gemini supports temp, top_p

Merge branch 'main' of github.com:All-Hands-AI/OpenHands into gemini-think
Fix: Add APIConnectionError to LLM_RETRY_EXCEPTIONS to handle temporary API errors (#9818 )
2026-04-29 03:00:45 -04:00 · 2025-08-05 22:52:12 +02:00 · 2025-08-05 22:40:32 +02:00 · 2025-08-05 16:38:41 -04:00 · 2025-08-05 14:38:53 -04:00 · 2025-08-04 17:50:59 -04:00
456 changed files with 31935 additions and 6804 deletions
@@ -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
@@ -40,7 +40,8 @@ jobs:
          # Only build nikolaik on PRs, otherwise build both nikolaik and ubuntu.
          if [[ "$GITHUB_EVENT_NAME" == "pull_request" ]]; then
            json=$(jq -n -c '[
-                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" }
+                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" },
+                { image: "ubuntu:24.04", tag: "ubuntu" }
              ]')
          else
            json=$(jq -n -c '[
@@ -58,9 +59,6 @@ jobs:
    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
@@ -86,24 +84,11 @@ 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
@@ -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 \
@@ -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' }}
@@ -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
@@ -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
@@ -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"
@@ -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:
@@ -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.
@@ -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
@@ -182,6 +182,8 @@ cython_debug/
 .roo/rules
 .cline/rules
 .windsurf/rules
+.repomix
+repomix-output.txt

 # evaluation
 evaluation/evaluation_outputs
@@ -15,8 +15,6 @@ make build && make run FRONTEND_PORT=12000 FRONTEND_HOST=0.0.0.0 BACKEND_HOST=0.

 IMPORTANT: Before making any changes to the codebase, ALWAYS run `make install-pre-commit-hooks` to ensure pre-commit hooks are properly installed.

-
-
 Before pushing any changes, you MUST ensure that any lint errors or simple test errors have been fixed.

 * 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).
@@ -32,6 +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
@@ -137,3 +141,65 @@ Your specialized knowledge and instructions here...
  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
@@ -1,56 +1,158 @@
 #!/bin/bash

 echo "Running OpenHands pre-commit hook..."
+echo "This hook runs selective linting based on changed files."

 # Store the exit code to return at the end
 # This allows us to be additive to existing pre-commit hooks
 EXIT_CODE=0

-# 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..."
+# Get the list of staged files
+STAGED_FILES=$(git diff --cached --name-only)

-    # Check if frontend directory exists
-    if [ -d "frontend" ]; then
-        # Change to frontend directory
-        cd frontend || exit 1
+# Check if any files match specific patterns
+has_frontend_changes=false
+has_backend_changes=false
+has_vscode_changes=false

-        # Run lint:fix
-        echo "Running npm lint:fix..."
-        npm run lint:fix
+# Check each file individually to avoid issues with grep
+for file in $STAGED_FILES; do
+    if [[ $file == frontend/* ]]; then
+        has_frontend_changes=true
+    elif [[ $file == openhands/* || $file == evaluation/* || $file == tests/* ]]; then
+        has_backend_changes=true
+        # Check for VSCode extension changes (subset of backend changes)
+        if [[ $file == openhands/integrations/vscode/* ]]; then
+            has_vscode_changes=true
+        fi
+    fi
+done
+
+echo "Analyzing changes..."
+echo "- Frontend changes: $has_frontend_changes"
+echo "- Backend changes: $has_backend_changes"
+echo "- VSCode extension changes: $has_vscode_changes"
+
+# Run frontend linting if needed
+if [ "$has_frontend_changes" = true ]; then
+    # Check if we're in a CI environment or if frontend dependencies are missing
+    if [ -n "$CI" ] || ! command -v react-router &> /dev/null || ! command -v vitest &> /dev/null; then
+        echo "Skipping frontend checks (CI environment or missing dependencies detected)."
+        echo "WARNING: Frontend files have changed but frontend checks are being skipped."
+        echo "Please run 'make lint-frontend' manually before submitting your PR."
+    else
+        echo "Running frontend linting..."
+        make lint-frontend
        if [ $? -ne 0 ]; then
            echo "Frontend linting failed. Please fix the issues before committing."
            EXIT_CODE=1
+        else
+            echo "Frontend linting checks passed!"
        fi

-        # Run build
-        echo "Running npm build..."
-        npm run build
-        if [ $? -ne 0 ]; then
-            echo "Frontend build failed. Please fix the issues before committing."
-            EXIT_CODE=1
-        fi
+        # Run additional frontend checks
+        if [ -d "frontend" ]; then
+            echo "Running additional frontend checks..."
+            cd frontend || exit 1

-        # Run tests
-        echo "Running npm test..."
-        npm test
-        if [ $? -ne 0 ]; then
-            echo "Frontend tests failed. Please fix the failing tests before committing."
-            EXIT_CODE=1
-        fi
+            # Run build
+            echo "Running npm build..."
+            npm run build
+            if [ $? -ne 0 ]; then
+                echo "Frontend build failed. Please fix the issues before committing."
+                EXIT_CODE=1
+            fi

-        # Return to the original directory
-        cd ..
+            # Run tests
+            echo "Running npm test..."
+            npm test
+            if [ $? -ne 0 ]; then
+                echo "Frontend tests failed. Please fix the failing tests before committing."
+                EXIT_CODE=1
+            fi

-        if [ $EXIT_CODE -eq 0 ]; then
-            echo "Frontend checks passed!"
+            cd ..
        fi
-    else
-        echo "Frontend directory not found. Skipping frontend checks."
    fi
 else
-    echo "No frontend changes detected. Skipping frontend checks."
+    echo "Skipping frontend checks (no frontend changes detected)."
+fi
+
+# Run backend linting if needed
+if [ "$has_backend_changes" = true ]; then
+    echo "Running backend linting..."
+    make lint-backend
+    if [ $? -ne 0 ]; then
+        echo "Backend linting failed. Please fix the issues before committing."
+        EXIT_CODE=1
+    else
+        echo "Backend linting checks passed!"
+    fi
+else
+    echo "Skipping backend checks (no backend changes detected)."
+fi
+
+# Run VSCode extension checks if needed
+if [ "$has_vscode_changes" = true ]; then
+    # Check if we're in a CI environment
+    if [ -n "$CI" ]; then
+        echo "Skipping VSCode extension checks (CI environment detected)."
+        echo "WARNING: VSCode extension files have changed but checks are being skipped."
+        echo "Please run VSCode extension checks manually before submitting your PR."
+    else
+        echo "Running VSCode extension checks..."
+        if [ -d "openhands/integrations/vscode" ]; then
+            cd openhands/integrations/vscode || exit 1
+
+            echo "Running npm lint:fix..."
+            npm run lint:fix
+            if [ $? -ne 0 ]; then
+                echo "VSCode extension linting failed. Please fix the issues before committing."
+                EXIT_CODE=1
+            else
+                echo "VSCode extension linting passed!"
+            fi
+
+            echo "Running npm typecheck..."
+            npm run typecheck
+            if [ $? -ne 0 ]; then
+                echo "VSCode extension type checking failed. Please fix the issues before committing."
+                EXIT_CODE=1
+            else
+                echo "VSCode extension type checking passed!"
+            fi
+
+            echo "Running npm compile..."
+            npm run compile
+            if [ $? -ne 0 ]; then
+                echo "VSCode extension compilation failed. Please fix the issues before committing."
+                EXIT_CODE=1
+            else
+                echo "VSCode extension compilation passed!"
+            fi
+
+            cd ../../..
+        fi
+    fi
+else
+    echo "Skipping VSCode extension checks (no VSCode extension changes detected)."
+fi
+
+# If no specific code changes detected, run basic checks
+if [ "$has_frontend_changes" = false ] && [ "$has_backend_changes" = false ]; then
+    echo "No specific code changes detected. Running basic checks..."
+    if [ -n "$STAGED_FILES" ]; then
+        # Run only basic pre-commit hooks for non-code files
+        poetry run pre-commit run --files $(echo "$STAGED_FILES" | tr '\n' ' ') --hook-stage commit --config ./dev_config/python/.pre-commit-config.yaml
+        if [ $? -ne 0 ]; then
+            echo "Basic checks failed. Please fix the issues before committing."
+            EXIT_CODE=1
+        else
+            echo "Basic checks passed!"
+        fi
+    else
+        echo "No files changed. Skipping basic checks."
+    fi
 fi

 # Run any existing pre-commit hooks that might have been installed by the user
@@ -34,7 +34,7 @@ _Dev Container: Reopen in Container_ command from the Command Palette

 #### Develop without sudo access

-If you want to develop without system admin/sudo access to upgrade/install `Python` and/or `NodeJs`, you can use
+If you want to develop without system admin/sudo access to upgrade/install `Python` and/or `NodeJS`, you can use
 `conda` or `mamba` to manage the packages for you:

 ```bash
@@ -71,7 +71,7 @@ This command will prompt you to enter the LLM API key, model name, and other var
 tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI,
 please set the model in the UI.

-Note: If you have previously run OpenHands using the docker command, you may have already set some environmental
+Note: If you have previously run OpenHands using the docker command, you may have already set some environment
 variables in your terminal. The final configurations are set from highest to lowest priority:
 Environment variables > config.toml variables > default variables

@@ -154,12 +154,12 @@ poetry run pytest ./tests/unit/test_*.py
 1. Add your dependency in `pyproject.toml` or use `poetry add xxx`.
 2. Update the poetry.lock file via `poetry lock --no-update`.

-### 9. Use existing Docker image
+### 10. Use existing Docker image

 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:0.48-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.51-nikolaik`

 ## Develop inside Docker container

@@ -3,10 +3,10 @@ SHELL=/usr/bin/env bash

 # Variables
 BACKEND_HOST ?= "127.0.0.1"
-BACKEND_PORT = 3000
+BACKEND_PORT ?= 3000
 BACKEND_HOST_PORT = "$(BACKEND_HOST):$(BACKEND_PORT)"
 FRONTEND_HOST ?= "127.0.0.1"
-FRONTEND_PORT = 3001
+FRONTEND_PORT ?= 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
 DEFAULT_MODEL = "gpt-4o"
 CONFIG_FILE = config.toml
@@ -174,7 +174,7 @@ install-python-dependencies:
 	fi
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"

-install-frontend-dependencies:
+install-frontend-dependencies: check-npm check-nodejs
 	@echo "$(YELLOW)Setting up frontend environment...$(RESET)"
 	@echo "$(YELLOW)Detect Node.js version...$(RESET)"
 	@cd frontend && node ./scripts/detect-node-version.js
@@ -182,17 +182,17 @@ install-frontend-dependencies:
 	@cd frontend && npm install
 	@echo "$(GREEN)Frontend dependencies installed successfully.$(RESET)"

-install-pre-commit-hooks:
+install-pre-commit-hooks: check-python check-poetry install-python-dependencies
 	@echo "$(YELLOW)Installing pre-commit hooks...$(RESET)"
 	@git config --unset-all core.hooksPath || true
 	@poetry run pre-commit install --config $(PRE_COMMIT_CONFIG_PATH)
 	@echo "$(GREEN)Pre-commit hooks installed successfully.$(RESET)"

-lint-backend:
+lint-backend: install-pre-commit-hooks
 	@echo "$(YELLOW)Running linters...$(RESET)"
 	@poetry run pre-commit run --all-files --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)

-lint-frontend:
+lint-frontend: install-frontend-dependencies
 	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
 	@cd frontend && npm run lint

@@ -62,17 +62,17 @@ system requirements and more information.


 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-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:0.48
+    docker.all-hands.dev/all-hands-ai/openhands:0.51
 ```

 > **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.
@@ -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:0.48-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-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:0.48
+    docker.all-hands.dev/all-hands-ai/openhands:0.51
 ```

 > **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。
@@ -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:0.48-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-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:0.48
+    docker.all-hands.dev/all-hands-ai/openhands:0.51
 ```

 **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。
@@ -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

@@ -57,8 +58,8 @@ RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs
 # Default is 60000, but we've seen up to 200000
 RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs

-RUN groupadd app
-RUN useradd -l -m -u $OPENHANDS_USER_ID -s /bin/bash openhands && \
+RUN groupadd --gid $OPENHANDS_USER_ID app
+RUN useradd -l -m -u $OPENHANDS_USER_ID --gid $OPENHANDS_USER_ID -s /bin/bash openhands && \
    usermod -aG app openhands && \
    usermod -aG sudo openhands && \
    echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
@@ -23,6 +23,18 @@ if [ -z "$WORKSPACE_MOUNT_PATH" ]; then
  unset WORKSPACE_BASE
 fi

+if [[ "$INSTALL_THIRD_PARTY_RUNTIMES" == "true" ]]; then
+  echo "Downloading and installing third_party_runtimes..."
+  echo "Warning: Third-party runtimes are provided as-is, not actively supported and may be removed in future releases."
+
+  if pip install 'openhands-ai[third_party_runtimes]' -qqq 2> >(tee /dev/stderr); then
+    echo "third_party_runtimes installed successfully."
+  else
+    echo "Failed to install third_party_runtimes." >&2
+    exit 1
+  fi
+fi
+
 if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
  echo "Running OpenHands as root"
  export RUN_AS_OPENHANDS=false
@@ -12,7 +12,7 @@ services:
      - SANDBOX_API_HOSTNAME=host.docker.internal
      - DOCKER_HOST_ADDR=host.docker.internal
      #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.48-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.51-nikolaik}
      - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
      - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
    ports:
@@ -7,7 +7,7 @@ services:
    image: openhands:latest
    container_name: openhands-app-${DATE:-}
    environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.51-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:
@@ -34,9 +34,19 @@
              {
                "group": "Integrations",
                "pages": [
+                  "usage/cloud/bitbucket-installation",
                  "usage/cloud/github-installation",
                  "usage/cloud/gitlab-installation",
-                  "usage/cloud/slack-installation"
+                  "usage/cloud/slack-installation",
+                  {
+                    "group": "Project Management Tools",
+                    "pages": [
+                      "usage/cloud/project-management/overview",
+                      "usage/cloud/project-management/jira-integration",
+                      "usage/cloud/project-management/jira-dc-integration",
+                      "usage/cloud/project-management/linear-integration"
+                    ]
+                  }
                ]
              },
              "usage/cloud/cloud-ui",
@@ -66,7 +76,9 @@
                        "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"
                      ]
                    }
@@ -1827,6 +1827,11 @@
          "updated_at": {
            "type": "string",
            "format": "date-time"
+          },
+          "owner_type": {
+            "type": "string",
+            "enum": ["user", "organization"],
+            "nullable": true
          }
        }
      },
@@ -0,0 +1,48 @@
+---
+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).
+
+## IP Whitelisting
+
+If your Bitbucket Cloud instance has IP restrictions, you'll need to whitelist the following IP addresses to allow OpenHands to access your repositories:
+
+### Core App IP
+```
+34.68.58.200
+```
+
+### Runtime IPs
+```
+34.10.175.217
+34.136.162.246
+34.45.0.142
+34.28.69.126
+35.224.240.213
+34.70.174.52
+34.42.4.87
+35.222.133.153
+34.29.175.97
+34.60.55.59
+```
+
+## 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.
@@ -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`.

@@ -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).
@@ -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).
@@ -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.
@@ -0,0 +1,118 @@
+---
+title: Jira Data Center Integration (Beta)
+description: Complete guide for setting up Jira Data Center integration with OpenHands Cloud, including service account creation, personal access token generation, webhook configuration, and workspace integration setup.
+---
+
+# Jira Data Center Integration
+
+## Platform Configuration
+
+### Step 1: Create Service Account
+
+1. **Access User Management**
+   - Log in to Jira Data Center as administrator
+   - Go to **Administration** > **User Management**
+
+2. **Create User**
+   - Click **Create User**
+   - Username: `openhands-agent`
+   - Full Name: `OpenHands Agent`
+   - Email: `openhands@yourcompany.com` (replace with your preferred service account email)
+   - Password: Set a secure password
+   - Click **Create**
+
+3. **Assign Permissions**
+   - Add user to appropriate groups
+   - Ensure access to relevant projects
+   - Grant necessary project permissions
+
+### Step 2: Generate API Token
+
+1. **Personal Access Tokens**
+   - Log in as the service account
+   - Go to **Profile** > **Personal Access Tokens**
+   - Click **Create token**
+   - Name: `OpenHands Cloud Integration`
+   - Expiry: Set appropriate expiration (recommend 1 year)
+   - Click **Create**
+   - **Important**: Copy and store the token securely
+
+### Step 3: Configure Webhook
+
+1. **Create Webhook**
+   - Go to **Administration** > **System** > **WebHooks**
+   - Click **Create a WebHook**
+   - **Name**: `OpenHands Cloud Integration`
+   - **URL**: `https://app.all-hands.dev/integration/jira-dc/events`
+   - Set a suitable webhook secret
+   - **Issue related events**: Select the following:
+     - Issue updated
+     - Comment created
+   - **JQL Filter**: Leave empty (or customize as needed)
+   - Click **Create**
+   - **Important**: Copy and store the webhook secret securely (you'll need this for workspace integration)
+
+---
+
+## Workspace Integration
+
+### Step 1: Log in to OpenHands Cloud
+
+1. **Navigate and Authenticate**
+   - Go to [OpenHands Cloud](https://app.all-hands.dev/)
+   - Sign in with your Git provider (GitHub, GitLab, or BitBucket)
+   - **Important:** Make sure you're signing in with the same Git provider account that contains the repositories you want the OpenHands agent to work on.
+
+### Step 2: Configure Jira Data Center Integration
+
+1. **Access Integration Settings**
+   - Navigate to **Settings** > **Integrations**
+   - Locate **Jira Data Center** section
+
+2. **Configure Workspace**
+   - Click **Configure** button
+   - Enter your workspace name and click **Connect**
+      - If no integration exists, you'll be prompted to enter additional credentials required for the workspace integration:
+         - **Webhook Secret**: The webhook secret from Step 3 above
+         - **Service Account Email**: The service account email from Step 1 above
+         - **Service Account API Key**: The personal access token from Step 2 above
+         - Ensure **Active** toggle is enabled
+
+3. **Complete OAuth Flow**
+   - You'll be redirected to Jira Data Center to complete OAuth verification
+   - Grant the necessary permissions to verify your workspace access. If you have access to multiple workspaces, select the correct one that you initially provided
+   - If successful, you will be redirected back to the **Integrations** settings in the OpenHands Cloud UI
+
+### Managing Your Integration
+
+**Edit Configuration:**
+- Click the **Edit** button next to your configured platform
+- Update any necessary credentials or settings
+- Click **Update** to apply changes
+- You will need to repeat the OAuth flow as before
+- **Important:** Only the original user who created the integration can see the edit view
+
+**Unlink Workspace:**
+- In the edit view, click **Unlink** next to the workspace name
+- This will deactivate your workspace link
+- **Important:** If the original user who configured the integration chooses to unlink their integration, any users currently linked to that integration will also be unlinked, and the workspace integration will be deactivated. The integration can only be reactivated by the original user.
+
+### Screenshots
+
+<AccordionGroup>
+<Accordion title="Workspace link flow">
+![workspace-link.png](/static/img/workspace-link.png)
+</Accordion>
+
+<Accordion title="Workspace Configure flow">
+![workspace-link.png](/static/img/workspace-configure.png)
+</Accordion>
+
+<Accordion title="Edit view as a user">
+![workspace-link.png](/static/img/workspace-user-edit.png)
+</Accordion>
+
+<Accordion title="Edit view as the workspace creator">
+![workspace-link.png](/static/img/workspace-admin-edit.png)
+</Accordion>
+</AccordionGroup>
@@ -0,0 +1,123 @@
+---
+title: Jira Cloud Integration
+description: Complete guide for setting up Jira Cloud integration with OpenHands Cloud, including service account creation, API token generation, webhook configuration, and workspace integration setup.
+---
+
+# Jira Cloud Integration
+
+## Platform Configuration
+
+### Step 1: Create Service Account
+
+1. **Navigate to User Management**
+   - Go to [Atlassian Admin](https://admin.atlassian.com/)
+   - Select your organization
+   - Go to **Directory** > **Users**
+
+2. **Create OpenHands Service Account**
+   - Click **Add user**
+   - Email: `openhands@yourcompany.com` (replace with your preferred service account email)
+   - Display name: `OpenHands Agent`
+   - Send invitation: **No** (you'll set password manually)
+   - Click **Add user**
+
+3. **Configure Account**
+   - Locate the created user and click on it
+   - Set a secure password
+   - Add to relevant Jira projects with appropriate permissions
+
+### Step 2: Generate API Token
+
+1. **Access API Token Management**
+   - Log in as the OpenHands service account
+   - Go to [API Tokens](https://id.atlassian.com/manage-profile/security/api-tokens)
+
+2. **Create API Token**
+   - Click **Create API token**
+   - Label: `OpenHands Cloud Integration`
+   - Expiry: Set appropriate expiration (recommend 1 year)
+   - Click **Create**
+   - **Important**: Copy and securely store the token immediately
+
+### Step 3: Configure Webhook
+
+1. **Navigate to Webhook Settings**
+   - Go to **Jira Settings** > **System** > **WebHooks**
+   - Click **Create a WebHook**
+
+2. **Configure Webhook**
+   - **Name**: `OpenHands Cloud Integration`
+   - **Status**: Enabled
+   - **URL**: `https://app.all-hands.dev/integration/jira/events`
+   - **Issue related events**: Select the following:
+     - Issue updated
+     - Comment created
+   - **JQL Filter**: Leave empty (or customize as needed)
+   - Click **Create**
+   - **Important**: Copy and store the webhook secret securely (you'll need this for workspace integration)
+
+---
+
+## Workspace Integration
+
+### Step 1: Log in to OpenHands Cloud
+
+1. **Navigate and Authenticate**
+   - Go to [OpenHands Cloud](https://app.all-hands.dev/)
+   - Sign in with your Git provider (GitHub, GitLab, or BitBucket)
+   - **Important:** Make sure you're signing in with the same Git provider account that contains the repositories you want the OpenHands agent to work on.
+
+### Step 2: Configure Jira Integration
+
+1. **Access Integration Settings**
+   - Navigate to **Settings** > **Integrations**
+   - Locate **Jira Cloud** section
+
+2. **Configure Workspace**
+   - Click **Configure** button
+   - Enter your workspace name and click **Connect**
+   - **Important:** Make sure you enter the full workspace name, eg: **yourcompany.atlassian.net**
+      - If no integration exists, you'll be prompted to enter additional credentials required for the workspace integration:
+         - **Webhook Secret**: The webhook secret from Step 3 above
+         - **Service Account Email**: The service account email from Step 1 above
+         - **Service Account API Key**: The API token from Step 2 above
+         - Ensure **Active** toggle is enabled
+
+3. **Complete OAuth Flow**
+   - You'll be redirected to Jira Cloud to complete OAuth verification
+   - Grant the necessary permissions to verify your workspace access.
+   - If successful, you will be redirected back to the **Integrations** settings in the OpenHands Cloud UI
+
+### Managing Your Integration
+
+**Edit Configuration:**
+- Click the **Edit** button next to your configured platform
+- Update any necessary credentials or settings
+- Click **Update** to apply changes
+- You will need to repeat the OAuth flow as before
+- **Important:** Only the original user who created the integration can see the edit view
+
+**Unlink Workspace:**
+- In the edit view, click **Unlink** next to the workspace name
+- This will deactivate your workspace link
+- **Important:** If the original user who configured the integration chooses to unlink their integration, any users currently linked to that workspace integration will also be unlinked, and the workspace integration will be deactivated. The integration can only be reactivated by the original user.
+
+### Screenshots
+
+<AccordionGroup>
+<Accordion title="Workspace link flow">
+![workspace-link.png](/static/img/workspace-link.png)
+</Accordion>
+
+<Accordion title="Workspace Configure flow">
+![workspace-link.png](/static/img/workspace-configure.png)
+</Accordion>
+
+<Accordion title="Edit view as a user">
+![workspace-link.png](/static/img/workspace-user-edit.png)
+</Accordion>
+
+<Accordion title="Edit view as the workspace creator">
+![workspace-link.png](/static/img/workspace-admin-edit.png)
+</Accordion>
+</AccordionGroup>
@@ -0,0 +1,122 @@
+---
+title: Linear Integration
+description: Complete guide for setting up Linear integration with OpenHands Cloud, including service account creation, API key generation, webhook configuration, and workspace integration setup.
+---
+
+# Linear Integration
+
+## Platform Configuration
+
+### Step 1: Create Service Account
+
+1. **Access Team Settings**
+   - Log in to Linear as a team admin
+   - Go to **Settings** > **Members**
+
+2. **Invite Service Account**
+   - Click **Invite members**
+   - Email: `openhands@yourcompany.com` (replace with your preferred service account email)
+   - Role: **Member** (with appropriate team access)
+   - Send invitation
+
+3. **Complete Setup**
+   - Accept invitation from the service account email
+   - Complete profile setup
+   - Ensure access to relevant teams/workspaces
+
+### Step 2: Generate API Key
+
+1. **Access API Settings**
+   - Log in as the service account
+   - Go to **Settings** > **API**
+
+2. **Create Personal API Key**
+   - Click **Create new key**
+   - Name: `OpenHands Cloud Integration`
+   - Scopes: Select the following:
+     - `Read` - Read access to issues and comments
+     - `Create comments` - Ability to create or update comments
+   - Select the teams you want to provide access to, or allow access for all teams you have permissions for
+   - Click **Create**
+   - **Important**: Copy and store the API key securely
+
+### Step 3: Configure Webhook
+
+1. **Access Webhook Settings**
+   - Go to **Settings** > **API** > **Webhooks**
+   - Click **New webhook**
+
+2. **Configure Webhook**
+   - **Label**: `OpenHands Cloud Integration`
+   - **URL**: `https://app.all-hands.dev/integration/linear/events`
+   - **Resource types**: Select:
+     - `Comment` - For comment events
+     - `Issue` - For issue updates (label changes)
+   - Select the teams you want to provide access to, or allow access for all public teams
+   - Click **Create webhook**
+   - **Important**: Copy and store the webhook secret securely (you'll need this for workspace integration)
+
+---
+
+## Workspace Integration
+
+### Step 1: Log in to OpenHands Cloud
+
+1. **Navigate and Authenticate**
+   - Go to [OpenHands Cloud](https://app.all-hands.dev/)
+   - Sign in with your Git provider (GitHub, GitLab, or BitBucket)
+   - **Important:** Make sure you're signing in with the same Git provider account that contains the repositories you want the OpenHands agent to work on.
+
+### Step 2: Configure Linear Integration
+
+1. **Access Integration Settings**
+   - Navigate to **Settings** > **Integrations**
+   - Locate **Linear** section
+
+2. **Configure Workspace**
+   - Click **Configure** button
+   - Enter your workspace name and click **Connect**
+      - If no integration exists, you'll be prompted to enter additional credentials required for the workspace integration:
+         - **Webhook Secret**: The webhook secret from Step 3 above
+         - **Service Account Email**: The service account email from Step 1 above
+         - **Service Account API Key**: The API key from Step 2 above
+         - Ensure **Active** toggle is enabled
+
+3. **Complete OAuth Flow**
+   - You'll be redirected to Linear to complete OAuth verification
+   - Grant the necessary permissions to verify your workspace access. If you have access to multiple workspaces, select the correct one that you initially provided
+   - If successful, you will be redirected back to the **Integrations** settings in the OpenHands Cloud UI
+
+### Managing Your Integration
+
+**Edit Configuration:**
+- Click the **Edit** button next to your configured platform
+- Update any necessary credentials or settings
+- Click **Update** to apply changes
+- You will need to repeat the OAuth flow as before
+- **Important:** Only the original user who created the integration can see the edit view
+
+**Unlink Workspace:**
+- In the edit view, click **Unlink** next to the workspace name
+- This will deactivate your workspace link
+- **Important:** If the original user who configured the integration chooses to unlink their integration, any users currently linked to that integration will also be unlinked, and the workspace integration will be deactivated. The integration can only be reactivated by the original user.
+
+### Screenshots
+
+<AccordionGroup>
+<Accordion title="Workspace link flow">
+![workspace-link.png](/static/img/workspace-link.png)
+</Accordion>
+
+<Accordion title="Workspace Configure flow">
+![workspace-link.png](/static/img/workspace-configure.png)
+</Accordion>
+
+<Accordion title="Edit view as a user">
+![workspace-link.png](/static/img/workspace-user-edit.png)
+</Accordion>
+
+<Accordion title="Edit view as the workspace creator">
+![workspace-link.png](/static/img/workspace-admin-edit.png)
+</Accordion>
+</AccordionGroup>
@@ -0,0 +1,79 @@
+---
+title: Project Management Tool Integrations
+description: Overview of OpenHands Cloud integrations with project management platforms including Jira Cloud, Jira Data Center, and Linear. Learn about setup requirements, usage methods, and troubleshooting.
+---
+
+# Project Management Tool Integrations
+
+## Overview
+
+OpenHands Cloud integrates with project management platforms (Jira Cloud, Jira Data Center, and Linear) to enable AI-powered task delegation. Users can invoke the OpenHands agent by:
+- Adding `@openhands` in ticket comments
+- Adding the `openhands` label to tickets
+
+## Prerequisites
+
+Integration requires two levels of setup:
+1. **Platform Configuration** - Administrative setup of service accounts and webhooks on your project management platform (see individual platform documentation below)
+2. **Workspace Integration** - Self-service configuration through the OpenHands Cloud UI to link your OpenHands account to the target workspace
+
+### Platform-Specific Setup Guides:
+- [Jira Cloud Integration](./jira-integration.md)
+- [Jira Data Center Integration](./jira-dc-integration.md)
+- [Linear Integration](./linear-integration.md)
+
+## Usage
+
+Once both the platform configuration and workspace integration are completed, users can trigger the OpenHands agent within their project management platforms using two methods:
+
+### Method 1: Comment Mention
+Add a comment to any issue with `@openhands` followed by your task description:
+```
+@openhands Please implement the user authentication feature described in this ticket
+```
+
+### Method 2: Label-based Delegation
+Add the label `openhands` to any issue. The OpenHands agent will automatically process the issue based on its description and requirements.
+
+### Git Repository Detection
+
+The OpenHands agent needs to identify which Git repository to work with when processing your issues. Here's how to ensure proper repository detection:
+
+#### Specifying the Target Repository
+
+**Required:** Include the target Git repository in your issue description or comment to ensure the agent works with the correct codebase.
+
+**Supported Repository Formats:**
+- Full HTTPS URL: `https://github.com/owner/repository.git`
+- GitHub URL without .git: `https://github.com/owner/repository`
+- Owner/repository format: `owner/repository`
+
+#### Platform-Specific Behavior
+
+**Linear Integration:** When GitHub integration is enabled for your Linear workspace with issue sync activated, the target repository is automatically detected from the linked GitHub issue. Manual specification is not required in this configuration.
+
+**Jira Integrations:** Always include the repository information in your issue description or `@openhands` comment to ensure proper repository detection.
+
+## Troubleshooting
+
+### Platform Configuration Issues
+- **Webhook not triggering**: Verify the webhook URL is correct and the proper event types are selected (Comment, Issue updated)
+- **API authentication failing**: Check API key/token validity and ensure required scopes are granted
+- **Permission errors**: Ensure the service account has access to relevant projects/teams and appropriate permissions
+
+### Workspace Integration Issues
+- **Workspace linking requests credentials**: If there are no active workspace integrations for the workspace you specified, you need to configure it first. Contact your platform administrator that you want to integrate with (eg: Jira, Linear)
+- **OAuth flow fails**: Ensure you're signing in with the same Git provider account that contains the repositories you want OpenHands to work on
+- **Integration not found**: Verify the workspace name matches exactly and that platform configuration was completed first
+
+### General Issues
+- **Agent not responding**: Check webhook logs in your platform settings and verify service account status
+- **Authentication errors**: Verify Git provider permissions and OpenHands Cloud access
+- **Partial functionality**: Ensure both platform configuration and workspace integration are properly completed
+
+### Getting Help
+For additional support, contact OpenHands Cloud support with:
+- Your integration platform (Linear, Jira Cloud, or Jira Data Center)
+- Workspace name
+- Error logs from webhook/integration attempts
+- Screenshots of configuration settings (without sensitive credentials)
@@ -12,6 +12,10 @@ description: This guide walks you through installing the OpenHands Slack app.
  allowFullScreen>
 </iframe>

+<Info>
+OpenHands utilizes a large language model (LLM), which may generate responses that are inaccurate or incomplete. While we strive for accuracy, OpenHands' outputs are not guaranteed to be correct, and we encourage users to validate critical information independently.
+</Info>
+
 ## Prerequisites

 - Access to OpenHands Cloud.
@@ -24,7 +28,7 @@ description: This guide walks you through installing the OpenHands Slack app.
  **This step is for Slack admins/owners**

  1. Make sure you have permissions to install Apps to your workspace.
-  2. Click the button below to install OpenHands Slack App <a target="_blank" href="https://slack.com/oauth/v2/authorize?client_id=7477886716822.8729519890534&scope=app_mentions:read,chat:write,users:read,channels:history,groups:history,mpim:history,im:history&user_scope=channels:history,groups:history,im:history,mpim:history"><img alt="Add to Slack" height="40" width="139" src="https://platform.slack-edge.com/img/add_to_slack.png" srcSet="https://platform.slack-edge.com/img/add_to_slack.png 1x, https://platform.slack-edge.com/img/add_to_slack@2x.png 2x" /></a>
+  2. Click the button below to install OpenHands Slack App <a target="_blank" href="https://slack.com/oauth/v2/authorize?client_id=7477886716822.8729519890534&scope=app_mentions:read,channels:history,chat:write,groups:history,im:history,mpim:history,users:read&user_scope="><img alt="Add to Slack" height="40" width="139" src="https://platform.slack-edge.com/img/add_to_slack.png" srcSet="https://platform.slack-edge.com/img/add_to_slack.png 1x, https://platform.slack-edge.com/img/add_to_slack@2x.png 2x" /></a>
  3. In the top right corner, select the workspace to install the OpenHands Slack app.
  4. Review permissions and click allow.

@@ -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?

@@ -20,7 +20,7 @@ for scripting.

 ### Running with Python

-**Note** - OpenHands requires Python version 3.12 or higher (Python 3.14 is not currently supported)
+**Note** - OpenHands requires Python version 3.12 or higher (Python 3.14 is not currently supported) and `uvx` for the default `fetch` MCP server (more details below).

 1. Install OpenHands using pip:
 ```bash
@@ -103,7 +103,7 @@ The conversation history will be saved in `~/.openhands/sessions`.
 ```bash
 docker run -it \
    --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
    -e SANDBOX_USER_ID=$(id -u) \
    -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
    -e LLM_API_KEY=$LLM_API_KEY \
@@ -112,7 +112,7 @@ docker run -it \
    -v ~/.openhands:/.openhands \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.48 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.51 \
    python -m openhands.cli.main --override-cli-mode true
 ```

@@ -123,7 +123,8 @@ docker run -it \

 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`.

@@ -152,6 +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

@@ -161,7 +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

@@ -173,6 +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.
+
+By default, the [Fetch MCP server](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch) will be automatically configured for OpenHands. You can also [enable search engine](../search-engine-setup) via the [Tavily MCP server](https://github.com/tavily-ai/tavily-mcp) by setting 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.
@@ -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).

@@ -61,7 +61,7 @@ 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:0.48-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
    -e SANDBOX_USER_ID=$(id -u) \
    -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
    -e LLM_API_KEY=$LLM_API_KEY \
@@ -73,13 +73,14 @@ docker run -it \
    -v ~/.openhands:/.openhands \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.48 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.51 \
    python -m openhands.core.main -t "write a bash script that prints hi"
 ```

 > **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.

 ## Additional Options

@@ -90,6 +91,6 @@ Common command-line options:
 - `-b 10.0` - Set budget limit (USD)
 - `--no-auto-continue` - Interactive mode

-Run `poetry run python -m openhands.core.main --help` for all options, or use a [`config.toml` file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml) for more flexibility.
+Run `poetry run python -m openhands.core.main --help` for all options.

 Set `export LOG_ALL_EVENTS=true` to log all agent actions.
@@ -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!
@@ -37,6 +39,12 @@ limits and monitor usage.
 - [mistralai/devstral-small](https://www.all-hands.dev/blog/devstral-a-new-state-of-the-art-open-model-for-coding-agents) (20 May 2025) -- also available through [OpenRouter](https://openrouter.ai/mistralai/devstral-small:free)
 - [all-hands/openhands-lm-32b-v0.1](https://www.all-hands.dev/blog/introducing-openhands-lm-32b----a-strong-open-coding-agent-model) (31 March 2025) -- also available through [OpenRouter](https://openrouter.ai/all-hands/openhands-lm-32b-v0.1)

+### Known Issues
+
+<Warning>
+As of July 2025, there are known issues with Gemini 2.5 Pro conversations taking longer than normal with OpenHands. We are continuing to investigate.
+</Warning>
+
 <Note>
 Most current local and open source models are not as powerful. When using such models, you may see long
 wait times between messages, poor responses, or errors about malformed JSON. OpenHands can only be as powerful as the
@@ -70,17 +78,20 @@ 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
+- **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](configuration-options#llm-customization).
+For detailed information about model customization, see
+[LLM Configuration Options](/usage/configuration-options#llm-configuration).

 ### API retries and rate limits

@@ -68,23 +68,23 @@ Download and install the LM Studio desktop app from [lmstudio.ai](https://lmstud
 1. Check [the installation guide](/usage/local-setup) and ensure all prerequisites are met before running OpenHands, then run:

 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-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:0.48
+    docker.all-hands.dev/all-hands-ai/openhands:0.51
 ```

 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:0.48
+Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.51
 Starting OpenHands...
 Running OpenHands as root
 14:22:13 - openhands:INFO: server_config.py:50 - Using config class None
@@ -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.
+
@@ -0,0 +1,35 @@
+---
+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)
+
+For `qwen3-coder-480b`, we charge the cheapest FP8 rate available on openrouter: $0.4 per million input tokens and $1.6 per million output tokens.
@@ -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:0.48-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-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:0.48
+    docker.all-hands.dev/all-hands-ai/openhands:0.51
 ```

 > **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.
@@ -10,38 +10,83 @@ 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:
 * The OpenHands UI through the Settings under the `MCP` tab.
 * The `config.toml` file under the `[mcp]` section if not using the UI.

-### Configuration Example via config.toml
+### Configuration Examples
+
+#### Recommended: Using Proxy Servers (SSE/HTTP)
+
+For stdio-based MCP servers, we recommend using MCP proxy tools like [`supergateway`](https://github.com/supercorp-ai/supergateway) instead of direct stdio connections.
+[SuperGateway](https://github.com/supercorp-ai/supergateway) is a popular MCP proxy that converts stdio MCP servers to HTTP/SSE endpoints:
+
+Start the proxy servers separately:
+```bash
+# Terminal 1: Filesystem server proxy
+supergateway --stdio "npx @modelcontextprotocol/server-filesystem /" --port 8080
+
+# Terminal 2: Fetch server proxy
+supergateway --stdio "uvx mcp-server-fetch" --port 8081
+```
+
+Then configure OpenHands to use the HTTP endpoint:

 ```toml
 [mcp]
-# SSE Servers - External servers that communicate via Server-Sent Events
+# SSE Servers - Recommended approach using proxy tools
 sse_servers = [
    # Basic SSE server with just a URL
    "http://example.com:8080/mcp",

-    # SSE server with API key authentication
-    {url="https://secure-example.com/mcp", api_key="your-api-key"}
-]
+    # SuperGateway proxy for fetch server
+    "http://localhost:8081/sse",

-# Stdio Servers - Local processes that communicate via standard input/output
+    # External MCP service with authentication
+    {url="https://api.example.com/mcp/sse", api_key="your-api-key"}
+]
+```
+
+
+
+#### Alternative: Direct Stdio Servers (Not Recommended for Production)
+
+```toml
+[mcp]
+# Direct stdio servers - use only for development/testing
 stdio_servers = [
    # Basic stdio server
    {name="fetch", command="uvx", args=["mcp-server-fetch"]},

    # Stdio server with environment variables
    {
-        name="data-processor",
-        command="python",
-        args=["-m", "my_mcp_server"],
+        name="filesystem",
+        command="npx",
+        args=["@modelcontextprotocol/server-filesystem", "/"],
        env={
-            "DEBUG": "true",
-            "PORT": "8080"
+            "DEBUG": "true"
        }
    }
 ]
@@ -57,8 +102,26 @@ 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

+**Note**: While stdio servers are supported, we recommend using MCP proxies (see above) for better reliability and performance.
+
 Stdio servers are configured using an object with the following properties:

 - `name` (required)
@@ -79,17 +142,55 @@ Stdio servers are configured using an object with the following properties:
  - Default: `{}`
  - Description: Environment variables to set for the server process

-## How MCP Works

-When OpenHands starts, it:
+#### When to Use Direct Stdio

-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.
+Direct stdio connections may still be appropriate in these scenarios:
+- **Development and testing**: Quick prototyping of MCP servers
+- **Simple, single-use tools**: Tools that don't require high reliability or concurrent access
+- **Local-only environments**: When you don't want to manage additional proxy processes

-The agent can then use these tools just like any built-in tool. When the agent calls an MCP tool:
+For production use, we recommend using proxy tools like SuperGateway.

-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.
+### Other Proxy Tools
+
+Other options include:
+
+- **Custom FastAPI/Express servers**: Build your own HTTP wrapper around stdio MCP servers
+- **Docker-based proxies**: Containerized solutions for better isolation
+- **Cloud-hosted MCP services**: Third-party services that provide MCP endpoints
+
+### Troubleshooting MCP Connections
+
+#### Common Issues with Stdio Servers
+- **Process crashes**: Stdio processes may crash without proper error handling
+- **Deadlocks**: Stdio communication can deadlock under high load
+- **Resource leaks**: Zombie processes if not properly managed
+- **Debugging difficulty**: Hard to inspect stdio communication
+
+#### Benefits of Using Proxies
+- **HTTP status codes**: Clear error reporting via standard HTTP responses
+- **Request logging**: Easy to log and monitor HTTP requests
+- **Load balancing**: Can distribute requests across multiple server instances
+- **Health checks**: HTTP endpoints can provide health status
+- **CORS support**: Better integration with web-based tools
+
+## Transport Protocols
+
+OpenHands supports three different MCP transport protocols:
+
+### 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.
+
+### Streamable HTTP (SHTTP)
+SHTTP is the modern HTTP-based transport protocol that provides enhanced features over SSE:
+
+- **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.
@@ -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

@@ -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
@@ -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
@@ -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)
@@ -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
@@ -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`
@@ -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,
@@ -225,6 +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
@@ -968,3 +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)
@@ -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
@@ -0,0 +1,227 @@
+#!/usr/bin/env bash
+set -eo pipefail
+source "evaluation/utils/version_control.sh"
+
+# Function to display usage information
+usage() {
+    echo "Usage: $0 [OPTIONS]"
+    echo "Options:"
+    echo "  --infer-dir DIR         Directory containing model inference outputs"
+    echo "  --split SPLIT           SWE-Bench dataset split selection"
+    echo "  --dataset DATASET       Dataset name"
+    echo "  --max-infer-turn NUM    Max number of turns for coding agent"
+    echo "  --align-with-max BOOL   Align failed instance indices with max iteration (true/false)"
+    echo "  -h, --help              Display this help message"
+    echo ""
+    echo "Example:"
+    echo "  $0 --infer-dir ./inference_outputs --split test --align-with-max false"
+}
+
+# Check if no arguments were provided
+if [ $# -eq 0 ]; then
+    usage
+    exit 1
+fi
+
+# Parse command line arguments
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --infer-dir)
+            INFER_DIR="$2"
+            shift 2
+            ;;
+        --split)
+            SPLIT="$2"
+            shift 2
+            ;;
+        --dataset)
+            DATASET="$2"
+            shift 2
+            ;;
+        --max-infer-turn)
+            MAX_TURN="$2"
+            shift 2
+            ;;
+        --align-with-max)
+            ALIGN_WITH_MAX="$2"
+            shift 2
+            ;;
+        -h|--help)
+            usage
+            exit 0
+            ;;
+        *)
+            echo "Unknown option: $1"
+            usage
+            exit 1
+            ;;
+    esac
+done
+
+# Check for required arguments (only INFER_DIR is required)
+if [ -z "$INFER_DIR" ]; then
+    echo "Error: Missing required arguments (--infer-dir is required)"
+    usage
+    exit 1
+fi
+
+# Set defaults for optional arguments if not provided
+if [ -z "$SPLIT" ]; then
+    SPLIT="test"
+    echo "Split not specified, using default: $SPLIT"
+fi
+
+if [ -z "$DATASET" ]; then
+    DATASET="princeton-nlp/SWE-bench_Verified"
+    echo "Dataset not specified, using default: $DATASET"
+fi
+
+if [ -z "$MAX_TURN" ]; then
+    MAX_TURN=20
+    echo "Max inference turn not specified, using default: $MAX_TURN"
+fi
+
+if [ -z "$ALIGN_WITH_MAX" ]; then
+    ALIGN_WITH_MAX="true"
+    echo "Align with max not specified, using default: $ALIGN_WITH_MAX"
+fi
+
+# Validate align-with-max value
+if [ "$ALIGN_WITH_MAX" != "true" ] && [ "$ALIGN_WITH_MAX" != "false" ]; then
+    print_error "Invalid value for --align-with-max: $ALIGN_WITH_MAX. Must be 'true' or 'false'"
+    exit 1
+fi
+
+# Color codes for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# Function to print colored output
+print_status() {
+    echo -e "${GREEN}[INFO]${NC} $1"
+}
+
+print_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+print_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+print_header() {
+    echo -e "${BLUE}[TASK]${NC} $1"
+}
+
+# Check if Python is available
+print_header "Checking Python installation..."
+if ! command -v python3 &> /dev/null; then
+    if ! command -v python &> /dev/null; then
+        print_error "Python is not installed or not in PATH"
+        exit 1
+    else
+        PYTHON_CMD="python"
+        print_status "Using python command"
+    fi
+else
+    PYTHON_CMD="python3"
+    print_status "Using python3 command"
+fi
+
+# Check if the Python script exists
+SCRIPT_NAME="./evaluation/benchmarks/swe_bench/loc_eval/loc_evaluator.py"
+if [ ! -f "$SCRIPT_NAME" ]; then
+    print_error "Python script '$SCRIPT_NAME' not found in current directory"
+    print_warning "Make sure the Python script is in the same directory as this bash script"
+    exit 1
+fi
+
+# Check if required directories exist
+print_header "Validating directories..."
+if [ ! -d "$INFER_DIR" ]; then
+    print_error "Inference directory not found: $INFER_DIR"
+    exit 1
+fi
+
+# Evaluation outputs
+EVAL_DIR="$INFER_DIR/eval_outputs"
+
+# Display configuration
+print_header "Starting Localization Evaluation with the following configuration:"
+echo "  Inference Directory:  $INFER_DIR"
+if [ -d "$EVAL_DIR" ]; then
+    echo "  Evaluation Directory:  $EVAL_DIR"
+else
+    echo "  Evaluation Directory:  None (evaluation outputs doesn't exist)"
+fi
+echo "  Output Directory:      $INFER_DIR/loc_eval"
+echo "  Split:                 $SPLIT"
+echo "  Dataset:               $DATASET"
+echo "  Max Turns:             $MAX_TURN"
+echo "  Align with Max:        $ALIGN_WITH_MAX"
+echo "  Python Command:        $PYTHON_CMD"
+echo ""
+
+# Check Python dependencies (optional check)
+print_header "Checking Python dependencies..."
+$PYTHON_CMD -c "
+import sys
+required_modules = ['pandas', 'json', 'os', 'argparse', 'collections']
+missing_modules = []
+
+for module in required_modules:
+    try:
+        __import__(module)
+    except ImportError:
+        missing_modules.append(module)
+
+if missing_modules:
+    print(f'Missing required modules: {missing_modules}')
+    sys.exit(1)
+else:
+    print('All basic dependencies are available')
+" || {
+    print_error "Some Python dependencies are missing"
+    print_warning "Please install required packages: pip install pandas"
+    exit 1
+}
+
+# Create log directory if doesn't exists
+mkdir -p "$INFER_DIR/loc_eval"
+
+# Set up logging
+LOG_FILE="$INFER_DIR/loc_eval/loc_evaluation_$(date +%Y%m%d_%H%M%S).log"
+print_status "Logging output to: $LOG_FILE"
+
+# Build the command
+CMD_ARGS="\"$SCRIPT_NAME\" \
+    --infer-dir \"$INFER_DIR\" \
+    --split \"$SPLIT\" \
+    --dataset \"$DATASET\" \
+    --max-infer-turn \"$MAX_TURN\" \
+    --align-with-max \"$ALIGN_WITH_MAX\""
+
+# Run the Python script
+print_header "Running localization evaluation..."
+eval "$PYTHON_CMD $CMD_ARGS" 2>&1 | tee "$LOG_FILE"
+
+# Check if the script ran successfully
+if [ ${PIPESTATUS[0]} -eq 0 ]; then
+    print_status "Localization evaluation completed successfully!"
+    print_status "Results saved to: $INFER_DIR/loc_eval"
+    print_status "Log file: $LOG_FILE"
+
+    # Display summary if results exist
+    if [ -f "$INFER_DIR/loc_eval/loc_eval_results/loc_acc/overall_eval.json" ]; then
+        print_header "Evaluation Summary:"
+        cat "$INFER_DIR/loc_eval/loc_eval_results/loc_acc/overall_eval.json"
+        echo
+    fi
+else
+    print_error "Localization evaluation failed!"
+    print_warning "Check the log file for details: $LOG_FILE"
+    exit 1
+fi
@@ -0,0 +1,31 @@
+# Terminal-Bench Evaluation on OpenHands
+
+Terminal-Bench has its own evaluation harness that is very different from OpenHands'. We
+implemented [OpenHands agent](https://github.com/laude-institute/terminal-bench/tree/main/terminal_bench/agents/installed_agents/openhands) using OpenHands local runtime
+inside terminal-bench framework. Hereby we introduce how to use the terminal-bench
+harness to evaluate OpenHands.
+
+## Installation
+
+Terminal-bench ships a CLI tool to manage tasks and run evaluation.
+Please follow official [Installation Doc](https://www.tbench.ai/docs/installation). You could also clone terminal-bench [source code](https://github.com/laude-institute/terminal-bench) and use `uv run tb` CLI.
+
+## Evaluation
+
+Please see [Terminal-Bench Leaderboard](https://www.tbench.ai/leaderboard) for the latest
+instruction on benchmarking guidance. The dataset might evolve.
+
+Sample command:
+
+```bash
+export LLM_BASE_URL=<optional base url>
+export LLM_API_KEY=<llm key>
+tb run \
+    --dataset-name terminal-bench-core \
+    --dataset-version 0.1.1 \
+    --agent openhands \
+    --model <model> \
+    --cleanup
+```
+
+You could run `tb --help` or `tb run --help` to learn more about their CLI.
@@ -164,6 +164,7 @@ 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
@@ -25,7 +25,8 @@ class Test(BaseIntegrationTest):
        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')

        # git add
-        action = CmdRunAction(command='git add hello.py .vscode/')
+        cmd_str = 'git add hello.py'
+        action = CmdRunAction(command=cmd_str)
        obs = runtime.run_action(action)
        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')

@@ -40,15 +41,6 @@ class Test(BaseIntegrationTest):
                reason=f'Failed to cat /workspace/hello.py: {obs.content}.',
            )

-        # check if the file /workspace/.vscode/settings.json exists
-        action = CmdRunAction(command='cat /workspace/.vscode/settings.json')
-        obs = runtime.run_action(action)
-        if obs.exit_code != 0:
-            return TestResult(
-                success=False,
-                reason=f'Failed to cat /workspace/.vscode/settings.json: {obs.content}.',
-            )
-
        # check if the staging area is empty
        action = CmdRunAction(command='git status')
        obs = runtime.run_action(action)
@@ -311,6 +311,76 @@ def assert_and_raise(condition: bool, msg: str):
        raise EvalException(msg)


+def log_skipped_maximum_retries_exceeded(instance, metadata, error, max_retries=5):
+    """Log and skip the instance when maximum retries are exceeded.
+
+    Args:
+        instance: The instance that failed
+        metadata: The evaluation metadata
+        error: The error that occurred
+        max_retries: The maximum number of retries that were attempted
+
+    Returns:
+        EvalOutput with the error information
+    """
+    from openhands.core.logger import openhands_logger as logger
+
+    # Log the error
+    logger.exception(error)
+    logger.error(
+        f'Maximum error retries reached for instance {instance.instance_id}. '
+        f'Check maximum_retries_exceeded.jsonl, fix the issue and run evaluation again. '
+        f'Skipping this instance and continuing with others.'
+    )
+
+    # Add the instance name to maximum_retries_exceeded.jsonl in the same folder as output.jsonl
+    if metadata and metadata.eval_output_dir:
+        retries_file_path = os.path.join(
+            metadata.eval_output_dir,
+            'maximum_retries_exceeded.jsonl',
+        )
+        try:
+            # Write the instance info as a JSON line
+            with open(retries_file_path, 'a') as f:
+                import json
+
+                # No need to get Docker image as we're not including it in the error entry
+
+                error_entry = {
+                    'instance_id': instance.instance_id,
+                    'error': str(error),
+                    'timestamp': time.strftime('%Y-%m-%d %H:%M:%S'),
+                }
+                f.write(json.dumps(error_entry) + '\n')
+            logger.info(f'Added instance {instance.instance_id} to {retries_file_path}')
+        except Exception as write_error:
+            logger.error(
+                f'Failed to write to maximum_retries_exceeded.jsonl: {write_error}'
+            )
+
+    return EvalOutput(
+        instance_id=instance.instance_id,
+        test_result={},
+        error=f'Maximum retries ({max_retries}) reached: {str(error)}',
+        status='error',
+    )
+
+
+def check_maximum_retries_exceeded(eval_output_dir):
+    """Check if maximum_retries_exceeded.jsonl exists and output a message."""
+    from openhands.core.logger import openhands_logger as logger
+
+    retries_file_path = os.path.join(eval_output_dir, 'maximum_retries_exceeded.jsonl')
+    if os.path.exists(retries_file_path):
+        logger.info(
+            'ATTENTION: Some instances reached maximum error retries and were skipped.'
+        )
+        logger.info(f'These instances are listed in: {retries_file_path}')
+        logger.info(
+            'Fix these instances and run evaluation again with EVAL_SKIP_MAXIMUM_RETRIES_EXCEEDED=false'
+        )
+
+
 def _process_instance_wrapper(
    process_instance_func: Callable[[pd.Series, EvalMetadata, bool], EvalOutput],
    instance: pd.Series,
@@ -363,11 +433,26 @@ def _process_instance_wrapper(
                    + f'[Encountered after {max_retries} retries. Please check the logs and report the issue.]'
                    + '-' * 10
                )
-                # Raise an error after all retries & stop the evaluation
-                logger.exception(e)
-                raise RuntimeError(
-                    f'Maximum error retries reached for instance {instance.instance_id}'
-                ) from e
+
+                # Check if EVAL_SKIP_MAXIMUM_RETRIES_EXCEEDED is set to true
+                skip_errors = (
+                    os.environ.get(
+                        'EVAL_SKIP_MAXIMUM_RETRIES_EXCEEDED', 'false'
+                    ).lower()
+                    == 'true'
+                )
+
+                if skip_errors:
+                    # Use the dedicated function to log and skip maximum retries exceeded
+                    return log_skipped_maximum_retries_exceeded(
+                        instance, metadata, e, max_retries
+                    )
+                else:
+                    # Raise an error after all retries & stop the evaluation
+                    logger.exception(e)
+                    raise RuntimeError(
+                        f'Maximum error retries reached for instance {instance.instance_id}'
+                    ) from e
            msg = (
                '-' * 10
                + '\n'
@@ -456,6 +541,10 @@ def run_evaluation(
    output_fp.close()
    logger.info('\nEvaluation finished.\n')

+    # Check if any instances reached maximum retries
+    if metadata and metadata.eval_output_dir:
+        check_maximum_retries_exceeded(metadata.eval_output_dir)
+

 def reset_logger_for_multiprocessing(
    logger: logging.Logger, instance_id: str, log_dir: str
@@ -8,4 +8,4 @@ npx lint-staged
 # Run backend pre-commit
 echo "Running backend pre-commit..."
 cd ..
-pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+poetry run pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
@@ -129,4 +129,159 @@ describe("ActionSuggestions", () => {
    expect(createPRPrompt).toContain("meaningful branch name");
    expect(createPRPrompt).not.toContain("SAME branch name");
  });
+
+  it("should use correct provider name based on conversation git_provider, not user authenticated providers", async () => {
+    // Test case for GitHub repository
+    const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
+    getConversationSpy.mockResolvedValue({
+      conversation_id: "test-github",
+      title: "GitHub Test",
+      selected_repository: "test-repo",
+      git_provider: "github",
+      selected_branch: "main",
+      last_updated_at: new Date().toISOString(),
+      created_at: new Date().toISOString(),
+      status: "RUNNING",
+      runtime_status: "STATUS$READY",
+      url: null,
+      session_api_key: null,
+    });
+
+    // Mock user having both GitHub and Bitbucket tokens
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        github: "github-token",
+        bitbucket: "bitbucket-token",
+      },
+    });
+
+    const onSuggestionsClick = vi.fn();
+    render(<ActionSuggestions onSuggestionsClick={onSuggestionsClick} />, {
+      wrapper: ({ children }) => (
+        <QueryClientProvider client={new QueryClient()}>
+          {children}
+        </QueryClientProvider>
+      ),
+    });
+
+    const buttons = await screen.findAllByTestId("suggestion");
+    const prButton = buttons.find((button) =>
+      button.textContent?.includes("Push & Create PR"),
+    );
+
+    expect(prButton).toBeInTheDocument();
+
+    if (prButton) {
+      prButton.click();
+    }
+
+    // The suggestion should mention GitHub, not Bitbucket
+    expect(onSuggestionsClick).toHaveBeenCalledWith(
+      expect.stringContaining("GitHub")
+    );
+    expect(onSuggestionsClick).not.toHaveBeenCalledWith(
+      expect.stringContaining("Bitbucket")
+    );
+  });
+
+  it("should use GitLab terminology when git_provider is gitlab", async () => {
+    const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
+    getConversationSpy.mockResolvedValue({
+      conversation_id: "test-gitlab",
+      title: "GitLab Test",
+      selected_repository: "test-repo",
+      git_provider: "gitlab",
+      selected_branch: "main",
+      last_updated_at: new Date().toISOString(),
+      created_at: new Date().toISOString(),
+      status: "RUNNING",
+      runtime_status: "STATUS$READY",
+      url: null,
+      session_api_key: null,
+    });
+
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        gitlab: "gitlab-token",
+      },
+    });
+
+    const onSuggestionsClick = vi.fn();
+    render(<ActionSuggestions onSuggestionsClick={onSuggestionsClick} />, {
+      wrapper: ({ children }) => (
+        <QueryClientProvider client={new QueryClient()}>
+          {children}
+        </QueryClientProvider>
+      ),
+    });
+
+    const buttons = await screen.findAllByTestId("suggestion");
+    const prButton = buttons.find((button) =>
+      button.textContent?.includes("Push & Create PR"),
+    );
+
+    if (prButton) {
+      prButton.click();
+    }
+
+    // Should mention GitLab and "merge request" instead of "pull request"
+    expect(onSuggestionsClick).toHaveBeenCalledWith(
+      expect.stringContaining("GitLab")
+    );
+    expect(onSuggestionsClick).toHaveBeenCalledWith(
+      expect.stringContaining("merge request")
+    );
+  });
+
+  it("should use Bitbucket terminology when git_provider is bitbucket", async () => {
+    const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
+    getConversationSpy.mockResolvedValue({
+      conversation_id: "test-bitbucket",
+      title: "Bitbucket Test",
+      selected_repository: "test-repo",
+      git_provider: "bitbucket",
+      selected_branch: "main",
+      last_updated_at: new Date().toISOString(),
+      created_at: new Date().toISOString(),
+      status: "RUNNING",
+      runtime_status: "STATUS$READY",
+      url: null,
+      session_api_key: null,
+    });
+
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        bitbucket: "bitbucket-token",
+      },
+    });
+
+    const onSuggestionsClick = vi.fn();
+    render(<ActionSuggestions onSuggestionsClick={onSuggestionsClick} />, {
+      wrapper: ({ children }) => (
+        <QueryClientProvider client={new QueryClient()}>
+          {children}
+        </QueryClientProvider>
+      ),
+    });
+
+    const buttons = await screen.findAllByTestId("suggestion");
+    const prButton = buttons.find((button) =>
+      button.textContent?.includes("Push & Create PR"),
+    );
+
+    if (prButton) {
+      prButton.click();
+    }
+
+    // Should mention Bitbucket
+    expect(onSuggestionsClick).toHaveBeenCalledWith(
+      expect.stringContaining("Bitbucket")
+    );
+  });
 });
@@ -120,6 +120,9 @@ describe("ExpandableMessage", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: true,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });
    const RouterStub = createRoutesStub([
@@ -28,7 +28,6 @@ describe("EventMessage", () => {
      action: "finish" as const,
      args: {
        final_thought: "Task completed successfully",
-        task_completed: "success" as const,
        outputs: {},
        thought: "Task completed successfully",
      },
@@ -114,7 +113,6 @@ describe("EventMessage", () => {
      action: "finish" as const,
      args: {
        final_thought: "Task completed successfully",
-        task_completed: "success" as const,
        outputs: {},
        thought: "Task completed successfully",
      },
@@ -19,7 +19,13 @@ describe("AuthModal", () => {
  });

  it("should render the GitHub and GitLab buttons", () => {
-    render(<AuthModal githubAuthUrl="mock-url" appMode="saas" />);
+    render(
+      <AuthModal
+        githubAuthUrl="mock-url"
+        appMode="saas"
+        providersConfigured={["github", "gitlab"]}
+      />,
+    );

    const githubButton = screen.getByRole("button", {
      name: "GITHUB$CONNECT_TO_GITHUB",
@@ -35,7 +41,13 @@ describe("AuthModal", () => {
  it("should redirect to GitHub auth URL when GitHub button is clicked", async () => {
    const user = userEvent.setup();
    const mockUrl = "https://github.com/login/oauth/authorize";
-    render(<AuthModal githubAuthUrl={mockUrl} appMode="saas" />);
+    render(
+      <AuthModal
+        githubAuthUrl={mockUrl}
+        appMode="saas"
+        providersConfigured={["github"]}
+      />,
+    );

    const githubButton = screen.getByRole("button", {
      name: "GITHUB$CONNECT_TO_GITHUB",
@@ -44,4 +56,63 @@ describe("AuthModal", () => {

    expect(window.location.href).toBe(mockUrl);
  });
+
+  it("should render Terms of Service and Privacy Policy text with correct links", () => {
+    render(<AuthModal githubAuthUrl="mock-url" appMode="saas" />);
+
+    // Find the terms of service section using data-testid
+    const termsSection = screen.getByTestId("auth-modal-terms-of-service");
+    expect(termsSection).toBeInTheDocument();
+
+    // Check that all text content is present in the paragraph
+    expect(termsSection).toHaveTextContent(
+      "AUTH$BY_SIGNING_UP_YOU_AGREE_TO_OUR",
+    );
+    expect(termsSection).toHaveTextContent("COMMON$TERMS_OF_SERVICE");
+    expect(termsSection).toHaveTextContent("COMMON$AND");
+    expect(termsSection).toHaveTextContent("COMMON$PRIVACY_POLICY");
+
+    // Check Terms of Service link
+    const tosLink = screen.getByRole("link", {
+      name: "COMMON$TERMS_OF_SERVICE",
+    });
+    expect(tosLink).toBeInTheDocument();
+    expect(tosLink).toHaveAttribute("href", "https://www.all-hands.dev/tos");
+    expect(tosLink).toHaveAttribute("target", "_blank");
+    expect(tosLink).toHaveClass("underline", "hover:text-primary");
+
+    // Check Privacy Policy link
+    const privacyLink = screen.getByRole("link", {
+      name: "COMMON$PRIVACY_POLICY",
+    });
+    expect(privacyLink).toBeInTheDocument();
+    expect(privacyLink).toHaveAttribute(
+      "href",
+      "https://www.all-hands.dev/privacy",
+    );
+    expect(privacyLink).toHaveAttribute("target", "_blank");
+    expect(privacyLink).toHaveClass("underline", "hover:text-primary");
+
+    // Verify that both links are within the terms section
+    expect(termsSection).toContainElement(tosLink);
+    expect(termsSection).toContainElement(privacyLink);
+  });
+
+  it("should open Terms of Service link in new tab", () => {
+    render(<AuthModal githubAuthUrl="mock-url" appMode="saas" />);
+
+    const tosLink = screen.getByRole("link", {
+      name: "COMMON$TERMS_OF_SERVICE",
+    });
+    expect(tosLink).toHaveAttribute("target", "_blank");
+  });
+
+  it("should open Privacy Policy link in new tab", () => {
+    render(<AuthModal githubAuthUrl="mock-url" appMode="saas" />);
+
+    const privacyLink = screen.getByRole("link", {
+      name: "COMMON$PRIVACY_POLICY",
+    });
+    expect(privacyLink).toHaveAttribute("target", "_blank");
+  });
 });
@@ -16,8 +16,6 @@ import { ConversationCard } from "#/components/features/conversation-panel/conve
 import { clickOnEditButton } from "./utils";

 // We'll use the actual i18next implementation but override the translation function
-import { I18nextProvider } from "react-i18next";
-import i18n from "i18next";

 // Mock the t function to return our custom translations
 vi.mock("react-i18next", async () => {
@@ -124,7 +122,8 @@ describe("ConversationCard", () => {

  it("should toggle a context menu when clicking the ellipsis button", async () => {
    const user = userEvent.setup();
-    renderWithProviders(
+    const onContextMenuToggle = vi.fn();
+    const { rerender } = renderWithProviders(
      <ConversationCard
        onDelete={onDelete}
        onChangeTitle={onChangeTitle}
@@ -132,6 +131,8 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen={false}
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

@@ -140,15 +141,32 @@ describe("ConversationCard", () => {
    const ellipsisButton = screen.getByTestId("ellipsis-button");
    await user.click(ellipsisButton);

+    expect(onContextMenuToggle).toHaveBeenCalledWith(true);
+
+    // Simulate context menu being opened by parent
+    rerender(
+      <ConversationCard
+        onDelete={onDelete}
+        onChangeTitle={onChangeTitle}
+        isActive
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
+      />,
+    );
+
    screen.getByTestId("context-menu");

    await user.click(ellipsisButton);

-    expect(screen.queryByTestId("context-menu")).not.toBeInTheDocument();
+    expect(onContextMenuToggle).toHaveBeenCalledWith(false);
  });

  it("should call onDelete when the delete button is clicked", async () => {
    const user = userEvent.setup();
+    const onContextMenuToggle = vi.fn();
    renderWithProviders(
      <ConversationCard
        onDelete={onDelete}
@@ -157,18 +175,18 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

-    const ellipsisButton = screen.getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-
    const menu = screen.getByTestId("context-menu");
    const deleteButton = within(menu).getByTestId("delete-button");

    await user.click(deleteButton);

    expect(onDelete).toHaveBeenCalled();
+    expect(onContextMenuToggle).toHaveBeenCalledWith(false);
  });

  test("clicking the selectedRepository should not trigger the onClick handler", async () => {
@@ -198,7 +216,11 @@ describe("ConversationCard", () => {

  test("conversation title should call onChangeTitle when changed and blurred", async () => {
    const user = userEvent.setup();
-    renderWithProviders(
+    let menuOpen = true;
+    const onContextMenuToggle = vi.fn((isOpen: boolean) => {
+      menuOpen = isOpen;
+    });
+    const { rerender } = renderWithProviders(
      <ConversationCard
        onDelete={onDelete}
        isActive
@@ -206,10 +228,27 @@ describe("ConversationCard", () => {
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
        onChangeTitle={onChangeTitle}
+        contextMenuOpen={menuOpen}
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

    await clickOnEditButton(user);
+
+    // Re-render with updated state
+    rerender(
+      <ConversationCard
+        onDelete={onDelete}
+        isActive
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+        onChangeTitle={onChangeTitle}
+        contextMenuOpen={menuOpen}
+        onContextMenuToggle={onContextMenuToggle}
+      />,
+    );
+
    const title = screen.getByTestId("conversation-card-title");

    expect(title).toBeEnabled();
@@ -227,6 +266,7 @@ describe("ConversationCard", () => {

  it("should reset title and not call onChangeTitle when the title is empty", async () => {
    const user = userEvent.setup();
+    const onContextMenuToggle = vi.fn();
    renderWithProviders(
      <ConversationCard
        onDelete={onDelete}
@@ -235,6 +275,8 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

@@ -271,6 +313,7 @@ describe("ConversationCard", () => {

  test("clicking the title should not trigger the onClick handler if edit mode", async () => {
    const user = userEvent.setup();
+    const onContextMenuToggle = vi.fn();
    renderWithProviders(
      <ConversationCard
        onDelete={onDelete}
@@ -279,6 +322,8 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

@@ -292,6 +337,7 @@ describe("ConversationCard", () => {

  test("clicking the delete button should not trigger the onClick handler", async () => {
    const user = userEvent.setup();
+    const onContextMenuToggle = vi.fn();
    renderWithProviders(
      <ConversationCard
        onDelete={onDelete}
@@ -300,12 +346,11 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

-    const ellipsisButton = screen.getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-
    const menu = screen.getByTestId("context-menu");
    const deleteButton = within(menu).getByTestId("delete-button");

@@ -315,7 +360,7 @@ describe("ConversationCard", () => {
  });

  it("should show display cost button only when showOptions is true", async () => {
-    const user = userEvent.setup();
+    const onContextMenuToggle = vi.fn();
    const { rerender } = renderWithProviders(
      <ConversationCard
        onDelete={onDelete}
@@ -324,21 +369,17 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

-    const ellipsisButton = screen.getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-
    // Wait for context menu to appear
    const menu = await screen.findByTestId("context-menu");
    expect(
      within(menu).queryByTestId("display-cost-button"),
    ).not.toBeInTheDocument();

-    // Close menu
-    await user.click(ellipsisButton);
-
    rerender(
      <ConversationCard
        onDelete={onDelete}
@@ -348,12 +389,11 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

-    // Open menu again
-    await user.click(ellipsisButton);
-
    // Wait for context menu to appear and check for display cost button
    const newMenu = await screen.findByTestId("context-menu");
    within(newMenu).getByTestId("display-cost-button");
@@ -361,6 +401,7 @@ describe("ConversationCard", () => {

  it("should show metrics modal when clicking the display cost button", async () => {
    const user = userEvent.setup();
+    const onContextMenuToggle = vi.fn();
    renderWithProviders(
      <ConversationCard
        onDelete={onDelete}
@@ -370,12 +411,11 @@ describe("ConversationCard", () => {
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
        showOptions
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

-    const ellipsisButton = screen.getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-
    const menu = screen.getByTestId("context-menu");
    const displayCostButton = within(menu).getByTestId("display-cost-button");

@@ -386,7 +426,7 @@ describe("ConversationCard", () => {
  });

  it("should not display the edit or delete options if the handler is not provided", async () => {
-    const user = userEvent.setup();
+    const onContextMenuToggle = vi.fn();
    const { rerender } = renderWithProviders(
      <ConversationCard
        onClick={onClick}
@@ -394,19 +434,15 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

-    const ellipsisButton = screen.getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-
    const menu = await screen.findByTestId("context-menu");
    expect(within(menu).queryByTestId("edit-button")).toBeInTheDocument();
    expect(within(menu).queryByTestId("delete-button")).not.toBeInTheDocument();

-    // toggle to hide the context menu
-    await user.click(ellipsisButton);
-
    rerender(
      <ConversationCard
        onClick={onClick}
@@ -414,10 +450,11 @@ describe("ConversationCard", () => {
        title="Conversation 1"
        selectedRepository={null}
        lastUpdatedAt="2021-10-01T12:00:00Z"
+        contextMenuOpen
+        onContextMenuToggle={onContextMenuToggle}
      />,
    );

-    await user.click(ellipsisButton);
    const newMenu = await screen.findByTestId("context-menu");
    expect(
      within(newMenu).queryByTestId("edit-button"),
@@ -529,4 +529,287 @@ describe("ConversationPanel", () => {

    expect(screen.queryByTestId("stop-button")).not.toBeInTheDocument();
  });
+
+  it("should show edit button in context menu", async () => {
+    const user = userEvent.setup();
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+    expect(cards).toHaveLength(3);
+
+    // Click ellipsis to open context menu
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    // Edit button should be visible
+    const editButton = screen.getByTestId("edit-button");
+    expect(editButton).toBeInTheDocument();
+    expect(editButton).toHaveTextContent("BUTTON$EDIT_TITLE");
+  });
+
+  it("should enter edit mode when edit button is clicked", async () => {
+    const user = userEvent.setup();
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Click ellipsis to open context menu
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    // Click edit button
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Should find input field instead of title text
+    const titleInput = within(cards[0]).getByTestId("conversation-card-title");
+    expect(titleInput).toBeInTheDocument();
+    expect(titleInput.tagName).toBe("INPUT");
+    expect(titleInput).toHaveValue("Conversation 1");
+    expect(titleInput).toHaveFocus();
+  });
+
+  it("should successfully update conversation title", async () => {
+    const user = userEvent.setup();
+
+    // Mock the updateConversation API call
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
+    updateConversationSpy.mockResolvedValue(true);
+
+    // Mock the toast function
+    const mockToast = vi.fn();
+    vi.mock("#/utils/custom-toast-handlers", () => ({
+      displaySuccessToast: mockToast,
+    }));
+
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Enter edit mode
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Edit the title
+    const titleInput = within(cards[0]).getByTestId("conversation-card-title");
+    await user.clear(titleInput);
+    await user.type(titleInput, "Updated Title");
+
+    // Blur the input to save
+    await user.tab();
+
+    // Verify API call was made with correct parameters
+    expect(updateConversationSpy).toHaveBeenCalledWith("1", {
+      title: "Updated Title",
+    });
+  });
+
+  it("should save title when Enter key is pressed", async () => {
+    const user = userEvent.setup();
+
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
+    updateConversationSpy.mockResolvedValue(true);
+
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Enter edit mode
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Edit the title and press Enter
+    const titleInput = within(cards[0]).getByTestId("conversation-card-title");
+    await user.clear(titleInput);
+    await user.type(titleInput, "Title Updated via Enter");
+    await user.keyboard("{Enter}");
+
+    // Verify API call was made
+    expect(updateConversationSpy).toHaveBeenCalledWith("1", {
+      title: "Title Updated via Enter",
+    });
+  });
+
+  it("should trim whitespace from title", async () => {
+    const user = userEvent.setup();
+
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
+    updateConversationSpy.mockResolvedValue(true);
+
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Enter edit mode
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Edit the title with extra whitespace
+    const titleInput = within(cards[0]).getByTestId("conversation-card-title");
+    await user.clear(titleInput);
+    await user.type(titleInput, "   Trimmed Title   ");
+    await user.tab();
+
+    // Verify API call was made with trimmed title
+    expect(updateConversationSpy).toHaveBeenCalledWith("1", {
+      title: "Trimmed Title",
+    });
+
+    // Verify input shows trimmed value
+    expect(titleInput).toHaveValue("Trimmed Title");
+  });
+
+  it("should revert to original title when empty", async () => {
+    const user = userEvent.setup();
+
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
+    updateConversationSpy.mockResolvedValue(true);
+
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Enter edit mode
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Clear the title completely
+    const titleInput = within(cards[0]).getByTestId("conversation-card-title");
+    await user.clear(titleInput);
+    await user.tab();
+
+    // Verify API was not called
+    expect(updateConversationSpy).not.toHaveBeenCalled();
+
+    // Verify input reverted to original value
+    expect(titleInput).toHaveValue("Conversation 1");
+  });
+
+  it("should handle API error when updating title", async () => {
+    const user = userEvent.setup();
+
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
+    updateConversationSpy.mockRejectedValue(new Error("API Error"));
+
+    vi.mock("#/utils/custom-toast-handlers", () => ({
+      displayErrorToast: vi.fn(),
+    }));
+
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Enter edit mode
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Edit the title
+    const titleInput = within(cards[0]).getByTestId("conversation-card-title");
+    await user.clear(titleInput);
+    await user.type(titleInput, "Failed Update");
+    await user.tab();
+
+    // Verify API call was made
+    expect(updateConversationSpy).toHaveBeenCalledWith("1", {
+      title: "Failed Update",
+    });
+
+    // Wait for error handling
+    await waitFor(() => {
+      expect(updateConversationSpy).toHaveBeenCalled();
+    });
+  });
+
+  it("should close context menu when edit button is clicked", async () => {
+    const user = userEvent.setup();
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Click ellipsis to open context menu
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    // Verify context menu is open
+    const contextMenu = screen.getByTestId("context-menu");
+    expect(contextMenu).toBeInTheDocument();
+
+    // Click edit button
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Verify context menu is closed
+    expect(screen.queryByTestId("context-menu")).not.toBeInTheDocument();
+  });
+
+  it("should not call API when title is unchanged", async () => {
+    const user = userEvent.setup();
+
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
+    updateConversationSpy.mockResolvedValue(true);
+
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Enter edit mode
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Don't change the title, just blur
+    const titleInput = within(cards[0]).getByTestId("conversation-card-title");
+    await user.tab();
+
+    // Verify API was called with the same title (since handleConversationTitleChange will always be called)
+    expect(updateConversationSpy).toHaveBeenCalledWith("1", {
+      title: "Conversation 1",
+    });
+  });
+
+  it("should handle special characters in title", async () => {
+    const user = userEvent.setup();
+
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
+    updateConversationSpy.mockResolvedValue(true);
+
+    renderConversationPanel();
+
+    const cards = await screen.findAllByTestId("conversation-card");
+
+    // Enter edit mode
+    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    const editButton = screen.getByTestId("edit-button");
+    await user.click(editButton);
+
+    // Edit the title with special characters
+    const titleInput = within(cards[0]).getByTestId("conversation-card-title");
+    await user.clear(titleInput);
+    await user.type(titleInput, "Special @#$%^&*()_+ Characters");
+    await user.tab();
+
+    // Verify API call was made with special characters
+    expect(updateConversationSpy).toHaveBeenCalledWith("1", {
+      title: "Special @#$%^&*()_+ Characters",
+    });
+  });
 });
@@ -72,6 +72,7 @@ describe("HomeHeader", () => {
      undefined,
      undefined,
      undefined,
+      undefined,
    );

    // expect to be redirected to /conversations/:conversationId
@@ -209,6 +209,7 @@ describe("RepoConnector", () => {
      undefined,
      "main",
      undefined,
+      undefined,
    );
  });

@@ -97,6 +97,7 @@ describe("TaskCard", () => {
        },
        undefined,
        undefined,
+        undefined,
      );
    });
  });
@@ -110,4 +111,29 @@ describe("TaskCard", () => {
    expect(launchButton).toHaveTextContent(/Loading/i);
    expect(launchButton).toBeDisabled();
  });
+
+  it("should navigate to the conversation page after creating a conversation", async () => {
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
+    createConversationSpy.mockResolvedValue({
+      conversation_id: "test-conversation-id",
+      title: "Test Conversation",
+      selected_repository: "repo1",
+      selected_branch: "main",
+      git_provider: "github",
+      last_updated_at: "2023-01-01T00:00:00Z",
+      created_at: "2023-01-01T00:00:00Z",
+      status: "RUNNING",
+      runtime_status: "STATUS$READY",
+      url: null,
+      session_api_key: null
+    });
+
+    renderTaskCard();
+
+    const launchButton = screen.getByTestId("task-launch-button");
+    await userEvent.click(launchButton);
+
+    // Wait for navigation to the conversation page
+    await screen.findByTestId("conversation-screen");
+  });
 });
@@ -0,0 +1,52 @@
+import { render, screen } from "@testing-library/react";
+import { describe, expect, it, vi } from "vitest";
+import { MaintenanceBanner } from "#/components/features/maintenance/maintenance-banner";
+
+// Mock react-i18next
+vi.mock("react-i18next", async () => {
+  const actual = await vi.importActual<typeof import("react-i18next")>("react-i18next");
+  return {
+    ...actual,
+    useTranslation: () => ({
+      t: (key: string, options?: { time?: string }) => {
+        const translations: Record<string, string> = {
+          "MAINTENANCE$SCHEDULED_MESSAGE": `Scheduled maintenance will begin at ${options?.time || "{{time}}"}`,
+        };
+        return translations[key] || key;
+      },
+    }),
+  };
+});
+
+describe("MaintenanceBanner", () => {
+  it("renders maintenance banner with formatted time", () => {
+    const startTime = "2024-01-15T10:00:00-05:00"; // EST timestamp
+
+    const { container } = render(<MaintenanceBanner startTime={startTime} />);
+
+    // Check if the banner is rendered
+    expect(screen.getByText(/Scheduled maintenance will begin at/)).toBeInTheDocument();
+
+    // Check if the warning icon (SVG) is present
+    const svgIcon = container.querySelector('svg');
+    expect(svgIcon).toBeInTheDocument();
+  });
+
+  it("handles invalid date gracefully", () => {
+    const invalidTime = "invalid-date";
+
+    render(<MaintenanceBanner startTime={invalidTime} />);
+
+    // Should still render the banner with the original string
+    expect(screen.getByText(/Scheduled maintenance will begin at invalid-date/)).toBeInTheDocument();
+  });
+
+  it("formats ISO date string correctly", () => {
+    const isoTime = "2024-01-15T15:30:00.000Z";
+
+    render(<MaintenanceBanner startTime={isoTime} />);
+
+    // Should render the banner (exact time format will depend on user's timezone)
+    expect(screen.getByText(/Scheduled maintenance will begin at/)).toBeInTheDocument();
+  });
+});
@@ -28,6 +28,9 @@ describe("PaymentForm", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: true,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });
  });
@@ -73,4 +73,73 @@ describe("TrajectoryActions", () => {

    expect(onExportTrajectory).toHaveBeenCalled();
  });
+
+  describe("SaaS mode", () => {
+    it("should only render export button when isSaasMode is true", () => {
+      renderWithProviders(
+        <TrajectoryActions
+          onPositiveFeedback={onPositiveFeedback}
+          onNegativeFeedback={onNegativeFeedback}
+          onExportTrajectory={onExportTrajectory}
+          isSaasMode={true}
+        />,
+      );
+
+      const actions = screen.getByTestId("feedback-actions");
+
+      // Should not render feedback buttons in SaaS mode
+      expect(within(actions).queryByTestId("positive-feedback")).toBeNull();
+      expect(within(actions).queryByTestId("negative-feedback")).toBeNull();
+
+      // Should still render export button
+      within(actions).getByTestId("export-trajectory");
+    });
+
+    it("should render all buttons when isSaasMode is false", () => {
+      renderWithProviders(
+        <TrajectoryActions
+          onPositiveFeedback={onPositiveFeedback}
+          onNegativeFeedback={onNegativeFeedback}
+          onExportTrajectory={onExportTrajectory}
+          isSaasMode={false}
+        />,
+      );
+
+      const actions = screen.getByTestId("feedback-actions");
+      within(actions).getByTestId("positive-feedback");
+      within(actions).getByTestId("negative-feedback");
+      within(actions).getByTestId("export-trajectory");
+    });
+
+    it("should render all buttons when isSaasMode is undefined (default behavior)", () => {
+      renderWithProviders(
+        <TrajectoryActions
+          onPositiveFeedback={onPositiveFeedback}
+          onNegativeFeedback={onNegativeFeedback}
+          onExportTrajectory={onExportTrajectory}
+        />,
+      );
+
+      const actions = screen.getByTestId("feedback-actions");
+      within(actions).getByTestId("positive-feedback");
+      within(actions).getByTestId("negative-feedback");
+      within(actions).getByTestId("export-trajectory");
+    });
+
+    it("should call onExportTrajectory when export button is clicked in SaaS mode", async () => {
+      renderWithProviders(
+        <TrajectoryActions
+          onPositiveFeedback={onPositiveFeedback}
+          onNegativeFeedback={onNegativeFeedback}
+          onExportTrajectory={onExportTrajectory}
+          isSaasMode={true}
+        />,
+      );
+
+      const exportButton = screen.getByTestId("export-trajectory");
+      await user.click(exportButton);
+
+      expect(onExportTrajectory).toHaveBeenCalled();
+    });
+  });
 });
@@ -1,27 +1,64 @@
 import { render, screen } from "@testing-library/react";
-import { describe, expect, it, test, vi, afterEach } from "vitest";
+import { describe, expect, it, test, vi, afterEach, beforeEach } from "vitest";
 import userEvent from "@testing-library/user-event";
 import { UserActions } from "#/components/features/sidebar/user-actions";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
+import { ReactElement } from "react";
+
+// Create a mock for useIsAuthed that we can control per test
+const useIsAuthedMock = vi
+  .fn()
+  .mockReturnValue({ data: true, isLoading: false });
+
+// Mock the useIsAuthed hook
+vi.mock("#/hooks/query/use-is-authed", () => ({
+  useIsAuthed: () => useIsAuthedMock(),
+}));

 describe("UserActions", () => {
  const user = userEvent.setup();
  const onClickAccountSettingsMock = vi.fn();
  const onLogoutMock = vi.fn();

+  // Create a wrapper with QueryClientProvider
+  const renderWithQueryClient = (ui: ReactElement) => {
+    const queryClient = new QueryClient({
+      defaultOptions: {
+        queries: {
+          retry: false,
+        },
+      },
+    });
+
+    return render(ui, {
+      wrapper: ({ children }) => (
+        <QueryClientProvider client={queryClient}>
+          {children}
+        </QueryClientProvider>
+      ),
+    });
+  };
+
+  beforeEach(() => {
+    // Reset the mock to default value before each test
+    useIsAuthedMock.mockReturnValue({ data: true, isLoading: false });
+  });
+
  afterEach(() => {
    onClickAccountSettingsMock.mockClear();
    onLogoutMock.mockClear();
+    vi.clearAllMocks();
  });

  it("should render", () => {
-    render(<UserActions onLogout={onLogoutMock} />);
+    renderWithQueryClient(<UserActions onLogout={onLogoutMock} />);

    expect(screen.getByTestId("user-actions")).toBeInTheDocument();
    expect(screen.getByTestId("user-avatar")).toBeInTheDocument();
  });

  it("should toggle the user menu when the user avatar is clicked", async () => {
-    render(
+    renderWithQueryClient(
      <UserActions
        onLogout={onLogoutMock}
        user={{ avatar_url: "https://example.com/avatar.png" }}
@@ -43,7 +80,7 @@ describe("UserActions", () => {
  });

  it("should call onLogout and close the menu when the logout option is clicked", async () => {
-    render(
+    renderWithQueryClient(
      <UserActions
        onLogout={onLogoutMock}
        user={{ avatar_url: "https://example.com/avatar.png" }}
@@ -62,20 +99,25 @@ describe("UserActions", () => {
    ).not.toBeInTheDocument();
  });

-  it("should NOT show context menu when user is undefined and avatar is clicked", async () => {
-    render(<UserActions onLogout={onLogoutMock} />);
+  it("should NOT show context menu when user is not authenticated and avatar is clicked", async () => {
+    // Set isAuthed to false for this test
+    useIsAuthedMock.mockReturnValue({ data: false, isLoading: false });
+
+    renderWithQueryClient(<UserActions onLogout={onLogoutMock} />);

    const userAvatar = screen.getByTestId("user-avatar");
    await user.click(userAvatar);

-    // Context menu should NOT appear because user is undefined
+    // Context menu should NOT appear because user is not authenticated
    expect(
      screen.queryByTestId("account-settings-context-menu"),
    ).not.toBeInTheDocument();
  });

  it("should show context menu even when user has no avatar_url", async () => {
-    render(<UserActions onLogout={onLogoutMock} user={{ avatar_url: "" }} />);
+    renderWithQueryClient(
+      <UserActions onLogout={onLogoutMock} user={{ avatar_url: "" }} />,
+    );

    const userAvatar = screen.getByTestId("user-avatar");
    await user.click(userAvatar);
@@ -86,42 +128,74 @@ describe("UserActions", () => {
    ).toBeInTheDocument();
  });

-  it("should NOT be able to access logout when no user is provided", async () => {
-    render(<UserActions onLogout={onLogoutMock} />);
+  it("should NOT be able to access logout when user is not authenticated", async () => {
+    // Set isAuthed to false for this test
+    useIsAuthedMock.mockReturnValue({ data: false, isLoading: false });
+
+    renderWithQueryClient(<UserActions onLogout={onLogoutMock} />);

    const userAvatar = screen.getByTestId("user-avatar");
    await user.click(userAvatar);

-    // Logout option should not be accessible because context menu doesn't appear
-    expect(
-      screen.queryByText("ACCOUNT_SETTINGS$LOGOUT"),
-    ).not.toBeInTheDocument();
-    expect(onLogoutMock).not.toHaveBeenCalled();
-  });
-
-  it("should handle user prop changing from undefined to defined", () => {
-    const { rerender } = render(<UserActions onLogout={onLogoutMock} />);
-
-    // Initially no user - context menu shouldn't work
+    // Context menu should NOT appear because user is not authenticated
    expect(
      screen.queryByTestId("account-settings-context-menu"),
    ).not.toBeInTheDocument();

-    // Add user prop
+    // Logout option should NOT be accessible when user is not authenticated
+    expect(screen.queryByText("ACCOUNT_SETTINGS$LOGOUT")).not.toBeInTheDocument();
+  });
+
+  it("should handle user prop changing from undefined to defined", async () => {
+    // Start with no authentication
+    useIsAuthedMock.mockReturnValue({ data: false, isLoading: false });
+
+    const { rerender } = renderWithQueryClient(
+      <UserActions onLogout={onLogoutMock} />,
+    );
+
+    // Initially no user and not authenticated - menu should not appear
+    let userAvatar = screen.getByTestId("user-avatar");
+    await user.click(userAvatar);
+    expect(
+      screen.queryByTestId("account-settings-context-menu"),
+    ).not.toBeInTheDocument();
+
+    // Set authentication to true for the rerender
+    useIsAuthedMock.mockReturnValue({ data: true, isLoading: false });
+
+    // Add user prop and create a new QueryClient to ensure fresh state
+    const queryClient = new QueryClient({
+      defaultOptions: {
+        queries: {
+          retry: false,
+        },
+      },
+    });
+
    rerender(
-      <UserActions
-        onLogout={onLogoutMock}
-        user={{ avatar_url: "https://example.com/avatar.png" }}
-      />,
+      <QueryClientProvider client={queryClient}>
+        <UserActions
+          onLogout={onLogoutMock}
+          user={{ avatar_url: "https://example.com/avatar.png" }}
+        />
+      </QueryClientProvider>,
    );

    // Component should still render correctly
    expect(screen.getByTestId("user-actions")).toBeInTheDocument();
    expect(screen.getByTestId("user-avatar")).toBeInTheDocument();
+
+    // Menu should now work with user defined and authenticated
+    userAvatar = screen.getByTestId("user-avatar");
+    await user.click(userAvatar);
+    expect(
+      screen.getByTestId("account-settings-context-menu"),
+    ).toBeInTheDocument();
  });

  it("should handle user prop changing from defined to undefined", async () => {
-    const { rerender } = render(
+    const { rerender } = renderWithQueryClient(
      <UserActions
        onLogout={onLogoutMock}
        user={{ avatar_url: "https://example.com/avatar.png" }}
@@ -135,16 +209,27 @@ describe("UserActions", () => {
      screen.getByTestId("account-settings-context-menu"),
    ).toBeInTheDocument();

-    // Remove user prop - menu should disappear
-    rerender(<UserActions onLogout={onLogoutMock} />);
+    // Set authentication to false for the rerender
+    useIsAuthedMock.mockReturnValue({ data: false, isLoading: false });

+    // Remove user prop - menu should disappear because user is no longer authenticated
+    rerender(
+      <QueryClientProvider client={new QueryClient()}>
+        <UserActions onLogout={onLogoutMock} />
+      </QueryClientProvider>,
+    );
+
+    // Context menu should NOT be visible when user becomes unauthenticated
    expect(
      screen.queryByTestId("account-settings-context-menu"),
    ).not.toBeInTheDocument();
+
+    // Logout option should not be accessible
+    expect(screen.queryByText("ACCOUNT_SETTINGS$LOGOUT")).not.toBeInTheDocument();
  });

  it("should work with loading state and user provided", async () => {
-    render(
+    renderWithQueryClient(
      <UserActions
        onLogout={onLogoutMock}
        user={{ avatar_url: "https://example.com/avatar.png" }}
@@ -1,140 +0,0 @@
-import { renderHook, waitFor } from "@testing-library/react";
-import { describe, expect, it, vi, beforeEach } from "vitest";
-import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
-import OpenHands from "#/api/open-hands";
-import { useFeedbackExists } from "#/hooks/query/use-feedback-exists";
-
-// Mock the useConfig hook
-vi.mock("#/hooks/query/use-config", () => ({
-  useConfig: vi.fn(),
-}));
-
-// Mock the useConversationId hook
-vi.mock("#/hooks/use-conversation-id", () => ({
-  useConversationId: () => ({ conversationId: "test-conversation-id" }),
-}));
-
-describe("useFeedbackExists", () => {
-  let queryClient: QueryClient;
-  const mockCheckFeedbackExists = vi.spyOn(OpenHands, "checkFeedbackExists");
-
-  beforeEach(() => {
-    queryClient = new QueryClient({
-      defaultOptions: { queries: { retry: false } },
-    });
-    mockCheckFeedbackExists.mockClear();
-  });
-
-  const wrapper = ({ children }: { children: React.ReactNode }) => (
-    <QueryClientProvider client={queryClient}>{children}</QueryClientProvider>
-  );
-
-  it("should not call API when APP_MODE is not saas", async () => {
-    const { useConfig } = await import("#/hooks/query/use-config");
-    vi.mocked(useConfig).mockReturnValue({
-      data: { APP_MODE: "oss" },
-      isLoading: false,
-      error: null,
-    } as ReturnType<typeof useConfig>);
-
-    const { result } = renderHook(() => useFeedbackExists(123), {
-      wrapper,
-    });
-
-    // Wait for any potential async operations
-    await waitFor(() => {
-      expect(result.current.isLoading).toBe(false);
-    });
-
-    // Verify that the API was not called
-    expect(mockCheckFeedbackExists).not.toHaveBeenCalled();
-
-    // Verify that the query is disabled
-    expect(result.current.data).toBeUndefined();
-  });
-
-  it("should call API when APP_MODE is saas", async () => {
-    const { useConfig } = await import("#/hooks/query/use-config");
-    vi.mocked(useConfig).mockReturnValue({
-      data: { APP_MODE: "saas" },
-      isLoading: false,
-      error: null,
-    } as ReturnType<typeof useConfig>);
-
-    mockCheckFeedbackExists.mockResolvedValue({
-      exists: true,
-      rating: 5,
-      reason: "Great job!",
-    });
-
-    const { result } = renderHook(() => useFeedbackExists(123), {
-      wrapper,
-    });
-
-    // Wait for the query to complete
-    await waitFor(() => {
-      expect(result.current.isLoading).toBe(false);
-    });
-
-    // Verify that the API was called
-    expect(mockCheckFeedbackExists).toHaveBeenCalledWith(
-      "test-conversation-id",
-      123,
-    );
-
-    // Verify that the data is returned
-    expect(result.current.data).toEqual({
-      exists: true,
-      rating: 5,
-      reason: "Great job!",
-    });
-  });
-
-  it("should not call API when eventId is not provided", async () => {
-    const { useConfig } = await import("#/hooks/query/use-config");
-    vi.mocked(useConfig).mockReturnValue({
-      data: { APP_MODE: "saas" },
-      isLoading: false,
-      error: null,
-    } as ReturnType<typeof useConfig>);
-
-    const { result } = renderHook(() => useFeedbackExists(undefined), {
-      wrapper,
-    });
-
-    // Wait for any potential async operations
-    await waitFor(() => {
-      expect(result.current.isLoading).toBe(false);
-    });
-
-    // Verify that the API was not called
-    expect(mockCheckFeedbackExists).not.toHaveBeenCalled();
-
-    // Verify that the query is disabled
-    expect(result.current.data).toBeUndefined();
-  });
-
-  it("should not call API when config is not loaded yet", async () => {
-    const { useConfig } = await import("#/hooks/query/use-config");
-    vi.mocked(useConfig).mockReturnValue({
-      data: undefined,
-      isLoading: true,
-      error: null,
-    } as ReturnType<typeof useConfig>);
-
-    const { result } = renderHook(() => useFeedbackExists(123), {
-      wrapper,
-    });
-
-    // Wait for any potential async operations
-    await waitFor(() => {
-      expect(result.current.isLoading).toBe(false);
-    });
-
-    // Verify that the API was not called
-    expect(mockCheckFeedbackExists).not.toHaveBeenCalled();
-
-    // Verify that the query is disabled
-    expect(result.current.data).toBeUndefined();
-  });
-});
@@ -76,6 +76,9 @@ describe("frontend/routes/_oh", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: false,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });

@@ -111,6 +114,9 @@ describe("frontend/routes/_oh", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: false,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });

@@ -192,6 +198,9 @@ describe("frontend/routes/_oh", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: false,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });

@@ -17,6 +17,9 @@ const VALID_OSS_CONFIG: GetConfigResponse = {
  FEATURE_FLAGS: {
    ENABLE_BILLING: false,
    HIDE_LLM_SETTINGS: false,
+    ENABLE_JIRA: false,
+    ENABLE_JIRA_DC: false,
+    ENABLE_LINEAR: false,
  },
 };

@@ -27,6 +30,9 @@ const VALID_SAAS_CONFIG: GetConfigResponse = {
  FEATURE_FLAGS: {
    ENABLE_BILLING: false,
    HIDE_LLM_SETTINGS: false,
+    ENABLE_JIRA: false,
+    ENABLE_JIRA_DC: false,
+    ENABLE_LINEAR: false,
  },
 };

@@ -222,10 +222,12 @@ describe("HomeScreen", () => {
      // All other buttons should be disabled when the header button is clicked
      await userEvent.click(headerLaunchButton);

-      expect(headerLaunchButton).toBeDisabled();
-      expect(repoLaunchButton).toBeDisabled();
-      tasksLaunchButtonsAfter.forEach((button) => {
-        expect(button).toBeDisabled();
+      await waitFor(() => {
+        expect(headerLaunchButton).toBeDisabled();
+        expect(repoLaunchButton).toBeDisabled();
+        tasksLaunchButtonsAfter.forEach((button) => {
+          expect(button).toBeDisabled();
+        });
      });
    });

@@ -240,10 +242,12 @@ describe("HomeScreen", () => {
      // All other buttons should be disabled when the repo button is clicked
      await userEvent.click(repoLaunchButton);

-      expect(headerLaunchButton).toBeDisabled();
-      expect(repoLaunchButton).toBeDisabled();
-      tasksLaunchButtonsAfter.forEach((button) => {
-        expect(button).toBeDisabled();
+      await waitFor(() => {
+        expect(headerLaunchButton).toBeDisabled();
+        expect(repoLaunchButton).toBeDisabled();
+        tasksLaunchButtonsAfter.forEach((button) => {
+          expect(button).toBeDisabled();
+        });
      });
    });

@@ -258,10 +262,12 @@ describe("HomeScreen", () => {
      // All other buttons should be disabled when the task button is clicked
      await userEvent.click(tasksLaunchButtons[0]);

-      expect(headerLaunchButton).toBeDisabled();
-      expect(repoLaunchButton).toBeDisabled();
-      tasksLaunchButtonsAfter.forEach((button) => {
-        expect(button).toBeDisabled();
+      await waitFor(() => {
+        expect(headerLaunchButton).toBeDisabled();
+        expect(repoLaunchButton).toBeDisabled();
+        tasksLaunchButtonsAfter.forEach((button) => {
+          expect(button).toBeDisabled();
+        });
      });
    });
  });
@@ -327,6 +333,9 @@ describe("Settings 404", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: false,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });
    const error = createAxiosNotFoundErrorObject();
@@ -349,6 +358,9 @@ describe("Setup Payment modal", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: true,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });
    const error = createAxiosNotFoundErrorObject();
@@ -366,17 +366,17 @@ describe("Form submission", () => {

    renderLlmSettingsScreen();
    await screen.findByTestId("llm-settings-screen");
-    screen.getByTestId("llm-settings-form-advanced");
+    await screen.findByTestId("llm-settings-form-advanced");

-    const submitButton = screen.getByTestId("submit-button");
+    const submitButton = await screen.findByTestId("submit-button");
    expect(submitButton).toBeDisabled();

-    const model = screen.getByTestId("llm-custom-model-input");
-    const baseUrl = screen.getByTestId("base-url-input");
-    const apiKey = screen.getByTestId("llm-api-key-input");
-    const agent = screen.getByTestId("agent-input");
-    const confirmation = screen.getByTestId("enable-confirmation-mode-switch");
-    const condensor = screen.getByTestId("enable-memory-condenser-switch");
+    const model = await screen.findByTestId("llm-custom-model-input");
+    const baseUrl = await screen.findByTestId("base-url-input");
+    const apiKey = await screen.findByTestId("llm-api-key-input");
+    const agent = await screen.findByTestId("agent-input");
+    const confirmation = await screen.findByTestId("enable-confirmation-mode-switch");
+    const condensor = await screen.findByTestId("enable-memory-condenser-switch");

    // enter custom model
    await userEvent.type(model, "-mini");
@@ -449,7 +449,7 @@ describe("Form submission", () => {
    expect(submitButton).toBeDisabled();

    // select security analyzer
-    const securityAnalyzer = screen.getByTestId("security-analyzer-input");
+    const securityAnalyzer = await screen.findByTestId("security-analyzer-input");
    await userEvent.click(securityAnalyzer);
    const securityAnalyzerOption = screen.getByText("mock-invariant");
    await userEvent.click(securityAnalyzerOption);
@@ -101,7 +101,8 @@ describe("Content", () => {

    renderSecretsSettings();

-    expect(getSecretsSpy).not.toHaveBeenCalled();
+    // In SAAS mode, getSecrets is still called because the user is authenticated
+    await waitFor(() => expect(getSecretsSpy).toHaveBeenCalled());
    await waitFor(() =>
      expect(screen.queryByTestId("add-secret-button")).not.toBeInTheDocument(),
    );
@@ -86,6 +86,9 @@ describe("Settings Billing", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: false,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });

@@ -104,6 +107,9 @@ describe("Settings Billing", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: true,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });

@@ -122,6 +128,9 @@ describe("Settings Billing", () => {
      FEATURE_FLAGS: {
        ENABLE_BILLING: true,
        HIDE_LLM_SETTINGS: false,
+        ENABLE_JIRA: false,
+        ENABLE_JIRA_DC: false,
+        ENABLE_LINEAR: false,
      },
    });

@@ -82,17 +82,5 @@ describe("extractModelAndProvider", () => {
      model: "claude-opus-4-20250514",
      separator: "/",
    });
-
-    expect(extractModelAndProvider("claude-3-haiku-20240307")).toEqual({
-      provider: "anthropic",
-      model: "claude-3-haiku-20240307",
-      separator: "/",
-    });
-
-    expect(extractModelAndProvider("claude-2.1")).toEqual({
-      provider: "anthropic",
-      model: "claude-2.1",
-      separator: "/",
-    });
  });
 });
@@ -52,14 +52,16 @@ test("organizeModelsAndProviders", () => {
      separator: "/",
      models: [
        "claude-3-5-sonnet-20241022",
+      ],
+    },
+    other: {
+      separator: "",
+      models: [
+        "together-ai-21.1b-41b",
        "claude-3-haiku-20240307",
        "claude-2",
        "claude-2.1",
      ],
    },
-    other: {
-      separator: "",
-      models: ["together-ai-21.1b-41b"],
-    },
  });
 });
@@ -1,56 +1,57 @@
 {
  "name": "openhands-frontend",
-  "version": "0.48.0",
+  "version": "0.51.1",
  "private": true,
  "type": "module",
  "engines": {
-    "node": ">=20.0.0"
+    "node": ">=22.0.0"
  },
  "dependencies": {
-    "@heroui/react": "^2.8.0-beta.13",
+    "@heroui/react": "^2.8.2",
    "@microlink/react-json-view": "^1.26.2",
    "@monaco-editor/react": "^4.7.0-rc.0",
-    "@react-router/node": "^7.6.3",
-    "@react-router/serve": "^7.6.3",
-    "@react-types/shared": "^3.29.1",
+    "@react-router/node": "^7.7.1",
+    "@react-router/serve": "^7.7.1",
+    "@react-types/shared": "^3.31.0",
    "@reduxjs/toolkit": "^2.8.2",
-    "@stripe/react-stripe-js": "^3.7.0",
-    "@stripe/stripe-js": "^7.4.0",
+    "@stripe/react-stripe-js": "^3.8.1",
+    "@stripe/stripe-js": "^7.7.0",
    "@tailwindcss/postcss": "^4.1.11",
    "@tailwindcss/vite": "^4.1.11",
-    "@tanstack/react-query": "^5.81.4",
-    "@vitejs/plugin-react": "^4.6.0",
+    "@tanstack/react-query": "^5.84.1",
+    "@vitejs/plugin-react": "^4.7.0",
    "@xterm/addon-fit": "^0.10.0",
    "@xterm/xterm": "^5.4.0",
-    "axios": "^1.10.0",
+    "axios": "^1.11.0",
    "clsx": "^2.1.1",
    "eslint-config-airbnb-typescript": "^18.0.0",
-    "framer-motion": "^12.23.0",
+    "framer-motion": "^12.23.12",
    "i18next": "^25.3.2",
    "i18next-browser-languagedetector": "^8.2.0",
    "i18next-http-backend": "^3.0.2",
-    "isbot": "^5.1.28",
-    "jose": "^6.0.11",
-    "lucide-react": "^0.525.0",
+    "isbot": "^5.1.29",
+    "jose": "^6.0.12",
+    "lucide-react": "^0.536.0",
    "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.257.0",
-    "react": "^19.1.0",
-    "react-dom": "^19.1.0",
+    "posthog-js": "^1.258.5",
+    "react": "^19.1.1",
+    "react-dom": "^19.1.1",
    "react-highlight": "^0.15.0",
    "react-hot-toast": "^2.5.1",
-    "react-i18next": "^15.6.0",
+    "react-i18next": "^15.6.1",
    "react-icons": "^5.5.0",
    "react-markdown": "^10.1.0",
    "react-redux": "^9.2.0",
-    "react-router": "^7.6.3",
+    "react-router": "^7.7.1",
    "react-syntax-highlighter": "^15.6.1",
    "react-textarea-autosize": "^8.5.9",
+    "remark-breaks": "^4.0.0",
    "remark-gfm": "^4.0.1",
    "sirv-cli": "^3.0.1",
    "socket.io-client": "^4.8.1",
    "tailwind-merge": "^3.3.1",
-    "vite": "^7.0.3",
-    "web-vitals": "^5.0.3",
+    "vite": "^7.0.6",
+    "web-vitals": "^5.1.0",
    "ws": "^8.18.2"
  },
  "scripts": {
@@ -81,19 +82,19 @@
  "devDependencies": {
    "@babel/parser": "^7.28.0",
    "@babel/traverse": "^7.28.0",
-    "@babel/types": "^7.27.0",
+    "@babel/types": "^7.28.2",
    "@mswjs/socket.io-binding": "^0.2.0",
-    "@playwright/test": "^1.53.2",
-    "@react-router/dev": "^7.6.3",
+    "@playwright/test": "^1.54.2",
+    "@react-router/dev": "^7.7.1",
    "@tailwindcss/typography": "^0.5.16",
-    "@tanstack/eslint-plugin-query": "^5.81.2",
-    "@testing-library/dom": "^10.4.0",
-    "@testing-library/jest-dom": "^6.6.1",
+    "@tanstack/eslint-plugin-query": "^5.83.1",
+    "@testing-library/dom": "^10.4.1",
+    "@testing-library/jest-dom": "^6.6.4",
    "@testing-library/react": "^16.3.0",
    "@testing-library/user-event": "^14.6.1",
-    "@types/node": "^24.0.12",
-    "@types/react": "^19.1.8",
-    "@types/react-dom": "^19.1.6",
+    "@types/node": "^24.1.0",
+    "@types/react": "^19.1.9",
+    "@types/react-dom": "^19.1.7",
    "@types/react-highlight": "^0.12.8",
    "@types/react-syntax-highlighter": "^15.5.13",
    "@types/ws": "^8.18.1",
@@ -101,15 +102,15 @@
    "@typescript-eslint/parser": "^7.18.0",
    "@vitest/coverage-v8": "^3.2.3",
    "autoprefixer": "^10.4.21",
-    "cross-env": "^7.0.3",
+    "cross-env": "^10.0.0",
    "eslint": "^8.57.0",
    "eslint-config-airbnb": "^19.0.4",
    "eslint-config-airbnb-typescript": "^18.0.0",
-    "eslint-config-prettier": "^10.1.5",
-    "eslint-plugin-i18next": "^6.1.2",
+    "eslint-config-prettier": "^10.1.8",
+    "eslint-plugin-i18next": "^6.1.3",
    "eslint-plugin-import": "^2.32.0",
    "eslint-plugin-jsx-a11y": "^6.10.2",
-    "eslint-plugin-prettier": "^5.5.1",
+    "eslint-plugin-prettier": "^5.5.3",
    "eslint-plugin-react": "^7.37.5",
    "eslint-plugin-react-hooks": "^4.6.2",
    "eslint-plugin-unused-imports": "^4.1.4",
@@ -118,9 +119,9 @@
    "lint-staged": "^16.1.2",
    "msw": "^2.6.6",
    "prettier": "^3.6.2",
-    "stripe": "^18.3.0",
+    "stripe": "^18.4.0",
    "tailwindcss": "^4.1.8",
-    "typescript": "^5.8.3",
+    "typescript": "^5.9.2",
    "vite-plugin-svgr": "^4.2.0",
    "vite-tsconfig-paths": "^5.1.4",
    "vitest": "^3.0.2"
@@ -7,7 +7,7 @@
 * - Please do NOT modify this file.
 */

-const PACKAGE_VERSION = '2.10.2'
+const PACKAGE_VERSION = '2.10.3'
 const INTEGRITY_CHECKSUM = 'f5825c521429caf22a4dd13b66e243af'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()
@@ -13,11 +13,15 @@ import {
  GitChange,
  GetMicroagentsResponse,
  GetMicroagentPromptResponse,
+  CreateMicroagent,
+  MicroagentContentResponse,
 } from "./open-hands.types";
 import { openHands } from "./open-hands-axios";
 import { ApiSettings, PostApiSettings, Provider } from "#/types/settings";
 import { GitUser, GitRepository, Branch } from "#/types/git";
 import { SuggestedTask } from "#/components/features/home/tasks/task.types";
+import { RepositoryMicroagent } from "#/types/microagent-management";
+import { BatchFeedbackData } from "#/hooks/query/use-batch-feedback";

 class OpenHands {
  private static currentConversation: Conversation | null = null;
@@ -164,6 +168,38 @@ class OpenHands {
    }
  }

+  /**
+   * Get feedback for multiple events in a conversation
+   * @param conversationId The conversation ID
+   * @returns Map of event IDs to feedback data including existence, rating, reason and metadata
+   */
+  static async getBatchFeedback(conversationId: string): Promise<
+    Record<
+      string,
+      {
+        exists: boolean;
+        rating?: number;
+        reason?: string;
+        metadata?: Record<string, BatchFeedbackData>;
+      }
+    >
+  > {
+    const url = `/feedback/conversation/${conversationId}/batch`;
+    const { data } = await openHands.get<
+      Record<
+        string,
+        {
+          exists: boolean;
+          rating?: number;
+          reason?: string;
+          metadata?: Record<string, BatchFeedbackData>;
+        }
+      >
+    >(url);
+
+    return data;
+  }
+
  /**
   * Authenticate with GitHub token
   * @returns Response with authentication status and user info if successful
@@ -250,6 +286,28 @@ class OpenHands {
    return data.results;
  }

+  static async searchConversations(
+    selectedRepository?: string,
+    conversationTrigger?: string,
+    limit: number = 20,
+  ): Promise<Conversation[]> {
+    const params = new URLSearchParams();
+    params.append("limit", limit.toString());
+
+    if (selectedRepository) {
+      params.append("selected_repository", selectedRepository);
+    }
+
+    if (conversationTrigger) {
+      params.append("conversation_trigger", conversationTrigger);
+    }
+
+    const { data } = await openHands.get<ResultSet<Conversation>>(
+      `/api/conversations?${params.toString()}`,
+    );
+    return data.results;
+  }
+
  static async deleteUserConversation(conversationId: string): Promise<void> {
    await openHands.delete(`/api/conversations/${conversationId}`);
  }
@@ -261,6 +319,7 @@ class OpenHands {
    suggested_task?: SuggestedTask,
    selected_branch?: string,
    conversationInstructions?: string,
+    createMicroagent?: CreateMicroagent,
  ): Promise<Conversation> {
    const body = {
      repository: selectedRepository,
@@ -269,6 +328,7 @@ class OpenHands {
      initial_user_msg: initialUserMsg,
      suggested_task,
      conversation_instructions: conversationInstructions,
+      create_microagent: createMicroagent,
    };

    const { data } = await openHands.post<Conversation>(
@@ -464,6 +524,43 @@ class OpenHands {
    return data;
  }

+  /**
+   * Get the available microagents for a repository
+   * @param owner The repository owner
+   * @param repo The repository name
+   * @returns The available microagents for the repository
+   */
+  static async getRepositoryMicroagents(
+    owner: string,
+    repo: string,
+  ): Promise<RepositoryMicroagent[]> {
+    const { data } = await openHands.get<RepositoryMicroagent[]>(
+      `/api/user/repository/${owner}/${repo}/microagents`,
+    );
+    return data;
+  }
+
+  /**
+   * Get the content of a specific microagent from a repository
+   * @param owner The repository owner
+   * @param repo The repository name
+   * @param filePath The path to the microagent file within the repository
+   * @returns The microagent content and metadata
+   */
+  static async getRepositoryMicroagentContent(
+    owner: string,
+    repo: string,
+    filePath: string,
+  ): Promise<MicroagentContentResponse> {
+    const { data } = await openHands.get<MicroagentContentResponse>(
+      `/api/user/repository/${owner}/${repo}/microagents/content`,
+      {
+        params: { file_path: filePath },
+      },
+    );
+    return data;
+  }
+
  static async getMicroagentPrompt(
    conversationId: string,
    eventId: number,
@@ -477,6 +574,18 @@ class OpenHands {

    return data.prompt;
  }
+
+  static async updateConversation(
+    conversationId: string,
+    updates: { title: string },
+  ): Promise<boolean> {
+    const { data } = await openHands.patch<boolean>(
+      `/api/conversations/${conversationId}`,
+      updates,
+    );
+
+    return data;
+  }
 }

 export default OpenHands;
@@ -50,9 +50,17 @@ export interface GetConfigResponse {
  GITHUB_CLIENT_ID: string;
  POSTHOG_CLIENT_KEY: string;
  STRIPE_PUBLISHABLE_KEY?: string;
+  PROVIDERS_CONFIGURED?: Provider[];
  FEATURE_FLAGS: {
    ENABLE_BILLING: boolean;
    HIDE_LLM_SETTINGS: boolean;
+    HIDE_MICROAGENT_MANAGEMENT?: boolean;
+    ENABLE_JIRA: boolean;
+    ENABLE_JIRA_DC: boolean;
+    ENABLE_LINEAR: boolean;
+  };
+  MAINTENANCE?: {
+    startTime: string;
  };
 }

@@ -77,7 +85,11 @@ export interface RepositorySelection {
  git_provider: Provider | null;
 }

-export type ConversationTrigger = "resolver" | "gui" | "suggested_task";
+export type ConversationTrigger =
+  | "resolver"
+  | "gui"
+  | "suggested_task"
+  | "microagent_management";

 export interface Conversation {
  conversation_id: string;
@@ -92,6 +104,7 @@ export interface Conversation {
  trigger?: ConversationTrigger;
  url: string | null;
  session_api_key: string | null;
+  pr_number?: number[] | null;
 }

 export interface ResultSet<T> {
@@ -131,3 +144,16 @@ export interface GetMicroagentPromptResponse {
  status: string;
  prompt: string;
 }
+
+export interface CreateMicroagent {
+  repo: string;
+  git_provider?: Provider;
+  title?: string;
+}
+
+export interface MicroagentContentResponse {
+  content: string;
+  path: string;
+  git_provider: Provider;
+  triggers: string[];
+}
@@ -19,8 +19,11 @@ export function ActionSuggestions({
  const [hasPullRequest, setHasPullRequest] = React.useState(false);

  const providersAreSet = providers.length > 0;
-  const isGitLab = providers.includes("gitlab");
-  const isBitbucket = providers.includes("bitbucket");
+
+  // Use the git_provider from the conversation, not the user's authenticated providers
+  const currentGitProvider = conversation?.git_provider;
+  const isGitLab = currentGitProvider === "gitlab";
+  const isBitbucket = currentGitProvider === "bitbucket";

  const pr = isGitLab ? "merge request" : "pull request";
  const prShort = isGitLab ? "MR" : "PR";
@@ -35,7 +38,7 @@ export function ActionSuggestions({
    pr,
    prShort,
    pushToBranch: `Please push the changes to a remote branch on ${getProviderName()}, but do NOT create a ${pr}. Check your current branch name first - if it's main, master, deploy, or another common default branch name, create a new branch with a descriptive name related to your changes. Otherwise, use the exact SAME branch name as the one you are currently on.`,
-    createPR: `Please push the changes to ${getProviderName()} and open a ${pr}. Please create a meaningful branch name that describes the changes. If a ${pr} template exists in the repository, please follow it when creating the ${prShort} description.`,
+    createPR: `Please push the changes to ${getProviderName()} and open a ${pr}. If you're on a default branch (e.g., main, master, deploy), create a new branch with a descriptive name otherwise use the current branch. If a ${pr} template exists in the repository, please follow it when creating the ${prShort} description.`,
    pushToPR: `Please push the latest changes to the existing ${pr}.`,
  };

@@ -232,17 +232,16 @@ export function ChatInterface() {

        <div className="flex flex-col gap-[6px] px-4 pb-4">
          <div className="flex justify-between relative">
-            {config?.APP_MODE !== "saas" && (
-              <TrajectoryActions
-                onPositiveFeedback={() =>
-                  onClickShareFeedbackActionButton("positive")
-                }
-                onNegativeFeedback={() =>
-                  onClickShareFeedbackActionButton("negative")
-                }
-                onExportTrajectory={() => onClickExportTrajectoryButton()}
-              />
-            )}
+            <TrajectoryActions
+              onPositiveFeedback={() =>
+                onClickShareFeedbackActionButton("positive")
+              }
+              onNegativeFeedback={() =>
+                onClickShareFeedbackActionButton("negative")
+              }
+              onExportTrajectory={() => onClickExportTrajectoryButton()}
+              isSaasMode={config?.APP_MODE === "saas"}
+            />

            <div className="absolute left-1/2 transform -translate-x-1/2 bottom-0">
              {curAgentState === AgentState.RUNNING && <TypingIndicator />}
@@ -1,6 +1,7 @@
 import React from "react";
 import Markdown from "react-markdown";
 import remarkGfm from "remark-gfm";
+import remarkBreaks from "remark-breaks";
 import { code } from "../markdown/code";
 import { cn } from "#/utils/utils";
 import { ul, ol } from "../markdown/list";
@@ -85,21 +86,19 @@ export function ChatMessage({
        />
      </div>

-      <div className="text-sm break-words flex">
-        <div>
-          <Markdown
-            components={{
-              code,
-              ul,
-              ol,
-              a: anchor,
-              p: paragraph,
-            }}
-            remarkPlugins={[remarkGfm]}
-          >
-            {message}
-          </Markdown>
-        </div>
+      <div className="text-sm break-words">
+        <Markdown
+          components={{
+            code,
+            ul,
+            ol,
+            a: anchor,
+            p: paragraph,
+          }}
+          remarkPlugins={[remarkGfm, remarkBreaks]}
+        >
+          {message}
+        </Markdown>
      </div>
      {children}
    </article>
@@ -1,6 +1,7 @@
 import React from "react";
 import Markdown from "react-markdown";
 import remarkGfm from "remark-gfm";
+import remarkBreaks from "remark-breaks";
 import { useTranslation } from "react-i18next";
 import { code } from "../markdown/code";
 import { ol, ul } from "../markdown/list";
@@ -46,7 +47,7 @@ export function ErrorMessage({ errorId, defaultMessage }: ErrorMessageProps) {
            ul,
            ol,
          }}
-          remarkPlugins={[remarkGfm]}
+          remarkPlugins={[remarkGfm, remarkBreaks]}
        >
          {defaultMessage}
        </Markdown>
@@ -77,25 +77,8 @@ const getMcpActionContent = (event: MCPAction): string => {
 const getThinkActionContent = (event: ThinkAction): string =>
  event.args.thought;

-const getFinishActionContent = (event: FinishAction): string => {
-  let content = event.args.final_thought;
-
-  switch (event.args.task_completed) {
-    case "success":
-      content += `\n\n\n${i18n.t("FINISH$TASK_COMPLETED_SUCCESSFULLY")}`;
-      break;
-    case "failure":
-      content += `\n\n\n${i18n.t("FINISH$TASK_NOT_COMPLETED")}`;
-      break;
-    case "partial":
-    default:
-      content += `\n\n\n${i18n.t("FINISH$TASK_COMPLETED_PARTIALLY")}`;
-      break;
-  }
-
-  return content.trim();
-};
-
+const getFinishActionContent = (event: FinishAction): string =>
+  event.args.final_thought.trim();
 const getNoContentActionContent = (): string => "";

 export const getActionContent = (event: OpenHandsAction): string => {
--- a/Show More
+++ b/Show More