update nikolaik

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -5,12 +5,11 @@ labels: ['bug']
 body:
   - type: markdown
     attributes:
-      value: Thank you for taking the time to fill out this bug report. Please provide as much information as possible
-       to help us understand and address the issue effectively.
+      value: Thank you for taking the time to fill out this bug report. Please provide as much information as possible to help us understand and address the issue effectively.
 
   - type: checkboxes
     attributes:
-      label: Is there an existing issue for the same bug? (If one exists, thumbs up or comment on the issue instead).
+      label: Is there an existing issue for the same bug?
       description: Please check if an issue already exists for the bug you encountered.
       options:
       - label: I have checked the existing issues.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,6 +1,6 @@
 ---
-name: Feature Request or Enhancement
-about: Suggest an idea for an OpenHands feature or enhancement
+name: Feature Request
+about: Suggest an idea for OpenHands features
 title: ''
 labels: 'enhancement'
 assignees: ''
@@ -9,9 +9,10 @@ assignees: ''
 
 **What problem or use case are you trying to solve?**
 
-**Describe the UX or technical implementation you have in mind**
+**Describe the UX of the solution you'd like**
+
+**Do you have thoughts on the technical implementation?**
+
+**Describe alternatives you've considered**
 
 **Additional context**
-
-
-### If you find this feature request or enhancement useful, make sure to add a 👍 to the issue

.github/ISSUE_TEMPLATE/technical_proposal.md

@@ -0,0 +1,18 @@
+---
+name: Technical Proposal
+about: Propose a new architecture or technology
+title: ''
+labels: 'proposal'
+assignees: ''
+
+---
+
+**Summary**
+
+**Motivation**
+
+**Technical Design**
+
+**Alternatives to Consider**
+
+**Additional context**

.github/workflows/dummy-agent-test.yml

@@ -0,0 +1,53 @@
+# Workflow that uses the DummyAgent to run a simple task
+name: Run E2E test with dummy agent
+
+# Always run on "main"
+# Always run on PRs
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Install tmux
+        run: sudo apt-get update && sudo apt-get install -y tmux
+      - name: Setup Node.js
+        uses: useblacksmith/setup-node@v5
+        with:
+          node-version: '22.x'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Set up Python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: '3.12'
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation
+      - name: Build Environment
+        run: make build
+      - name: Run tests
+        run: |
+          set -e
+          SANDBOX_FORCE_REBUILD_RUNTIME=True poetry run python3 openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
+      - name: Check exit code
+        run: |
+          if [ $? -ne 0 ]; then
+            echo "Test failed"
+            exit 1
+          else
+            echo "Test passed"
+          fi

.github/workflows/ghcr-build.yml

@@ -25,31 +25,10 @@ concurrency:
   cancel-in-progress: true
 
 env:
+  BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST: nikolaik/python-nodejs:python3.12-nodejs22
   RELEVANT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
 
 jobs:
-  define-matrix:
-    runs-on: blacksmith
-    outputs:
-      base_image: ${{ steps.define-base-images.outputs.base_image }}
-    steps:
-      - name: Define base images
-        shell: bash
-        id: define-base-images
-        run: |
-          # Only build nikolaik on PRs, otherwise build both nikolaik and ubuntu.
-          if [[ "$GITHUB_EVENT_NAME" == "pull_request" ]]; then
-            json=$(jq -n -c '[
-                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" }
-              ]')
-          else
-            json=$(jq -n -c '[
-                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" },
-                { image: "ubuntu:24.04", tag: "ubuntu" }
-              ]')
-          fi
-          echo "base_image=$json" >> "$GITHUB_OUTPUT"
-
   # Builds the OpenHands Docker images
   ghcr_build_app:
     name: Build App Image
@@ -58,7 +37,6 @@ jobs:
       contents: read
       packages: write
     outputs:
-      # Since this job uses outputs it cannot use matrix
       hash_from_app_image: ${{ steps.get_hash_in_app_image.outputs.hash_from_app_image }}
     steps:
       - name: Checkout
@@ -106,10 +84,11 @@ jobs:
     permissions:
       contents: read
       packages: write
-    needs: define-matrix
     strategy:
       matrix:
-        base_image: ${{ fromJson(needs.define-matrix.outputs.base_image) }}
+        base_image:
+          - image: 'nikolaik/python-nodejs:python3.12-nodejs22'
+            tag: nikolaik
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -139,54 +118,35 @@ jobs:
             ~/.cache/pypoetry
             ~/.virtualenvs
           key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          # This is the one that saves the cache, the others set 'lookup-only: true'
           restore-keys: |
             ${{ runner.os }}-poetry-
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies POETRY_GROUP=main INSTALL_PLAYWRIGHT=0
+        run: make install-python-dependencies
       - name: Create source distribution and Dockerfile
         run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild
       - name: Lowercase Repository Owner
         run: |
           echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
-      - name: Short SHA
-        run: |
-          echo SHORT_SHA=$(git rev-parse --short "$RELEVANT_SHA") >> $GITHUB_ENV
-      - name: Determine docker build params
-        if: github.event.pull_request.head.repo.fork != true
-        shell: bash
-        run: |
-          ./containers/build.sh -i runtime -o ${{ env.REPO_OWNER }} -t ${{ matrix.base_image.tag }} --dry
-
-          DOCKER_BUILD_JSON=$(jq -c . < docker-build-dry.json)
-          echo "DOCKER_TAGS=$(echo "$DOCKER_BUILD_JSON" | jq -r '.tags | join(",")')" >> $GITHUB_ENV
-          echo "DOCKER_PLATFORM=$(echo "$DOCKER_BUILD_JSON" | jq -r '.platform')" >> $GITHUB_ENV
-          echo "DOCKER_BUILD_ARGS=$(echo "$DOCKER_BUILD_JSON" | jq -r '.build_args | join(",")')" >> $GITHUB_ENV
       - name: Build and push runtime image ${{ matrix.base_image.image }}
         if: github.event.pull_request.head.repo.fork != true
-        uses: useblacksmith/build-push-action@v1
-        with:
-          push: true
-          tags: ${{ env.DOCKER_TAGS }}
-          platforms: ${{ env.DOCKER_PLATFORM }}
-          build-args: ${{ env.DOCKER_BUILD_ARGS }}
-          context: containers/runtime
-          provenance: false
-      # Forked repos can't push to GHCR, so we just build in order to populate the cache for rebuilding
+        run: |
+          ./containers/build.sh -i runtime -o ${{ env.REPO_OWNER }} --push -t ${{ matrix.base_image.tag }}
+      # Forked repos can't push to GHCR, so we need to upload the image as an artifact
       - name: Build runtime image ${{ matrix.base_image.image }} for fork
         if: github.event.pull_request.head.repo.fork
-        uses: useblacksmith/build-push-action@v1
+        uses: docker/build-push-action@v6
         with:
           tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          outputs: type=docker,dest=/tmp/runtime-${{ matrix.base_image.tag }}.tar
           context: containers/runtime
-      - name: Upload runtime source for fork
+      - name: Upload runtime image for fork
         if: github.event.pull_request.head.repo.fork
         uses: actions/upload-artifact@v4
         with:
-          name: runtime-src-${{ matrix.base_image.tag }}
-          path: containers/runtime
+          name: runtime-${{ matrix.base_image.tag }}
+          path: /tmp/runtime-${{ matrix.base_image.tag }}.tar
 
   verify_hash_equivalence_in_runtime_and_app:
     name: Verify Hash Equivalence in Runtime and Docker images
@@ -196,8 +156,6 @@ jobs:
       fail-fast: false
       matrix:
         base_image: ['nikolaik']
-    env:
-      BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST: nikolaik/python-nodejs:python3.12-nodejs22
     steps:
       - uses: actions/checkout@v4
         with:
@@ -209,7 +167,6 @@ jobs:
             ~/.cache/pypoetry
             ~/.virtualenvs
           key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          lookup-only: true
           restore-keys: |
             ${{ runner.os }}-poetry-
       - name: Set up Python
@@ -219,7 +176,7 @@ jobs:
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies POETRY_GROUP=main INSTALL_PLAYWRIGHT=0
+        run: make install-python-dependencies
       - name: Get hash in App Image
         run: |
           echo "Hash from app image: ${{ needs.ghcr_build_app.outputs.hash_from_app_image }}"
@@ -246,34 +203,28 @@ jobs:
   # Run unit tests with the Docker runtime Docker images as root
   test_runtime_root:
     name: RT Unit Tests (Root)
-    needs: [ghcr_build_runtime, define-matrix]
-    runs-on: blacksmith-8vcpu-ubuntu-2204
+    needs: [ghcr_build_runtime]
+    runs-on: blacksmith-4vcpu-ubuntu-2204
     strategy:
       fail-fast: false
       matrix:
-        base_image: ${{ fromJson(needs.define-matrix.outputs.base_image) }}
+        base_image: ['nikolaik']
     steps:
       - uses: actions/checkout@v4
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
-      - name: Download runtime source for fork
+      # Forked repos can't push to GHCR, so we need to download the image as an artifact
+      - name: Download runtime image for fork
         if: github.event.pull_request.head.repo.fork
         uses: actions/download-artifact@v4
         with:
-          name: runtime-src-${{ matrix.base_image.tag }}
-          path: containers/runtime
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
-      # Forked repos can't push to GHCR, so we need to rebuild using cache
-      - name: Build runtime image ${{ matrix.base_image.image }} for fork
+          name: runtime-${{ matrix.base_image }}
+          path: /tmp
+      - name: Load runtime image for fork
         if: github.event.pull_request.head.repo.fork
-        uses: useblacksmith/build-push-action@v1
-        with:
-          load: true
-          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
-          context: containers/runtime
+        run: |
+          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
       - name: Cache Poetry dependencies
         uses: useblacksmith/cache@v5
         with:
@@ -281,7 +232,6 @@ jobs:
             ~/.cache/pypoetry
             ~/.virtualenvs
           key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          lookup-only: true
           restore-keys: |
             ${{ runner.os }}-poetry-
       - name: Set up Python
@@ -291,7 +241,10 @@ jobs:
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies POETRY_GROUP=main,test,runtime INSTALL_PLAYWRIGHT=0
+        run: make install-python-dependencies
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
       - name: Run docker runtime tests
         run: |
           # We install pytest-xdist in order to run tests across CPUs
@@ -300,17 +253,14 @@ jobs:
           # Install to be able to retry on failures for flaky tests
           poetry run pip install pytest-rerunfailures
 
-          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
-
-          # Setting RUN_AS_OPENHANDS to false means use root.
-          # That should mean SANDBOX_USER_ID is ignored but some tests do not check for RUN_AS_OPENHANDS.
+          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
 
           TEST_RUNTIME=docker \
           SANDBOX_USER_ID=$(id -u) \
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=false \
-          poetry run pytest -n 7 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         env:
@@ -319,33 +269,27 @@ jobs:
   # Run unit tests with the Docker runtime Docker images as openhands user
   test_runtime_oh:
     name: RT Unit Tests (openhands)
-    runs-on: blacksmith-8vcpu-ubuntu-2204
-    needs: [ghcr_build_runtime, define-matrix]
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    needs: [ghcr_build_runtime]
     strategy:
       matrix:
-        base_image: ${{ fromJson(needs.define-matrix.outputs.base_image) }}
+        base_image: ['nikolaik']
     steps:
       - uses: actions/checkout@v4
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
-      - name: Download runtime source for fork
+      # Forked repos can't push to GHCR, so we need to download the image as an artifact
+      - name: Download runtime image for fork
         if: github.event.pull_request.head.repo.fork
         uses: actions/download-artifact@v4
         with:
-          name: runtime-src-${{ matrix.base_image.tag }}
-          path: containers/runtime
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
-      # Forked repos can't push to GHCR, so we need to rebuild using cache
-      - name: Build runtime image ${{ matrix.base_image.image }} for fork
+          name: runtime-${{ matrix.base_image }}
+          path: /tmp
+      - name: Load runtime image for fork
         if: github.event.pull_request.head.repo.fork
-        uses: useblacksmith/build-push-action@v1
-        with:
-          load: true
-          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
-          context: containers/runtime
+        run: |
+          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
       - name: Cache Poetry dependencies
         uses: useblacksmith/cache@v5
         with:
@@ -353,7 +297,6 @@ jobs:
             ~/.cache/pypoetry
             ~/.virtualenvs
           key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          lookup-only: true
           restore-keys: |
             ${{ runner.os }}-poetry-
       - name: Set up Python
@@ -363,7 +306,10 @@ jobs:
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies POETRY_GROUP=main,test,runtime INSTALL_PLAYWRIGHT=0
+        run: make install-python-dependencies
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
       - name: Run runtime tests
         run: |
           # We install pytest-xdist in order to run tests across CPUs
@@ -372,14 +318,14 @@ jobs:
           # Install to be able to retry on failures for flaky tests
           poetry run pip install pytest-rerunfailures
 
-          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
 
           TEST_RUNTIME=docker \
           SANDBOX_USER_ID=$(id -u) \
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=true \
-          poetry run pytest -n 7 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         env:

.github/workflows/openhands-resolver.yml

@@ -16,11 +16,6 @@ on:
         type: string
         default: "main"
         description: "Target branch to pull and create PR against"
-      pr_type:
-        required: false
-        type: string
-        default: "draft"
-        description: "The PR type that is going to be created (draft, ready)"
       LLM_MODEL:
         required: false
         type: string
@@ -150,15 +145,13 @@ jobs:
           fi
 
       - name: Set environment variables
-        env:
-          REVIEW_BODY: ${{ github.event.review.body || '' }}
         run: |
           # Handle pull request events first
           if [ -n "${{ github.event.pull_request.number }}" ]; then
             echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
           # Handle pull request review events
-          elif [ -n "$REVIEW_BODY" ]; then
+          elif [ -n "${{ github.event.review.body }}" ]; then
             echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
           # Handle issue comment events that reference a PR
@@ -171,7 +164,7 @@ jobs:
             echo "ISSUE_TYPE=issue" >> $GITHUB_ENV
           fi
 
-          if [ -n "$REVIEW_BODY" ]; then
+          if [ -n "${{ github.event.review.body }}" ]; then
             echo "COMMENT_ID=${{ github.event.review.id || 'None' }}" >> $GITHUB_ENV
           else
             echo "COMMENT_ID=${{ github.event.comment.id || 'None' }}" >> $GITHUB_ENV
@@ -179,7 +172,7 @@ jobs:
 
           echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
           echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.PAT_TOKEN || github.token }}" >> $GITHUB_ENV
-          echo "SANDBOX_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
+          echo "SANDBOX_ENV_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
 
           # Set branch variables
           echo "TARGET_BRANCH=${{ inputs.target_branch || 'main' }}" >> $GITHUB_ENV
@@ -285,9 +278,9 @@ jobs:
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
               --target-branch ${{ env.TARGET_BRANCH }} \
-              --pr-type ${{ inputs.pr_type || 'draft' }} \
+              --pr-type draft \
               --reviewer ${{ github.actor }} | tee pr_result.txt && \
-              grep "PR created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
+              grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
           else
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \

.github/workflows/run-eval.yml

@@ -19,10 +19,9 @@ jobs:
           ref: ${{ github.head_ref }}
 
       - name: Trigger remote job
-        env:
-          PR_BRANCH: ${{ github.head_ref }}
         run: |
           REPO_URL="https://github.com/${{ github.repository }}"
+          PR_BRANCH="${{ github.head_ref }}"
           echo "Repository URL: $REPO_URL"
           echo "PR Branch: $PR_BRANCH"
 

.openhands/microagents/repo.md

@@ -54,20 +54,3 @@ Frontend:
 ## Template for Github Pull Request
 
 If you are starting a pull request (PR), please follow the template in `.github/pull_request_template.md`.
-
-## Implementation Details
-
-These details may or may not be useful for your current task.
-
-### Frontend
-
-#### Action Handling:
-- Actions are defined in `frontend/src/types/action-type.ts`
-- The `HANDLED_ACTIONS` array in `frontend/src/state/chat-slice.ts` determines which actions are displayed as collapsible UI elements
-- To add a new action type to the UI:
-  1. Add the action type to the `HANDLED_ACTIONS` array
-  2. Implement the action handling in `addAssistantAction` function in chat-slice.ts
-  3. Add a translation key in the format `ACTION_MESSAGE$ACTION_NAME` to the i18n files
-- Actions with `thought` property are displayed in the UI based on their action type:
-  - Regular actions (like "run", "edit") display the thought as a separate message
-  - Special actions (like "think") are displayed as collapsible elements only

Development.md

@@ -118,7 +118,7 @@ poetry run pytest ./tests/unit/test_*.py
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
 setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.34-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.30-nikolaik`
 
 ## Develop inside Docker container
 

Makefile

@@ -39,7 +39,6 @@ ifeq ($(INSTALL_DOCKER),)
 	@$(MAKE) -s check-docker
 endif
 	@$(MAKE) -s check-poetry
-	@$(MAKE) -s check-tmux
 	@echo "$(GREEN)Dependencies checked successfully.$(RESET)"
 
 check-system:
@@ -102,18 +101,6 @@ check-docker:
 		exit 1; \
 	fi
 
-check-tmux:
-	@echo "$(YELLOW)Checking tmux installation...$(RESET)"
-	@if command -v tmux > /dev/null; then \
-		echo "$(BLUE)$(shell tmux -V) is already installed.$(RESET)"; \
-	else \
-		echo "$(YELLOW)╔════════════════════════════════════════════════════════════════════════════╗$(RESET)"; \
-		echo "$(YELLOW)║ OPTIONAL: tmux is not installed.                                          ║$(RESET)"; \
-		echo "$(YELLOW)║ Some advanced terminal features may not work without tmux.                ║$(RESET)"; \
-		echo "$(YELLOW)║ You can install it if needed, but it's not required for development.      ║$(RESET)"; \
-		echo "$(YELLOW)╚════════════════════════════════════════════════════════════════════════════╝$(RESET)"; \
-	fi
-
 check-poetry:
 	@echo "$(YELLOW)Checking Poetry installation...$(RESET)"
 	@if command -v poetry > /dev/null; then \
@@ -146,29 +133,20 @@ install-python-dependencies:
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@if [ -n "${POETRY_GROUP}" ]; then \
-		echo "Installing only POETRY_GROUP=${POETRY_GROUP}"; \
-		poetry install --only $${POETRY_GROUP}; \
+	@poetry install
+	@if [ -f "/etc/manjaro-release" ]; then \
+		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
+		poetry run pip install playwright; \
+		poetry run playwright install chromium; \
 	else \
-		poetry install; \
-	fi
-	@if [ "${INSTALL_PLAYWRIGHT}" != "false" ] && [ "${INSTALL_PLAYWRIGHT}" != "0" ]; then \
-		if [ -f "/etc/manjaro-release" ]; then \
-			echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
-			poetry run pip install playwright; \
-			poetry run playwright install chromium; \
+		if [ ! -f cache/playwright_chromium_is_installed.txt ]; then \
+			echo "Running playwright install --with-deps chromium..."; \
+			poetry run playwright install --with-deps chromium; \
+			mkdir -p cache; \
+			touch cache/playwright_chromium_is_installed.txt; \
 		else \
-			if [ ! -f cache/playwright_chromium_is_installed.txt ]; then \
-				echo "Running playwright install --with-deps chromium..."; \
-				poetry run playwright install --with-deps chromium; \
-				mkdir -p cache; \
-				touch cache/playwright_chromium_is_installed.txt; \
-			else \
-				echo "Setup already done. Skipping playwright installation."; \
-			fi \
+			echo "Setup already done. Skipping playwright installation."; \
 		fi \
-	else \
-		echo "Skipping Playwright installation (INSTALL_PLAYWRIGHT=${INSTALL_PLAYWRIGHT})."; \
 	fi
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
 
@@ -188,7 +166,7 @@ install-pre-commit-hooks:
 
 lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --files openhands/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
 
 lint-frontend:
 	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
@@ -207,7 +185,7 @@ test:
 
 build-frontend:
 	@echo "$(YELLOW)Building frontend...$(RESET)"
-	@cd frontend && npm run prepare && npm run build
+	@cd frontend && npm run build
 
 # Start backend
 start-backend:

README.md

@@ -18,7 +18,7 @@
   <br/>
   <a href="https://docs.all-hands.dev/modules/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
   <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
-  <a href="https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=0#gid=0"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
+  <a href="https://huggingface.co/spaces/OpenHands/evaluation"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
   <hr>
 </div>
 
@@ -27,7 +27,7 @@ Welcome to OpenHands (formerly OpenDevin), a platform for software development a
 OpenHands agents can do anything a human developer can: modify code, run commands, browse the web,
 call APIs, and yes—even copy code snippets from StackOverflow.
 
-Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or [sign up for OpenHands Cloud](https://app.all-hands.dev) to get started.
+Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [Quick Start](#-quick-start).
 
 > [!IMPORTANT]
 > Using OpenHands for work? We'd love to chat! Fill out
@@ -36,50 +36,37 @@ Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or [sign up for
 
 ![App screenshot](./docs/static/img/screenshot.png)
 
-## ☁️ OpenHands Cloud
-The easiest way to get started with OpenHands is on [OpenHands Cloud](https://app.all-hands.dev),
-which comes with $50 in free credits for new users.
+## ⚡ Quick Start
 
-## 💻 Running OpenHands Locally
-
-OpenHands can also run on your local system using Docker.
+The easiest way to run OpenHands is in Docker.
 See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) guide for
 system requirements and more information.
 
-> [!WARNING]
-> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/modules/usage/runtimes/docker#hardened-docker-installation)
-> to secure your deployment by restricting network binding and implementing additional security measures.
-
-
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.30
 ```
 
+> [!WARNING]
+> On a public network? See our [Hardened Docker Installation](https://docs.all-hands.dev/modules/usage/runtimes/docker#hardened-docker-installation) guide
+> to secure your deployment by restricting network binding and implementing additional security measures.
+
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
 
-When you open the application, you'll be asked to choose an LLM provider and add an API key.
+Finally, you'll need a model provider and API key.
 [Anthropic's Claude 3.5 Sonnet](https://www.anthropic.com/api) (`anthropic/claude-3-5-sonnet-20241022`)
 works best, but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
 
-## 💡 Other ways to run OpenHands
-
-> [!CAUTION]
-> OpenHands is meant to be run by a single user on their local workstation.
-> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in authentication, isolation, or scalability.
->
-> If you're interested in running OpenHands in a multi-tenant environment, please
-> [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
-> for advanced deployment options.
+---
 
 You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes/docker#connecting-to-your-filesystem),
 run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
@@ -88,6 +75,14 @@ or run it on tagged issues with [a github action](https://docs.all-hands.dev/mod
 
 Visit [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
+> [!CAUTION]
+> OpenHands is meant to be run by a single user on their local workstation.
+> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in isolation or scalability.
+>
+> If you're interested in running OpenHands in a multi-tenant environment, please
+> [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
+> for advanced deployment options.
+
 If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
 Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting) can help.

config.template.toml

@@ -216,26 +216,13 @@ model = "gpt-4o"
 [agent]
 
 # Whether the browsing tool is enabled
-enable_browsing = true
+codeact_enable_browsing = true
 
 # Whether the LLM draft editor is enabled
-enable_llm_editor = false
-
-# Whether the standard editor tool (str_replace_editor) is enabled
-# Only has an effect if enable_llm_editor is False
-enable_editor = true
+codeact_enable_llm_editor = false
 
 # Whether the IPython tool is enabled
-enable_jupyter = true
-
-# Whether the command tool is enabled
-enable_cmd = true
-
-# Whether the think tool is enabled
-enable_think = true
-
-# Whether the finish tool is enabled
-enable_finish = true
+codeact_enable_jupyter = true
 
 # LLM config group to use
 #llm_config = 'your-llm-config-group'

containers/build.sh

@@ -7,17 +7,15 @@ org_name=""
 push=0
 load=0
 tag_suffix=""
-dry_run=0
 
 # Function to display usage information
 usage() {
-    echo "Usage: $0 -i <image_name> [-o <org_name>] [--push] [--load] [-t <tag_suffix>] [--dry]"
+    echo "Usage: $0 -i <image_name> [-o <org_name>] [--push] [--load] [-t <tag_suffix>]"
     echo "  -i: Image name (required)"
     echo "  -o: Organization name"
     echo "  --push: Push the image"
     echo "  --load: Load the image"
     echo "  -t: Tag suffix"
-    echo "  --dry: Don't build, only create build-args.json"
     exit 1
 }
 
@@ -29,7 +27,6 @@ while [[ $# -gt 0 ]]; do
         --push) push=1; shift ;;
         --load) load=1; shift ;;
         -t) tag_suffix="$2"; shift 2 ;;
-        --dry) dry_run=1; shift ;;
         *) usage ;;
     esac
 done
@@ -116,13 +113,10 @@ echo "Repo: $DOCKER_REPOSITORY"
 echo "Base dir: $DOCKER_BASE_DIR"
 
 args=""
-full_tags=()
 for tag in "${tags[@]}"; do
   args+=" -t $DOCKER_REPOSITORY:$tag"
-  full_tags+=("$DOCKER_REPOSITORY:$tag")
 done
 
-
 if [[ $push -eq 1 ]]; then
   args+=" --push"
   args+=" --cache-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max"
@@ -142,26 +136,6 @@ else
   # For push or without load, build for multiple platforms
   platform="linux/amd64,linux/arm64"
 fi
-if [[ $dry_run -eq 1 ]]; then
-  echo "Dry Run is enabled. Writing build config to docker-build-dry.json"
-  jq -n \
-    --argjson tags "$(printf '%s\n' "${full_tags[@]}" | jq -R . | jq -s .)" \
-    --arg platform "$platform" \
-    --arg openhands_build_version "$OPENHANDS_BUILD_VERSION" \
-    --arg dockerfile "$dir/Dockerfile" \
-    '{
-      tags: $tags,
-      platform: $platform,
-      build_args: [
-        "OPENHANDS_BUILD_VERSION=" + $openhands_build_version
-      ],
-      dockerfile: $dockerfile
-    }' > docker-build-dry.json
-
-    exit 0
-fi
-
-
 
 echo "Building for platform(s): $platform"
 

containers/dev/Dockerfile

@@ -61,8 +61,8 @@ RUN add-apt-repository ppa:deadsnakes/ppa \
     && apt-get install -y python3.12 python3.12-venv python3.12-dev python3-pip \
     && ln -s /usr/bin/python3.12 /usr/bin/python
 
-# NodeJS >= 22.x
-RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
+# NodeJS >= 18.17.1
+RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash - \
     && apt-get install -y nodejs
 
 # Poetry >= 1.8
@@ -108,7 +108,7 @@ WORKDIR /app
 
 # cache build dependencies
 RUN \
-  --mount=type=bind,source=./,target=/app/,rw \
+  --mount=type=bind,source=./,target=/app/ \
   <<EOF
 #!/bin/bash
 make -s clean

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.34-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.30-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik}
       #- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of openhands-state for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/.gitignore

@@ -3,7 +3,6 @@
 
 # Production
 /build
-/static/swagger-ui
 
 # Generated files
 .docusaurus

docs/DOC_STYLE_GUIDE.md

@@ -32,8 +32,6 @@ For instructions or processes that need to be followed in a specific order, use
 
 Example:
   1. Step one: Do this.
-    - First this sub step.
-    - Then this sub step.
   2. Step two: Complete this action.
   3. Step three: Verify the result.
 
@@ -49,14 +47,6 @@ docker run -it \
     ...
 ```
 
-### Use of Note and Warning
-
-When adding a note or warning, use the built-in note and warning syntax.
-
-Example:
-:::note
-This section is for advanced users only.
-:::
 
 ### Referring to UI Elements
 

docs/docusaurus.config.ts

@@ -36,7 +36,6 @@ const config: Config = {
     mermaid: true,
   },
   themes: ['@docusaurus/theme-mermaid'],
-  plugins: [],
   presets: [
     [
       'classic',
@@ -76,11 +75,6 @@ const config: Config = {
           position: 'left',
           label: 'User Guides',
         },
-        {
-          href: 'https://docs.all-hands.dev/swagger-ui/', // FIXME: this should be a relative path, but docusarus steals the click
-          label: 'API',
-          position: 'left',
-        },
         {
           type: 'localeDropdown',
           position: 'left',

docs/generate-swagger-ui.js

@@ -1,102 +0,0 @@
-const fs = require('fs');
-const path = require('path');
-const swaggerUiDist = require('swagger-ui-dist');
-
-/**
- * This script manually sets up Swagger UI for the Docusaurus documentation.
- * 
- * Why we need this approach:
- * 1. Docusaurus doesn't have a built-in way to integrate Swagger UI
- * 2. We need to copy the necessary files from swagger-ui-dist to our static directory
- * 3. We need to create a custom index.html file that points to our OpenAPI spec
- * 4. This approach allows us to customize the Swagger UI to match our documentation style
- */
-
-// Get the absolute path to the swagger-ui-dist package
-const swaggerUiDistPath = swaggerUiDist.getAbsoluteFSPath();
-
-// Create the target directory if it doesn't exist
-const targetDir = path.join(__dirname, 'static', 'swagger-ui');
-if (!fs.existsSync(targetDir)) {
-  fs.mkdirSync(targetDir, { recursive: true });
-}
-
-// Copy all files from swagger-ui-dist to our target directory
-const files = fs.readdirSync(swaggerUiDistPath);
-files.forEach(file => {
-  const sourcePath = path.join(swaggerUiDistPath, file);
-  const targetPath = path.join(targetDir, file);
-  
-  // Skip directories and non-essential files
-  if (fs.statSync(sourcePath).isDirectory() || 
-      file === 'package.json' || 
-      file === 'README.md' ||
-      file.endsWith('.map')) {
-    return;
-  }
-  
-  fs.copyFileSync(sourcePath, targetPath);
-});
-
-// Create a custom index.html file that points to our OpenAPI spec
-const indexHtml = `
-<!DOCTYPE html>
-<html lang="en">
-<head>
-  <meta charset="UTF-8">
-  <title>OpenHands API Documentation</title>
-  <link rel="stylesheet" type="text/css" href="./swagger-ui.css" />
-  <link rel="icon" type="image/png" href="./favicon-32x32.png" sizes="32x32" />
-  <link rel="icon" type="image/png" href="./favicon-16x16.png" sizes="16x16" />
-  <style>
-    html {
-      box-sizing: border-box;
-      overflow: -moz-scrollbars-vertical;
-      overflow-y: scroll;
-    }
-    
-    *,
-    *:before,
-    *:after {
-      box-sizing: inherit;
-    }
-    
-    body {
-      margin: 0;
-      background: #fafafa;
-    }
-  </style>
-</head>
-
-<body>
-  <div id="swagger-ui"></div>
-
-  <script src="./swagger-ui-bundle.js" charset="UTF-8"> </script>
-  <script src="./swagger-ui-standalone-preset.js" charset="UTF-8"> </script>
-  <script>
-    window.onload = function() {
-      // Begin Swagger UI call region
-      const ui = SwaggerUIBundle({
-        url: "/openapi.json",
-        dom_id: '#swagger-ui',
-        deepLinking: true,
-        presets: [
-          SwaggerUIBundle.presets.apis,
-          SwaggerUIStandalonePreset
-        ],
-        plugins: [
-          SwaggerUIBundle.plugins.DownloadUrl
-        ],
-        layout: "StandaloneLayout"
-      });
-      // End Swagger UI call region
-      window.ui = ui;
-    };
-  </script>
-</body>
-</html>
-`;
-
-fs.writeFileSync(path.join(targetDir, 'index.html'), indexHtml);
-
-console.log('Swagger UI files generated successfully in static/swagger-ui/');

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/configuration-options.md

@@ -354,12 +354,12 @@ Les options de configuration de l'agent sont définies dans les sections `[agent
   - Valeur par défaut : `true`
   - Description : Si l'appel de fonction est activé
 
-- `enable_browsing`
+- `codeact_enable_browsing`
   - Type : `bool`
   - Valeur par défaut : `false`
   - Description : Si le délégué de navigation est activé dans l'espace d'action (fonctionne uniquement avec l'appel de fonction)
 
-- `enable_llm_editor`
+- `codeact_enable_llm_editor`
   - Type : `bool`
   - Valeur par défaut : `false`
   - Description : Si l'éditeur LLM est activé dans l'espace d'action (fonctionne uniquement avec l'appel de fonction)

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/custom_sandbox_guide.md

@@ -60,7 +60,25 @@ Félicitations !
 
 ## Explication technique
 
-Veuillez consulter le [chapitre sur les images Docker personnalisées dans la documentation d'exécution](https://docs.all-hands.dev/fr/modules/usage/architecture/runtime) pour obtenir des explications plus détaillées.
+Lorsqu'une image personnalisée est utilisée pour la première fois, elle ne sera pas trouvée et donc elle sera construite (à l'exécution ultérieure, l'image construite sera trouvée et renvoyée).
+
+L'image personnalisée est construite avec [_build_sandbox_image()](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/docker/image_agnostic_util.py#L29), qui crée un fichier docker en utilisant votre image personnalisée comme base et configure ensuite l'environnement pour OpenHands, comme ceci:
+
+```python
+dockerfile_content = (
+        f'FROM {base_image}\n'
+        'RUN apt update && apt install -y openssh-server wget sudo\n'
+        'RUN mkdir -p -m0755 /var/run/sshd\n'
+        'RUN mkdir -p /openhands && mkdir -p /openhands/logs && chmod 777 /openhands/logs\n'
+        'RUN wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"\n'
+        'RUN bash Miniforge3-$(uname)-$(uname -m).sh -b -p /openhands/miniforge3\n'
+        'RUN bash -c ". /openhands/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"\n'
+        'RUN echo "export PATH=/openhands/miniforge3/bin:$PATH" >> ~/.bashrc\n'
+        'RUN echo "export PATH=/openhands/miniforge3/bin:$PATH" >> /openhands/bash.bashrc\n'
+    ).strip()
+```
+
+> Remarque: Le nom de l'image est modifié via [_get_new_image_name()](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/docker/image_agnostic_util.py#L63) et c'est ce nom modifié qui sera recherché lors des exécutions ultérieures.
 
 ## Dépannage / Erreurs
 

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.cli
 ```
 

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/gui-mode.md

@@ -21,18 +21,14 @@ OpenHands fournit un mode Interface Graphique (GUI) convivial pour interagir ave
 3. Entrez la `Clé API` correspondante pour le fournisseur choisi.
 4. Cliquez sur "Enregistrer" pour appliquer les paramètres.
 
-### Jetons de Contrôle de Version
-
-OpenHands prend en charge plusieurs fournisseurs de contrôle de version. Vous pouvez configurer des jetons pour plusieurs fournisseurs simultanément.
-
-#### Configuration du Jeton GitHub
+### Configuration du Jeton GitHub
 
 OpenHands exporte automatiquement un `GITHUB_TOKEN` vers l'environnement shell s'il est disponible. Cela peut se produire de deux manières :
 
 1. **Localement (OSS)** : L'utilisateur saisit directement son jeton GitHub
 2. **En ligne (SaaS)** : Le jeton est obtenu via l'authentification OAuth GitHub
 
-##### Configuration d'un Jeton GitHub Local
+#### Configuration d'un Jeton GitHub Local
 
 1. **Générer un Personal Access Token (PAT)** :
    - Allez dans Paramètres GitHub > Paramètres développeur > Personal Access Tokens > Tokens (classique)
@@ -44,11 +40,11 @@ OpenHands exporte automatiquement un `GITHUB_TOKEN` vers l'environnement shell s
 
 2. **Entrer le Jeton dans OpenHands** :
    - Cliquez sur le bouton Paramètres (icône d'engrenage) en haut à droite
-   - Accédez à la section "Git Provider Settings"
+   - Accédez à la section "GitHub"
    - Collez votre jeton dans le champ "Jeton GitHub"
    - Cliquez sur "Enregistrer" pour appliquer les modifications
 
-##### Politiques de Jetons Organisationnels
+#### Politiques de Jetons Organisationnels
 
 Si vous travaillez avec des dépôts organisationnels, une configuration supplémentaire peut être nécessaire :
 
@@ -63,7 +59,7 @@ Si vous travaillez avec des dépôts organisationnels, une configuration supplé
    - Si nécessaire, cliquez sur "Activer SSO" à côté de votre organisation
    - Terminez le processus d'autorisation SSO
 
-##### Authentification OAuth (Mode En Ligne)
+#### Authentification OAuth (Mode En Ligne)
 
 Lorsque vous utilisez OpenHands en mode en ligne, le flux OAuth GitHub :
 
@@ -78,7 +74,7 @@ Lorsque vous utilisez OpenHands en mode en ligne, le flux OAuth GitHub :
    - Autorisez OpenHands à accéder à votre compte GitHub
    - Si vous utilisez une organisation, autorisez l'accès à l'organisation si vous y êtes invité
 
-##### Dépannage
+#### Dépannage
 
 Problèmes courants et solutions :
 
@@ -99,43 +95,6 @@ Problèmes courants et solutions :
    - Vérifiez la console du navigateur pour tout message d'erreur
    - Utilisez le bouton "Tester la connexion" dans les paramètres s'il est disponible
 
-#### Configuration du Jeton GitLab
-
-OpenHands exporte automatiquement un `GITLAB_TOKEN` vers l'environnement shell, uniquement pour les installations locales, s'il est disponible.
-
-##### Configuration d'un Jeton GitLab
-
-1. **Générer un Personal Access Token (PAT)** :
-   - Sur GitLab, allez dans Paramètres utilisateur > Jetons d'accès
-   - Créez un nouveau jeton avec les portées suivantes :
-     - `api` (Accès API)
-     - `read_user` (Lecture des informations utilisateur)
-     - `read_repository` (Lecture du dépôt)
-     - `write_repository` (Écriture du dépôt)
-   - Définissez une date d'expiration ou laissez vide pour un jeton sans expiration
-
-2. **Entrer le Jeton dans OpenHands** :
-   - Cliquez sur le bouton Paramètres (icône d'engrenage)
-   - Accédez à la section `Git Provider Settings`
-   - Collez votre jeton dans le champ `Jeton GitLab`
-   - Si vous utilisez GitLab auto-hébergé, entrez l'URL de votre instance GitLab
-   - Cliquez sur `Enregistrer les modifications` pour appliquer les changements
-
-##### Dépannage
-
-Problèmes courants et solutions :
-
-1. **Jeton Non Reconnu** :
-   - Assurez-vous que le jeton est correctement enregistré dans les paramètres
-   - Vérifiez que le jeton n'a pas expiré
-   - Vérifiez que le jeton a les portées requises
-   - Pour les instances auto-hébergées, vérifiez l'URL correcte de l'instance
-
-2. **Accès Refusé** :
-   - Vérifiez les permissions d'accès au projet
-   - Vérifiez si le jeton possède les portées nécessaires
-   - Pour les dépôts de groupe/organisation, assurez-vous d'avoir les accès appropriés
-
 ### Paramètres Avancés
 
 1. Basculez sur `Options Avancées` pour accéder aux paramètres supplémentaires.

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.30
 ```
 
 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/configuration-options.md

@@ -348,12 +348,12 @@ dockerコマンドで使用する場合は、`-e LLM_<option>`として渡しま
   - デフォルト値: `true`
   - 説明: 関数呼び出しが有効かどうか
 
-- `enable_browsing`
+- `codeact_enable_browsing`
   - 型: `bool`
   - デフォルト値: `false`
   - 説明: アクションスペースでブラウジングデリゲートが有効かどうか（関数呼び出しでのみ機能）
 
-- `enable_llm_editor`
+- `codeact_enable_llm_editor`
   - 型: `bool`
   - デフォルト値: `false`
   - 説明: アクションスペースでLLMエディタが有効かどうか（関数呼び出しでのみ機能）

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/custom_sandbox_guide.md

@@ -60,7 +60,25 @@ base_container_image="custom_image"
 
 ## 技術的な説明
 
-詳細な説明については、[実行時ドキュメントのカスタムDockerイメージの章](https://docs.all-hands.dev/ja/modules/usage/architecture/runtime)を参照してください。
+カスタムイメージが初めて使用される場合、イメージが見つからないため、ビルドされます (その後の実行では、ビルドされたイメージが見つかり、返されます)。
+
+カスタムイメージは [_build_sandbox_image()](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/docker/image_agnostic_util.py#L29) でビルドされます。これは、カスタムイメージをベースとして使用して docker ファイルを作成し、次のように OpenHands の環境を設定します:
+
+```python
+dockerfile_content = (
+        f'FROM {base_image}\n'
+        'RUN apt update && apt install -y openssh-server wget sudo\n'
+        'RUN mkdir -p -m0755 /var/run/sshd\n'
+        'RUN mkdir -p /openhands && mkdir -p /openhands/logs && chmod 777 /openhands/logs\n'
+        'RUN wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"\n'
+        'RUN bash Miniforge3-$(uname)-$(uname -m).sh -b -p /openhands/miniforge3\n'
+        'RUN bash -c ". /openhands/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"\n'
+        'RUN echo "export PATH=/openhands/miniforge3/bin:$PATH" >> ~/.bashrc\n'
+        'RUN echo "export PATH=/openhands/miniforge3/bin:$PATH" >> /openhands/bash.bashrc\n'
+    ).strip()
+```
+
+> 注: イメージ名は [_get_new_image_name()](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/docker/image_agnostic_util.py#L63) で変更され、この変更された名前が後続の実行時に検索されます。
 
 ## トラブルシューティング / エラー
 

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -34,7 +34,7 @@ Docker で OpenHands を CLI モードで実行するには:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -44,7 +44,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.cli
 ```
 

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/how-to/gui-mode.md

@@ -16,11 +16,7 @@ OpenHandsは、AI アシスタントとやり取りするためのグラフィ
 3. 選択したプロバイダーに対応する`API Key`を入力します。
 4. `Save Changes`をクリックして設定を適用します。
 
-### バージョン管理トークン
-
-OpenHandsは複数のバージョン管理プロバイダーをサポートしています。複数のプロバイダーのトークンを同時に設定できます。
-
-#### GitHubトークンの設定
+### GitHubトークンの設定
 
 OpenHandsは、利用可能な場合、自動的に`GITHUB_TOKEN`をシェル環境にエクスポートします。これは2つの方法で行われます。
 
@@ -38,7 +34,7 @@ OpenHandsは、利用可能な場合、自動的に`GITHUB_TOKEN`をシェル環
      - Minimal Permissions（検索用に**Meta Data = Read-only**を選択し、ブランチ作成用に**Pull Requests = Read and Write**、**Content = Read and Write**を選択します）
   2. **OpenHandsにトークンを入力**:
    - 設定ボタン（歯車アイコン）をクリックします。
-   - `Git Provider Settings`セクションに移動します。
+   - `GitHub Settings`セクションに移動します。
    - `GitHub Token`フィールドにトークンを貼り付けます。
    - `Save Changes`をクリックして変更を適用します。
 </details>
@@ -98,46 +94,6 @@ OpenHandsは、利用可能な場合、自動的に`GITHUB_TOKEN`をシェル環
    - 組織を使用している場合は、プロンプトが表示されたら組織へのアクセスを承認します。
 </details>
 
-#### GitLabトークンの設定
-
-OpenHandsは、利用可能な場合、ローカルインストールのみ、自動的に`GITLAB_TOKEN`をシェル環境にエクスポートします。
-
-<details>
-  <summary>GitLabトークンの設定</summary>
-
-  1. **Personal Access Token（PAT）の生成**:
-   - GitLabで、User Settings > Access Tokensに移動します。
-   - 以下のスコープを持つ新しいトークンを作成します:
-     - `api`（APIアクセス）
-     - `read_user`（ユーザー情報の読み取り）
-     - `read_repository`（リポジトリ読み取り）
-     - `write_repository`（リポジトリ書き込み）
-   - 有効期限を設定するか、無期限トークンの場合は空白のままにします。
-  2. **OpenHandsにトークンを入力**:
-   - 設定ボタン（歯車アイコン）をクリックします。
-   - `Git Provider Settings`セクションに移動します。
-   - `GitLab Token`フィールドにトークンを貼り付けます。
-   - セルフホスト型GitLabを使用している場合は、GitLabインスタンスのURLを入力します。
-   - `Save Changes`をクリックして変更を適用します。
-</details>
-
-<details>
-  <summary>トラブルシューティング</summary>
-
-  一般的な問題と解決策:
-
-  - **トークンが認識されない**:
-     - トークンが設定に正しく保存されていることを確認します。
-     - トークンの有効期限が切れていないことを確認します。
-     - トークンに必要なスコープがあることを確認します。
-     - セルフホスト型インスタンスの場合は、正しいインスタンスURLを確認します。
-
-  - **アクセスが拒否された**:
-     - プロジェクトのアクセス権限を確認します。
-     - トークンに必要なスコープがあるかどうかを確認します。
-     - グループ/組織のリポジトリの場合は、適切なアクセス権があることを確認します。
-</details>
-
 ### 高度な設定
 
 1. 設定ページ内で、`Advanced`オプションを切り替えて追加の設定にアクセスします。

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -31,7 +31,7 @@ DockerでOpenHandsをヘッドレスモードで実行するには:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -42,7 +42,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/prompting/microagents-overview.md

@@ -21,8 +21,8 @@ OpenHandsがリポジトリで動作する際:
 ```
 ---
 name: <Microagentの名前>
-type: <Microagentのタイプ>
-version: <Microagentのバージョン>
+type: <MicroAgentのタイプ>
+version: <MicroAgentのバージョン>
 agent: <エージェントのタイプ (通常はCodeActAgent)>
 triggers:
 - <オプション: microagentをトリガーするキーワード。トリガーを削除すると、常に含まれるようになります>

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/runtimes/docker.md

@@ -25,7 +25,7 @@ nikolaik の `SANDBOX_RUNTIME_CONTAINER_IMAGE` は、ランタイムサーバー
 
     ```bash
     docker run # ...
-        -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+        -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
         -e SANDBOX_USER_ID=$(id -u) \
         -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
         -v $WORKSPACE_BASE:/opt/workspace_base \
@@ -82,5 +82,5 @@ docker network create openhands-network
 # 分離されたネットワークで OpenHands を実行
 docker run # ... \
     --network openhands-network \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.30
 ```

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/cloud/cloud-github-resolver.md

@@ -7,7 +7,7 @@ O GitHub Cloud Resolver automatiza correções de código e fornece assistência
 ## Configuração
 
 O Resolvedor do GitHub na Nuvem está disponível automaticamente quando você
-[concede acesso ao repositório do OpenHands Cloud](./openhands-cloud#adding-repository-access).
+[concede acesso ao repositório do OpenHands Cloud](./openhands-cloud.md#adding-repository-access).
 
 ## Uso
 

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/configuration-options.md

@@ -292,17 +292,17 @@ As opções de configuração do agente são definidas nas seções `[agent]` e
   - Padrão: `true`
   - Descrição: Se a chamada de função está habilitada
 
-- `enable_browsing`
+- `codeact_enable_browsing`
   - Tipo: `bool`
   - Padrão: `false`
   - Descrição: Se o delegado de navegação está habilitado no espaço de ação (funciona apenas com chamada de função)
 
-- `enable_llm_editor`
+- `codeact_enable_llm_editor`
   - Tipo: `bool`
   - Padrão: `false`
   - Descrição: Se o editor LLM está habilitado no espaço de ação (funciona apenas com chamada de função)
 
-- `enable_jupyter`
+- `codeact_enable_jupyter`
   - Tipo: `bool`
   - Padrão: `false`
   - Descrição: Se o Jupyter está habilitado no espaço de ação

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -35,7 +35,7 @@ Para executar o OpenHands no modo CLI com Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.cli
 ```
 

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/how-to/gui-mode.md

@@ -17,11 +17,7 @@ O OpenHands fornece um modo de Interface Gráfica do Usuário (GUI) para interag
 3. Insira a `Chave de API` correspondente para o provedor escolhido.
 4. Clique em `Salvar Alterações` para aplicar as configurações.
 
-### Tokens de Controle de Versão
-
-O OpenHands suporta múltiplos provedores de controle de versão. Você pode configurar tokens para vários provedores simultaneamente.
-
-#### Configuração do Token do GitHub
+### Configuração do Token do GitHub
 
 O OpenHands exporta automaticamente um `GITHUB_TOKEN` para o ambiente shell se ele estiver disponível. Isso pode acontecer de duas maneiras:
 
@@ -39,7 +35,7 @@ O OpenHands exporta automaticamente um `GITHUB_TOKEN` para o ambiente shell se e
      - Minimal Permissions (Selecione **Meta Data = Read-only** para pesquisa, **Pull Requests = Read and Write**, **Content = Read and Write** para criação de branches)
   2. **Insira o Token no OpenHands**:
    - Clique no botão Settings (ícone de engrenagem).
-   - Navegue até a seção `Git Provider Settings`.
+   - Navegue até a seção `GitHub Settings`.
    - Cole seu token no campo `GitHub Token`.
    - Clique em `Save Changes` para aplicar as alterações.
 </details>
@@ -99,46 +95,6 @@ O OpenHands exporta automaticamente um `GITHUB_TOKEN` para o ambiente shell se e
    - Se estiver usando uma organização, autorize o acesso à organização se solicitado.
 </details>
 
-#### Configuração do Token do GitLab
-
-O OpenHands exporta automaticamente um `GITLAB_TOKEN` para o ambiente shell, apenas para instalações locais, se ele estiver disponível.
-
-<details>
-  <summary>Configurando um Token do GitLab</summary>
-
-  1. **Gere um Personal Access Token (PAT)**:
-   - No GitLab, vá para User Settings > Access Tokens.
-   - Crie um novo token com os seguintes escopos:
-     - `api` (Acesso à API)
-     - `read_user` (Leitura de informações do usuário)
-     - `read_repository` (Leitura do repositório)
-     - `write_repository` (Escrita no repositório)
-   - Defina uma data de expiração ou deixe em branco para um token sem expiração.
-  2. **Insira o Token no OpenHands**:
-   - Clique no botão Settings (ícone de engrenagem).
-   - Navegue até a seção `Git Provider Settings`.
-   - Cole seu token no campo `GitLab Token`.
-   - Se estiver usando GitLab auto-hospedado, insira a URL da sua instância GitLab.
-   - Clique em `Save Changes` para aplicar as alterações.
-</details>
-
-<details>
-  <summary>Solução de Problemas</summary>
-
-  Problemas comuns e soluções:
-
-  - **Token Não Reconhecido**:
-     - Certifique-se de que o token esteja salvo corretamente nas configurações.
-     - Verifique se o token não expirou.
-     - Verifique se o token possui os escopos necessários.
-     - Para instâncias auto-hospedadas, verifique a URL correta da instância.
-
-  - **Acesso Negado**:
-     - Verifique as permissões de acesso ao projeto.
-     - Verifique se o token possui os escopos necessários.
-     - Para repositórios de grupo/organização, certifique-se de ter o acesso adequado.
-</details>
-
 ### Configurações Avançadas
 
 1. Dentro da página Settings, ative as opções `Advanced` para acessar configurações adicionais.

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -32,7 +32,7 @@ Para executar o OpenHands no modo Headless com Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.main -t "escreva um script bash que imprima oi"
 ```
 

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -58,17 +58,17 @@
 A maneira mais fácil de executar o OpenHands é no Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.30
 ```
 
 Você encontrará o OpenHands em execução em http://localhost:3000!

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/prompting/microagents-overview.md

@@ -21,8 +21,8 @@ Todos os microagentes usam arquivos markdown com frontmatter YAML que possuem in
 ```
 ---
 name: <Nome do microagente>
-type: <Tipo do Microagent>
-version: <Versão do Microagent>
+type: <Tipo do MicroAgent>
+version: <Versão do MicroAgent>
 agent: <O tipo de agente (normalmente CodeActAgent)>
 triggers:
 - <Palavras-chave opcionais que acionam o microagente. Se os gatilhos forem removidos, ele sempre será incluído>

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -13,7 +13,7 @@ Este é o Runtime padrão que é usado quando você inicia o OpenHands. Você po
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/configuration-options.md

@@ -349,17 +349,17 @@ Agent 配置选项在 `config.toml` 文件的 `[agent]` 和 `[agent.<agent_name>
   - 默认值: `true`
   - 描述: 是否启用函数调用
 
-- `enable_browsing`
+- `codeact_enable_browsing`
   - 类型: `bool`
   - 默认值: `false`
   - 描述: 是否在 action space 中启用浏览代理(仅适用于函数调用)
 
-- `enable_llm_editor`
+- `codeact_enable_llm_editor`
   - 类型: `bool`
   - 默认值: `false`
   - 描述: 是否在 action space 中启用 LLM 编辑器(仅适用于函数调用)
 
-- `enable_jupyter`
+- `codeact_enable_jupyter`
   - 类型: `bool`
   - 默认值: `false`
   - 描述: 是否在 action space 中启用 Jupyter

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/custom_sandbox_guide.md

@@ -1,6 +1,6 @@
 # 💿 如何创建自定义 Docker 沙箱
 
-默认的 OpenHands 沙箱包含一个[最小化 ubuntu 配置](https://github.com/All-Hands-AI/OpenHands/blob/main/containers/e2b-sandbox/Dockerfile)。您的应用场景可能需要在默认状态下安装额外的软件。本指南将教您如何通过使用自定义 Docker 映像来实现这一目标。
+默认的 OpenHands 沙箱包含一个[最小化 ubuntu 配置](https://github.com/All-Hands-AI/OpenHands/blob/main/containers/sandbox/Dockerfile)。您的应用场景可能需要在默认状态下安装额外的软件。本指南将教您如何通过使用自定义 Docker 映像来实现这一目标。
 
 目前提供两种实现方案：
 1. 从 Docker Hub 拉取已有镜像。例如，如果您想安装 `nodejs` ，您可以通过使用 `node:20` 镜像来实现。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.cli
 ```
 

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/gui-mode.md

@@ -19,18 +19,14 @@ OpenHands 提供了一个用户友好的图形用户界面（GUI）模式，用
 3. 输入所选提供商对应的 `API Key`。
 4. 点击"保存"应用设置。
 
-### 版本控制令牌
-
-OpenHands 支持多个版本控制提供商。您可以同时配置多个提供商的令牌。
-
-#### GitHub Token 设置
+### GitHub Token 设置
 
 如果可用，OpenHands 会自动将 `GITHUB_TOKEN` 导出到 shell 环境中。这可以通过两种方式实现：
 
 1. **本地（OSS）**：用户直接输入他们的 GitHub token
 2. **在线（SaaS）**：通过 GitHub OAuth 身份验证获取 token
 
-##### 设置本地 GitHub Token
+#### 设置本地 GitHub Token
 
 1. **生成个人访问令牌（PAT）**：
    - 转到 GitHub 设置 > 开发者设置 > 个人访问令牌 > 令牌（经典）
@@ -42,11 +38,11 @@ OpenHands 支持多个版本控制提供商。您可以同时配置多个提供
 
 2. **在 OpenHands 中输入令牌**：
    - 点击右上角的设置按钮（齿轮图标）
-   - 导航到"Git Provider Settings"部分
+   - 导航到"GitHub"部分
    - 将令牌粘贴到"GitHub Token"字段中
    - 点击"保存"应用更改
 
-##### 组织令牌策略
+#### 组织令牌策略
 
 如果您使用组织仓库，可能需要额外的设置：
 
@@ -61,7 +57,7 @@ OpenHands 支持多个版本控制提供商。您可以同时配置多个提供
    - 如果需要，点击组织旁边的"启用 SSO"
    - 完成 SSO 授权过程
 
-##### OAuth 身份验证（在线模式）
+#### OAuth 身份验证（在线模式）
 
 在在线模式下使用 OpenHands 时，GitHub OAuth 流程：
 
@@ -76,7 +72,7 @@ OpenHands 支持多个版本控制提供商。您可以同时配置多个提供
    - 授权 OpenHands 访问您的 GitHub 帐户
    - 如果使用组织，在出现提示时授权组织访问
 
-##### 故障排除
+#### 故障排除
 
 常见问题和解决方案：
 
@@ -97,43 +93,6 @@ OpenHands 支持多个版本控制提供商。您可以同时配置多个提供
    - 检查浏览器控制台中是否有任何错误消息
    - 如果可用，使用设置中的"测试连接"按钮
 
-#### GitLab Token 设置
-
-OpenHands 会自动将 `GITLAB_TOKEN` 导出到 shell 环境中，仅适用于本地安装，如果它可用的话。
-
-##### 设置 GitLab Token
-
-1. **生成个人访问令牌（PAT）**：
-   - 在 GitLab 中，转到用户设置 > 访问令牌
-   - 创建具有以下范围的新令牌：
-     - `api`（API 访问）
-     - `read_user`（读取用户信息）
-     - `read_repository`（读取仓库）
-     - `write_repository`（写入仓库）
-   - 设置过期日期或留空以获取永不过期的令牌
-
-2. **在 OpenHands 中输入令牌**：
-   - 点击设置按钮（齿轮图标）
-   - 导航到 `Git Provider Settings` 部分
-   - 将令牌粘贴到 `GitLab Token` 字段中
-   - 如果使用自托管 GitLab，请输入您的 GitLab 实例 URL
-   - 点击 `Save Changes` 应用更改
-
-##### 故障排除
-
-常见问题和解决方案：
-
-1. **令牌无法识别**：
-   - 确保令牌已正确保存在设置中
-   - 检查令牌是否已过期
-   - 验证令牌是否具有所需的范围
-   - 对于自托管实例，验证正确的实例 URL
-
-2. **访问被拒绝**：
-   - 验证项目访问权限
-   - 检查令牌是否具有必要的范围
-   - 对于组/组织仓库，确保您拥有适当的访问权限
-
 ### 高级设置
 
 1. 切换`高级选项`以访问其他设置。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.30
 ```
 
 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/modules/usage/cloud/cloud-github-resolver.md

@@ -5,7 +5,7 @@ The GitHub Resolver automates code fixes and provides intelligent assistance for
 ## Setup
 
 The Cloud GitHub Resolver is available automatically when you
-[grant OpenHands Cloud repository access](./openhands-cloud#adding-repository-access).
+[grant OpenHands Cloud repository access](./openhands-cloud.md#adding-repository-access).
 
 ## Usage
 

docs/modules/usage/cloud/openhands-cloud.md

@@ -0,0 +1,45 @@
+# Openhands Cloud
+
+OpenHands Cloud is the cloud hosted version of OpenHands by All Hands AI.
+
+## Accessing OpenHands Cloud
+
+Currently, users are being admitted to access OpenHands Cloud in waves. To sign up,
+[join the waitlist](https://www.all-hands.dev/join-waitlist). Once you are approved, you will get an email with
+instructions on how to access it.
+
+## Getting Started
+
+After visiting OpenHands Cloud, you will be asked to connect with your GitHub account:
+1. After reading and accepting the terms of service, click `Connect to GitHub`.
+2. Review the permissions requested by OpenHands and then click `Authorize OpenHands AI`.
+   - OpenHands will require some permissions from your GitHub account. To read more about these permissions,
+     you can click the `Learn more` link on the GitHub authorize page.
+
+## Repository Access
+
+### Adding Repository Access
+
+You can grant OpenHands specific repository access:
+1. Click the `Select a GitHub project` dropdown, select `Add more repositories...`.
+2. Select the organization, then choose the specific repositories to grant OpenHands access to.
+   - Openhands requests short-lived tokens (8-hour expiry) with these permissions:
+     - Actions: Read and write
+     - Administration: Read-only
+     - Commit statuses: Read and write
+     - Contents: Read and write
+     - Issues: Read and write
+     - Metadata: Read-only
+     - Pull requests: Read and write
+     - Webhooks: Read and write
+     - Workflows: Read and write
+   - Repository access for a user is granted based on:
+     - Granted permission for the repository.
+     - User's GitHub permissions (owner/collaborator).
+3. Click on `Install & Authorize`.
+
+### Modifying Repository Access
+
+You can modify repository access at any time by:
+* Using the same `Select a GitHub project > Add more repositories` workflow, or
+* Visiting the Settings page and selecting `Configure GitHub Repositories` under the `GitHub Settings` section.

docs/modules/usage/cloud/openhands-cloud.mdx

@@ -1,63 +0,0 @@
-# Openhands Cloud
-
-OpenHands Cloud is the cloud hosted version of OpenHands by All Hands AI.
-
-## Accessing OpenHands Cloud
-
-OpenHands Cloud can be accessed at https://app.all-hands.dev/.
-
-## Getting Started
-
-After visiting OpenHands Cloud, you will be asked to connect with your GitHub or GitLab account:
-
-1. After reading and accepting the terms of service, click `Log in with GitHub` or `Log in with GitLab`.
-2. Review the permissions requested by OpenHands and then click `Authorize OpenHands AI`.
-   - OpenHands will require some permissions from your GitHub or GitLab account. To read more about these permissions:
-     - GitHub: You can click the `Learn more` link on the GitHub authorize page.
-     - GitLab: You can expand each permission request on the GitLab authorize page.
-
-## Repository Access
-
-### GitHub
-
-#### Adding Repository Access
-
-You can grant OpenHands specific repository access:
-1. Click `Add GitHub repos` on the Home page.
-2. Select the organization, then choose the specific repositories to grant OpenHands access to.
-   <details>
-     <summary>Permission Details for Repository Access</summary>
-
-     Openhands requests short-lived tokens (8-hour expiry) with these permissions:
-     - Actions: Read and write
-     - Administration: Read-only
-     - Commit statuses: Read and write
-     - Contents: Read and write
-     - Issues: Read and write
-     - Metadata: Read-only
-     - Pull requests: Read and write
-     - Webhooks: Read and write
-     - Workflows: Read and write
-
-     Repository access for a user is granted based on:
-     - Granted permission for the repository.
-     - User's GitHub permissions (owner/collaborator).
-   </details>
-
-3. Click on `Install & Authorize`.
-
-#### Modifying Repository Access
-
-You can modify GitHub repository access at any time by:
-* Using the same `Add GitHub repos` workflow, or
-* Visiting the Settings page and selecting `Configure GitHub Repositories` under the `Git Settings` section.
-
-### GitLab
-
-When using your GitLab account, OpenHands will automatically have access to your repositories.
-
-## Conversation Persistence
-
-- Conversations List – Displays only the 10 most recent conversations initiated within the past 10 days.
-- Workspaces – Conversation workspaces are retained for 14 days.
-- Runtimes – Runtimes remain active ("warm") for 30 minutes. After this period, resuming a conversation may take 1–2 minutes.

docs/modules/usage/configuration-options.md

@@ -1,8 +1,10 @@
 # Configuration Options
 
+This guide details all configuration options available for OpenHands, helping you customize its behavior and integrate it with other services.
+
 :::note
-This page outlines all available configuration options for OpenHands, allowing you to customize its behavior and
-integrate it with other services. In GUI Mode, any settings applied through the Settings UI will take precedence.
+If you are running in [GUI Mode](https://docs.all-hands.dev/modules/usage/how-to/gui-mode), the settings available in the Settings UI will always
+take precedence.
 :::
 
 ## Core Configuration
@@ -291,17 +293,17 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - Default: `true`
   - Description: Whether function calling is enabled
 
-- `enable_browsing`
+- `codeact_enable_browsing`
   - Type: `bool`
   - Default: `false`
   - Description: Whether browsing delegate is enabled in the action space (only works with function calling)
 
-- `enable_llm_editor`
+- `codeact_enable_llm_editor`
   - Type: `bool`
   - Default: `false`
   - Description: Whether LLM editor is enabled in the action space (only works with function calling)
 
-- `enable_jupyter`
+- `codeact_enable_jupyter`
   - Type: `bool`
   - Default: `false`
   - Description: Whether Jupyter is enabled in the action space

docs/modules/usage/getting-started.mdx

@@ -3,97 +3,109 @@
 So you've [run OpenHands](./installation) and have
 [set up your LLM](./installation#setup). Now what?
 
-OpenHands can assist with a range of engineering tasks. However, the technology is still new, and we’re far from having
-agents that can handle complex tasks independently. It’s important to understand what the agent does well and where it
-needs support.
+OpenHands can help you tackle a wide variety of engineering tasks. But the technology
+is still new, and we're a long way off from having agents that can take on large, complicated
+engineering tasks without any guidance. So it's important to get a feel for what the agent
+does well, and where it might need some help.
 
 ## Hello World
 
-Start with a simple "hello world" example. It might be trickier than it seems!
+The first thing you might want to try is a simple "hello world" example.
+This can be more complicated than it sounds!
 
-Prompt the agent with:
-> Write a bash script hello.sh that prints "hello world!"
+Try prompting the agent with:
+> Please write a bash script hello.sh that prints "hello world!"
 
-The agent will write the script, set the correct permissions, and run it to check the output.
+You should see that the agent not only writes the script, it sets the correct
+permissions and runs the script to check the output.
 
 You can continue prompting the agent to refine your code. This is a great way to
 work with agents. Start simple, and iterate.
 
-> Modify hello.sh so that it accepts a name as the first argument, but defaults to "world"
+> Please modify hello.sh so that it accepts a name as the first argument, but defaults to "world"
 
-You can also use any language you need. The agent may need time to set up the environment.
+You can also work in any language you need, though the agent might need to spend some
+time setting up its environment!
 
 > Please convert hello.sh to a Ruby script, and run it
 
 ## Building From Scratch
 
-Agents excel at "greenfield" tasks, where they don’t need context about existing code and
-they can start from scratch.
-Begin with a simple task and iterate from there. Be specific about what you want and the tech stack.
+Agents do exceptionally well at "greenfield" tasks (tasks where they don't need
+any context about an existing codebase) and they can just start from scratch.
+
+It's best to start with a simple task, and then iterate on it. It's also best to be
+as specific as possible about what you want, what the tech stack should be, etc.
 
 For example, we might build a TODO app:
 
-> Build a frontend-only TODO app in React. All state should be stored in localStorage.
+> Please build a basic TODO list app in React. It should be frontend-only, and all state
+> should be kept in localStorage.
 
-Once the basic structure is in place, continue refining:
+We can keep iterating on the app once the skeleton is there:
 
-> Allow adding an optional due date to each task.
+> Please allow adding an optional due date to every task.
 
-Just like normal development, commit and push your code often.
+Just like with normal development, it's good to commit and push your code frequently.
 This way you can always revert back to an old state if the agent goes off track.
 You can ask the agent to commit and push for you:
 
-> Commit the changes and push them to a new branch called "feature/due-dates"
+> Please commit the changes and push them to a new branch called "feature/due-dates"
+
 
 ## Adding New Code
 
-OpenHands is great at adding new code to an existing codebase.
+OpenHands can also do a great job adding new code to an existing code base.
 
-For instance, you can ask OpenHands to add a GitHub action that lints your code. It might check your codebase to
-determine the language, then create a new file in `./github/workflows/lint.yml`.
+For example, you can ask OpenHands to add a new GitHub action to your project
+which lints your code. OpenHands may take a peek at your codebase to see what language
+it should use and then drop a new file into `./github/workflows/lint.yml`.
 
-> Add a GitHub action that lints the code in this repository.
+> Please add a GitHub action that lints the code in this repository.
 
-Some tasks need more context. While OpenHands can use commands like ls and grep to search, providing context upfront
-speeds things up and reduces token usage.
+Some tasks might require a bit more context. While OpenHands can use `ls` and `grep`
+to search through your codebase, providing context up front allows it to move faster,
+and more accurately. And it'll cost you fewer tokens!
 
-> Modify ./backend/api/routes.js to add a new route that returns a list of all tasks.
+> Please modify ./backend/api/routes.js to add a new route that returns a list of all tasks.
 
-> Add a new React component to the ./frontend/components directory to display a list of Widgets.
-> It should use the existing Widget component.
+> Please add a new React component that displays a list of Widgets to the ./frontend/components
+> directory. It should use the existing Widget component.
 
 ## Refactoring
 
-OpenHands does great at refactoring code in small chunks. Rather than rearchitecting the entire codebase,
-it's more effective to break up long files and functions or rename variables.
+OpenHands does great at refactoring existing code, especially in small chunks.
+You probably don't want to try rearchitecting your whole codebase, but breaking up
+long files and functions, renaming variables, etc. tend to work very well.
 
-> Rename all the single-letter variables in ./app.go.
+> Please rename all the single-letter variables in ./app.go.
 
-> Split the `build_and_deploy_widgets` function into two functions, `build_widgets` and `deploy_widgets` in widget.php.
+> Please break the function `build_and_deploy_widgets` into two functions, `build_widgets` and `deploy_widgets` in widget.php.
 
-> Break ./api/routes.js into separate files for each route.
+> Please break ./api/routes.js into separate files for each route.
 
 ## Bug Fixes
 
-OpenHands can help track down and fix bugs, but bug fixing can be tricky and often requires more context.
-It’s helpful if you’ve already diagnosed the issue and just need OpenHands to handle the logic.
+OpenHands can also help you track down and fix bugs in your code. But as any
+developer knows, bug fixing can be extremely tricky, and often OpenHands will need more context.
+It helps if you've diagnosed the bug, but want OpenHands to figure out the logic.
 
-> The email field in the `/subscribe` endpoint is rejecting .io domains. Fix this.
+> Currently the email field in the `/subscribe` endpoint is rejecting .io domains. Please fix this.
 
-> The `search_widgets` function in ./app.py is doing a case-sensitive search. Make it case-insensitive.
+> The `search_widgets` function in ./app.py is doing a case-sensitive search. Please make it case-insensitive.
 
-For bug fixing, test-driven development can be really useful. You can ask the agent to write a new test and iterate
-until the bug is fixed:
+It often helps to do test-driven development when bug fixing with an agent.
+You can ask the agent to write a new test, and then iterate until it fixes the bug:
 
-> The `hello` function crashes on the empty string. Write a test that reproduces this bug, then fix the code so it passes.
+> The `hello` function crashes on the empty string. Please write a test that reproduces this bug, then fix the code so it passes.
 
 ## More
 
-OpenHands can assist with nearly any coding task, but it takes some practice to get the best results.
-Keep these tips in mind:
+OpenHands is capable of helping out on just about any coding task but it takes some practice
+to get the most out of it. Remember to:
 * Keep your tasks small.
-* Be specific.
-* Provide plenty of context.
+* Be as specific as possible.
+* Provide as much context as possible.
 * Commit and push frequently.
 
 See [Prompting Best Practices](./prompting/prompting-best-practices) for more tips on how to get the most out of OpenHands.

docs/modules/usage/how-to/cli-mode.md

@@ -35,7 +35,7 @@ To run OpenHands in CLI mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,11 +45,52 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.cli
 ```
 
 This command will start an interactive session in Docker where you can input tasks and receive responses from OpenHands.
 
-The `-e SANDBOX_USER_ID=$(id -u)` is passed to the Docker command to ensure the sandbox user matches the host user’s
-permissions. This prevents the agent from creating root-owned files in the mounted workspace.
+## Examples of CLI Commands and Expected Outputs
+
+Here are some examples of CLI commands and their expected outputs:
+
+### Example 1: Simple Task
+
+```bash
+>> Write a Python script that prints "Hello, World!"
+```
+
+Expected Output:
+
+```bash
+🤖 Sure! Here is a Python script that prints "Hello, World!":
+
+❯ print("Hello, World!")
+```
+
+### Example 2: Bash Command
+
+```bash
+>> Create a directory named "test_dir"
+```
+
+Expected Output:
+
+```bash
+🤖 Creating a directory named "test_dir":
+
+❯ mkdir test_dir
+```
+
+### Example 3: Error Handling
+
+```bash
+>> Delete a non-existent file
+```
+
+Expected Output:
+
+```bash
+🤖 An error occurred. Please try again.
+```

docs/modules/usage/how-to/custom-sandbox-guide.md

@@ -1,10 +1,5 @@
 # Custom Sandbox
 
-:::note
-This guide is for users that would like to use their own custom Docker image for the runtime. For example
-with certain tools or programming languages pre-installed.
-:::
-
 The sandbox is where the agent performs its tasks. Instead of running commands directly on your computer
 (which could be risky), the agent runs them inside a Docker container.
 

docs/modules/usage/how-to/github-action.md

@@ -1,6 +1,6 @@
 # Using the OpenHands GitHub Action
 
-This guide explains how to use the OpenHands GitHub Action in your own projects.
+This guide explains how to use the OpenHands GitHub Action, both within the OpenHands repository and in your own projects.
 
 ## Using the Action in the OpenHands Repository
 

docs/modules/usage/how-to/gui-mode.md

@@ -11,21 +11,17 @@ OpenHands provides a Graphical User Interface (GUI) mode for interacting with th
 
 ### Initial Setup
 
-1. Upon first launch, you'll see a settings popup.
+1. Upon first launch, you'll see a settings page.
 2. Select an `LLM Provider` and `LLM Model` from the dropdown menus. If the required model does not exist in the list,
-   select `see advanced settings`. Then toggle `Advanced` options and enter it with the correct prefix in the
-   `Custom Model` text box.
+   toggle `Advanced` options and enter it with the correct prefix in the `Custom Model` text box.
 3. Enter the corresponding `API Key` for your chosen provider.
 4. Click `Save Changes` to apply the settings.
 
-### Version Control Tokens
+### GitHub Token Setup
 
-OpenHands supports multiple version control providers. You can configure tokens for multiple providers simultaneously.
-
-#### GitHub Token Setup
-
-OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if provided:
+OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it is available. This can happen in two ways:
 
+**Local Installation**: The user directly inputs their GitHub token.
 <details>
   <summary>Setting Up a GitHub Token</summary>
 
@@ -36,11 +32,12 @@ OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if pro
      - `repo` (Full control of private repositories)
    - **Fine-Grained Tokens**
      - All Repositories (You can select specific repositories, but this will impact what returns in repo search)
-     - Minimal Permissions ( Select `Meta Data = Read-only` read for search, `Pull Requests = Read and Write` and `Content = Read and Write` for branch creation)
+     - Minimal Permissions ( Select **Meta Data = Read-only** read for search, **Pull Requests = Read and Write**, **Content = Read and Write** for branch creation)
   2. **Enter Token in OpenHands**:
    - Click the Settings button (gear icon).
+   - Navigate to the `GitHub Settings` section.
    - Paste your token in the `GitHub Token` field.
-   - Click `Save` to apply the changes.
+   - Click `Save Changes` to apply the changes.
 </details>
 
 <details>
@@ -81,43 +78,21 @@ OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if pro
      - Check the browser console for any error messages.
 </details>
 
-#### GitLab Token Setup
-
-OpenHands automatically exports a `GITLAB_TOKEN` to the shell environment if provided:
+**OpenHands Cloud**: The token is obtained through GitHub OAuth authentication.
 
 <details>
-  <summary>Setting Up a GitLab Token</summary>
+  <summary>OAuth Authentication</summary>
 
-  1. **Generate a Personal Access Token (PAT)**:
-   - On GitLab, go to User Settings > Access Tokens.
-   - Create a new token with the following scopes:
-     - `api` (API access)
-     - `read_user` (Read user information)
-     - `read_repository` (Read repository)
-     - `write_repository` (Write repository)
-   - Set an expiration date or leave it blank for a non-expiring token.
-  2. **Enter Token in OpenHands**:
-   - Click the Settings button (gear icon).
-   - Paste your token in the `GitLab Token` field.
-   - Enter your GitLab instance URL if using self-hosted GitLab.
-   - Click `Save` to apply the changes.
-</details>
+  When using OpenHands Cloud, the GitHub OAuth flow requests the following permissions:
+   - Repository access (read/write)
+   - Workflow management
+   - Organization read access
 
-<details>
-  <summary>Troubleshooting</summary>
-
-  Common issues and solutions:
-
-  - **Token Not Recognized**:
-     - Ensure the token is properly saved in settings.
-     - Check that the token hasn't expired.
-     - Verify the token has the required scopes.
-     - For self-hosted instances, verify the correct instance URL.
-
-  - **Access Denied**:
-     - Verify project access permissions.
-     - Check if the token has the necessary scopes.
-     - For group/organization repositories, ensure you have proper access.
+  To authenticate OpenHands:
+   - Click `Sign in with GitHub` when prompted.
+   - Review the requested permissions.
+   - Authorize OpenHands to access your GitHub account.
+   - If using an organization, authorize organization access if prompted.
 </details>
 
 ### Advanced Settings

docs/modules/usage/how-to/headless-mode.md

@@ -32,7 +32,7 @@ To run OpenHands in Headless mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,13 +43,10 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.30 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 
-The `-e SANDBOX_USER_ID=$(id -u)` is passed to the Docker command to ensure the sandbox user matches the host user’s
-permissions. This prevents the agent from creating root-owned files in the mounted workspace.
-
 ## Advanced Headless Configurations
 
 To view all available configuration options for headless mode, run the Python command with the `--help` flag.

docs/modules/usage/installation.mdx

@@ -58,31 +58,30 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.30-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.30
 ```
 
 You'll find OpenHands running at http://localhost:3000!
 
-You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes/docker#connecting-to-your-filesystem),
+You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes#connecting-to-your-filesystem),
 run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
 interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
 or run it on tagged issues with [a GitHub action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
 ## Setup
 
-After launching OpenHands, you **must** select an `LLM Provider` and `LLM Model` and enter a corresponding `API Key`.
-This can be done during the initial settings popup or by selecting the `Settings`
-button (gear icon) in the UI.
+Upon launching OpenHands, you'll see a Settings page. You **must** select an `LLM Provider` and `LLM Model` and enter a corresponding `API Key`.
+These can be changed at any time by selecting the `Settings` button (gear icon) in the UI.
 
 If the required model does not exist in the list, you can toggle `Advanced` options and manually enter it with the correct prefix
 in the `Custom Model` text box.
@@ -94,17 +93,17 @@ OpenHands requires an API key to access most language models. Here's how to get
 
 #### Anthropic (Claude)
 
-1. [Create an Anthropic account](https://console.anthropic.com/).
-2. [Generate an API key](https://console.anthropic.com/settings/keys).
-3. [Set up billing](https://console.anthropic.com/settings/billing).
+1. [Create an Anthropic account](https://console.anthropic.com/)
+2. [Generate an API key](https://console.anthropic.com/settings/keys)
+3. [Set up billing](https://console.anthropic.com/settings/billing)
 
 Consider setting usage limits to control costs.
 
 #### OpenAI
 
-1. [Create an OpenAI account](https://platform.openai.com/).
-2. [Generate an API key](https://platform.openai.com/api-keys).
-3. [Set up billing](https://platform.openai.com/account/billing/overview).
+1. [Create an OpenAI account](https://platform.openai.com/)
+2. [Generate an API key](https://platform.openai.com/api-keys)
+3. [Set up billing](https://platform.openai.com/account/billing/overview)
 
 Now you're ready to [get started with OpenHands](./getting-started).
 
@@ -116,6 +115,8 @@ We use SemVer so `0.9` will automatically point to the latest `0.9.x` release, a
 - For the most up-to-date development version, replace $VERSION in `openhands:$VERSION` and `runtime:$VERSION`, with `main`.
 This version is unstable and is recommended for testing or development purposes only.
 
+You can choose the tag that best suits your needs based on stability requirements and desired features.
+
 For the development workflow, see [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
 Are you having trouble? Check out our [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting).

docs/modules/usage/key-features.md

@@ -1,31 +1,60 @@
+
 # OpenHands Feature Overview
 
-![overview](/img/oh-features.png)
+![overview](https://www.all-hands.dev/assets/product/product-slide-1.webp)
 
-### Chat Panel
-- Displays the conversation between the user and OpenHands.
-- OpenHands explains its actions in this panel.
-
-### Changes
-- Shows the file changes performed by OpenHands.
-
-### Workspace
-- Browse project files and directories.
-- Use the `Open in VS Code` option to:
-  * Modify files
+## 1. Workspace
+The Workspace feature provides a comprehensive development environment with the following key capabilities:
+- File Explorer: Browse, view, and manage project files and directories
+- Project Management: Import, create, and navigate between different projects
+- Integrated Development Tools: Seamless integration with various development workflows
+- File Operations:
+  * View file contents
+  * Create new files and folders
   * Upload and download files
+  * Basic file manipulation
 
-### Terminal
-- A space for OpenHands and users to run terminal commands.
+## 2. Jupyter Notebook
+The Jupyter Notebook feature offers an interactive coding and data analysis environment:
+- Interactive Code Cells: Execute Python code in a cell-based interface
+- Input and Output Tracking: Maintain a history of code inputs and their corresponding outputs
+- Persistent Session: Preserve code execution context between cells
+- Supports various Python operations and data analysis tasks
+- Real-time code execution and result visualization
 
-### Jupyter
-- Shows all Python commands that were executed by OpenHands.
-- Particularly handy when using OpenHands to perform data visualization tasks.
+## 3. Browser (Beta)
+The Browser feature provides web interaction capabilities:
+- Web Page Navigation: Open and browse websites within the application
+- Screenshot Capture: Automatically generate screenshots of web pages
+- Interaction Tools:
+  * Click elements
+  * Fill out forms
+  * Scroll pages
+  * Navigate through web content
+- Supports 15 different browser interaction functions
 
-### App
-- Displays the web server when OpenHands runs an application.
-- Users can interact with the running application.
+## 4. Terminal
+The Terminal feature offers a command-line interface within the application:
+- Execute Shell Commands: Run bash and system commands
+- Command History: Track and recall previous commands
+- Environment Interaction: Interact directly with the system's command line
+- Support for various programming and system administration tasks
 
-### Browser
-- Used by OpenHands to browse websites.
-- The browser is non-interactive.
+## 5. Chat / AI Conversation
+The Chat interface provides an AI-powered conversational experience:
+- Interactive AI Assistant: Engage in natural language conversations
+- Context-Aware Responses: AI understands and responds to development-related queries
+- Action Suggestions: Provides actionable recommendations for tasks
+- Conversation Management: Create, delete, and manage different conversation threads
+
+## 6. App (Beta)
+The main application interface combines all these features:
+- Integrated Workspace: Seamless integration of workspace, browser, terminal, and AI chat
+- Configurable Layout: Customize the arrangement of different feature panels
+- State Management: Maintain context and state across different features
+- Security and Privacy Controls: Manage application settings and permissions
+
+### Additional Notes
+- The application is currently in beta, with ongoing improvements and feature additions
+- Supports various development workflows and AI-assisted coding
+- Designed to enhance developer productivity through integrated tools and AI assistance

docs/modules/usage/llms/azure-llms.md

@@ -25,7 +25,7 @@ You will need your ChatGPT deployment name which can be found on the deployments
 <deployment-name> below.
 :::
 
-1. Enable `Advanced` options.
+1. Enable `Advanced` options
 2. Set the following:
    - `Custom Model` to azure/<deployment-name>
    - `Base URL` to your Azure API Base URL (e.g. `https://example-endpoint.openai.azure.com`)

docs/modules/usage/llms/llms.md

@@ -1,9 +1,5 @@
 # 🤖 LLM Backends
 
-:::note
-This section is for users who want to connect OpenHands to different LLMs.
-:::
-
 OpenHands can connect to any LLM supported by LiteLLM. However, it requires a powerful model to work.
 
 ## Model Recommendations
@@ -13,14 +9,10 @@ recommendations for model selection. Our latest benchmarking results can be foun
 
 Based on these findings and community feedback, the following models have been verified to work reasonably well with OpenHands:
 
-- [anthropic/claude-3-7-sonnet-20250219](https://www.anthropic.com/api) (recommended)
-- [gemini/gemini-2.5-pro](https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025/)
-- [deepseek/deepseek-chat](https://api-docs.deepseek.com/)
-- [openai/o3-mini](https://openai.com/index/openai-o3-mini/)
-- [openai/o3](https://openai.com/index/introducing-o3-and-o4-mini/)
-- [openai/o4-mini](https://openai.com/index/introducing-o3-and-o4-mini/)
-- [all-hands/openhands-lm-32b-v0.1](https://www.all-hands.dev/blog/introducing-openhands-lm-32b----a-strong-open-coding-agent-model) -- available through [OpenRouter](https://openrouter.ai/all-hands/openhands-lm-32b-v0.1)
-
+- anthropic/claude-3-5-sonnet-20241022 (recommended)
+- anthropic/claude-3-5-haiku-20241022
+- deepseek/deepseek-chat
+- gpt-4o
 
 :::warning
 OpenHands will issue many prompts to the LLM you configure. Most of these LLMs cost money, so be sure to set spending
@@ -64,7 +56,6 @@ We have a few guides for running OpenHands with specific model providers:
 - [Azure](llms/azure-llms)
 - [Google](llms/google-llms)
 - [Groq](llms/groq)
-- [Local LLMs with SGLang or vLLM](llms/../local-llms.md)
 - [LiteLLM Proxy](llms/litellm-proxy)
 - [OpenAI](llms/openai-llms)
 - [OpenRouter](llms/openrouter)

docs/modules/usage/llms/local-llms.md

@@ -1,83 +1,192 @@
-# Local LLM with SGLang or vLLM
+# Local LLM with Ollama
 
 :::warning
 When using a Local LLM, OpenHands may have limited functionality.
-It is highly recommended that you use GPUs to serve local models for optimal experience.
 :::
 
-## News
+Ensure that you have the Ollama server up and running.
+For detailed startup instructions, refer to [here](https://github.com/ollama/ollama).
 
-- 2025/03/31: We released an open model OpenHands LM v0.1 32B that achieves 37.1% on SWE-Bench Verified
-([blog](https://www.all-hands.dev/blog/introducing-openhands-lm-32b----a-strong-open-coding-agent-model), [model](https://huggingface.co/all-hands/openhands-lm-32b-v0.1)).
+This guide assumes you've started ollama with `ollama serve`. If you're running ollama differently (e.g. inside docker), the instructions might need to be modified. Please note that if you're running WSL the default ollama configuration blocks requests from docker containers. See [here](#configuring-ollama-service-wsl-en).
 
-## Download the Model from Huggingface
+## Pull Models
 
-For example, to download [OpenHands LM 32B v0.1](https://huggingface.co/all-hands/openhands-lm-32b-v0.1):
+Ollama model names can be found [here](https://ollama.com/library). For a small example, you can use
+the `codellama:7b` model. Bigger models will generally perform better.
 
 ```bash
-huggingface-cli download all-hands/openhands-lm-32b-v0.1 --local-dir all-hands/openhands-lm-32b-v0.1
+ollama pull codellama:7b
 ```
 
-## Create an OpenAI-Compatible Endpoint With a Model Serving Framework
-
-### Serving with SGLang
-
-- Install SGLang following [the official documentation](https://docs.sglang.ai/start/install.html).
-- Example launch command for OpenHands LM 32B (with at least 2 GPUs):
+you can check which models you have downloaded like this:
 
 ```bash
-SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python3 -m sglang.launch_server \
-    --model all-hands/openhands-lm-32b-v0.1 \
-    --served-model-name openhands-lm-32b-v0.1 \
-    --port 8000 \
-    --tp 2 --dp 1 \
-    --host 0.0.0.0 \
-    --api-key mykey --context-length 131072
+~$ ollama list
+NAME                            ID              SIZE    MODIFIED
+codellama:7b                    8fdf8f752f6e    3.8 GB  6 weeks ago
+mistral:7b-instruct-v0.2-q4_K_M eb14864c7427    4.4 GB  2 weeks ago
+starcoder2:latest               f67ae0f64584    1.7 GB  19 hours ago
 ```
 
-### Serving with vLLM
+## Run OpenHands with Docker
 
-- Install vLLM following [the official documentation](https://docs.vllm.ai/en/latest/getting_started/installation.html).
-- Example launch command for OpenHands LM 32B (with at least 2 GPUs):
+### Start OpenHands
+Use the instructions [here](../getting-started) to start OpenHands using Docker.
+But when running `docker run`, you'll need to add a few more arguments:
 
 ```bash
-vllm serve all-hands/openhands-lm-32b-v0.1 \
-    --host 0.0.0.0 --port 8000 \
-    --api-key mykey \
-    --tensor-parallel-size 2 \
-    --served-model-name openhands-lm-32b-v0.1
-    --enable-prefix-caching
+docker run # ...
+    --add-host host.docker.internal:host-gateway \
+    -e LLM_OLLAMA_BASE_URL="http://host.docker.internal:11434" \
+    # ...
 ```
 
-## Run and Configure OpenHands
+LLM_OLLAMA_BASE_URL is optional. If you set it, it will be used to show
+the available installed models in the UI.
 
-### Run OpenHands
 
-#### Using Docker
+### Configure the Web Application
 
-Run OpenHands using [the official docker run command](../installation#start-the-app).
+When running `openhands`, you'll need to set the following in the OpenHands UI through the Settings:
+- the model to "ollama/<model-name>"
+- the base url to `http://host.docker.internal:11434`
+- the API key is optional, you can use any string, such as `ollama`.
 
-#### Using Development Mode
+
+## Run OpenHands in Development Mode
+
+### Build from Source
 
 Use the instructions in [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) to build OpenHands.
-Ensure `config.toml` exists by running `make setup-config` which will create one for you. In the `config.toml`, enter the following:
+Make sure `config.toml` is there by running `make setup-config` which will create one for you. In `config.toml`, enter the followings:
 
 ```
 [core]
-workspace_base="/path/to/your/workspace"
+workspace_base="./workspace"
 
 [llm]
-model="openhands-lm-32b-v0.1"
-ollama_base_url="http://localhost:8000"
+embedding_model="local"
+ollama_base_url="http://localhost:11434"
+
 ```
 
-Start OpenHands using `make run`.
+Done! Now you can start OpenHands by: `make run`. You now should be able to connect to `http://localhost:3000/`
 
-### Configure OpenHands
+### Configure the Web Application
 
-Once OpenHands is running, you'll need to set the following in the OpenHands UI through the Settings:
-1. Enable `Advanced` options.
-2. Set the following:
-- `Custom Model` to `openai/<served-model-name>` (e.g. `openai/openhands-lm-32b-v0.1`)
-- `Base URL` to `http://host.docker.internal:8000`
-- `API key` to the same string you set when serving the model (e.g. `mykey`)
+In the OpenHands UI, click on the Settings wheel in the bottom-left corner.
+Then in the `Model` input, enter `ollama/codellama:7b`, or the name of the model you pulled earlier.
+If it doesn’t show up in the dropdown, enable `Advanced Settings` and type it in. Please note: you need the model name as listed by `ollama list`, with the prefix `ollama/`.
+
+In the API Key field, enter `ollama` or any value, since you don't need a particular key.
+
+In the Base URL field, enter `http://localhost:11434`.
+
+And now you're ready to go!
+
+## Configuring the ollama service (WSL) {#configuring-ollama-service-wsl-en}
+
+The default configuration for ollama in WSL only serves localhost. This means you can't reach it from a docker container. eg. it wont work with OpenHands. First let's test that ollama is running correctly.
+
+```bash
+ollama list # get list of installed models
+curl http://localhost:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+#ex. curl http://localhost:11434/api/generate -d '{"model":"codellama:7b","prompt":"hi"}'
+#ex. curl http://localhost:11434/api/generate -d '{"model":"codellama","prompt":"hi"}' #the tag is optional if there is only one
+```
+
+Once that is done, test that it allows "outside" requests, like those from inside a docker container.
+
+```bash
+docker ps # get list of running docker containers, for most accurate test choose the OpenHands sandbox container.
+docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+#ex. docker exec cd9cc82f7a11 curl http://host.docker.internal:11434/api/generate -d '{"model":"codellama","prompt":"hi"}'
+```
+
+## Fixing it
+
+Now let's make it work. Edit /etc/systemd/system/ollama.service with sudo privileges. (Path may vary depending on linux flavor)
+
+```bash
+sudo vi /etc/systemd/system/ollama.service
+```
+
+or
+
+```bash
+sudo nano /etc/systemd/system/ollama.service
+```
+
+In the [Service] bracket add these lines
+
+```
+Environment="OLLAMA_HOST=0.0.0.0:11434"
+Environment="OLLAMA_ORIGINS=*"
+```
+
+Then save, reload the configuration and restart the service.
+
+```bash
+sudo systemctl daemon-reload
+sudo systemctl restart ollama
+```
+
+Finally test that ollama is accessible from within the container
+
+```bash
+ollama list # get list of installed models
+docker ps # get list of running docker containers, for most accurate test choose the OpenHands sandbox container.
+docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+```
+
+
+# Local LLM with LM Studio
+
+Steps to set up LM Studio:
+1. Open LM Studio
+2. Go to the Local Server tab.
+3. Click the "Start Server" button.
+4. Select the model you want to use from the dropdown.
+
+
+Set the following configs:
+```bash
+LLM_MODEL="openai/lmstudio"
+LLM_BASE_URL="http://localhost:1234/v1"
+CUSTOM_LLM_PROVIDER="openai"
+```
+
+### Docker
+
+```bash
+docker run # ...
+    -e LLM_MODEL="openai/lmstudio" \
+    -e LLM_BASE_URL="http://host.docker.internal:1234/v1" \
+    -e CUSTOM_LLM_PROVIDER="openai" \
+    # ...
+```
+
+You should now be able to connect to `http://localhost:3000/`
+
+In the development environment, you can set the following configs in the `config.toml` file:
+
+```
+[core]
+workspace_base="./workspace"
+
+[llm]
+model="openai/lmstudio"
+base_url="http://localhost:1234/v1"
+custom_llm_provider="openai"
+```
+
+Done! Now you can start OpenHands by: `make run` without Docker. You now should be able to connect to `http://localhost:3000/`
+
+# Note
+
+For WSL, run the following commands in cmd to set up the networking mode to mirrored:
+
+```
+python -c  "print('[wsl2]\nnetworkingMode=mirrored',file=open(r'%UserProfile%\.wslconfig','w'))"
+wsl --shutdown
+```

docs/modules/usage/prompting/prompting-best-practices.md

@@ -1,38 +1,37 @@
 # Prompting Best Practices
 
-When working with OpenHands AI software developer, providing clear and effective prompts is key to getting accurate
-and useful responses. This guide outlines best practices for crafting effective prompts.
+When working with OpenHands AI software developer, it's crucial to provide clear and effective prompts. This guide outlines best practices for creating prompts that will yield the most accurate and useful responses.
 
 ## Characteristics of Good Prompts
 
 Good prompts are:
 
-- **Concrete**: Clearly describe what functionality should be added or what error needs fixing.
-- **Location-specific**: Specify the locations in the codebase that should be modified, if known.
-- **Appropriately scoped**: Focus on a single feature, typically not exceeding 100 lines of code.
+- **Concrete**: They explain exactly what functionality should be added or what error needs to be fixed.
+- **Location-specific**: If known, they explain the locations in the code base that should be modified.
+- **Appropriately scoped**: They should be the size of a single feature, typically not exceeding 100 lines of code.
 
 ## Examples
 
 ### Good Prompt Examples
 
-- Add a function `calculate_average` in `utils/math_operations.py` that takes a list of numbers as input and returns their average.
-- Fix the TypeError in `frontend/src/components/UserProfile.tsx` occurring on line 42. The error suggests we're trying to access a property of undefined.
-- Implement input validation for the email field in the registration form. Update `frontend/src/components/RegistrationForm.tsx` to check if the email is in a valid format before submission.
+- "Add a function `calculate_average` in `utils/math_operations.py` that takes a list of numbers as input and returns their average."
+- "Fix the TypeError in `frontend/src/components/UserProfile.tsx` occurring on line 42. The error suggests we're trying to access a property of undefined."
+- "Implement input validation for the email field in the registration form. Update `frontend/src/components/RegistrationForm.tsx` to check if the email is in a valid format before submission."
 
 ### Bad Prompt Examples
 
-- Make the code better. (Too vague, not concrete)
-- Rewrite the entire backend to use a different framework. (Not appropriately scoped)
-- There's a bug somewhere in the user authentication. Can you find and fix it? (Lacks specificity and location information)
+- "Make the code better." (Too vague, not concrete)
+- "Rewrite the entire backend to use a different framework." (Not appropriately scoped)
+- "There's a bug somewhere in the user authentication. Can you find and fix it?" (Lacks specificity and location information)
 
 ## Tips for Effective Prompting
 
 - Be as specific as possible about the desired outcome or the problem to be solved.
 - Provide context, including relevant file paths and line numbers if available.
-- Break large tasks into smaller, manageable prompts.
-- Include relevant error messages or logs.
-- Specify the programming language or framework, if not obvious.
+- Break down large tasks into smaller, manageable prompts.
+- Include any relevant error messages or logs.
+- Specify the programming language or framework if it's not obvious from the context.
 
-The more precise and informative your prompt, the better OpenHands can assist you.
+Remember, the more precise and informative your prompt is, the better the AI can assist you in developing or modifying the OpenHands software.
 
 See [Getting Started with OpenHands](../getting-started) for more examples of helpful prompts.

docs/modules/usage/runtimes-index.md

@@ -1,26 +1,24 @@
 # Runtime Configuration
 
-:::note
-This section is for users that would like to use a runtime other than Docker for OpenHands.
-:::
-
 A Runtime is an environment where the OpenHands agent can edit files and run
 commands.
 
-By default, OpenHands uses a [Docker-based runtime](./runtimes/docker), running on your local computer.
+By default, OpenHands uses a Docker-based runtime, running on your local computer.
 This means you only have to pay for the LLM you're using, and your code is only ever sent to the LLM.
 
-We also support other runtimes, which are typically managed by third-parties.
+We also support "remote" runtimes, which are typically managed by third-parties.
+They can make setup a bit simpler and more scalable, especially
+if you're running many OpenHands conversations in parallel (e.g. to do evaluation).
 
-Additionally, we provide a [Local Runtime](./runtimes/local) that runs directly on your machine without Docker,
+Additionally, we provide a "local" runtime that runs directly on your machine without Docker,
 which can be useful in controlled environments like CI pipelines.
 
 ## Available Runtimes
 
 OpenHands supports several different runtime environments:
 
-- [Docker Runtime](./runtimes/docker.md) - The default runtime that uses Docker containers for isolation (recommended for most users).
-- [OpenHands Remote Runtime](./runtimes/remote.md) - Cloud-based runtime for parallel execution (beta).
-- [Modal Runtime](./runtimes/modal.md) - Runtime provided by our partners at Modal.
-- [Daytona Runtime](./runtimes/daytona.md) - Runtime provided by Daytona.
-- [Local Runtime](./runtimes/local.md) - Direct execution on your local machine without Docker.
+- [Docker Runtime](./runtimes/docker.md) - The default runtime that uses Docker containers for isolation (recommended for most users)
+- [OpenHands Remote Runtime](./runtimes/remote.md) - Cloud-based runtime for parallel execution (beta)
+- [Modal Runtime](./runtimes/modal.md) - Runtime provided by our partners at Modal
+- [Daytona Runtime](./runtimes/daytona.md) - Runtime provided by Daytona
+- [Local Runtime](./runtimes/local.md) - Direct execution on your local machine without Docker

docs/modules/usage/runtimes/docker.md

@@ -8,7 +8,7 @@ that contains our Runtime server, as well as some basic utilities for Python and
 You can also [build your own runtime image](../how-to/custom-sandbox-guide).
 
 ## Connecting to Your filesystem
-A useful feature is the ability to connect to your local filesystem. To mount your filesystem into the runtime:
+One useful feature here is the ability to connect to your local filesystem. To mount your filesystem into the runtime:
 1. Set `WORKSPACE_BASE`:
 
     ```bash
@@ -35,25 +35,25 @@ A useful feature is the ability to connect to your local filesystem. To mount yo
 Be careful! There's nothing stopping the OpenHands agent from deleting or modifying
 any files that are mounted into its workspace.
 
-The `-e SANDBOX_USER_ID=$(id -u)` is passed to the Docker command to ensure the sandbox user matches the host user’s
-permissions. This prevents the agent from creating root-owned files in the mounted workspace.
+This setup can cause some issues with file permissions (hence the `SANDBOX_USER_ID` variable)
+but seems to work well on most systems.
 
 ## Hardened Docker Installation
 
-When deploying OpenHands in environments where security is a priority, you should consider implementing a hardened
-Docker configuration. This section provides recommendations for securing your OpenHands Docker deployment beyond the default configuration.
+When deploying OpenHands in environments where security is a priority, you should consider implementing a hardened Docker configuration. This section provides recommendations for securing your OpenHands Docker deployment beyond the default configuration.
 
 ### Security Considerations
 
-The default Docker configuration in the README is designed for ease of use on a local development machine. If you're
-running on a public network (e.g. airport WiFi), you should implement additional security measures.
+The default Docker configuration in the README is designed for ease of use on a local development machine. If you're running on a public network (e.g. airport WiFi),
+you should implement additional security measures.
 
 ### Network Binding Security
 
-By default, OpenHands binds to all network interfaces (`0.0.0.0`), which can expose your instance to all networks the
-host is connected to. For a more secure setup:
+By default, OpenHands binds to all network interfaces (`0.0.0.0`), which can expose your instance to all networks the host is connected to. For a more secure setup:
 
-1. **Restrict Network Binding**: Use the `runtime_binding_address` configuration to restrict which network interfaces OpenHands listens on:
+1. **Restrict Network Binding**:
+
+   Use the `runtime_binding_address` configuration to restrict which network interfaces OpenHands listens on:
 
    ```bash
    docker run # ...
@@ -63,7 +63,9 @@ host is connected to. For a more secure setup:
 
    This configuration ensures OpenHands only listens on the loopback interface (`127.0.0.1`), making it accessible only from the local machine.
 
-2. **Secure Port Binding**: Modify the `-p` flag to bind only to localhost instead of all interfaces:
+2. **Secure Port Binding**:
+
+   Modify the `-p` flag to bind only to localhost instead of all interfaces:
 
    ```bash
    docker run # ... \

docs/modules/usage/runtimes/local.md

@@ -1,26 +1,23 @@
 # Local Runtime
 
-The Local Runtime allows the OpenHands agent to execute actions directly on your local machine without using Docker.
-This runtime is primarily intended for controlled environments like CI pipelines or testing scenarios where Docker is not available.
+The Local Runtime allows the OpenHands agent to execute actions directly on your local machine without using Docker. This runtime is primarily intended for controlled environments like CI pipelines or testing scenarios where Docker is not available.
 
 :::caution
-**Security Warning**: The Local Runtime runs without any sandbox isolation. The agent can directly access and modify
-files on your machine. Only use this runtime in controlled environments or when you fully understand the security implications.
+**Security Warning**: The Local Runtime runs without any sandbox isolation. The agent can directly access and modify files on your machine. Only use this runtime in controlled environments or when you fully understand the security implications.
 :::
 
 ## Prerequisites
 
 Before using the Local Runtime, ensure that:
 
-1. You can run OpenHands using the [Development workflow](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+1. You have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 2. tmux is available on your system.
 
 ## Configuration
 
-To use the Local Runtime, besides required configurations like the LLM provider, model and API key, you'll need to set
-the following options via environment variables or the [config.toml file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml) when starting OpenHands:
+To use the Local Runtime, besides required configurations like the model, API key, you'll need to set the following options via environment variables or the [config.toml file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml) when starting OpenHands:
 
-Via environment variables:
+- Via environment variables:
 
 ```bash
 # Required
@@ -30,7 +27,7 @@ export RUNTIME=local
 export WORKSPACE_BASE=/path/to/your/workspace
 ```
 
-Via `config.toml`:
+- Via `config.toml`:
 
 ```toml
 [core]
@@ -62,3 +59,4 @@ The Local Runtime is particularly useful for:
 - CI/CD pipelines where Docker is not available.
 - Testing and development of OpenHands itself.
 - Environments where container usage is restricted.
+- Scenarios where direct file system access is required.

docs/modules/usage/runtimes/modal.md

@@ -9,5 +9,5 @@ You'll then need to set the following environment variables when starting OpenHa
 docker run # ...
     -e RUNTIME=modal \
     -e MODAL_API_TOKEN_ID="your-id" \
-    -e MODAL_API_TOKEN_SECRET="modal-api-key" \
+    -e MODAL_API_TOKEN_SECRET="your-secret" \
 ```

docs/modules/usage/runtimes/remote.md

@@ -1,9 +1,6 @@
 # OpenHands Remote Runtime
 
-:::note
-This runtime is specifically designed for agent evaluation purposes only through the
-[OpenHands evaluation harness](https://github.com/All-Hands-AI/OpenHands/tree/main/evaluation). It should not be used to launch production OpenHands applications.
-:::
+OpenHands Remote Runtime is currently in beta (read [here](https://runtime.all-hands.dev/) for more details), it allows you to launch runtimes in parallel in the cloud.
+Fill out [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply if you want to try this out!
 
-OpenHands Remote Runtime is currently in beta (read [here](https://runtime.all-hands.dev/) for more details), it allows you to launch runtimes
-in parallel in the cloud. Fill out [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply if you want to try this out!
+NOTE: This runtime is specifically designed for agent evaluation purposes only through [OpenHands evaluation harness](https://github.com/All-Hands-AI/OpenHands/tree/main/evaluation). It should not be used to launch production OpenHands applications.

docs/modules/usage/troubleshooting/troubleshooting.md

@@ -20,18 +20,25 @@ Try these in order:
 * If using Docker Desktop, ensure `Settings > Advanced > Allow the default Docker socket to be used` is enabled.
 * Depending on your configuration you may need `Settings > Resources > Network > Enable host networking` enabled in Docker Desktop.
 * Reinstall Docker Desktop.
+---
 
-### Permission Error
+# Development Workflow Specific
+### Error building runtime docker image
 
 **Description**
 
-On initial prompt, an error is seen with `Permission Denied` or `PermissionError`.
+Attempts to start a new session fail, and errors with terms like the following appear in the logs:
+```
+debian-security bookworm-security
+InRelease At least one invalid signature was encountered.
+```
 
-**Resolution**
+This seems to happen when the hash of an existing external library changes and your local docker instance has
+cached a previous version. To work around this, please try the following:
 
-* Check if the `~/.openhands-state` is owned by `root`. If so, you can:
-  * Change the directory's ownership: `sudo chown <user>:<user> ~/.openhands-state`.
-  * or update permissions on the directory: `sudo chmod 777 ~/.openhands-state`
-  * or delete it if you don’t need previous data. OpenHands will recreate it. You'll need to re-enter LLM settings.
-* If mounting a local directory, ensure your `WORKSPACE_BASE` has the necessary permissions for the user running
-  OpenHands.
+* Stop any containers where the name has the prefix `openhands-runtime-` :
+  `docker ps --filter name=openhands-runtime- --filter status=running -aq | xargs docker stop`
+* Remove any containers where the name has the prefix `openhands-runtime-` :
+  `docker rmi $(docker images --filter name=openhands-runtime- -q --no-trunc)`
+* Stop and Remove any containers / images where the name has the prefix `openhands-runtime-`
+* Prune containers / images : `docker container prune -f && docker image prune -f`

docs/package-lock.json

@@ -15,8 +15,8 @@
         "@mdx-js/react": "^3.1.0",
         "clsx": "^2.0.0",
         "prism-react-renderer": "^2.4.1",
-        "react": "^19.1.0",
-        "react-dom": "^19.1.0",
+        "react": "^19.0.0",
+        "react-dom": "^19.0.0",
         "react-icons": "^5.5.0",
         "react-use": "^17.6.0"
       },
@@ -24,9 +24,7 @@
         "@docusaurus/module-type-aliases": "^3.5.1",
         "@docusaurus/tsconfig": "^3.7.0",
         "@docusaurus/types": "^3.5.1",
-        "swagger-cli": "^4.0.4",
-        "swagger-ui-dist": "^5.21.0",
-        "typescript": "~5.8.3"
+        "typescript": "~5.8.2"
       },
       "engines": {
         "node": ">=18.0"
@@ -275,273 +273,6 @@
         "node": ">=6.0.0"
       }
     },
-    "node_modules/@apidevtools/openapi-schemas": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/@apidevtools/openapi-schemas/-/openapi-schemas-2.1.0.tgz",
-      "integrity": "sha512-Zc1AlqrJlX3SlpupFGpiLi2EbteyP7fXmUOGup6/DnkRgjP9bgMM/ag+n91rsv0U1Gpz0H3VILA/o3bW7Ua6BQ==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">=10"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli": {
-      "version": "4.0.4",
-      "resolved": "https://registry.npmjs.org/@apidevtools/swagger-cli/-/swagger-cli-4.0.4.tgz",
-      "integrity": "sha512-hdDT3B6GLVovCsRZYDi3+wMcB1HfetTU20l2DC8zD3iFRNMC6QNAZG5fo/6PYeHWBEv7ri4MvnlKodhNB0nt7g==",
-      "deprecated": "This package has been abandoned. Please switch to using the actively maintained @redocly/cli",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "@apidevtools/swagger-parser": "^10.0.1",
-        "chalk": "^4.1.0",
-        "js-yaml": "^3.14.0",
-        "yargs": "^15.4.1"
-      },
-      "bin": {
-        "swagger-cli": "bin/swagger-cli.js"
-      },
-      "engines": {
-        "node": ">=10"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/argparse": {
-      "version": "1.0.10",
-      "resolved": "https://registry.npmjs.org/argparse/-/argparse-1.0.10.tgz",
-      "integrity": "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "sprintf-js": "~1.0.2"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/camelcase": {
-      "version": "5.3.1",
-      "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz",
-      "integrity": "sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">=6"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/cliui": {
-      "version": "6.0.0",
-      "resolved": "https://registry.npmjs.org/cliui/-/cliui-6.0.0.tgz",
-      "integrity": "sha512-t6wbgtoCXvAzst7QgXxJYqPt0usEfbgQdftEPbLL/cvv6HPE5VgvqCuAIDR0NgU52ds6rFwqrgakNLrHEjCbrQ==",
-      "dev": true,
-      "license": "ISC",
-      "dependencies": {
-        "string-width": "^4.2.0",
-        "strip-ansi": "^6.0.0",
-        "wrap-ansi": "^6.2.0"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/emoji-regex": {
-      "version": "8.0.0",
-      "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
-      "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==",
-      "dev": true,
-      "license": "MIT"
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/find-up": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/find-up/-/find-up-4.1.0.tgz",
-      "integrity": "sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "locate-path": "^5.0.0",
-        "path-exists": "^4.0.0"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/js-yaml": {
-      "version": "3.14.1",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.1.tgz",
-      "integrity": "sha512-okMH7OXXJ7YrN9Ok3/SXrnu4iX9yOk+25nqX4imS2npuvTYDmo/QEZoqwZkYaIDk3jVvBOTOIEgEhaLOynBS9g==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "argparse": "^1.0.7",
-        "esprima": "^4.0.0"
-      },
-      "bin": {
-        "js-yaml": "bin/js-yaml.js"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/locate-path": {
-      "version": "5.0.0",
-      "resolved": "https://registry.npmjs.org/locate-path/-/locate-path-5.0.0.tgz",
-      "integrity": "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "p-locate": "^4.1.0"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/p-limit": {
-      "version": "2.3.0",
-      "resolved": "https://registry.npmjs.org/p-limit/-/p-limit-2.3.0.tgz",
-      "integrity": "sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "p-try": "^2.0.0"
-      },
-      "engines": {
-        "node": ">=6"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/p-locate": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/p-locate/-/p-locate-4.1.0.tgz",
-      "integrity": "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "p-limit": "^2.2.0"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/path-exists": {
-      "version": "4.0.0",
-      "resolved": "https://registry.npmjs.org/path-exists/-/path-exists-4.0.0.tgz",
-      "integrity": "sha512-ak9Qy5Q7jYb2Wwcey5Fpvg2KoAc/ZIhLSLOSBmRmygPsGwkVVt0fZa0qrtMz+m6tJTAHfZQ8FnmB4MG4LWy7/w==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/string-width": {
-      "version": "4.2.3",
-      "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
-      "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "emoji-regex": "^8.0.0",
-        "is-fullwidth-code-point": "^3.0.0",
-        "strip-ansi": "^6.0.1"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/wrap-ansi": {
-      "version": "6.2.0",
-      "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-6.2.0.tgz",
-      "integrity": "sha512-r6lPcBGxZXlIcymEu7InxDMhdW0KDxpLgoFLcguasxCaJ/SOIZwINatK9KY/tf+ZrlywOKU0UDj3ATXUBfxJXA==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "ansi-styles": "^4.0.0",
-        "string-width": "^4.1.0",
-        "strip-ansi": "^6.0.0"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/y18n": {
-      "version": "4.0.3",
-      "resolved": "https://registry.npmjs.org/y18n/-/y18n-4.0.3.tgz",
-      "integrity": "sha512-JKhqTOwSrqNA1NY5lSztJ1GrBiUodLMmIZuLiDaMRJ+itFd+ABVE8XBjOvIWL+rSqNDC74LCSFmlb/U4UZ4hJQ==",
-      "dev": true,
-      "license": "ISC"
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/yargs": {
-      "version": "15.4.1",
-      "resolved": "https://registry.npmjs.org/yargs/-/yargs-15.4.1.tgz",
-      "integrity": "sha512-aePbxDmcYW++PaqBsJ+HYUFwCdv4LVvdnhBy78E57PIor8/OVvhMrADFFEDh8DHDFRv/O9i3lPhsENjO7QX0+A==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "cliui": "^6.0.0",
-        "decamelize": "^1.2.0",
-        "find-up": "^4.1.0",
-        "get-caller-file": "^2.0.1",
-        "require-directory": "^2.1.1",
-        "require-main-filename": "^2.0.0",
-        "set-blocking": "^2.0.0",
-        "string-width": "^4.2.0",
-        "which-module": "^2.0.0",
-        "y18n": "^4.0.0",
-        "yargs-parser": "^18.1.2"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/@apidevtools/swagger-cli/node_modules/yargs-parser": {
-      "version": "18.1.3",
-      "resolved": "https://registry.npmjs.org/yargs-parser/-/yargs-parser-18.1.3.tgz",
-      "integrity": "sha512-o50j0JeToy/4K6OZcaQmW6lyXXKhq7csREXcDwk2omFPJEwUNOVtJKvmDr9EI1fAJZUyZcRF7kxGBWmRXudrCQ==",
-      "dev": true,
-      "license": "ISC",
-      "dependencies": {
-        "camelcase": "^5.0.0",
-        "decamelize": "^1.2.0"
-      },
-      "engines": {
-        "node": ">=6"
-      }
-    },
-    "node_modules/@apidevtools/swagger-methods": {
-      "version": "3.0.2",
-      "resolved": "https://registry.npmjs.org/@apidevtools/swagger-methods/-/swagger-methods-3.0.2.tgz",
-      "integrity": "sha512-QAkD5kK2b1WfjDS/UQn/qQkbwF31uqRjPTrsCs5ZG9BQGAkjwvqGFjjPqAuzac/IYzpPtRzjCP1WrTuAIjMrXg==",
-      "dev": true,
-      "license": "MIT"
-    },
-    "node_modules/@apidevtools/swagger-parser": {
-      "version": "10.1.1",
-      "resolved": "https://registry.npmjs.org/@apidevtools/swagger-parser/-/swagger-parser-10.1.1.tgz",
-      "integrity": "sha512-u/kozRnsPO/x8QtKYJOqoGtC4kH6yg1lfYkB9Au0WhYB0FNLpyFusttQtvhlwjtG3rOwiRz4D8DnnXa8iEpIKA==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "@apidevtools/json-schema-ref-parser": "11.7.2",
-        "@apidevtools/openapi-schemas": "^2.1.0",
-        "@apidevtools/swagger-methods": "^3.0.2",
-        "@jsdevtools/ono": "^7.1.3",
-        "ajv": "^8.17.1",
-        "ajv-draft-04": "^1.0.0",
-        "call-me-maybe": "^1.0.2"
-      },
-      "peerDependencies": {
-        "openapi-types": ">=7"
-      }
-    },
-    "node_modules/@apidevtools/swagger-parser/node_modules/@apidevtools/json-schema-ref-parser": {
-      "version": "11.7.2",
-      "resolved": "https://registry.npmjs.org/@apidevtools/json-schema-ref-parser/-/json-schema-ref-parser-11.7.2.tgz",
-      "integrity": "sha512-4gY54eEGEstClvEkGnwVkTkrx0sqwemEFG5OSRRn3tD91XH0+Q8XIkYIfo7IwEWPpJZwILb9GUXeShtplRc/eA==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "@jsdevtools/ono": "^7.1.3",
-        "@types/json-schema": "^7.0.15",
-        "js-yaml": "^4.1.0"
-      },
-      "engines": {
-        "node": ">= 16"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/philsturgeon"
-      }
-    },
     "node_modules/@babel/code-frame": {
       "version": "7.26.2",
       "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
@@ -4104,13 +3835,6 @@
         "@jridgewell/sourcemap-codec": "^1.4.14"
       }
     },
-    "node_modules/@jsdevtools/ono": {
-      "version": "7.1.3",
-      "resolved": "https://registry.npmjs.org/@jsdevtools/ono/-/ono-7.1.3.tgz",
-      "integrity": "sha512-4JQNk+3mVzK3xh2rqd6RB4J46qUR19azEHBneZyTZM+c456qOrbbM/5xcR8huNCCcbVt7+UmizG6GuUvPvKUYg==",
-      "dev": true,
-      "license": "MIT"
-    },
     "node_modules/@leichtgewicht/ip-codec": {
       "version": "2.0.5",
       "resolved": "https://registry.npmjs.org/@leichtgewicht/ip-codec/-/ip-codec-2.0.5.tgz",
@@ -4246,14 +3970,6 @@
       "integrity": "sha512-8LduaNlMZGwdZ6qWrKlfa+2M4gahzFkprZiAt2TF8uS0qQgBizKXpXURqvTJ4WtmupWxaLqjRb2UCTe72mu+Aw==",
       "license": "MIT"
     },
-    "node_modules/@scarf/scarf": {
-      "version": "1.4.0",
-      "resolved": "https://registry.npmjs.org/@scarf/scarf/-/scarf-1.4.0.tgz",
-      "integrity": "sha512-xxeapPiUXdZAE3che6f3xogoJPeZgig6omHEy1rIY5WVsB3H2BHNnZH+gHG6x91SCWyQCzWGsuL2Hh3ClO5/qQ==",
-      "dev": true,
-      "hasInstallScript": true,
-      "license": "Apache-2.0"
-    },
     "node_modules/@sideway/address": {
       "version": "4.1.5",
       "resolved": "https://registry.npmjs.org/@sideway/address/-/address-4.1.5.tgz",
@@ -5251,21 +4967,6 @@
         "url": "https://github.com/sponsors/epoberezkin"
       }
     },
-    "node_modules/ajv-draft-04": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/ajv-draft-04/-/ajv-draft-04-1.0.0.tgz",
-      "integrity": "sha512-mv00Te6nmYbRp5DCwclxtt7yV/joXJPGS7nM+97GdxvuttCOfgI3K4U25zboyeX0O+myI8ERluxQe5wljMmVIw==",
-      "dev": true,
-      "license": "MIT",
-      "peerDependencies": {
-        "ajv": "^8.5.0"
-      },
-      "peerDependenciesMeta": {
-        "ajv": {
-          "optional": true
-        }
-      }
-    },
     "node_modules/ajv-formats": {
       "version": "2.1.1",
       "resolved": "https://registry.npmjs.org/ajv-formats/-/ajv-formats-2.1.1.tgz",
@@ -5848,13 +5549,6 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
-    "node_modules/call-me-maybe": {
-      "version": "1.0.2",
-      "resolved": "https://registry.npmjs.org/call-me-maybe/-/call-me-maybe-1.0.2.tgz",
-      "integrity": "sha512-HpX65o1Hnr9HH25ojC1YGs7HCQLq0GCOibSaWER0eNpgJ/Z1MZv2mTc7+xh6WOPxbRVcmgbv4hGU+uSQ/2xFZQ==",
-      "dev": true,
-      "license": "MIT"
-    },
     "node_modules/callsites": {
       "version": "3.1.0",
       "resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz",
@@ -7498,16 +7192,6 @@
         }
       }
     },
-    "node_modules/decamelize": {
-      "version": "1.2.0",
-      "resolved": "https://registry.npmjs.org/decamelize/-/decamelize-1.2.0.tgz",
-      "integrity": "sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">=0.10.0"
-      }
-    },
     "node_modules/decode-named-character-reference": {
       "version": "1.0.2",
       "resolved": "https://registry.npmjs.org/decode-named-character-reference/-/decode-named-character-reference-1.0.2.tgz",
@@ -8916,16 +8600,6 @@
         "node": ">=6.9.0"
       }
     },
-    "node_modules/get-caller-file": {
-      "version": "2.0.5",
-      "resolved": "https://registry.npmjs.org/get-caller-file/-/get-caller-file-2.0.5.tgz",
-      "integrity": "sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg==",
-      "dev": true,
-      "license": "ISC",
-      "engines": {
-        "node": "6.* || 8.* || >= 10.*"
-      }
-    },
     "node_modules/get-intrinsic": {
       "version": "1.2.7",
       "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.2.7.tgz",
@@ -13436,16 +13110,15 @@
       }
     },
     "node_modules/nanoid": {
-      "version": "3.3.11",
-      "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.11.tgz",
-      "integrity": "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w==",
+      "version": "3.3.7",
+      "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.7.tgz",
+      "integrity": "sha512-eSRppjcPIatRIMC1U6UngP8XFcz8MQWGQdt1MTBQ7NaAmvXDfvNxbvWV3x2y6CdEUciCSsDHDQZbhYaB8QEo2g==",
       "funding": [
         {
           "type": "github",
           "url": "https://github.com/sponsors/ai"
         }
       ],
-      "license": "MIT",
       "bin": {
         "nanoid": "bin/nanoid.cjs"
       },
@@ -13754,14 +13427,6 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
-    "node_modules/openapi-types": {
-      "version": "12.1.3",
-      "resolved": "https://registry.npmjs.org/openapi-types/-/openapi-types-12.1.3.tgz",
-      "integrity": "sha512-N4YtSYJqghVu4iek2ZUvcN/0aqH1kRDuNqzcycDxhOUpg7GdvLa2F3DgS6yBNhInhv2r/6I0Flkn7CqL8+nIcw==",
-      "dev": true,
-      "license": "MIT",
-      "peer": true
-    },
     "node_modules/opener": {
       "version": "1.5.2",
       "resolved": "https://registry.npmjs.org/opener/-/opener-1.5.2.tgz",
@@ -14144,9 +13809,9 @@
       }
     },
     "node_modules/postcss": {
-      "version": "8.4.49",
-      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.4.49.tgz",
-      "integrity": "sha512-OCVPnIObs4N29kxTjzLfUryOkvZEq+pf8jTF0lg8E7uETuWHA+v7j3c/xJmiqpX450191LlmZfUKkXxkTry7nA==",
+      "version": "8.4.38",
+      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.4.38.tgz",
+      "integrity": "sha512-Wglpdk03BSfXkHoQa3b/oulrotAkwrlLDRSOb9D0bN86FdRyE9lppSp33aHNPgBa0JKCoB+drFLZkQoRRYae5A==",
       "funding": [
         {
           "type": "opencollective",
@@ -14161,11 +13826,10 @@
           "url": "https://github.com/sponsors/ai"
         }
       ],
-      "license": "MIT",
       "dependencies": {
         "nanoid": "^3.3.7",
-        "picocolors": "^1.1.1",
-        "source-map-js": "^1.2.1"
+        "picocolors": "^1.0.0",
+        "source-map-js": "^1.2.0"
       },
       "engines": {
         "node": "^10 || ^12 || >=14"
@@ -15703,15 +15367,6 @@
         "node": ">= 0.10"
       }
     },
-    "node_modules/punycode": {
-      "version": "2.3.1",
-      "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz",
-      "integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==",
-      "license": "MIT",
-      "engines": {
-        "node": ">=6"
-      }
-    },
     "node_modules/pupa": {
       "version": "3.1.0",
       "resolved": "https://registry.npmjs.org/pupa/-/pupa-3.1.0.tgz",
@@ -15848,9 +15503,9 @@
       }
     },
     "node_modules/react": {
-      "version": "19.1.0",
-      "resolved": "https://registry.npmjs.org/react/-/react-19.1.0.tgz",
-      "integrity": "sha512-FS+XFBNvn3GTAWq26joslQgWNoFu08F4kl0J4CgdNKADkdSGXQyTCnKteIAJy96Br6YbpEU1LSzV5dYtjMkMDg==",
+      "version": "19.0.0",
+      "resolved": "https://registry.npmjs.org/react/-/react-19.0.0.tgz",
+      "integrity": "sha512-V8AVnmPIICiWpGfm6GLzCR/W5FXLchHop40W4nXBmdlEceh16rCN8O8LNWm5bh5XUX91fh7KpA+W0TgMKmgTpQ==",
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -15983,15 +15638,15 @@
       }
     },
     "node_modules/react-dom": {
-      "version": "19.1.0",
-      "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.1.0.tgz",
-      "integrity": "sha512-Xs1hdnE+DyKgeHJeJznQmYMIBG3TKIHJJT95Q58nHLSrElKlGQqDTR2HQ9fx5CN/Gk6Vh/kupBTDLU11/nDk/g==",
+      "version": "19.0.0",
+      "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.0.0.tgz",
+      "integrity": "sha512-4GV5sHFG0e/0AD4X+ySy6UJd3jVl1iNsNHdpad0qhABJ11twS3TTBnseqsKurKcsNqCEFeGL3uLpVChpIO3QfQ==",
       "license": "MIT",
       "dependencies": {
-        "scheduler": "^0.26.0"
+        "scheduler": "^0.25.0"
       },
       "peerDependencies": {
-        "react": "^19.1.0"
+        "react": "^19.0.0"
       }
     },
     "node_modules/react-error-overlay": {
@@ -16550,16 +16205,6 @@
         "node": ">=0.10"
       }
     },
-    "node_modules/require-directory": {
-      "version": "2.1.1",
-      "resolved": "https://registry.npmjs.org/require-directory/-/require-directory-2.1.1.tgz",
-      "integrity": "sha512-fGxEI7+wsG9xrvdjsrlmL22OMTTiHRwAMroiEeMgq8gzoLC/PQr7RsRDSTLUg/bZAZtF+TVIkHc6/4RIKrui+Q==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">=0.10.0"
-      }
-    },
     "node_modules/require-from-string": {
       "version": "2.0.2",
       "resolved": "https://registry.npmjs.org/require-from-string/-/require-from-string-2.0.2.tgz",
@@ -16577,13 +16222,6 @@
         "node": "*"
       }
     },
-    "node_modules/require-main-filename": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/require-main-filename/-/require-main-filename-2.0.0.tgz",
-      "integrity": "sha512-NKN5kMDylKuldxYLSUfrbo5Tuzh4hd+2E8NPPX02mZtn1VuREQToYe/ZdlJy+J3uCpfaiGF05e7B8W0iXbQHmg==",
-      "dev": true,
-      "license": "ISC"
-    },
     "node_modules/requires-port": {
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/requires-port/-/requires-port-1.0.0.tgz",
@@ -16779,9 +16417,9 @@
       "integrity": "sha512-+aWOz7yVScEGoKNd4PA10LZ8sk0A/z5+nXQG5giUO5rprX9jgYsTdov9qCchZiPIZezbZH+jRut8nPodFAX4Jg=="
     },
     "node_modules/scheduler": {
-      "version": "0.26.0",
-      "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.26.0.tgz",
-      "integrity": "sha512-NlHwttCI/l5gCPR3D1nNXtWABUmBwvZpEQiD4IXSbIDq8BzLIK/7Ir5gTFSGZDUu37K5cMNp0hFtzO38sC7gWA==",
+      "version": "0.25.0",
+      "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.25.0.tgz",
+      "integrity": "sha512-xFVuu11jh+xcO7JOAGJNOXld8/TcEHK/4CituBUeUb5hqxJLj9YuemAEuvm9gQ/+pgXYfbQuqAkiYu+u7YEsNA==",
       "license": "MIT"
     },
     "node_modules/schema-utils": {
@@ -17064,13 +16702,6 @@
         "node": ">= 0.8.0"
       }
     },
-    "node_modules/set-blocking": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/set-blocking/-/set-blocking-2.0.0.tgz",
-      "integrity": "sha512-KiKBS8AnWGEyLzofFfmvKwpdPzqiy16LvQfK3yv/fVH7Bj13/wl3JSR1J+rfgRE9q7xUJK4qvgS8raSOeLUehw==",
-      "dev": true,
-      "license": "ISC"
-    },
     "node_modules/set-function-length": {
       "version": "1.2.2",
       "resolved": "https://registry.npmjs.org/set-function-length/-/set-function-length-1.2.2.tgz",
@@ -17349,10 +16980,9 @@
       }
     },
     "node_modules/source-map-js": {
-      "version": "1.2.1",
-      "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz",
-      "integrity": "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==",
-      "license": "BSD-3-Clause",
+      "version": "1.2.0",
+      "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.0.tgz",
+      "integrity": "sha512-itJW8lvSA0TXEphiRoawsCksnlf8SyvmFzIhltqAHluXd88pkCd+cXJVHTDwdCr0IzwptSm035IHQktUu1QUMg==",
       "engines": {
         "node": ">=0.10.0"
       }
@@ -17717,32 +17347,6 @@
       "resolved": "https://registry.npmjs.org/mdn-data/-/mdn-data-2.0.30.tgz",
       "integrity": "sha512-GaqWWShW4kv/G9IEucWScBx9G1/vsFZZJUO+tD26M8J8z3Kw5RDQjaoZe03YAClgeS/SWPOcb4nkFBTEi5DUEA=="
     },
-    "node_modules/swagger-cli": {
-      "version": "4.0.4",
-      "resolved": "https://registry.npmjs.org/swagger-cli/-/swagger-cli-4.0.4.tgz",
-      "integrity": "sha512-Cp8YYuLny3RJFQ4CvOBTaqmOOgYsem52dPx1xM5S4EUWFblIh2Q8atppMZvXKUr1e9xH5RwipYpmdUzdPcxWcA==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "@apidevtools/swagger-cli": "4.0.4"
-      },
-      "bin": {
-        "swagger-cli": "swagger-cli.js"
-      },
-      "engines": {
-        "node": ">=10"
-      }
-    },
-    "node_modules/swagger-ui-dist": {
-      "version": "5.21.0",
-      "resolved": "https://registry.npmjs.org/swagger-ui-dist/-/swagger-ui-dist-5.21.0.tgz",
-      "integrity": "sha512-E0K3AB6HvQd8yQNSMR7eE5bk+323AUxjtCz/4ZNKiahOlPhPJxqn3UPIGs00cyY/dhrTDJ61L7C/a8u6zhGrZg==",
-      "dev": true,
-      "license": "Apache-2.0",
-      "dependencies": {
-        "@scarf/scarf": "=1.4.0"
-      }
-    },
     "node_modules/tapable": {
       "version": "2.2.1",
       "resolved": "https://registry.npmjs.org/tapable/-/tapable-2.2.1.tgz",
@@ -18034,9 +17638,9 @@
       }
     },
     "node_modules/typescript": {
-      "version": "5.8.3",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.8.3.tgz",
-      "integrity": "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==",
+      "version": "5.8.2",
+      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.8.2.tgz",
+      "integrity": "sha512-aJn6wq13/afZp/jT9QZmwEjDqqvSGp1VT5GVg+f/t6/oVyrgXM6BY1h9BRh/O5p3PlUPAe+WuiEZOmb/49RqoQ==",
       "license": "Apache-2.0",
       "bin": {
         "tsc": "bin/tsc",
@@ -18345,6 +17949,14 @@
         "punycode": "^2.1.0"
       }
     },
+    "node_modules/uri-js/node_modules/punycode": {
+      "version": "2.3.1",
+      "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz",
+      "integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==",
+      "engines": {
+        "node": ">=6"
+      }
+    },
     "node_modules/url-loader": {
       "version": "4.1.1",
       "resolved": "https://registry.npmjs.org/url-loader/-/url-loader-4.1.1.tgz",
@@ -18998,13 +18610,6 @@
         "node": ">= 8"
       }
     },
-    "node_modules/which-module": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/which-module/-/which-module-2.0.1.tgz",
-      "integrity": "sha512-iBdZ57RDvnOR9AGBhML2vFZf7h8vmBjhoaZqODJBFWHVtKkDmKuHai3cx5PgVMrX5YDNp27AofYbAwctSS+vhQ==",
-      "dev": true,
-      "license": "ISC"
-    },
     "node_modules/widest-line": {
       "version": "4.0.1",
       "resolved": "https://registry.npmjs.org/widest-line/-/widest-line-4.0.1.tgz",

docs/package.json

@@ -4,18 +4,16 @@
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",
-    "start": "node generate-swagger-ui.js && docusaurus start",
-    "build": "node generate-swagger-ui.js && docusaurus build",
+    "start": "docusaurus start",
+    "build": "docusaurus build",
     "swizzle": "docusaurus swizzle",
     "deploy": "docusaurus deploy",
     "clear": "docusaurus clear",
     "serve": "docusaurus serve",
     "write-translations": "docusaurus write-translations",
     "write-heading-ids": "docusaurus write-heading-ids",
-    "typecheck": "tsc",
-    "generate-swagger-ui": "node generate-swagger-ui.js"
+    "typecheck": "tsc"
   },
-  "// Note": "The OpenAPI spec is stored in docs/static/openapi.json so it's accessible at /openapi.json in the deployed site",
   "dependencies": {
     "@docusaurus/core": "^3.7.0",
     "@docusaurus/plugin-content-pages": "^3.7.0",
@@ -24,8 +22,8 @@
     "@mdx-js/react": "^3.1.0",
     "clsx": "^2.0.0",
     "prism-react-renderer": "^2.4.1",
-    "react": "^19.1.0",
-    "react-dom": "^19.1.0",
+    "react": "^19.0.0",
+    "react-dom": "^19.0.0",
     "react-icons": "^5.5.0",
     "react-use": "^17.6.0"
   },
@@ -33,9 +31,7 @@
     "@docusaurus/module-type-aliases": "^3.5.1",
     "@docusaurus/tsconfig": "^3.7.0",
     "@docusaurus/types": "^3.5.1",
-    "swagger-cli": "^4.0.4",
-    "swagger-ui-dist": "^5.21.0",
-    "typescript": "~5.8.3"
+    "typescript": "~5.8.2"
   },
   "browserslist": {
     "production": [
@@ -51,6 +47,5 @@
   },
   "engines": {
     "node": ">=18.0"
-  },
-  "packageManager": "yarn@1.22.22+sha512.a6b2f7906b721bba3d67d4aff083df04dad64c399707841b7acf00f6b133b7ac24255f2652fa22ae3534329dc6180534e98d17432037ff6fd140556e2bb3137e"
+  }
 }

docs/sidebars.ts

@@ -18,23 +18,6 @@ const sidebars: SidebarsConfig = {
       label: 'Key Features',
       id: 'usage/key-features',
     },
-    {
-      type: 'category',
-      label: 'OpenHands Cloud',
-      items: [
-        {
-          type: 'doc',
-          label: 'Openhands Cloud',
-          id: 'usage/cloud/openhands-cloud',
-        },
-
-        {
-          type: 'doc',
-          label: 'Cloud GitHub Resolver',
-          id: 'usage/cloud/cloud-github-resolver',
-        },
-      ],
-    },
     {
       type: 'category',
       label: 'Prompting',
@@ -44,17 +27,6 @@ const sidebars: SidebarsConfig = {
           label: 'Best Practices',
           id: 'usage/prompting/prompting-best-practices',
         },
-      ],
-    },
-    {
-      type: 'category',
-      label: 'Customization',
-      items: [
-        {
-          type: 'doc',
-          label: 'Repository Customization',
-          id: 'usage/customization/repository',
-        },
         {
           type: 'category',
           label: 'Microagents',
@@ -83,6 +55,17 @@ const sidebars: SidebarsConfig = {
         },
       ],
     },
+    {
+      type: 'category',
+      label: 'Customization',
+      items: [
+        {
+          type: 'doc',
+          label: 'Repository Customization',
+          id: 'usage/customization/repository',
+        },
+      ],
+    },
     {
       type: 'category',
       label: 'Usage Methods',
@@ -107,6 +90,23 @@ const sidebars: SidebarsConfig = {
           label: 'Github Action',
           id: 'usage/how-to/github-action',
         },
+        {
+          type: 'category',
+          label: 'Cloud',
+          items: [
+            {
+              type: 'doc',
+              label: 'Openhands Cloud',
+              id: 'usage/cloud/openhands-cloud',
+            },
+
+            {
+              type: 'doc',
+              label: 'Cloud GitHub Resolver',
+              id: 'usage/cloud/cloud-github-resolver',
+            },
+          ],
+        },
       ],
     },
     {
@@ -141,11 +141,6 @@ const sidebars: SidebarsConfig = {
                   label: 'Groq',
                   id: 'usage/llms/groq',
                 },
-                {
-                  type: 'doc',
-                  label: 'Local LLMs with SGLang or vLLM',
-                  id: 'usage/llms/local-llms',
-                },
                 {
                   type: 'doc',
                   label: 'LiteLLM Proxy',
@@ -268,4 +263,4 @@ const sidebars: SidebarsConfig = {
   ],
 };
 
-export default sidebars;
+export default sidebars;

docs/static/README.md

@@ -1,15 +0,0 @@
-# Static Files for OpenHands Documentation
-
-This directory contains static files that are copied directly to the build output of the Docusaurus documentation.
-
-## OpenAPI Specification
-
-The `openapi.json` file in this directory is the OpenAPI specification for the OpenHands API. It is copied to the build output and is accessible at `/openapi.json` in the deployed site.
-
-This file is used by the Swagger UI interface, which is accessible at `/swagger-ui/` in the deployed site.
-
-## Why is the OpenAPI spec in the static directory?
-
-The OpenAPI specification is placed in the static directory so that it's accessible at a predictable URL in the deployed site. This allows the Swagger UI to reference it directly.
-
-We only need one copy of the OpenAPI spec file, which is this one in the static directory.

docs/yarn.lock

@@ -158,48 +158,6 @@
     "@jridgewell/gen-mapping" "^0.3.5"
     "@jridgewell/trace-mapping" "^0.3.24"
 
-"@apidevtools/json-schema-ref-parser@11.7.2":
-  version "11.7.2"
-  resolved "https://registry.npmjs.org/@apidevtools/json-schema-ref-parser/-/json-schema-ref-parser-11.7.2.tgz"
-  integrity sha512-4gY54eEGEstClvEkGnwVkTkrx0sqwemEFG5OSRRn3tD91XH0+Q8XIkYIfo7IwEWPpJZwILb9GUXeShtplRc/eA==
-  dependencies:
-    "@jsdevtools/ono" "^7.1.3"
-    "@types/json-schema" "^7.0.15"
-    js-yaml "^4.1.0"
-
-"@apidevtools/openapi-schemas@^2.1.0":
-  version "2.1.0"
-  resolved "https://registry.npmjs.org/@apidevtools/openapi-schemas/-/openapi-schemas-2.1.0.tgz"
-  integrity sha512-Zc1AlqrJlX3SlpupFGpiLi2EbteyP7fXmUOGup6/DnkRgjP9bgMM/ag+n91rsv0U1Gpz0H3VILA/o3bW7Ua6BQ==
-
-"@apidevtools/swagger-cli@4.0.4":
-  version "4.0.4"
-  resolved "https://registry.npmjs.org/@apidevtools/swagger-cli/-/swagger-cli-4.0.4.tgz"
-  integrity sha512-hdDT3B6GLVovCsRZYDi3+wMcB1HfetTU20l2DC8zD3iFRNMC6QNAZG5fo/6PYeHWBEv7ri4MvnlKodhNB0nt7g==
-  dependencies:
-    "@apidevtools/swagger-parser" "^10.0.1"
-    chalk "^4.1.0"
-    js-yaml "^3.14.0"
-    yargs "^15.4.1"
-
-"@apidevtools/swagger-methods@^3.0.2":
-  version "3.0.2"
-  resolved "https://registry.npmjs.org/@apidevtools/swagger-methods/-/swagger-methods-3.0.2.tgz"
-  integrity sha512-QAkD5kK2b1WfjDS/UQn/qQkbwF31uqRjPTrsCs5ZG9BQGAkjwvqGFjjPqAuzac/IYzpPtRzjCP1WrTuAIjMrXg==
-
-"@apidevtools/swagger-parser@^10.0.1":
-  version "10.1.1"
-  resolved "https://registry.npmjs.org/@apidevtools/swagger-parser/-/swagger-parser-10.1.1.tgz"
-  integrity sha512-u/kozRnsPO/x8QtKYJOqoGtC4kH6yg1lfYkB9Au0WhYB0FNLpyFusttQtvhlwjtG3rOwiRz4D8DnnXa8iEpIKA==
-  dependencies:
-    "@apidevtools/json-schema-ref-parser" "11.7.2"
-    "@apidevtools/openapi-schemas" "^2.1.0"
-    "@apidevtools/swagger-methods" "^3.0.2"
-    "@jsdevtools/ono" "^7.1.3"
-    ajv "^8.17.1"
-    ajv-draft-04 "^1.0.0"
-    call-me-maybe "^1.0.2"
-
 "@babel/code-frame@^7.0.0", "@babel/code-frame@^7.16.0", "@babel/code-frame@^7.25.9", "@babel/code-frame@^7.26.0", "@babel/code-frame@^7.8.3":
   version "7.26.2"
   resolved "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz"
@@ -2004,11 +1962,6 @@
     "@jridgewell/resolve-uri" "^3.1.0"
     "@jridgewell/sourcemap-codec" "^1.4.14"
 
-"@jsdevtools/ono@^7.1.3":
-  version "7.1.3"
-  resolved "https://registry.npmjs.org/@jsdevtools/ono/-/ono-7.1.3.tgz"
-  integrity sha512-4JQNk+3mVzK3xh2rqd6RB4J46qUR19azEHBneZyTZM+c456qOrbbM/5xcR8huNCCcbVt7+UmizG6GuUvPvKUYg==
-
 "@leichtgewicht/ip-codec@^2.0.1":
   version "2.0.5"
   resolved "https://registry.npmjs.org/@leichtgewicht/ip-codec/-/ip-codec-2.0.5.tgz"
@@ -2097,11 +2050,6 @@
   resolved "https://registry.npmjs.org/@polka/url/-/url-1.0.0-next.28.tgz"
   integrity sha512-8LduaNlMZGwdZ6qWrKlfa+2M4gahzFkprZiAt2TF8uS0qQgBizKXpXURqvTJ4WtmupWxaLqjRb2UCTe72mu+Aw==
 
-"@scarf/scarf@=1.4.0":
-  version "1.4.0"
-  resolved "https://registry.npmjs.org/@scarf/scarf/-/scarf-1.4.0.tgz"
-  integrity sha512-xxeapPiUXdZAE3che6f3xogoJPeZgig6omHEy1rIY5WVsB3H2BHNnZH+gHG6x91SCWyQCzWGsuL2Hh3ClO5/qQ==
-
 "@sideway/address@^4.1.5":
   version "4.1.5"
   resolved "https://registry.npmjs.org/@sideway/address/-/address-4.1.5.tgz"
@@ -2443,7 +2391,7 @@
   resolved "https://registry.npmjs.org/@types/js-cookie/-/js-cookie-2.2.7.tgz"
   integrity sha512-aLkWa0C0vO5b4Sr798E26QgOkss68Un0bLjs7u9qxzPT5CG+8DuNTffWES58YzJs3hrVAOs1wonycqEBqNJubA==
 
-"@types/json-schema@*", "@types/json-schema@^7.0.15", "@types/json-schema@^7.0.4", "@types/json-schema@^7.0.5", "@types/json-schema@^7.0.8", "@types/json-schema@^7.0.9":
+"@types/json-schema@*", "@types/json-schema@^7.0.4", "@types/json-schema@^7.0.5", "@types/json-schema@^7.0.8", "@types/json-schema@^7.0.9":
   version "7.0.15"
   resolved "https://registry.npmjs.org/@types/json-schema/-/json-schema-7.0.15.tgz"
   integrity sha512-5+fP8P8MFNC+AyZCDxrB2pkZFPGzqQWUzpSeuuVLvm8VMcorNYavBqoFcxK8bQz4Qsbn4oUEEem4wDLfcysGHA==
@@ -2806,11 +2754,6 @@ aggregate-error@^3.0.0:
     clean-stack "^2.0.0"
     indent-string "^4.0.0"
 
-ajv-draft-04@^1.0.0:
-  version "1.0.0"
-  resolved "https://registry.npmjs.org/ajv-draft-04/-/ajv-draft-04-1.0.0.tgz"
-  integrity sha512-mv00Te6nmYbRp5DCwclxtt7yV/joXJPGS7nM+97GdxvuttCOfgI3K4U25zboyeX0O+myI8ERluxQe5wljMmVIw==
-
 ajv-formats@^2.1.1:
   version "2.1.1"
   resolved "https://registry.npmjs.org/ajv-formats/-/ajv-formats-2.1.1.tgz"
@@ -2845,7 +2788,7 @@ ajv@^6.12.2, ajv@^6.12.5, ajv@^6.9.1:
     json-schema-traverse "^0.4.1"
     uri-js "^4.2.2"
 
-ajv@^8.0.0, ajv@^8.17.1, ajv@^8.5.0, ajv@^8.8.2, ajv@^8.9.0:
+ajv@^8.0.0, ajv@^8.8.2, ajv@^8.9.0:
   version "8.17.1"
   resolved "https://registry.npmjs.org/ajv/-/ajv-8.17.1.tgz"
   integrity sha512-B/gBuNg5SiMTrPkC+A2+cW0RszwxYmn6VYxB/inlBStS5nx6xHIt/ehKRhIMhqusl7a8LjQoZnjCs5vhwxOQ1g==
@@ -3186,11 +3129,6 @@ call-bound@^1.0.2, call-bound@^1.0.3:
     call-bind-apply-helpers "^1.0.1"
     get-intrinsic "^1.2.6"
 
-call-me-maybe@^1.0.2:
-  version "1.0.2"
-  resolved "https://registry.npmjs.org/call-me-maybe/-/call-me-maybe-1.0.2.tgz"
-  integrity sha512-HpX65o1Hnr9HH25ojC1YGs7HCQLq0GCOibSaWER0eNpgJ/Z1MZv2mTc7+xh6WOPxbRVcmgbv4hGU+uSQ/2xFZQ==
-
 callsites@^3.0.0:
   version "3.1.0"
   resolved "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz"
@@ -3204,11 +3142,6 @@ camel-case@^4.1.2:
     pascal-case "^3.1.2"
     tslib "^2.0.3"
 
-camelcase@^5.0.0:
-  version "5.3.1"
-  resolved "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz"
-  integrity sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg==
-
 camelcase@^6.2.0:
   version "6.3.0"
   resolved "https://registry.npmjs.org/camelcase/-/camelcase-6.3.0.tgz"
@@ -3353,15 +3286,6 @@ cli-table3@^0.6.3:
   optionalDependencies:
     "@colors/colors" "1.5.0"
 
-cliui@^6.0.0:
-  version "6.0.0"
-  resolved "https://registry.npmjs.org/cliui/-/cliui-6.0.0.tgz"
-  integrity sha512-t6wbgtoCXvAzst7QgXxJYqPt0usEfbgQdftEPbLL/cvv6HPE5VgvqCuAIDR0NgU52ds6rFwqrgakNLrHEjCbrQ==
-  dependencies:
-    string-width "^4.2.0"
-    strip-ansi "^6.0.0"
-    wrap-ansi "^6.2.0"
-
 clone-deep@^4.0.1:
   version "4.0.1"
   resolved "https://registry.npmjs.org/clone-deep/-/clone-deep-4.0.1.tgz"
@@ -4140,11 +4064,6 @@ debug@2.6.9:
   dependencies:
     ms "2.0.0"
 
-decamelize@^1.2.0:
-  version "1.2.0"
-  resolved "https://registry.npmjs.org/decamelize/-/decamelize-1.2.0.tgz"
-  integrity sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA==
-
 decode-named-character-reference@^1.0.0:
   version "1.0.2"
   resolved "https://registry.npmjs.org/decode-named-character-reference/-/decode-named-character-reference-1.0.2.tgz"
@@ -4826,14 +4745,6 @@ find-up@^3.0.0:
   dependencies:
     locate-path "^3.0.0"
 
-find-up@^4.1.0:
-  version "4.1.0"
-  resolved "https://registry.npmjs.org/find-up/-/find-up-4.1.0.tgz"
-  integrity sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw==
-  dependencies:
-    locate-path "^5.0.0"
-    path-exists "^4.0.0"
-
 find-up@^5.0.0:
   version "5.0.0"
   resolved "https://registry.npmjs.org/find-up/-/find-up-5.0.0.tgz"
@@ -4943,11 +4854,6 @@ gensync@^1.0.0-beta.2:
   resolved "https://registry.npmjs.org/gensync/-/gensync-1.0.0-beta.2.tgz"
   integrity sha512-3hN7NaskYvMDLQY55gnW3NQ+mesEAepTqlg+VEbj7zzqEMBVNhzcGYYeqFo/TlYz6eQiFcp1HcsCZO+nGgS8zg==
 
-get-caller-file@^2.0.1:
-  version "2.0.5"
-  resolved "https://registry.npmjs.org/get-caller-file/-/get-caller-file-2.0.5.tgz"
-  integrity sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg==
-
 get-intrinsic@^1.2.4, get-intrinsic@^1.2.5, get-intrinsic@^1.2.6:
   version "1.2.7"
   resolved "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.2.7.tgz"
@@ -5847,14 +5753,6 @@ js-yaml@^3.13.1:
     argparse "^1.0.7"
     esprima "^4.0.0"
 
-js-yaml@^3.14.0:
-  version "3.14.1"
-  resolved "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.1.tgz"
-  integrity sha512-okMH7OXXJ7YrN9Ok3/SXrnu4iX9yOk+25nqX4imS2npuvTYDmo/QEZoqwZkYaIDk3jVvBOTOIEgEhaLOynBS9g==
-  dependencies:
-    argparse "^1.0.7"
-    esprima "^4.0.0"
-
 js-yaml@^4.1.0:
   version "4.1.0"
   resolved "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.0.tgz"
@@ -5997,13 +5895,6 @@ locate-path@^3.0.0:
     p-locate "^3.0.0"
     path-exists "^3.0.0"
 
-locate-path@^5.0.0:
-  version "5.0.0"
-  resolved "https://registry.npmjs.org/locate-path/-/locate-path-5.0.0.tgz"
-  integrity sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g==
-  dependencies:
-    p-locate "^4.1.0"
-
 locate-path@^6.0.0:
   version "6.0.0"
   resolved "https://registry.npmjs.org/locate-path/-/locate-path-6.0.0.tgz"
@@ -7146,9 +7037,9 @@ nano-css@^5.6.2:
     stylis "^4.3.0"
 
 nanoid@^3.3.7:
-  version "3.3.11"
-  resolved "https://registry.npmjs.org/nanoid/-/nanoid-3.3.11.tgz"
-  integrity sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w==
+  version "3.3.7"
+  resolved "https://registry.npmjs.org/nanoid/-/nanoid-3.3.7.tgz"
+  integrity sha512-eSRppjcPIatRIMC1U6UngP8XFcz8MQWGQdt1MTBQ7NaAmvXDfvNxbvWV3x2y6CdEUciCSsDHDQZbhYaB8QEo2g==
 
 negotiator@~0.6.4:
   version "0.6.4"
@@ -7307,11 +7198,6 @@ open@^8.0.9, open@^8.4.0:
     is-docker "^2.1.1"
     is-wsl "^2.2.0"
 
-openapi-types@>=7:
-  version "12.1.3"
-  resolved "https://registry.npmjs.org/openapi-types/-/openapi-types-12.1.3.tgz"
-  integrity sha512-N4YtSYJqghVu4iek2ZUvcN/0aqH1kRDuNqzcycDxhOUpg7GdvLa2F3DgS6yBNhInhv2r/6I0Flkn7CqL8+nIcw==
-
 opener@^1.5.2:
   version "1.5.2"
   resolved "https://registry.npmjs.org/opener/-/opener-1.5.2.tgz"
@@ -7329,13 +7215,6 @@ p-limit@^2.0.0:
   dependencies:
     p-try "^2.0.0"
 
-p-limit@^2.2.0:
-  version "2.3.0"
-  resolved "https://registry.npmjs.org/p-limit/-/p-limit-2.3.0.tgz"
-  integrity sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w==
-  dependencies:
-    p-try "^2.0.0"
-
 p-limit@^3.0.2:
   version "3.1.0"
   resolved "https://registry.npmjs.org/p-limit/-/p-limit-3.1.0.tgz"
@@ -7357,13 +7236,6 @@ p-locate@^3.0.0:
   dependencies:
     p-limit "^2.0.0"
 
-p-locate@^4.1.0:
-  version "4.1.0"
-  resolved "https://registry.npmjs.org/p-locate/-/p-locate-4.1.0.tgz"
-  integrity sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A==
-  dependencies:
-    p-limit "^2.2.0"
-
 p-locate@^5.0.0:
   version "5.0.0"
   resolved "https://registry.npmjs.org/p-locate/-/p-locate-5.0.0.tgz"
@@ -7546,7 +7418,7 @@ periscopic@^3.0.0:
     estree-walker "^3.0.0"
     is-reference "^3.0.0"
 
-picocolors@^1.0.0, picocolors@^1.0.1, picocolors@^1.1.0, picocolors@^1.1.1:
+picocolors@^1.0.0, picocolors@^1.0.1, picocolors@^1.1.0:
   version "1.1.1"
   resolved "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz"
   integrity sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==
@@ -8118,13 +7990,13 @@ postcss-zindex@^6.0.2:
   integrity sha512-5BxW9l1evPB/4ZIc+2GobEBoKC+h8gPGCMi+jxsYvd2x0mjq7wazk6DrP71pStqxE9Foxh5TVnonbWpFZzXaYg==
 
 "postcss@^7.0.0 || ^8.0.1", postcss@^8, postcss@^8.0.3, postcss@^8.0.9, postcss@^8.1.0, postcss@^8.2.2, postcss@^8.4, postcss@^8.4.21, postcss@^8.4.23, postcss@^8.4.24, postcss@^8.4.26, postcss@^8.4.31, postcss@^8.4.33, postcss@^8.4.38, postcss@^8.4.6:
-  version "8.4.49"
-  resolved "https://registry.npmjs.org/postcss/-/postcss-8.4.49.tgz"
-  integrity sha512-OCVPnIObs4N29kxTjzLfUryOkvZEq+pf8jTF0lg8E7uETuWHA+v7j3c/xJmiqpX450191LlmZfUKkXxkTry7nA==
+  version "8.4.38"
+  resolved "https://registry.npmjs.org/postcss/-/postcss-8.4.38.tgz"
+  integrity sha512-Wglpdk03BSfXkHoQa3b/oulrotAkwrlLDRSOb9D0bN86FdRyE9lppSp33aHNPgBa0JKCoB+drFLZkQoRRYae5A==
   dependencies:
     nanoid "^3.3.7"
-    picocolors "^1.1.1"
-    source-map-js "^1.2.1"
+    picocolors "^1.0.0"
+    source-map-js "^1.2.0"
 
 pretty-error@^4.0.0:
   version "4.0.0"
@@ -8300,12 +8172,12 @@ react-dev-utils@^12.0.1:
     strip-ansi "^6.0.1"
     text-table "^0.2.0"
 
-react-dom@*, "react-dom@^16.6.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "react-dom@^18.0.0 || ^19.0.0", react-dom@^19.1.0, "react-dom@>= 16.8.0 < 19.0.0":
-  version "19.1.0"
-  resolved "https://registry.npmjs.org/react-dom/-/react-dom-19.1.0.tgz"
-  integrity sha512-Xs1hdnE+DyKgeHJeJznQmYMIBG3TKIHJJT95Q58nHLSrElKlGQqDTR2HQ9fx5CN/Gk6Vh/kupBTDLU11/nDk/g==
+react-dom@*, "react-dom@^16.6.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "react-dom@^18.0.0 || ^19.0.0", react-dom@^19.0.0, "react-dom@>= 16.8.0 < 19.0.0":
+  version "19.0.0"
+  resolved "https://registry.npmjs.org/react-dom/-/react-dom-19.0.0.tgz"
+  integrity sha512-4GV5sHFG0e/0AD4X+ySy6UJd3jVl1iNsNHdpad0qhABJ11twS3TTBnseqsKurKcsNqCEFeGL3uLpVChpIO3QfQ==
   dependencies:
-    scheduler "^0.26.0"
+    scheduler "^0.25.0"
 
 react-error-overlay@^6.0.11:
   version "6.0.11"
@@ -8417,10 +8289,10 @@ react-use@^17.6.0:
     ts-easing "^0.2.0"
     tslib "^2.1.0"
 
-react@*, "react@^16.13.1 || ^17.0.0 || ^18.0.0", "react@^16.6.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "react@^18.0.0 || ^19.0.0", react@^19.1.0, "react@>= 16.8.0 < 19.0.0", react@>=15, react@>=16, react@>=16.0.0:
-  version "19.1.0"
-  resolved "https://registry.npmjs.org/react/-/react-19.1.0.tgz"
-  integrity sha512-FS+XFBNvn3GTAWq26joslQgWNoFu08F4kl0J4CgdNKADkdSGXQyTCnKteIAJy96Br6YbpEU1LSzV5dYtjMkMDg==
+react@*, "react@^16.13.1 || ^17.0.0 || ^18.0.0", "react@^16.6.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "react@^18.0.0 || ^19.0.0", react@^19.0.0, "react@>= 16.8.0 < 19.0.0", react@>=15, react@>=16, react@>=16.0.0:
+  version "19.0.0"
+  resolved "https://registry.npmjs.org/react/-/react-19.0.0.tgz"
+  integrity sha512-V8AVnmPIICiWpGfm6GLzCR/W5FXLchHop40W4nXBmdlEceh16rCN8O8LNWm5bh5XUX91fh7KpA+W0TgMKmgTpQ==
 
 readable-stream@^2.0.1:
   version "2.3.8"
@@ -8643,11 +8515,6 @@ repeat-string@^1.0.0:
   resolved "https://registry.npmjs.org/repeat-string/-/repeat-string-1.6.1.tgz"
   integrity sha512-PV0dzCYDNfRi1jCDbJzpW7jNNDRuCOG/jI5ctQcGKt/clZD+YcPS3yIlWuTJMmESC8aevCFmWJy5wjAFgNqN6w==
 
-require-directory@^2.1.1:
-  version "2.1.1"
-  resolved "https://registry.npmjs.org/require-directory/-/require-directory-2.1.1.tgz"
-  integrity sha512-fGxEI7+wsG9xrvdjsrlmL22OMTTiHRwAMroiEeMgq8gzoLC/PQr7RsRDSTLUg/bZAZtF+TVIkHc6/4RIKrui+Q==
-
 require-from-string@^2.0.2:
   version "2.0.2"
   resolved "https://registry.npmjs.org/require-from-string/-/require-from-string-2.0.2.tgz"
@@ -8658,11 +8525,6 @@ require-from-string@^2.0.2:
   resolved "https://registry.npmjs.org/require-like/-/require-like-0.1.2.tgz"
   integrity sha512-oyrU88skkMtDdauHDuKVrgR+zuItqr6/c//FXzvmxRGMexSDc6hNvJInGW3LL46n+8b50RykrvwSUIIQH2LQ5A==
 
-require-main-filename@^2.0.0:
-  version "2.0.0"
-  resolved "https://registry.npmjs.org/require-main-filename/-/require-main-filename-2.0.0.tgz"
-  integrity sha512-NKN5kMDylKuldxYLSUfrbo5Tuzh4hd+2E8NPPX02mZtn1VuREQToYe/ZdlJy+J3uCpfaiGF05e7B8W0iXbQHmg==
-
 requires-port@^1.0.0:
   version "1.0.0"
   resolved "https://registry.npmjs.org/requires-port/-/requires-port-1.0.0.tgz"
@@ -8782,10 +8644,10 @@ sax@^1.2.4:
   resolved "https://registry.npmjs.org/sax/-/sax-1.4.1.tgz"
   integrity sha512-+aWOz7yVScEGoKNd4PA10LZ8sk0A/z5+nXQG5giUO5rprX9jgYsTdov9qCchZiPIZezbZH+jRut8nPodFAX4Jg==
 
-scheduler@^0.26.0:
-  version "0.26.0"
-  resolved "https://registry.npmjs.org/scheduler/-/scheduler-0.26.0.tgz"
-  integrity sha512-NlHwttCI/l5gCPR3D1nNXtWABUmBwvZpEQiD4IXSbIDq8BzLIK/7Ir5gTFSGZDUu37K5cMNp0hFtzO38sC7gWA==
+scheduler@^0.25.0:
+  version "0.25.0"
+  resolved "https://registry.npmjs.org/scheduler/-/scheduler-0.25.0.tgz"
+  integrity sha512-xFVuu11jh+xcO7JOAGJNOXld8/TcEHK/4CituBUeUb5hqxJLj9YuemAEuvm9gQ/+pgXYfbQuqAkiYu+u7YEsNA==
 
 schema-utils@^3.0.0:
   version "3.3.0"
@@ -8943,11 +8805,6 @@ serve-static@1.16.2:
     parseurl "~1.3.3"
     send "0.19.0"
 
-set-blocking@^2.0.0:
-  version "2.0.0"
-  resolved "https://registry.npmjs.org/set-blocking/-/set-blocking-2.0.0.tgz"
-  integrity sha512-KiKBS8AnWGEyLzofFfmvKwpdPzqiy16LvQfK3yv/fVH7Bj13/wl3JSR1J+rfgRE9q7xUJK4qvgS8raSOeLUehw==
-
 set-function-length@^1.2.2:
   version "1.2.2"
   resolved "https://registry.npmjs.org/set-function-length/-/set-function-length-1.2.2.tgz"
@@ -9121,10 +8978,10 @@ sort-css-media-queries@2.2.0:
   resolved "https://registry.npmjs.org/sort-css-media-queries/-/sort-css-media-queries-2.2.0.tgz"
   integrity sha512-0xtkGhWCC9MGt/EzgnvbbbKhqWjl1+/rncmhTh5qCpbYguXh6S/qwePfv/JQ8jePXXmqingylxoC49pCkSPIbA==
 
-source-map-js@^1.0.1, source-map-js@^1.2.1:
-  version "1.2.1"
-  resolved "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz"
-  integrity sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==
+source-map-js@^1.0.1, source-map-js@^1.2.0:
+  version "1.2.0"
+  resolved "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.0.tgz"
+  integrity sha512-itJW8lvSA0TXEphiRoawsCksnlf8SyvmFzIhltqAHluXd88pkCd+cXJVHTDwdCr0IzwptSm035IHQktUu1QUMg==
 
 source-map-support@~0.5.20:
   version "0.5.21"
@@ -9255,7 +9112,16 @@ string_decoder@~1.1.1:
   dependencies:
     safe-buffer "~5.1.0"
 
-string-width@^4.1.0, string-width@^4.2.0:
+string-width@^4.1.0:
+  version "4.2.3"
+  resolved "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz"
+  integrity sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==
+  dependencies:
+    emoji-regex "^8.0.0"
+    is-fullwidth-code-point "^3.0.0"
+    strip-ansi "^6.0.1"
+
+string-width@^4.2.0:
   version "4.2.3"
   resolved "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz"
   integrity sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==
@@ -9388,20 +9254,6 @@ svgo@^3.0.2, svgo@^3.2.0:
     csso "^5.0.5"
     picocolors "^1.0.0"
 
-swagger-cli@^4.0.4:
-  version "4.0.4"
-  resolved "https://registry.npmjs.org/swagger-cli/-/swagger-cli-4.0.4.tgz"
-  integrity sha512-Cp8YYuLny3RJFQ4CvOBTaqmOOgYsem52dPx1xM5S4EUWFblIh2Q8atppMZvXKUr1e9xH5RwipYpmdUzdPcxWcA==
-  dependencies:
-    "@apidevtools/swagger-cli" "4.0.4"
-
-swagger-ui-dist@^5.21.0:
-  version "5.21.0"
-  resolved "https://registry.npmjs.org/swagger-ui-dist/-/swagger-ui-dist-5.21.0.tgz"
-  integrity sha512-E0K3AB6HvQd8yQNSMR7eE5bk+323AUxjtCz/4ZNKiahOlPhPJxqn3UPIGs00cyY/dhrTDJ61L7C/a8u6zhGrZg==
-  dependencies:
-    "@scarf/scarf" "=1.4.0"
-
 tapable@^1.0.0:
   version "1.1.3"
   resolved "https://registry.npmjs.org/tapable/-/tapable-1.1.3.tgz"
@@ -9535,10 +9387,10 @@ typedarray-to-buffer@^3.1.5:
   dependencies:
     is-typedarray "^1.0.0"
 
-"typescript@>= 2.7", typescript@>=4.9.5, typescript@~5.8.3:
-  version "5.8.3"
-  resolved "https://registry.npmjs.org/typescript/-/typescript-5.8.3.tgz"
-  integrity sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==
+"typescript@>= 2.7", typescript@>=4.9.5, typescript@~5.8.2:
+  version "5.8.2"
+  resolved "https://registry.npmjs.org/typescript/-/typescript-5.8.2.tgz"
+  integrity sha512-aJn6wq13/afZp/jT9QZmwEjDqqvSGp1VT5GVg+f/t6/oVyrgXM6BY1h9BRh/O5p3PlUPAe+WuiEZOmb/49RqoQ==
 
 undici-types@~5.26.4:
   version "5.26.5"
@@ -9952,11 +9804,6 @@ websocket-extensions@>=0.1.1:
   resolved "https://registry.npmjs.org/websocket-extensions/-/websocket-extensions-0.1.4.tgz"
   integrity sha512-OqedPIGOfsDlo31UNwYbCFMSaO9m9G/0faIHj5/dZFDMFqPTcx6UwqyOy3COEaEOg/9VsGIpdqn62W5KhoKSpg==
 
-which-module@^2.0.0:
-  version "2.0.1"
-  resolved "https://registry.npmjs.org/which-module/-/which-module-2.0.1.tgz"
-  integrity sha512-iBdZ57RDvnOR9AGBhML2vFZf7h8vmBjhoaZqODJBFWHVtKkDmKuHai3cx5PgVMrX5YDNp27AofYbAwctSS+vhQ==
-
 which@^1.3.1:
   version "1.3.1"
   resolved "https://registry.npmjs.org/which/-/which-1.3.1.tgz"
@@ -9983,15 +9830,6 @@ wildcard@^2.0.0, wildcard@^2.0.1:
   resolved "https://registry.npmjs.org/wildcard/-/wildcard-2.0.1.tgz"
   integrity sha512-CC1bOL87PIWSBhDcTrdeLo6eGT7mCFtrg0uIJtqJUFyK+eJnzl8A1niH56uu7KMa5XFrtiV+AQuHO3n7DsHnLQ==
 
-wrap-ansi@^6.2.0:
-  version "6.2.0"
-  resolved "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-6.2.0.tgz"
-  integrity sha512-r6lPcBGxZXlIcymEu7InxDMhdW0KDxpLgoFLcguasxCaJ/SOIZwINatK9KY/tf+ZrlywOKU0UDj3ATXUBfxJXA==
-  dependencies:
-    ansi-styles "^4.0.0"
-    string-width "^4.1.0"
-    strip-ansi "^6.0.0"
-
 wrap-ansi@^7.0.0:
   version "7.0.0"
   resolved "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-7.0.0.tgz"
@@ -10047,11 +9885,6 @@ xml-js@^1.6.11:
   dependencies:
     sax "^1.2.4"
 
-y18n@^4.0.0:
-  version "4.0.3"
-  resolved "https://registry.npmjs.org/y18n/-/y18n-4.0.3.tgz"
-  integrity sha512-JKhqTOwSrqNA1NY5lSztJ1GrBiUodLMmIZuLiDaMRJ+itFd+ABVE8XBjOvIWL+rSqNDC74LCSFmlb/U4UZ4hJQ==
-
 yallist@^3.0.2:
   version "3.1.1"
   resolved "https://registry.npmjs.org/yallist/-/yallist-3.1.1.tgz"
@@ -10062,31 +9895,6 @@ yaml@^1.7.2:
   resolved "https://registry.npmjs.org/yaml/-/yaml-1.10.2.tgz"
   integrity sha512-r3vXyErRCYJ7wg28yvBY5VSoAF8ZvlcW9/BwUzEtUsjvX/DKs24dIkuwjtuprwJJHsbyUbLApepYTR1BN4uHrg==
 
-yargs-parser@^18.1.2:
-  version "18.1.3"
-  resolved "https://registry.npmjs.org/yargs-parser/-/yargs-parser-18.1.3.tgz"
-  integrity sha512-o50j0JeToy/4K6OZcaQmW6lyXXKhq7csREXcDwk2omFPJEwUNOVtJKvmDr9EI1fAJZUyZcRF7kxGBWmRXudrCQ==
-  dependencies:
-    camelcase "^5.0.0"
-    decamelize "^1.2.0"
-
-yargs@^15.4.1:
-  version "15.4.1"
-  resolved "https://registry.npmjs.org/yargs/-/yargs-15.4.1.tgz"
-  integrity sha512-aePbxDmcYW++PaqBsJ+HYUFwCdv4LVvdnhBy78E57PIor8/OVvhMrADFFEDh8DHDFRv/O9i3lPhsENjO7QX0+A==
-  dependencies:
-    cliui "^6.0.0"
-    decamelize "^1.2.0"
-    find-up "^4.1.0"
-    get-caller-file "^2.0.1"
-    require-directory "^2.1.1"
-    require-main-filename "^2.0.0"
-    set-blocking "^2.0.0"
-    string-width "^4.2.0"
-    which-module "^2.0.0"
-    y18n "^4.0.0"
-    yargs-parser "^18.1.2"
-
 yocto-queue@^0.1.0:
   version "0.1.0"
   resolved "https://registry.npmjs.org/yocto-queue/-/yocto-queue-0.1.0.tgz"

evaluation/benchmarks/commit0/run_infer.py

@@ -131,9 +131,9 @@ def get_config(
         )
     )
     agent_config = AgentConfig(
-        enable_jupyter=False,
-        enable_browsing=RUN_WITH_BROWSING,
-        enable_llm_editor=False,
+        codeact_enable_jupyter=False,
+        codeact_enable_browsing=RUN_WITH_BROWSING,
+        codeact_enable_llm_editor=False,
     )
     config.set_agent_config(agent_config)
     return config

evaluation/benchmarks/discoverybench/run_infer.py

@@ -79,8 +79,8 @@ def get_config(
     agent_config.enable_prompt_extensions = False
     agent_config = AgentConfig(
         function_calling=False,
-        enable_jupyter=True,
-        enable_browsing=True,
+        codeact_enable_jupyter=True,
+        codeact_enable_browsing_delegate=True,
     )
     config.set_agent_config(agent_config)
     return config

evaluation/benchmarks/lca_ci_build_repair/.gitignore

@@ -1 +0,0 @@
-config.yaml

evaluation/benchmarks/lca_ci_build_repair/README.MD

@@ -1,35 +0,0 @@
-# CI Builds Repair Benchmark Integration
-
-This module integrates the CI Builds Repair benchmark developed by [JetBrains-Research](https://github.com/JetBrains-Research/lca-baselines/tree/main/ci-builds-repair/ci-builds-repair-benchmark).
-
-For more information, refer to the [GitHub repository](https://github.com/JetBrains-Research/lca-baselines/tree/main/ci-builds-repair/ci-builds-repair-benchmark) and the associated [research paper](https://arxiv.org/abs/2406.11612).
-See notice below for details
-
-## Setup
-
-Before running any scripts, make sure to configure the benchmark by setting up `config.yaml`.
-This benchmark pushes to JetBrains' private GitHub repository. You will to request a `token_gh` provided by their team, to run this benchmark.
-
-## Inference
-
-To run inference with your model:
-
-```bash
-./evaluation/benchmarks/lca_ci_build_repair/scripts/run_infer.sh llm.yourmodel
-```
-
-## Evaluation
-
-To evaluate the predictions:
-
-```bash
-./evaluation/benchmarks/lca_ci_build_repair/scripts/eval_infer.sh predictions_path_containing_output
-```
-
-## Results
-The benchmark contains 68 instances, we skip instances #126 and #145, and only run 66 instances due to dockerization errors.
-
-Due to running in live GitHub machines, the benchmark is sensitive to the date it is run. Even the golden patches in the dataset might present failures due to updates.
-For example, on 2025-04-09, running the benchmark against the golden patches gave 57/67 successes, with 1 job left in the waiting list.
-
-On 2025-04-10, running the benchmark full with OH and no oracle, 37 succeeded. That is 54% of the complete set of 68 instances and 64% of the 57 that succeed with golden patches.

evaluation/benchmarks/lca_ci_build_repair/config_template.yaml

@@ -1,11 +0,0 @@
-LCA_PATH: path #where to clone lca-ci rep
-model_name: OpenHands
-benchmark_owner: ICML-25-BenchName-builds-repair
-token_gh: your_token
-#for lca-ci-repo
-repos_folder: /path/to/repos # here the cloned repos would be stored
-out_folder: /out/folder # here the result files would be stored
-data_cache_dir: /data/cache/dir/ # here the cached dataset would be stored
-username_gh: username-gh # your GitHub username
-# test_username: test_user # username that would be displayed in the benchmark. Optional. If ommitted, username_gh would be used
-language: Python # dataset language (now only Python is available)

evaluation/benchmarks/lca_ci_build_repair/eval_infer.py

@@ -1,242 +0,0 @@
-"""Implements evaluation on JetBrains CI builds repair baselines
-
-Please see https://github.com/JetBrains-Research/lca-baselines/tree/main/ci-builds-repair
-and https://huggingface.co/datasets/JetBrains-Research/lca-ci-builds-repair
-
-TODOs:
-- Add more flags
-"""
-
-import json
-import os
-from pathlib import Path
-
-import ruamel.yaml
-
-from evaluation.utils.shared import (
-    EvalMetadata,
-    get_default_sandbox_config_for_eval,
-    make_metadata,
-)
-from openhands.core.config import (
-    AppConfig,
-    LLMConfig,
-    get_parser,
-    load_app_config,
-)
-from openhands.core.logger import openhands_logger as logger
-from openhands.core.main import create_runtime
-from openhands.events.action import CmdRunAction
-from openhands.events.observation import CmdOutputObservation
-from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync
-
-
-def get_config(
-    metadata: EvalMetadata,
-) -> AppConfig:
-    sandbox_config = get_default_sandbox_config_for_eval()
-    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
-        default_agent=metadata.agent_class,
-        run_as_openhands=False,
-        runtime='docker',
-        max_iterations=metadata.max_iterations,
-        sandbox=sandbox_config,
-        # do not mount workspace
-        workspace_base=None,
-        workspace_mount_path=None,
-    )
-    config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.enable_prompt_extensions = False
-    return config
-
-
-config = load_app_config()
-
-
-def load_bench_config():
-    script_dir = os.path.dirname(
-        os.path.abspath(__file__)
-    )  # Get the absolute path of the script
-    config_path = os.path.join(script_dir, 'config.yaml')
-    yaml = ruamel.yaml.YAML(typ='rt')
-    with open(config_path, 'r') as file:
-        return yaml.load(file)
-
-
-bench_config = load_bench_config()
-
-
-def run_eval(
-    runtime: Runtime,
-):
-    """Run the evaluation and create report"""
-    logger.info(f"{'-' * 50} BEGIN Runtime Initialization Fn {'-' * 50}")
-    obs: CmdOutputObservation
-
-    lca_path = bench_config['LCA_PATH']
-    lca_ci_path = os.path.join(
-        lca_path, 'lca-baselines', 'ci-builds-repair', 'ci-builds-repair-benchmark'
-    )
-
-    model_name = bench_config['model_name']
-
-    action = CmdRunAction(command=f'mkdir {lca_path}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    action = CmdRunAction(command=f'cd {lca_path}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    lca_repo_url = 'https://github.com/juanmichelini/lca-baselines'
-    action = CmdRunAction(command=f'git clone {lca_repo_url}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    action = CmdRunAction(command=f'cd {lca_ci_path}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    action = CmdRunAction(command='git switch open-hands-integration')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    script_dir = os.path.dirname(
-        os.path.abspath(__file__)
-    )  # Get the absolute path of the script
-    config_path = os.path.join(script_dir, 'config.yaml')
-    runtime.copy_to(config_path, lca_ci_path)
-
-    token_gh = bench_config['token_gh']
-    commandf = f'export TOKEN_GH={token_gh}'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-
-    action = CmdRunAction(command='poetry install')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-
-    # Set up the task environment
-    commandf = f'poetry run python run_eval_jobs.py --model-name "{model_name}" --config-path "{lca_ci_path}/config.yaml" --job-ids-file "/tmp/output_lca.jsonl" --result-filename "testfile.jsonl"  > /tmp/single_output.txt'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(f'run_eval_jobs.py gave {obs.content} !')
-    # assert obs.exit_code == 0
-
-    commandf = 'cat /tmp/single_output.txt'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(f' {commandf} gave {obs.content}!')
-
-    testfile_path = os.path.join(bench_config['out_folder'], 'testfile.jsonl')
-    commandf = f'cat {testfile_path}'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    report_str = obs.content
-
-    logger.info(f"{'-' * 50} END Runtime Initialization Fn {'-' * 50}")
-    return report_str
-
-
-def process_predictions(predictions_path: str):
-    output_path = Path(predictions_path)
-    if output_path.suffix != '.jsonl':
-        raise ValueError('output_path must end in .jsonl')
-
-    output_lca_path = output_path.with_name(output_path.stem + '_lca.jsonl')
-
-    with output_path.open() as infile, output_lca_path.open('w') as outfile:
-        for line in infile:
-            data = json.loads(line)
-            json.dump(data.get('test_result'), outfile)
-            outfile.write('\n')
-
-    return str(output_lca_path)
-
-
-if __name__ == '__main__':
-    parser = get_parser()
-    parser.add_argument(
-        '-s',
-        '--eval-split',
-        type=str,
-        default='test',
-        choices=['test'],
-        help='data split to evaluate on, must be test',
-    )
-    parser.add_argument(
-        '--predictions-path',
-        type=str,
-        help='Path to the directory containing the output.jsonl with the predictions.',
-    )
-    args, _ = parser.parse_known_args()
-
-    data_split = args.eval_split
-
-    llm_config = LLMConfig(model='dummy_model')
-
-    metadata = make_metadata(
-        llm_config,
-        f'jetbrains-lca-ci--{data_split}',
-        args.agent_cls,
-        args.max_iterations,
-        args.eval_note,
-        args.predictions_path,
-    )
-
-    # prepare image
-    config = get_config(metadata)
-    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
-    logger.info('Converting output.jsonl into output_lca.jsonl')
-    predictions_lca_path = process_predictions(
-        os.path.join(args.predictions_path, 'output.jsonl')
-    )
-    runtime.copy_to(predictions_lca_path, '/tmp')
-
-    # get results
-    results_str = run_eval(runtime)
-    results_path = os.path.join(args.predictions_path, 'results.jsonl')
-    with open(results_path, 'w') as file:
-        file.write(results_str)
-    logger.info(f'Saved results to {results_path}')
-
-    # make a summary
-    resolved_instances = []
-    unresolved_instances = []
-    for line in results_str.strip().splitlines():
-        data = json.loads(line)
-        conclusion = data.get('conclusion')
-        if conclusion == 'success':
-            resolved_instances.append(data)
-        elif conclusion == 'failure':
-            unresolved_instances.append(data)
-
-    completed_instances = resolved_instances + unresolved_instances
-
-    report = {
-        'success': len(resolved_instances),
-        'failure': len(unresolved_instances),
-        'resolved_instances': resolved_instances,
-        'unresolved_instances': unresolved_instances,
-        'completed_instances': completed_instances,
-    }
-
-    print(f'Results: {report}')
-    report_path = os.path.join(args.predictions_path, 'report.jsonl')
-    with open(report_path, 'w') as out_f:
-        out_f.write(json.dumps(report) + '\n')
-
-    logger.info(f'Saved report of results in swebench format to {report_path}')

evaluation/benchmarks/lca_ci_build_repair/run_infer.py

@@ -1,406 +0,0 @@
-"""Implements inference on JetBrains CI builds repair baselines
-
-Please see https://github.com/JetBrains-Research/lca-baselines/tree/main/ci-builds-repair
-and https://huggingface.co/datasets/JetBrains-Research/lca-ci-builds-repair
-
-TODOs:
-- Add EXP_NAME
-"""
-
-import asyncio
-import json
-import os
-from typing import Any
-
-import pandas as pd
-import ruamel.yaml
-from datasets import load_dataset
-
-from evaluation.utils.shared import (
-    EvalMetadata,
-    EvalOutput,
-    codeact_user_response,
-    compatibility_for_eval_history_pairs,
-    get_default_sandbox_config_for_eval,
-    make_metadata,
-    prepare_dataset,
-    reset_logger_for_multiprocessing,
-    run_evaluation,
-)
-from openhands.controller.state.state import State
-from openhands.core.config import (
-    AppConfig,
-    get_llm_config_arg,
-    get_parser,
-    load_app_config,
-)
-from openhands.core.logger import openhands_logger as logger
-from openhands.core.main import create_runtime, run_controller
-from openhands.events.action import CmdRunAction, MessageAction
-from openhands.events.observation import CmdOutputObservation
-from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync
-
-
-def get_config(
-    metadata: EvalMetadata,
-) -> AppConfig:
-    sandbox_config = get_default_sandbox_config_for_eval()
-    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
-        default_agent=metadata.agent_class,
-        run_as_openhands=False,
-        runtime='docker',
-        max_iterations=metadata.max_iterations,
-        sandbox=sandbox_config,
-        # do not mount workspace
-        workspace_base=None,
-        workspace_mount_path=None,
-    )
-    config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.enable_prompt_extensions = False
-    return config
-
-
-config = load_app_config()
-
-
-def load_bench_config():
-    script_dir = os.path.dirname(
-        os.path.abspath(__file__)
-    )  # Get the absolute path of the script
-    config_path = os.path.join(script_dir, 'config.yaml')
-    yaml = ruamel.yaml.YAML(typ='rt')
-    with open(config_path, 'r') as file:
-        return yaml.load(file)
-
-
-bench_config = load_bench_config()
-
-AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
-    'CodeActAgent': codeact_user_response,
-}
-
-AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have completed the task, please finish the interaction using the "finish" tool.\n'
-}
-
-
-def initialize_runtime(
-    runtime: Runtime,
-    instance: pd.Series,
-):
-    """Initialize the runtime for the agent.
-
-    This function is called before the runtime is used to run the agent.
-    """
-    logger.info(f"{'-' * 50} BEGIN Runtime Initialization Fn {'-' * 50}")
-    obs: CmdOutputObservation
-
-    lca_path = bench_config['LCA_PATH']
-    lca_ci_path = os.path.join(
-        lca_path, 'lca-baselines', 'ci-builds-repair', 'ci-builds-repair-benchmark'
-    )
-
-    repo_name = instance['repo_name']
-    repos_path = bench_config['repos_folder']
-    repo_owner = instance['repo_owner']
-    repo_path = os.path.join(repos_path, f'{repo_owner}__{repo_name}')
-    model_name = bench_config['model_name']
-
-    action = CmdRunAction(command=f'mkdir {lca_path}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    action = CmdRunAction(command=f'cd {lca_path}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    lca_repo_url = 'https://github.com/juanmichelini/lca-baselines'
-    action = CmdRunAction(command=f'git clone {lca_repo_url}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    action = CmdRunAction(command=f'cd {lca_ci_path}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    action = CmdRunAction(command='git switch open-hands-integration')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    script_dir = os.path.dirname(
-        os.path.abspath(__file__)
-    )  # Get the absolute path of the script
-    config_path = os.path.join(script_dir, 'config.yaml')
-    with open(config_path, 'r') as file:
-        config_as_text = file.read()
-
-    commandf = f"echo '{config_as_text}' > config.yaml"
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-
-    token_gh = bench_config['token_gh']
-    commandf = f'export TOKEN_GH={token_gh}'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-
-    action = CmdRunAction(command='poetry install')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-
-    # Set up the task environment
-    commandf = f'poetry run python run_get_datapoint.py --model-name {model_name} --id {instance["id"]} > branch_name.txt'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    if obs.exit_code != 0:
-        print(f'run_get_datapoint.py failed at {instance["id"]} with {obs.content}')
-    assert obs.exit_code == 0
-
-    commandf = 'cat branch_name.txt'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    bench_config['user_branch_name'] = obs.content
-
-    # Navigate to the task's code path
-    action = CmdRunAction(command=f'cd {repo_path}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-
-    logger.info(f"{'-' * 50} END Runtime Initialization Fn {'-' * 50}")
-
-
-def complete_runtime(
-    runtime: Runtime,
-    instance: pd.Series,
-) -> dict[str, Any]:
-    """Complete the runtime for the agent.
-
-    This function is called before the runtime is used to run the agent.
-    If you need to do something in the sandbox to get the correctness metric after
-    the agent has run, modify this function.
-    """
-    logger.info(f"{'-' * 50} BEGIN Runtime Completion Fn {'-' * 50}")
-    obs: CmdOutputObservation
-
-    model_name = bench_config['model_name']
-
-    lca_path = bench_config['LCA_PATH']
-    lca_ci_path = os.path.join(
-        lca_path, 'lca-baselines', 'ci-builds-repair', 'ci-builds-repair-benchmark'
-    )
-
-    user_branch_name = bench_config['user_branch_name']
-
-    token_gh = bench_config['token_gh']
-    commandf = f'export TOKEN_GH={token_gh}'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-
-    # Navigate to the lca-baseslines scripts path
-    action = CmdRunAction(command=f'cd {lca_ci_path}')
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    assert obs.exit_code == 0
-
-    commandf = f'poetry run python run_push_datapoint.py --id {instance["id"]} --model-name {model_name} --user-branch-name {user_branch_name} > single_output.json'
-    logger.info(f'Running push script: {commandf}')
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    # assert obs.exit_code == 0
-
-    commandf = 'cat single_output.json'
-    action = CmdRunAction(command=commandf)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    result = json.loads(obs.content)
-
-    logger.info(f"{'-' * 50} END Runtime Completion Fn {'-' * 50}")
-
-    return result
-
-
-def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool = True):
-    config = get_config(metadata)
-
-    # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
-    if reset_logger:
-        log_dir = os.path.join(metadata.eval_output_dir, 'infer_logs')
-        reset_logger_for_multiprocessing(logger, instance['instance_id'], log_dir)
-    else:
-        logger.info(f'Starting evaluation for instance {instance["instance_id"]}.')
-
-    repo_name = instance['repo_name']
-    repo_workflow = instance['workflow_path']
-    repo_logs = instance['logs']
-    repos_path = bench_config['repos_folder']
-    repo_owner = instance['repo_owner']
-    repo_path = os.path.join(repos_path, f'{repo_owner}__{repo_name}')
-
-    # Prepare the task instruction
-    instruction_no_oracle = f"""
-<uploaded_files>
-{repo_path}
-</uploaded_files>
-
-I've uploaded a python code repository in the directory {repo_path}, Consider the following issue:
-
-<issue_description>
-The repository must pass the CI workflow {repo_workflow}.
-but it gave the following error
-{repo_logs}
-</issue_description>
-
-Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?
-I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!
-Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
-Your task is to make the minimal changes to non-test files in the {repo_path} directory to ensure the <issue_description> is satisfied.
-
-Follow these phases to resolve the issue:
-
-Phase 1. READING: read the problem and reword it in clearer terms
-   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
-   1.2 Hightlight message errors, method names, variables, file names, stack traces, and technical details.
-   1.3 Explain the problem in clear terms.
-   1.4 Enumerate the steps to reproduce the problem.
-   1.5 Hightlight any best practices to take into account when testing and fixing the issue
-
-Phase 2. RUNNING: install and run the tests on the repository
-   2.1 Follow the readme
-   2.2 Install the environment and anything needed
-   2.2 Iterate and figure out how to run the tests
-
-Phase 3. EXPLORATION: find the files that are related to the problem and possible solutions
-   3.1 Use `grep` to search for relevant methods, classes, keywords and error messages.
-   3.2 Identify all files related to the problem statement.
-   3.3 Propose the methods and files to fix the issue and explain why.
-   3.4 From the possible file locations, select the most likely location to fix the issue.
-
-Phase 4. TEST CREATION: before implementing any fix, create a script to reproduce and verify the issue.
-   4.1 Look at existing test files in the repository to understand the test format/structure.
-   4.2 Create a minimal reproduction script that reproduces the located issue.
-   4.3 Run the reproduction script to confirm you are reproducing the issue.
-   4.4 Adjust the reproduction script as necessary.
-
-Phase 5. FIX ANALYSIS: state clearly the problem and how to fix it
-   5.1 State clearly what the problem is.
-   5.2 State clearly where the problem is located.
-   5.3 State clearly how the test reproduces the issue.
-   5.4 State clearly the best practices to take into account in the fix.
-   5.5 State clearly how to fix the problem.
-
-Phase 6. FIX IMPLEMENTATION: Edit the source code to implement your chosen solution.
-   6.1 Make minimal, focused changes to fix the issue.
-
-Phase 7. VERIFICATION: Test your implementation thoroughly.
-   7.1 Run your reproduction script to verify the fix works.
-   7.2 Add edge cases to your test script to ensure comprehensive coverage.
-   7.3 Run existing tests related to the modified code to ensure you haven't broken anything. Run any tests in the repository related to:
-     7.2.1 The issue you are fixing
-     7.2.2 The files you modified
-     7.2.3 The functions you changed
-   7.4 If any tests fail, revise your implementation until all tests pass
-
-Phase 8. REVIEW: Carefully re-read the problem description and compare your changes with the base commit {instance["sha_fail"]}.
-   8.1 Ensure you've fully addressed all requirements.
-
-Once all phases are done, announce: 'Agent Task Complete'.
-Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.
-"""
-    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
-    initialize_runtime(runtime, instance)
-
-    # Run the agent
-    state: State | None = asyncio.run(
-        run_controller(
-            config=config,
-            initial_user_action=MessageAction(content=instruction_no_oracle),
-            runtime=runtime,
-            fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN.get(
-                metadata.agent_class
-            ),
-        )
-    )
-    assert state is not None
-    metrics = state.metrics.get() if state.metrics else {}
-
-    test_result = complete_runtime(runtime, instance)
-
-    # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
-    # for compatibility with the existing output format, we can remake the pairs here
-    # remove when it becomes unnecessary
-    histories = compatibility_for_eval_history_pairs(state.history)
-
-    # Save the output
-    output = EvalOutput(
-        instance_id=instance['instance_id'],
-        # instance=instance.to_dict(orient='recorods'),
-        instruction=instruction_no_oracle,
-        metadata=metadata,
-        history=histories,
-        test_result=test_result,
-        metrics=metrics,
-    )
-    return output
-
-
-if __name__ == '__main__':
-    parser = get_parser()
-    parser.add_argument(
-        '-s',
-        '--eval-split',
-        type=str,
-        default='test',
-        choices=['test'],
-        help='data split to evaluate on, must be test',
-    )
-    args, _ = parser.parse_known_args()
-
-    data_split = args.eval_split
-
-    bench = load_dataset(
-        'JetBrains-Research/lca-ci-builds-repair', split=data_split
-    ).to_pandas()
-    # todo: see why 126 is giving problems on inference
-    # todo: see why 145 is giving problems on eval
-    bench = bench[bench['id'] != 126]
-    bench = bench[bench['id'] != 145]
-    # bench = bench.iloc[0:56]
-    # add column instnace_id for compatibility with oh repo, old id column must be kept for lca repo
-    bench['instance_id'] = bench['id'].astype(str)
-
-    llm_config = None
-    if args.llm_config:
-        llm_config = get_llm_config_arg(args.llm_config)
-        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
-        llm_config.modify_params = False
-    if llm_config is None:
-        raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
-
-    metadata = make_metadata(
-        llm_config,
-        f'jetbrains-lca-ci--{data_split}',
-        args.agent_cls,
-        args.max_iterations,
-        args.eval_note,
-        args.eval_output_dir,
-    )
-    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
-    instances = prepare_dataset(bench, output_file, args.eval_n_limit)
-
-    run_evaluation(
-        instances, metadata, output_file, args.eval_num_workers, process_instance
-    )

evaluation/benchmarks/lca_ci_build_repair/scripts/eval_infer.sh

@@ -1,33 +0,0 @@
-#!/usr/bin/env bash
-set -eo pipefail
-
-source "evaluation/utils/version_control.sh"
-
-PROCESS_FILEPATH=$1
-if [ -z "$PROCESS_FILEPATH" ]; then
-    echo "Error: PROCESS_FILEPATH is empty. Usage: ./eval_infer.sh <output_file> [instance_id] [dataset_name] [split]"
-    exit 1
-fi
-
-get_openhands_version
-
-PROCESS_FILEPATH=$(realpath $PROCESS_FILEPATH)
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
-echo "PROCESS_FILEPATH: $PROCESS_FILEPATH"
-
-EVAL_NOTE="$OPENHANDS_VERSION"
-if [ -n "$EXP_NAME" ]; then
-  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
-fi
-
-function run_eval() {
-  COMMAND="poetry run python ./evaluation/benchmarks/lca_ci_build_repair/eval_infer.py \
-    --predictions-path $PROCESS_FILEPATH "
-
-  echo "RUNNING: $COMMAND"
-  # Run the command
-  eval $COMMAND
-}
-
-unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
-run_eval

evaluation/benchmarks/lca_ci_build_repair/scripts/run_infer.sh

@@ -1,27 +0,0 @@
-#!/usr/bin/env bash
-set -eo pipefail
-
-source "evaluation/utils/version_control.sh"
-
-MODEL_CONFIG=$1
-
-get_openhands_version
-
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
-echo "MODEL_CONFIG: $MODEL_CONFIG"
-
-EVAL_NOTE="$OPENHANDS_VERSION"
-if [ -n "$EXP_NAME" ]; then
-  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
-fi
-
-function run_eval() {
-  COMMAND="poetry run python ./evaluation/benchmarks/lca_ci_build_repair/run_infer.py \
-    --llm-config $MODEL_CONFIG "
-
-  # Run the command
-  eval $COMMAND
-}
-
-#unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
-run_eval

evaluation/benchmarks/lca_ci_build_repair/setup.py

@@ -1,60 +0,0 @@
-"""Installs LCA CI Build Repair benchmark with scripts for OH integration."""
-
-import os
-import shutil
-import subprocess
-
-import yaml
-
-
-def setup():
-    # Read config.yaml
-    print('Reading config.yaml')
-    script_dir = os.path.dirname(
-        os.path.abspath(__file__)
-    )  # Get the absolute path of the script
-    config_path = os.path.join(script_dir, 'config.yaml')
-    with open(config_path, 'r') as f:
-        config = yaml.safe_load(f)
-
-    lca_path = config['LCA_PATH']
-    lca_ci_path = os.path.join(
-        lca_path, 'lca-baselines', 'ci-builds-repair', 'ci-builds-repair-benchmark'
-    )
-    repo_url = 'https://github.com/juanmichelini/lca-baselines'
-
-    # Clone the repository to LCA_CI_PATH
-    print(f'Cloning lca-baselines repository from {repo_url} into {lca_path}')
-    result = subprocess.run(
-        ['git', 'clone', repo_url], cwd=lca_path, capture_output=True, text=True
-    )
-    if result.returncode != 0:
-        print(f'Warning cloning repository: {result.stderr}')
-
-    # Clone the repository to LCA_CI_PATH
-    print('Switching branches')
-    result = subprocess.run(
-        ['git', 'switch', 'open-hands-integration'],
-        cwd=lca_ci_path,
-        capture_output=True,
-        text=True,
-    )
-    if result.returncode != 0:
-        print(f'Warning switching repository: {result.stderr}')
-
-    # Move and rename config_lca.yaml (overwrite if exists)
-    lca_ci_config_path = os.path.join(lca_ci_path, 'config.yaml')
-    print(f'Copying config.yaml to {lca_ci_config_path}')
-    shutil.copy(config_path, lca_ci_config_path)
-
-    # Run poetry install in LCA_CI_PATH
-    print(f"Running 'poetry install' in {lca_ci_path}")
-    result = subprocess.run(
-        ['poetry', 'install'], cwd=lca_ci_path, capture_output=True, text=True
-    )
-    if result.returncode != 0:
-        print(f'Warning during poetry install: {result.stderr}')
-
-
-if __name__ == '__main__':
-    setup()

evaluation/benchmarks/swe_bench/README.md

@@ -2,8 +2,6 @@
 
 This folder contains the evaluation harness that we built on top of the original [SWE-Bench benchmark](https://www.swebench.com/) ([paper](https://arxiv.org/abs/2310.06770)).
 
-**UPDATE (4/8/2025): We now support running SWT-Bench evaluation! For more details, checkout [the corresponding section](#SWT-Bench-Evaluation).**
-
 **UPDATE (03/27/2025): We now support SWE-Bench multimodal evaluation! Simply use "princeton-nlp/SWE-bench_Multimodal" as the dataset name in the `run_infer.sh` script to evaluate on multimodal instances.**
 
 **UPDATE (2/18/2025): We now support running SWE-Gym using the same evaluation harness here. For more details, checkout [this README](./SWE-Gym.md).**
@@ -143,7 +141,7 @@ With `output.jsonl` file, you can run `eval_infer.sh` to evaluate generated patc
 ./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh $YOUR_OUTPUT_JSONL [instance_id] [dataset_name] [split]
 
 # Example
-./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Lite/CodeActAgent/gpt-4-1106-preview_maxiter_50_N_v1.0/output.jsonl
+./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh evaluation/evaluation_outputs/outputs/swe_bench/CodeActAgent/gpt-4-1106-preview_maxiter_50_N_v1.0/output.jsonl
 ```
 
 The script now accepts optional arguments:
@@ -158,7 +156,7 @@ For example, to evaluate a specific instance with a custom dataset and split:
 ./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh $YOUR_OUTPUT_JSONL instance_123 princeton-nlp/SWE-bench test
 ```
 
-> You can also pass in a JSONL with [SWE-Bench format](https://github.com/SWE-bench/SWE-bench/blob/main/assets/evaluation.md#-creating-predictions) to `./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh`, where each line is a JSON of `{"model_patch": "XXX", "model_name_or_path": "YYY", "instance_id": "ZZZ"}`.
+> You can also pass in a JSONL with [SWE-Bench format](https://github.com/princeton-nlp/SWE-bench/blob/main/tutorials/evaluation.md#-creating-predictions) to `./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh`, where each line is a JSON of `{"model_patch": "XXX", "model_name_or_path": "YYY", "instance_id": "ZZZ"}`.
 
 The final results will be saved to `evaluation/evaluation_outputs/outputs/swe_bench/CodeActAgent/gpt-4-1106-preview_maxiter_50_N_v1.0/` with the following files/directory:
 
@@ -184,58 +182,3 @@ To clean-up all existing runtimes that you've already started, run:
 ```bash
 ALLHANDS_API_KEY="YOUR-API-KEY" ./evaluation/utils/scripts/cleanup_remote_runtime.sh
 ```
-
-## SWT-Bench Evaluation
-
-[SWT-Bench](https://swtbench.com/) ([paper](https://arxiv.org/abs/2406.12952)) is a benchmark for evaluating the capability of LLMs at creating unit tests. It is performed on the same instances as SWE-Bench, but requires a separate evaluation harness to capture coverage and issue reproduction. We therefore detail below how to leverage the inference script in this folder to run inference on SWT-Bench and how to use the SWT-Bench evaluation harness to evaluate them.
-
-### Run inference on SWT-Bench
-
-To run inference on SWT-Bench, you can use the same `run_infer.sh` script as described for evaluation on plain SWE-Bench. The only differences is that you need to specify the `mode` parameter to `swt` or `swt-ci` when running the script. For example, to run inference on SWT-Bench Verified, run the following command:
-
-```bash
-./evaluation/benchmarks/swe_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [swe-dataset] test 1 swt
-
-# Example - This runs evaluation on CodeActAgent for 500 instances on "SWT-bench_Verified"'s test set (corresponding to SWE-bench_Verified), with max 100 iteration per instances, with 1 number of workers running in parallel
-./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4o-2024-11-20 HEAD CodeActAgent 500 100 1 princeton-nlp/SWE-bench_Verified test 1 swt
-```
-
-The two modes `swt` and `swt-ci` have the following effect:
-- `swt`: This mode will change the prompt to instruct the agent to generate reproducing test cases instead of resolving the issue.
-- `swt-ci`: In addition to the changes by `swt`, this mode sets up the CI environment by i) pre-installing the environment in the docker image, such that the test framework can be executed without errors and ii) telling the model the exact command to run the test framework.
-
-### Run evaluation for SWT-bench
-
-The evaluation of these results is done leveraging [the SWT-Bench evaluation harness](https://github.com/logic-star-ai/swt-bench/tree/master).
-
-#### Extracting results into SWT-Bench harness format
-In order to run evaluation of the obtained inference results in the SWT-Bench harness, we transform the results to a format that the SWT-Bench evaluation harness expects.
-
-```bash
-python3 evaluation/benchmarks/swe_bench/scripts/swtbench/convert.py --prediction_file [output.jsonl] > [output_swt.jsonl]
-
-# Example
-python3 evaluation/benchmarks/swe_bench/scripts/swtbench/convert.py --prediction_file "evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Verified-test/CodeActAgent/gpt-4o-2024-11-20_maxiter_100_N_v0.31.0-no-hint-swt-run_1/output.jsonl" > OpenHands-gpt-4o-2024-11-20.jsonl
-```
-
-#### Running the results in SWT-Bench
-
-Next, we run the [SWT-Bench evaluation harness](https://github.com/logic-star-ai/swt-bench/tree/master) with these results.
-First set-up and validate the setup as described in the harness [here](https://github.com/logic-star-ai/swt-bench/tree/master?tab=readme-ov-file#-set-up).
-Then, run the evaluation with the following command:
-
-```bash
-# Example
-python3 -m src.main \
-    --dataset_name princeton-nlp/SWE-bench_Verified \
-    --predictions_path <pathTo>/OpenHands-gpt-4o-2024-11-20.jsonl \
-    --max_workers 12 \
-    --run_id OpenHands-CodeAct-gpt-4o-2024-11-20  --patch_types vanilla  --build_mode api
-```
-
-The results of the evaluation can be obtained by running the reporting script of the harness.
-
-```bash
-# Example
-python -m src.report run_instance_swt_logs/OpenHands-CodeAct-gpt-4o-2024-11-20/OpenHands__CodeActAgent__gpt-4o-2024-11-20 --dataset verified
-```

evaluation/benchmarks/swe_bench/binary_patch_utils.py

@@ -1,52 +0,0 @@
-"""
-Utilities for handling binary files and patch generation in SWE-bench evaluation.
-"""
-
-
-def remove_binary_diffs(patch_text):
-    """
-    Remove binary file diffs from a git patch.
-
-    Args:
-        patch_text (str): The git patch text
-
-    Returns:
-        str: The cleaned patch text with binary diffs removed
-    """
-    lines = patch_text.splitlines()
-    cleaned_lines = []
-    block = []
-    is_binary_block = False
-
-    for line in lines:
-        if line.startswith('diff --git '):
-            if block and not is_binary_block:
-                cleaned_lines.extend(block)
-            block = [line]
-            is_binary_block = False
-        elif 'Binary files' in line:
-            is_binary_block = True
-            block.append(line)
-        else:
-            block.append(line)
-
-    if block and not is_binary_block:
-        cleaned_lines.extend(block)
-    return '\n'.join(cleaned_lines)
-
-
-def remove_binary_files_from_git():
-    """
-    Generate a bash command to remove binary files from git staging.
-
-    Returns:
-        str: A bash command that removes binary files from git staging
-    """
-    return """
-    for file in $(git status --porcelain | grep -E "^(M| M|\\?\\?|A| A)" | cut -c4-); do
-        if [ -f "$file" ] && (file "$file" | grep -q "executable" || git check-attr binary "$file" | grep -q "binary: set"); then
-            git rm -f "$file" 2>/dev/null || rm -f "$file"
-            echo "Removed: $file"
-        fi
-    done
-    """.strip()

evaluation/benchmarks/swe_bench/resource/mapping.py

@@ -28,7 +28,7 @@ def get_resource_mapping(dataset_name: str) -> dict[str, float]:
 
         with open(file_path, 'r') as f:
             _global_resource_mapping[dataset_name] = json.load(f)
-        logger.debug(f'Loaded resource mapping for {dataset_name}')
+        logger.info(f'Loaded resource mapping for {dataset_name}')
     return _global_resource_mapping[dataset_name]
 
 

evaluation/benchmarks/swe_bench/resource/swt_bench_constants.py

@@ -1,842 +0,0 @@
-# Based on https://github.com/logic-star-ai/swt-bench/blob/master/src/constants.py
-
-# Constants - Installation Specifications
-MAP_VERSION_TO_INSTALL_SKLEARN = {
-    k: {
-        'python': '3.6',
-        'packages': 'numpy scipy cython pytest pandas matplotlib',
-        'install': 'python -m pip install -v --no-use-pep517 --no-build-isolation -e .',
-        'pip_packages': [
-            'cython',
-            'numpy==1.19.2',
-            'setuptools',
-            'scipy==1.5.2',
-        ],
-    }
-    for k in ['0.20', '0.21', '0.22']
-}
-MAP_VERSION_TO_INSTALL_SKLEARN.update(
-    {
-        k: {
-            'python': '3.9',
-            'packages': "'numpy==1.19.2' 'scipy==1.5.2' 'cython==3.0.10' pytest 'pandas<2.0.0' 'matplotlib<3.9.0' setuptools pytest joblib threadpoolctl",
-            'install': 'python -m pip install -v --no-use-pep517 --no-build-isolation -e .',
-            'pip_packages': ['cython', 'setuptools', 'numpy', 'scipy'],
-        }
-        for k in ['1.3', '1.4']
-    }
-)
-MAP_VERSION_TO_INSTALL_FLASK = {
-    '2.0': {
-        'python': '3.9',
-        'packages': 'requirements.txt',
-        'install': 'python -m pip install -e .',
-        'pip_packages': [
-            'setuptools==70.0.0',
-            'Werkzeug==2.3.7',
-            'Jinja2==3.0.1',
-            'itsdangerous==2.1.2',
-            'click==8.0.1',
-            'MarkupSafe==2.1.3',
-        ],
-    },
-    '2.1': {
-        'python': '3.10',
-        'packages': 'requirements.txt',
-        'install': 'python -m pip install -e .',
-        'pip_packages': [
-            'click==8.1.3',
-            'itsdangerous==2.1.2',
-            'Jinja2==3.1.2',
-            'MarkupSafe==2.1.1',
-            'Werkzeug==2.3.7',
-        ],
-    },
-}
-MAP_VERSION_TO_INSTALL_FLASK.update(
-    {
-        k: {
-            'python': '3.11',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-            'pip_packages': [
-                'click==8.1.3',
-                'itsdangerous==2.1.2',
-                'Jinja2==3.1.2',
-                'MarkupSafe==2.1.1',
-                'Werkzeug==2.3.7',
-            ],
-        }
-        for k in ['2.2', '2.3']
-    }
-)
-MAP_VERSION_TO_INSTALL_DJANGO = {
-    k: {
-        'python': '3.5',
-        'packages': 'requirements.txt',
-        'pre_install': [
-            'apt-get update && apt-get install -y locales',
-            "echo 'en_US UTF-8' > /etc/locale.gen",
-            'locale-gen en_US.UTF-8',
-        ],
-        'install': 'python setup.py install',
-        'pip_packages': ['setuptools'],
-        'eval_commands': [
-            'export LANG=en_US.UTF-8',
-            'export LC_ALL=en_US.UTF-8',
-            'export PYTHONIOENCODING=utf8',
-            'export LANGUAGE=en_US:en',
-        ],
-    }
-    for k in ['1.7', '1.8', '1.9', '1.10', '1.11', '2.0', '2.1', '2.2']
-}
-MAP_VERSION_TO_INSTALL_DJANGO.update(
-    {
-        k: {'python': '3.5', 'install': 'python setup.py install'}
-        for k in ['1.4', '1.5', '1.6']
-    }
-)
-MAP_VERSION_TO_INSTALL_DJANGO.update(
-    {
-        k: {
-            'python': '3.6',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-            'eval_commands': [
-                "sed -i '/en_US.UTF-8/s/^# //g' /etc/locale.gen && locale-gen",
-                'export LANG=en_US.UTF-8',
-                'export LANGUAGE=en_US:en',
-                'export LC_ALL=en_US.UTF-8',
-            ],
-        }
-        for k in ['3.0', '3.1', '3.2']
-    }
-)
-MAP_VERSION_TO_INSTALL_DJANGO.update(
-    {
-        k: {
-            'python': '3.8',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-        }
-        for k in ['4.0']
-    }
-)
-MAP_VERSION_TO_INSTALL_DJANGO.update(
-    {
-        k: {
-            'python': '3.9',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-        }
-        for k in ['4.1', '4.2']
-    }
-)
-MAP_VERSION_TO_INSTALL_DJANGO.update(
-    {
-        k: {
-            'python': '3.11',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-        }
-        for k in ['5.0']
-    }
-)
-MAP_VERSION_TO_INSTALL_REQUESTS = {
-    k: {'python': '3.9', 'packages': 'pytest', 'install': 'python -m pip install .'}
-    for k in ['0.7', '0.8', '0.9', '0.11', '0.13', '0.14', '1.1', '1.2', '2.0', '2.2']
-    + ['2.3', '2.4', '2.5', '2.7', '2.8', '2.9', '2.10', '2.11', '2.12', '2.17']
-    + ['2.18', '2.19', '2.22', '2.26', '2.25', '2.27', '3.0']
-}
-MAP_VERSION_TO_INSTALL_SEABORN = {
-    k: {
-        'python': '3.9',
-        'install': 'python -m pip install -e .',
-        'pip_packages': [
-            'contourpy==1.1.0',
-            'cycler==0.11.0',
-            'fonttools==4.42.1',
-            'importlib-resources==6.0.1',
-            'kiwisolver==1.4.5',
-            'matplotlib==3.7.2',
-            'numpy==1.25.2',
-            'packaging==23.1',
-            'pandas==1.3.5',  # 2.0.3
-            'pillow==10.0.0',
-            'pyparsing==3.0.9',
-            'pytest',
-            'python-dateutil==2.8.2',
-            'pytz==2023.3.post1',
-            'scipy==1.11.2',
-            'six==1.16.0',
-            'tzdata==2023.1',
-            'zipp==3.16.2',
-        ],
-    }
-    for k in ['0.11']
-}
-MAP_VERSION_TO_INSTALL_SEABORN.update(
-    {
-        k: {
-            'python': '3.9',
-            'install': 'python -m pip install -e .[dev]',
-            'pip_packages': [
-                'contourpy==1.1.0',
-                'cycler==0.11.0',
-                'fonttools==4.42.1',
-                'importlib-resources==6.0.1',
-                'kiwisolver==1.4.5',
-                'matplotlib==3.7.2',
-                'numpy==1.25.2',
-                'packaging==23.1',
-                'pandas==2.0.0',
-                'pillow==10.0.0',
-                'pyparsing==3.0.9',
-                'pytest',
-                'python-dateutil==2.8.2',
-                'pytz==2023.3.post1',
-                'scipy==1.11.2',
-                'six==1.16.0',
-                'tzdata==2023.1',
-                'zipp==3.16.2',
-            ],
-        }
-        for k in ['0.12', '0.13']
-    }
-)
-MAP_VERSION_TO_INSTALL_PYTEST = {
-    k: {'python': '3.9', 'install': 'python -m pip install -e .'}
-    for k in [
-        '4.4',
-        '4.5',
-        '4.6',
-        '5.0',
-        '5.1',
-        '5.2',
-        '5.3',
-        '5.4',
-        '6.0',
-        '6.2',
-        '6.3',
-        '7.0',
-        '7.1',
-        '7.2',
-        '7.4',
-        '8.0',
-    ]
-}
-MAP_VERSION_TO_INSTALL_PYTEST['4.4']['pip_packages'] = [
-    'atomicwrites==1.4.1',
-    'attrs==23.1.0',
-    'more-itertools==10.1.0',
-    'pluggy==0.13.1',
-    'py==1.11.0',
-    'setuptools==68.0.0',
-    'six==1.16.0',
-]
-MAP_VERSION_TO_INSTALL_PYTEST['4.5']['pip_packages'] = [
-    'atomicwrites==1.4.1',
-    'attrs==23.1.0',
-    'more-itertools==10.1.0',
-    'pluggy==0.11.0',
-    'py==1.11.0',
-    'setuptools==68.0.0',
-    'six==1.16.0',
-    'wcwidth==0.2.6',
-]
-MAP_VERSION_TO_INSTALL_PYTEST['4.6']['pip_packages'] = [
-    'atomicwrites==1.4.1',
-    'attrs==23.1.0',
-    'more-itertools==10.1.0',
-    'packaging==23.1',
-    'pluggy==0.13.1',
-    'py==1.11.0',
-    'six==1.16.0',
-    'wcwidth==0.2.6',
-]
-for k in ['5.0', '5.1', '5.2']:
-    MAP_VERSION_TO_INSTALL_PYTEST[k]['pip_packages'] = [
-        'atomicwrites==1.4.1',
-        'attrs==23.1.0',
-        'more-itertools==10.1.0',
-        'packaging==23.1',
-        'pluggy==0.13.1',
-        'py==1.11.0',
-        'wcwidth==0.2.6',
-    ]
-MAP_VERSION_TO_INSTALL_PYTEST['5.3']['pip_packages'] = [
-    'attrs==23.1.0',
-    'more-itertools==10.1.0',
-    'packaging==23.1',
-    'pluggy==0.13.1',
-    'py==1.11.0',
-    'wcwidth==0.2.6',
-]
-MAP_VERSION_TO_INSTALL_PYTEST['5.4']['pip_packages'] = [
-    'py==1.11.0',
-    'packaging==23.1',
-    'attrs==23.1.0',
-    'more-itertools==10.1.0',
-    'pluggy==0.13.1',
-]
-MAP_VERSION_TO_INSTALL_PYTEST['6.0']['pip_packages'] = [
-    'attrs==23.1.0',
-    'iniconfig==2.0.0',
-    'more-itertools==10.1.0',
-    'packaging==23.1',
-    'pluggy==0.13.1',
-    'py==1.11.0',
-    'toml==0.10.2',
-]
-for k in ['6.2', '6.3']:
-    MAP_VERSION_TO_INSTALL_PYTEST[k]['pip_packages'] = [
-        'attrs==23.1.0',
-        'iniconfig==2.0.0',
-        'packaging==23.1',
-        'pluggy==0.13.1',
-        'py==1.11.0',
-        'toml==0.10.2',
-    ]
-MAP_VERSION_TO_INSTALL_PYTEST['7.0']['pip_packages'] = [
-    'attrs==23.1.0',
-    'iniconfig==2.0.0',
-    'packaging==23.1',
-    'pluggy==0.13.1',
-    'py==1.11.0',
-]
-for k in ['7.1', '7.2']:
-    MAP_VERSION_TO_INSTALL_PYTEST[k]['pip_packages'] = [
-        'attrs==23.1.0',
-        'iniconfig==2.0.0',
-        'packaging==23.1',
-        'pluggy==0.13.1',
-        'py==1.11.0',
-        'tomli==2.0.1',
-    ]
-MAP_VERSION_TO_INSTALL_PYTEST['7.4']['pip_packages'] = [
-    'iniconfig==2.0.0',
-    'packaging==23.1',
-    'pluggy==1.3.0',
-    'exceptiongroup==1.1.3',
-    'tomli==2.0.1',
-]
-MAP_VERSION_TO_INSTALL_PYTEST['8.0']['pip_packages'] = [
-    'iniconfig==2.0.0',
-    'packaging==23.1',
-    'pluggy==1.3.0',
-    'exceptiongroup==1.1.3',
-    'tomli==2.0.1',
-]
-MAP_VERSION_TO_INSTALL_MATPLOTLIB = {
-    k: {
-        'python': '3.11',
-        'packages': 'environment.yml',
-        'install': 'python -m pip install -e .',
-        'pre_install': [
-            'apt-get -y update && apt-get -y upgrade && apt-get install -y imagemagick ffmpeg texlive texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-luatex cm-super dvipng'
-        ],
-        'pip_packages': [
-            'contourpy==1.1.0',
-            'cycler==0.11.0',
-            'fonttools==4.42.1',
-            'ghostscript',
-            'kiwisolver==1.4.5',
-            'numpy==1.25.2',
-            'packaging==23.1',
-            'pillow==10.0.0',
-            'pikepdf',
-            'pyparsing==3.0.9',
-            'python-dateutil==2.8.2',
-            'six==1.16.0',
-            'setuptools==68.1.2',
-            'setuptools-scm==7.1.0',
-            'typing-extensions==4.7.1',
-        ],
-    }
-    for k in ['3.5', '3.6', '3.7']
-}
-MAP_VERSION_TO_INSTALL_MATPLOTLIB.update(
-    {
-        k: {
-            'python': '3.8',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-            'pre_install': [
-                'apt-get -y update && apt-get -y upgrade && apt-get install -y imagemagick ffmpeg libfreetype6-dev pkg-config texlive texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-luatex cm-super'
-            ],
-            'pip_packages': ['pytest', 'ipython'],
-        }
-        for k in ['3.1', '3.2', '3.3', '3.4']
-    }
-)
-MAP_VERSION_TO_INSTALL_MATPLOTLIB.update(
-    {
-        k: {
-            'python': '3.7',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-            'pre_install': [
-                'apt-get -y update && apt-get -y upgrade && apt-get install -y imagemagick ffmpeg libfreetype6-dev pkg-config'
-            ],
-            'pip_packages': ['pytest'],
-        }
-        for k in ['3.0']
-    }
-)
-MAP_VERSION_TO_INSTALL_MATPLOTLIB.update(
-    {
-        k: {
-            'python': '3.5',
-            'install': 'python setup.py build; python setup.py install',
-            'pre_install': [
-                'apt-get -y update && apt-get -y upgrade && && apt-get install -y imagemagick ffmpeg'
-            ],
-            'pip_packages': ['pytest'],
-            'execute_test_as_nonroot': True,
-        }
-        for k in ['2.0', '2.1', '2.2', '1.0', '1.1', '1.2', '1.3', '1.4', '1.5']
-    }
-)
-MAP_VERSION_TO_INSTALL_SPHINX = {
-    k: {
-        'python': '3.9',
-        'pip_packages': ['tox==4.16.0', 'tox-current-env==0.0.11'],
-        'install': 'python -m pip install -e .[test]',
-        'pre_install': ["sed -i 's/pytest/pytest -rA/' tox.ini"],
-    }
-    for k in ['1.5', '1.6', '1.7', '1.8', '2.0', '2.1', '2.2', '2.3', '2.4', '3.0']
-    + ['3.1', '3.2', '3.3', '3.4', '3.5', '4.0', '4.1', '4.2', '4.3', '4.4']
-    + ['4.5', '5.0', '5.1', '5.2', '5.3', '6.0', '6.2', '7.0', '7.1', '7.2']
-}
-for k in ['3.0', '3.1', '3.2', '3.3', '3.4', '3.5', '4.0', '4.1', '4.2', '4.3', '4.4']:
-    MAP_VERSION_TO_INSTALL_SPHINX[k]['pre_install'].extend(
-        [
-            "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
-            "sed -i 's/sphinxcontrib-applehelp/sphinxcontrib-applehelp<=1.0.7/' setup.py",
-            "sed -i 's/sphinxcontrib-devhelp/sphinxcontrib-devhelp<=1.0.5/' setup.py",
-            "sed -i 's/sphinxcontrib-qthelp/sphinxcontrib-qthelp<=1.0.6/' setup.py",
-            "sed -i 's/alabaster>=0.7,<0.8/alabaster>=0.7,<0.7.12/' setup.py",
-            "sed -i \"s/'packaging',/'packaging', 'markupsafe<=2.0.1',/\" setup.py",
-        ]
-    )
-    if k in ['4.2', '4.3', '4.4']:
-        MAP_VERSION_TO_INSTALL_SPHINX[k]['pre_install'].extend(
-            [
-                "sed -i 's/sphinxcontrib-htmlhelp>=2.0.0/sphinxcontrib-htmlhelp>=2.0.0,<=2.0.4/' setup.py",
-                "sed -i 's/sphinxcontrib-serializinghtml>=1.1.5/sphinxcontrib-serializinghtml>=1.1.5,<=1.1.9/' setup.py",
-            ]
-        )
-    elif k == '4.1':
-        MAP_VERSION_TO_INSTALL_SPHINX[k]['pre_install'].extend(
-            [
-                (
-                    "grep -q 'sphinxcontrib-htmlhelp>=2.0.0' setup.py && "
-                    "sed -i 's/sphinxcontrib-htmlhelp>=2.0.0/sphinxcontrib-htmlhelp>=2.0.0,<=2.0.4/' setup.py || "
-                    "sed -i 's/sphinxcontrib-htmlhelp/sphinxcontrib-htmlhelp<=2.0.4/' setup.py"
-                ),
-                (
-                    "grep -q 'sphinxcontrib-serializinghtml>=1.1.5' setup.py && "
-                    "sed -i 's/sphinxcontrib-serializinghtml>=1.1.5/sphinxcontrib-serializinghtml>=1.1.5,<=1.1.9/' setup.py || "
-                    "sed -i 's/sphinxcontrib-serializinghtml/sphinxcontrib-serializinghtml<=1.1.9/' setup.py"
-                ),
-            ]
-        )
-    else:
-        MAP_VERSION_TO_INSTALL_SPHINX[k]['pre_install'].extend(
-            [
-                "sed -i 's/sphinxcontrib-htmlhelp/sphinxcontrib-htmlhelp<=2.0.4/' setup.py",
-                "sed -i 's/sphinxcontrib-serializinghtml/sphinxcontrib-serializinghtml<=1.1.9/' setup.py",
-            ]
-        )
-MAP_VERSION_TO_INSTALL_SPHINX['7.2']['pre_install'] += [
-    'apt-get update && apt-get install -y graphviz'
-]
-MAP_VERSION_TO_INSTALL_ASTROPY = {
-    k: {
-        'python': '3.9',
-        'install': 'python -m pip install -e .[test] --verbose',
-        'pip_packages': [
-            'attrs==23.1.0',
-            'exceptiongroup==1.1.3',
-            'execnet==2.0.2',
-            'hypothesis==6.82.6',
-            'iniconfig==2.0.0',
-            'numpy==1.25.2',
-            'packaging==23.1',
-            'pluggy==1.3.0',
-            'psutil==5.9.5',
-            'pyerfa==2.0.0.3',
-            'pytest-arraydiff==0.5.0',
-            'pytest-astropy-header==0.2.2',
-            'pytest-astropy==0.10.0',
-            'pytest-cov==4.1.0',
-            'pytest-doctestplus==1.0.0',
-            'pytest-filter-subpackage==0.1.2',
-            'pytest-mock==3.11.1',
-            'pytest-openfiles==0.5.0',
-            'pytest-remotedata==0.4.0',
-            'pytest-xdist==3.3.1',
-            'pytest==7.4.0',
-            'PyYAML==6.0.1',
-            'setuptools==68.0.0',
-            'sortedcontainers==2.4.0',
-            'tomli==2.0.1',
-        ],
-    }
-    for k in ['0.1', '0.2', '0.3', '0.4', '1.1', '1.2', '1.3', '3.0', '3.1', '3.2']
-    + ['4.1', '4.2', '4.3', '5.0', '5.1', '5.2']
-}
-for k in ['4.1', '4.2', '4.3', '5.0', '5.1', '5.2']:
-    MAP_VERSION_TO_INSTALL_ASTROPY[k]['pre_install'] = [
-        'sed -i \'s/requires = \\["setuptools",/requires = \\["setuptools==68.0.0",/\' pyproject.toml'
-    ]
-MAP_VERSION_TO_INSTALL_SYMPY = {
-    k: {
-        'python': '3.9',
-        'packages': 'mpmath flake8',
-        'pip_packages': ['mpmath==1.3.0', 'flake8-comprehensions'],
-        'install': 'python -m pip install -e .',
-    }
-    for k in ['0.7', '1.0', '1.1', '1.10', '1.11', '1.12', '1.2', '1.4', '1.5', '1.6']
-    + ['1.7', '1.8', '1.9']
-}
-MAP_VERSION_TO_INSTALL_SYMPY.update(
-    {
-        k: {
-            'python': '3.9',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-            'pip_packages': ['mpmath==1.3.0'],
-        }
-        for k in ['1.13']
-    }
-)
-MAP_VERSION_TO_INSTALL_PYLINT = {
-    k: {
-        'python': '3.9',
-        'packages': 'requirements.txt',
-        'install': 'python -m pip install -e .',
-    }
-    for k in [
-        '2.10',
-        '2.11',
-        '2.13',
-        '2.14',
-        '2.15',
-        '2.16',
-        '2.17',
-        '2.8',
-        '2.9',
-        '3.0',
-    ]
-}
-MAP_VERSION_TO_INSTALL_PYLINT['2.8']['pip_packages'] = ['pyenchant==3.2']
-MAP_VERSION_TO_INSTALL_PYLINT['2.8']['pre_install'] = [
-    'apt-get update && apt-get install -y libenchant-2-dev hunspell-en-us'
-]
-MAP_VERSION_TO_INSTALL_PYLINT.update(
-    {
-        k: {
-            **MAP_VERSION_TO_INSTALL_PYLINT[k],
-            'pip_packages': ['astroid==3.0.0a6', 'setuptools'],
-        }
-        for k in ['3.0']
-    }
-)
-
-MAP_VERSION_TO_INSTALL_XARRAY = {
-    k: {
-        'python': '3.10',
-        'packages': 'environment.yml',
-        'install': 'python -m pip install -e .',
-        'pip_packages': [
-            'numpy==1.23.0',
-            'packaging==23.1',
-            'pandas==1.5.3',
-            'pytest==7.4.0',
-            'python-dateutil==2.8.2',
-            'pytz==2023.3',
-            'six==1.16.0',
-            'scipy==1.11.1',
-            'setuptools==68.0.0',
-        ],
-        'no_use_env': True,
-    }
-    for k in ['0.12', '0.18', '0.19', '0.20', '2022.03', '2022.06', '2022.09']
-}
-
-MAP_VERSION_TO_INSTALL_SQLFLUFF = {
-    k: {
-        'python': '3.9',
-        'packages': 'requirements.txt',
-        'install': 'python -m pip install -e .',
-    }
-    for k in [
-        '0.10',
-        '0.11',
-        '0.12',
-        '0.13',
-        '0.4',
-        '0.5',
-        '0.6',
-        '0.8',
-        '0.9',
-        '1.0',
-        '1.1',
-        '1.2',
-        '1.3',
-        '1.4',
-        '2.0',
-        '2.1',
-        '2.2',
-    ]
-}
-MAP_VERSION_TO_INSTALL_DBT_CORE = {
-    k: {
-        'python': '3.9',
-        'packages': 'requirements.txt',
-        'install': 'python -m pip install -e .',
-    }
-    for k in [
-        '0.13',
-        '0.14',
-        '0.15',
-        '0.16',
-        '0.17',
-        '0.18',
-        '0.19',
-        '0.20',
-        '0.21',
-        '1.0',
-        '1.1',
-        '1.2',
-        '1.3',
-        '1.4',
-        '1.5',
-        '1.6',
-        '1.7',
-    ]
-}
-MAP_VERSION_TO_INSTALL_PYVISTA = {
-    k: {
-        'python': '3.9',
-        'install': 'python -m pip install -e .',
-        'pip_packages': ['pytest'],
-    }
-    for k in ['0.20', '0.21', '0.22', '0.23']
-}
-MAP_VERSION_TO_INSTALL_PYVISTA.update(
-    {
-        k: {
-            'python': '3.9',
-            'packages': 'requirements.txt',
-            'install': 'python -m pip install -e .',
-            'pip_packages': ['pytest'],
-        }
-        for k in [
-            '0.24',
-            '0.25',
-            '0.26',
-            '0.27',
-            '0.28',
-            '0.29',
-            '0.30',
-            '0.31',
-            '0.32',
-            '0.33',
-            '0.34',
-            '0.35',
-            '0.36',
-            '0.37',
-            '0.38',
-            '0.39',
-            '0.40',
-            '0.41',
-            '0.42',
-            '0.43',
-        ]
-    }
-)
-MAP_VERSION_TO_INSTALL_ASTROID = {
-    k: {
-        'python': '3.9',
-        'install': 'python -m pip install -e .',
-        'pip_packages': ['pytest'],
-    }
-    for k in [
-        '2.10',
-        '2.12',
-        '2.13',
-        '2.14',
-        '2.15',
-        '2.16',
-        '2.5',
-        '2.6',
-        '2.7',
-        '2.8',
-        '2.9',
-        '3.0',
-    ]
-}
-MAP_VERSION_TO_INSTALL_MARSHMALLOW = {
-    k: {
-        'python': '3.9',
-        'install': "python -m pip install -e '.[dev]'",
-    }
-    for k in [
-        '2.18',
-        '2.19',
-        '2.20',
-        '3.0',
-        '3.1',
-        '3.10',
-        '3.11',
-        '3.12',
-        '3.13',
-        '3.15',
-        '3.16',
-        '3.19',
-        '3.2',
-        '3.4',
-        '3.8',
-        '3.9',
-    ]
-}
-MAP_VERSION_TO_INSTALL_PVLIB = {
-    k: {
-        'python': '3.9',
-        'install': 'python -m pip install -e .[all]',
-        'packages': 'pandas scipy',
-        'pip_packages': ['jupyter', 'ipython', 'matplotlib', 'pytest', 'flake8'],
-    }
-    for k in ['0.1', '0.2', '0.3', '0.4', '0.5', '0.6', '0.7', '0.8', '0.9']
-}
-MAP_VERSION_TO_INSTALL_PYDICOM = {
-    k: {'python': '3.6', 'install': 'python -m pip install -e .', 'packages': 'numpy'}
-    for k in [
-        '1.0',
-        '1.1',
-        '1.2',
-        '1.3',
-        '1.4',
-        '2.0',
-        '2.1',
-        '2.2',
-        '2.3',
-        '2.4',
-        '3.0',
-    ]
-}
-MAP_VERSION_TO_INSTALL_PYDICOM.update(
-    {k: {**MAP_VERSION_TO_INSTALL_PYDICOM[k], 'python': '3.8'} for k in ['1.4', '2.0']}
-)
-MAP_VERSION_TO_INSTALL_PYDICOM.update(
-    {k: {**MAP_VERSION_TO_INSTALL_PYDICOM[k], 'python': '3.9'} for k in ['2.1', '2.2']}
-)
-MAP_VERSION_TO_INSTALL_PYDICOM.update(
-    {k: {**MAP_VERSION_TO_INSTALL_PYDICOM[k], 'python': '3.10'} for k in ['2.3']}
-)
-MAP_VERSION_TO_INSTALL_PYDICOM.update(
-    {k: {**MAP_VERSION_TO_INSTALL_PYDICOM[k], 'python': '3.11'} for k in ['2.4', '3.0']}
-)
-MAP_VERSION_TO_INSTALL_HUMANEVAL = {k: {'python': '3.9'} for k in ['1.0']}
-MAP_VERSION_TO_INSTALL_HUMANEVAL_FIX = {
-    k: {'python': '3.10', 'packages': 'pytest'} for k in ['0.0.1']
-}
-
-# Constants - Task Instance Instllation Environment
-MAP_VERSION_TO_INSTALL = {
-    'astropy/astropy': MAP_VERSION_TO_INSTALL_ASTROPY,
-    'dbt-labs/dbt-core': MAP_VERSION_TO_INSTALL_DBT_CORE,
-    'django/django': MAP_VERSION_TO_INSTALL_DJANGO,
-    'matplotlib/matplotlib': MAP_VERSION_TO_INSTALL_MATPLOTLIB,
-    'marshmallow-code/marshmallow': MAP_VERSION_TO_INSTALL_MARSHMALLOW,
-    'mwaskom/seaborn': MAP_VERSION_TO_INSTALL_SEABORN,
-    'pallets/flask': MAP_VERSION_TO_INSTALL_FLASK,
-    'psf/requests': MAP_VERSION_TO_INSTALL_REQUESTS,
-    'pvlib/pvlib-python': MAP_VERSION_TO_INSTALL_PVLIB,
-    'pydata/xarray': MAP_VERSION_TO_INSTALL_XARRAY,
-    'pydicom/pydicom': MAP_VERSION_TO_INSTALL_PYDICOM,
-    'pylint-dev/astroid': MAP_VERSION_TO_INSTALL_ASTROID,
-    'pylint-dev/pylint': MAP_VERSION_TO_INSTALL_PYLINT,
-    'pytest-dev/pytest': MAP_VERSION_TO_INSTALL_PYTEST,
-    'pyvista/pyvista': MAP_VERSION_TO_INSTALL_PYVISTA,
-    'scikit-learn/scikit-learn': MAP_VERSION_TO_INSTALL_SKLEARN,
-    'sphinx-doc/sphinx': MAP_VERSION_TO_INSTALL_SPHINX,
-    'sqlfluff/sqlfluff': MAP_VERSION_TO_INSTALL_SQLFLUFF,
-    'swe-bench/humaneval': MAP_VERSION_TO_INSTALL_HUMANEVAL,
-    'nielstron/humaneval_fix': MAP_VERSION_TO_INSTALL_HUMANEVAL_FIX,
-    'sympy/sympy': MAP_VERSION_TO_INSTALL_SYMPY,
-}
-
-# Constants - Repository Specific Installation Instructions
-MAP_REPO_TO_INSTALL = {}
-
-# Constants - Task Instance Test Frameworks
-TEST_PYTEST_VERBOSE = 'pytest -rA --tb=long -p no:cacheprovider'
-MAP_REPO_TO_TEST_FRAMEWORK_VERBOSE = {
-    'astropy/astropy': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_ASTROPY.keys()
-    },
-    'django/django': {
-        k: './tests/runtests.py --verbosity 2 --settings=test_sqlite --parallel 1'
-        for k in MAP_VERSION_TO_INSTALL_DJANGO.keys()
-    },
-    'marshmallow-code/marshmallow': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_MARSHMALLOW.keys()
-    },
-    'matplotlib/matplotlib': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_MATPLOTLIB.keys()
-    },
-    'mwaskom/seaborn': {
-        k: 'pytest -rA --tb=long' for k in MAP_VERSION_TO_INSTALL_SEABORN.keys()
-    },
-    'pallets/flask': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_FLASK.keys()
-    },
-    'psf/requests': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_REQUESTS.keys()
-    },
-    'pvlib/pvlib-python': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_PVLIB.keys()
-    },
-    'pydata/xarray': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_XARRAY.keys()
-    },
-    'pydicom/pydicom': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_PYDICOM.keys()
-    },
-    'pylint-dev/astroid': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_ASTROID.keys()
-    },
-    'pylint-dev/pylint': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_PYLINT.keys()
-    },
-    'pytest-dev/pytest': {
-        k: 'pytest -rA --tb=long' for k in MAP_VERSION_TO_INSTALL_PYTEST.keys()
-    },
-    'pyvista/pyvista': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_PYVISTA.keys()
-    },
-    'scikit-learn/scikit-learn': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_SKLEARN.keys()
-    },
-    'sphinx-doc/sphinx': {
-        k: 'tox -epy39 -v --' for k in MAP_VERSION_TO_INSTALL_SPHINX.keys()
-    },
-    'sqlfluff/sqlfluff': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_SQLFLUFF.keys()
-    },
-    'swe-bench/humaneval': {
-        k: 'python' for k in MAP_VERSION_TO_INSTALL_HUMANEVAL.keys()
-    },
-    'nielstron/humaneval_fix': {
-        k: TEST_PYTEST_VERBOSE for k in MAP_VERSION_TO_INSTALL_HUMANEVAL.keys()
-    },
-    'sympy/sympy': {
-        k: 'bin/test -C --verbose' for k in MAP_VERSION_TO_INSTALL_SYMPY.keys()
-    },
-}
-MAP_REPO_TO_TEST_FRAMEWORK_VERBOSE['django/django']['1.9'] = (
-    './tests/runtests.py --verbosity 2'
-)

evaluation/benchmarks/swe_bench/run_infer.py

@@ -3,25 +3,16 @@ import copy
 import json
 import os
 import tempfile
-from typing import Any, Literal
+from typing import Any
 
 import pandas as pd
 import toml
 from datasets import load_dataset
 
 import openhands.agenthub
-from evaluation.benchmarks.swe_bench.binary_patch_utils import (
-    remove_binary_diffs,
-    remove_binary_files_from_git,
-)
 from evaluation.benchmarks.swe_bench.resource.mapping import (
     get_instance_resource_factor,
 )
-from evaluation.benchmarks.swe_bench.resource.swt_bench_constants import (
-    MAP_REPO_TO_INSTALL,
-    MAP_REPO_TO_TEST_FRAMEWORK_VERBOSE,
-    MAP_VERSION_TO_INSTALL,
-)
 from evaluation.utils.shared import (
     EvalException,
     EvalMetadata,
@@ -47,12 +38,8 @@ from openhands.core.config import (
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
 from openhands.critic import AgentFinishedCritic
-from openhands.events.action import CmdRunAction, FileReadAction, MessageAction
-from openhands.events.observation import (
-    CmdOutputObservation,
-    ErrorObservation,
-    FileReadObservation,
-)
+from openhands.events.action import CmdRunAction, MessageAction
+from openhands.events.observation import CmdOutputObservation, ErrorObservation
 from openhands.events.serialization.event import event_from_dict, event_to_dict
 from openhands.runtime.base import Runtime
 from openhands.utils.async_utils import call_async_from_sync
@@ -60,7 +47,6 @@ from openhands.utils.shutdown_listener import sleep_if_should_continue
 
 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
 RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
-BenchMode = Literal['swe', 'swt', 'swt-ci']
 
 
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
@@ -74,36 +60,7 @@ def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
 
 def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageAction:
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
-    mode = metadata.details['mode']
-    if mode.startswith('swt'):
-        test_instructions = (
-            f'The following command can be used to run the tests: `{list(MAP_REPO_TO_TEST_FRAMEWORK_VERBOSE[instance.repo].values())[0]}`. Make sure they fail in the expected way.\n'
-            if mode.endswith('ci')
-            else ''
-        )
-        instruction = f"""\
-<uploaded_files>
-/workspace/{workspace_dir_name}
-</uploaded_files>
-I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following issue description:
-
-<issue_description>
-{instance.problem_statement}
-</issue_description>
-
-
-Can you help me implement the necessary changes to the repository to test whether the issue in <issue_description> was resolved?
-I will take care of all changes to any of the non-test files. This means you DON'T have to modify the actual logic and ONLY have to update test logic and tests!
-Your task is to make the minimal changes to tests files in the /workspace directory to reproduce the issue in the <issue_description>, i.e., such that the generated tests fail in the current state (where the issue is unresolved) and pass when the issue will be resolved.
-Follow these steps to reproduce the issue:
-1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.
-2. Create a script `reproduction.py` to reproduce the error and execute it with `python reproduction.py` using the BashTool, to confirm the error
-3. Edit the sourcecode of the repo to integrate your reproduction script into the test framework
-4. Run the test framework and make sure your tests fail! Only submit FAILING tests! Never submit passing tests.
-{test_instructions}Your thinking should be thorough and so it's fine if it's very long.
-"""
-    else:
-        instruction = f"""
+    instruction = f"""
 <uploaded_files>
 /workspace/{workspace_dir_name}
 </uploaded_files>
@@ -119,54 +76,39 @@ I've already taken care of all changes to any of the test files described in the
 Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
 Your task is to make the minimal changes to non-test files in the /workspace/{workspace_dir_name} directory to ensure the <issue_description> is satisfied.
 
-Follow these phases to resolve the issue:
+Follow these steps to resolve the issue:
 
-Phase 1. READING: read the problem and reword it in clearer terms
-   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
-   1.2 Hightlight message errors, method names, variables, file names, stack traces, and technical details.
-   1.3 Explain the problem in clear terms.
-   1.4 Enumerate the steps to reproduce the problem.
-   1.5 Hightlight any best practices to take into account when testing and fixing the issue
+1. EXPLORATION: First, thoroughly explore the repository structure using tools like `find` and `grep`.
+   - Identify all files mentioned in the problem statement
+   - Locate where the issue occurs in the codebase
+   - Understand the surrounding context and dependencies
+   - Use `grep` to search for relevant functions, classes, or error messages
 
-Phase 2. RUNNING: install and run the tests on the repository
-   2.1 Follow the readme
-   2.2 Install the environment and anything needed
-   2.2 Iterate and figure out how to run the tests
+2. ANALYSIS: Based on your exploration, think carefully about the problem and propose 2-5 possible approaches to fix the issue.
+   - Analyze the root cause of the problem
+   - Consider trade-offs between different solutions
+   - Select the most promising approach and explain your reasoning
 
-Phase 3. EXPLORATION: find the files that are related to the problem and possible solutions
-   3.1 Use `grep` to search for relevant methods, classes, keywords and error messages.
-   3.2 Identify all files related to the problem statement.
-   3.3 Propose the methods and files to fix the issue and explain why.
-   3.4 From the possible file locations, select the most likely location to fix the issue.
+3. TEST CREATION: Before implementing any fix, create a script to reproduce and verify the issue.
+   - Look at existing test files in the repository to understand the test format/structure
+   - Create a minimal reproduction script that demonstrates the issue
+   - Run your script to confirm the error exists
 
-Phase 4. TEST CREATION: before implementing any fix, create a script to reproduce and verify the issue.
-   4.1 Look at existing test files in the repository to understand the test format/structure.
-   4.2 Create a minimal reproduction script that reproduces the located issue.
-   4.3 Run the reproduction script to confirm you are reproducing the issue.
-   4.4 Adjust the reproduction script as necessary.
+4. IMPLEMENTATION: Edit the source code to implement your chosen solution.
+   - Make minimal, focused changes to fix the issue
 
-Phase 5. FIX ANALYSIS: state clearly the problem and how to fix it
-   5.1 State clearly what the problem is.
-   5.2 State clearly where the problem is located.
-   5.3 State clearly how the test reproduces the issue.
-   5.4 State clearly the best practices to take into account in the fix.
-   5.5 State clearly how to fix the problem.
+5. VERIFICATION: Test your implementation thoroughly.
+   - Run your reproduction script to verify the fix works
+   - Add edge cases to your test script to ensure comprehensive coverage
+   - Run existing tests related to the modified code to ensure you haven't broken anything
 
-Phase 6. FIX IMPLEMENTATION: Edit the source code to implement your chosen solution.
-   6.1 Make minimal, focused changes to fix the issue.
-
-Phase 7. VERIFICATION: Test your implementation thoroughly.
-   7.1 Run your reproduction script to verify the fix works.
-   7.2 Add edge cases to your test script to ensure comprehensive coverage.
-   7.3 Run existing tests related to the modified code to ensure you haven't broken anything.
-
-8. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {instance["base_commit"]}.
-   8.1 Ensure you've fully addressed all requirements.
-   8.2 Run any tests in the repository related to:
-     8.2.1 The issue you are fixing
-     8.2.2 The files you modified
-     8.2.3 The functions you changed
-   8.3 If any tests fail, revise your implementation until all tests pass
+6. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {instance["base_commit"]}.
+   - Ensure you've fully addressed all requirements
+   - Run any tests in the repository related to:
+     * The issue you are fixing
+     * The files you modified
+     * The functions you changed
+   - If any tests fail, revise your implementation until all tests pass
 
 Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.
 """
@@ -179,7 +121,7 @@ Be thorough in your exploration, testing, and reasoning. It's fine if your think
         )
 
     if 'image_assets' in instance:
-        assets = json.loads(instance['image_assets'])
+        assets = instance['image_assets']
         assert (
             'problem_statement' in assets
         ), 'problem_statement is required in image_assets'
@@ -204,8 +146,8 @@ def get_instance_docker_image(
         # swebench/sweb.eval.x86_64.django_1776_django-11333:v1
         docker_image_prefix = 'docker.io/swebench/'
         repo, name = instance_id.split('__')
-        image_name = f'swebench/sweb.eval.x86_64.{repo}_1776_{name}:latest'.lower()
-        logger.debug(f'Using official SWE-Bench image: {image_name}')
+        image_name = f'swebench/sweb.eval.x86_64.{repo}_1776_{name}:latest'
+        logger.info(f'Using official SWE-Bench image: {image_name}')
         return image_name
     else:
         # OpenHands version of the image
@@ -222,7 +164,10 @@ def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
     # We use a different instance image for the each instance of swe-bench eval
-    use_swebench_official_image = 'swe-gym' not in metadata.dataset.lower()
+    use_swebench_official_image = bool(
+        ('verified' in metadata.dataset.lower() or 'lite' in metadata.dataset.lower())
+        and 'swe-gym' not in metadata.dataset.lower()
+    )
     base_container_image = get_instance_docker_image(
         instance['instance_id'],
         swebench_official_image=use_swebench_official_image,
@@ -260,9 +205,9 @@ def get_config(
         )
     )
     agent_config = AgentConfig(
-        enable_jupyter=False,
-        enable_browsing=RUN_WITH_BROWSING,
-        enable_llm_editor=False,
+        codeact_enable_jupyter=False,
+        codeact_enable_browsing=RUN_WITH_BROWSING,
+        codeact_enable_llm_editor=False,
         condenser=metadata.condenser_config,
         enable_prompt_extensions=False,
     )
@@ -273,7 +218,6 @@ def get_config(
 def initialize_runtime(
     runtime: Runtime,
     instance: pd.Series,  # this argument is not required
-    metadata: EvalMetadata,
 ):
     """Initialize the runtime for the agent.
 
@@ -285,17 +229,16 @@ def initialize_runtime(
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
     obs: CmdOutputObservation
 
-    # Set instance id and git configuration
+    # Set instance id
     action = CmdRunAction(
-        command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc && git config --global core.pager "" && git config --global diff.binary false"""
+        command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc"""
     )
     action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to export SWE_INSTANCE_ID and configure git: {str(obs)}',
+        obs.exit_code == 0, f'Failed to export SWE_INSTANCE_ID: {str(obs)}'
     )
 
     action = CmdRunAction(command="""export USER=$(whoami); echo USER=${USER} """)
@@ -391,42 +334,15 @@ def initialize_runtime(
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
 
-    if metadata.details['mode'] == 'swt-ci':
-        # set up repo
-        setup_commands = []
-        if instance['repo'] in MAP_REPO_TO_INSTALL:
-            setup_commands.append(MAP_REPO_TO_INSTALL[instance['repo']])
-
-        # Run pre-install set up if provided
-        install = MAP_VERSION_TO_INSTALL.get(instance['repo'], {}).get(
-            instance['version'], []
-        )
-        if 'pre_install' in install:
-            for pre_install in install['pre_install']:
-                setup_commands.append(pre_install)
-
-        if 'install' in install:
-            setup_commands.append(install['install'])
-
-        for command in setup_commands:
-            action = CmdRunAction(command=command)
-            action.set_hard_timeout(600)
-            logger.info(action, extra={'msg_type': 'ACTION'})
-            obs = runtime.run_action(action)
-            logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-
-    if 'multimodal' not in metadata.dataset.lower():
-        # Only for non-multimodal datasets, we need to activate the testbed environment for Python
-        # SWE-Bench multimodal datasets are not using the testbed environment
-        action = CmdRunAction(command='which python')
-        action.set_hard_timeout(600)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-        assert_and_raise(
-            obs.exit_code == 0 and 'testbed' in obs.content,
-            f'Expected to find python interpreter from testbed, but got: {str(obs)}',
-        )
+    action = CmdRunAction(command='which python')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0 and 'testbed' in obs.content,
+        f'Expected to find python interpreter from testbed, but got: {str(obs)}',
+    )
 
     logger.info('-' * 30)
     logger.info('END Runtime Initialization Fn')
@@ -470,21 +386,6 @@ def complete_runtime(
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
 
-    if obs.exit_code == -1:
-        # The previous command is still running
-        # We need to kill previous command
-        logger.info('The previous command is still running, trying to ctrl+z it...')
-        action = CmdRunAction(command='C-z')
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-
-        # Then run the command again
-        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-        action.set_hard_timeout(600)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-
     assert_and_raise(
         isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
         f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
@@ -536,22 +437,11 @@ def complete_runtime(
         f'Failed to git add -A: {str(obs)}',
     )
 
-    # Remove binary files from git staging
-    action = CmdRunAction(command=remove_binary_files_from_git())
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-        f'Failed to remove binary files: {str(obs)}',
-    )
-
     n_retries = 0
     git_patch = None
     while n_retries < 5:
         action = CmdRunAction(
-            command=f'git diff --no-color --cached {instance["base_commit"]} > patch.diff'
+            command=f'git diff --no-color --cached {instance["base_commit"]}'
         )
         action.set_hard_timeout(max(300 + 100 * n_retries, 600))
         logger.info(action, extra={'msg_type': 'ACTION'})
@@ -560,28 +450,8 @@ def complete_runtime(
         n_retries += 1
         if isinstance(obs, CmdOutputObservation):
             if obs.exit_code == 0:
-                # Read the patch file
-                action = FileReadAction(path='patch.diff')
-                action.set_hard_timeout(max(300 + 100 * n_retries, 600))
-                logger.info(action, extra={'msg_type': 'ACTION'})
-                obs = runtime.run_action(action)
-                logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-                if isinstance(obs, FileReadObservation):
-                    git_patch = obs.content
-                    break
-                elif isinstance(obs, ErrorObservation):
-                    # Fall back to cat "patch.diff" to get the patch
-                    assert 'File could not be decoded as utf-8' in obs.content
-                    action = CmdRunAction(command='cat patch.diff')
-                    action.set_hard_timeout(max(300 + 100 * n_retries, 600))
-                    logger.info(action, extra={'msg_type': 'ACTION'})
-                    obs = runtime.run_action(action)
-                    assert isinstance(obs, CmdOutputObservation) and obs.exit_code == 0
-                    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-                    git_patch = obs.content
-                    break
-                else:
-                    assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
+                git_patch = obs.content.strip()
+                break
             else:
                 logger.info('Failed to get git diff, retrying...')
                 sleep_if_should_continue(10)
@@ -593,9 +463,6 @@ def complete_runtime(
 
     assert_and_raise(git_patch is not None, 'Failed to get git diff (None)')
 
-    # Remove binary diffs from the patch
-    git_patch = remove_binary_diffs(git_patch)
-
     logger.info('-' * 30)
     logger.info('END Runtime Completion Fn')
     logger.info('-' * 30)
@@ -637,7 +504,7 @@ def process_instance(
     call_async_from_sync(runtime.connect)
 
     try:
-        initialize_runtime(runtime, instance, metadata)
+        initialize_runtime(runtime, instance)
 
         message_action = get_instruction(instance, metadata)
 
@@ -737,13 +604,6 @@ if __name__ == '__main__':
         default='test',
         help='split to evaluate on',
     )
-    parser.add_argument(
-        '--mode',
-        type=str,
-        default='swe',
-        choices=['swe', 'swt', 'swt-ci'],
-        help="mode to run the evaluation, either 'swe', 'swt', or 'swt-ci'",
-    )
     args, _ = parser.parse_known_args()
 
     # NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
@@ -780,7 +640,7 @@ if __name__ == '__main__':
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 
-    details = {'mode': args.mode}
+    details = {}
     _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
 
     dataset_descrption = (
@@ -886,19 +746,9 @@ if __name__ == '__main__':
             with open(cur_output_file, 'r') as f:
                 for line in f:
                     instance = json.loads(line)
-                    try:
-                        history = [
-                            event_from_dict(event) for event in instance['history']
-                        ]
-                        critic_result = critic.evaluate(
-                            history, instance['test_result'].get('git_patch', '')
-                        )
-                        if not critic_result.success:
-                            instances_failed.append(instance['instance_id'])
-                    except Exception as e:
-                        logger.error(
-                            f'Error loading history for instance {instance["instance_id"]}: {e}'
-                        )
+                    history = [event_from_dict(event) for event in instance['history']]
+                    critic_result = critic.evaluate(history)
+                    if not critic_result.success:
                         instances_failed.append(instance['instance_id'])
             logger.info(
                 f'{len(instances_failed)} instances failed the current attempt {attempt}: {instances_failed}'
@@ -927,11 +777,7 @@ if __name__ == '__main__':
             with open(cur_output_file, 'r') as f:
                 for line in f:
                     instance = json.loads(line)
-                    # Also make sure git_patch is not empty - otherwise we fall back to previous attempt (empty patch is worse than anything else)
-                    if (
-                        instance['instance_id'] not in added_instance_ids
-                        and instance['test_result'].get('git_patch', '').strip()
-                    ):
+                    if instance['instance_id'] not in added_instance_ids:
                         fout.write(line)
                         added_instance_ids.add(instance['instance_id'])
             logger.info(

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

@@ -12,7 +12,6 @@ NUM_WORKERS=$6
 DATASET=$7
 SPLIT=$8
 N_RUNS=$9
-MODE=${10}
 
 if [ -z "$NUM_WORKERS" ]; then
   NUM_WORKERS=1
@@ -46,11 +45,6 @@ if [ -z "$SPLIT" ]; then
   SPLIT="test"
 fi
 
-if [ -z "$MODE" ]; then
-  MODE="swe"
-  echo "MODE not specified, use default $MODE"
-fi
-
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 
@@ -61,10 +55,6 @@ echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "DATASET: $DATASET"
 echo "SPLIT: $SPLIT"
-echo "MAX_ITER: $MAX_ITER"
-echo "NUM_WORKERS: $NUM_WORKERS"
-echo "COMMIT_HASH: $COMMIT_HASH"
-echo "MODE: $MODE"
 
 # Default to NOT use Hint
 if [ -z "$USE_HINT_TEXT" ]; then
@@ -84,13 +74,9 @@ fi
 if [ -n "$EXP_NAME" ]; then
   EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
 fi
-# if mode != swe, add mode to the eval note
-if [ "$MODE" != "swe" ]; then
-  EVAL_NOTE="${EVAL_NOTE}-${MODE}"
-fi
 
 function run_eval() {
-  local eval_note="${1}"
+  local eval_note=$1
   COMMAND="poetry run python evaluation/benchmarks/swe_bench/run_infer.py \
     --agent-cls $AGENT \
     --llm-config $MODEL_CONFIG \
@@ -98,8 +84,7 @@ function run_eval() {
     --eval-num-workers $NUM_WORKERS \
     --eval-note $eval_note \
     --dataset $DATASET \
-    --split $SPLIT \
-    --mode $MODE"
+    --split $SPLIT"
 
   if [ -n "$EVAL_LIMIT" ]; then
     echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/swe_bench/scripts/setup/instance_swe_entry.sh

@@ -18,7 +18,6 @@ if [[ -z "$item" ]]; then
   exit 1
 fi
 
-
 WORKSPACE_NAME=$(echo "$item" | jq -r '(.repo | tostring) + "__" + (.version | tostring) | gsub("/"; "__")')
 
 echo "WORKSPACE_NAME: $WORKSPACE_NAME"
@@ -37,7 +36,5 @@ mkdir -p /workspace
 cp -r /testbed /workspace/$WORKSPACE_NAME
 
 # Activate instance-specific environment
-if [ -d /opt/miniconda3 ]; then
-    . /opt/miniconda3/etc/profile.d/conda.sh
-    conda activate testbed
-fi
+. /opt/miniconda3/etc/profile.d/conda.sh
+conda activate testbed

evaluation/benchmarks/swe_bench/scripts/swtbench/convert.py

@@ -1,95 +0,0 @@
-import argparse
-import json
-import logging
-
-import unidiff
-
-from evaluation.benchmarks.swe_bench.resource.swt_bench_constants import (
-    MAP_VERSION_TO_INSTALL,
-)
-
-_LOGGER = logging.getLogger(__name__)
-
-
-def remove_setup_files(model_patch: str, instance: dict, delete_setup_changes: bool):
-    """Discard all changes that a patch applies to files changes by the pre_install script and that are reproduction scripts (top-level script)"""
-    setup_files = ['setup.py', 'tox.ini', 'pyproject.toml']
-    pre_install = (
-        MAP_VERSION_TO_INSTALL.get(instance['repo'], {})
-        .get(instance['version'], {})
-        .get('pre_install', [])
-    )
-    relevant_files = (
-        [
-            file
-            for file in setup_files
-            if any(file in install and 'sed' in install for install in pre_install)
-        ]
-        if delete_setup_changes
-        else []
-    )
-    for i in range(10):
-        try:
-            # Appearently outputs.jsonl has .strip() applied, so we try to reconstruct the original patch by adding auxiliary whitespace
-            patch = unidiff.PatchSet(model_patch + i * '\n')
-            break
-        except unidiff.UnidiffParseError:
-            pass
-
-    to_delete = []
-    for i, file in enumerate(patch):
-        if (
-            any(f in file.source_file for f in relevant_files)
-            or file.target_file.count('/') == 1
-        ):
-            to_delete.append(i)
-    for i in reversed(to_delete):
-        del patch[i]
-    return str(patch)
-
-
-def main(
-    prediction_file: str,
-):
-    """Main function to extract the model patches from the OpenHands prediction file and turn them into the expected SWT-Bench format."""
-    with open(prediction_file) as f:
-        for line in f:
-            pred = json.loads(line)
-            try:
-                git_diff = pred['test_result']['git_patch']
-            except KeyError:
-                _LOGGER.warning(
-                    'Warning: No git diff found for instance %s', pred['instance_id']
-                )
-                continue
-            ci_mode = pred['metadata']['details'].get('mode', '') == 'swt-ci'
-            try:
-                git_diff = remove_setup_files(git_diff, pred['instance'], ci_mode)
-            except:  # noqa: E722
-                _LOGGER.warning(
-                    'Warning: Invalid git diff found for instance %s',
-                    pred['instance_id'],
-                )
-            print(
-                json.dumps(
-                    {
-                        'instance_id': pred['instance_id'],
-                        'model_name_or_path': f'{pred["metadata"]["llm_config"]["openrouter_app_name"]}__{pred["metadata"]["agent_class"]}__{pred["metadata"]["llm_config"]["model"]}',
-                        'model_patch': git_diff,
-                        'full_output': json.dumps(pred),
-                    }
-                )
-            )
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        '--prediction_file',
-        type=str,
-        required=True,
-        help='Path to the prediction file (.../outputs.jsonl)',
-    )
-    args = parser.parse_args()
-
-    main(args.prediction_file)

evaluation/benchmarks/testgeneval/run_infer.py

@@ -158,9 +158,9 @@ def get_config(
         )
     )
     agent_config = AgentConfig(
-        enable_jupyter=False,
-        enable_browsing=RUN_WITH_BROWSING,
-        enable_llm_editor=False,
+        codeact_enable_jupyter=False,
+        codeact_enable_browsing=RUN_WITH_BROWSING,
+        codeact_enable_llm_editor=False,
         condenser=metadata.condenser_config,
         enable_prompt_extensions=False,
     )

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -40,9 +40,6 @@ def get_config(
 ) -> AppConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = base_container_image
-    sandbox_config.enable_auto_lint = True
-    # If the web services are running on the host machine, this must be set to True
-    sandbox_config.use_host_network = True
     config = AppConfig(
         run_as_openhands=False,
         max_budget_per_task=4,

evaluation/benchmarks/the_agent_company/scripts/run_infer.sh

@@ -145,7 +145,7 @@ while IFS= read -r task_image; do
     docker pull $task_image
 
     # Build the Python command
-    COMMAND="poetry run python -m evaluation.benchmarks.the_agent_company.run_infer \
+    COMMAND="poetry run python run_infer.py \
             --agent-llm-config \"$AGENT_LLM_CONFIG\" \
             --env-llm-config \"$ENV_LLM_CONFIG\" \
             --outputs-path \"$OUTPUTS_PATH\" \