* Fix AgentRejectAction handling
* Add ManagerAgent to integration tests
* Fix regenerate.sh
* Fix merge
* Update README for micro-agents
* Add test reject to regenerate.sh
* regenerate.sh: Add support for running a specific test and/or agent
* Refine reject schema, and allow ManagerAgent to handle reject
* Add test artifacts for test_simple_task_rejection
* Fix manager agent tests
* Fix README
* test_simple_task_rejection: check final agent state
* Integration test: exit if mock prompt not found
* Update test_simple_task_rejection tests
* Fix test_edits test artifacts after prompt update
* Fix ManagerAgent test_edits
* WIP
* Fix tests
* update test_edits for ManagerAgent
* Skip local sandbox for reject test
* Fix test comparison
This PR fixes#1897. In addition, this PR fixes and tweaks a few micro-agents.
For the first time, I am able to use ManagerAgent to complete test_write_simple_script and test_edits tasks in integration tests, so this PR also adds ManagerAgent as part of integration tests. test_write_simple_script involves delegation to CoderAgent while test_edits involves delegation to TypoFixerAgent.
Also for the first time, I am able to use DelegateAgent to complete test_write_simple_script and test_edits tasks in integration tests, so this PR also adds DelegateAgent as part of integration tests. It involves delegation to StudyRepoForTaskAgent, CoderAgent and VerifierAgent.
This PR is a blocker for #1735 and likely #1945.
* feat: add max_budget_per_task configuration to control task cost
* Fix test_arg_parser.py
* Use the config.max_budget_per_task as default value
* Add max_budget_per_task to core/main.py as well
* Update opendevin/controller/agent_controller.py
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>
---------
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>
* properly log user messages;
format browser action/obs, summarize action, messages properly for logging
* add source to message
* add spaces for printing
* Refactor monologue to use the messages in state history
* add messages, clean up
* fix monologue
* update integration tests
* move private method
* update SWE agent to use the history from State
* integration tests for SWE agent
* rename monologue to initial_thoughts, since that is what it is
* Refactor monologue to use the messages in state history
remove now unused method
* is_stuck update
* fix is_stuck
* unit tests
* fix tests
* Revert "Refactor monologue to use the messages in state history"
This reverts commit 76b4b765ef.
* Override eq for CmdOutputObservation to ignore the pid, compare the actual command only
* Revert "Override eq for CmdOutputObservation to ignore the pid, compare the actual command only"
This reverts commit 6418d856b5.
* improve error info logging
* Move assignment of self.state.error to report_error function
* only log exception to state, but not to user
---------
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>
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 06f0155bc1.
* 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 6cc8961133.
* 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
