0.8.2

What's Changed

• [Eval,Arch] Update GPTQ eval and add headless_mode for Controller by @xingyaoww in
• [eval,fix]: metrics get carried across eval instances by @xingyaoww in #3072
• [Eval] Support SWE-Bench pull from custom docker namespace by @xingyaoww in #3136
• [Arch] Shrink runtime image size by @xingyaoww in #3051
• [Arch] Add runtime image build CI & clean up runtime build using jinja2 template by @xingyaoww in #3055
• CI: Force stop colima by @SmartManoj in #3053
• [FIX] Update SWEBenchSSHBox after global config was removed from sandbox. by @RajWorking in
• fix: add llm drop_params parameter to LLMConfig by @tobitege in #2471
• (fix) colima: use a docker context specific to runner; prevent duplicate start by @tobitege in #3097
• Bug fix: Metrics not accumulated across agent delegation by @li-boxuan in #3012
• fix: Remove extra arg from swebench ssh box by @xingyaoww in #3054
• (fix) fixed ghcr_push use of image name by @tobitege in #3101
• (fix) Runtime yml missing zip handling (fixes #3101) by @tobitege in #3104
• (fix) ghcr-runtime: no unzip, artifact downloads as-is (followup to #3104) by @tobitege in #3105
• fix: make max_budget_per_task optional in run_agent_controller by @xingyaoww in #3071
• Fix: revert torch version by @yufansong in #3118
• (fix) test_runtime: run tests per runtime, not alternating by @tobitege in #3103
• (fix) colima: fix return code handling (followup to #3097) by @tobitege in #3106
• fix (ghcr push): add missing extension by @xingyaoww in #3120
• fix (ghcr-runtime): fix filename for docker image tar by @xingyaoww in #3121
• (fix) Fix DummyAgent (used in E2E test) by @tobitege in #3137
• Fix(test,CI): runtime build tests by @xingyaoww in #3126
• [Docs] fixed broken shell command by @tolik518 in #3135
• refactor: rename 'changeAgentState' Issue#2977 by @DecodersLord in #3050
• (test|refactor)(frontend): Refactor and test the FileIcon component by @amanape in #3108
• Remove monologue agent by @neubig in #3036
  #3014
• Remove config from files by @neubig in #3039
  #2994
• Update Dockerfile casing by @charliez0 in #3045
• Remove global config from tests by @neubig in #3052
• Removed config from agent controller by @neubig in #3038
• Validate to_replace in edit_file_by_replace AgentSkill by @li-boxuan in #3073
• Modify codeAct paper link by @linshaoxin-maker in #3076
• Change doc title of agent hub by @neubig in #3100
• Update paper link in README.md by @xingyaoww in #3102
• Remove remaining global config by @neubig in #3099
• Always log user messages by @enyst in #3145
• chore-icon-transparency by @tofarr in #3138
• chore: Release 0.8.1 by @mamoodi in #3035
• chore(deps): bump @nextui-org/react from 2.4.3 to 2.4.5 in /frontend by @dependabot in #3021
• chore(deps-dev): bump openai from 1.35.13 to 1.36.0 by @dependabot in #3033
• chore(deps): bump uvicorn from 0.30.1 to 0.30.3 by @dependabot in #3062
• chore(deps-dev): bump mypy from 1.10.1 to 1.11.0 by @dependabot in #3066
• chore(deps): bump react-use from 17.5.0 to 17.5.1 in /docs by @dependabot in #3063
• chore(deps-dev): bump eslint-plugin-react from 7.34.4 to 7.35.0 in /frontend by @dependabot in #3060
• chore(deps-dev): bump jsdom from 24.1.0 to 24.1.1 in /frontend by @dependabot in #3057
• chore(deps-dev): bump openai from 1.36.0 to 1.36.1 by @dependabot in #3069
• chore(deps): bump litellm from 1.41.24 to 1.41.25 by @dependabot in #3064
• chore(deps-dev): bump pytest from 8.2.2 to 8.3.1 by @dependabot in #3065
• chore(deps-dev): bump ruff from 0.5.3 to 0.5.4 by @dependabot in #3068
• chore(deps): bump @nextui-org/react from 2.4.5 to 2.4.6 in /frontend by @dependabot in #3059
• chore(deps-dev): bump typescript from 5.5.3 to 5.5.4 in /docs by @dependabot in #3079
• chore(deps-dev): bump @typescript-eslint/parser from 7.16.1 to 7.17.0 in /frontend by @dependabot in #3080
• chore(deps-dev): bump openai from 1.36.1 to 1.37.0 by @dependabot in #3088
• chore(deps): bump litellm from 1.41.25 to 1.41.27 by @dependabot in #3086
• chore(deps-dev): bump typescript from 5.5.3 to 5.5.4 in /frontend by @dependabot in #3084
• chore(deps-dev): bump @testing-library/jest-dom from 6.4.6 to 6.4.8 in /frontend by @dependabot in #3083
• chore(deps-dev): bump @typescript-eslint/eslint-plugin from 7.16.1 to 7.17.0 in /frontend by @dependabot in #3081
• chore(deps): bump boto3 from 1.34.145 to 1.34.146 by @dependabot in #3087
• chore(deps-dev): bump chromadb from 0.5.4 to 0.5.5 by @dependabot in #3085
• chore(deps): bump litellm from 1.41.27 to 1.41.28 by @dependabot in #3092
• chore(deps): bump boto3 from 1.34.146 to 1.34.147 by @dependabot in #3093
• chore(deps): bump @react-types/shared from 3.24.0 to 3.24.1 in /frontend by @dependabot in #3094
• chore(deps-dev): bump @types/node from 20.14.11 to 20.14.12 in /frontend by @dependabot in #3095
• chore(deps): bump litellm from 1.41.28 to 1.42.1 by @dependabot in #3109
• chore(deps-dev): bump torch from 2.2.2 to 2.4.0 by @dependabot in #3110
• chore(deps): bump google-cloud-aiplatform from 1.59.0 to 1.60.0 by @dependabot in #3111
• chore(deps): bump boto3 from 1.34.147 to 1.34.148 by @dependabot in #3112
• chore(deps-dev): bump pytest from 8.3.1 to 8.3.2 by @dependabot in #3113
• chore(deps-dev): bump postcss from 8.4.39 to 8.4.40 in /frontend by @dependabot in #3114
• chore(deps): bump vite from 5.3.4 to 5.3.5 in /frontend by @dependabot in #3115
• chore(deps-dev): bump tailwindcss from 3.4.6 to 3.4.7 in /frontend by @dependabot in #3116
• chore(deps-dev): bump husky from 9.1.1 to 9.1.2 in /frontend by @dependabot in #3117
• chore(deps): bump litellm from 1.42.1 to 1.42.3 by @dependabot in #3131
• chore(deps-dev): bump ruff from 0.5.4 to 0.5.5 by @dependabot in #3132
• chore(deps-dev): bump streamlit from 1.36.0 to 1.37.0 by @dependabot in #3129
• chore(deps): bump boto3 from 1.34.148 to 1.34.149 by @dependabot in #3133
• chore(deps-dev): bump openai from 1.37.0 to 1.37.1 by @dependabot in #3134
• chore(deps): bump @react-types/shared from 3.23.1 to 3.24.0 in /frontend by @dependabot in #3082

New Contributors

• @charliez0 made their first contribution in #3045
• @DecodersLord made their first contribution in #3050
• @linshaoxin-maker made their first contribution in #3076
• @tolik518 made their first contribution in #3135
• @tofarr made their first contribution in #3138

*Full Changelog...

0.8.1

What's Changed

• Arch: refactor and add unit tests for EventStreamRuntime docker image build by @xingyaoww in #2908
• [Arch] Add tests for EventStreamRuntime and fix bash parsing by @xingyaoww in #2933
• [Agent, Eval] Fixes LLM config issue for delegation & Add eval to measure the delegation accuracy by @xingyaoww in #2948
• CI: Add retry mechanism by @SmartManoj in #2915
• CI: Stop colima instance if failed to start by @SmartManoj in #2989
• docs: Add doc on how issues are triaged by @mamoodi in #2928
• docs: updated docstrings using ruff's autofix feature by @anushkumarv in #2923
• [SWE-bench] Util: Compare files modified between gold patches and OpenDevin patches by @li-boxuan in #2934
• refactor: Frontend tests by @amanape in #2959
• Refactor: remove the use of global variable in test_sandbox by @xingyaoww in #2985
• (test|refactor)(frontend): Refactor and extend tests for ChatMessage.tsx by @amanape in #2976
• (test|refactor)(frontend): Refactor/cleanup and extend tests for ChatInterface, its children, and introduce improvements to the feedback flow by @amanape in #2997
• Run all tests in development.md by @neubig in #2951
• Rework --llm-config CLI arg by @li-boxuan in #2957
• Ref: Remove make-i18n from makefile by @SmartManoj in #2905
• Remove legacy swe_bench/scripts/summarise_results.py by @li-boxuan in #2932
• hotfix(frontend): Remove unused framer-motion package by @amanape in #2973
• Remove global config from bedrock by @neubig in #2954
• Support Instance Level Images for SWE-Bench Evaluation by @Jiayi-Pan in #2874
• Remove global config from sandbox by @neubig in #2961
• Remove global config from logger by @neubig in #2974
• Remove global config from auth by @neubig in #2962
• Refactor LLM config by @neubig in #2953
• Fix bug with model list by @neubig in #2978
• fix bug in config.py file, update reference to variable by @JeffKatzy in #2984
• docs-issue-#2887: Create openshift-example.md by @eng-waleed1 in #2960
• [LLM] Increase the default retries for LLM by @xingyaoww in #2986
• Fix: Review PR Dogfood by @SmartManoj in #2916
• INT: prevent error on repeat integration tests after failed test(s) by @tobitege in #2935
• fix(frontend): Remove unused react router package by @amanape in #2972
• Fix: Run Unit Test by @SmartManoj in #2993
• State: Add local_iteration attribute by @li-boxuan in #2990
• Remove global config from session by @neubig in #2987
• Fix: evaluation leaks api_key in metadata; fix llm_config argument in run infer by @xingyaoww in #2998
• Convert docs to new URL by @neubig in #3002
• (fix) Session: set base_url in default_llm_config by @tobitege in #3003
• fix: runtime test for mac by @xingyaoww in #3005
• frontend: update url for share opendevin trajectory visualization by @xingyaoww in #3009
• Fix playwright cache error during container restart by @SmartManoj in #3011
• Fix: handle the case where env var is empty by @xingyaoww in #3016
• fix docs links by @juliangums in #3017
• #2220, integrated aider style linting, currently passes related o… by @jigsawlabs-student in #2489
• husky: Run package commands directly by @amanape in #3013
• chore: Release 0.8.0 by @mamoodi in #2919
• chore: Update wordings in pull request template by @SmartManoj in #2926
• chores: remove useless code in eval by @yufansong in #2922
• chore(deps-dev): bump ruff from 0.5.2 to 0.5.3 by @dependabot in #3026
• chore(deps-dev): bump llama-index-embeddings-azure-openai from 0.1.10 to 0.1.11 by @dependabot in #3024
• chore(deps): bump boto3 from 1.34.144 to 1.34.145 by @dependabot in #3022
• chore(deps): bump i18next from 23.12.1 to 23.12.2 in /frontend by @dependabot in #3020
• chore(deps-dev): bump jupyterlab from 4.2.3 to 4.2.4 by @dependabot in #3028
• chore(deps): bump litellm from 1.41.15 to 1.41.19 by @dependabot in #2906
• chore(deps-dev): bump prettier from 3.3.2 to 3.3.3 in /frontend by @dependabot in #2938
• chore(deps): bump fastapi from 0.111.0 to 0.111.1 by @dependabot in #2944
• chore(deps-dev): bump ruff from 0.5.1 to 0.5.2 by @dependabot in #2945
• chore(deps-dev): bump eslint-plugin-react from 7.34.3 to 7.34.4 in /frontend by @dependabot in #2940
• chore(deps): bump i18next from 23.11.5 to 23.12.1 in /frontend by @dependabot in #2939
• chore(deps): bump boto3 from 1.34.143 to 1.34.144 by @dependabot in #2941
• chore(deps): bump litellm from 1.41.19 to 1.41.21 by @dependabot in #2942
• chore(deps-dev): bump whatthepatch from 1.0.5 to 1.0.6 by @dependabot in #2943
• chore(deps): bump react-i18next from 14.1.2 to 14.1.3 in /frontend by @dependabot in #2965
• chore(deps): bump vite from 5.3.3 to 5.3.4 in /frontend by @dependabot in #2967
• chore(deps-dev): bump @typescript-eslint/parser from 7.16.0 to 7.16.1 in /frontend by @dependabot in #2969
• chore(deps-dev): bump tailwindcss from 3.4.4 to 3.4.5 in /frontend by @dependabot in #2971
• chore(deps-dev): bump @typescript-eslint/eslint-plugin from 7.16.0 to 7.16.1 in /frontend by @dependabot in #2970
• chore(deps): bump litellm from 1.41.21 to 1.41.23 by @dependabot in #2964
• chore(deps-dev): bump eslint-plugin-prettier from 5.1.3 to 5.2.1 in /frontend by @dependabot in #2980
• chore(deps): bump react-i18next from 14.1.3 to 15.0.0 in /frontend by @dependabot in #2981
• chore(deps-dev): bump tailwindcss from 3.4.5 to 3.4.6 in /frontend by @dependabot in #2983
• chore(deps-dev): bump @types/node from 20.14.10 to 20.14.11 in /frontend by @dependabot in #2982
• chore(deps): bump pyarrow from 16.1.0 to 17.0.0 by @dependabot in #2963
• chore(deps): bump litellm from 1.41.23 to 1.41.24 by @dependabot in #2999
• chore(deps-dev): bump pytest-asyncio from 0.23.7 to 0.23.8 by @dependabot in #3000
• chore(deps): bump @nextui-org/react from 2.4.2 to 2.4.3 in /frontend by @dependabot in #2995
• chore(deps-dev): bump husky from 9.0.11 to 9.1.1 in /frontend by @dependabot in #2996

New Contributors

• @anushkumarv made their first contribution in #2923
• @JeffKatzy made their first contribution in #2984
• @eng-waleed1 made their first contribution in #2960
• @juliangums made their first contribution in #3017
• @jigsawlabs-student made their first contribution in #2489

Full Changelog: 0.8.0...0.8.1

0.8.0

What's Changed

• [Arch] Remove supports for Background Commands by @xingyaoww in #2803
  #2810
• arch: deprecating recall action and search_memory by @xingyaoww in #2900
• arch: refractor eventstream into async by @xingyaoww in #2907
• [Arch] Implement EventStream Runtime Client with Jupyter Support using Agnostic Sandbox by @xingyaoww in #2879
• [Arch] EventStreamRuntime supports browser by @xingyaoww in #2899
• [Agent] Improve edits by adding back append_file by @xingyaoww in #2722
• Bugfix: add missing f in f-string for logging debug message in task creation by @SmartManoj in #2836
• CI: Delete colima default profile by @SmartManoj in #2807
• CI: Support uploading frontend unit test coverage. by @iFurySt in #2772
• CI: Check exit code for E2E test by @SmartManoj in #2834
• docs: Reorder docs and small update to README by @mamoodi in #2860
• doc: Mention negative feedback feature in bug report. by @SmartManoj in #2827
• Doc: Fix Azure Guide by @SmartManoj in #2894
• Doc: LM Studio Guide by @SmartManoj in #2875
• Doc: Mention FORCE_REGENERATE var by @SmartManoj in #2833
• [Evaluation] Simplify eval & and multi-processing related fixes by @xingyaoww in
• feat: Implement user confirmation mode, request confirmation when running bash/python code in this mode by @adrgs in #2774
• Fix delegator LLM config when config is set from UI by @li-boxuan in #2913
• Fix: hostname in logging by @SmartManoj in #2914
• [Fix] Minor bug in parse_response of CodeActResponseParser by @RajWorking in #2912
• fix: Runtime import by @xingyaoww in #2897
• Refactor: Remove extra log in property by @SmartManoj in #2687
• Refactoring: event stream based agent history by @enyst in #2709
• Refractor: move image agnostic util to shared runtime util by @xingyaoww in #2859
• Test: Update regenerate.sh by @SmartManoj in #2832
• Update README for release 0.7.1 by @mamoodi in #2814
• Use README as the only place for getting started instructions by @mamoodi in #2815
• Make the sandbox Python runtime completely transparent by @Shimada666 in #2796
• Fix gemini-1.5-flash crash due to missing 'vertexai' module by @SmartManoj in #2826
• trim the sandbox image and install plugin dependencies in agnostic image by @Shimada666 in #2792
• Update custom sandbox usage guide by @Shimada666 in #2829
• fix git diff TIMEOUT problem in swe_bench evaluation by @bin123apple in #2828
• Two fixes to swe bench eval by @neubig in #2831
• Streamline Logging Events by @SmartManoj in #2532
• Display real-time build logs for the agnostic image by @Shimada666 in #2830
• added netcat to the requirements by @rdmueller in #2822
• History clean up by @enyst in #2849
• Add websocket runtime and od-client-runtime by @yufansong in #2603
• add od runtime clinet dependencies in sandbox image by @yufansong in #2858
• fix client pexpect remove permission todo by @yufansong in #2863
• fix pexpect output code error in docker image by @yufansong in #2862
• Fix instance agonistic: remove Miniforge after installation by @Jiayi-Pan in #2878
• Customize LLM config per agent by @li-boxuan in #2756
• chores: open the websockets ports for port mapping and remove chores. by @yufansong in #2864
• Ref: Restore last mute setting by @SmartManoj in #2895
• Integration testing: unset irrelevant env variables by @li-boxuan in #2902
• Remove legacy dummy action from CI by @li-boxuan in #2903
• chore(deps): bump litellm from 1.41.6 to 1.41.7 by @dependabot in #2812
• chore(deps-dev): bump ruff from 0.5.0 to 0.5.1 by @dependabot in #2811
• chore(deps): bump tenacity from 8.4.2 to 8.5.0 by @dependabot in #2813
• chore(deps): bump tailwind-merge from 2.3.0 to 2.4.0 in /frontend by @dependabot in #2851
• chore(deps-dev): bump @types/node from 20.14.9 to 20.14.10 in /frontend by @dependabot in #2852
• chore(deps): bump litellm from 1.41.7 to 1.41.11 by @dependabot in #2854
• chore(deps): bump boto3 from 1.34.139 to 1.34.140 by @dependabot in #2855
• chore(deps-dev): bump @typescript-eslint/parser from 7.15.0 to 7.16.0 in /frontend by @dependabot in #2873
• chore(deps): bump framer-motion from 11.2.13 to 11.2.14 in /frontend by @dependabot in #2871
• chore(deps): bump google-generativeai from 0.7.1 to 0.7.2 by @dependabot in #2868
• chore(deps): bump boto3 from 1.34.140 to 1.34.141 by @dependabot in #2869
• chore(deps): bump litellm from 1.41.11 to 1.41.13 by @dependabot in #2870
• chore(deps-dev): bump @typescript-eslint/eslint-plugin from 7.15.0 to 7.16.0 in /frontend by @dependabot in #2872
• chore(deps): bump json-repair from 0.25.2 to 0.25.3 by @dependabot in #2881
• chore(deps): bump litellm from 1.41.13 to 1.41.14 by @dependabot in #2883
• chore(deps-dev): bump openai from 1.35.10 to 1.35.13 by @dependabot in #2885
• chore(deps): bump framer-motion from 11.2.14 to 11.3.0 in /frontend by @dependabot in #2880
• chore(deps): bump boto3 from 1.34.141 to 1.34.142 by @dependabot in #2882
• chore(deps): bump google-cloud-aiplatform from 1.58.0 to 1.59.0 by @dependabot in #2884
• chore(deps): bump framer-motion from 11.3.0 to 11.3.2 in /frontend by @dependabot in #2890
• chore(deps): bump litellm from 1.41.14 to 1.41.15 by @dependabot in #2891
• chore(deps-dev): bump chromadb from 0.5.3 to 0.5.4 by @dependabot in #2892
• chore(deps): bump boto3 from 1.34.142 to 1.34.143 by @dependabot in #2893

New Contributors

• @bin123apple made their first contribution in #2828
• @rdmueller made their first contribution in #2822
• @adrgs made their first contribution in #2774
• @RajWorking made their first contribution in #2912

Full Changelog: 0.7.1...0.8.0

0.7.1

What's Changed

• Update tag to use in README and docs to 0.7.0 by @mamoodi in #2683
• Remove MAX_CHARS traffic control by @li-boxuan in #2694
• doc: Update CONTRIBUTING.md by @SmartManoj in #2671
• Sync history to stream by @enyst in #2640
• [Evaluation] Default to not use hint for SWE-Bench eval by @xingyaoww in #2696
• CLI concurrency by @enyst in #2695
• Add ability to restore the cli session (optional) by @enyst in #2699
• Small refactoring of obs truncation by @enyst in #2701
• Bypass MAX_ITERATIONS and MAX_BUDGET_PER_TASK on web GUI by @li-boxuan in #2697
• docs: Update documentation with some consistency by @mamoodi in #2706
• Remove SWE agent by @enyst in #2708
• feat: added make run-wsl by @tobitege in #2711
• mixin: improve logging by @tobitege in #2713
• style: refine the copy button and add copy feedback for the icon. by @iFurySt in #2715
• test: fix the failed unit tests. by @iFurySt in #2721
• fix(docs): translate missing parts in zh-Hans and fr by @Umpire2018 in #2724
• fix: improve exit_code processing (ssh_box) by @tobitege in #2726
• [Evaluation] Use the latest official SWE-Bench Dockerization for evaluation by @xingyaoww in #2728
• [Agent] (Potentially) improve Editing using diff by @xingyaoww in #2685
• refactor: Renamed variables to resolve naming conflicts and eliminate warnings by @iFurySt in #2732
• Refactor: Enhance file handling and code editing functionality by @PierrunoYT in #2646
• Fix: Add scroll functionality to file explorer sidepane by @richardokonicha in #2731
• CI: For colima, modify CPU count and memory by @SmartManoj in #2712
• [Evaluation] fix SWE-Bench docker image name by @xingyaoww in #2751
• feature: Add config template. by @iFurySt in #2736
• Remove global args by @neubig in #2760
• feature: Enable DEBUG level logging based on config setting. by @iFurySt in #2762
• docs: Update custom sandbox guide to include steps to use pre-existin… by @richardokonicha in #2740
• Fix the FE failed unit test. by @iFurySt in #2773
• Restore SWE-bench dep refs by @john-b-yang in #2752
• Add 'latest' tag to Docker builds for stable releases only by @richardokonicha in #2781
• refactor: multiple code improvements by @iFurySt in #2771
• Added local ollama models by @SmartManoj in #2433
• Make CodeAct finish task by @sb-git-cloud in #2673
• Add event synchronously by @enyst in #2700
• [Evaluation] Log empty patch stats for SWE-Bench by @xingyaoww in #2776
• [Arch] Removing docker exec box by @xingyaoww in #2802
• [Eval] initialize llm inside process_instance to circumvent "AttributeError:… by @xingyaoww in #2805
• [LLM] Retry for internal server error by @xingyaoww in #2806
• Refactored sandbox config by @SmartManoj in #2455
• docs: update docker run command to pull default 'latest' tag by @richardokonicha in #2804
• Simplify eval code by @neubig in #2775
• chore: Add architecture diagram. by @iFurySt in #2783
• chore(deps): bump boto3 from 1.34.138 to 1.34.139 by @dependabot in #2788
• chore(deps): bump litellm from 1.41.3 to 1.41.6 by @dependabot in #2790
• chore(deps): bump react from 18.2.0 to 18.3.1 in /docs by @dependabot in #2786
• chore(deps): bump react-dom from 18.2.0 to 18.3.1 in /docs by @dependabot in #2787
• chore(deps-dev): bump typescript from 5.2.2 to 5.5.3 in /docs by @dependabot in #2785
• chore(deps-dev): bump openai from 1.35.9 to 1.35.10 by @dependabot in #2789
• chore(deps): bump framer-motion from 11.2.12 to 11.2.13 in /frontend by @dependabot in #2793
• chore: Add docs for dependabot and add the open pr limit from 5 to 20. by @iFurySt in #2784
• chore(deps): bump vite from 5.3.2 to 5.3.3 in /frontend by @dependabot in #2767
• chore(deps): bump jose from 5.6.2 to 5.6.3 in /frontend by @dependabot in #2766
• chore(deps): bump boto3 from 1.34.137 to 1.34.138 by @dependabot in #2769
• chore(deps-dev): bump openai from 1.35.8 to 1.35.9 by @dependabot in #2770
• chore(deps): bump react-router-dom from 6.24.0 to 6.24.1 in /frontend by @dependabot in #2768
• chore(deps-dev): bump typescript from 5.5.2 to 5.5.3 in /frontend by @dependabot in #2741
• chore(deps): bump litellm from 1.40.29 to 1.41.3 by @dependabot in #2746
• chore(deps-dev): bump openai from 1.35.7 to 1.35.8 by @dependabot in #2745
• chore(deps-dev): bump @typescript-eslint/parser from 7.14.1 to 7.15.0 in /frontend by @dependabot in #2743
• chore(deps): bump boto3 from 1.34.136 to 1.34.137 by @dependabot in #2744
• chore(deps-dev): bump @typescript-eslint/eslint-plugin from 7.14.1 to 7.15.0 in /frontend by @dependabot in #2742
• chore(deps): bump boto3 from 1.34.135 to 1.34.136 by @dependabot in #2718
• chore(deps-dev): bump postcss from 8.4.38 to 8.4.39 in /frontend by @dependabot in #2716
• chore(deps): bump @reduxjs/toolkit from 2.2.5 to 2.2.6 in /frontend by @dependabot in #2717
• chore(deps-dev): bump ruff from 0.4.10 to 0.5.0 by @dependabot in #2719

New Contributors

• @richardokonicha made their first contribution in #2731
• @john-b-yang made their first contribution in #2752
• @sb-git-cloud made their first contribution in #2673

Full Changelog: 0.7.0...0.7.1

0.7.0

What's Changed

• Update screenshot by @xingyaoww in #2286
• Bump openai from 1.30.5 to 1.31.0 by @dependabot in #2283
• [feat] WebArena benchmark, MiniWoB++ benchmark and related arch changes by @frankxu2004 in #2170
• fix: test_sandbox tests didn't close dockers by @tobitege in #2274
• [Hotfix] Fix ML-Bench continue run_inference.py by @super-dainiu in #2284
• Bump boto3 from 1.34.118 to 1.34.119 by @dependabot in #2280
• Update AgentHub README.md by @isavita in #2290
• doc: add Python keyring to Troubleshooting documentation by @tobitege in #2289
• Bump openai from 1.31.0 to 1.31.2 by @dependabot in #2301
• Bump litellm from 1.40.2 to 1.40.4 by @dependabot in #2300
• Bump ruff from 0.4.7 to 0.4.8 by @dependabot in #2297
• Bump boto3 from 1.34.119 to 1.34.120 by @dependabot in #2299
• Makefile setup-config to store the persist_sandbox boolean value by @mohammadkazem-sadoughi in #2304
• Bump tailwindcss from 3.4.3 to 3.4.4 in /frontend by @dependabot in #2298
• fix: ExplorerActions overlapping with file name. by @birajsilwal in #2287
• CodeActAgent to delegate to BrowsingAgent by @li-boxuan in #2103
• [bugfix] browse actions shouldn't change url and screenshot, only observations by @frankxu2004 in #2311
• Fix failed test_browse_internet CodeActAgent integration prompts by @yufansong in #2318
• tests: more Agentskills tests; updated .gitignore by @tobitege in #2307
• Fix python environment in solve-issue dogfood action by @yufansong in #2313
• Bump openai from 1.31.2 to 1.32.0 by @dependabot in #2317
• Bump boto3 from 1.34.120 to 1.34.121 by @dependabot in #2316
• Bump vite from 5.2.12 to 5.2.13 in /frontend by @dependabot in #2315
• fix: hide special paths; sort models by @tobitege in #2325
• fix: remove bottom chatbox fade (frontend) by @tobitege in #2323
• Add back jupyter PWD env var for agentskills by @xingyaoww in #2327
• feat: support ToolQA benchmark by @yueqis in #2263
• feat: revert hiden special paths change in file action by @yufansong in #2328
• Support gpqa benchmark evaluation by @1jsingh in #2080
• fix(frontend): prevent API key from resetting after modal change by @tobitege in #2329
• fix: codeact bug [If running a command that never returns, it gets stuck #1895] by @assertion in #2034
• Feat: Support Gorilla APIBench by @yueqis in #2081
• Remote deprecated file by @yufansong in #2332
• fix: Backticks get always escaped by runtime; add Ipython test by @tobitege in #2321
• fix: warning about zope-interface (pyproject) by @tobitege in #2335
• Revamp AgentRejectAction and allow ManagerAgent to handle rejection by @li-boxuan in #1735
• Downgraded Python version to 3.12.3 by @SmartManoj in #2331
• remove deprecated github-token config by @enyst in #2334
• Restore previous browsing agent behavior when evaluating on WebArena and miniwob++ only by @frankxu2004 in #2341
• doc: Added citation subsection in README by @poudel-bibek in #2339
• Refactored prompt.py to reduce token usage by @temotskipa in #1996
• Parameterize Python version by @ohhmm in #2348
• fix typos by @RainRat in #2352
• fix: remove backtick escaping from run_ipython by @tobitege in #2347
• Issues Category Update: Removed Question Type by @SmartManoj in #2345
• conftest: Exit without revealing secrets by @li-boxuan in #2351
• BioCoder integration by @tangxiangru in #2076
• Refactor response to action in agent step by @yufansong in #2350
• fix: remove some MonologueAgent mentions by @tobitege in #2364
• chore(deps): bump litellm from 1.40.4 to 1.40.7 by @dependabot in #2370
• chore(deps): bump boto3 from 1.34.121 to 1.34.122 by @dependabot in #2372
• chore(deps-dev): bump openai from 1.32.0 to 1.33.0 by @dependabot in #2373
• chore(deps-dev): bump llama-index-embeddings-azure-openai from 0.1.9 to 0.1.10 by @dependabot in #2374
• chore(deps-dev): bump llama-index-vector-stores-chroma from 0.1.8 to 0.1.9 by @dependabot in #2375
• Fix llm key leaks bug by @yufansong in #2376
• chore(deps): bump @vitejs/plugin-react from 4.3.0 to 4.3.1 in /frontend by @dependabot in #2371
• feat: append_file incl. all tests [agentskills] by @tobitege in #2346
• Add SWEBench-docker eval by @xingyaoww in #2085
• fix: avoid repeat logging of unneeded messages by @tobitege in #2380
• Minor SWE-Bench inference config tweak by @xingyaoww in #2381
• fix(swe_bench_eval): Mkdir infer_logs instead of logs by @xingyaoww in #2382
• refactor browsing agent response parse by @yufansong in #2366
• chore(deps): bump boto3 from 1.34.122 to 1.34.123 by @dependabot in #2391
• chore(deps): bump litellm from 1.40.7 to 1.40.8 by @dependabot in #2392
• chore(deps-dev): bump prettier from 3.3.1 to 3.3.2 in /frontend by @dependabot in #2390
• chore(deps-dev): bump @typescript-eslint/eslint-plugin from 7.12.0 to 7.13.0 in /frontend by @dependabot in #2389
• chore(deps-dev): bump @testing-library/jest-dom from 6.4.5 to 6.4.6 in /frontend by @dependabot in #2388
• chore(deps-dev): bump @typescript-eslint/parser from 7.12.0 to 7.13.0 in /frontend by @dependabot in #2387
• Add integration test for CodeActSWEAgent by @yufansong in #2377
• fix the failed unit test. by @iFurySt in #2405
• chore(deps-dev): bump lint-staged from 15.2.5 to 15.2.6 in /frontend by @dependabot in #2407
• chore(deps): bump litellm from 1.40.8 to 1.40.9 by @dependabot in #2411
• chore(deps): bump boto3 from 1.34.123 to 1.34.124 by @dependabot in #2410
• Use LLM to analyze ML-Bench failure cases by @super-dainiu in #2399
• Refactor MonologueAgent, PlannerAgent add response parser by @yufansong in #2400
• Refactor CodeActSWEAgent, add response parser by @yufansong in #2368
• Dockerfile for make plugins sandbox-agnostic by @yufansong in #2409
• chore(deps-dev): bump lint-staged from 15.2.6 to 15.2.7 in /frontend by @dependabot in #2414
• chore(deps): bump vite from 5.2.13 to 5.3.0 in /frontend by @dependabot in #2416
• chore(deps-dev): bump openai from 1.33.0 to 1.34.0 by @dependabot in #2422
• chore(deps): bump boto3 from 1.34.124 to 1.34.125 by @dependabot in #2423
• chore(deps): bump datasets from 2.19.2 to 2.20.0 by @dependabot in #2424
• Replace all instances of OPENDEVIN_WORKSPACE with WORKSPACE_BASE by @neubig in #2418
• workspace_mount_path sentinel: an undefined string by @enyst in #2431
• regenerate.sh: Exit upon common known errors by @li-boxuan in https://github...

0.6.2

What's Changed

• Bump pytest from 8.2.1 to 8.2.2 by @dependabot in #2252
• Bump boto3 from 1.34.117 to 1.34.118 by @dependabot in #2253
• Bugfix by added config to disable plugin initialization for Persistent sandbox by @SmartManoj in #2179
• Bump google-generativeai from 0.5.4 to 0.6.0 by @dependabot in #2254
• Bump opencv-python from 4.9.0.80 to 4.10.0.82 by @dependabot in #2255
• Bump litellm from 1.39.5 to 1.40.0 by @dependabot in #2256
• Bump @typescript-eslint/parser from 7.11.0 to 7.12.0 in /frontend by @dependabot in #2261
• Fixed output logging by @SmartManoj in #2244
• Bump jose from 5.3.0 to 5.4.0 in /frontend by @dependabot in #2259
• Bump @types/node from 20.14.0 to 20.14.1 in /frontend by @dependabot in #2258
• fix frontend tests; minor readme update by @tobitege in #2219
• fix test_config to prevent leaks by @tobitege in #2245
• Fix agentskills tests by @tobitege in #2242
• Fix SWE-Bench README typos by @tobitege in #2250
• fix: add an early exit check for agent answers in agent bench. by @iFurySt in #2257
• Add ML-Bench Evaluation with OpenDevin by @super-dainiu in #2015
• [Mint evaluation] Fix bug in stopping when the agent reaches max steps or solution proposals by @ryanhoangt in #2268
• Bump @testing-library/react from 15.0.7 to 16.0.0 in /frontend by @dependabot in #2227
• [AgentBench evaluation] set run_as_devin to true by @li-boxuan in #2269
• Bump @typescript-eslint/eslint-plugin from 7.11.0 to 7.12.0 in /frontend by @dependabot in #2260
• fix: there maybe unexpected files in event file list, not like 1.json… by @assertion in #2270
• Improved logs by @SmartManoj in #2272
• fix typos by @RainRat in #2267
• Bump prettier from 3.3.0 to 3.3.1 in /frontend by @dependabot in #2281
• Bump @types/node from 20.14.1 to 20.14.2 in /frontend by @dependabot in #2279
• Bump json-repair from 0.21.0 to 0.23.1 by @dependabot in #2278
• Bump litellm from 1.40.0 to 1.40.2 by @dependabot in #2282
• Solved Hugging Face cache issue. by @SmartManoj in #2277

New Contributors

• @super-dainiu made their first contribution in #2015

Full Changelog: 0.6.1...0.6.2

0.6.1

What's Changed

• Bump litellm from 1.39.3 to 1.39.5 by @dependabot in #2163
• Fix: Feedback should be sent through the backend to avoid CORS issues by @neubig in #2046
• Bump boto3 from 1.34.115 to 1.34.116 by @dependabot in #2164
• Install chromium only once by @SmartManoj in #2100
• Add remaining subsets for MINT benchmark by @ryanhoangt in #2142
• Added logs by @SmartManoj in #2153
• Lazy launching BrowseEnv / making BrowseEnv optional by @assertion in #2155
• Fixed makefile by @SmartManoj in #2168
• Fix: Codebase font fixed, and other fixes for #2138 PR by @zeul22 in #2154
• Fix persist_sandbox in Makefile by @li-boxuan in #2171
• Initialized plugins only once for persistent sandboxes by @SmartManoj in #2162
• Fix ssh box hung issue by @li-boxuan in #2172
• Detailed logs for ssh_box by @SmartManoj in #2173
• Add AgentBench. by @iFurySt in #2012
• Fix: Avoid bash backtick eval in runtime commands. by @iFurySt in #2180
• Support BIRD benchmark by @huybery in #2117
• Update slack invite link to make it valid by @neubig in #2182
• Restricted persistent sandbox to opendevin user only by @SmartManoj in #2177
• Refactored logging by @SmartManoj in #2159
• Auto started persistent container by @SmartManoj in #2151
• Add supported benchmarks to evaluation README by @iFurySt in #2183
• fix typos by @RainRat in #2187
• fix: Fix husky install deprecated message (since v9 of husky) (#2190) by @tobitege in #2191
• [Eval, EDA] modify the exiting logic and reward calculation, delete unused function by @dreasysnail in #2198
• Add cost metrics to evaluation outputs for all benchmarks by @ryanhoangt in #2199
• Bump docs to 0.6 by @neubig in #2193
• Windows doc extended with more WSL hints by @tobitege in #2205
• ssh_box: Close containers before throwing exception by @li-boxuan in #2206
• fix: German translations added/updated by @tobitege in #2208
• Fix file descriptor leaks in agentskills by @li-boxuan in #2209
• ssh_box: Fix Docker client descriptor leak by @li-boxuan in #2212
• evaluation: Reset configs in finally block by @li-boxuan in #2214
• Named docker app container by @SmartManoj in #2202
• logger.py: Fix resource leak by @li-boxuan in #2215
• Add consent dialog by @neubig in #2169
• Bump prettier from 3.2.5 to 3.3.0 in /frontend by @dependabot in #2225
• Bump @types/node from 20.12.13 to 20.14.0 in /frontend by @dependabot in #2226
• fix: keep colon part in model name for OpenRouter by @tobitege in #2223
• Bump e2b from 0.17.0 to 0.17.1 by @dependabot in #2229
• Bump uvicorn from 0.30.0 to 0.30.1 by @dependabot in #2230
• Bump datasets from 2.19.1 to 2.19.2 by @dependabot in #2231
• Bump boto3 from 1.34.116 to 1.34.117 by @dependabot in #2232
• doc: changed the welcome logo from 60vh to auto by @poudel-bibek in #2235
• chore: fix some comments by @finaltrip in #2234
• Bump ruff from 0.4.6 to 0.4.7 by @dependabot in #2233
• Fix: Properly close Docker client in DockerExecBox to prevent resource leakage by @iFurySt in #2224
• Transition Share-OpenDevin to gcloud endpoint by @neubig in #2240
• Add docs for sharing feedback by @neubig in #2241
• Fix python environment in review-pr dogfood action by @yufansong in #2237
• One-step launch instructions by @renxida in #2189
• fix: restore python linting. by @iFurySt in #2228
• Quick doc fix by @SmartManoj in #2243

New Contributors

• @tobitege made their first contribution in #2191
• @poudel-bibek made their first contribution in #2235
• @finaltrip made their first contribution in #2234
• @renxida made their first contribution in #2189

Full Changelog: 0.6.0...0.6.1