4fce28706f
SWE-agent Multimodal ( #1223 )
...
* Add ImageParsingHistoryProcessor
* Add SWEBenchMultimodal problem statement parsing
* cache processed swe-bench multimodal inputs
* Add testing for multimodal problem statement
* Update environment variable for PROBLEM_STATEMENT
* Update timeout params to multimodal config
* Add problem statement with images to Inspector view
* Update configs and add default_mm_no_images
* Add templates.disable_image_processing option
* Add Observation Images to Inspector
* Update configs for gemini
* Update docs for multimodal updates
* Fix: Protocols aren't inherited
* Chore: pathlib instead of os.path and make pre-commit happy
* add web_browser bundle
---------
Co-authored-by: carlosejimenez <cjsaltlake@gmail.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-07-09 03:19:59 -04:00
16849a0c32
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-06-12 22:30:20 +00:00
25c7d5350a
Add testing for tools command parsing
2025-06-12 22:28:53 +00:00
bfda41ba46
Remove web UI ( #1190 )
...
* Remove web UI
* remove test server
2025-06-04 12:53:09 -04:00
ae8ded6f9e
Critical fix: WindowedFile last line display bug ( #1187 )
2025-06-02 14:36:34 -04:00
0147e4c11a
Dev: Remove obsolete test data ( #1149 )
2025-05-22 15:14:00 -04:00
1998ce1168
Breaking change: Rename defaults tool bundle ( #1147 )
...
* Breaking change: Rename defaults tool bundle
* Breaking change: Renaming of tool bundles
2025-05-22 11:54:45 -04:00
f6af95e7bb
CHANGE: Rename configs ( #1144 )
...
* CHANGE: Rename configs
* Further renames
2025-05-21 17:09:36 -04:00
be0def1e36
Feat: Add quick-stats tool ( #1125 )
...
* Feat: Add quick-stats tool
* Add tests
2025-05-14 07:03:15 -04:00
83fe102f1f
Doc: Fix default config & model ( #1105 )
...
* Doc: Fix default config
* Doc: Fix default config & model
2025-05-06 09:33:14 -04:00
3dc19dc701
CI: Fix test of getting instances
2025-05-01 10:56:36 +02:00
054467d7d3
Add multilingual
2025-05-01 10:26:42 +02:00
76c65b5da7
Add multimodal support
2025-05-01 10:21:15 +02:00
392651976b
Revert "Feat: Basic enigma/ctf support ( #1026 )"
...
This reverts commit 5f4066b7be
2025-04-04 22:06:46 -04:00
5f4066b7be
Feat: Basic enigma/ctf support ( #1026 )
...
* ctf problem statements
* add ctf repo config
* fixed errors in CTF problem loading
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* removed ctf from repo type, so it will be needed to specified explicitly
* add tests
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* CR comments
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* added git init to the reset commands of CTFRepoConfig
* type should be explicitly set in CTFProblemStatement
* changed default factories in CTFProblemStatement to allow for union smart validation
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* extracted CTF problem statement default factory to a function
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-04-04 15:47:33 -04:00
3d99e925ca
CI: Fix unittest for image name ( #1031 )
2025-03-16 18:32:33 -04:00
b36e18fb48
Fix: Create PRs ( #954 )
...
Closes #952
2025-02-17 19:10:05 -05:00
4330902ed4
CI fixes
2025-02-12 20:17:24 -08:00
de239e89ce
WIP
2025-02-12 20:17:24 -08:00
291683f4bb
CI: Test fixes and skips
2025-02-12 20:17:24 -08:00
e04ed365a9
CI: Fix swe-agent installation ( #847 )
...
* CI: Fix swe-agent installation
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* CI: No longer pull docker containers
* Fix platform dependent tests
* Temporarily reveal pytest outputs
* Ensure editable install
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-12-07 18:47:35 -05:00
73d42cf4cd
Doc: Fix dead links ( #846 )
...
* Doc: Fix dead links
* Update more links
* More dead links
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* dead links
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-12-07 18:03:03 -05:00
f320ca5c79
Doc: Update github repo links
2024-12-07 17:06:54 -05:00
a2fcd6ee9d
CI: Fix unittests after introducing registry bundle
2024-12-07 16:25:26 -05:00
5c25314f47
Tools: Split out registry as separate bundle
2024-12-07 11:57:20 -05:00
2f8b242667
Breaking: Move problem_statement and repo configs
2024-12-07 11:57:20 -05:00
d675dd74b6
Change: Rename PreExistingRepoConfig for consistency
2024-12-06 23:57:13 -05:00
f3a5a2579f
Always save replay config
2024-12-06 18:25:58 -05:00
47e4f9c701
CI: Fix model test after setting default t=0.
2024-12-06 17:44:37 -05:00
64c80fcd33
Change: run_batch uses instance id for output
2024-12-06 17:44:34 -05:00
f39e057122
Follow rename of SwerexException
2024-12-06 13:47:49 -05:00
92943e9a11
Ref: Move all exceptions to one custom file
2024-12-05 14:01:07 -05:00
3c519e78b7
Inspector: Hide full list of results
2024-12-04 19:04:30 -05:00
60c9f0fdf6
CI: Fix unittest
...
Unclear why this ever worked. Probably because before we had an
exception from swe-rex that was caught and then the number of
messages matched somehow?
2024-12-04 18:40:59 -05:00
b7504b5e1e
CI: Fix tests tripped up by changed default config
2024-12-04 18:06:36 -05:00
bb6badf271
Fix pydantic warnings about StepOutput data
...
This should fix the following warnings:
🤠 WARNING [swea-agent-scikit-learn__scikit-learn-13439] Requerying model with output from last step (RetryWithOutput)
/opt/miniconda3/envs/swea13/lib/python3.13/site-packages/pydantic/main.py:426: UserWarning: Pydantic serializer warnings:
Expected `str` but got `int` with value `1` - serialized value may not be as expected
Expected `str` but got `dict` with value `{'arguments': '{"search":...tor."}', 'name': 'edit'}` - serialized value may not be as
expected
2024-12-02 15:11:24 -05:00
e749549246
Fix: TagToolCallObservations
2024-12-02 14:50:54 -05:00
4f76380f6e
CI/Ref: Refactor test_last_n_observations
2024-12-02 14:38:52 -05:00
3e4dc26a1d
Feat: TagToolCallObservations HistoryProcessor
2024-12-02 13:07:57 -05:00
db2dfb2821
Merge branch 'swerex-integration' of https://github.com/swe-agent/swe-agent-refactor into swerex-integration
2024-12-02 12:21:54 -05:00
a5e59c9447
CI: Fix windowed file unittest
2024-12-02 12:07:30 -05:00
1da1d117f7
Update local_history -> messages in tests
2024-12-02 16:59:03 +00:00
8f32710a96
CI: Fixing unittests for flake8 utils
2024-12-01 11:50:34 -05:00
a71432d092
CI: Comment out flake8 lineno update test for now
2024-12-01 10:21:00 -05:00
bf3c04fc3b
Merge remote-tracking branch 'refs/remotes/origin/swerex-integration' into swerex-integration
2024-11-29 22:58:00 +00:00
48df7fefbe
make history_processor -> history_processors
2024-11-29 22:57:55 +00:00
2fc41de639
make history_processor -> history_processors
2024-11-29 22:50:43 +00:00
bc85bf540e
Improve function calling error template
2024-11-29 17:39:39 -05:00
44542b587d
Add last message to history
2024-11-28 15:03:12 -05:00
d3fb277c89
Remove implicit flags
2024-11-27 16:34:17 +00:00
Kilian Lieret