* (feat) making prompt caching optional instead of enabled default
At present, only the Claude models support prompt caching as a experimental feature, therefore, this feature should be implemented as an optional setting rather than being enabled by default.
Signed-off-by: Yi Lin <teroincn@gmail.com>
* handle the conflict
* fix unittest mock return value
* fix lint error in whitespace
---------
Signed-off-by: Yi Lin <teroincn@gmail.com>
* CodeActAgent: fix message prep if prompt caching is not supported
* fix python version in regen tests workflow
* fix in conftest "mock_completion" method
* add disable_vision to LLMConfig; revert change in message parsing in llm.py
* format messages in several files for completion
* refactored message(s) formatting (llm.py); added vision_is_active()
* fix a unit test
* regenerate: added LOG_TO_FILE and FORCE_REGENERATE env flags
* try to fix path to logs folder in workflow
* llm: prevent index error
* try FORCE_USE_LLM in regenerate
* tweaks everywhere...
* fix 2 random unit test errors :(
* added FORCE_REGENERATE_TESTS=true to regenerate CLI
* fix test_lint_file_fail_typescript again
* double-quotes for env vars in workflow; llm logger set to debug
* fix typo in regenerate
* regenerate iterations now 20; applied iteration counter fix by Li
* regenerate: pass FORCE_REGENERATE flag into env
* fixes for int tests. several mock files updated.
* browsing_agent: fix response_parser.py adding ) to empty response
* test_browse_internet: fix skipif and revert obsolete mock files
* regenerate: fi bracketing for http server start/kill conditions
* disable test_browse_internet for CodeAct*Agents; mock files updated after merge
* missed to include more mock files earlier
* reverts after review feedback from Li
* forgot one
* browsing agent test, partial fixes and updated mock files
* test_browse_internet works in my WSL now!
* adapt unit test test_prompt_caching.py
* add DEBUG to regenerate workflow command
* convert regenerate workflow params to inputs
* more integration test mock files updated
* more files
* test_prompt_caching: restored test_prompt_caching_headers purpose
* file_ops: fix potential exception, like "cross device copy"; fixed mock files accordingly
* reverts/changes wrt feedback from xingyao
* updated docs and config template
* code cleanup wrt review feedback
* Catch exception and return finish action with an exception message in case of exception in llm completion
* Remove exception logs
* Raise llm response error for any exception in llm completion
* Raise LLMResponseError from async completion and async streaming completion as well
* improve file editing prompts and unit test
converted most raise calls to a _output_error call in file_ops.py
* tweaks in test_agent_skill.py wrt to SEP separator
* tweaked the separator
* remove server runtime remnants and TEST_RUNTIME references
* restore use of TEST_RUNTIME args and variables
* fix integration tests
* added hint to properly escape docstrings
* revert latest prompt change
---------
Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>
* Add prompt caching
* remove anthropic-version from extra_headers
* change supports_prompt_caching method to attribute
* change caching strat and log cache statistics
* add reminder as a new message to fix caching
* fix unit test
* append reminder to the end of the last message content
* move token logs to post completion function
* fix unit test failure
* fix reminder and prompt caching
* unit tests for prompt caching
* add test
* clean up tests
* separate reminder, use latest two messages
* fix tests
---------
Co-authored-by: tobitege <10787084+tobitege@users.noreply.github.com>
Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
* clean up sandbox and ssh related stuff
* remove ssh hostname
* remove ssh hostname
* remove ssh password
* update config
* fix typo that breaks the test
* switch default to eventstream runtime
* remove pull docker from makefile
* fix unittest
* fix file store path
* try deprecate server runtime
* remove persist sandbox
* move file utils
* remove server runtime related workflow
* remove unused method
* attempt to remove the reliance on filestore for BE
* fix async for list file
* fix list_files to post
* fix list files
* add suffix to directory
* make sure list file returns abs path;
make sure other backend endpoints accpets abs path
* remove server runtime test workflow
* set git config in runtime
* make sure codeact agent produce message in u/a/u/a order
* integration tests
* sync message changes to codeact swe
* fix integration tests
---------
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
* update and polish gptq eval
* fix typo
* Update evaluation/gpqa/README.md
Co-authored-by: Graham Neubig <neubig@gmail.com>
* Update evaluation/gpqa/run_infer.py
Co-authored-by: Graham Neubig <neubig@gmail.com>
* add headless mode to all appropriate agent controller call
* delegate set to error when in headless mode
* try to deduplicate a bit
* make headless_mode default to True and only change it to false for AgentSession
---------
Co-authored-by: Graham Neubig <neubig@gmail.com>
* Updated documentation using ruff's autofix feature
* Updated pyproject.toml to include docstring validations
* Updated documentation using ruff's autofix feature
* Updated pyproject.toml to include docstring validations
* Updated docstrings using ruff's autfix feature
* Deleted opendevin/runtime/utils/soource.py, Keeping in sync with main
---------
Co-authored-by: Graham Neubig <neubig@gmail.com>
* add replace-based block edit & preliminary test case fix
* further fix the insert behavior
* make edit only work on first occurence
* bump codeact version since we now use new edit agentskills
* update prompt for new agentskills
* update integration tests
* make run_infer.sh executable
* remove code block for edit_file
* update integration test for prompt changes
* default to not use hint for eval
* fix insert emptyfile bug
* throw value error when `to_replace` is empty
* make `_edit_or_insert_file` return string so we can try to fix some linter errors (best attempt)
* add todo
* update integration test
* fix sandbox test for this PR
* fix inserting with additional newline
* rename to edit_file_by_replace
* add back `edit_file_by_line`
* update prompt for new editing tool
* fix integration tests
* bump codeact version since there are more changes
* add back append file
* fix current line for append
* fix append unit tests
* change the location where we show edited line no to agent and fix tests
* update integration tests
* fix global window size affect by open_file bug
* fix global window size affect by open_file bug
* increase window size to 300
* add file beginning and ending marker to avoid looping
* expand the editor window to better display edit error for model
* refractor to breakdown edit to internal functions
* reduce window to 200
* move window to 100
* refractor to cleanup some logic into _calculate_window_bounds
* fix integration tests
* fix sandbox test on new prompt
* update demonstration with new changes
* fix integration
* initialize llm inside process_instance to circumvent "AttributeError: Can't pickle local object"
* update kwargs
* retry for internal server error
* fix max iteration
* override max iter from config
* fix integration tests
* remove edit file by line
* fix integration tests
* add instruction to avoid hanging
* Revert "add instruction to avoid hanging"
This reverts commit 06fd2c59387c1c2348bc95cb487af1eb913c6ddd.
* handle content policy violation error
* fix integration tests
* fix typo in prompt - the window is 100
* update all integration tests
---------
Co-authored-by: Graham Neubig <neubig@gmail.com>
Co-authored-by: Xingyao Wang <xingyao@all-hands.dev>
Currently, OpenDevin uses a global singleton LLM config and a global singleton agent config. This PR allows customers to configure an LLM config for each agent. A hypothetically useful scenario is to use a cheaper LLM for repo exploration / code search, and a more powerful LLM to actually do the problem solving (CodeActAgent).
Partially solves #2075 (web GUI improvement is not the goal of this PR)
