mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-04-27 20:28:16 +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).
139 lines
4.9 KiB
Python
139 lines
4.9 KiB
Python
from unittest.mock import patch
|
|
|
|
import pytest
|
|
from _router_auth_helpers import make_authed_test_app
|
|
from fastapi import HTTPException
|
|
from fastapi.testclient import TestClient
|
|
|
|
from app.gateway.routers import threads
|
|
from deerflow.config.paths import Paths
|
|
|
|
|
|
def test_delete_thread_data_removes_thread_directory(tmp_path):
|
|
paths = Paths(tmp_path)
|
|
thread_dir = paths.thread_dir("thread-cleanup")
|
|
workspace = paths.sandbox_work_dir("thread-cleanup")
|
|
uploads = paths.sandbox_uploads_dir("thread-cleanup")
|
|
outputs = paths.sandbox_outputs_dir("thread-cleanup")
|
|
|
|
for directory in [workspace, uploads, outputs]:
|
|
directory.mkdir(parents=True, exist_ok=True)
|
|
(workspace / "notes.txt").write_text("hello", encoding="utf-8")
|
|
(uploads / "report.pdf").write_bytes(b"pdf")
|
|
(outputs / "result.json").write_text("{}", encoding="utf-8")
|
|
|
|
assert thread_dir.exists()
|
|
|
|
response = threads._delete_thread_data("thread-cleanup", paths=paths)
|
|
|
|
assert response.success is True
|
|
assert not thread_dir.exists()
|
|
|
|
|
|
def test_delete_thread_data_is_idempotent_for_missing_directory(tmp_path):
|
|
paths = Paths(tmp_path)
|
|
|
|
response = threads._delete_thread_data("missing-thread", paths=paths)
|
|
|
|
assert response.success is True
|
|
assert not paths.thread_dir("missing-thread").exists()
|
|
|
|
|
|
def test_delete_thread_data_rejects_invalid_thread_id(tmp_path):
|
|
paths = Paths(tmp_path)
|
|
|
|
with pytest.raises(HTTPException) as exc_info:
|
|
threads._delete_thread_data("../escape", paths=paths)
|
|
|
|
assert exc_info.value.status_code == 422
|
|
assert "Invalid thread_id" in exc_info.value.detail
|
|
|
|
|
|
def test_delete_thread_route_cleans_thread_directory(tmp_path):
|
|
from deerflow.runtime.user_context import get_effective_user_id
|
|
|
|
paths = Paths(tmp_path)
|
|
user_id = get_effective_user_id()
|
|
thread_dir = paths.thread_dir("thread-route", user_id=user_id)
|
|
paths.sandbox_work_dir("thread-route", user_id=user_id).mkdir(parents=True, exist_ok=True)
|
|
(paths.sandbox_work_dir("thread-route", user_id=user_id) / "notes.txt").write_text("hello", encoding="utf-8")
|
|
|
|
app = make_authed_test_app()
|
|
app.include_router(threads.router)
|
|
|
|
with patch("app.gateway.routers.threads.get_paths", return_value=paths):
|
|
with TestClient(app) as client:
|
|
response = client.delete("/api/threads/thread-route")
|
|
|
|
assert response.status_code == 200
|
|
assert response.json() == {"success": True, "message": "Deleted local thread data for thread-route"}
|
|
assert not thread_dir.exists()
|
|
|
|
|
|
def test_delete_thread_route_rejects_invalid_thread_id(tmp_path):
|
|
paths = Paths(tmp_path)
|
|
|
|
app = make_authed_test_app()
|
|
app.include_router(threads.router)
|
|
|
|
with patch("app.gateway.routers.threads.get_paths", return_value=paths):
|
|
with TestClient(app) as client:
|
|
response = client.delete("/api/threads/../escape")
|
|
|
|
assert response.status_code == 404
|
|
|
|
|
|
def test_delete_thread_route_returns_422_for_route_safe_invalid_id(tmp_path):
|
|
paths = Paths(tmp_path)
|
|
|
|
app = make_authed_test_app()
|
|
app.include_router(threads.router)
|
|
|
|
with patch("app.gateway.routers.threads.get_paths", return_value=paths):
|
|
with TestClient(app) as client:
|
|
response = client.delete("/api/threads/thread.with.dot")
|
|
|
|
assert response.status_code == 422
|
|
assert "Invalid thread_id" in response.json()["detail"]
|
|
|
|
|
|
def test_delete_thread_data_returns_generic_500_error(tmp_path):
|
|
paths = Paths(tmp_path)
|
|
|
|
with (
|
|
patch.object(paths, "delete_thread_dir", side_effect=OSError("/secret/path")),
|
|
patch.object(threads.logger, "exception") as log_exception,
|
|
):
|
|
with pytest.raises(HTTPException) as exc_info:
|
|
threads._delete_thread_data("thread-cleanup", paths=paths)
|
|
|
|
assert exc_info.value.status_code == 500
|
|
assert exc_info.value.detail == "Failed to delete local thread data."
|
|
assert "/secret/path" not in exc_info.value.detail
|
|
log_exception.assert_called_once_with("Failed to delete thread data for %s", "thread-cleanup")
|
|
|
|
|
|
# ── Server-reserved metadata key stripping ──────────────────────────────────
|
|
|
|
|
|
def test_strip_reserved_metadata_removes_user_id():
|
|
"""Client-supplied user_id is dropped to prevent reflection attacks."""
|
|
out = threads._strip_reserved_metadata({"user_id": "victim-id", "title": "ok"})
|
|
assert out == {"title": "ok"}
|
|
|
|
|
|
def test_strip_reserved_metadata_passes_through_safe_keys():
|
|
"""Non-reserved keys are preserved verbatim."""
|
|
md = {"title": "ok", "tags": ["a", "b"], "custom": {"x": 1}}
|
|
assert threads._strip_reserved_metadata(md) == md
|
|
|
|
|
|
def test_strip_reserved_metadata_empty_input():
|
|
"""Empty / None metadata returns same object — no crash."""
|
|
assert threads._strip_reserved_metadata({}) == {}
|
|
|
|
|
|
def test_strip_reserved_metadata_strips_all_reserved_keys():
|
|
out = threads._strip_reserved_metadata({"user_id": "x", "keep": "me"})
|
|
assert out == {"keep": "me"}
|