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

Files

Robert Brennan b028bd46bb Use messages to drive tasks (#1688 )

* finish is working

* start reworking main_goal

* remove main_goal from microagents

* remove main_goal from other agents

* fix issues

* revert codeact line

* make plan a subclass of task

* fix frontend for new plan setup

* lint

* fix type

* more lint

* fix build issues

* fix codeact mgs

* fix edge case in regen script

* fix task validation errors

* regenerate integration tests

* fix up tests

* fix sweagent

* revert codeact prompt

* update integration tests

* update integration tests

* handle loading state

* Update agenthub/codeact_agent/codeact_agent.py

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

* Update opendevin/controller/agent_controller.py

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

* Update agenthub/codeact_agent/codeact_agent.py

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

* Update opendevin/controller/state/plan.py

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

* update docs

* regenerate tests

* remove none from state type

* revert test files

* update integration tests

* rename plan to root_task

* revert plugin perms

* regen integration tests

* tweak integration script

* prettier

* fix test

* set workspace up for regeneration

* regenerate tests

* Change directory of copy

* Updated tests

* Disable PlannerAgent test

* Fix listen

* Updated prompts

* Disable planner again

* Make codecov more lenient

* Update agenthub/README.md

* Update opendevin/server/README.md

* re-enable planner tests

* finish top level tasks

* regen planner

* fix root task factory

---------

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>
Co-authored-by: Graham Neubig <neubig@gmail.com>
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>

2024-05-13 23:14:15 +00:00

agent

Use messages to drive tasks (#1688 )

2024-05-13 23:14:15 +00:00

auth

Use generic types (#1680 )

2024-05-10 04:21:22 +02:00

mock

Migrate to new folder structure in preparation for refactor (#1531 )

2024-05-02 17:01:54 +00:00

session

refactor : delete useless messages.json messages (#1706 )

2024-05-11 11:59:05 +00:00

__init__.py

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

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

listen.py

Use messages to drive tasks (#1688 )

2024-05-13 23:14:15 +00:00

README.md

Default to less expensive gpt-3.5-turbo model (#1675 )

2024-05-09 19:11:27 -04:00

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: https://github.com/vi/websocat

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-3.5-turbo # Default model for the agent to use
WORKSPACE_BASE=/path/to/your/workspace # Default path to model's 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
- background - if true, run the command in the background
kill - kills a background command
- id - the ID of the background command to kill
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