads, agents). - DeerFlowClient: __init__(config=...) captures config locally. - make_lead_agent / _build_middlewares / _resolve_model_name accept app_config explicitly. - RunContext.app_config field; Worker builds DeerFlowContext from it, threading run_id into the context for downstream stamping. - Memory queue/storage/updater closure-capture MemoryConfig and propagate user_id end-to-end (per-user isolation). - Sandbox/skills/community/factories/tools thread app_config. - resolve_context() rejects non-typed runtime.context. - Test suite migrated off AppConfig.current() monkey-patches. - AppConfig.current() classmethod deleted. Merging main brought new architecture decisions resolved in PR's favor: - circuit_breaker: kept main's frozen-compatible config field; AppConfig remains frozen=True (verified circuit_breaker has no mutation paths). - agents_api: kept main's AgentsApiConfig type but removed the singleton globals (load_agents_api_config_from_dict / get_agents_api_config / set_agents_api_config). 8 routes in agents.py now read via Depends(get_config). - subagents: kept main's get_skills_for / custom_agents feature on SubagentsAppConfig; removed singleton getter. registry.py now reads app_config.subagents directly. - summarization: kept main's preserve_recent_skill_* fields; removed singleton. - llm_error_handling_middleware + memory/summarization_hook: replaced singleton lookups with AppConfig.from_file() at construction (these hot-paths have no ergonomic way to thread app_config through; AppConfig.from_file is a pure load). - worker.py + thread_data_middleware.py: DeerFlowContext.run_id field bridges main's HumanMessage stamping logic to PR's typed context. Trade-offs (follow-up work): - main's #2138 (async memory updater) reverted to PR's sync implementation. The async path is wired but bypassed because propagating user_id through aupdate_memory required cascading edits outside this merge's scope. - tests/test_subagent_skills_config.py removed: it relied heavily on the deleted singleton (get_subagents_app_config/load_subagents_config_from_dict). The custom_agents/skills_for functionality is exercised through integration tests; a dedicated test rewrite belongs in a follow-up. Verification: backend test suite — 2560 passed, 4 skipped, 84 failures. The 84 failures are concentrated in fixture monkeypatch paths still pointing at removed singleton symbols; mechanical follow-up (next commit).
197 lines
7.0 KiB
Python
197 lines
7.0 KiB
Python
"""Tests for RunRepository (SQLAlchemy-backed RunStore).
|
|
|
|
Uses a temp SQLite DB to test ORM-backed CRUD operations.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from deerflow.persistence.run import RunRepository
|
|
|
|
|
|
async def _make_repo(tmp_path):
|
|
from deerflow.persistence.engine import get_session_factory, init_engine
|
|
|
|
url = f"sqlite+aiosqlite:///{tmp_path / 'test.db'}"
|
|
await init_engine("sqlite", url=url, sqlite_dir=str(tmp_path))
|
|
return RunRepository(get_session_factory())
|
|
|
|
|
|
async def _cleanup():
|
|
from deerflow.persistence.engine import close_engine
|
|
|
|
await close_engine()
|
|
|
|
|
|
class TestRunRepository:
|
|
@pytest.mark.anyio
|
|
async def test_put_and_get(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1", status="pending")
|
|
row = await repo.get("r1")
|
|
assert row is not None
|
|
assert row["run_id"] == "r1"
|
|
assert row["thread_id"] == "t1"
|
|
assert row["status"] == "pending"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_get_missing_returns_none(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
assert await repo.get("nope") is None
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_update_status(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1")
|
|
await repo.update_status("r1", "running")
|
|
row = await repo.get("r1")
|
|
assert row["status"] == "running"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_update_status_with_error(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1")
|
|
await repo.update_status("r1", "error", error="boom")
|
|
row = await repo.get("r1")
|
|
assert row["status"] == "error"
|
|
assert row["error"] == "boom"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_thread(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1")
|
|
await repo.put("r2", thread_id="t1")
|
|
await repo.put("r3", thread_id="t2")
|
|
rows = await repo.list_by_thread("t1")
|
|
assert len(rows) == 2
|
|
assert all(r["thread_id"] == "t1" for r in rows)
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_thread_owner_filter(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1", user_id="alice")
|
|
await repo.put("r2", thread_id="t1", user_id="bob")
|
|
rows = await repo.list_by_thread("t1", user_id="alice")
|
|
assert len(rows) == 1
|
|
assert rows[0]["user_id"] == "alice"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_delete(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1")
|
|
await repo.delete("r1")
|
|
assert await repo.get("r1") is None
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_delete_nonexistent_is_noop(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.delete("nope") # should not raise
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_pending(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1", status="pending")
|
|
await repo.put("r2", thread_id="t1", status="running")
|
|
await repo.put("r3", thread_id="t2", status="pending")
|
|
pending = await repo.list_pending()
|
|
assert len(pending) == 2
|
|
assert all(r["status"] == "pending" for r in pending)
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_update_run_completion(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1", status="running")
|
|
await repo.update_run_completion(
|
|
"r1",
|
|
status="success",
|
|
total_input_tokens=100,
|
|
total_output_tokens=50,
|
|
total_tokens=150,
|
|
llm_call_count=2,
|
|
lead_agent_tokens=120,
|
|
subagent_tokens=20,
|
|
middleware_tokens=10,
|
|
message_count=3,
|
|
last_ai_message="The answer is 42",
|
|
first_human_message="What is the meaning?",
|
|
)
|
|
row = await repo.get("r1")
|
|
assert row["status"] == "success"
|
|
assert row["total_tokens"] == 150
|
|
assert row["llm_call_count"] == 2
|
|
assert row["lead_agent_tokens"] == 120
|
|
assert row["message_count"] == 3
|
|
assert row["last_ai_message"] == "The answer is 42"
|
|
assert row["first_human_message"] == "What is the meaning?"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_metadata_preserved(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1", metadata={"key": "value"})
|
|
row = await repo.get("r1")
|
|
assert row["metadata"] == {"key": "value"}
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_kwargs_with_non_serializable(self, tmp_path):
|
|
"""kwargs containing non-JSON-serializable objects should be safely handled."""
|
|
repo = await _make_repo(tmp_path)
|
|
|
|
class Dummy:
|
|
pass
|
|
|
|
await repo.put("r1", thread_id="t1", kwargs={"obj": Dummy()})
|
|
row = await repo.get("r1")
|
|
assert "obj" in row["kwargs"]
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_update_run_completion_preserves_existing_fields(self, tmp_path):
|
|
"""update_run_completion does not overwrite thread_id or assistant_id."""
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1", assistant_id="agent1", status="running")
|
|
await repo.update_run_completion("r1", status="success", total_tokens=100)
|
|
row = await repo.get("r1")
|
|
assert row["thread_id"] == "t1"
|
|
assert row["assistant_id"] == "agent1"
|
|
assert row["total_tokens"] == 100
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_thread_ordered_desc(self, tmp_path):
|
|
"""list_by_thread returns newest first."""
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1", created_at="2024-01-01T00:00:00+00:00")
|
|
await repo.put("r2", thread_id="t1", created_at="2024-01-02T00:00:00+00:00")
|
|
rows = await repo.list_by_thread("t1")
|
|
assert rows[0]["run_id"] == "r2"
|
|
assert rows[1]["run_id"] == "r1"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_thread_limit(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
for i in range(5):
|
|
await repo.put(f"r{i}", thread_id="t1")
|
|
rows = await repo.list_by_thread("t1", limit=2)
|
|
assert len(rows) == 2
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_owner_none_returns_all(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.put("r1", thread_id="t1", user_id="alice")
|
|
await repo.put("r2", thread_id="t1", user_id="bob")
|
|
rows = await repo.list_by_thread("t1", user_id=None)
|
|
assert len(rows) == 2
|
|
await _cleanup()
|