mirror of https://github.com/All-Hands-AI/OpenHands.git synced 2026-04-29 03:00:45 -04:00

Files

Xingyao Wang e45d46c993 [Arch] Implement EventStream Runtime Client with Jupyter Support using Agnostic Sandbox (#2879 )

* support loading a particular runtime class via config.runtime (default to server to not break things)

* move image agnostic util to shared runtime util

* move dependency

* include poetry.lock in sdist

* accept port as arg for client

* make client start server with specified port

* update image agnostic utility for eventstream runtime

* make client and runtime working with REST API

* rename execute_server

* add plugin to initialize stuff inside es-runtime;
cleanup runtime methods to delegate everything to container

* remove redundant ls -alh

* fix jupyter

* improve logging in agnostic sandbox

* improve logging of test function

* add read & edit

* update agnostic sandbox

* support setting work dir at start

* fix file read/write test

* fix unit test

* update tescase

* Fix unit test again

* fix unit test again again

2024-07-12 01:52:26 +08:00

auth

Refactor session management (#1810 )

2024-05-22 18:33:16 +00:00

data_models

Add links to a feedback sharing site (#2580 )

2024-06-22 09:36:31 +02:00

mock

Refactor session management (#1810 )

2024-05-22 18:33:16 +00:00

session

[Arch] Implement EventStream Runtime Client with Jupyter Support using Agnostic Sandbox (#2879 )

2024-07-12 01:52:26 +08:00

__init__.py

feat: websocket connection management and sandbox bound to session. (#559 )

2024-04-05 12:19:52 -05:00

listen.py

feat: Implement user confirmation mode, request confirmation when running bash/python code in this mode (#2774 )

2024-07-11 14:57:21 +03:00

README.md

[Arch] Remove supports for Background Commands (#2803 )

2024-07-06 03:38:05 +08:00

README.md

OpenDevin Server

This is a WebSocket server that executes tasks using an agent.

Install

Follow the instructions in the base README.md to install dependencies and set up.

Start the Server

uvicorn opendevin.server.listen:app --reload --port 3000

Test the Server

You can use websocat to test the server.

websocat ws://127.0.0.1:3000/ws
{"action": "start", "args": {"task": "write a bash script that prints hello"}}

Supported Environment Variables

LLM_API_KEY=sk-... # Your OpenAI API Key
LLM_MODEL=gpt-4o   # Default model for the agent to use
WORKSPACE_BASE=/path/to/your/workspace # Default absolute path to workspace

API Schema

There are two types of messages that can be sent to, or received from, the server:

Actions
Observations

Actions

An action has three parts:

action: The action to be taken
args: The arguments for the action
message: A friendly message that can be put in the chat log

There are several kinds of actions. Their arguments are listed below. This list may grow over time.

initialize - initializes the agent. Only sent by client.
- model - the name of the model to use
- directory - the path to the workspace
- agent_cls - the class of the agent to use
start - starts a new development task. Only sent by the client.
- task - the task to start
read - reads the content of a file.
- path - the path of the file to read
write - writes the content to a file.
- path - the path of the file to write
- content - the content to write to the file
run - runs a command.
- command - the command to run
browse - opens a web page.
- url - the URL to open
recall - searches long-term memory
- query - the query to search for
think - Allows the agent to make a plan, set a goal, or record thoughts
- thought - the thought to record
finish - agent signals that the task is completed

Observations

An observation has four parts:

observation: The observation type
content: A string representing the observed data
extras: additional structured data
message: A friendly message that can be put in the chat log

There are several kinds of observations. Their extras are listed below. This list may grow over time.

read - the content of a file
- path - the path of the file read
browse - the HTML content of a url
- url - the URL opened
run - the output of a command
- command - the command run
- exit_code - the exit code of the command
recall - the result of a search
- query - the query searched for
chat - a message from the user