- Update `workflow_runner.py` to retrieve `Skill Individual` items with their real `agent_id` rather than names, preventing assignment mismatches when routing via `WorkerCluster`.
- Update `ConsciousnessNode` prompts to strictly instruct the LLM to output real `agent_id`s in `agent_id` workflow fields.
- Update `WorkStep` schemas to reflect the requirement of `agent_id`.
- Add a 2-second polling interval in the frontend `LeftPanel.tsx` to automatically update the workflow list state rather than fetching only once upon tab selection.
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
- Added `available_skills` to `ConsciousnessNodeDeps` and `ForWorkflowEngineInput`.
- Updated `WorkflowRunningEngine` to retrieve all available skills from `GlobalStateMachine` and pass them during `ForWorkflowEngineInput` creation.
- Updated `ConsciousnessNode` to dynamically inject these skills into the system prompt. This allows the AI to correctly insert `skill_individuals` into `PretorWorkflow` steps (as tools for `composite_individual` or `primary_individual`).
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix: resolve 422 error adding deepseek provider
- Updated `pretor/api/provider.py` to allow "deepseek" as a valid Literal in `ProviderRegister` Pydantic model.
- Validated tests to ensure the backend can correctly receive deepseek configurations.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix: complete deepseek provider registration wiring
- Updated `pretor/core/global_state_machine/provider_manager.py` to correctly map `"deepseek"` to `DeepseekProvider`.
- Updated `pretor/core/global_state_machine/model_provider/__init__.py` to export `DeepseekProvider`.
- Confirmed this fully resolves the Provider Manager failing to instantiate DeepSeek despite passing API validation.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix: support pydantic-ai decorator proxying on DeepSeekReasonerAgent
- Implemented `__getattr__` on `DeepSeekReasonerAgent` to safely proxy all unrecognized attributes (such as `@agent.system_prompt` and `@agent.tool`) directly to the underlying PydanticAI `Agent` object.
- Resolves the crash where `SupervisoryNode.create_agent()` threw an `AttributeError` when trying to decorate `system_prompt`.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* refactor: remove gemini provider from frontend and backend
- Removed `gemini` from `ProviderRegister` API validator.
- Removed `GeminiProvider` files, tests, and its mappings from `AgentFactory` and `ProviderManager`.
- Removed `gemini` from frontend TypeScript types and UI selection dropdown.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* Refactor tool loading to use static database assignment
- Add `tools` field to `WorkerIndividual` and `SystemNodeConfig` models
- Update frontend WorkerIndividualSettings to support multi-select tools and select `bound_skill` from available backend API
- Deprecate dynamic `get_tool` method during agent execution, replacing it with `load_tools_from_list` via absolute paths during agent initialization
- Fix deprecated tool loading usage across `SupervisoryNode`, `ConsciousnessNode`, `ControlNode`, and `BaseIndividual`
- Provide `reload` API route to clear `GlobalIndividualManager` state to rebuild nodes cleanly upon next request
- Fix `user_test.py` related to unhashed password assignments in testing mock object
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* Refactor tool loading to use static database assignment part 2
- Restore BaseIndividual's `_init_agent` method to inject parsed `tools_list` via absolute paths dynamically using `load_tools_from_list`
- Restore React component multi-select support for tools dropdown via `/api/v1/resource/tool` backend response integration
- Restore `user_test.py` compatibility related to access hasher assignments
- Passed 75 tests with no errors
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* Refactor tool loading to use static database assignment
- Add `tools` field to `WorkerIndividual` and `SystemNodeConfig` models
- Update frontend WorkerIndividualSettings to support multi-select tools and select `bound_skill` from available backend API
- Deprecate dynamic `get_tool` method during agent execution, replacing it with `load_tools_from_list` via absolute paths during agent initialization
- Fix deprecated tool loading usage across `SupervisoryNode`, `ConsciousnessNode`, `ControlNode`, and `BaseIndividual`
- Provide `reload` API route to clear `GlobalIndividualManager` state to rebuild nodes cleanly upon next request
- Fix `user_test.py` related to unhashed password assignments in testing mock object
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* Finalize all tool loading refactoring with complete changes
- Merged database schema enhancements for `tools` multi-select list
- Completed the `load_tools_from_list` via absolute paths utility update
- Refactored `AgentFactory` and corresponding initialization calls in `BaseIndividual`, `SupervisoryNode`, `ConsciousnessNode`, and `ControlNode` to inject statically via constructor
- Updated frontend UI `WorkerIndividualSettings` with UI for `bound_skill` selection and dynamic multi-tool selector array
- Removed all legacy usages of dynamic `tools=tool` invocation
- Provided backend `/reload` API and automatic clearing of instance cache upon individual configuration update
- Repaired mock password assignment logic in testing suite
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* Restore complete tool loading refactor logic
- Re-apply BaseIndividual tools resolution logic
- Correctly patch API, UI files, system nodes and testing scripts avoiding checkout loss
- Passed all 75 integration and unit tests successfully
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
- Removed Monitoring view and associated `/ws/state` cluster websocket route.
- Modified workflow tracing from WebSocket (`/api/v1/workflow/ws/{trace_id}`) to Server-Sent Events (`/api/v1/workflow/sse/{trace_id}`) for unidirectional pushes, introducing a new `/api/v1/workflow/reply/{trace_id}` POST route to handle incoming client replies.
- Cleaned up dummy data and unneeded links in the chat layout (LeftPanel, ChatPanel).
- Implemented file upload functionality: added a `/api/v1/adapter/client/upload` endpoint to the backend which saves files to a local `uploads` directory, and added an integrated file input triggered via the `+` button in the frontend chat interface to facilitate uploading with an automated chat message confirmation.
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix: correct actorlist handle in supervisory node and ui form reset (#30)
- Fixed `AttributeError` for `workflow_template_manager` in `SupervisoryNode` by properly unpacking the `.global_state_machine` handle from `ray_actor_hook`.
- Removed overly broad blanket `Exception` swallowing for WebSocket cancellation that caused closed loops in Uvicorn handlers to leak and dump HTTP errors.
- UI: Reset `model_id` to blank whenever a user alters the `Provider Title` to prevent stale incompatible models from breaking submission.
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* Fix provider manager and skill settings 17493544742337088454 (#31)
* fix: correct actorlist handle in supervisory node and ui form reset
- Fixed `AttributeError` for `workflow_template_manager` in `SupervisoryNode` by properly unpacking the `.global_state_machine` handle from `ray_actor_hook`.
- Removed overly broad blanket `Exception` swallowing for WebSocket cancellation that caused closed loops in Uvicorn handlers to leak and dump HTTP errors.
- UI: Reset `model_id` to blank whenever a user alters the `Provider Title` to prevent stale incompatible models from breaking submission.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix: dynamically resolve backend urls based on browser window location
- Updated `apiClient.ts` to use a relative base URL (`''`) if `VITE_API_BASE_URL` is omitted, allowing axios to infer the current domain in reverse-proxied environments.
- Updated WebSocket URL generation in `RightPanel.tsx` and `useClusterState.ts` to dynamically calculate protocol (`ws:` vs `wss:`) and host from `window.location`.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* Refactor GlobalStateMachine/PostgresDatabase reflection, error retry mechanisms, and frontend worker individual UI.
- Replaced dynamic getattr reflection in GlobalStateMachine and PostgresDatabase with explicit wrapper methods to improve stability and avoid Missing Method AttributeErrors.
- Add `get_tool_list` explicit wrapper method resolving runtime crashes.
- Implemented `RetryableError` and `NonRetryableError` base exceptions, wrapping network errors and utilizing custom `@retry_on_retryable_error` decorator on Provider requests instead of Ray actor's unsupported `retry_exceptions`.
- Added exponential backoff algorithms for WebSocket reconnections in the frontend.
- Added strict TypeScript-based schema validation for WorkflowTemplate creation payloads.
- Redesigned the Worker Individual configuration UI into a unified list containing both System Nodes and Custom Workers, supporting Add, Edit, and Delete workflows, and resolving the provider-switching bug.
- Updated unit tests to align with architectural changes.
- Cleaned up temp scripts.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* ✨ [Feature] Add frontend authentication page and 401 error interceptor (#21)
* feat: add frontend authentication page and 401 interceptor
Adds a new AuthPage component for user login and registration, integrates it into App.tsx to protect routes, and sets up an Axios interceptor to handle 401 Unauthorized responses by clearing local storage and reloading. Also fixes a missing logger attribute in WorkflowEngine for backend tests.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix: gracefully handle closed websockets
Updates the websocket endpoints in `pretor/api/cluster.py` and `pretor/api/workflow.py` to catch `RuntimeError` alongside `WebSocketDisconnect`. This prevents the application from crashing and spamming error logs when the frontend client unexpectedly closes the connection and the underlying TCP transport is closed.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* feat: add worker form and update global settings
Adds a new form in the Worker Individual Settings page to create custom worker individuals via the `/api/v1/agent/worker` endpoint. Also updates the System Settings page to remove the obsolete "Max Concurrent Workflows" setting and makes the system language and theme toggles functional by persisting to local storage and updating the document root class.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix: resolve provider owner type, resource UI, and db ready check
This commit fixes the following issues:
1. `provider_owner` type bug: Changed type from `int` to `str` in DB models and Pydantic schemas.
2. Frontend Provider Dropdown: `WorkerIndividualSettings.tsx` now uses a dropdown to select a created provider instead of a free-form input field.
3. Database Initialization Sync: Added an `asyncio.Event()` to `postgres.py` to prevent any DB actions from executing before `init_db()` is complete.
4. Resource Management UI: Added new pages `SkillSettings.tsx` and `WorkflowTemplateSettings.tsx` to handle frontend requests to manage skills and workflow templates.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix(backend): initialize async queue properly and fix auth login error handling (#18)
- Moved `self.workflow_queue = asyncio.Queue()` to the top of `WorkflowRunningEngine.run` to ensure the queue exists before coroutines start polling it, resolving initialization race conditions.
- Handled `user` object nullability check correctly in `/api/v1/auth/login` to raise `UserNotExistError` instead of crashing on attribute access.
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* feat: Integrate frontend dashboard and wire up settings endpoints
- Imported and moved the pretor_dashboard dev branch into `frontend/`.
- Configured FastAPI `PretorGateway` to mount `frontend/dist` out of the box and serve it effectively.
- Fixed `global_state_machine` Ray Actor hook references in `pretor/api/resource.py`.
- Added missing GET `/api/v1/auth/list` endpoint to list all users.
- Added missing DELETE `/api/v1/auth/{user_id}` endpoint to remove users.
- Plumbed API calls in the frontend's `UsersSettings.tsx` to get, delete, and alter the authority roles.
- Wired up provider deletion API endpoints within `ProvidersSettings.tsx`.
- Ran `npm run build` so `frontend/dist` is current.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* feat: Integrate frontend dashboard and wire up settings endpoints
- Imported and moved the pretor_dashboard dev branch into `frontend/`.
- Configured FastAPI `PretorGateway` to mount `frontend/dist` out of the box and serve it effectively.
- Fixed `global_state_machine` Ray Actor hook references in `pretor/api/resource.py`.
- Added missing GET `/api/v1/auth/list` endpoint to list all users.
- Added missing DELETE `/api/v1/auth/{user_id}` endpoint to remove users.
- Plumbed API calls in the frontend's `UsersSettings.tsx` to get, delete, and alter the authority roles.
- Wired up provider deletion API endpoints within `ProvidersSettings.tsx`.
- Ran `npm run build` so `frontend/dist` is current.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix(backend): Remove __call__ from PretorGateway and assign first user as SUPER_ADMINISTRATOR
- Removed `__call__` from `PretorGateway` in `pretor/core/api/__init__.py` to fix Ray Serve `ValueError` during initialization.
- Modified `AuthDatabase.add_user` in `pretor/core/database/module/user.py` to check for existing users. The first registered user now receives `UserAuthority.SUPER_ADMINISTRATOR` access while subsequent users get `USER` access.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix(backend): Remove __call__ from PretorGateway and assign first user as SUPER_ADMINISTRATOR
- Removed `__call__` from `PretorGateway` in `pretor/core/api/__init__.py` to fix Ray Serve `ValueError` during initialization.
- Added connection error handling in `PostgresDatabase.init_db()` to prevent startup crashes when PostgreSQL is unavailable.
- Updated `AuthDatabase.add_user` to automatically grant `SUPER_ADMINISTRATOR` privileges to the first registered user.
- Fixed unit tests in `user_test.py` that were improperly mocking `session.execute`, removing confusing stack traces during testing.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix(backend): Remove __call__ from PretorGateway and assign first user as SUPER_ADMINISTRATOR
- Removed `__call__` from `PretorGateway` in `pretor/core/api/__init__.py` to fix Ray Serve `ValueError` during initialization.
- Added connection error handling in `PostgresDatabase.init_db()` to prevent startup crashes when PostgreSQL is unavailable.
- Updated `AuthDatabase.add_user` to automatically grant `SUPER_ADMINISTRATOR` privileges to the first registered user.
- Fixed unit tests in `user_test.py` that were improperly mocking `session.execute`, removing confusing stack traces during testing.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* fix(backend): initialize async queue properly and fix auth login error handling (#18)
- Moved `self.workflow_queue = asyncio.Queue()` to the top of `WorkflowRunningEngine.run` to ensure the queue exists before coroutines start polling it, resolving initialization race conditions.
- Handled `user` object nullability check correctly in `/api/v1/auth/login` to raise `UserNotExistError` instead of crashing on attribute access.
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
* feat: Integrate frontend dashboard and wire up settings endpoints
- Imported and moved the pretor_dashboard dev branch into `frontend/`.
- Configured FastAPI `PretorGateway` to mount `frontend/dist` out of the box and serve it effectively.
- Fixed `global_state_machine` Ray Actor hook references in `pretor/api/resource.py`.
- Added missing GET `/api/v1/auth/list` endpoint to list all users.
- Added missing DELETE `/api/v1/auth/{user_id}` endpoint to remove users.
- Plumbed API calls in the frontend's `UsersSettings.tsx` to get, delete, and alter the authority roles.
- Wired up provider deletion API endpoints within `ProvidersSettings.tsx`.
- Ran `npm run build` so `frontend/dist` is current.
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>
朝夕