mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-10 10:48:27 +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).
179 lines
6.6 KiB
Python
179 lines
6.6 KiB
Python
"""Tests for ThreadMetaRepository (SQLAlchemy-backed)."""
|
|
|
|
import pytest
|
|
|
|
from deerflow.persistence.thread_meta import ThreadMetaRepository
|
|
|
|
|
|
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 ThreadMetaRepository(get_session_factory())
|
|
|
|
|
|
async def _cleanup():
|
|
from deerflow.persistence.engine import close_engine
|
|
|
|
await close_engine()
|
|
|
|
|
|
class TestThreadMetaRepository:
|
|
@pytest.mark.anyio
|
|
async def test_create_and_get(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
record = await repo.create("t1")
|
|
assert record["thread_id"] == "t1"
|
|
assert record["status"] == "idle"
|
|
assert "created_at" in record
|
|
|
|
fetched = await repo.get("t1")
|
|
assert fetched is not None
|
|
assert fetched["thread_id"] == "t1"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_create_with_assistant_id(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
record = await repo.create("t1", assistant_id="agent1")
|
|
assert record["assistant_id"] == "agent1"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_create_with_owner_and_display_name(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
record = await repo.create("t1", user_id="user1", display_name="My Thread")
|
|
assert record["user_id"] == "user1"
|
|
assert record["display_name"] == "My Thread"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_create_with_metadata(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
record = await repo.create("t1", metadata={"key": "value"})
|
|
assert record["metadata"] == {"key": "value"}
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_get_nonexistent(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
assert await repo.get("nonexistent") is None
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_check_access_no_record_allows(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
assert await repo.check_access("unknown", "user1") is True
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_check_access_owner_matches(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1", user_id="user1")
|
|
assert await repo.check_access("t1", "user1") is True
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_check_access_owner_mismatch(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1", user_id="user1")
|
|
assert await repo.check_access("t1", "user2") is False
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_check_access_no_owner_allows_all(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
# Explicit user_id=None to bypass the new AUTO default that
|
|
# would otherwise pick up the test user from the autouse fixture.
|
|
await repo.create("t1", user_id=None)
|
|
assert await repo.check_access("t1", "anyone") is True
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_check_access_strict_missing_row_denied(self, tmp_path):
|
|
"""require_existing=True flips the missing-row case to *denied*.
|
|
|
|
Closes the delete-idempotence cross-user gap: after a thread is
|
|
deleted, the row is gone, and the permissive default would let any
|
|
caller "claim" it as untracked. The strict mode demands a row.
|
|
"""
|
|
repo = await _make_repo(tmp_path)
|
|
assert await repo.check_access("never-existed", "user1", require_existing=True) is False
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_check_access_strict_owner_match_allowed(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1", user_id="user1")
|
|
assert await repo.check_access("t1", "user1", require_existing=True) is True
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_check_access_strict_owner_mismatch_denied(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1", user_id="user1")
|
|
assert await repo.check_access("t1", "user2", require_existing=True) is False
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_check_access_strict_null_owner_still_allowed(self, tmp_path):
|
|
"""Even in strict mode, a row with NULL user_id stays shared.
|
|
|
|
The strict flag tightens the *missing row* case, not the *shared
|
|
row* case — legacy pre-auth rows that survived a clean migration
|
|
without an owner are still everyone's.
|
|
"""
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1", user_id=None)
|
|
assert await repo.check_access("t1", "anyone", require_existing=True) is True
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_update_status(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1")
|
|
await repo.update_status("t1", "busy")
|
|
record = await repo.get("t1")
|
|
assert record["status"] == "busy"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_delete(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1")
|
|
await repo.delete("t1")
|
|
assert await repo.get("t1") 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("nonexistent") # should not raise
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_update_metadata_merges(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1", metadata={"a": 1, "b": 2})
|
|
await repo.update_metadata("t1", {"b": 99, "c": 3})
|
|
record = await repo.get("t1")
|
|
# Existing key preserved, overlapping key overwritten, new key added
|
|
assert record["metadata"] == {"a": 1, "b": 99, "c": 3}
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_update_metadata_on_empty(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.create("t1")
|
|
await repo.update_metadata("t1", {"k": "v"})
|
|
record = await repo.get("t1")
|
|
assert record["metadata"] == {"k": "v"}
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_update_metadata_nonexistent_is_noop(self, tmp_path):
|
|
repo = await _make_repo(tmp_path)
|
|
await repo.update_metadata("nonexistent", {"k": "v"}) # should not raise
|
|
await _cleanup()
|