* style(frontend): remove the welcome message in the code editor
I don't feel like we need this and it can be confusing since there is no file called "welcome". Also, the chat window already has a welcome message.
* lint
* remove empty checks
---------
Co-authored-by: Jim Su <jimsu@protonmail.com>
* feat: start Devin without Docker locally
* chore: make consistent model choices
* chore: more detailed explanation for using litellm server as walkaround
* chore: simply pr
* 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>
* build: when running in dev mode, reload the poetry server whenever a file changes
* only reload for specific directories
---------
Co-authored-by: Jim Su <jimsu@protonmail.com>
* 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
* fix swe-tool plugins;
add missing _split_string
* remove import for temporarily fix (will add back in another pr)
* 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
* fix swe-tool plugins;
add missing _split_string
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* fix weird behavior of pxssh where the output would not flush correctly
* make ssh box can handle exit_code properly as well
* Update opendevin/sandbox/docker/ssh_box.py
Co-authored-by: Robert Brennan <accounts@rbren.io>
* fix typo
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* create new modal for loading previous session
* style and replace modal
* retire old components and group modals into folder
* Utilise i18n for text content and add en translations
* prevent modal from being dismissed via the backdrop
* reference issue that its fixing
* fix incorrect role in tests
* initial commit'
* add output support
* update addon-fit library and mgirate to useXTerm
* add test todos
* move useXTerm to hooks folder
* Fix import path error
---------
Co-authored-by: Jim Su <jimsu@protonmail.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
* Fix linter issue
---------
Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>
Co-authored-by: Robert Brennan <accounts@rbren.io>
* Workaround for a bug with sshd
* Update containers/sandbox/Dockerfile
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
---------
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
* 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>
* Refactor imports to use absolute path
* Rename absolute import symbol from src to #
* Refactor imports to use absolute path
* Rename absolute import symbol from src to #
* Remove unused LoadMessageModal
* create new modal for loading previous session
* style and replace modal
* retire old components and group modals into folder
* Utilise i18n for text content and add en translations
* prevent modal from being dismissed via the backdrop
* reference issue that its fixing
* fix incorrect role in tests
---------
Co-authored-by: Jim Su <jimsu@protonmail.com>
* post playwright commands
* post playwright commands with deps
* post playwright commands
* post playwright commands with deps
* Put playwright install in the correct place
---------
Co-authored-by: Graham Neubig <neubig@gmail.com>
* AgentHub.planner_agent.prompt: Optimize the get_prompt function by using a dictionary to map ActionType to hints, thus avoiding repetitions and making the code more readable and maintainable.
* Update prompt.py
* Fix Lint issues in prompt.py
* Fix lint issues in prompt.py
* Fix Lint issues in prompt.py
* Fix Lint issues prompt.py
* Remove trailing whitespace
---------
Co-authored-by: Alex Bäuerle <alex@a13x.io>
Co-authored-by: Robert Brennan <accounts@rbren.io>
Co-authored-by: Jim Su <jimsu@protonmail.com>
* 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
* allow arrow functions for components
* initial commit - BaseModal
* initial commit - SettingsForm
* extend tests and component
* extend to support language
* refactor tests
* move files and separate component/tests
* extend functionality
* refactor
* major refactor and flip flops
* add tests
* fix styles and names
* add loading state
* remove old SettingModal
* refactor component into smaller ones
* fix model input
* revert eslint rule to allow multiple function definitions for components and remove unused helper function
* add new i18n key for language placeholder
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
* fix: correct port number in `LocalLLMs.md`
- improve details and linting
* Update docs/guides/LocalLLMs.md
---------
Co-authored-by: Robert Brennan <accounts@rbren.io>
