greatmengqi
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).
114 lines
3.5 KiB
Python
114 lines
3.5 KiB
Python
"""CSRF protection middleware for FastAPI.
|
|
|
|
Per RFC-001:
|
|
State-changing operations require CSRF protection.
|
|
"""
|
|
|
|
import secrets
|
|
from collections.abc import Callable
|
|
|
|
from fastapi import Request, Response
|
|
from starlette.middleware.base import BaseHTTPMiddleware
|
|
from starlette.responses import JSONResponse
|
|
from starlette.types import ASGIApp
|
|
|
|
CSRF_COOKIE_NAME = "csrf_token"
|
|
CSRF_HEADER_NAME = "X-CSRF-Token"
|
|
CSRF_TOKEN_LENGTH = 64 # bytes
|
|
|
|
|
|
def is_secure_request(request: Request) -> bool:
|
|
"""Detect whether the original client request was made over HTTPS."""
|
|
return request.headers.get("x-forwarded-proto", request.url.scheme) == "https"
|
|
|
|
|
|
def generate_csrf_token() -> str:
|
|
"""Generate a secure random CSRF token."""
|
|
return secrets.token_urlsafe(CSRF_TOKEN_LENGTH)
|
|
|
|
|
|
def should_check_csrf(request: Request) -> bool:
|
|
"""Determine if a request needs CSRF validation.
|
|
|
|
CSRF is checked for state-changing methods (POST, PUT, DELETE, PATCH).
|
|
GET, HEAD, OPTIONS, and TRACE are exempt per RFC 7231.
|
|
"""
|
|
if request.method not in ("POST", "PUT", "DELETE", "PATCH"):
|
|
return False
|
|
|
|
path = request.url.path.rstrip("/")
|
|
# Exempt /api/v1/auth/me endpoint
|
|
if path == "/api/v1/auth/me":
|
|
return False
|
|
return True
|
|
|
|
|
|
_AUTH_EXEMPT_PATHS: frozenset[str] = frozenset(
|
|
{
|
|
"/api/v1/auth/login/local",
|
|
"/api/v1/auth/logout",
|
|
"/api/v1/auth/register",
|
|
"/api/v1/auth/initialize",
|
|
}
|
|
)
|
|
|
|
|
|
def is_auth_endpoint(request: Request) -> bool:
|
|
"""Check if the request is to an auth endpoint.
|
|
|
|
Auth endpoints don't need CSRF validation on first call (no token).
|
|
"""
|
|
return request.url.path.rstrip("/") in _AUTH_EXEMPT_PATHS
|
|
|
|
|
|
class CSRFMiddleware(BaseHTTPMiddleware):
|
|
"""Middleware that implements CSRF protection using Double Submit Cookie pattern."""
|
|
|
|
def __init__(self, app: ASGIApp) -> None:
|
|
super().__init__(app)
|
|
|
|
async def dispatch(self, request: Request, call_next: Callable) -> Response:
|
|
_is_auth = is_auth_endpoint(request)
|
|
|
|
if should_check_csrf(request) and not _is_auth:
|
|
cookie_token = request.cookies.get(CSRF_COOKIE_NAME)
|
|
header_token = request.headers.get(CSRF_HEADER_NAME)
|
|
|
|
if not cookie_token or not header_token:
|
|
return JSONResponse(
|
|
status_code=403,
|
|
content={"detail": "CSRF token missing. Include X-CSRF-Token header."},
|
|
)
|
|
|
|
if not secrets.compare_digest(cookie_token, header_token):
|
|
return JSONResponse(
|
|
status_code=403,
|
|
content={"detail": "CSRF token mismatch."},
|
|
)
|
|
|
|
response = await call_next(request)
|
|
|
|
# For auth endpoints that set up session, also set CSRF cookie
|
|
if _is_auth and request.method == "POST":
|
|
# Generate a new CSRF token for the session
|
|
csrf_token = generate_csrf_token()
|
|
is_https = is_secure_request(request)
|
|
response.set_cookie(
|
|
key=CSRF_COOKIE_NAME,
|
|
value=csrf_token,
|
|
httponly=False, # Must be JS-readable for Double Submit Cookie pattern
|
|
secure=is_https,
|
|
samesite="strict",
|
|
)
|
|
|
|
return response
|
|
|
|
|
|
def get_csrf_token(request: Request) -> str | None:
|
|
"""Get the CSRF token from the current request's cookies.
|
|
|
|
This is useful for server-side rendering where you need to embed
|
|
token in forms or headers.
|
|
"""
|
|
return request.cookies.get(CSRF_COOKIE_NAME)
|