f08aef1804
* Rebuild Studio branch on top of main * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix security and code quality issues for Studio PR #4237 - Validate models_dir query param against allowed directory roots to prevent path traversal in /api/models/local endpoint - Replace string startswith() with Path.is_relative_to() for frontend path traversal check in serve_frontend - Sanitize SSE error messages to not leak exception details to clients (4 locations in inference.py) - Bind port-discovery socket to 127.0.0.1 instead of all interfaces in llama_cpp backend - Import datasets_root and resolve_output_dir in embedding training function to fix NameError and use managed output directory - Remove stale .gitignore entries for package-lock.json and test directories so tests can be tracked in version control - Add venv-reexecution logic to ui CLI command matching the studio command behavior * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Move models_dir path validation before try/except block The HTTPException(403) was inside the try/except Exception handler, so it would be caught and re-raised as a 500. Moving the validation before the try block ensures the 403 is returned directly and also makes the control flow clearer for static analysis (path is validated before any filesystem operations). * Use os.path.realpath + startswith for models_dir validation CodeQL py/path-injection does not recognize Path.is_relative_to() as a sanitizer. Switched to os.path.realpath + str.startswith which is a recognized sanitizer pattern in CodeQL's taint analysis. The startswith check uses root_str + os.sep to prevent prefix collisions (e.g. /app/models_evil matching /app/models). * Never pass user input to Path constructor in models_dir validation CodeQL traces taint through Path(resolved) even after a startswith barrier guard. Fix: the user-supplied models_dir is only used as a string for comparison against allowed roots. The Path object passed to _scan_models_dir comes from the trusted allowed_roots list, not from user input. This fully breaks the taint chain. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
108 lines
3.5 KiB
Python
108 lines
3.5 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
import secrets
|
|
from datetime import datetime, timedelta, timezone
|
|
from typing import Optional
|
|
|
|
from fastapi import Depends, HTTPException, status
|
|
from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
|
|
import jwt
|
|
|
|
from .storage import load_jwt_secret, save_refresh_token, verify_refresh_token
|
|
|
|
ALGORITHM = "HS256"
|
|
ACCESS_TOKEN_EXPIRE_MINUTES = 60
|
|
REFRESH_TOKEN_EXPIRE_DAYS = 7
|
|
|
|
# Load stable secret from SQLite (set during first-time setup)
|
|
# This will raise RuntimeError if auth hasn't been initialized yet
|
|
try:
|
|
SECRET_KEY = load_jwt_secret()
|
|
except RuntimeError:
|
|
# Fallback: use a temporary secret until setup is complete
|
|
# This allows the app to start, but protected routes will fail until setup
|
|
SECRET_KEY = secrets.token_urlsafe(64)
|
|
|
|
security = HTTPBearer() # Reads Authorization: Bearer <token>
|
|
|
|
|
|
def create_access_token(
|
|
subject: str,
|
|
expires_delta: Optional[timedelta] = None,
|
|
) -> str:
|
|
"""
|
|
Create a signed JWT for the given subject (e.g. username).
|
|
|
|
Tokens are valid across restarts because SECRET_KEY is stored in SQLite.
|
|
"""
|
|
to_encode = {"sub": subject}
|
|
expire = datetime.now(timezone.utc) + (
|
|
expires_delta or timedelta(minutes = ACCESS_TOKEN_EXPIRE_MINUTES)
|
|
)
|
|
to_encode.update({"exp": expire})
|
|
return jwt.encode(to_encode, SECRET_KEY, algorithm = ALGORITHM)
|
|
|
|
|
|
def create_refresh_token(subject: str) -> str:
|
|
"""
|
|
Create a random refresh token, store its hash in SQLite, and return it.
|
|
|
|
Refresh tokens are opaque (not JWTs) and expire after REFRESH_TOKEN_EXPIRE_DAYS.
|
|
"""
|
|
token = secrets.token_urlsafe(48)
|
|
expires_at = datetime.now(timezone.utc) + timedelta(days = REFRESH_TOKEN_EXPIRE_DAYS)
|
|
save_refresh_token(token, subject, expires_at.isoformat())
|
|
return token
|
|
|
|
|
|
def refresh_access_token(refresh_token: str) -> Optional[str]:
|
|
"""
|
|
Validate a refresh token and issue a new access token.
|
|
|
|
The refresh token itself is NOT consumed — it stays valid until expiry.
|
|
Returns a new access_token or None if the refresh token is invalid/expired.
|
|
"""
|
|
username = verify_refresh_token(refresh_token)
|
|
if username is None:
|
|
return None
|
|
return create_access_token(subject = username)
|
|
|
|
|
|
def reload_secret() -> None:
|
|
"""
|
|
Reload the JWT secret from SQLite.
|
|
|
|
Call this after setup to ensure new tokens use the persistent secret.
|
|
"""
|
|
global SECRET_KEY
|
|
SECRET_KEY = load_jwt_secret()
|
|
|
|
|
|
async def get_current_subject(
|
|
credentials: HTTPAuthorizationCredentials = Depends(security),
|
|
) -> str:
|
|
"""
|
|
FastAPI dependency to validate the JWT and return the subject.
|
|
|
|
Use this as a dependency on routes that should be protected, e.g.:
|
|
|
|
@router.get("/secure")
|
|
async def secure_endpoint(current_subject: str = Depends(get_current_subject)):
|
|
...
|
|
"""
|
|
token = credentials.credentials
|
|
try:
|
|
payload = jwt.decode(token, SECRET_KEY, algorithms = [ALGORITHM])
|
|
subject: Optional[str] = payload.get("sub")
|
|
if subject is None:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_401_UNAUTHORIZED,
|
|
detail = "Invalid token payload",
|
|
)
|
|
return subject
|
|
except jwt.InvalidTokenError:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_401_UNAUTHORIZED,
|
|
detail = "Invalid or expired token",
|
|
)
|