* [eval] increase timeout for swebench eval init/complete
* allow CmdRunAction to optionally block when .timeout is setted
* fix unit test for serialization
* fix unit tests for security analyzer
* fix integration tests
* add more timeout
* move filematching logic into server
* wait until ready before returning
* show loading message instead of empty
* logspam
* delint
* fix type
* add a few more default ignores
* Reduce runtime tests duration by running them across CPUs
* fix hardcoded image name
* test two cpus
* Test folder change
* Up the CPU to 4 again to test
* Change to 3 CPUs
* Down to 2
* Add param to remove all openhands containers
* Add comment
* Add reruns just in case
* Fix ordering of if
* Add Handling of Cache Prompt When Formatting Messages
* Fix Value for Cache Control
* Fix Value for Cache Control
* Update openhands/core/message.py
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
* Fix lint error
* Serialize Messages if Propt Caching Is Enabled
* Remove formatting message change
---------
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
Co-authored-by: tobitege <10787084+tobitege@users.noreply.github.com>
* dummy test change
* regen yml: 1st install python 3.11, then poetry
* fix caching for poetry; old entry for python was rather useless
* fix steps order (cache before poetry)
* add poetry caching to ghcr_runtime; fix fork conditions
* ghcr_runtime: more caching actions; condition fixes
* fix interim action error (order of steps)
* cache@v4 instead of v3
* fixed interim typo for 2 fork conditions
* runtime/test_env_vars: compacted multiple tests into one to reduce time
* ugh if fork condition changes again
* (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>
* feat: add SWE-bench fullset support
* fix instance image list
* update eval script and documentation
* increase timeout for remote runtime
* add push script
* handle the case when ret push is an generator
* update pbar
* set SWE-Bench default to run SWE-Bench lite
* add script to cleanup remote runtime
* fix the cases when tag is too long
* update README
* update readme for cleanup
* rename od to oh
* Update evaluation/swe_bench/README.md
Co-authored-by: Graham Neubig <neubig@gmail.com>
* Update evaluation/swe_bench/README.md
Co-authored-by: Graham Neubig <neubig@gmail.com>
* Update evaluation/swe_bench/scripts/cleanup_remote_runtime.sh
Co-authored-by: Graham Neubig <neubig@gmail.com>
* Update evaluation/swe_bench/scripts/cleanup_remote_runtime.sh
Co-authored-by: Graham Neubig <neubig@gmail.com>
* Update evaluation/swe_bench/scripts/cleanup_remote_runtime.sh
Co-authored-by: Graham Neubig <neubig@gmail.com>
* gets API key and Runtime from env var
---------
Co-authored-by: Graham Neubig <neubig@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
* feat: add SWE-bench fullset support
* fix instance image list
* update eval script and documentation
* increase timeout for remote runtime
* add push script
* handle the case when ret push is an generator
* update pbar
* set SWE-Bench default to run SWE-Bench lite
Fix a potential issue that might lead to file corruption when edit linting is enabled
#3124 introduces a feature for editing: running linter twice before and after the change and only extract new errors introduced by the agent. This has some potential issues and I am working on #3649 to address them, but I feel like I am not gonna finish it in the next few days, and that PR has become harder and harder to review, thus this PR, which only focuses on a small improvement.
So what's the issue? When we run linters on the original file before our edits, we need to copy the original file and use a temporary file to lint, because linting may have side-effect (e.g. modifying the file in-place). I used the word "may" because:
Flake8 has no side-effect, so not a problem as of now.
We don't enforce this or document this "no side-effect" as a requirement for linter implementation, so side-effect is allowed.
Regardless, the "after-edit-linting" uses the same approach: backup the file before linting to avoid data corruption. We should keep our "before-edit-linting" consistent.
Why no new unittest that reproduces the issue? Well, as I have mentioned earlier, flake8 has no side-effect, so technically it's not a bug but a flaw. Therefore, there's no way to write a test that reproduces the issue.
* 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>
* change runtime to be synchronous
* fix test runtime with the new interface
* fix arg
* fix eval
* fix missing config attribute
* fix plugins
* fix on_event by revert it back to async
* update upload_file endpoint
* fix argument to upload file
* remove unncessary async for eval;
fix evaluation run in parallel
* use asyncio to run controller for eval
* revert file upload
* truncate eval test result output
* feat: refactor building logic into runtime builder
* return image name
* fix testcases
* use runtime builder for eventstream runtime
* have runtime builder return str
* add api_key to sandbox config
* draft remote runtime
* remove extra if clause
* initialize runtime based on box class
* add build logic
* use base64 for file upload
* get runtime image prefix from API
* replace ___ with _s_ to make it a valid image name
* use /build to start build and /build_status to check the build progress
* update logging
* fix exit code
* always use port
* add remote runtime
* rename runtime
* fix tests import
* make dir first if work_dir does not exists;
* update debug print to remote runtime
* fix exit close_sync
* update logging
* add retry for stop
* use all box class for test keep prompt
* fix test browsing
* add retry stop
* merge init commands to save startup time
* fix await
* remove sandbox url
* support execute through specific runtime url
* fix file ops
* simplify close
* factor out runtime retry code
* fix exception handling
* fix content type error (e.g., bad gateway when runtime is not ready)
* add retry for wait until alive;
add retry for check image exists
* Revert "add retry for wait until alive;"
This reverts commit dd013cd2681a159cd07747497d8c95e145d01c32.
* retry when wait until alive
* clean up msg
* directly save sdist to temp dir for _put_source_code_to_dir
* support running testcases in parallel
* tweak logging;
try to close session
* try to close session even on exception
* update poetry lock
* support remote to run integration tests
* add warning for workspace base on remote runtime
* set default runtime api
* remove server runtime
* update poetry lock
* support running swe-bench (n=1) eval on remoteruntime
* add a timeout of 30 min
* add todo for docker namespace
* update poetry loc
* linter and test_aider_linter extensions for eslint
* linter tweaks
* try enabling verbose output in linter test
* one more option for linter test
* try conftest.py for tests/unit folder
* enable verbose mode in workflow; remove conftest.py again
* debug print statements of linter results
* skip some tests if eslint is not installed at all
* more tweaks
* final test skip setups
* code quality revisions
* fix test again
---------
Co-authored-by: Graham Neubig <neubig@gmail.com>
* added optional START_ID env flag to resume from that instance id
* prepare_dataset: fix comparisons by using instance id's as int
* aider bench complete_runtime: close runtime to close container
* added matrix display of instance id for logging
* fix typo in summarize_results.py saying summarise_results
* changed start_id to skip_num to skip rows from dataset (start_id wasn't supportable)
* doc changes about huggingface spaces to temporarily point back to OD
