This PR includes three changes:
1) Iteration reminder should start with MAX_ITERATIONS from config rather than default value 100
2) In the first prompt, we should tell the LLM it has `MAX_ITERATIONS - 1` turns left, rather than `MAX_ITERATIONS - 2`
3) Remove legacy ITERATION_REMINDER config
* support returning states at the end of controller
* remove return None
* fix issue of overriding final state
* return the final state on close
* merge AgentState with State
* fix integration test
* add ChangeAgentStateAction to history in attempt to fix integration
* add back set agent state
* update tests
* update tests
* directly return get state
* add back the missing .close()
* Update typo in opendevin/core/main.py
---------
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>
* mypy is invaluable
* fix config, add test
* Add new-style toml support
* add singleton, small doc fixes
* fix some cases of loading toml, clean up, try to make it clearer
* Add defaults_dict for UI
* allow config to be mutable
error handling
fix toml parsing
* remove debug stuff
* Adapt Makefile
* Add defaults for temperature and top_p
* update to CodeActAgent
* comments
* fix unit tests
* implement groups of llm settings (CLI)
* fix merge issue
* small fix sandboxes, small refactoring
* adapt LLM init to accept overrides at runtime
* reading config is enough
* Encapsulate minimally embeddings initialization
* agent bug fix; fix tests
* fix sandboxes tests
* refactor globals in sandboxes to properties
* Add AgentRejectAction across multiple modules
This commit introduces the AgentRejectAction class and integrates it across various modules and actions. It includes updates to READMEs, action definitions, and agent controllers to handle the new 'reject' action. This functionality will allow agents to properly signal task rejection.
* Fix unit test
* Remove wrong generates attributes from a few micro-agents
* remove extra actions
* remove message observations
* support null obs
* handle null obs
* fix frontend for changes
* fix the way messages flow to the UI
* change think to message
* add regen script
* regenerate all integration tests
* change task
* remove gh test
* fix messages
* fix tests
* help agent exit after hitting max iter
* Update opendevin/events/observation/success.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>
---------
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
* move towards event stream
* refactor agent state changes
* move agent state logic
* fix callbacks
* break on finish
* closer to working
* change frontend to accomodate new flow
* handle start action
* fix locked stream
* revert message
* logspam
* no async on close
* get rid of agent_task
* fix up closing
* better asyncio handling
* sleep to give back control
* fix key
* logspam
* update frontend agent state actions
* fix pause and cancel
* delint
* fix map
* delint
* wait for agent to finish
* fix unit test
* event stream enums
* fix merge issues
* fix lint
* fix test
* fix test
* add user message action
* add user message action
* fix up user messages
* fix main.py flow
* refactor message waiting
* lint
* fix test
* fix test
* simplify if/else
* fix state reset
* logspam
* add error status
* minor changes to control bar
* handle user messages when not awaiting
* restart agent after stopping
* Update opendevin/controller/agent_controller.py
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
* delint
* refactor initialize
* delint
* fix dispatch
---------
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
* move towards event stream
* refactor agent state changes
* move agent state logic
* fix callbacks
* break on finish
* closer to working
* change frontend to accomodate new flow
* handle start action
* fix locked stream
* revert message
* logspam
* no async on close
* get rid of agent_task
* fix up closing
* better asyncio handling
* sleep to give back control
* fix key
* logspam
* update frontend agent state actions
* fix pause and cancel
* delint
* fix map
* delint
* wait for agent to finish
* fix unit test
* event stream enums
* fix merge issues
* fix lint
* fix test
* fix test
* add user message action
* add user message action
* fix up user messages
* fix main.py flow
* refactor message waiting
* lint
* fix test
* fix test
* Feat: add lint frontend and lint all to Makefile.
* style codes.
* Remove redundant target.
---------
Co-authored-by: Jim Su <jimsu@protonmail.com>
Co-authored-by: Robert Brennan <accounts@rbren.io>
* add a single-threaded server serving browsergym
* update poetry
* update browser page content
* add import to make sure browsergym environments are registered properly
* remove flask server, use multiprocess impl and Pipe
* fix
* refactor BrowserEnv
* update browser action and obs to include more complete info
* fix screenshot
* update poetry lock
* add playwright install to workflow
* update
* add better html to text conversion
* update for better text conversion to maintain parity with the current handling of browseurlaction
* update
* update poetry
* update multiprocessing mp
* fix multiprocessing
* update
* update github workflow
---------
Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>
* initialize plugin definition
* initialize plugin definition
* simplify mixin
* further improve plugin mixin
* add cache dir for pip
* support clean up cache
* add script for setup jupyter and execution server
* integrate JupyterRequirement to ssh_box
* source bashrc at the end of plugin load
* add execute_cli that accept code via stdin
* make JUPYTER_EXEC_SERVER_PORT configurable via env var
* increase background cmd sleep time
* Update opendevin/sandbox/plugins/mixin.py
Co-authored-by: Robert Brennan <accounts@rbren.io>
* add mixin to base class
* make jupyter requirement a dataclass
* source plugins only when >0 requirements
* add `sandbox_plugins` for each agent & have controller take care of it
* update build.sh to make logs available in /opendevin/logs
* switch to use config for lib and cache dir
* Add SANDBOX_WORKSPACE_DIR into config
* Add SANDBOX_WORKSPACE_DIR into config
* fix occurence of /workspace
* fix permission issue with /workspace
* use python to implement execute_cli to avoid stdin escape issue
* add IPythonRunCellAction and get it working
* wait until jupyter is avaialble
* support plugin via copying instead of mounting
* add agent talk action
* support follow-up user language feedback
* add __str__ for action to be printed better
* only print PLAN at the beginning
* wip: update codeact agent
* get rid the initial messate
* update codeact agent to handle null action;
add thought to bash
* dispatch thought for RUN action as well
* fix weird behavior of pxssh where the output would not flush correctly
* make ssh box can handle exit_code properly as well
* add initial version of swe-agent plugin;
* rename swe cursors
* split setup script into two and create two requirements
* print SWE-agent command documentation
* update swe-agent to default to no custom docs
* add initial version of swe-agent plugin;
* rename swe cursors
* split setup script into two and create two requirements
* print SWE-agent command documentation
* update swe-agent to default to no custom docs
* update dockerfile with dependency from swe-agent
* make env setup a separate script for .bashrc source
* add wip prompt
* fix mount_dir for ssh_box
* update prompt
* fix mount_dir for ssh_box
* default to use host network
* default to use host network
* move prompt to a separate file
* fix swe-tool plugins;
add missing _split_string
* remove hostname from sshbox
* update the prompt with edit functionality
* fix swe-tool plugins;
add missing _split_string
* add awaiting into status bar
* fix the bug of additional send event
* remove some print action
* move logic to config.py
* remove debugging comments
* make host network as default
* make WORKSPACE_MOUNT_PATH as abspath
* implement execute_cli via file cp
* Revert "implement execute_cli via file cp"
This reverts commit 06f0155bc17d1f99097e71b83b2143f6e8092654.
* add codeact dependencies to default container
* add IPythonRunCellObservation
* add back cache dir and default to /tmp
* make USE_HOST_NETWORK a bool
* revert use host network to false
* add temporarily fix for IPython RUN action
* update prompt
* revert USE_HOST_NETWORK to true since it is not affecting anything
* attempt to fix lint
* remove newline
* fix jupyter execution server
* add `thought` to most action class
* fix unit tests for current action abstraction
* support user exit
* update test cases with the latest action format (added 'thought')
* fix integration test for CodeActAGent by mocking stdin
* only mock stdin for tests with user_responses.log
* remove -exec integration test for CodeActAgent since it is not supported
* remove specific stop word
* fix comments
* improve clarity of prompt
* fix py lint
* fix integration tests
* sandbox might failed in chown due to mounting, but it won't be fatal
* update debug instruction for sshbox
* fix typo
* get RUN_AS_DEVIN and network=host working with app sandbox
* get RUN_AS_DEVIN and network=host working with app sandbox
* attempt to fix the workspace base permission
* sandbox might failed in chown due to mounting, but it won't be fatal
* update sshbox instruction
* remove default user id since it will be passed in the instruction
* revert permission fix since it should be resolved by correct SANDBOX_USER_ID
* the permission issue can be fixed by simply provide correct env var
* remove log
* set sandbox user id to getuid by default
* move logging to initializer
* make the uid consistent across host, app container, and sandbox
* remove hostname as it causes sudo issue
* fix permission of entrypoint script
* make the uvicron app run as host user uid for jupyter plugin
* add warning message
* update dev md for instruction of running unit tests
* add back unit tests
* revert back to the original sandbox implementation to fix testcases
* revert use host network
* get docker socket gid and usermod instead of chmod 777
* allow unit test workflow to find docker.sock
* make sandbox test working via patch
* fix arg parser that's broken for some reason
* try to fix app build disk space issue
* fix integration test
* Revert "fix arg parser that's broken for some reason"
This reverts commit 6cc89611337bb74555fd16b4be78681fb7e36573.
* update Development.md
* cleanup intergration tests & add exception for CodeAct+execbox
* fix config
* implement user_message action
* fix doc
* fix event dict error
* fix frontend lint
* revert accidentally changes to integration tests
* revert accidentally changes to integration tests
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
Co-authored-by: Robert Brennan <contact@rbren.io>
* feat: make the response of agent_controller better to process when exception occurred during executing step.
* Update opendevin/controller/agent_controller.py
---------
Co-authored-by: aaren.xzh <aaren.xzh@antfin.com>
Co-authored-by: Robert Brennan <accounts@rbren.io>
* Add malformed JSON where we don't even start finding actions
* Send any exception during JSON parsing back
* Use specific exceptions
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* refactor error handling so not all exceptions are caught
* revert
* Send the failed decoding back to the LLM (#1322)
* fix quotes
---------
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
* Add checks to stop infinite loops
* Send an AgentErrorObservation for the user to see an oops loop
* (NullAction, Obs) problem should be (NullAction, error Obs)
* Merge the two with AgentErrorObs.
* Update opendevin/controller/agent_controller.py
* initialize plugin definition
* initialize plugin definition
* simplify mixin
* further improve plugin mixin
* add cache dir for pip
* support clean up cache
* add script for setup jupyter and execution server
* integrate JupyterRequirement to ssh_box
* source bashrc at the end of plugin load
* add execute_cli that accept code via stdin
* make JUPYTER_EXEC_SERVER_PORT configurable via env var
* increase background cmd sleep time
* Update opendevin/sandbox/plugins/mixin.py
Co-authored-by: Robert Brennan <accounts@rbren.io>
* add mixin to base class
* make jupyter requirement a dataclass
* source plugins only when >0 requirements
* add `sandbox_plugins` for each agent & have controller take care of it
* update build.sh to make logs available in /opendevin/logs
* switch to use config for lib and cache dir
* fix permission issue with /workspace
* use python to implement execute_cli to avoid stdin escape issue
* wait until jupyter is avaialble
* support plugin via copying instead of mounting
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* Clean up manual sleep
* Add default retries and document them.
* Add doctrings to llm
* Add exponential backoff for rate limiting errors
* Get embeddings for the action and its own content, not the user message
* Add a few bad exceptions to stop loop
* Stop loop when the step has no action
* Add action with content, no message, to history
* make retry settings customizable
* fix condense to stop the loop for the same reasons as completion
* Add 500-504 exception to retries
* document the retry variables
* Add retries and limits for embeddings. Replaces llama-index hard-coded decorator.
* Rename to retry_min_wait and retry_max_wait
* feat: support controlling agent task state.
* feat: add agent task state to agent status bar.
* feat: add agent task control bar to FE.
* Remove stop agent task action.
* Merge pause and resume buttons into one button; Add loading and disabled status for action buttons.
* Apply suggestions from code review
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* Refactor print_to_color into a color formatter
misc fixes
catch ValueErrors and others from Router initialization
add default methods
* Tweak console log formatting, clean up after rebasing exceptions out
* Fix prompts/responses
* clean up
* keep regular colors when no msg_type
* fix filename
* handle file log first
* happy mypy
* ok, mypy
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* CI: Add autopep8 linter
Currently, we have autopep8 as part of pre-commit-hook. To ensure
consistent behaviour, we should have it in CI as well.
Moreover, pre-commit-hook contains a double-quote-string-fixer hook
which changes all double quotes to single quotes, but I do observe
some PRs with massive changes that do the opposite way. I suspect
that these authors 1) disable or circumvent the pre-commit-hook,
and 2) have other linters such as black in their IDE, which
automatically change all single quotes to double quotes. This
has caused a lot of unnecessary diff, made review really hard,
and led to a lot of conflicts.
* Use -diff for autopep8
* autopep8: Freeze version in CI
* Ultimate fix
* Remove pep8 long line disable workaround
* Fix lint.yml
* Fix all files under opendevin and agenthub
* feat: add agent manager to manage all agents;
* extract the host ssh port to prevent conflict.
* clean all containers with prefix is sandbox-
* merge from upstream/main
* merge from upstream/main
* Update frontend/src/state/settingsSlice.ts
* Update opendevin/sandbox/ssh_box.py
* Update opendevin/sandbox/exec_box.py
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* Add logging config for the app and for llm debug
* - switch to python, add special llm logger
- add logging to sandbox.py
- add session.py
- add a directory per session
- small additions for AgentController
* - add sys log, but try to exclude litellm; log llm responses as json
* Update opendevin/_logging.py
Co-authored-by: Anas DORBANI <95044293+dorbanianas@users.noreply.github.com>
* - use standard file naming
- quick pass through a few more files
* fix ruff
* clean up
* mypy types
* make mypy happy
---------
Co-authored-by: Anas DORBANI <95044293+dorbanianas@users.noreply.github.com>
* feat: websocket connection management and sandbox bound to session.
* fix: set default value to id
* feat: add session management.
* fix for mypy
* fix for mypy
* fix the pnpm-lock.
* fix the default model is empty will throw error.
