feat(aci): adding file viewing capability to different extension types
- [ ] This change is worth documenting at https://docs.all-hands.dev/
- [ ] Include this change in the Release Notes. If checked, you must provide an end-user friendly description for your change below
End-user friendly description of the problem this fixes or functionality this introduces.
Summarize what the PR does, explaining any non-trivial design decisions.
Part of changes in https://github.com/All-Hands-AI/OpenHands/pull/8598. This PR contains changes to the str_replace_editor
Link of any specific issues this addresses:
To run this PR locally, use the following command:
docker run -it --rm -p 3000:3000 -v /var/run/docker.sock:/var/run/docker.sock --add-host host.docker.internal:host-gateway -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:bc99d5e-nikolaik --name openhands-app-bc99d5e docker.all-hands.dev/all-hands-ai/openhands:bc99d5e
Baseline performance with claude 4 sonnet:
"submitted_instances": 50,
"completed_instances": 50,
"resolved_instances": 38,
"unresolved_instances": 12,
With changes:
Instances submitted: 50
Instances completed: 49
Instances incomplete: 450
Instances resolved: 36
Instances unresolved: 13
I'm gonna run a larger set (200) to make sure
On main: 133/200 On this PR: 138/200
Let's go with this @ryanhoangt
Looks like there are a few issues preventing this PR from being merged!
- GitHub Actions are failing:
- Run Python Unit Tests
- Docker
If you'd like me to help, just leave a comment, like
@OpenHands please fix the failing actions on PR #8742
Feel free to include any additional details that might help me get this PR into a better state.
You can manage your notification settings
With changes (with updated prompt): 134/200
Total instances: 500
Instances submitted: 200
Instances completed: 199
Instances incomplete: 300
Instances resolved: 134
Instances unresolved: 65
Instances with empty patches: 0
Instances with errors: 1
Unstopped containers: 0
Unremoved images: 500
Report written to claude-sonnet-4-20250514_maxiter_500_N_v0.39.2-no-hint-main-05-27-2025-acl-viewer-prompt-change-v1-run_1.20250602_111239.json
MODEL_NAME_OR_PATH: claude-sonnet-4-20250514_maxiter_500_N_v0.39.2-no-hint-main-05-27-2025-acl-viewer-prompt-change-v1-run_1
RESULT_OUTPUT_DIR: /home/xingyaow/OpenHands-eval/evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Verified-test/CodeActAgent/claude-sonnet-4-20250514_maxiter_500_N_v0.39.2-no-hint-main-05-27-2025-acl-viewer-prompt-change-v1-run_1
Checking for changes: 0it [00:00, ?it/s]
Updating output file: 200it [00:01, 144.91it/s]
@ryanhoangt I think we can cut a new release in openhands-aci and get it merged