fix(security): harden auth system and fix run journal logic bug

backend/app/gateway/auth/config.py

@@ -4,11 +4,8 @@
 import os
 import secrets
 
-from dotenv import load_dotenv
 from pydantic import BaseModel, Field
 
-load_dotenv()
-
 logger = logging.getLogger(__name__)
 
 
@@ -37,6 +34,9 @@ def get_auth_config() -> AuthConfig:
     """Get the global AuthConfig instance. Parses from env on first call."""
     global _auth_config
     if _auth_config is None:
+        from dotenv import load_dotenv
+
+        load_dotenv()
         jwt_secret = os.environ.get("AUTH_JWT_SECRET")
         if not jwt_secret:
             jwt_secret = secrets.token_urlsafe(32)

backend/app/gateway/auth/password.py

@@ -1,18 +1,30 @@
-"""Password hashing utilities using bcrypt directly."""
+"""Password hashing utilities using bcrypt with SHA-256 pre-hashing.
+
+Passwords are pre-hashed with SHA-256 before bcrypt to avoid silent
+truncation at 72 bytes (bcrypt's internal limit). This ensures the
+full password contributes to the hash regardless of length.
+"""
 
 import asyncio
+import base64
+import hashlib
 
 import bcrypt
 
 
+def _pre_hash(password: str) -> bytes:
+    """Pre-hash password with SHA-256 to bypass bcrypt's 72-byte limit."""
+    return base64.b64encode(hashlib.sha256(password.encode("utf-8")).digest())
+
+
 def hash_password(password: str) -> str:
-    """Hash a password using bcrypt."""
-    return bcrypt.hashpw(password.encode("utf-8"), bcrypt.gensalt()).decode("utf-8")
+    """Hash a password using bcrypt with SHA-256 pre-hashing."""
+    return bcrypt.hashpw(_pre_hash(password), bcrypt.gensalt()).decode("utf-8")
 
 
 def verify_password(plain_password: str, hashed_password: str) -> bool:
     """Verify a password against its hash."""
-    return bcrypt.checkpw(plain_password.encode("utf-8"), hashed_password.encode("utf-8"))
+    return bcrypt.checkpw(_pre_hash(plain_password), hashed_password.encode("utf-8"))
 
 
 async def hash_password_async(password: str) -> str:

backend/app/gateway/authz.py

@@ -181,6 +181,9 @@ async def wrapper(*args: Any, **kwargs: Any) -> Any:
         auth_context = await _authenticate(request)
         request.state.auth = auth_context
 
+        if not auth_context.is_authenticated:
+            raise HTTPException(status_code=401, detail="Authentication required")
+
         return await func(*args, **kwargs)
 
     return wrapper

backend/app/gateway/langgraph_auth.py

@@ -73,7 +73,7 @@ async def authenticate(request):
     if isinstance(payload, TokenError):
         raise Auth.exceptions.HTTPException(
             status_code=401,
-            detail=f"Token error: {payload.value}",
+            detail="Invalid token",
         )
 
     user = await get_local_provider().get_user(payload.sub)

backend/app/gateway/routers/auth.py

@@ -146,7 +146,13 @@ def _set_session_cookie(response: Response, token: str, request: Request) -> Non
 
 
 # ── Rate Limiting ────────────────────────────────────────────────────────
-# In-process dict — not shared across workers. Sufficient for single-worker deployments.
+# In-process dict — not shared across workers.
+#
+# **Limitation**: with multi-worker deployments (e.g., gunicorn -w N), each
+# worker maintains its own lockout table, so an attacker effectively gets
+# N × _MAX_LOGIN_ATTEMPTS guesses before being locked out everywhere. For
+# production multi-worker setups, replace this with a shared store (Redis,
+# database-backed counter) to enforce a true per-IP limit.
 
 _MAX_LOGIN_ATTEMPTS = 5
 _LOCKOUT_SECONDS = 300  # 5 minutes
@@ -376,9 +382,37 @@ async def get_me(request: Request):
     return UserResponse(id=str(user.id), email=user.email, system_role=user.system_role, needs_setup=user.needs_setup)
 
 
+_SETUP_STATUS_COOLDOWN: dict[str, float] = {}
+_SETUP_STATUS_COOLDOWN_SECONDS = 60
+_MAX_TRACKED_SETUP_STATUS_IPS = 10000
+
+
 @router.get("/setup-status")
-async def setup_status():
+async def setup_status(request: Request):
     """Check if an admin account exists. Returns needs_setup=True when no admin exists."""
+    client_ip = _get_client_ip(request)
+    now = time.time()
+    last_check = _SETUP_STATUS_COOLDOWN.get(client_ip, 0)
+    elapsed = now - last_check
+    if elapsed < _SETUP_STATUS_COOLDOWN_SECONDS:
+        retry_after = max(1, int(_SETUP_STATUS_COOLDOWN_SECONDS - elapsed))
+        raise HTTPException(
+            status_code=status.HTTP_429_TOO_MANY_REQUESTS,
+            detail="Setup status check is rate limited",
+            headers={"Retry-After": str(retry_after)},
+        )
+    # Evict stale entries when dict grows too large to bound memory usage.
+    if len(_SETUP_STATUS_COOLDOWN) >= _MAX_TRACKED_SETUP_STATUS_IPS:
+        cutoff = now - _SETUP_STATUS_COOLDOWN_SECONDS
+        stale = [k for k, t in _SETUP_STATUS_COOLDOWN.items() if t < cutoff]
+        for k in stale:
+            del _SETUP_STATUS_COOLDOWN[k]
+        # If still too large after evicting expired entries, remove oldest half.
+        if len(_SETUP_STATUS_COOLDOWN) >= _MAX_TRACKED_SETUP_STATUS_IPS:
+            by_time = sorted(_SETUP_STATUS_COOLDOWN.items(), key=lambda kv: kv[1])
+            for k, _ in by_time[: len(by_time) // 2]:
+                del _SETUP_STATUS_COOLDOWN[k]
+    _SETUP_STATUS_COOLDOWN[client_ip] = now
     admin_count = await get_local_provider().count_admin_users()
     return {"needs_setup": admin_count == 0}
 

backend/packages/harness/deerflow/runtime/journal.py

@@ -141,7 +141,7 @@ def on_chat_model_start(
         logger.info(f"on_chat_model_start {run_id}: tags={tags} serialized={serialized} messages={messages}")
 
         # Capture the first human message sent to any LLM in this run.
-        if not self._first_human_msg and not messages:
+        if not self._first_human_msg and messages:
             for batch in messages.reversed():
                 for m in batch.reversed():
                     if isinstance(m, HumanMessage) and m.name != "summary":

backend/tests/test_auth.py

@@ -166,7 +166,7 @@ def test_get_auth_context_set():
 
 
 def test_require_auth_sets_auth_context():
-    """require_auth sets auth context on request from cookie."""
+    """require_auth rejects unauthenticated requests with 401."""
     from fastapi import Request
 
     app = FastAPI()
@@ -178,10 +178,9 @@ async def endpoint(request: Request):
         return {"authenticated": ctx.is_authenticated}
 
     with TestClient(app) as client:
-        # No cookie → anonymous
+        # No cookie → 401 (require_auth independently enforces authentication)
         response = client.get("/test")
-        assert response.status_code == 200
-        assert response.json()["authenticated"] is False
+        assert response.status_code == 401
 
 
 def test_require_auth_requires_request_param():

backend/tests/test_initialize_admin.py

@@ -22,18 +22,21 @@
 def _setup_auth(tmp_path):
     """Fresh SQLite engine + auth config per test."""
     from app.gateway import deps
+    from app.gateway.routers.auth import _SETUP_STATUS_COOLDOWN
     from deerflow.persistence.engine import close_engine, init_engine
 
     set_auth_config(AuthConfig(jwt_secret=_TEST_SECRET))
     url = f"sqlite+aiosqlite:///{tmp_path}/init_admin.db"
     asyncio.run(init_engine("sqlite", url=url, sqlite_dir=str(tmp_path)))
     deps._cached_local_provider = None
     deps._cached_repo = None
+    _SETUP_STATUS_COOLDOWN.clear()
     try:
         yield
     finally:
         deps._cached_local_provider = None
         deps._cached_repo = None
+        _SETUP_STATUS_COOLDOWN.clear()
         asyncio.run(close_engine())
 
 
@@ -163,3 +166,17 @@ def test_setup_status_false_when_only_regular_user_exists(client):
     resp = client.get("/api/v1/auth/setup-status")
     assert resp.status_code == 200
     assert resp.json()["needs_setup"] is True
+
+
+def test_setup_status_rate_limited_on_second_call(client):
+    """Second /setup-status call within the cooldown window returns 429 with Retry-After."""
+    # First call succeeds.
+    resp1 = client.get("/api/v1/auth/setup-status")
+    assert resp1.status_code == 200
+
+    # Immediate second call is rate-limited.
+    resp2 = client.get("/api/v1/auth/setup-status")
+    assert resp2.status_code == 429
+    assert "Retry-After" in resp2.headers
+    retry_after = int(resp2.headers["Retry-After"])
+    assert 1 <= retry_after <= 60

backend/tests/test_langgraph_auth.py

@@ -63,7 +63,7 @@ def test_invalid_jwt_raises_401():
     with pytest.raises(Auth.exceptions.HTTPException) as exc:
         asyncio.run(authenticate(_req({"access_token": "garbage"})))
     assert exc.value.status_code == 401
-    assert "Token error" in str(exc.value.detail)
+    assert "Invalid token" in str(exc.value.detail)
 
 
 def test_expired_jwt_raises_401():
@@ -295,7 +295,7 @@ def test_csrf_post_matching_token_proceeds_to_jwt():
         )
     # Past CSRF, rejected by JWT decode
     assert exc.value.status_code == 401
-    assert "Token error" in str(exc.value.detail)
+    assert "Invalid token" in str(exc.value.detail)
 
 
 def test_csrf_put_requires_token():