* Some improvements to prompts, some better exception handling for various file IO errors, added timeout and max return token configurations for the LLM api.
* More monologue prompt improvements
* Dynamically set username provided in prompt.
* Remove absolute paths from llm prompts, fetch working directory from sandbox when resolving paths in fileio operations, add customizable timeout for bash commands, mention said timeout in llm prompt.
* Switched ssh_box to disabling tty echo and removed the logic attempting to delete it from the response afterwards, fixed get_working_directory for ssh_box.
* Update prompts in integration tests to match monologue agent changes.
* Minor tweaks to make merge easier.
* Another minor prompt tweak, better invalid json handling.
* Fix lint error
* More catch-up to fix lint errors introduced by merge.
* Force WORKSPACE_MOUNT_PATH_IN_SANDBOX to match WORKSPACE_MOUNT_PATH in local sandbox mode, combine exception handlers in prompts.py.
---------
Co-authored-by: Jim Su <jimsu@protonmail.com>
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
* Add errors for non-unicode file data or command return, trim excessively long command returns.
* Fix lint issue.
* Fix lint issue (try 2).
* Realized that prompts were trimmed elsewhere and dropped the new addition.
* Some improvements to prompts, some better exception handling for various file IO errors, added timeout and max return token configurations for the LLM api.
* More monologue prompt improvements
* Dynamically set username provided in prompt.
* Remove absolute paths from llm prompts, fetch working directory from sandbox when resolving paths in fileio operations, add customizable timeout for bash commands, mention said timeout in llm prompt.
* Switched ssh_box to disabling tty echo and removed the logic attempting to delete it from the response afterwards, fixed get_working_directory for ssh_box.
* Update prompts in integration tests to match monologue agent changes.
* Minor tweaks to make merge easier.
* Another minor prompt tweak, better invalid json handling.
* Fix lint error
* More catch-up to fix lint errors introduced by merge.
---------
Co-authored-by: Jim Su <jimsu@protonmail.com>
Co-authored-by: Robert Brennan <accounts@rbren.io>
* Send the permission error to the llm
* Update opendevin/action/fileop.py
* Update opendevin/action/fileop.py
---------
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
* 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>
* Merge branch 'main' of https://github.com/JayQuimby/OpenDevin
* Using commands.sh for ACI
* parsing, prompting, and actions modifications
* added start and end index to read and write
* bug fixes and test updates
* Lint code changes to ensure code is proper
* State management, bugs, prompts
* Prompt Engineering
* exception handling
* big fixes
* more bug fixes
* merge conflicts
* Renamed SWEAgent, basic tests, bug fixes
* prompt changes, bug fixes
* merge conflicts
* merge conflict
* start and end line for read and write
* more merge conflicts
* env error
* linter error
* read fixed, prompt change, example added
* added x_line:end read operation
---------
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
* Fix: local files in the browser (at least for Windows)
The Browser works for screenshoting websites, but when the LLM tries to display a local file that he created, it can't access the full directory on Windows.
* Update browse.py
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* rearrange workspace_dir and max_step as arguments to controller
* remove unused output
* abstract each action into dataclass
* move actions
* fix action import
* move cmd manager and change method to private
* move controller
* rename action folder
* add state
* a draft of Controller & new agent abstraction
* add agent actions
* remove controller file
* add observation to perform a refractor on langchains agent
* revert to make this compatible via translation
* fix typo and translate error
* add error to observation
* index thought as dict
* refractor controller
* fix circular dependency caused by type hint
* add runnable attribute to agent
* add mixin to denote executable
* change baseclass
* make file read/write action compatible w/ docker directory
* remove event
* fix some merge issue
* fix sandbox w/ permission issue
* cleanup history abstraction since langchains agent is not really using it
* tweak to make langchains agent working
* make all actions return observation
* fix missing import
* add echo action for agent
* add error code to cmd output obs
* make cmd manager returns cmd output obs
* fix codeact agent to make it work
* fix all ruff issue
* fix mypy
* add import agenthub back
* add message for Action attribute (migrate from previous event)
* fix typo
* fix instruction setting
* fix instruction setting
* attempt to fix session
* ruff fix
* add .to_dict method for base and observation
* add message for recall
* try to simplify the state_updated_info with tuple of action and obs
* update_info to Tuple[Action, Observation]
* make codeact agent and langchains compatible with Tuple[Action, Observation]
* fix ruff
* fix ruff
* change to base path to fix minimal langchains agent
* add NullAction to potentially handle for chat scenario
* Update opendevin/controller/command_manager.py
Co-authored-by: Robert Brennan <accounts@rbren.io>
* fix event args
* set the default workspace to "workspace"
* make directory relative (so it does not show up to agent in File*Action)
* fix typo
* await to yield for sending observation
* fix message format
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
