hordelab/hub

0 Fork 0

T

Shivering Ocelot 4e15b44d39 Refactor agent execution to use AgentRun with OpenAI-compatible API

Major refactoring to support isolated run objects with streaming, events, and OpenAI-compatible endpoints.

## Backend Changes

- **Agent class**: Added `run()` method, `received_message()` wraps chat into AgentRun
- **AgentRun class**: New class for run state with event system, serialization, and user tracking
- **inference.py**: Complete refactor with `build_messages()`, `chat_completion()`, tool support for llama-cpp/ollama/replicate
- **tools.py**: New centralized tool management (ToolSpec, ToolParameter, format_tools_for_engine)
- **tools.py**: Removed legacy Toolset/Action/ToolDescription system
- **server.py**: Added OpenAI-compatible `/api/openai/v1/chat/completions` endpoint with streaming support
- **temporary.py**: Added `self.runs` dict to State class
- **expert.py**: Refactored to use new Agent.run() signature
- **scripted.py**: Updated to raise NotImplementedError

## Frontend Changes

- **backend.js**: Added `onRunEvents()` for run event subscriptions
- **Sidebar.vue**: Added runs navigation mode
- **router/index.js**: Renamed User route to RunsView
- **RunsView.vue**: New view for listing/monitoring agent runs

## Breaking Changes

- Agent `prompt()` signature changed: `(instruction, input=None, **kwargs)` instead of `(content)`
- Agent `received_message()` must use AgentRun pattern
- Tools.py removed, functionality moved to tool.py
- Deprecated tool prompt/action system removed

2026-05-25 18:05:17 -05:00

backend

Refactor agent execution to use AgentRun with OpenAI-compatible API

2026-05-25 18:05:17 -05:00

cli

Implement basic agent and toolset functionality

2025-05-21 20:18:01 -05:00

frontend

Refactor agent execution to use AgentRun with OpenAI-compatible API

2026-05-25 18:05:17 -05:00

testing

Temporary agents and chats

2026-04-16 15:16:03 -05:00

.gitignore

Refactor agent execution to use AgentRun with OpenAI-compatible API

2026-05-25 18:05:17 -05:00

Makefile

install npm dependencies, add last_edit message field

2025-07-14 17:11:56 -05:00

package.json

Temporary agents and chats

2026-04-16 15:16:03 -05:00

readme.md

backend: separate App and server, add websocket endpoint, accept data directory command argument. initialize sqlalchemy database and models in new module. frontend: create backend class for managing ws connection, move ui to chat_screen, create scaffold chat and agent classes.

2025-05-06 17:50:57 -05:00

run.sh

Temporary agents and chats

2026-04-16 15:16:03 -05:00

scratchpad.md

Token based authentication

2025-05-28 01:15:46 -05:00

readme.md

Backend

To run the Flask server, follow these steps:

Build and activate the virtual environment, install the required dependencies, and build the gui by running make with the default target:
```
make
```
Run the server using the provided script:
```
./run.sh
```

Now, visit http://127.0.0.1:5000 in your web browser to see the application in action.

Frontend

Frontend uses flutter. For Ubuntu you can use this guideline to install it.

Configuration

You can set the backend URL for Android and native builds using the environment variable BACKEND_URL. Make sure to set this variable before running the application. Defaults to null if nothing is set.