Complete fix for '[Errno 21] Is a directory' errors

- Fixed CLIRuntime.read() to check directories before binary file checks
- Added directory validation to all file reader functions (parse_pdf, parse_docx, parse_latex, parse_audio, parse_pptx, _base64_img)
- Moved directory/existence checks before any file operations to prevent raw errno 21 errors
- Enhanced unit tests to cover all file reader functions
- All functions now return user-friendly error messages instead of raw errno 21

This completely eliminates '[Errno 21] Is a directory' errors from the OpenHands CLI interface.

.github/CODEOWNERS

@@ -3,6 +3,7 @@
 
 # Frontend code owners
 /frontend/ @rbren @amanape
+/openhands-ui/ @amanape
 
 # Evaluation code owners
 /evaluation/ @xingyaoww @neubig

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -45,6 +45,13 @@ body:
       description: What version of OpenHands are you using?
       placeholder: ex. 0.9.8, main, etc.
 
+  - type: input
+    id: model-name
+    attributes:
+      label: Model Name
+      description: What model are you using?
+      placeholder: ex. gpt-4o, claude-3-5-sonnet, openrouter/deepseek-r1, etc.
+
   - type: dropdown
     id: os
     attributes:

.github/workflows/fe-unit-tests.yml

@@ -9,8 +9,8 @@ on:
       - main
   pull_request:
     paths:
-      - 'frontend/**'
-      -  '.github/workflows/fe-unit-tests.yml'
+      - "frontend/**"
+      - ".github/workflows/fe-unit-tests.yml"
 
 # 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:
@@ -24,7 +24,7 @@ jobs:
     runs-on: blacksmith-4vcpu-ubuntu-2204
     strategy:
       matrix:
-        node-version: [20, 22]
+        node-version: 22
       fail-fast: true
     steps:
       - name: Checkout
@@ -38,7 +38,7 @@ jobs:
         run: npm ci
       - name: Run TypeScript compilation
         working-directory: ./frontend
-        run: npm run make-i18n && tsc
+        run: npm run build
       - name: Run tests and collect coverage
         working-directory: ./frontend
         run: npm run test:coverage

.github/workflows/ghcr-build.yml

@@ -42,7 +42,6 @@ jobs:
             json=$(jq -n -c '[
                 { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" },
                 { image: "ubuntu:24.04", tag: "ubuntu" }
-
               ]')
           else
             json=$(jq -n -c '[
@@ -56,12 +55,10 @@ jobs:
   ghcr_build_app:
     name: Build App Image
     runs-on: blacksmith-4vcpu-ubuntu-2204
+    if: "!(github.event_name == 'push' && startsWith(github.ref, 'refs/tags/ext-v'))"
     permissions:
       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
         uses: actions/checkout@v4
@@ -87,24 +84,12 @@ jobs:
         if: "!github.event.pull_request.head.repo.fork"
         run: |
           ./containers/build.sh -i openhands -o ${{ env.REPO_OWNER }} --push
-      - name: Build app image
-        if: "github.event.pull_request.head.repo.fork"
-        run: |
-          ./containers/build.sh -i openhands -o ${{ env.REPO_OWNER }} --load
-      - name: Get hash in App Image
-        id: get_hash_in_app_image
-        run: |
-          # Run the build script in the app image
-          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${{ env.REPO_OWNER }}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
-          # Get the hash from the build script
-          hash_from_app_image=$(cat docker-outputs.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
-          echo "hash_from_app_image=$hash_from_app_image" >> $GITHUB_OUTPUT
-          echo "Hash from app image: $hash_from_app_image"
 
   # Builds the runtime Docker images
   ghcr_build_runtime:
     name: Build Image
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: blacksmith-8vcpu-ubuntu-2204
+    if: "!(github.event_name == 'push' && startsWith(github.ref, 'refs/tags/ext-v'))"
     permissions:
       contents: read
       packages: write
@@ -130,22 +115,13 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
+      - name: Install poetry via pipx
+        run: pipx install poetry
       - name: Set up Python
         uses: useblacksmith/setup-python@v6
         with:
           python-version: '3.12'
-      - name: Cache Poetry dependencies
-        uses: useblacksmith/cache@v5
-        with:
-          path: |
-            ~/.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: |
-            ${{ runner.os }}-poetry-
-      - name: Install poetry via pipx
-        run: pipx install poetry
+          cache: poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies POETRY_GROUP=main INSTALL_PLAYWRIGHT=0
       - name: Create source distribution and Dockerfile
@@ -190,61 +166,6 @@ jobs:
           name: runtime-src-${{ matrix.base_image.tag }}
           path: containers/runtime
 
-  verify_hash_equivalence_in_runtime_and_app:
-    name: Verify Hash Equivalence in Runtime and Docker images
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    needs: [ghcr_build_runtime, ghcr_build_app]
-    strategy:
-      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:
-          ref: ${{ github.event.pull_request.head.sha }}
-      - name: Cache Poetry dependencies
-        uses: useblacksmith/cache@v5
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          lookup-only: true
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Set up Python
-        uses: useblacksmith/setup-python@v6
-        with:
-          python-version: '3.12'
-      - 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
-      - name: Get hash in App Image
-        run: |
-          echo "Hash from app image: ${{ needs.ghcr_build_app.outputs.hash_from_app_image }}"
-          echo "hash_from_app_image=${{ needs.ghcr_build_app.outputs.hash_from_app_image }}" >> $GITHUB_ENV
-
-      - name: Get hash using code (development mode)
-        run: |
-          mkdir -p containers/runtime
-          poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild > output.txt 2>&1
-          hash_from_code=$(cat output.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
-          echo "hash_from_code=$hash_from_code" >> $GITHUB_ENV
-
-      - name: Compare hashes
-        run: |
-          echo "Hash from App Image: ${{ env.hash_from_app_image }}"
-          echo "Hash from Code: ${{ env.hash_from_code }}"
-          if [ "${{ env.hash_from_app_image }}" = "${{ env.hash_from_code }}" ]; then
-            echo "Hashes match!"
-          else
-            echo "Hashes do not match!"
-            exit 1
-          fi
-
   # Run unit tests with the Docker runtime Docker images as root
   test_runtime_root:
     name: RT Unit Tests (Root)
@@ -276,25 +197,17 @@ jobs:
           load: true
           tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
           context: containers/runtime
-      - name: Cache Poetry dependencies
-        uses: useblacksmith/cache@v5
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          lookup-only: true
-          restore-keys: |
-            ${{ runner.os }}-poetry-
+      - name: Install poetry via pipx
+        run: pipx install poetry
       - name: Set up Python
         uses: useblacksmith/setup-python@v6
         with:
           python-version: '3.12'
-      - name: Install poetry via pipx
-        run: pipx install poetry
+          cache: poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies INSTALL_PLAYWRIGHT=0
       - name: Run docker runtime tests
+        shell: bash
         run: |
           # We install pytest-xdist in order to run tests across CPUs
           poetry run pip install pytest-xdist
@@ -346,25 +259,17 @@ jobs:
           load: true
           tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
           context: containers/runtime
-      - name: Cache Poetry dependencies
-        uses: useblacksmith/cache@v5
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          lookup-only: true
-          restore-keys: |
-            ${{ runner.os }}-poetry-
+      - name: Install poetry via pipx
+        run: pipx install poetry
       - name: Set up Python
         uses: useblacksmith/setup-python@v6
         with:
           python-version: '3.12'
-      - name: Install poetry via pipx
-        run: pipx install poetry
+          cache: poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies POETRY_GROUP=main,test,runtime INSTALL_PLAYWRIGHT=0
       - name: Run runtime tests
+        shell: bash
         run: |
           # We install pytest-xdist in order to run tests across CPUs
           poetry run pip install pytest-xdist
@@ -391,7 +296,7 @@ jobs:
     name: All Runtime Tests Passed
     if: ${{ !cancelled() && !contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') }}
     runs-on: blacksmith-4vcpu-ubuntu-2204
-    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
+    needs: [test_runtime_root, test_runtime_oh]
     steps:
       - name: All tests passed
         run: echo "All runtime tests have passed successfully!"
@@ -400,7 +305,7 @@ jobs:
     name: All Runtime Tests Passed
     if: ${{ cancelled() || contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') }}
     runs-on: blacksmith-4vcpu-ubuntu-2204
-    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
+    needs: [test_runtime_root, test_runtime_oh]
     steps:
       - name: Some tests failed
         run: |
@@ -425,6 +330,7 @@ jobs:
           PR_NUMBER: ${{ github.event.pull_request.number }}
           REPO: ${{ github.repository }}
           SHORT_SHA: ${{ steps.short_sha.outputs.SHORT_SHA }}
+        shell: bash
         run: |
           echo "updating PR description"
           DOCKER_RUN_COMMAND="docker run -it --rm \

.github/workflows/integration-runner.yml

@@ -54,7 +54,7 @@ jobs:
             Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
 
       - name: Install Python dependencies using Poetry
-        run: poetry install --with dev,test,runtime
+        run: poetry install --with dev,test,runtime,evaluation
 
       - name: Configure config.toml for testing with Haiku
         env:
@@ -179,8 +179,8 @@ jobs:
         id: create_comment
         uses: KeisukeYamashita/create-comment@v1
         with:
-          # if triggered by PR, use PR number, otherwise use 5318 as fallback issue number for manual triggers
-          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 5318 }}
+          # if triggered by PR, use PR number, otherwise use 9745 as fallback issue number for manual triggers
+          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 9745 }}
           unique: false
           comment: |
               Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (integration-test label on PR #{0})', github.event.pull_request.number) || (github.event_name == 'workflow_dispatch' && format('Manual Trigger: {0}', github.event.inputs.reason)) || 'Nightly Scheduled Run' }}

.github/workflows/lint-fix.yml

@@ -21,10 +21,10 @@ jobs:
           fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Install Node.js 20
+      - name: Install Node.js 22
         uses: useblacksmith/setup-node@v5
         with:
-          node-version: 20
+          node-version: 22
       - name: Install frontend dependencies
         run: |
           cd frontend
@@ -68,7 +68,7 @@ jobs:
         uses: useblacksmith/setup-python@v6
         with:
           python-version: 3.12
-          cache: 'pip'
+          cache: "pip"
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Fix python lint issues

.github/workflows/lint.yml

@@ -7,7 +7,7 @@ name: Lint
 on:
   push:
     branches:
-    - main
+      - 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
@@ -22,10 +22,10 @@ jobs:
     runs-on: blacksmith-4vcpu-ubuntu-2204
     steps:
       - uses: actions/checkout@v4
-      - name: Install Node.js 20
+      - name: Install Node.js 22
         uses: useblacksmith/setup-node@v5
         with:
-          node-version: 20
+          node-version: 22
       - name: Install dependencies
         run: |
           cd frontend
@@ -49,7 +49,7 @@ jobs:
         uses: useblacksmith/setup-python@v6
         with:
           python-version: 3.12
-          cache: 'pip'
+          cache: "pip"
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks

.github/workflows/npm-publish-ui.yml

@@ -0,0 +1,108 @@
+name: Publish OpenHands UI Package
+
+# * Always run on "main"
+# * Run on PRs that have changes in the "openhands-ui" folder or this workflow
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "openhands-ui/**"
+      - ".github/workflows/npm-publish-ui.yml"
+
+# 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: npm-publish-ui
+  cancel-in-progress: false
+
+jobs:
+  check-version:
+    name: Check if version has changed
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    defaults:
+      run:
+        shell: bash
+    outputs:
+      should-publish: ${{ steps.version-check.outputs.should-publish }}
+      current-version: ${{ steps.version-check.outputs.current-version }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 2 # Need previous commit to compare
+
+      - name: Check if version changed
+        id: version-check
+        run: |
+          # Get current version from package.json
+          CURRENT_VERSION=$(jq -r .version openhands-ui/package.json)
+          echo "current-version=$CURRENT_VERSION" >> $GITHUB_OUTPUT
+
+          # Check if package.json version changed in this commit
+          if git diff HEAD~1 HEAD --name-only | grep -q "openhands-ui/package.json"; then
+            # Check if the version field specifically changed
+            if git diff HEAD~1 HEAD openhands-ui/package.json | grep -q '"version"'; then
+              echo "Version changed in package.json, will publish"
+              echo "should-publish=true" >> $GITHUB_OUTPUT
+            else
+              echo "package.json changed but version did not change, skipping publish"
+              echo "should-publish=false" >> $GITHUB_OUTPUT
+            fi
+          else
+            echo "package.json did not change, skipping publish"
+            echo "should-publish=false" >> $GITHUB_OUTPUT
+          fi
+
+  publish:
+    name: Publish to npm
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    needs: check-version
+    if: needs.check-version.outputs.should-publish == 'true'
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version-file: "openhands-ui/.bun-version"
+
+      - name: Install dependencies
+        working-directory: ./openhands-ui
+        run: bun install --frozen-lockfile
+
+      - name: Build package
+        working-directory: ./openhands-ui
+        run: bun run build
+
+      - name: Check if package already exists on npm
+        id: npm-check
+        working-directory: ./openhands-ui
+        run: |
+          PACKAGE_NAME=$(jq -r .name package.json)
+          VERSION="${{ needs.check-version.outputs.current-version }}"
+
+          # Check if this version already exists on npm
+          if npm view "$PACKAGE_NAME@$VERSION" version 2>/dev/null; then
+            echo "Version $VERSION already exists on npm, skipping publish"
+            echo "already-exists=true" >> $GITHUB_OUTPUT
+          else
+            echo "Version $VERSION does not exist on npm, proceeding with publish"
+            echo "already-exists=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Setup npm authentication
+        if: steps.npm-check.outputs.already-exists == 'false'
+        run: |
+          echo "//registry.npmjs.org/:_authToken=${{ secrets.NPM_TOKEN }}" > ~/.npmrc
+
+      - name: Publish to npm
+        if: steps.npm-check.outputs.already-exists == 'false'
+        working-directory: ./openhands-ui
+        run: |
+          # The prepublishOnly script will run automatically and build the package
+          npm publish
+          echo "✅ Successfully published @openhands/ui@${{ needs.check-version.outputs.current-version }} to npm"

.github/workflows/py-tests.yml

@@ -1,5 +1,5 @@
-# Workflow that runs python unit tests
-name: Run Python Unit Tests
+# Workflow that runs python tests
+name: Run Python Tests
 
 # The jobs in this workflow are required, so they must run at all times
 # * Always run on "main"
@@ -16,9 +16,9 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  # Run python unit tests on Linux
+  # Run python tests on Linux
   test-on-linux:
-    name: Python Unit Tests on Linux
+    name: Python Tests on Linux
     runs-on: blacksmith-4vcpu-ubuntu-2204
     env:
       INSTALL_DOCKER: '0' # Set to '0' to skip Docker installation
@@ -51,6 +51,8 @@ jobs:
         run: poetry run pytest --forked -n auto -svv ./tests/unit
       - name: Run Runtime Tests with CLIRuntime
         run: TEST_RUNTIME=cli poetry run pytest -svv tests/runtime/test_bash.py
+      - name: Run E2E Tests
+        run: poetry run pytest -svv tests/e2e
 
   # Run specific Windows python tests
   test-on-windows:

.github/workflows/run-eval.yml

@@ -1,56 +1,135 @@
-# Run evaluation on a PR
+# Run evaluation on a PR, after releases, or manually
 name: Run Eval
 
-# Runs when a PR is labeled with one of the "run-eval-" labels
+# Runs when a PR is labeled with one of the "run-eval-" labels, after releases, or manually triggered
 on:
   pull_request:
     types: [labeled]
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to evaluate'
+        required: true
+        default: 'main'
+      eval_instances:
+        description: 'Number of evaluation instances'
+        required: true
+        default: '50'
+        type: choice
+        options:
+          - '1'
+          - '2'
+          - '50'
+          - '100'
+      reason:
+        description: 'Reason for manual trigger'
+        required: false
+        default: ''
+
+env:
+  # Environment variable for the master GitHub issue number where all evaluation results will be commented
+  # This should be set to the issue number where you want all evaluation results to be posted
+  MASTER_EVAL_ISSUE_NUMBER: ${{ vars.MASTER_EVAL_ISSUE_NUMBER || '0' }}
 
 jobs:
   trigger-job:
     name: Trigger remote eval job
-    if: ${{ github.event.label.name == 'run-eval-1' || github.event.label.name == 'run-eval-2' || github.event.label.name == 'run-eval-50' || github.event.label.name == 'run-eval-100' }}
+    if: ${{ (github.event_name == 'pull_request' && (github.event.label.name == 'run-eval-1' || github.event.label.name == 'run-eval-2' || github.event.label.name == 'run-eval-50' || github.event.label.name == 'run-eval-100')) || github.event_name == 'release' || github.event_name == 'workflow_dispatch' }}
     runs-on: blacksmith-4vcpu-ubuntu-2204
 
     steps:
-      - name: Checkout PR branch
+      - name: Checkout branch
         uses: actions/checkout@v4
         with:
-          ref: ${{ github.head_ref }}
+          ref: ${{ github.event_name == 'pull_request' && github.head_ref || (github.event_name == 'workflow_dispatch' && github.event.inputs.branch) || github.ref }}
 
-      - name: Trigger remote job
-        env:
-          PR_BRANCH: ${{ github.head_ref }}
+      - name: Set evaluation parameters
+        id: eval_params
         run: |
           REPO_URL="https://github.com/${{ github.repository }}"
           echo "Repository URL: $REPO_URL"
-          echo "PR Branch: $PR_BRANCH"
 
-          if [[ "${{ github.event.label.name }}" == "run-eval-1" ]]; then
-            EVAL_INSTANCES="1"
-          elif [[ "${{ github.event.label.name }}" == "run-eval-2" ]]; then
-            EVAL_INSTANCES="2"
-          elif [[ "${{ github.event.label.name }}" == "run-eval-50" ]]; then
+          # Determine branch based on trigger type
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            EVAL_BRANCH="${{ github.head_ref }}"
+            echo "PR Branch: $EVAL_BRANCH"
+          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            EVAL_BRANCH="${{ github.event.inputs.branch }}"
+            echo "Manual Branch: $EVAL_BRANCH"
+          else
+            # For release events, use the tag name or main branch
+            EVAL_BRANCH="${{ github.ref_name }}"
+            echo "Release Branch/Tag: $EVAL_BRANCH"
+          fi
+
+          # Determine evaluation instances based on trigger type
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            if [[ "${{ github.event.label.name }}" == "run-eval-1" ]]; then
+              EVAL_INSTANCES="1"
+            elif [[ "${{ github.event.label.name }}" == "run-eval-2" ]]; then
+              EVAL_INSTANCES="2"
+            elif [[ "${{ github.event.label.name }}" == "run-eval-50" ]]; then
+              EVAL_INSTANCES="50"
+            elif [[ "${{ github.event.label.name }}" == "run-eval-100" ]]; then
+              EVAL_INSTANCES="100"
+            fi
+          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            EVAL_INSTANCES="${{ github.event.inputs.eval_instances }}"
+          else
+            # For release events, default to 50 instances
             EVAL_INSTANCES="50"
-          elif [[ "${{ github.event.label.name }}" == "run-eval-100" ]]; then
-            EVAL_INSTANCES="100"
+          fi
+
+          echo "Evaluation instances: $EVAL_INSTANCES"
+          echo "repo_url=$REPO_URL" >> $GITHUB_OUTPUT
+          echo "eval_branch=$EVAL_BRANCH" >> $GITHUB_OUTPUT
+          echo "eval_instances=$EVAL_INSTANCES" >> $GITHUB_OUTPUT
+
+      - name: Trigger remote job
+        run: |
+          # Determine PR number for the remote evaluation system
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            PR_NUMBER="${{ github.event.pull_request.number }}"
+          else
+            # For non-PR triggers, use the master issue number as PR number
+            PR_NUMBER="${{ env.MASTER_EVAL_ISSUE_NUMBER }}"
           fi
 
           curl -X POST \
             -H "Authorization: Bearer ${{ secrets.PAT_TOKEN }}" \
             -H "Accept: application/vnd.github+json" \
-            -d "{\"ref\": \"main\", \"inputs\": {\"github-repo\": \"${REPO_URL}\", \"github-branch\": \"${PR_BRANCH}\", \"pr-number\": \"${{ github.event.pull_request.number }}\", \"eval-instances\": \"${EVAL_INSTANCES}\"}}" \
+            -d "{\"ref\": \"main\", \"inputs\": {\"github-repo\": \"${{ steps.eval_params.outputs.repo_url }}\", \"github-branch\": \"${{ steps.eval_params.outputs.eval_branch }}\", \"pr-number\": \"${PR_NUMBER}\", \"eval-instances\": \"${{ steps.eval_params.outputs.eval_instances }}\"}}" \
             https://api.github.com/repos/All-Hands-AI/evaluation/actions/workflows/create-branch.yml/dispatches
 
           # Send Slack message
-          PR_URL="https://github.com/${{ github.repository }}/pull/${{ github.event.pull_request.number }}"
-          slack_text="PR $PR_URL has triggered evaluation on $EVAL_INSTANCES instances..."
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            TRIGGER_URL="https://github.com/${{ github.repository }}/pull/${{ github.event.pull_request.number }}"
+            slack_text="PR $TRIGGER_URL has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances..."
+          elif [[ "${{ github.event_name }}" == "release" ]]; then
+            TRIGGER_URL="https://github.com/${{ github.repository }}/releases/tag/${{ github.ref_name }}"
+            slack_text="Release $TRIGGER_URL has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances..."
+          else
+            TRIGGER_URL="https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"
+            slack_text="Manual trigger (${{ github.event.inputs.reason || 'No reason provided' }}) has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances for branch ${{ steps.eval_params.outputs.eval_branch }}..."
+          fi
+
           curl -X POST -H 'Content-type: application/json' --data '{"text":"'"$slack_text"'"}' \
             https://hooks.slack.com/services/${{ secrets.SLACK_TOKEN }}
 
-      - name: Comment on PR
+      - name: Comment on issue/PR
         uses: KeisukeYamashita/create-comment@v1
         with:
+          # For PR triggers, comment on the PR. For other triggers, comment on the master issue
+          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || env.MASTER_EVAL_ISSUE_NUMBER }}
           unique: false
           comment: |
-            Running evaluation on the PR. Once eval is done, the results will be posted.
+            **Evaluation Triggered**
+
+            **Trigger:** ${{ github.event_name == 'pull_request' && format('Pull Request #{0}', github.event.pull_request.number) || (github.event_name == 'release' && 'Release') || format('Manual Trigger: {0}', github.event.inputs.reason || 'No reason provided') }}
+            **Branch:** ${{ steps.eval_params.outputs.eval_branch }}
+            **Instances:** ${{ steps.eval_params.outputs.eval_instances }}
+            **Commit:** ${{ github.sha }}
+
+            Running evaluation on the specified branch. Once eval is done, the results will be posted here.

.github/workflows/stale.yml

@@ -15,7 +15,7 @@ jobs:
           stale-issue-message: 'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
           stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
           days-before-stale: 30
-          exempt-issue-labels: 'tracked'
+          exempt-issue-labels: 'roadmap'
           close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
           close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
           days-before-close: 7

.github/workflows/ui-build.yml

@@ -0,0 +1,34 @@
+name: Run UI Component Build
+
+# * Always run on "main"
+# * Run on PRs that have changes in the "openhands-ui" folder or this workflow
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths:
+      - 'openhands-ui/**'
+      -  '.github/workflows/ui-build.yml'
+
+# 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:
+  ui-build:
+    name: Build openhands-ui
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version-file: "openhands-ui/.bun-version"
+      - name: Install dependencies
+        working-directory: ./openhands-ui
+        run: bun install --frozen-lockfile
+      - name: Build package
+        working-directory:  ./openhands-ui
+        run: bun run build

.github/workflows/vscode-extension-build.yml

@@ -0,0 +1,156 @@
+# Workflow that validates the VSCode extension builds correctly
+name: VSCode Extension CI
+
+# * Always run on "main"
+# * Run on PRs that have changes in the VSCode extension folder or this workflow
+# * Run on tags that start with "ext-v"
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - 'ext-v*'
+  pull_request:
+    paths:
+      - 'openhands/integrations/vscode/**'
+      - 'build_vscode.py'
+      - '.github/workflows/vscode-extension-build.yml'
+
+# 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:
+  # Validate VSCode extension builds correctly
+  validate-vscode-extension:
+    name: Validate VSCode Extension Build
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: useblacksmith/setup-node@v5
+        with:
+          node-version: '22'
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install VSCode extension dependencies
+        working-directory: ./openhands/integrations/vscode
+        run: npm ci
+
+      - name: Build VSCode extension via build_vscode.py
+        run: python build_vscode.py
+        env:
+          # Ensure we don't skip the build
+          SKIP_VSCODE_BUILD: ""
+
+      - name: Validate .vsix file
+        run: |
+          # Verify the .vsix was created and is valid
+          if [ -f "openhands/integrations/vscode/openhands-vscode-0.0.1.vsix" ]; then
+            echo "✅ VSCode extension built successfully"
+            ls -la openhands/integrations/vscode/openhands-vscode-0.0.1.vsix
+
+            # Basic validation that the .vsix is a valid zip file
+            echo "🔍 Validating .vsix structure..."
+            file openhands/integrations/vscode/openhands-vscode-0.0.1.vsix
+            unzip -t openhands/integrations/vscode/openhands-vscode-0.0.1.vsix
+
+            echo "✅ VSCode extension validation passed"
+          else
+            echo "❌ VSCode extension build failed - .vsix not found"
+            exit 1
+          fi
+
+      - name: Upload VSCode extension artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: vscode-extension
+          path: openhands/integrations/vscode/openhands-vscode-0.0.1.vsix
+          retention-days: 7
+
+      - name: Comment on PR with artifact link
+        if: github.event_name == 'pull_request'
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const fs = require('fs');
+            const path = require('path');
+
+            // Get file size for display
+            const vsixPath = 'openhands/integrations/vscode/openhands-vscode-0.0.1.vsix';
+            const stats = fs.statSync(vsixPath);
+            const fileSizeKB = Math.round(stats.size / 1024);
+
+            const comment = `## 🔧 VSCode Extension Built Successfully!
+
+            The VSCode extension has been built and is ready for testing.
+
+            **📦 Download**: [openhands-vscode-0.0.1.vsix](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}) (${fileSizeKB} KB)
+
+            **🚀 To install**:
+            1. Download the artifact from the workflow run above
+            2. In VSCode: \`Ctrl+Shift+P\` → "Extensions: Install from VSIX..."
+            3. Select the downloaded \`.vsix\` file
+
+            **✅ Tested with**: Node.js 22
+            **🔍 Validation**: File structure and integrity verified
+
+            ---
+            *Built from commit ${{ github.sha }}*`;
+
+            // Check if we already commented on this PR and delete it
+            const { data: comments } = await github.rest.issues.listComments({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: context.issue.number,
+            });
+
+            const botComment = comments.find(comment =>
+              comment.user.login === 'github-actions[bot]' &&
+              comment.body.includes('VSCode Extension Built Successfully')
+            );
+
+            if (botComment) {
+              await github.rest.issues.deleteComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                comment_id: botComment.id,
+              });
+            }
+
+            // Create a new comment
+            await github.rest.issues.createComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: context.issue.number,
+              body: comment
+            });
+
+  release:
+    name: Create GitHub Release
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    needs: validate-vscode-extension
+    if: startsWith(github.ref, 'refs/tags/ext-v')
+
+    steps:
+      - name: Download .vsix artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: vscode-extension
+          path: ./
+
+      - name: Create Release
+        uses: ncipollo/release-action@v1.16.0
+        with:
+          artifacts: "*.vsix"
+          token: ${{ secrets.GITHUB_TOKEN }}
+          draft: true
+          allowUpdates: true

.gitignore

@@ -182,6 +182,8 @@ cython_debug/
 .roo/rules
 .cline/rules
 .windsurf/rules
+.repomix
+repomix-output.txt
 
 # evaluation
 evaluation/evaluation_outputs

.openhands/microagents/glossary.md

@@ -121,7 +121,7 @@ A specialized prompt that enhances OpenHands with domain-specific knowledge, rep
 A central repository of available microagents and their configurations.
 
 #### Public Microagent
-A general-purpose microagent available to all OpenHands users, triggered by specific keywords.
+A general-purpose microagent available to all OpenHands users, triggered by specific keywords. Located in `microagents/`.
 
 #### Repository Microagent
 A type of microagent that provides repository-specific context and guidelines, stored in the `.openhands/microagents/` directory.

.openhands/microagents/repo.md

@@ -19,6 +19,7 @@ Before pushing any changes, you MUST ensure that any lint errors or simple test
 
 * If you've made changes to the backend, you should run `pre-commit run --config ./dev_config/python/.pre-commit-config.yaml` (this will run on staged files).
 * If you've made changes to the frontend, you should run `cd frontend && npm run lint:fix && npm run build ; cd ..`
+* If you've made changes to the VSCode extension, you should run `cd openhands/integrations/vscode && npm run lint:fix && npm run compile ; cd ../../..`
 
 The pre-commit hooks MUST pass successfully before pushing any changes to the repository. This is a mandatory requirement to maintain code quality and consistency.
 
@@ -29,6 +30,12 @@ then re-run the command to ensure it passes. Common issues include:
 - Trailing whitespace
 - Missing newlines at end of files
 
+## Git Best Practices
+
+- Prefer specific `git add <filename>` instead of `git add .` to avoid accidentally staging unintended files
+- Be especially careful with `git reset --hard` after staging files, as it will remove accidentally staged files
+- When remote has new changes, use `git fetch upstream && git rebase upstream/<branch>` on the same branch
+
 ## Repository Structure
 Backend:
 - Located in the `openhands` directory
@@ -60,6 +67,22 @@ Frontend:
   - Mutation hooks should follow the pattern use[Action] (e.g., `useDeleteConversation`)
   - Architecture rule: UI components → TanStack Query hooks → Data Access Layer (`frontend/src/api`) → API endpoints
 
+VSCode Extension:
+- Located in the `openhands/integrations/vscode` directory
+- Setup: Run `npm install` in the extension directory
+- Linting:
+  - Run linting with fixes: `npm run lint:fix`
+  - Check only: `npm run lint`
+  - Type checking: `npm run typecheck`
+- Building:
+  - Compile TypeScript: `npm run compile`
+  - Package extension: `npm run package-vsix`
+- Testing:
+  - Run tests: `npm run test`
+- Development Best Practices:
+  - Use `vscode.window.createOutputChannel()` for debug logging instead of `showErrorMessage()` popups
+  - Pre-commit process runs both frontend and backend checks when committing extension changes
+
 ## Template for Github Pull Request
 
 If you are starting a pull request (PR), please follow the template in `.github/pull_request_template.md`.
@@ -68,6 +91,29 @@ If you are starting a pull request (PR), please follow the template in `.github/
 
 These details may or may not be useful for your current task.
 
+### Microagents
+
+Microagents are specialized prompts that enhance OpenHands with domain-specific knowledge and task-specific workflows. They are Markdown files that can include frontmatter for configuration.
+
+#### Types:
+- **Public Microagents**: Located in `microagents/`, available to all users
+- **Repository Microagents**: Located in `.openhands/microagents/`, specific to this repository
+
+#### Loading Behavior:
+- **Without frontmatter**: Always loaded into LLM context
+- **With triggers in frontmatter**: Only loaded when user's message matches the specified trigger keywords
+
+#### Structure:
+```yaml
+---
+triggers:
+- keyword1
+- keyword2
+---
+# Microagent Content
+Your specialized knowledge and instructions here...
+```
+
 ### Frontend
 
 #### Action Handling:
@@ -95,3 +141,65 @@ These details may or may not be useful for your current task.
   2. Add the setting to the backend:
      - Add the setting to the `Settings` model in `openhands/storage/data_models/settings.py`
      - Update any relevant backend code to apply the setting (e.g., in session creation)
+
+### Adding New LLM Models
+
+To add a new LLM model to OpenHands, you need to update multiple files across both frontend and backend:
+
+#### Model Configuration Procedure:
+
+1. **Frontend Model Arrays** (`frontend/src/utils/verified-models.ts`):
+   - Add the model to `VERIFIED_MODELS` array (main list of all verified models)
+   - Add to provider-specific arrays based on the model's provider:
+     - `VERIFIED_OPENAI_MODELS` for OpenAI models
+     - `VERIFIED_ANTHROPIC_MODELS` for Anthropic models
+     - `VERIFIED_MISTRAL_MODELS` for Mistral models
+     - `VERIFIED_OPENHANDS_MODELS` for models available through OpenHands provider
+
+2. **Backend CLI Integration** (`openhands/cli/utils.py`):
+   - Add the model to the appropriate `VERIFIED_*_MODELS` arrays
+   - This ensures the model appears in CLI model selection
+
+3. **Backend Model List** (`openhands/utils/llm.py`):
+   - **CRITICAL**: Add the model to the `openhands_models` list (lines 57-66) if using OpenHands provider
+   - This is required for the model to appear in the frontend model selector
+   - Format: `'openhands/model-name'` (e.g., `'openhands/o3'`)
+
+4. **Backend LLM Configuration** (`openhands/llm/llm.py`):
+   - Add to feature-specific arrays based on model capabilities:
+     - `FUNCTION_CALLING_SUPPORTED_MODELS` if the model supports function calling
+     - `REASONING_EFFORT_SUPPORTED_MODELS` if the model supports reasoning effort parameters
+     - `CACHE_PROMPT_SUPPORTED_MODELS` if the model supports prompt caching
+     - `MODELS_WITHOUT_STOP_WORDS` if the model doesn't support stop words
+
+5. **Validation**:
+   - Run backend linting: `pre-commit run --config ./dev_config/python/.pre-commit-config.yaml`
+   - Run frontend linting: `cd frontend && npm run lint:fix`
+   - Run frontend build: `cd frontend && npm run build`
+
+#### Model Verification Arrays:
+
+- **VERIFIED_MODELS**: Main array of all verified models shown in the UI
+- **VERIFIED_OPENAI_MODELS**: OpenAI models (LiteLLM doesn't return provider prefix)
+- **VERIFIED_ANTHROPIC_MODELS**: Anthropic models (LiteLLM doesn't return provider prefix)
+- **VERIFIED_MISTRAL_MODELS**: Mistral models (LiteLLM doesn't return provider prefix)
+- **VERIFIED_OPENHANDS_MODELS**: Models available through OpenHands managed provider
+
+#### Model Feature Support Arrays:
+
+- **FUNCTION_CALLING_SUPPORTED_MODELS**: Models that support structured function calling
+- **REASONING_EFFORT_SUPPORTED_MODELS**: Models that support reasoning effort parameters (like o1, o3)
+- **CACHE_PROMPT_SUPPORTED_MODELS**: Models that support prompt caching for efficiency
+- **MODELS_WITHOUT_STOP_WORDS**: Models that don't support stop word parameters
+
+#### Frontend Model Integration:
+
+- Models are automatically available in the model selector UI once added to verified arrays
+- The `extractModelAndProvider` utility automatically detects provider from model arrays
+- Provider-specific models are grouped and prioritized in the UI selection
+
+#### CLI Model Integration:
+
+- Models appear in CLI provider selection based on the verified arrays
+- The `organize_models_and_providers` function groups models by provider
+- Default model selection prioritizes verified models for each provider

.openhands/pre-commit.sh

@@ -1,29 +1,32 @@
 #!/bin/bash
 
 echo "Running OpenHands pre-commit hook..."
+echo "This hook runs 'make lint' to ensure code quality before committing."
 
 # Store the exit code to return at the end
 # This allows us to be additive to existing pre-commit hooks
 EXIT_CODE=0
 
+# Run make lint to check both frontend and backend code
+echo "Running linting checks with 'make lint'..."
+make lint
+if [ $? -ne 0 ]; then
+    echo "Linting failed. Please fix the issues before committing."
+    EXIT_CODE=1
+else
+    echo "Linting checks passed!"
+fi
+
 # Check if frontend directory has changed
 frontend_changes=$(git diff --cached --name-only | grep "^frontend/")
 if [ -n "$frontend_changes" ]; then
-    echo "Frontend changes detected. Running frontend checks..."
+    echo "Frontend changes detected. Running additional frontend checks..."
 
     # Check if frontend directory exists
     if [ -d "frontend" ]; then
         # Change to frontend directory
         cd frontend || exit 1
 
-        # Run lint:fix
-        echo "Running npm lint:fix..."
-        npm run lint:fix
-        if [ $? -ne 0 ]; then
-            echo "Frontend linting failed. Please fix the issues before committing."
-            EXIT_CODE=1
-        fi
-
         # Run build
         echo "Running npm build..."
         npm run build
@@ -50,7 +53,7 @@ if [ -n "$frontend_changes" ]; then
         echo "Frontend directory not found. Skipping frontend checks."
     fi
 else
-    echo "No frontend changes detected. Skipping frontend checks."
+    echo "No frontend changes detected. Skipping additional frontend checks."
 fi
 
 # Run any existing pre-commit hooks that might have been installed by the user

CONTRIBUTING.md

@@ -31,7 +31,7 @@ We're always looking to improve the look and feel of the application. If you've
 for something that's bugging you, feel free to open up a PR that changes the [`./frontend`](./frontend) directory.
 
 If you're looking to make a bigger change, add a new UI element, or significantly alter the style
-of the application, please open an issue first, or better, join the #frontend channel in our Slack
+of the application, please open an issue first, or better, join the #eng-ui-ux channel in our Slack
 to gather consensus from our design team first.
 
 #### Improving the agent

Development.md

@@ -159,7 +159,7 @@ 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:0.45-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.50-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -11,7 +11,7 @@
   <a href="https://github.com/All-Hands-AI/OpenHands/stargazers"><img src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Stargazers"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
   <br/>
-  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-34zm4j0gj-Qz5kRHoca8DFCbqXPS~f_A"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
   <br/>
@@ -62,17 +62,17 @@ system requirements and more information.
 
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.45
+    docker.all-hands.dev/all-hands-ai/openhands:0.50
 ```
 
 > **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
@@ -85,15 +85,14 @@ works best, but you have [many options](https://docs.all-hands.dev/usage/llms).
 
 ## 💡 Other ways to run OpenHands
 
-> [!CAUTION]
+> [!WARNING]
 > 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.
+> If you're interested in running OpenHands in a multi-tenant environment, check out the source-available, commercially-licensed
+> [OpenHands Cloud Helm Chart](https://github.com/all-Hands-AI/OpenHands-cloud)
 
-You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/usage/runtimes/docker#connecting-to-your-filesystem),
+You can [connect OpenHands to your local filesystem](https://docs.all-hands.dev/usage/runtimes/docker#connecting-to-your-filesystem),
 run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/usage/how-to/headless-mode),
 interact with it via a [friendly CLI](https://docs.all-hands.dev/usage/how-to/cli-mode),
 or run it on tagged issues with [a github action](https://docs.all-hands.dev/usage/how-to/github-action).
@@ -118,7 +117,7 @@ troubleshooting resources, and advanced configuration options.
 OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
 through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
 
-- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-34zm4j0gj-Qz5kRHoca8DFCbqXPS~f_A) - Here we talk about research, architecture, and future development.
+- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA) - Here we talk about research, architecture, and future development.
 - [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 - [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
 

README_CN.md

@@ -12,7 +12,7 @@
   <a href="https://github.com/All-Hands-AI/OpenHands/stargazers"><img src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Stargazers"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
   <br/>
-  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-34zm4j0gj-Qz5kRHoca8DFCbqXPS~f_A"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="加入我们的Slack社区"></a>
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="加入我们的Slack社区"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="加入我们的Discord社区"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="致谢"></a>
   <br/>
@@ -51,17 +51,17 @@ OpenHands也可以使用Docker在本地系统上运行。
 
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.45
+    docker.all-hands.dev/all-hands-ai/openhands:0.50
 ```
 
 > **注意**: 如果您在0.44版本之前使用过OpenHands，您可能需要运行 `mv ~/.openhands-state ~/.openhands` 来将对话历史迁移到新位置。
@@ -107,7 +107,7 @@ docker run -it --rm --pull=always \
 OpenHands是一个社区驱动的项目，我们欢迎每个人的贡献。我们大部分沟通
 通过Slack进行，因此这是开始的最佳场所，但我们也很乐意您通过Discord或Github与我们联系：
 
-- [加入我们的Slack工作空间](https://join.slack.com/t/openhands-ai/shared_invite/zt-34zm4j0gj-Qz5kRHoca8DFCbqXPS~f_A) - 这里我们讨论研究、架构和未来发展。
+- [加入我们的Slack工作空间](https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA) - 这里我们讨论研究、架构和未来发展。
 - [加入我们的Discord服务器](https://discord.gg/ESHStjSjD4) - 这是一个社区运营的服务器，用于一般讨论、问题和反馈。
 - [阅读或发布Github问题](https://github.com/All-Hands-AI/OpenHands/issues) - 查看我们正在处理的问题，或添加您自己的想法。
 

README_JA.md

@@ -10,7 +10,7 @@
   <a href="https://github.com/All-Hands-AI/OpenHands/stargazers"><img src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Stargazers"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
   <br/>
-  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-34zm4j0gj-Qz5kRHoca8DFCbqXPS~f_A"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Slackコミュニティに参加"></a>
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Slackコミュニティに参加"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Discordコミュニティに参加"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="クレジット"></a>
   <br/>
@@ -42,17 +42,17 @@ OpenHandsはDockerを利用してローカル環境でも実行できます。
 > 公共ネットワークで実行していますか？[Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)を参照して、ネットワークバインディングの制限や追加のセキュリティ対策を実施してください。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.45
+    docker.all-hands.dev/all-hands-ai/openhands:0.50
 ```
 
 **注**: バージョン0.44以前のOpenHandsを使用していた場合は、会話履歴を移行するために `mv ~/.openhands-state ~/.openhands` を実行してください。

build_vscode.py

@@ -0,0 +1,114 @@
+import os
+import pathlib
+import subprocess
+
+# This script is intended to be run by Poetry during the build process.
+
+# Define the expected name of the .vsix file based on the extension's package.json
+# This should match the name and version in openhands-vscode/package.json
+EXTENSION_NAME = 'openhands-vscode'
+EXTENSION_VERSION = '0.0.1'
+VSIX_FILENAME = f'{EXTENSION_NAME}-{EXTENSION_VERSION}.vsix'
+
+# Paths
+ROOT_DIR = pathlib.Path(__file__).parent.resolve()
+VSCODE_EXTENSION_DIR = ROOT_DIR / 'openhands' / 'integrations' / 'vscode'
+
+
+def check_node_version():
+    """Check if Node.js version is sufficient for building the extension."""
+    try:
+        result = subprocess.run(
+            ['node', '--version'], capture_output=True, text=True, check=True
+        )
+        version_str = result.stdout.strip()
+        # Extract major version number (e.g., "v12.22.9" -> 12)
+        major_version = int(version_str.lstrip('v').split('.')[0])
+        return major_version >= 18  # Align with frontend actual usage (18.20.1)
+    except (subprocess.CalledProcessError, FileNotFoundError, ValueError):
+        return False
+
+
+def build_vscode_extension():
+    """Builds the VS Code extension."""
+    vsix_path = VSCODE_EXTENSION_DIR / VSIX_FILENAME
+
+    # Check if VSCode extension build is disabled via environment variable
+    if os.environ.get('SKIP_VSCODE_BUILD', '').lower() in ('1', 'true', 'yes'):
+        print('--- Skipping VS Code extension build (SKIP_VSCODE_BUILD is set) ---')
+        if vsix_path.exists():
+            print(f'--- Using existing VS Code extension: {vsix_path} ---')
+        else:
+            print('--- No pre-built VS Code extension found ---')
+        return
+
+    # Check Node.js version - if insufficient, use pre-built extension as fallback
+    if not check_node_version():
+        print('--- Warning: Node.js version < 18 detected or Node.js not found ---')
+        print('--- Skipping VS Code extension build (requires Node.js >= 18) ---')
+        print('--- Using pre-built extension if available ---')
+
+        if not vsix_path.exists():
+            print('--- Warning: No pre-built VS Code extension found ---')
+            print('--- VS Code extension will not be available ---')
+        else:
+            print(f'--- Using pre-built VS Code extension: {vsix_path} ---')
+        return
+
+    print(f'--- Building VS Code extension in {VSCODE_EXTENSION_DIR} ---')
+
+    try:
+        # Ensure npm dependencies are installed
+        print('--- Running npm install for VS Code extension ---')
+        subprocess.run(
+            ['npm', 'install'],
+            cwd=VSCODE_EXTENSION_DIR,
+            check=True,
+            shell=os.name == 'nt',
+        )
+
+        # Package the extension
+        print(f'--- Packaging VS Code extension ({VSIX_FILENAME}) ---')
+        subprocess.run(
+            ['npm', 'run', 'package-vsix'],
+            cwd=VSCODE_EXTENSION_DIR,
+            check=True,
+            shell=os.name == 'nt',
+        )
+
+        # Verify the generated .vsix file exists
+        if not vsix_path.exists():
+            raise FileNotFoundError(
+                f'VS Code extension package not found after build: {vsix_path}'
+            )
+
+        print(f'--- VS Code extension built successfully: {vsix_path} ---')
+
+    except subprocess.CalledProcessError as e:
+        print(f'--- Warning: Failed to build VS Code extension: {e} ---')
+        print('--- Continuing without building extension ---')
+        if not vsix_path.exists():
+            print('--- Warning: No pre-built VS Code extension found ---')
+            print('--- VS Code extension will not be available ---')
+
+
+def build(setup_kwargs):
+    """
+    This function is called by Poetry during the build process.
+    `setup_kwargs` is a dictionary that will be passed to `setuptools.setup()`.
+    """
+    print('--- Running custom Poetry build script (build_vscode.py) ---')
+
+    # Build the VS Code extension and place the .vsix file
+    build_vscode_extension()
+
+    # Poetry will handle including files based on pyproject.toml `include` patterns.
+    # Ensure openhands/integrations/vscode/*.vsix is included there.
+
+    print('--- Custom Poetry build script (build_vscode.py) finished ---')
+
+
+if __name__ == '__main__':
+    print('Running build_vscode.py directly for testing VS Code extension packaging...')
+    build_vscode_extension()
+    print('Direct execution of build_vscode.py finished.')

config.template.toml

@@ -10,18 +10,7 @@
 # General core configurations
 ##############################################################################
 [core]
-# API key for E2B
-#e2b_api_key = ""
-
-# API key for Modal
-#modal_api_token_id = ""
-#modal_api_token_secret = ""
-
-# API key for Daytona
-#daytona_api_key = ""
-
-# Daytona Target
-#daytona_target = ""
+# API keys and configuration for core services
 
 # Base path for the workspace
 #workspace_base = "./workspace"
@@ -29,9 +18,6 @@
 # Cache directory path
 #cache_dir = "/tmp/cache"
 
-# Reasoning effort for o1 models (low, medium, high, or not set)
-#reasoning_effort = "medium"
-
 # Debugging enabled
 #debug = false
 
@@ -60,6 +46,9 @@
 # Maximum file size for uploads, in megabytes
 #file_uploads_max_file_size_mb = 0
 
+# Enable the browser environment
+#enable_browser = true
+
 # Maximum budget per task, 0.0 means no limit
 #max_budget_per_task = 0.0
 
@@ -127,6 +116,9 @@ api_key = ""
 # API version
 #api_version = ""
 
+# Reasoning effort for OpenAI o-series models (low, medium, high, or not set)
+#reasoning_effort = "medium"
+
 # Cost per input token
 #input_cost_per_token = 0.0
 
@@ -201,6 +193,27 @@ model = "gpt-4o"
 #native_tool_calling = None
 
 
+# Safety settings for models that support them (e.g., Mistral AI, Gemini)
+# Example for Mistral AI:
+# safety_settings = [
+#   { "category" = "hate", "threshold" = "low" },
+#   { "category" = "harassment", "threshold" = "low" },
+#   { "category" = "sexual", "threshold" = "low" },
+#   { "category" = "dangerous", "threshold" = "low" }
+# ]
+#
+# Example for Gemini:
+# safety_settings = [
+#   { "category" = "HARM_CATEGORY_HARASSMENT", "threshold" = "BLOCK_NONE" },
+#   { "category" = "HARM_CATEGORY_HATE_SPEECH", "threshold" = "BLOCK_NONE" },
+#   { "category" = "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold" = "BLOCK_NONE" },
+#   { "category" = "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold" = "BLOCK_NONE" }
+# ]
+#safety_settings = []
+
+[llm.draft_editor]
+# The number of times llm_editor tries to fix an error when editing.
+correct_num = 5
 
 [llm.gpt4o-mini]
 api_key = ""
@@ -216,6 +229,7 @@ model = "gpt-4o"
 [agent]
 
 # Whether the browsing tool is enabled
+# Note: when this is set to true, enable_browser in the core config must also be true
 enable_browsing = true
 
 # Whether the LLM draft editor is enabled
@@ -250,6 +264,9 @@ enable_finish = true
 # length limit
 enable_history_truncation = true
 
+# Whether the condensation request tool is enabled
+enable_condensation_request = false
+
 [agent.RepoExplorerAgent]
 # Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
 # useful when an agent doesn't demand high quality but uses a lot of tokens
@@ -318,6 +335,9 @@ classpath = "my_package.my_module.MyCustomAgent"
 # Enable GPU support in the runtime
 #enable_gpu = false
 
+# When there are multiple cards, you can specify the GPU by ID
+#cuda_visible_devices = ''
+
 # Additional Docker runtime kwargs
 #docker_runtime_kwargs = {}
 

containers/app/Dockerfile

@@ -1,5 +1,5 @@
 ARG OPENHANDS_BUILD_VERSION=dev
-FROM node:22.16.0-bookworm-slim AS frontend-builder
+FROM node:24.3.0-bookworm-slim AS frontend-builder
 
 WORKDIR /app
 
@@ -26,7 +26,7 @@ RUN apt-get update -y \
 
 COPY pyproject.toml poetry.lock ./
 RUN touch README.md
-RUN export POETRY_CACHE_DIR && poetry install --no-root --extras all-runtimes && rm -rf $POETRY_CACHE_DIR
+RUN export POETRY_CACHE_DIR && poetry install --no-root && rm -rf $POETRY_CACHE_DIR
 
 FROM base AS openhands-app
 
@@ -45,6 +45,7 @@ ENV OPENHANDS_BUILD_VERSION=$OPENHANDS_BUILD_VERSION
 ENV SANDBOX_USER_ID=0
 ENV FILE_STORE=local
 ENV FILE_STORE_PATH=/.openhands
+ENV INIT_GIT_IN_EMPTY_WORKSPACE=1
 RUN mkdir -p $FILE_STORE_PATH
 RUN mkdir -p $WORKSPACE_BASE
 

containers/dev/compose.yml

@@ -12,7 +12,7 @@ services:
       - SANDBOX_API_HOSTNAME=host.docker.internal
       - DOCKER_HOST_ADDR=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.45-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.50-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

dev_config/python/.pre-commit-config.yaml

@@ -3,9 +3,9 @@ repos:
     rev: v5.0.0
     hooks:
       - id: trailing-whitespace
-        exclude: docs/modules/python
+        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/)
       - id: end-of-file-fixer
-        exclude: docs/modules/python
+        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/)
       - id: check-yaml
         args: ["--allow-multiple-documents"]
       - id: debug-statements
@@ -28,17 +28,19 @@ repos:
         entry: ruff check --config dev_config/python/ruff.toml
         types_or: [python, pyi, jupyter]
         args: [--fix, --unsafe-fixes]
+        exclude: third_party/
       # Run the formatter.
       - id: ruff-format
         entry: ruff format --config dev_config/python/ruff.toml
         types_or: [python, pyi, jupyter]
+        exclude: third_party/
 
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.15.0
     hooks:
       - id: mypy
         additional_dependencies:
-          [types-requests, types-setuptools, types-pyyaml, types-toml, types-docker, lxml]
+          [types-requests, types-setuptools, types-pyyaml, types-toml, types-docker, pydantic, lxml]
         # To see gaps add `--html-report mypy-report/`
         entry: mypy --config-file dev_config/python/mypy.ini openhands/
         always_run: true

dev_config/python/mypy.ini

@@ -7,3 +7,9 @@ warn_unreachable = True
 warn_redundant_casts = True
 no_implicit_optional = True
 strict_optional = True
+
+# Exclude third-party runtime directory from type checking
+exclude = third_party/
+
+[mypy-openhands.memory.condenser.impl.*]
+disable_error_code = override

dev_config/python/ruff.toml

@@ -1,3 +1,6 @@
+# Exclude third-party runtime directory from linting
+exclude = ["third_party/"]
+
 [lint]
 select = [
     "E",

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:0.45-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik}
       #- SANDBOX_USER_ID=${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 for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/docs.json

@@ -34,6 +34,7 @@
               {
                 "group": "Integrations",
                 "pages": [
+                  "usage/cloud/bitbucket-installation",
                   "usage/cloud/github-installation",
                   "usage/cloud/gitlab-installation",
                   "usage/cloud/slack-installation"
@@ -66,7 +67,9 @@
                         "usage/llms/groq",
                         "usage/llms/local-llms",
                         "usage/llms/litellm-proxy",
+                        "usage/llms/moonshot",
                         "usage/llms/openai-llms",
+                        "usage/llms/openhands-llms",
                         "usage/llms/openrouter"
                       ]
                     }
@@ -151,6 +154,12 @@
           }
         ]
       },
+      {
+        "tab": "Success Stories",
+        "pages": [
+          "success-stories/index"
+        ]
+      },
       {
           "tab": "API Reference",
           "openapi": "/openapi.json"
@@ -190,7 +199,7 @@
   },
   "footer": {
     "socials": {
-      "slack": "https://join.slack.com/t/openhands-ai/shared_invite/zt-34zm4j0gj-Qz5kRHoca8DFCbqXPS~f_A",
+      "slack": "https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA",
       "github": "https://github.com/All-Hands-AI/OpenHands",
       "discord": "https://discord.gg/ESHStjSjD4"
     }

docs/openapi.json

@@ -1827,6 +1827,11 @@
           "updated_at": {
             "type": "string",
             "format": "date-time"
+          },
+          "owner_type": {
+            "type": "string",
+            "enum": ["user", "organization"],
+            "nullable": true
           }
         }
       },

docs/success-stories/index.mdx

@@ -0,0 +1,217 @@
+---
+title: "Success Stories"
+description: "Real-world examples of what you can achieve with OpenHands"
+---
+
+Discover how developers and teams are using OpenHands to automate their software development workflows. From quick fixes to complex projects, see what's possible with AI-powered development assistance.
+
+Check out the [#success-stories](https://www.linen.dev/s/openhands/c/success-stories) channel on our Slack for more!
+
+<Update label="2025-06-13 OpenHands helps frontline support" description="@Joe Pelletier">
+
+## One of the cool things about OpenHands, and especially the Slack Integration, is the ability to empower folks who are on the ‘front lines’ with customers.
+
+For example, often times Support and Customer Success teams will field bug reports, doc questions, and other ‘nits’ from customers. They tend to have few options to deal with this, other than file a feedback ticket with product teams and hope it gets prioritized in an upcoming sprint.
+
+Instead, with tools like OpenHands and the Slack integration, they can request OpenHands to make fixes proactively and then have someone on the engineering team (like a lead engineer, a merge engineer, or even technical product manager) review the PR and approve it — thus reducing the cycle time for ‘quick wins’ from weeks to just a few hours.
+
+Here's how we do that with the OpenHands project:
+
+<iframe
+  width="560"
+  height="560"
+  src="https://www.linen.dev/s/openhands/t/29118545/seems-mcp-config-from-config-toml-is-being-overwritten-hence#629f8e2b-cde8-427e-920c-390557a06cc9"
+  frameborder="0"
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+  allowfullscreen
+></iframe>
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29124350/one-of-the-cool-things-about-openhands-and-especially-the-sl#25029f37-7b0d-4535-9187-83b3e06a4011)
+
+</Update>
+
+
+<Update label="2025-06-13 Ask OpenHands to show me some love" description="@Graham Neubig">
+
+## Asked openhands to “show me some love” and...
+
+Asked openhands to “show me some love” and it coded up this app for me, actually kinda genuinely feel loved
+
+<video
+  controls
+  autoplay
+  className="w-full aspect-video"
+  src="/success-stories/stories/2025-06-13-show-love/v1.mp4"
+></video>
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100731/asked-openhands-to-show-me-some-love-and-it-coded-up-this-ap#1e08af6b-b7d5-4167-8a53-17e6806555e0)
+
+</Update>
+
+<Update label="2025-06-11 OpenHands does 100% of my infra IAM research for me" description="@Xingyao Wang">
+
+## Now, OpenHands does 100% of my infra IAM research for me
+
+Got an IAM error on GCP? Send a screenshot to OH... and it just works!!!
+Can't imagine going back to the early days without OH: I'd spend an entire afternoon figuring how to get IAM right
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100732/now-openhands-does-100-of-my-infra-iam-research-for-me-sweat#20482a73-4e2e-4edd-b6d1-c9e8442fccd1)
+
+![](/success-stories/stories/2025-06-11-infra-iam/s1.png)
+![](/success-stories/stories/2025-06-11-infra-iam/s2.png)
+
+</Update>
+
+<Update label="2025-06-08 OpenHands builds an interactive map for me" description="@Rodrigo Argenton Freire (ODLab)">
+
+## Very simple example, but baby steps....
+
+I am a professor of architecture and urban design. We built, me and some students, an interactive map prototype to help visitors and new students to find important places in the campus. Considering that we lack a lot of knowledge in programming, that was really nice to build and a smooth process.
+We first created the main components with all-hands and then adjusted some details locally. Definitely, saved us a lot of time and money.
+That's a prototype but we will have all the info by tuesday.
+https://buriti-emau.github.io/Mapa-UFU/
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100736/very-simple-example-but-baby-steps-i-am-a-professor-of-archi#8f2e3f3f-44e6-44ea-b9a8-d53487470179)
+
+![](/success-stories/stories/2025-06-08-map/s1.png)
+
+</Update>
+
+
+<Update label="2025-06-06 Web Search Saves the Day" description="@Ian Walker">
+
+## Tavily adapter helps solve persistent debugging issue
+
+Big congratulations to the new [Tavily adapter](https://www.all-hands.dev/blog/building-a-provably-versatile-agent)... OpenHands and I have been beavering away at a Lightstreamer client library for most of this week but were getting a persistent (and unhelpful) "unexpected error" from the server.
+
+Coming back to the problem today, after trying several unsuccessful fixes prompted by me, OH decided all by itself to search the web, and found the cause of the problem (of course it was simply CRLF line endings...). I was on the verge of giving up - good thing OH has more stamina than me!
+
+This demonstrates how OpenHands' web search capabilities can help solve debugging issues that would otherwise require extensive manual research.
+
+<iframe
+  width="560"
+  height="560"
+  src="https://www.linen.dev/s/openhands/t/29100737/big-congratulations-to-the-new-tavily-adapter-openhands-and-#87b027e5-188b-425e-8aa9-719dcb4929f4"
+  title="YouTube video player"
+  frameborder="0"
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+  allowfullscreen
+></iframe>
+
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100737/big-congratulations-to-the-new-tavily-adapter-openhands-and-#76f1fb26-6ef7-4709-b9ea-fb99105e47e4)
+
+</Update>
+
+<Update label="2025-06-05 OpenHands updates my personal website for a new paper" description="@Xingyao Wang">
+
+## I asked OpenHands to update my personal website for the "OpenHands Versa" paper.
+
+It is an extremely trivial task: You just need to browse to arxiv, copy the author names, format them for BibTeX, and then modify the papers.bib file. But now I'm getting way too lazy to even open my IDE and actually do this one-file change!
+
+[Original Tweet/X thread](https://x.com/xingyaow_/status/1930796287919542410)
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100738/i-asked-openhands-to-update-my-personal-website-for-the-open#f0324022-b12b-4d34-b12b-bdbc43823f69)
+
+</Update>
+
+<Update label="2025-06-02 OpenHands makes an animated gif of swe-bench verified scores over time" description="@Graham Neubig">
+
+## I asked OpenHands to make an animated gif of swe-bench verified scores over time.
+
+It took a bit of prompting but ended up looking pretty nice I think
+
+<video width="560" height="315" autoPlay loop muted src="/success-stories/stories/2025-06-02-swebench-score/s1.mp4"></video>
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100744/i-asked-openhands-to-make-an-animated-gif-of-swe-bench-verif#fb3b82c9-6222-4311-b97b-b2ac1cfe6dff)
+
+</Update>
+
+<Update label="2025-05-30 AWS Troubleshooting" description="@Graham Neubig">
+
+## Quick AWS security group fix
+
+I really don't like trying to fix issues with AWS, especially security groups and other finicky things like this. But I started up an instance and wasn't able to ssh in. So I asked OpenHands:
+
+> Currently, the following ssh command is timing out:
+>
+> $ ssh -i gneubig.pem ubuntu@XXX.us-east-2.compute.amazonaws.com
+> ssh: connect to host XXX.us-east-2.compute.amazonaws.com port 22: Operation timed out
+>
+> Use the provided AWS credentials to take a look at i-XXX and examine why
+
+And 2 minutes later I was able to SSH in!
+
+This shows how OpenHands can quickly diagnose and fix AWS infrastructure issues that would normally require manual investigation.
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100747/i-really-don-t-like-trying-to-fix-issues-with-aws-especially#d92a66d2-3bc1-4467-9d09-dc983004d083)
+
+</Update>
+
+
+<Update label="2025-05-04 Chrome Extension Development" description="@Xingyao Wang">
+
+## OpenHands builds Chrome extension for GitHub integration
+
+I asked OpenHands to write a Chrome extension based on our [OpenHands Cloud API](https://docs.all-hands.dev/modules/usage/cloud/cloud-api). Once installed, you can now easily launch an OpenHands cloud session from your GitHub webpage/PR!
+
+This demonstrates OpenHands' ability to create browser extensions and integrate with external APIs, enabling seamless workflows between GitHub and OpenHands Cloud.
+
+![Chrome extension](/success-stories/stories/2025-05-04-chrome-extension/s1.png)
+![Chrome extension](/success-stories/stories/2025-05-04-chrome-extension/s2.png)
+
+[GitHub Repository](https://github.com/xingyaoww/openhands-chrome-extension)
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100755/i-asked-openhands-to-write-a-chrome-extension-based-on-our-h#88f14b7f-f8ff-40a6-83c2-bd64e95924c5)
+
+</Update>
+
+
+<Update label="2025-04-11 Visual UI Testing" description="@Xingyao Wang">
+
+## OpenHands tests UI automatically with visual browsing
+
+Thanks to visual browsing -- OpenHands can actually test some simple UI by serving the website, clicking the button in the browser and looking at screenshots now!
+
+Prompt is just:
+```
+I want to create a Hello World app in Javascript that:
+* Displays Hello World in the middle.
+* Has a button that when clicked, changes the greeting with a bouncing animation to fun versions of Hello.
+* Has a counter for how many times the button has been clicked.
+* Has another button that changes the app's background color.
+```
+
+Eager-to-work Sonnet 3.7 will test stuff for you without you asking!
+
+This showcases OpenHands' visual browsing capabilities, enabling it to create, serve, and automatically test web applications through actual browser interactions and screenshot analysis.
+
+![Visual UI testing](/success-stories/stories/2025-04-11-visual-ui/s1.png)
+
+[Original Slack thread](https://www.linen.dev/s/openhands/t/29100764/thanks-to-u07k0p3bdb9-s-visual-browsing-openhands-can-actual#21beb9bc-1a04-4272-87e9-4d3e3b9925e7)
+
+</Update>
+
+<Update label="2025-03-07 Proactive Error Handling" description="@Graham Neubig">
+
+## OpenHands fixes crashes before you notice them
+
+Interesting story, I asked OpenHands to start an app on port 12000, it showed up on the app pane. I started using the app, and then it crashed... But because it crashed in OpenHands, OpenHands immediately saw the error message and started fixing the problem without me having to do anything. It was already fixing the problem before I even realized what was going wrong.
+
+This demonstrates OpenHands' proactive monitoring capabilities - it doesn't just execute commands, but actively watches for errors and begins remediation automatically, often faster than human reaction time.
+
+</Update>
+
+<Update label="2024-12-03 Creative Design Acceleration" description="@Rohit Malhotra">
+
+## Pair programming for interactive design projects
+
+Used OpenHands as a pair programmer to do heavy lifting for a creative/interactive design project in p5js.
+
+I usually take around 2 days for high fidelity interactions (planning strategy + writing code + circling back with designer), did this in around 5hrs instead with the designer watching curiously the entire time.
+
+This showcases how OpenHands can accelerate creative and interactive design workflows, reducing development time by 75% while maintaining high quality output.
+
+[Original Tweet](https://x.com/rohit_malh5/status/1863995531657425225)
+
+</Update>

docs/usage/cloud/bitbucket-installation.mdx

@@ -0,0 +1,25 @@
+---
+title: Bitbucket Integration
+description: This guide walks you through the process of installing OpenHands Cloud for your Bitbucket repositories. Once
+  set up, it will allow OpenHands to work with your Bitbucket repository.
+---
+
+## Prerequisites
+
+- Signed in to [OpenHands Cloud](https://app.all-hands.dev) with [a Bitbucket account](/usage/cloud/openhands-cloud).
+
+## Adding Bitbucket Repository Access
+
+Upon signing into OpenHands Cloud with a Bitbucket account, OpenHands will have access to your repositories.
+
+## Working With Bitbucket Repos in Openhands Cloud
+
+After signing in with a Bitbucket account, use the `select a repo` and `select a branch` dropdowns to select the
+appropriate repository and branch you'd like OpenHands to work on. Then click on `Launch` to start the conversation!
+
+![Connect Repo](/static/img/connect-repo-no-github.png)
+
+## Next Steps
+
+- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
+- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.

docs/usage/cloud/cloud-ui.mdx

@@ -9,8 +9,9 @@ description: The Cloud UI provides a web interface for interacting with OpenHand
 The landing page is where you can:
 
 - [Add GitHub repository access](/usage/cloud/github-installation#adding-github-repository-access) to OpenHands.
-- [Select a GitHub repo](/usage/cloud/github-installation#working-with-github-repos-in-openhands-cloud) or
-  [a GitLab repo](/usage/cloud/gitlab-installation#working-with-gitlab-repos-in-openhands-cloud) to start working on.
+- [Select a GitHub repo](/usage/cloud/github-installation#working-with-github-repos-in-openhands-cloud),
+  [a GitLab repo](/usage/cloud/gitlab-installation#working-with-gitlab-repos-in-openhands-cloud) or
+  [a Bitbucket repo](/usage/cloud/bitbucket-installation#working-with-bitbucket-repos-in-openhands-cloud) to start working on.
 - See `Suggested Tasks` for repositories that OpenHands has access to.
 - Launch an empty conversation using `Launch from Scratch`.
 

docs/usage/cloud/github-installation.mdx

@@ -51,8 +51,7 @@ Giving GitHub repository access to OpenHands also allows you to work on GitHub i
 
 ### Working with Issues
 
-On your repository, label an issue with `openhands` or add a message starting with
-`@openhands`. OpenHands will:
+On your repository, label an issue with `openhands` or add a message starting with `@openhands`. OpenHands will:
 1. Comment on the issue to let you know it is working on it.
    - You can click on the link to track the progress on OpenHands Cloud.
 2. Open a pull request if it determines that the issue has been successfully resolved.
@@ -65,6 +64,8 @@ To get OpenHands to work on pull requests, mention `@openhands` in the comments
 - Request updates
 - Get code explanations
 
+**Important Note**: The `@openhands` mention functionality in pull requests only works if the pull request is both *to* and *from* a repository that you have added through the interface. This is because OpenHands needs appropriate permissions to access both repositories.
+
 ## Next Steps
 
 - [Learn about the Cloud UI](/usage/cloud/cloud-ui).

docs/usage/cloud/gitlab-installation.mdx

@@ -1,7 +1,7 @@
 ---
 title: GitLab Integration
 description: This guide walks you through the process of installing OpenHands Cloud for your GitLab repositories. Once
-  set up, it will allow OpenHands to work with your GitLab repository.
+  set up, it will allow OpenHands to work with your GitLab repository through the Cloud UI or straight from GitLab!.
 ---
 
 ## Prerequisites
@@ -17,7 +17,7 @@ Upon signing into OpenHands Cloud with a GitLab account, OpenHands will have acc
 After signing in with a Gitlab account, use the `select a repo` and `select a branch` dropdowns to select the
 appropriate repository and branch you'd like OpenHands to work on. Then click on `Launch` to start the conversation!
 
-![Connect Repo](/static/img/connect-repo.png)
+![Connect Repo](/static/img/connect-repo-no-github.png)
 
 ## Using Tokens with Reduced Scopes
 
@@ -25,6 +25,33 @@ OpenHands requests an API-scoped token during OAuth authentication. By default,
 To restrict the agent's permissions, you can define a custom secret `GITLAB_TOKEN`, which will override the default token assigned to the agent.
 While the high-permission API token is still requested and used for other components of the application (e.g. opening merge requests), the agent will not have access to it.
 
+## Working on GitLab Issues and Merge Requests Using Openhands
+
+<Note>
+This feature works for personal projects and is available for group projects with a
+[Premium or Ultimate tier subscription](https://docs.gitlab.com/user/project/integrations/webhooks/#group-webhooks).
+
+A webhook is automatically installed within a few minutes after the owner/maintainer of the project or group logs into
+OpenHands Cloud. If you decide to delete the webhook, then re-installing will require the support of All Hands AI but we are planning to improve this in a future release.
+</Note>
+
+Giving GitLab repository access to OpenHands also allows you to work on GitLab issues and merge requests directly.
+
+### Working with Issues
+
+On your repository, label an issue with `openhands` or add a message starting with `@openhands`. OpenHands will:
+1. Comment on the issue to let you know it is working on it.
+   - You can click on the link to track the progress on OpenHands Cloud.
+2. Open a merge request if it determines that the issue has been successfully resolved.
+3. Comment on the issue with a summary of the performed tasks and a link to the PR.
+
+### Working with Merge Requests
+
+To get OpenHands to work on merge requests, mention `@openhands` in the comments to:
+- Ask questions
+- Request updates
+- Get code explanations
+
 ## Next Steps
 
 - [Learn about the Cloud UI](/usage/cloud/cloud-ui).

docs/usage/cloud/openhands-cloud.mdx

@@ -8,9 +8,9 @@ description: Getting started with OpenHands Cloud.
 OpenHands Cloud is the hosted cloud version of All Hands AI's OpenHands. To get started with OpenHands Cloud,
 visit [app.all-hands.dev](https://app.all-hands.dev).
 
-You'll be prompted to connect with your GitHub or GitLab account:
+You'll be prompted to connect with your GitHub, GitLab or Bitbucket account:
 
-1. Click `Log in with GitHub` or `Log in with GitLab`.
+1. Click `Log in with GitHub`, `Log in with GitLab` or `Log in with Bitbucket`.
 2. Review the permissions requested by OpenHands and authorize the application.
    - OpenHands will require certain permissions from your account. To read more about these permissions,
      you can click the `Learn more` link on the authorization page.
@@ -22,5 +22,6 @@ Once you've connected your account, you can:
 
 - [Install GitHub Integration](/usage/cloud/github-installation) to use OpenHands with your GitHub repositories.
 - [Install GitLab Integration](/usage/cloud/gitlab-installation) to use OpenHands with your GitLab repositories.
+- [Install Bitbucket Integration](/usage/cloud/bitbucket-installation) to use OpenHands with your Bitbucket repositories.
 - [Learn about the Cloud UI](/usage/cloud/cloud-ui).
 - [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.

docs/usage/cloud/slack-installation.mdx

@@ -3,6 +3,15 @@ title: Slack Integration (Beta)
 description: This guide walks you through installing the OpenHands Slack app.
 ---
 
+<iframe
+  className="w-full aspect-video"
+  src="https://www.youtube.com/embed/hbloGmfZsJ4"
+  title="OpenHands Slack Integration Tutorial"
+  frameBorder="0"
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
+  allowFullScreen>
+</iframe>
+
 ## Prerequisites
 
 - Access to OpenHands Cloud.

docs/usage/configuration-options.mdx

@@ -1,8 +1,19 @@
 ---
 title: Configuration Options
-description: 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.
+description: This page outlines all available configuration options for OpenHands, allowing you to customize its
+  behavior and integrate it with other services.
 ---
 
+<Note>
+   In GUI Mode, any settings applied through the Settings UI will take precedence.
+</Note>
+
+## Location of the `config.toml` File
+
+When running OpenHands in CLI, headless, or development mode, you can use a project-specific `config.toml` file for configuration, which must be
+located in the same directory from which the command is run. Alternatively, you may use the `--config-file` option to
+specify a different path to the `config.toml` file.
+
 ## Core Configuration
 
 The core configuration options are defined in the `[core]` section of the `config.toml` file.

docs/usage/faqs.mdx

@@ -12,7 +12,8 @@ icon: question
   [GitHub](/usage/cloud/github-installation), [GitLab](/usage/cloud/gitlab-installation),
   and [Slack](/usage/cloud/slack-installation) integrations.
 2. **Run on your own**: If you prefer to run it on your own hardware, follow our [Getting Started guide](/usage/local-setup).
-3. **First steps**: Complete the [start building tutorial](/usage/getting-started) to learn the basics.
+3. **First steps**: Read over the [start building guidelines](/usage/getting-started) and
+  [prompting best practices](/usage/prompting/prompting-best-practices) to learn the basics.
 
 ### Can I use OpenHands for production workloads?
 
@@ -88,7 +89,7 @@ If you would like to set things up more systematically, you can:
 1. **Search existing issues**: Check our [GitHub issues](https://github.com/All-Hands-AI/OpenHands/issues) to see if
   others have encountered the same problem.
 2. **Join our community**: Get help from other users and developers:
-   - [Slack community](https://join.slack.com/t/openhands-ai/shared_invite/zt-34zm4j0gj-Qz5kRHoca8DFCbqXPS~f_A)
+   - [Slack community](https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA)
    - [Discord server](https://discord.gg/ESHStjSjD4)
 3. **Check our troubleshooting guide**: Common issues and solutions are documented in
   [Troubleshooting](/usage/troubleshooting/troubleshooting).

docs/usage/how-to/cli-mode.mdx

@@ -7,6 +7,15 @@ description: The Command-Line Interface (CLI) provides a powerful interface that
 This mode is different from the [headless mode](/usage/how-to/headless-mode), which is non-interactive and better
 for scripting.
 
+<iframe
+  className="w-full aspect-video"
+  src="https://www.youtube.com/embed/PfvIx4y8h7w"
+  title="OpenHands CLI Tutorial"
+  frameBorder="0"
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
+  allowFullScreen>
+</iframe>
+
 ## Getting Started
 
 ### Running with Python
@@ -14,34 +23,73 @@ for scripting.
 **Note** - OpenHands requires Python version 3.12 or higher (Python 3.14 is not currently supported)
 
 1. Install OpenHands using pip:
-
 ```bash
 pip install openhands-ai
 ```
 
-   Or if you prefer not to manage your own Python environment, you can use `uvx`:
+  Or if you prefer not to manage your own Python environment, you can use `uvx`:
 
 ```bash
 uvx --python 3.12 --from openhands-ai openhands
 ```
 
-2. Launch an interactive OpenHands conversation from the command line:
+<AccordionGroup>
 
+<Accordion title="Create shell aliases for easy access across environments">
+
+Add the following to your shell configuration file (`.bashrc`, `.zshrc`, etc.):
+
+```bash
+# Add OpenHands aliases
+alias openhands="uvx --python 3.12 --from openhands-ai openhands"
+alias oh="uvx --python 3.12 --from openhands-ai openhands"
+```
+
+After adding these lines, reload your shell configuration with `source ~/.bashrc` or `source ~/.zshrc` (depending on your shell).
+
+</Accordion>
+
+<Accordion title="Install OpenHands in home directory without global installation">
+
+You can install OpenHands in a virtual environment in your home directory using `uv`:
+
+```bash
+# Create a virtual environment in your home directory
+cd ~
+uv venv .openhands-venv --python 3.12
+
+# Install OpenHands in the virtual environment
+uv pip install -t ~/.openhands-venv/lib/python3.12/site-packages openhands-ai
+
+# Add the bin directory to your PATH in your shell configuration file
+echo 'export PATH="$PATH:$HOME/.openhands-venv/bin"' >> ~/.bashrc  # or ~/.zshrc
+
+# Reload your shell configuration
+source ~/.bashrc  # or source ~/.zshrc
+```
+
+</Accordion>
+
+</AccordionGroup>
+
+2. Launch an interactive OpenHands conversation from the command line:
 ```bash
 openhands
 ```
 
+<Note>
+  If you have cloned the repository, you can also run the CLI directly using Poetry:
+
+  poetry run python -m openhands.cli.main
+</Note>
+
 3. Set your model, API key, and other preferences using the UI (or alternatively environment variables, below).
 
 This command opens an interactive prompt where you can type tasks or commands and get responses from OpenHands.
+The first time you run the CLI, it will take you through configuring the required LLM
+settings. These will be saved for future sessions.
 
-#### For Developers
-
-If you have cloned the repository, you can run the CLI directly using Poetry:
-
-```bash
-poetry run python -m openhands.cli.main
-```
+The conversation history will be saved in `~/.openhands/sessions`.
 
 ### Running with Docker
 
@@ -55,7 +103,7 @@ poetry run python -m openhands.cli.main
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -64,15 +112,21 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.45 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.50 \
     python -m openhands.cli.main --override-cli-mode true
 ```
 
-> **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
+<Note>
+  If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your
+  conversation history to the new location.
+</Note>
 
-This launches the CLI in Docker, allowing you to interact with OpenHands as described above.
+This launches the CLI in Docker, allowing you to interact with OpenHands.
 
-The `-e SANDBOX_USER_ID=$(id -u)` ensures files created by the agent in your workspace have the correct permissions.
+The `-e SANDBOX_USER_ID=$(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.
+
+The conversation history will be saved in `~/.openhands/sessions`.
 
 ## Interactive CLI Overview
 
@@ -99,6 +153,7 @@ You can use the following commands whenever the prompt (`>`) is displayed:
 | `/new`       | Start a new conversation                                       |
 | `/settings`  | View and modify current LLM/agent settings                     |
 | `/resume`    | Resume the agent if paused                                     |
+| `/mcp`       | Manage MCP server configuration and view connection errors    |
 
 #### Settings and Configuration
 
@@ -108,7 +163,7 @@ follow the prompts:
 - **Basic settings**: Choose a model/provider and enter your API key.
 - **Advanced settings**: Set custom endpoints, enable or disable confirmation mode, and configure memory condensation.
 
-Settings can also be managed via the `config.toml` file.
+Settings can also be managed via the `config.toml` file in the current directory or `~/.openhands/config.toml`.
 
 #### Repository Initialization
 
@@ -120,6 +175,41 @@ project details and structure. Use this when onboarding the agent to a new codeb
 You can pause the agent while it is running by pressing `Ctrl-P`. To continue the conversation after pausing, simply
 type `/resume` at the prompt.
 
+#### MCP Server Management
+
+To configure Model Context Protocol (MCP) servers, you can refer to the documentation on [MCP servers](../mcp) and use the `/mcp` command in the CLI. This command provides an interactive interface for managing Model Context Protocol (MCP) servers:
+
+- **List configured servers**: View all currently configured MCP servers (SSE, Stdio, and SHTTP)
+- **Add new server**: Interactively add a new MCP server with guided prompts
+- **Remove server**: Remove an existing MCP server from your configuration
+- **View errors**: Display any connection errors that occurred during MCP server startup
+
+This command modifies your `~/.openhands/config.toml` file and will prompt you to restart OpenHands for changes to take effect.
+
+To enable the [Tavily MCP server](https://github.com/tavily-ai/tavily-mcp) search engine, you can set the `search_api_key` under the `[core]` section in the `~/.openhands/config.toml` file.
+
+##### Example of the `config.toml` file with MCP server configuration:
+
+```toml
+[core]
+search_api_key = "tvly-your-api-key-here"
+
+[mcp]
+stdio_servers = [
+    {name="fetch", command="uvx", args=["mcp-server-fetch"]},
+]
+
+sse_servers = [
+    # Basic SSE server with just a URL
+    "http://example.com:8080/sse",
+]
+
+shttp_servers = [
+    # Streamable HTTP server with API key authentication
+    {url="https://secure-example.com/mcp", api_key="your-api-key"}
+]
+```
+
 ## Tips and Troubleshooting
 
 - Use `/help` at any time to see the list of available commands.

docs/usage/how-to/custom-sandbox-guide.mdx

@@ -1,6 +1,7 @@
 ---
 title: Custom Sandbox
-description: 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.
+description: 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

docs/usage/how-to/gui-mode.mdx

@@ -25,7 +25,8 @@ You can use the Settings page at any time to:
 - Setup the LLM provider and model for OpenHands.
 - [Setup the search engine](/usage/search-engine-setup).
 - [Configure MCP servers](/usage/mcp).
-- [Connect to GitHub](/usage/how-to/gui-mode#github-setup) and [connect to GitLab](/usage/how-to/gui-mode#gitlab-setup).
+- [Connect to GitHub](/usage/how-to/gui-mode#github-setup), [connect to GitLab](/usage/how-to/gui-mode#gitlab-setup)
+  and [connect to Bitbucket](/usage/how-to/gui-mode#bitbucket-setup).
 - Set application settings like your preferred language, notifications and other preferences.
 - [Manage custom secrets](/usage/common-settings#secrets-management).
 
@@ -122,17 +123,15 @@ OpenHands automatically exports a `GITLAB_TOKEN` to the shell environment if pro
 </Accordion>
 </AccordionGroup>
 
-#### BitBucket Setup (Coming soon ...)
+#### BitBucket Setup
 <AccordionGroup>
 <Accordion title="Setting Up a BitBucket Password">
 1. **Generate an App Password**:
    - On BitBucket, go to Personal Settings > App Password.
    - Create a new password with the following scopes:
-     - `repository: read`
+     - `account`: `read`
      - `repository: write`
-     - `pull requests: read`
      - `pull requests: write`
-     - `issues: read`
      - `issues: write`
    - App passwords are non-expiring token. OpenHands will migrate to using API tokens in the future.
   2. **Enter Token in OpenHands**:

docs/usage/how-to/headless-mode.mdx

@@ -18,42 +18,79 @@ poetry run python -m openhands.core.main -t "write a bash script that prints hi"
 You'll need to be sure to set your model, API key, and other settings via environment variables
 [or the `config.toml` file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml).
 
-## With Docker
+### Working with Repositories
 
-To run OpenHands in Headless mode with Docker:
+You can specify a repository for OpenHands to work with using `--selected-repo` or the `SANDBOX_SELECTED_REPO` environment variable:
 
-1. Set the following environment variables in your terminal:
-   - `SANDBOX_VOLUMES` to specify the directory you want OpenHands to access ([See using SANDBOX_VOLUMES for more info](../runtimes/docker#using-sandbox_volumes))
-   - `LLM_MODEL` - the LLM model to use (e.g. `export LLM_MODEL="anthropic/claude-sonnet-4-20250514"`)
-   - `LLM_API_KEY` - your API key (e.g. `export LLM_API_KEY="sk_test_12345"`)
-
-2. Run the following Docker command:
+> **Note**: Currently, authentication tokens (GITHUB_TOKEN, GITLAB_TOKEN, or BITBUCKET_TOKEN) are required for all repository operations, including public repositories. This is a known limitation that may be addressed in future versions to allow tokenless access to public repositories.
 
 ```bash
+# Using command-line argument
+poetry run python -m openhands.core.main \
+  --selected-repo "owner/repo-name" \
+  -t "analyze the codebase and suggest improvements"
+
+# Using environment variable
+export SANDBOX_SELECTED_REPO="owner/repo-name"
+poetry run python -m openhands.core.main -t "fix any linting issues"
+
+# Authentication tokens are currently required for ALL repository operations (public and private)
+# This includes GitHub, GitLab, and Bitbucket repositories
+export GITHUB_TOKEN="your-token"  # or GITLAB_TOKEN, BITBUCKET_TOKEN
+poetry run python -m openhands.core.main \
+  --selected-repo "owner/repo-name" \
+  -t "review the security implementation"
+
+# Using task files instead of inline task
+echo "Review the README and suggest improvements" > task.txt
+poetry run python -m openhands.core.main -f task.txt --selected-repo "owner/repo"
+```
+
+## With Docker
+
+Set environment variables and run the Docker command:
+
+```bash
+# Set required environment variables
+export SANDBOX_VOLUMES="/path/to/workspace"  # See SANDBOX_VOLUMES docs for details
+export LLM_MODEL="anthropic/claude-sonnet-4-20250514"
+export LLM_API_KEY="your-api-key"
+export SANDBOX_SELECTED_REPO="owner/repo-name"  # Optional: requires GITHUB_TOKEN
+export GITHUB_TOKEN="your-token"  # Required for repository operations
+
+# Run OpenHands
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
     -e LLM_MODEL=$LLM_MODEL \
+    -e SANDBOX_SELECTED_REPO=$SANDBOX_SELECTED_REPO \
+    -e GITHUB_TOKEN=$GITHUB_TOKEN \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     --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:0.45 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.50 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
-> **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
+
+> **Note**: If you used OpenHands before version 0.44, run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history.
 
 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
+## Additional Options
 
-To view all available configuration options for headless mode, run the Python command with the `--help` flag.
+Common command-line options:
+- `-d "/path/to/workspace"` - Set working directory
+- `-f task.txt` - Load task from file
+- `-i 50` - Set max iterations
+- `-b 10.0` - Set budget limit (USD)
+- `--no-auto-continue` - Interactive mode
 
-### Additional Logs
+Run `poetry run python -m openhands.core.main --help` for all options.
 
-For the headless mode to log all the agent actions, in the terminal run: `export LOG_ALL_EVENTS=true`
+Set `export LOG_ALL_EVENTS=true` to log all agent actions.

docs/usage/llms/llms.mdx

@@ -10,7 +10,8 @@ This section is for users who want to connect OpenHands to different LLMs.
 ## Model Recommendations
 
 Based on our evaluations of language models for coding tasks (using the SWE-bench dataset), we can provide some
-recommendations for model selection. Our latest benchmarking results can be found in [this spreadsheet](https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=0).
+recommendations for model selection. Our latest benchmarking results can be found in
+[this spreadsheet](https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=0).
 
 Based on these findings and community feedback, these are the latest models that have been verified to work reasonably well with OpenHands:
 
@@ -20,6 +21,7 @@ Based on these findings and community feedback, these are the latest models that
 - [openai/o4-mini](https://openai.com/index/introducing-o3-and-o4-mini/)
 - [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/)
+- [moonshot/kimi-k2-0711-preview](https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2)
 
 If you have successfully run OpenHands with specific providers, we encourage you to open a PR to share your setup process
 to help others using the same provider!
@@ -70,9 +72,21 @@ We have a few guides for running OpenHands with specific model providers:
 - [Groq](/usage/llms/groq)
 - [Local LLMs with SGLang or vLLM](/usage/llms/local-llms)
 - [LiteLLM Proxy](/usage/llms/litellm-proxy)
+- [Moonshot AI](/usage/llms/moonshot)
 - [OpenAI](/usage/llms/openai-llms)
+- [OpenHands](/usage/llms/openhands-llms)
 - [OpenRouter](/usage/llms/openrouter)
 
+## Model Customization
+
+LLM providers have specific settings that can be customized to optimize their performance with OpenHands, such as:
+
+- **Custom Tokenizers**: For specialized models, you can add a suitable tokenizer.
+- **Native Tool Calling**: Toggle native function/tool calling capabilities.
+
+For detailed information about model customization, see
+[LLM Configuration Options](/usage/configuration-options#llm-configuration).
+
 ### API retries and rate limits
 
 LLM providers typically have rate limits, sometimes very low, and may require retries. OpenHands will automatically

docs/usage/llms/local-llms.mdx

@@ -6,75 +6,85 @@ description: When using a Local LLM, OpenHands may have limited functionality. I
 ## News
 
 - 2025/05/21: We collaborated with Mistral AI and released [Devstral Small](https://mistral.ai/news/devstral) that achieves [46.8% on SWE-Bench Verified](https://github.com/SWE-bench/experiments/pull/228)!
-- 2025/03/31: We released an open model OpenHands LM v0.1 32B that achieves 37.1% on SWE-Bench Verified
+- 2025/03/31: We released an open model OpenHands LM 32B v0.1 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)).
 
+## Quickstart: Running OpenHands with a Local LLM using LM Studio
 
-## Quickstart: Running OpenHands on Your Macbook
+This guide explains how to serve a local Devstral LLM using [LM Studio](https://lmstudio.ai/) and have OpenHands connect to it.
 
-### Serve the model on your Macbook
+We recommend:
+- **LM Studio** as the local model server, which handles metadata downloads automatically and offers a simple, user-friendly interface for configuration.
+- **Devstral Small 2505** as the LLM for software development, trained on real GitHub issues and optimized for agent-style workflows like OpenHands.
 
-We recommend using [LMStudio](https://lmstudio.ai/) for serving these models locally.
+### Hardware Requirements
 
-1. Download [LM Studio](https://lmstudio.ai/) and install it
+Running Devstral requires a recent GPU with at least 16GB of VRAM, or a Mac with Apple Silicon (M1, M2, etc.) with at least 32GB of RAM.
 
-2. Download the model:
-   - Option 1: Directly download the LLM from [this link](https://lmstudio.ai/model/devstral-small-2505-mlx) or by searching for the name `Devstral-Small-2505` in LM Studio
-   - Option 2: Download a LLM in GGUF format. For example, to download [Devstral Small 2505 GGUF](https://huggingface.co/mistralai/Devstral-Small-2505_gguf), using `huggingface-cli download mistralai/Devstral-Small-2505_gguf --local-dir mistralai/Devstral-Small-2505_gguf`. Then in bash terminal, run `lms import {model_name}` in the directory where you've downloaded the model checkpoint (e.g. run `lms import devstralQ4_K_M.gguf` in `mistralai/Devstral-Small-2505_gguf`)
+### 1. Install LM Studio
 
-3. Open LM Studio application, you should first switch to `power user` mode, and then open the developer tab:
+Download and install the LM Studio desktop app from [lmstudio.ai](https://lmstudio.ai/).
 
-![image](./screenshots/1_select_power_user.png)
+### 2. Download Devstral Small
 
-4. Then click `Select a model to load` on top of the application:
+1. Make sure to set the User Interface Complexity Level to "Power User", by clicking on the appropriate label at the bottom of the window.
+2. Click the "Discover" button (Magnifying Glass icon) on the left navigation bar to open the Models download page.
 
-![image](./screenshots/2_select_model.png)
+![image](./screenshots/01_lm_studio_open_model_hub.png)
 
-5. And choose the model you want to use, holding `option` on mac to enable advanced loading options:
+3. Search for the "Devstral Small 2505" model, confirm it's the official Mistral AI (mistralai) model, then proceed to download.
 
-![image](./screenshots/3_select_devstral.png)
+![image](./screenshots/02_lm_studio_download_devstral.png)
 
-6. You should then pick an appropriate context window for OpenHands based on your hardware configuration (larger than 32768 is recommended for using OpenHands, but too large may cause you to run out of memory); Flash attention is also recommended if it works on your machine.
+4. Wait for the download to finish.
 
-![image](./screenshots/4_set_context_window.png)
+### 3. Load the Model
 
-7. And you should start the server (if it is not already in `Running` status), un-toggle `Serve on Local Network` and remember the port number of the LMStudio URL (`1234` is the port number for `http://127.0.0.1:1234` in this example):
+1. Click the "Developer" button (Console icon) on the left navigation bar to open the Developer Console.
+2. Click the "Select a model to load" dropdown at the top of the application window.
 
-![image](./screenshots/5_copy_url.png)
+![image](./screenshots/03_lm_studio_open_load_model.png)
 
-8. Finally, you can click the `copy` button near model name to copy the model name (`imported-models/uncategorized/devstralq4_k_m.gguf` in this example):
+3. Enable the "Manually choose model load parameters" switch.
+4. Select 'Devstral Small 2505' from the model list.
 
-![image](./screenshots/6_copy_to_get_model_name.png)
+![image](./screenshots/04_lm_studio_setup_devstral_part_1.png)
 
-### Start OpenHands with locally served model
+5. Enable the "Show advanced settings" switch at the bottom of the Model settings flyout to show all the available settings.
+6. Set "Context Length" to at least 32768 and enable Flash Attention.
+7. Click "Load Model" to start loading the model.
 
-Check [the installation guide](/usage/local-setup) to make sure you have all the prerequisites for running OpenHands.
+![image](./screenshots/05_lm_studio_setup_devstral_part_2.png)
+
+### 4. Start the LLM server
+
+1. Enable the switch next to "Status" at the top-left of the Window.
+2. Take note of the Model API Identifier shown on the sidebar on the right.
+
+![image](./screenshots/06_lm_studio_start_server.png)
+
+### 5. Start OpenHands
+
+1. Check [the installation guide](/usage/local-setup) and ensure all prerequisites are met before running OpenHands, then run:
 
 ```bash
-export LMSTUDIO_MODEL_NAME="imported-models/uncategorized/devstralq4_k_m.gguf" # <- Replace this with the model name you copied from LMStudio
-export LMSTUDIO_URL="http://host.docker.internal:1234"  # <- Replace this with the port from LMStudio
-
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik
-
-mkdir -p ~/.openhands && echo '{"language":"en","agent":"CodeActAgent","max_iterations":null,"security_analyzer":null,"confirmation_mode":false,"llm_model":"lm_studio/'$LMSTUDIO_MODEL_NAME'","llm_api_key":"dummy","llm_base_url":"'$LMSTUDIO_URL/v1'","remote_runtime_resource_factor":null,"github_token":null,"enable_default_condenser":true,"user_consents_to_analytics":true}' > ~/.openhands/settings.json
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.45
+    docker.all-hands.dev/all-hands-ai/openhands:0.50
 ```
 
-> **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
-
-Once your server is running -- you can visit `http://localhost:3000` in your browser to use OpenHands with local Devstral model:
+2. Wait until the server is running (see log below):
 ```
 Digest: sha256:e72f9baecb458aedb9afc2cd5bc935118d1868719e55d50da73190d3a85c674f
-Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.45
+Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.50
 Starting OpenHands...
 Running OpenHands as root
 14:22:13 - openhands:INFO: server_config.py:50 - Using config class None
@@ -84,65 +94,109 @@ INFO:     Application startup complete.
 INFO:     Uvicorn running on http://0.0.0.0:3000 (Press CTRL+C to quit)
 ```
 
+3. Visit `http://localhost:3000` in your browser.
 
-## Advanced: Serving LLM on GPUs
+### 6. Configure OpenHands to use the LLM server
 
-### Download model checkpoints
+Once you open OpenHands in your browser, you'll need to configure it to use the local LLM server you just started.
 
-<Note>
-The model checkpoints downloaded here should NOT be in GGUF format.
-</Note>
+When started for the first time, OpenHands will prompt you to set up the LLM provider.
 
-For example, to download [OpenHands LM 32B v0.1](https://huggingface.co/all-hands/openhands-lm-32b-v0.1):
+1. Click "see advanced settings" to open the LLM Settings page.
+
+![image](./screenshots/07_openhands_open_advanced_settings.png)
+
+2. Enable the "Advanced" switch at the top of the page to show all the available settings.
+
+3. Set the following values:
+    - **Custom Model**: `openai/mistralai/devstral-small-2505` (the Model API identifier from LM Studio, prefixed with "openai/")
+    - **Base URL**: `http://host.docker.internal:1234/v1`
+    - **API Key**: `local-llm`
+
+4. Click "Save Settings" to save the configuration.
+
+![image](./screenshots/08_openhands_configure_local_llm_parameters.png)
+
+That's it! You can now start using OpenHands with the local LLM server.
+
+If you encounter any issues, let us know on [Slack](https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA) or [Discord](https://discord.gg/ESHStjSjD4).
+
+## Advanced: Alternative LLM Backends
+
+This section describes how to run local LLMs with OpenHands using alternative backends like Ollama, SGLang, or vLLM — without relying on LM Studio.
+
+### Create an OpenAI-Compatible Endpoint with Ollama
+
+- Install Ollama following [the official documentation](https://ollama.com/download).
+- Example launch command for Devstral Small 2505:
 
 ```bash
-huggingface-cli download all-hands/openhands-lm-32b-v0.1 --local-dir all-hands/openhands-lm-32b-v0.1
+# ⚠️ WARNING: OpenHands requires a large context size to work properly.
+# When using Ollama, set OLLAMA_CONTEXT_LENGTH to at least 32768.
+# The default (4096) is way too small — not even the system prompt will fit, and the agent will not behave correctly.
+OLLAMA_CONTEXT_LENGTH=32768 OLLAMA_HOST=0.0.0.0:11434 OLLAMA_KEEP_ALIVE=-1 nohup ollama serve &
+ollama pull devstral:latest
 ```
 
-### Create an OpenAI-Compatible Endpoint With SGLang
+### Create an OpenAI-Compatible Endpoint with vLLM or SGLang
+
+First, download the model checkpoints. For [Devstral Small 2505](https://huggingface.co/mistralai/Devstral-Small-2505):
+
+```bash
+huggingface-cli download mistralai/Devstral-Small-2505 --local-dir mistralai/Devstral-Small-2505
+```
+
+#### Serving the model using 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):
+- Example launch command for Devstral Small 2505 (with at least 2 GPUs):
 
 ```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 \
+    --model mistralai/Devstral-Small-2505 \
+    --served-model-name Devstral-Small-2505 \
     --port 8000 \
     --tp 2 --dp 1 \
     --host 0.0.0.0 \
     --api-key mykey --context-length 131072
 ```
 
-### Create an OpenAI-Compatible Endpoint with vLLM
+#### Serving the model using vLLM
 
 - 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):
+- Example launch command for Devstral Small 2505 (with at least 2 GPUs):
 
 ```bash
-vllm serve all-hands/openhands-lm-32b-v0.1 \
+vllm serve mistralai/Devstral-Small-2505 \
     --host 0.0.0.0 --port 8000 \
     --api-key mykey \
     --tensor-parallel-size 2 \
-    --served-model-name openhands-lm-32b-v0.1
+    --served-model-name Devstral-Small-2505 \
     --enable-prefix-caching
 ```
 
-### Create an OpenAI-Compatible Endpoint with Ollama
+If you are interested in further improved inference speed, you can also try Snowflake's version
+of vLLM, [ArcticInference](https://www.snowflake.com/en/engineering-blog/fast-speculative-decoding-vllm-arctic/),
+which can achieve up to 2x speedup in some cases.
 
-- Install Ollama following [the official documentation](https://ollama.com/download).
-- For Ollama configuration, use `ollama/<modelname>` as custom model in web. Api key also can be set to `ollama`.
-- Example launch command for Devstral LM 24B:
+1. Install the Arctic Inference library that automatically patches vLLM:
 
 ```bash
-OLLAMA_CONTEXT_LENGTH=32768 OLLAMA_HOST=0.0.0.0:11434 OLLAMA_KEEP_ALIVE=-1 nohup ollama serve&
-#The minimum context size is ~8196, even the system prompt won't fit smaller
-ollama pull devstral:latest
+pip install git+https://github.com/snowflakedb/ArcticInference.git
 ```
 
-## Advanced: Run and Configure OpenHands
+2. Run the launch command with speculative decoding enabled:
 
-### Run OpenHands
+```bash
+vllm serve mistralai/Devstral-Small-2505 \
+    --host 0.0.0.0 --port 8000 \
+    --api-key mykey \
+    --tensor-parallel-size 2 \
+    --served-model-name Devstral-Small-2505 \
+    --speculative-config '{"method": "suffix"}'
+```
+
+### Run OpenHands (Alternative Backends)
 
 #### Using Docker
 
@@ -151,28 +205,20 @@ Run OpenHands using [the official docker run command](../installation#start-the-
 #### Using Development Mode
 
 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:
-
-```
-[core]
-workspace_base="/path/to/your/workspace"
-
-[llm]
-model="openhands-lm-32b-v0.1"
-ollama_base_url="http://localhost:8000"
-```
 
 Start OpenHands using `make run`.
 
-### Configure OpenHands
+### Configure OpenHands (Alternative Backends)
 
-Once OpenHands is running, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
-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`)
+Once OpenHands is running, open the Settings page in the UI and go to the `LLM` tab.
 
-<Note>
-**API Key for Local LLMs**: When using local LLM servers (including Ollama, LM Studio, vLLM, etc.), you can enter any value as the API key if your server doesn't require authentication. The OpenHands UI requires an API key to be entered, but for local servers without authentication, you can use any placeholder value like `local-key`, `test123`, or `dummy`.
-</Note>
+1. Click **"see advanced settings"** to access the full configuration panel.
+2. Enable the **Advanced** toggle at the top of the page.
+3. Set the following parameters, if you followed the examples above:
+   - **Custom Model**: `openai/<served-model-name>`
+     e.g. `openai/devstral` if you're using Ollama, or `openai/Devstral-Small-2505` for SGLang or vLLM.
+   - **Base URL**: `http://host.docker.internal:<port>/v1`
+     Use port `11434` for Ollama, or `8000` for SGLang and vLLM.
+   - **API Key**:
+     - For **Ollama**: any placeholder value (e.g. `dummy`, `local-llm`)
+     - For **SGLang** or **vLLM**: use the same key provided when starting the server (e.g. `mykey`)

docs/usage/llms/moonshot.mdx

@@ -0,0 +1,25 @@
+---
+title: Moonshot AI
+description: How to use Moonshot AI models with OpenHands
+---
+
+## Using Moonshot AI with OpenHands
+
+[Moonshot AI](https://platform.moonshot.ai/) offers several powerful models, including Kimi-K2, which has been verified to work well with OpenHands.
+
+### Setup
+
+1. Sign up for an account at [Moonshot AI Platform](https://platform.moonshot.ai/)
+2. Generate an API key from your account settings
+3. Configure OpenHands to use Moonshot AI:
+
+| Setting | Value |
+| --- | --- |
+| LLM Provider | `moonshot` |
+| LLM Model | `kimi-k2-0711-preview` |
+| API Key | Your Moonshot API key |
+
+### Recommended Models
+
+- `moonshot/kimi-k2-0711-preview` - Kimi-K2 is Moonshot's most powerful model with a 131K context window, function calling support, and web search capabilities.
+

docs/usage/llms/openhands-llms.mdx

@@ -0,0 +1,34 @@
+---
+title: OpenHands
+description: OpenHands LLM provider with access to state-of-the-art (SOTA) agentic coding models.
+---
+
+## Obtain Your OpenHands LLM API Key
+
+1. [Log in to OpenHands Cloud](/usage/cloud/openhands-cloud).
+2. Go to the Settings page and navigate to the `API Keys` tab.
+3. Copy your `LLM API Key`.
+
+![OpenHands LLM API Key](/static/img/openhands-llm-api-key.png)
+
+## Configuration
+
+When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
+- `LLM Provider` to `OpenHands`
+- `LLM Model` to the model you will be using (e.g. claude-sonnet-4-20250514)
+- `API Key` to your OpenHands LLM API key copied from above
+
+## Using OpenHands LLM Provider in the CLI
+
+1. [Run OpenHands CLI](/usage/how-to/cli-mode).
+2. To select OpenHands as the LLM provider:
+  - If this is your first time running the CLI, choose `openhands` and then select the model that you would like to use.
+  - If you have previously run the CLI, run the `/settings` command and select to modify the `Basic` settings. Then
+    choose `openhands` and finally the model.
+
+![OpenHands Provider in CLI](/static/img/openhands-provider-cli.png)
+
+## Pricing
+
+Pricing follows official API provider rates.
+[You can view model prices here.](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json)

docs/usage/local-setup.mdx

@@ -67,17 +67,17 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 ### Start the App
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.45-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.50-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.45
+    docker.all-hands.dev/all-hands-ai/openhands:0.50
 ```
 
 > **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.

docs/usage/mcp.mdx

@@ -1,6 +1,7 @@
 ---
 title: Model Context Protocol (MCP)
-description: This page outlines how to configure and use the Model Context Protocol (MCP) in OpenHands, allowing you to extend the agent's capabilities with custom tools.
+description: This page outlines how to configure and use the Model Context Protocol (MCP) in OpenHands, allowing you
+  to extend the agent's capabilities with custom tools.
 ---
 
 ## Overview
@@ -9,6 +10,25 @@ Model Context Protocol (MCP) is a mechanism that allows OpenHands to communicate
 servers can provide additional functionality to the agent, such as specialized data processing, external API access,
 or custom tools. MCP is based on the open standard defined at [modelcontextprotocol.io](https://modelcontextprotocol.io).
 
+<Note>
+MCP is currently not available on OpenHands Cloud. This feature is only available when running OpenHands locally.
+</Note>
+
+### How MCP Works
+
+When OpenHands starts, it:
+
+1. Reads the MCP configuration.
+2. Connects to any configured SSE and SHTTP servers.
+3. Starts any configured stdio servers.
+4. Registers the tools provided by these servers with the agent.
+
+The agent can then use these tools just like any built-in tool. When the agent calls an MCP tool:
+
+1. OpenHands routes the call to the appropriate MCP server.
+2. The server processes the request and returns a response.
+3. OpenHands converts the response to an observation and presents it to the agent.
+
 ## Configuration
 
 MCP configuration can be defined in:
@@ -28,6 +48,15 @@ sse_servers = [
     {url="https://secure-example.com/mcp", api_key="your-api-key"}
 ]
 
+# SHTTP Servers - External servers that communicate via Streamable HTTP
+shttp_servers = [
+    # Basic SHTTP server with just a URL
+    "http://example.com:8080/mcp",
+
+    # SHTTP server with API key authentication
+    {url="https://secure-example.com/mcp", api_key="your-api-key"}
+]
+
 # Stdio Servers - Local processes that communicate via standard input/output
 stdio_servers = [
     # Basic stdio server
@@ -56,6 +85,22 @@ SSE servers are configured using either a string URL or an object with the follo
   - Type: `str`
   - Description: The URL of the SSE server
 
+- `api_key` (optional)
+  - Type: `str`
+  - Description: API key for authentication
+
+### SHTTP Servers
+
+SHTTP (Streamable HTTP) servers are configured using either a string URL or an object with the following properties:
+
+- `url` (required)
+  - Type: `str`
+  - Description: The URL of the SHTTP server
+
+- `api_key` (optional)
+  - Type: `str`
+  - Description: API key for authentication
+
 ### Stdio Servers
 
 Stdio servers are configured using an object with the following properties:
@@ -78,17 +123,22 @@ Stdio servers are configured using an object with the following properties:
   - Default: `{}`
   - Description: Environment variables to set for the server process
 
-## How MCP Works
+## Transport Protocols
 
-When OpenHands starts, it:
+OpenHands supports three different MCP transport protocols:
 
-1. Reads the MCP configuration.
-2. Connects to any configured SSE servers.
-3. Starts any configured stdio servers.
-4. Registers the tools provided by these servers with the agent.
+### Server-Sent Events (SSE)
+SSE is a legacy HTTP-based transport that uses Server-Sent Events for server-to-client communication and HTTP POST requests for client-to-server communication. This transport is suitable for basic streaming scenarios but has limitations in session management and connection resumability.
 
-The agent can then use these tools just like any built-in tool. When the agent calls an MCP tool:
+### Streamable HTTP (SHTTP)
+SHTTP is the modern HTTP-based transport protocol that provides enhanced features over SSE:
 
-1. OpenHands routes the call to the appropriate MCP server.
-2. The server processes the request and returns a response.
-3. OpenHands converts the response to an observation and presents it to the agent.
+- **Improved Session Management**: Supports stateful sessions with session IDs for maintaining context across requests
+- **Connection Resumability**: Can resume broken connections and replay missed messages using event IDs
+- **Bidirectional Communication**: Uses HTTP POST for client-to-server and optional SSE streams for server-to-client communication
+- **Better Error Handling**: Enhanced error reporting and recovery mechanisms
+
+SHTTP is the recommended transport for HTTP-based MCP servers as it provides better reliability and features compared to the legacy SSE transport.
+
+### Standard Input/Output (stdio)
+Stdio transport enables communication through standard input and output streams, making it ideal for local integrations and command-line tools. This transport is used for locally executed MCP servers that run as separate processes.

docs/usage/prompting/microagents-org.mdx

@@ -11,6 +11,8 @@ accordingly. However, they are applied to all repositories belonging to the orga
 Add a `.openhands` repository under the organization or user and create a `microagents` directory and place the
 microagents in that directory.
 
+For GitLab organizations, use `openhands-config` as the repository name instead of `.openhands`, since GitLab doesn't support repository names starting with non-alphanumeric characters.
+
 ## Example
 
 General microagent file example for organization `Great-Co` located inside the `.openhands` repository:
@@ -20,3 +22,14 @@ General microagent file example for organization `Great-Co` located inside the `
 * Document interfaces and public APIs; use implementation comments only for non-obvious logic.
 * Follow the same naming convention for variables, classes, constants, etc. already used in each repository.
 ```
+
+For GitLab organizations, the same microagent would be located inside the `openhands-config` repository.
+
+## User Microagents When Running Openhands on Your Own
+
+<Note>
+  This works with CLI, headless and development modes. It does not work out of the box when running OpenHands using the docker command.
+</Note>
+
+When running OpenHands on your own, you can place microagents in the `~/.openhands/microagents` folder on your local
+system and OpenHands will always load it for all your conversations.

docs/usage/runtimes/daytona.mdx

@@ -3,20 +3,6 @@ title: Daytona Runtime
 description: You can use [Daytona](https://www.daytona.io/) as a runtime provider.
 ---
 
-## Installation
-
-The Daytona runtime is available as an optional runtime. To use it, install OpenHands with the Daytona extra:
-
-```bash
-pip install openhands-ai[daytona]
-```
-
-Or to install all available runtimes:
-
-```bash
-pip install openhands-ai[all-runtimes]
-```
-
 ## Step 1: Retrieve Your Daytona API Key
 1. Visit the [Daytona Dashboard](https://app.daytona.io/dashboard/keys).
 2. Click **"Create Key"**.

docs/usage/runtimes/docker.mdx

@@ -3,8 +3,6 @@ title: Docker Runtime
 description: This is the default Runtime that's used when you start OpenHands.
 ---
 
-This is the default Runtime that's used when you start OpenHands.
-
 ## Image
 The `SANDBOX_RUNTIME_CONTAINER_IMAGE` from nikolaik is a pre-built runtime image
 that contains our Runtime server, as well as some basic utilities for Python and NodeJS.

docs/usage/runtimes/e2b.mdx

@@ -0,0 +1,44 @@
+---
+title: E2B Runtime
+description: E2B is an open-source secure cloud environment (sandbox) made for running AI-generated code and agents.
+---
+
+[E2B](https://e2b.dev) offers [Python](https://pypi.org/project/e2b/) and [JS/TS](https://www.npmjs.com/package/e2b)
+SDK to spawn and control these sandboxes.
+
+## Getting started
+
+1. [Get your API key](https://e2b.dev/docs/getting-started/api-key)
+
+1. Set your E2B API key to the `E2B_API_KEY` env var when starting the Docker container
+
+1. **Optional** - Install the CLI with NPM.
+    ```sh
+    npm install -g @e2b/cli@latest
+    ```
+    Full CLI API is [here](https://e2b.dev/docs/cli/installation).
+
+## OpenHands sandbox
+
+You can use the E2B CLI to create a custom sandbox with a Dockerfile. Read the full guide
+[here](https://e2b.dev/docs/guide/custom-sandbox). The premade OpenHands sandbox for E2B is set up in the `containers`
+directory. and it's called `openhands`.
+
+## Debugging
+
+You can connect to a running E2B sandbox with E2B CLI in your terminal.
+
+- List all running sandboxes (based on your API key)
+    ```sh
+    e2b sandbox list
+    ```
+
+- Connect to a running sandbox
+    ```sh
+    e2b sandbox connect <sandbox-id>
+    ```
+
+## Links
+
+- [E2B Docs](https://e2b.dev/docs)
+- [E2B GitHub](https://github.com/e2b-dev/e2b)

docs/usage/runtimes/local.mdx

@@ -1,6 +1,8 @@
 ---
 title: Local Runtime
-description: 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.
+description: 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.
 ---
 
 <Warning>

docs/usage/runtimes/modal.mdx

@@ -0,0 +1,14 @@
+---
+title: Modal Runtime
+---
+
+Our partners at [Modal](https://modal.com/) have provided a runtime for OpenHands.
+To use the Modal Runtime, create an account, and then [create an API key.](https://modal.com/settings)
+
+You'll then need to set the following environment variables when starting OpenHands:
+```bash
+docker run # ...
+    -e RUNTIME=modal \
+    -e MODAL_API_TOKEN_ID="your-id" \
+    -e MODAL_API_TOKEN_SECRET="modal-api-key" \
+```

docs/usage/runtimes/overview.mdx

@@ -19,5 +19,18 @@ OpenHands supports several different runtime environments:
 - [Docker Runtime](/usage/runtimes/docker) - The default runtime that uses Docker containers for isolation (recommended for most users).
 - [OpenHands Remote Runtime](/usage/runtimes/remote) - Cloud-based runtime for parallel execution (beta).
 - [Local Runtime](/usage/runtimes/local) - Direct execution on your local machine without Docker.
-- [Daytona Runtime](/usage/runtimes/daytona) - Runtime provided by Daytona.
-- [Third-party Runtimes](https://github.com/All-Hands-AI/third-party-runtimes) - These runtimes are supported by their developers, not by OpenHands. Please find them in the repository linked here if you would like to run on third-party infrastructure providers.
+
+### Third-Party Runtimes
+
+The following third-party runtimes are available when you install the `third_party_runtimes` extra:
+
+```bash
+pip install openhands-ai[third_party_runtimes]
+```
+
+- [E2B Runtime](/usage/runtimes/e2b) - Open source runtime using E2B sandboxes.
+- [Modal Runtime](/usage/runtimes/modal) - Serverless runtime using Modal infrastructure.
+- [Runloop Runtime](/usage/runtimes/runloop) - Cloud runtime using Runloop infrastructure.
+- [Daytona Runtime](/usage/runtimes/daytona) - Development environment runtime using Daytona.
+
+**Note**: These third-party runtimes are supported by their respective developers, not by the OpenHands team. For issues specific to these runtimes, please refer to their documentation or contact their support teams.

docs/usage/runtimes/remote.mdx

@@ -1,7 +1,11 @@
 ---
 title: Remote Runtime
-description: 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.
+description: 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!

docs/usage/runtimes/runloop.mdx

@@ -0,0 +1,32 @@
+---
+title: Runloop Runtime
+description: Runloop provides a fast, secure and scalable AI sandbox (Devbox). Check out the
+  [runloop docs](https://docs.runloop.ai/overview/what-is-runloop) for more detail.
+---
+
+## Access
+Runloop is currently available in a closed beta. For early access, or
+just to say hello, sign up at https://www.runloop.ai/hello
+
+## Set up
+With your runloop API,
+```bash
+export RUNLOOP_API_KEY=<your-api-key>
+```
+
+Configure the runtime
+```bash
+export RUNTIME="runloop"
+```
+
+## Interact with your devbox
+Runloop provides additional tools to interact with your Devbox based
+runtime environment. See the [docs](https://docs.runloop.ai/tools) for an up
+to date list of tools.
+
+### Dashboard
+View logs, ssh into, or view your Devbox status from the [dashboard](https://platform.runloop.ai)
+
+### CLI
+Use the Runloop CLI to view logs, execute commands, and more.
+See the setup instructions [here](https://docs.runloop.ai/tools/cli)

docs/usage/search-engine-setup.mdx

@@ -1,6 +1,6 @@
 ---
 title: Search Engine Setup
-description: Configure OpenHands to use Tavily as a search engine
+description: Configure OpenHands to use Tavily as a search engine.
 ---
 
 ## Setting Up Search Engine in OpenHands
@@ -11,10 +11,10 @@ OpenHands can be configured to use [Tavily](https://tavily.com/) as a search eng
 
 To use the search functionality in OpenHands, you'll need to obtain a Tavily API key:
 
-1. Visit [Tavily's website](https://tavily.com/) and sign up for an account
-2. Navigate to the API section in your dashboard
-3. Generate a new API key
-4. Copy the API key (it should start with `tvly-`)
+1. Visit [Tavily's website](https://tavily.com/) and sign up for an account.
+2. Navigate to the API section in your dashboard.
+3. Generate a new API key.
+4. Copy the API key (it should start with `tvly-`).
 
 ### Configuring Search in OpenHands
 
@@ -22,13 +22,12 @@ Once you have your Tavily API key, you can configure OpenHands to use it:
 
 #### In the OpenHands UI
 
-1. Open OpenHands and navigate to the Settings page by clicking the gear icon
-2. In the LLM settings tab, locate the "Search API Key (Tavily)" field
-3. Enter your Tavily API key (starting with `tvly-`)
-4. Click "Save" to apply the changes
+1. Open OpenHands and navigate to the Settings page.
+2. Under the `LLM` tab, enter your Tavily API key (starting with `tvly-`) in the `Search API Key (Tavily)` field.
+3. Click `Save` to apply the changes.
 
 <Note>
-The search API key field is optional. If you don't provide a key, the search functionality will not be available to the agent.
+  The search API key field is optional. If you don't provide a key, the search functionality will not be available to the agent.
 </Note>
 
 #### Using Configuration Files
@@ -45,22 +44,23 @@ search_api_key = "tvly-your-api-key-here"
 
 When the search engine is configured:
 
-1. The agent can decide to search the web when it needs external information
-2. Search queries are sent to Tavily's API via [Tavily's MCP server](https://github.com/tavily-ai/tavily-mcp) which includes a variety of [tools](https://docs.tavily.com/documentation/api-reference/introduction) (search, extract, crawl, map).
-3. Results are returned and incorporated into the agent's context
-4. The agent can use this information to provide more accurate and up-to-date responses
+- The agent can decide to search the web when it needs external information.
+- Search queries are sent to Tavily's API via [Tavily's MCP server](https://github.com/tavily-ai/tavily-mcp) which
+  includes a variety of [tools](https://docs.tavily.com/documentation/api-reference/introduction) (search, extract, crawl, map).
+- Results are returned and incorporated into the agent's context.
+- The agent can use this information to provide more accurate and up-to-date responses.
 
 ### Limitations
 
-- Search results depend on Tavily's coverage and freshness
-- Usage may be subject to Tavily's rate limits and pricing tiers
-- The agent will only search when it determines that external information is needed
+- Search results depend on Tavily's coverage and freshness.
+- Usage may be subject to Tavily's rate limits and pricing tiers.
+- The agent will only search when it determines that external information is needed.
 
 ### Troubleshooting
 
 If you encounter issues with the search functionality:
 
-- Verify that your API key is correct and active
-- Check that your API key starts with `tvly-`
-- Ensure you have an active internet connection
-- Check Tavily's status page for any service disruptions
+- Verify that your API key is correct and active.
+- Check that your API key starts with `tvly-`.
+- Ensure you have an active internet connection.
+- Check Tavily's status page for any service disruptions.

docs/usage/troubleshooting/troubleshooting.mdx

@@ -38,6 +38,21 @@ On initial prompt, an error is seen with `Permission Denied` or `PermissionError
 * If mounting a local directory, ensure your `WORKSPACE_BASE` has the necessary permissions for the user running
   OpenHands.
 
+### Internal Server Error. Ports are not available
+
+**Description**
+
+When running on Windows, the error `Internal Server Error ("ports are not available: exposing port TCP
+...: bind: An attempt was made to access a socket in a
+way forbidden by its access permissions.")` is encountered.
+
+**Resolution**
+
+* Run the following command in PowerShell, as Administrator to reset the NAT service and release the ports:
+```
+Restart-Service -Name "winnat"
+```
+
 ### Unable to access VS Code tab via local IP
 
 **Description**

evaluation/README.md

@@ -101,13 +101,14 @@ The OpenHands evaluation harness supports a wide variety of benchmarks across [s
 - SWE-Bench: [`evaluation/benchmarks/swe_bench`](./benchmarks/swe_bench)
 - HumanEvalFix: [`evaluation/benchmarks/humanevalfix`](./benchmarks/humanevalfix)
 - BIRD: [`evaluation/benchmarks/bird`](./benchmarks/bird)
-- BioCoder: [`evaluation/benchmarks/ml_bench`](./benchmarks/ml_bench)
+- BioCoder: [`evaluation/benchmarks/biocoder`](./benchmarks/biocoder)
 - ML-Bench: [`evaluation/benchmarks/ml_bench`](./benchmarks/ml_bench)
 - APIBench: [`evaluation/benchmarks/gorilla`](./benchmarks/gorilla/)
 - ToolQA: [`evaluation/benchmarks/toolqa`](./benchmarks/toolqa/)
 - AiderBench: [`evaluation/benchmarks/aider_bench`](./benchmarks/aider_bench/)
 - Commit0: [`evaluation/benchmarks/commit0_bench`](./benchmarks/commit0_bench/)
 - DiscoveryBench: [`evaluation/benchmarks/discoverybench`](./benchmarks/discoverybench/)
+- TerminalBench: [`evaluation/benchmarks/terminal_bench`](./benchmarks/terminal_bench)
 
 ### Web Browsing
 

evaluation/benchmarks/commit0/run_infer.py

@@ -117,6 +117,7 @@ def get_config(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         max_iterations=metadata.max_iterations,
+        enable_browser=RUN_WITH_BROWSING,
         runtime=os.environ.get('RUNTIME', 'docker'),
         sandbox=sandbox_config,
         # do not mount workspace

evaluation/benchmarks/gaia/run_infer.py

@@ -3,13 +3,20 @@ import copy
 import functools
 import os
 import re
+import shutil
+import zipfile
 
 import huggingface_hub
 import pandas as pd
 from datasets import load_dataset
+from PIL import Image
 from pydantic import SecretStr
 
 from evaluation.benchmarks.gaia.scorer import question_scorer
+from evaluation.benchmarks.gaia.utils import (
+    image_to_jpg_base64_url,
+    image_to_png_base64_url,
+)
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
@@ -97,27 +104,44 @@ def initialize_runtime(
     if instance['file_name'] != '':
         # if this question comes with a file, we need to save it to the workspace
         assert metadata.data_split is not None
+        extension_name = instance['file_name'].split('.')[-1]
         src_file = os.path.join(
             DATASET_CACHE_DIR, '2023', metadata.data_split, instance['file_name']
         )
         assert os.path.exists(src_file)
-        dest_file = os.path.join('/workspace', instance['file_name'])
-        runtime.copy_to(src_file, dest_file)
+        if extension_name == 'zip':
+            temp_dir = os.path.join(
+                DATASET_CACHE_DIR, '2023', metadata.data_split, 'tmp_file'
+            )
+            os.makedirs(temp_dir, exist_ok=True)
+            with zipfile.ZipFile(src_file, 'r') as zip_ref:
+                zip_ref.extractall(temp_dir)
+            for root, dirs, files in os.walk(temp_dir):
+                for file in files:
+                    dest_file = '/workspace'
+                    runtime.copy_to(os.path.join(root, file), dest_file)
+            shutil.rmtree(temp_dir)
+        elif extension_name not in ['jpg', 'png']:
+            dest_file = '/workspace'
+            runtime.copy_to(src_file, dest_file)
 
-        # rename to file.extension_name
-        extension_name = instance['file_name'].split('.')[-1]
-        action = CmdRunAction(
-            command=f'mv /workspace/{instance["file_name"]} /workspace/file.{extension_name}'
-        )
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        assert obs.exit_code == 0
+            # rename to file.extension_name
+            action = CmdRunAction(
+                command=f'mv /workspace/{instance["file_name"]} /workspace/file.{extension_name}'
+            )
+            logger.info(action, extra={'msg_type': 'ACTION'})
+            obs = runtime.run_action(action)
+            assert obs.exit_code == 0
 
     action = CmdRunAction(command='cd /workspace')
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     assert obs.exit_code == 0
 
+    action = CmdRunAction(
+        command='apt-get update && apt-get install -y ffmpeg && apt-get install -y ffprobe'
+    )
+    runtime.run_action(action)
     logger.info(f'{"-" * 50} END Runtime Initialization Fn {"-" * 50}')
 
 
@@ -151,8 +175,31 @@ Here is the task:
         task_question=instance['Question'],
     )
     logger.info(f'Instruction: {instruction}')
+    image_urls = []
     if dest_file:
-        instruction += f'\n\nThe mentioned file is provided in the workspace at: {dest_file.split("/")[-1]}'
+        if extension_name not in ['jpg', 'png', 'zip']:
+            instruction += f'To solve this task you will have to use the attached file provided in the workspace at location: {dest_file}\n\n'
+        elif extension_name == 'zip':
+            filenames = []
+            src_file = os.path.join(
+                DATASET_CACHE_DIR, '2023', metadata.data_split, instance['file_name']
+            )
+            with zipfile.ZipFile(src_file, 'r') as zip_ref:
+                filenames = zip_ref.namelist()
+
+            filenames = [f'/workspace/{file}' for file in filenames]
+            filenames = ', '.join(filenames)
+            instruction += f'To solve this task you will have to use the attached files provided in the workspace at locations: {filenames}\n\n'
+        else:  # Image files: jpg, png
+            src_file = os.path.join(
+                DATASET_CACHE_DIR, '2023', metadata.data_split, instance['file_name']
+            )
+            instruction += 'Image: To solve this task you will have to use the image shown below.\n\n'
+            image = Image.open(src_file)
+            if extension_name == 'jpg':
+                image_urls.append(image_to_jpg_base64_url(image))
+            else:
+                image_urls.append(image_to_png_base64_url(image))
 
     instruction += """IMPORTANT: When seeking information from a website, REFRAIN from arbitrary URL navigation. You should utilize the designated search engine tool with precise keywords to obtain relevant URLs or use the specific website's search interface. DO NOT navigate directly to specific URLs as they may not exist.\n\nFor example: if you want to search for a research paper on Arxiv, either use the search engine tool with specific keywords or navigate to arxiv.org and then use its interface.\n"""
     instruction += 'IMPORTANT: You should NEVER ask for Human Help.\n'
@@ -174,7 +221,9 @@ Here is the task:
     state: State | None = asyncio.run(
         run_controller(
             config=config,
-            initial_user_action=MessageAction(content=instruction),
+            initial_user_action=MessageAction(
+                content=instruction, image_urls=image_urls
+            ),
             runtime=runtime,
             fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
                 metadata.agent_class

evaluation/benchmarks/gaia/utils.py

@@ -0,0 +1,43 @@
+import base64
+import io
+
+import numpy as np
+from PIL import Image
+
+
+def image_to_png_base64_url(
+    image: np.ndarray | Image.Image, add_data_prefix: bool = True
+):
+    """Convert a numpy array to a base64 encoded png image url."""
+    if isinstance(image, np.ndarray):
+        image = Image.fromarray(image)
+    if image.mode in ('RGBA', 'LA'):
+        image = image.convert('RGB')
+    buffered = io.BytesIO()
+    image.save(buffered, format='PNG')
+
+    image_base64 = base64.b64encode(buffered.getvalue()).decode()
+    return (
+        f'data:image/png;base64,{image_base64}'
+        if add_data_prefix
+        else f'{image_base64}'
+    )
+
+
+def image_to_jpg_base64_url(
+    image: np.ndarray | Image.Image, add_data_prefix: bool = True
+):
+    """Convert a numpy array to a base64 encoded jpeg image url."""
+    if isinstance(image, np.ndarray):
+        image = Image.fromarray(image)
+    if image.mode in ('RGBA', 'LA'):
+        image = image.convert('RGB')
+    buffered = io.BytesIO()
+    image.save(buffered, format='JPEG')
+
+    image_base64 = base64.b64encode(buffered.getvalue()).decode()
+    return (
+        f'data:image/jpeg;base64,{image_base64}'
+        if add_data_prefix
+        else f'{image_base64}'
+    )

evaluation/benchmarks/multi_swe_bench/README.md

@@ -41,6 +41,10 @@ default, it is set to 1.
 - `language`, the language of your evaluating dataset.
 - `dataset`, the absolute position of the dataset jsonl.
 
+**Skipping errors on build**
+
+For debugging purposes, you can set `export EVAL_SKIP_MAXIMUM_RETRIES_EXCEEDED=true` to continue evaluation even when instances reach maximum retries. After evaluation completes, check `maximum_retries_exceeded.jsonl` for a list of failed instances, fix those issues, and then run the evaluation again with `export EVAL_SKIP_MAXIMUM_RETRIES_EXCEEDED=false`.
+
 The results will be generated in evaluation/evaluation_outputs/outputs/XXX/CodeActAgent/YYY/output.jsonl, you can refer to the [example](examples/output.jsonl).
 
 ## Runing evaluation

evaluation/benchmarks/multi_swe_bench/run_infer.py

@@ -17,6 +17,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     assert_and_raise,
+    check_maximum_retries_exceeded,
     codeact_user_response,
     get_default_sandbox_config_for_eval,
     get_metrics,
@@ -344,6 +345,7 @@ def get_config(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         max_iterations=metadata.max_iterations,
+        enable_browser=RUN_WITH_BROWSING,
         runtime=os.environ.get('RUNTIME', 'docker'),
         sandbox=sandbox_config,
         # do not mount workspace
@@ -843,3 +845,5 @@ if __name__ == '__main__':
         timeout_seconds=120 * 60,  # 2 hour PER instance should be more than enough
         max_retries=5,
     )
+    # Check if any instances reached maximum retries
+    check_maximum_retries_exceeded(metadata.eval_output_dir)

evaluation/benchmarks/swe_bench/README.md

@@ -38,6 +38,10 @@ Please follow instruction [here](../../README.md#setup) to setup your local deve
 > - If your LLM config has temperature=0, we will automatically use temperature=0.1 for the 2nd and 3rd attempts
 >
 > To enable this iterative protocol, set `export ITERATIVE_EVAL_MODE=true`
+>
+> **Skipping errors on build**
+>
+> For debugging purposes, you can set `export EVAL_SKIP_MAXIMUM_RETRIES_EXCEEDED=true` to continue evaluation even when instances reach maximum retries. After evaluation completes, check `maximum_retries_exceeded.jsonl` for a list of failed instances, fix those issues, and then run the evaluation again with `export EVAL_SKIP_MAXIMUM_RETRIES_EXCEEDED=false`.
 
 
 ### Running Locally with Docker

evaluation/benchmarks/swe_bench/loc_eval/README.md

@@ -0,0 +1,45 @@
+# **Localization Evaluation for SWE-Bench**
+
+This folder implements localization evaluation at both file and function levels to complementing the assessment of agent inference on [SWE-Bench](https://www.swebench.com/).
+
+## **1. Environment Setup**
+- Python env: [Install python environment](../../../README.md#development-environment)
+- LLM config: [Configure LLM config](../../../README.md#configure-openhands-and-your-llm)
+
+## **2. Inference & Evaluation**
+- Inference and evaluation follow the original `run_infer.sh` and `run_eval.sh` implementation
+    - You may refer to instructions at [README.md](../README.md) for running inference and evaluation on SWE-Bench
+
+## **3. Localization Evaluation**
+- Localization evaluation computes two-level localization accuracy, while also considers task success as an additional metric for overall evaluation:
+    - **File Localization Accuracy:** Accuracy of correctly localizing the target file
+    - **Function Localization Accuracy:** Accuracy of correctly localizing the target function
+    - **Resolve Rate** (will be auto-skipped if missing): Success rate of whether tasks are successfully resolved
+    - **File Localization Efficiency:** Average number of iterations taken to successfully localize the target file
+    - **Function Localization Efficiency:** Average number of iterations taken to successfully localize the target file
+    - **Task success efficiency:** Average number of iterations taken to resolve the task
+    - **Resource efficiency:** the API expenditure of the agent running inference on SWE-Bench instances
+
+- Run localization evaluation
+    - Format:
+        ```bash
+        ./evaluation/benchmarks/swe_bench/scripts/eval_localization.sh [infer-dir] [split] [dataset] [max-infer-turn] [align-with-max]
+        ```
+        - `infer-dir`: inference directory containing inference outputs
+        - `split`: SWE-Bench dataset split to use
+        - `dataset`: SWE-Bench dataset name
+        - `max-infer-turn`: the maximum number of iterations the agent took to run inference
+        - `align-with-max`: whether to align failure indices (e.g., incorrect localization, unresolved tasks) with `max_iter`
+
+    - Example:
+        ```bash
+        # Example
+        ./evaluation/benchmarks/swe_bench/scripts/eval_localization.sh \
+            --infer-dir ./evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Verified-test/CodeActAgent/gpt_4o_100_N \
+            --split test \
+            --dataset princeton-nlp/SWE-bench_Verified \
+            --max-infer-turn 100 \
+            --align-with-max true
+        ```
+
+- Localization evaluation results will be automatically saved to `[infer-dir]/loc_eval`

evaluation/benchmarks/swe_bench/run_infer.py

@@ -28,6 +28,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     assert_and_raise,
+    check_maximum_retries_exceeded,
     codeact_user_response,
     get_default_sandbox_config_for_eval,
     get_metrics,
@@ -109,9 +110,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageActio
         template_name = 'swt.j2'
     elif mode == 'swe':
         if 'claude' in llm_model:
-            template_name = 'swe_claude.j2'
-        elif 'gemini' in llm_model:
-            template_name = 'swe_gemini.j2'
+            template_name = 'swe_default.j2'
         elif 'gpt-4.1' in llm_model:
             template_name = 'swe_gpt4.j2'
         else:
@@ -227,6 +226,7 @@ def get_config(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         max_iterations=metadata.max_iterations,
+        enable_browser=RUN_WITH_BROWSING,
         runtime=os.environ.get('RUNTIME', 'docker'),
         sandbox=sandbox_config,
         # do not mount workspace
@@ -970,3 +970,5 @@ if __name__ == '__main__':
         logger.info(
             f'Done! Total {len(added_instance_ids)} instances added to {output_file}'
         )
+        # Check if any instances reached maximum retries
+        check_maximum_retries_exceeded(metadata.eval_output_dir)

evaluation/benchmarks/swe_bench/run_localize.py

@@ -203,6 +203,7 @@ def get_config(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         max_iterations=metadata.max_iterations,
+        enable_browser=RUN_WITH_BROWSING,
         runtime=os.environ.get('RUNTIME', 'docker'),
         sandbox=sandbox_config,
         # do not mount workspace