Spaces:
Runtime error
Runtime error
Commit History
-
solved issue
f1c3c6d
-
Add multi-LLM support, settings & migrationsβ
Introduce a multi-LLM architecture and related settings plus DB migrations. Added alembic migrations to add missing columns and new llm config tables; new backend/integrations/llm modules (providers.py, factory.py, registry.py, resolver.py) to replace the global client pattern and enable per-task LLM resolution. Added settings route for LLM provider/task management and wired services (planner, executor, chat, response analyzer) to use get_llm_for_task (including async plan generation and a /plan/stream SSE endpoint). Updated routes and services to use DB session and timezone-aware datetimes, added frontend pages/components (SettingsPage, UsagePage, workflow subcomponents), and updated env.example with AUTH credentials. Misc: small .claude tweaks and other bugfixes related to planning/streaming, token usage logging, and Vite proxy config.1e24842
-
changed the project structure and ui , updated security and enhanced the project
3f78860 -
Add auth, credential encryption, and session ownership (Items 3, 5, 6)β
Item 3 β Authentication: - backend/core/auth.py: create_access_token() + verify_token() dependency (JWT/PyJWT) - backend/app/api/routes/auth.py: POST /auth/login, GET /auth/me (public) - backend/main.py: all API routers now protected with Depends(verify_token) - Config: AUTH_USERNAME, AUTH_PASSWORD, JWT_SECRET, JWT_EXPIRE_HOURS - Frontend: token stored in module memory (never localStorage); axios request interceptor adds Authorization header; 401 broadcasts auth:logout event - LoginPage.jsx: themed sign-in card shown before app loads - App.jsx: guards main app behind isAuthenticated state Item 5 β Credential encryption: - backend/core/crypto.py: encrypt_credentials()/decrypt_credentials() via Fernet - Transparent backwards-compat: legacy plaintext dicts pass through unchanged - specs.py: encrypts on save, decrypts on GET /credentials and GET /specs/:id - execution.py: decrypts stored creds before passing to LLM planner and executor - Config: ENCRYPTION_KEY (Fernet key, optional β waβ¦098f3ea -
Security & reliability: Phase 1β3 fixes (Items 1β15)β
- git rm --cached tracked binary uploads from documents/ - Add .env.example with placeholder values - Extract shared Limiter to backend/core/limiter.py (Item 14) - Tighten CORS: restrict allow_methods and allow_headers (Item 7) - Fix traceback import inside except in chat.py; add logger (Item 13) - Fix DNS rebinding SSRF: resolve IP once via resolve_safe_ip(), pin to resolved IP with Host header so httpx cannot re-resolve (Item 4) - Fix mutable default args in prepare_step_request (Item 10) - Wrap prepare_step_request in asyncio.to_thread() (Item 8) - Add LLM parse retry with AppError after 2 failures in api_executor (Item 9) - Replace print() with logger calls in database.py and chat_assistant.py (Item 12) - Increase response truncation to 4000 chars, JSON-aware, configurable (Item 15) - Add RESPONSE_TRUNCATION_LIMIT to settings (Item 15) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>c6f3411
-
Refactor backend: split routes, add services & testsβ
Restructure the backend into modular API route files and core services. Added new FastAPI route modules (assets, chat, execution, history, sessions, specs) and supporting core modules (config, logging, errors, url_guard) plus LLM integration client and many service updates (api_executor, chat_assistant, llm_planner, response_analyzer). Implemented SSRF protection, rate limiting, spec upload/parse, execution planning and analysis, media hub asset handling, session/context endpoints, and exportable history. Added tests, pytest.ini, updated requirements and .gitignore, removed .env.example, and added documentation/plans/screenshots and upload placeholders. Overall prepares the project for clearer separation of concerns, improved security, and test coverage.ef865f2