Modify split_bash_commands to filter out comment-only commands

- Changed split_bash_commands to only return non-comment commands
- This eliminates the need to filter comment-only commands in calling code
- Preserves backward compatibility for comment-only input (returns as single command)
- Handles mixed commands by filtering out standalone comment lines
- Commands with inline comments are preserved as-is
- All existing tests continue to pass
- Fixed formatting in related test files

.github/CODEOWNERS

@@ -2,7 +2,7 @@
 # See https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners
 
 # Frontend code owners
-/frontend/ @rbren @amanape
+/frontend/ @amanape
 /openhands-ui/ @amanape
 
 # Evaluation code owners

.github/scripts/update_pr_description.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+
+set -euxo pipefail
+
+# This script updates the PR description with commands to run the PR locally
+# It adds both Docker and uvx commands
+
+# Get the branch name for the PR
+BRANCH_NAME=$(gh pr view "$PR_NUMBER" --json headRefName --jq .headRefName)
+
+# Define the Docker command
+DOCKER_RUN_COMMAND="docker run -it --rm \
+  -p 3000:3000 \
+  -v /var/run/docker.sock:/var/run/docker.sock \
+  --add-host host.docker.internal:host-gateway \
+  -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:${SHORT_SHA}-nikolaik \
+  --name openhands-app-${SHORT_SHA} \
+  docker.all-hands.dev/all-hands-ai/openhands:${SHORT_SHA}"
+
+# Define the uvx command
+UVX_RUN_COMMAND="uvx --python 3.12 --from git+https://github.com/All-Hands-AI/OpenHands@${BRANCH_NAME} openhands"
+
+# Get the current PR body
+PR_BODY=$(gh pr view "$PR_NUMBER" --json body --jq .body)
+
+# Prepare the new PR body with both commands
+if echo "$PR_BODY" | grep -q "To run this PR locally, use the following command:"; then
+  # For existing PR descriptions, use a more robust approach
+  # Split the PR body at the "To run this PR locally" section and replace everything after it
+  BEFORE_SECTION=$(echo "$PR_BODY" | sed '/To run this PR locally, use the following command:/,$d')
+  NEW_PR_BODY=$(cat <<EOF
+${BEFORE_SECTION}
+
+To run this PR locally, use the following command:
+
+GUI with Docker:
+\`\`\`
+${DOCKER_RUN_COMMAND}
+\`\`\`
+
+CLI with uvx:
+\`\`\`
+${UVX_RUN_COMMAND}
+\`\`\`
+EOF
+)
+else
+  # For new PR descriptions: use heredoc safely without indentation
+  NEW_PR_BODY=$(cat <<EOF
+$PR_BODY
+
+---
+
+To run this PR locally, use the following command:
+
+GUI with Docker:
+\`\`\`
+${DOCKER_RUN_COMMAND}
+\`\`\`
+
+CLI with uvx:
+\`\`\`
+${UVX_RUN_COMMAND}
+\`\`\`
+EOF
+)
+fi
+
+# Update the PR description
+echo "Updating PR description with Docker and uvx commands"
+gh pr edit "$PR_NUMBER" --body "$NEW_PR_BODY"

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

@@ -24,7 +24,7 @@ jobs:
     runs-on: blacksmith-4vcpu-ubuntu-2204
     strategy:
       matrix:
-        node-version: 22
+        node-version: [22]
       fail-fast: true
     steps:
       - name: Checkout

.github/workflows/ghcr-build.yml

@@ -332,29 +332,5 @@ jobs:
           SHORT_SHA: ${{ steps.short_sha.outputs.SHORT_SHA }}
         shell: bash
         run: |
-          echo "updating PR description"
-          DOCKER_RUN_COMMAND="docker run -it --rm \
-            -p 3000:3000 \
-            -v /var/run/docker.sock:/var/run/docker.sock \
-            --add-host host.docker.internal:host-gateway \
-            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:$SHORT_SHA-nikolaik \
-            --name openhands-app-$SHORT_SHA \
-            docker.all-hands.dev/all-hands-ai/openhands:$SHORT_SHA"
-
-          PR_BODY=$(gh pr view $PR_NUMBER --json body --jq .body)
-
-          if echo "$PR_BODY" | grep -q "To run this PR locally, use the following command:"; then
-            UPDATED_PR_BODY=$(echo "${PR_BODY}" | sed -E "s|docker run -it --rm.*|$DOCKER_RUN_COMMAND|")
-          else
-            UPDATED_PR_BODY="${PR_BODY}
-
-          ---
-
-          To run this PR locally, use the following command:
-          \`\`\`
-          $DOCKER_RUN_COMMAND
-          \`\`\`"
-          fi
-
-          echo "updated body: $UPDATED_PR_BODY"
-          gh pr edit $PR_NUMBER --body "$UPDATED_PR_BODY"
+          echo "Updating PR description with Docker and uvx commands"
+          bash ${GITHUB_WORKSPACE}/.github/scripts/update_pr_description.sh

.github/workflows/py-tests.yml

@@ -48,11 +48,11 @@ jobs:
       - name: Build Environment
         run: make build
       - name: Run Unit Tests
-        run: poetry run pytest --forked -n auto -svv ./tests/unit
+        run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest --forked -n auto -svv ./tests/unit
       - name: Run Runtime Tests with CLIRuntime
-        run: TEST_RUNTIME=cli poetry run pytest -svv tests/runtime/test_bash.py
+        run: PYTHONPATH=".:$PYTHONPATH" TEST_RUNTIME=cli poetry run pytest -svv tests/runtime/test_bash.py
       - name: Run E2E Tests
-        run: poetry run pytest -svv tests/e2e
+        run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest -svv tests/e2e
 
   # Run specific Windows python tests
   test-on-windows:
@@ -77,9 +77,11 @@ jobs:
       - name: Run Windows unit tests
         run: poetry run pytest -svv tests/unit/test_windows_bash.py
         env:
+          PYTHONPATH: ".;$env:PYTHONPATH"
           DEBUG: "1"
       - name: Run Windows runtime tests with LocalRuntime
         run: $env:TEST_RUNTIME="local"; poetry run pytest -svv tests/runtime/test_bash.py
         env:
+          PYTHONPATH: ".;$env:PYTHONPATH"
           TEST_RUNTIME: local
           DEBUG: "1"

.github/workflows/run-eval.yml

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

.github/workflows/stale.yml

@@ -12,11 +12,11 @@ jobs:
     steps:
       - uses: actions/stale@v9
         with:
-          stale-issue-message: 'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          days-before-stale: 30
+          stale-issue-message: 'This issue is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
+          stale-pr-message: 'This PR is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
+          days-before-stale: 40
           exempt-issue-labels: 'roadmap'
-          close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
-          close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
-          days-before-close: 7
+          close-issue-message: 'This issue was automatically closed due to 50 days of inactivity. We do this to help keep the issues somewhat manageable and focus on active issues.'
+          close-pr-message: 'This PR was closed because it had no activity for 50 days. If you feel this was closed in error, and you would like to continue the PR, please resubmit or let us know.'
+          days-before-close: 10
           operations-per-run: 150

.openhands/microagents/repo.md

@@ -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

.openhands/pre-commit.sh

@@ -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

Development.md

@@ -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:0.49-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.51-nikolaik`
 
 ## Develop inside Docker container
 

Makefile

@@ -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
 

README.md

@@ -62,17 +62,17 @@ system requirements and more information.
 
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.49-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:0.49-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:0.49
+    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.

README_CN.md

@@ -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:0.49-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:0.49-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:0.49
+    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。

README_JA.md

@@ -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:0.49-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:0.49-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:0.49
+    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。

containers/app/Dockerfile

@@ -58,8 +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

containers/app/entrypoint.sh

@@ -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

containers/dev/compose.yml

@@ -12,7 +12,7 @@ services:
       - SANDBOX_API_HOSTNAME=host.docker.internal
       - DOCKER_HOST_ADDR=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.49-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${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:

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

@@ -40,7 +40,7 @@ repos:
     hooks:
       - id: mypy
         additional_dependencies:
-          [types-requests, types-setuptools, types-pyyaml, types-toml, types-docker, pydantic, lxml]
+          [types-requests, types-setuptools, types-pyyaml, types-toml, types-docker, types-Markdown, pydantic, lxml]
         # To see gaps add `--html-report mypy-report/`
         entry: mypy --config-file dev_config/python/mypy.ini openhands/
         always_run: true

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.49-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:

docs/docs.json

@@ -37,7 +37,16 @@
                   "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",
@@ -62,6 +71,7 @@
                     {
                       "group": "Providers",
                       "pages": [
+                        "usage/llms/openhands-llms",
                         "usage/llms/azure-llms",
                         "usage/llms/google-llms",
                         "usage/llms/groq",
@@ -69,7 +79,6 @@
                         "usage/llms/litellm-proxy",
                         "usage/llms/moonshot",
                         "usage/llms/openai-llms",
-                        "usage/llms/openhands-llms",
                         "usage/llms/openrouter"
                       ]
                     }

docs/usage/cloud/bitbucket-installation.mdx

@@ -8,6 +8,29 @@ description: This guide walks you through the process of installing OpenHands Cl
 
 - 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.

docs/usage/cloud/project-management/jira-dc-integration.mdx

@@ -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>

docs/usage/cloud/project-management/jira-integration.mdx

@@ -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>

docs/usage/cloud/project-management/linear-integration.mdx

@@ -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>

docs/usage/cloud/project-management/overview.mdx

@@ -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)

docs/usage/cloud/slack-installation.mdx

@@ -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.
 

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

@@ -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:0.49-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:0.49 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.51 \
     python -m openhands.cli.main --override-cli-mode true
 ```
 
@@ -153,6 +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
 
@@ -162,7 +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
 
@@ -174,6 +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.

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

@@ -7,6 +7,67 @@ description: High level overview of the Graphical User Interface (GUI) in OpenHa
 
 - [OpenHands is running](/usage/local-setup)
 
+## Launching the GUI Server
+
+### Using the CLI Command
+
+You can launch the OpenHands GUI server directly from the command line using the `serve` command:
+
+<Callout type="info">
+**Prerequisites**: You need to have the [OpenHands CLI installed](/usage/how-to/cli-mode) first, OR have `uv` installed and run `uvx --python 3.12 --from openhands-ai openhands serve`. Otherwise, you'll need to use Docker directly (see the [Docker section](#using-docker-directly) below).
+</Callout>
+
+```bash
+openhands serve
+```
+
+This command will:
+- Check that Docker is installed and running
+- Pull the required Docker images
+- Launch the OpenHands GUI server at http://localhost:3000
+- Use the same configuration directory (`~/.openhands`) as the CLI mode
+
+#### Mounting Your Current Directory
+
+To mount your current working directory into the GUI server container, use the `--mount-cwd` flag:
+
+```bash
+openhands serve --mount-cwd
+```
+
+This is useful when you want to work on files in your current directory through the GUI. The directory will be mounted at `/workspace` inside the container.
+
+#### Using GPU Support
+
+If you have NVIDIA GPUs and want to make them available to the OpenHands container, use the `--gpu` flag:
+
+```bash
+openhands serve --gpu
+```
+
+This will enable GPU support via nvidia-docker, mounting all available GPUs into the container. You can combine this with other flags:
+
+```bash
+openhands serve --gpu --mount-cwd
+```
+
+**Prerequisites for GPU support:**
+- NVIDIA GPU drivers must be installed on your host system
+- [NVIDIA Container Toolkit (nvidia-docker2)](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html) must be installed and configured
+
+#### Requirements
+
+Before using the `openhands serve` command, ensure that:
+- Docker is installed and running on your system
+- You have internet access to pull the required Docker images
+- Port 3000 is available on your system
+
+The CLI will automatically check these requirements and provide helpful error messages if anything is missing.
+
+### Using Docker Directly
+
+Alternatively, you can run the GUI server using Docker directly. See the [local setup guide](/usage/local-setup) for detailed Docker instructions.
+
 ## Overview
 
 ### Initial Setup

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

@@ -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:0.49-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=$LLM_API_KEY \
@@ -73,7 +73,7 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.49 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.51 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/usage/llms/llms.mdx

@@ -18,7 +18,7 @@ Based on these findings and community feedback, these are the latest models that
 ### Cloud / API-Based Models
 
 - [anthropic/claude-sonnet-4-20250514](https://www.anthropic.com/api) (recommended)
-- [openai/o4-mini](https://openai.com/index/introducing-o3-and-o4-mini/)
+- [openai/gpt-5-2025-08-07](https://openai.com/api/) (recommended)
 - [gemini/gemini-2.5-pro](https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025/)
 - [deepseek/deepseek-chat](https://api-docs.deepseek.com/)
 - [moonshot/kimi-k2-0711-preview](https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2)
@@ -39,6 +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

docs/usage/llms/local-llms.mdx

@@ -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:0.49-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:0.49-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:0.49
+    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:0.49
+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

docs/usage/llms/openhands-llms.mdx

@@ -30,5 +30,6 @@ When running OpenHands, you'll need to set the following in the OpenHands UI thr
 
 ## 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)
+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.

docs/usage/local-setup.mdx

@@ -66,18 +66,42 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 
 ### Start the App
 
+#### Option 1: Using the CLI Launcher (Recommended)
+
+If you have Python 3.12+ installed, you can use the CLI launcher for a simpler experience:
+
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.49-nikolaik
+# Install OpenHands
+pip install openhands-ai
+
+# Launch the GUI server
+openhands serve
+
+# Or with GPU support (requires nvidia-docker)
+openhands serve --gpu
+
+# Or with current directory mounted
+openhands serve --mount-cwd
+```
+
+Or using `uvx --python 3.12 --from openhands-ai openhands serve` if you have [uv](https://docs.astral.sh/uv/) installed.
+
+This will automatically handle Docker requirements checking, image pulling, and launching the GUI server. The `--gpu` flag enables GPU support via nvidia-docker, and `--mount-cwd` mounts your current directory into the container.
+
+#### Option 2: Using Docker Directly
+
+```bash
+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:0.49-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:0.49
+    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.
@@ -100,6 +124,16 @@ OpenHands requires an API key to access most language models. Here's how to get
 
 <AccordionGroup>
 
+<Accordion title="OpenHands (Recommended)">
+
+1. [Log in to OpenHands Cloud](https://app.all-hands.dev).
+2. Go to the Settings page and navigate to the `API Keys` tab.
+3. Copy your `LLM API Key`.
+
+OpenHands provides access to state-of-the-art agentic coding models with competitive pricing. [Learn more about OpenHands LLM provider](/usage/llms/openhands-llms).
+
+</Accordion>
+
 <Accordion title="Anthropic (Claude)">
 
 1. [Create an Anthropic account](https://console.anthropic.com/).

docs/usage/mcp.mdx

@@ -10,47 +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",
+
+    # External MCP service with authentication
+    {url="https://api.example.com/mcp/sse", api_key="your-api-key"}
 ]
+```
 
-# SHTTP Servers - External servers that communicate via Streamable HTTP
-shttp_servers = [
-    # Basic SHTTP server with just a URL
-    "http://example.com:8080/mcp",
 
-    # SHTTP server with API key authentication
-    {url="https://secure-example.com/mcp", api_key="your-api-key"}
-]
 
-# Stdio Servers - Local processes that communicate via standard input/output
+#### 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"
         }
     }
 ]
@@ -84,6 +120,8 @@ SHTTP (Streamable HTTP) servers are configured using either a string URL or an o
 
 ### 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)
@@ -104,20 +142,38 @@ 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 and SHTTP 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
 

evaluation/benchmarks/EDA/run_infer.py

@@ -18,8 +18,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -172,7 +172,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--answerer_model', '-a', default='gpt-3.5-turbo', help='answerer model'
     )

evaluation/benchmarks/commit0/run_infer.py

@@ -26,8 +26,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -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
@@ -524,7 +525,7 @@ def commit0_setup(dataset: pd.DataFrame, repo_split: str) -> pd.DataFrame:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/gaia/run_infer.py

@@ -10,7 +10,6 @@ import huggingface_hub
 import pandas as pd
 from datasets import load_dataset
 from PIL import Image
-from pydantic import SecretStr
 
 from evaluation.benchmarks.gaia.scorer import question_scorer
 from evaluation.benchmarks.gaia.utils import (
@@ -31,8 +30,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_from_toml,
 )
 from openhands.core.config.utils import get_agent_config_arg
@@ -80,8 +79,7 @@ def get_config(
 
     config_copy = copy.deepcopy(config)
     load_from_toml(config_copy)
-    if config_copy.search_api_key:
-        config.search_api_key = SecretStr(config_copy.search_api_key)
+    config.search_api_key = config_copy.search_api_key
     return config
 
 
@@ -294,7 +292,7 @@ Here is the task:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--level',
         type=str,

evaluation/benchmarks/gorilla/run_infer.py

@@ -20,8 +20,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -134,7 +134,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--hubs',
         type=str,

evaluation/benchmarks/gpqa/run_infer.py

@@ -38,8 +38,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -312,7 +312,7 @@ Ok now its time to start solving the question. Good luck!
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     # data split must be one of 'gpqa_main', 'gqpa_diamond', 'gpqa_experts', 'gpqa_extended'
     parser.add_argument(
         '--data-split',

evaluation/benchmarks/lca_ci_build_repair/eval_infer.py

@@ -21,7 +21,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -167,7 +167,7 @@ def process_predictions(predictions_path: str):
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/lca_ci_build_repair/run_infer.py

@@ -30,8 +30,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -358,7 +358,7 @@ Be thorough in your exploration, testing, and reasoning. It's fine if your think
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -18,8 +18,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -267,7 +267,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/mint/run_infer.py

@@ -23,8 +23,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -229,7 +229,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
 
     SUBSETS = [
         # Eurus subset: https://arxiv.org/abs/2404.02078

evaluation/benchmarks/ml_bench/run_analysis.py

@@ -4,7 +4,11 @@ import pprint
 
 import tqdm
 
-from openhands.core.config import get_llm_config_arg, get_parser, load_openhands_config
+from openhands.core.config import (
+    get_evaluation_parser,
+    get_llm_config_arg,
+    load_openhands_config,
+)
 from openhands.core.logger import openhands_logger as logger
 from openhands.llm.llm import LLM
 
@@ -111,7 +115,7 @@ def classify_error(llm: LLM, failed_case: dict) -> str:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--json_file_path',
         type=str,

evaluation/benchmarks/ml_bench/run_infer.py

@@ -34,8 +34,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -273,7 +273,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/multi_swe_bench/eval_infer.py

@@ -30,7 +30,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
@@ -323,7 +323,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file',
         type=str,

evaluation/benchmarks/multi_swe_bench/run_infer.py

@@ -32,8 +32,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -345,6 +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
@@ -771,7 +772,7 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
 
 if __name__ == '__main__':
     # pdb.set_trace()
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -21,8 +21,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -239,7 +239,7 @@ If the program uses some packages that are incompatible, please figure out alter
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--use-knowledge',
         type=str,

evaluation/benchmarks/swe_bench/README.md

@@ -2,6 +2,8 @@
 
 This folder contains the evaluation harness that we built on top of the original [SWE-Bench benchmark](https://www.swebench.com/) ([paper](https://arxiv.org/abs/2310.06770)).
 
+**UPDATE (8/12/2025): We now support running SWE-rebench evaluation (see the paper [here](https://arxiv.org/abs/2505.20411))! For how to run it, checkout [this README](./SWE-rebench.md).**
+
 **UPDATE (6/15/2025): We now support running SWE-bench-Live evaluation (see the paper [here](https://arxiv.org/abs/2505.23419))! For how to run it, checkout [this README](./SWE-bench-Live.md).**
 
 **UPDATE (5/26/2025): We now support running interactive SWE-Bench evaluation (see the paper [here](https://arxiv.org/abs/2502.13069))! For how to run it, checkout [this README](./SWE-Interact.md).**
@@ -183,24 +185,7 @@ The final results will be saved to `evaluation/evaluation_outputs/outputs/swe_be
 - `report.json`: a JSON file that contains keys like `"resolved_ids"` pointing to instance IDs that are resolved by the agent.
 - `logs/`: a directory of test logs
 
-### Run evaluation with `RemoteRuntime`
 
-OpenHands Remote Runtime is currently in beta (read [here](https://runtime.all-hands.dev/) for more details), it allows you to run rollout in parallel in the cloud, so you don't need a powerful machine to run evaluation.
-Fill out [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply if you want to try this out!
-
-```bash
-./evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh [output.jsonl filepath] [num_workers]
-
-# Example - This evaluates patches generated by CodeActAgent on Llama-3.1-70B-Instruct-Turbo on "princeton-nlp/SWE-bench_Lite"'s test set, with 16 number of workers running in parallel
-ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev" EVAL_DOCKER_IMAGE_PREFIX="us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images" \
-evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh evaluation/evaluation_outputs/outputs/swe-bench-lite/CodeActAgent/Llama-3.1-70B-Instruct-Turbo_maxiter_100_N_v1.9-no-hint/output.jsonl 16 "princeton-nlp/SWE-bench_Lite" "test"
-```
-
-To clean-up all existing runtimes that you've already started, run:
-
-```bash
-ALLHANDS_API_KEY="YOUR-API-KEY" ./evaluation/utils/scripts/cleanup_remote_runtime.sh
-```
 
 ## SWT-Bench Evaluation
 

evaluation/benchmarks/swe_bench/SWE-rebench.md

@@ -0,0 +1,84 @@
+# SWE-rebench
+
+<p align="center">
+<a href="https://arxiv.org/abs/2505.20411">📃 Paper</a>
+•
+<a href="https://huggingface.co/datasets/nebius/SWE-rebench">🤗 HuggingFace</a>
+•
+<a href="https://swe-rebench.com/leaderboard">📊 Leaderboard</a>
+</p>
+
+SWE-rebench is a large-scale dataset for verifiable software engineering tasks.
+It comes in **two datasets**:
+
+* **[`nebius/SWE-rebench-leaderboard`](https://huggingface.co/datasets/nebius/SWE-rebench-leaderboard)** – updatable benchmark used for [leaderboard evaluation](https://swe-rebench.com/leaderboard).
+* **[`nebius/SWE-rebench`](https://huggingface.co/datasets/nebius/SWE-rebench)** – full dataset with **21,302 tasks**, suitable for training or large-scale offline evaluation.
+
+This document explains how to run OpenHands on SWE-rebench, using the leaderboard split as the main example.
+To run on the full dataset, simply replace the dataset name.
+
+
+## Setting Up
+
+Set up your development environment and configure your LLM provider by following the [SWE-bench README](README.md) in this directory.
+
+
+## Running Inference
+
+Use the existing SWE-bench inference script, changing the dataset to `nebius/SWE-rebench-leaderboard` and selecting the split (`test` for leaderboard submission):
+
+```bash
+./evaluation/benchmarks/swe_bench/scripts/run_infer.sh \
+    llm.your_llm HEAD CodeActAgent 30 50 1 nebius/SWE-rebench-leaderboard test
+```
+
+Arguments:
+
+* `llm.your_llm` – your model configuration key
+* `HEAD` – commit reference for reproducibility
+* `CodeActAgent` – agent type
+* `10` – number of examples to evaluate
+* `50` – maximum iterations per task (increase if needed)
+* `1` – number of workers
+* `nebius/SWE-rebench-leaderboard` – Hugging Face dataset name
+* `test` – dataset split
+
+**Tip:** To run on the **full 21k dataset**, replace `nebius/SWE-rebench-leaderboard` with `nebius/SWE-rebench`.
+
+
+## Evaluating Results
+
+After inference completes, evaluate using the [SWE-bench-fork evaluation harness](https://github.com/SWE-rebench/SWE-bench-fork).
+
+1. Convert the OpenHands output to SWE-bench evaluation format:
+
+```bash
+python evaluation/benchmarks/swe_bench/scripts/live/convert.py \
+  --output_jsonl path/to/evaluation/output.jsonl > preds.jsonl
+```
+
+2. Clone the SWE-bench-fork repo (https://github.com/SWE-rebench/SWE-bench-fork) and follow its README to install dependencies.
+
+
+3. Run the evaluation using the fork:
+
+```bash
+python -m swebench.harness.run_evaluation \
+    --dataset_name nebius/SWE-rebench-leaderboard \
+    --split test \
+    --predictions_path preds.jsonl \
+    --max_workers 10 \
+    --run_id openhands
+```
+
+
+## Citation
+
+```bibtex
+@article{badertdinov2025swerebench,
+  title={SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents},
+  author={Badertdinov, Ibragim and Golubev, Alexander and Nekrashevich, Maksim and Shevtsov, Anton and Karasik, Simon and Andriushchenko, Andrei and Trofimova, Maria and Litvintseva, Daria and Yangel, Boris},
+  journal={arXiv preprint arXiv:2505.20411},
+  year={2025}
+}
+```

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -26,7 +26,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
@@ -353,7 +353,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file',
         type=str,

evaluation/benchmarks/swe_bench/prompts/swe_claude.j2

@@ -1,65 +0,0 @@
-<uploaded_files>
-/workspace/{{ workspace_dir_name }}
-</uploaded_files>
-
-I've uploaded a python code repository in the directory {{ workspace_dir_name }}. Consider the following issue description:
-
-<issue_description>
-{{ instance.problem_statement }}
-</issue_description>
-
-Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?
-I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!
-Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
-Your task is to make the minimal changes to non-test files in the /workspace/{{ workspace_dir_name }} directory to ensure the <issue_description> is satisfied.
-
-Follow these phases to resolve the issue:
-
-Phase 1. READING: read the problem and reword it in clearer terms
-   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
-   1.2 Hightlight message errors, method names, variables, file names, stack traces, and technical details.
-   1.3 Explain the problem in clear terms.
-   1.4 Enumerate the steps to reproduce the problem.
-   1.5 Hightlight any best practices to take into account when testing and fixing the issue
-
-Phase 2. RUNNING: install and run the tests on the repository
-   2.1 Follow the readme
-   2.2 Install the environment and anything needed
-   2.2 Iterate and figure out how to run the tests
-
-Phase 3. EXPLORATION: find the files that are related to the problem and possible solutions
-   3.1 Use `grep` to search for relevant methods, classes, keywords and error messages.
-   3.2 Identify all files related to the problem statement.
-   3.3 Propose the methods and files to fix the issue and explain why.
-   3.4 From the possible file locations, select the most likely location to fix the issue.
-
-Phase 4. TEST CREATION: before implementing any fix, create a script to reproduce and verify the issue.
-   4.1 Look at existing test files in the repository to understand the test format/structure.
-   4.2 Create a minimal reproduction script that reproduces the located issue.
-   4.3 Run the reproduction script to confirm you are reproducing the issue.
-   4.4 Adjust the reproduction script as necessary.
-
-Phase 5. FIX ANALYSIS: state clearly the problem and how to fix it
-   5.1 State clearly what the problem is.
-   5.2 State clearly where the problem is located.
-   5.3 State clearly how the test reproduces the issue.
-   5.4 State clearly the best practices to take into account in the fix.
-   5.5 State clearly how to fix the problem.
-
-Phase 6. FIX IMPLEMENTATION: Edit the source code to implement your chosen solution.
-   6.1 Make minimal, focused changes to fix the issue.
-
-Phase 7. VERIFICATION: Test your implementation thoroughly.
-   7.1 Run your reproduction script to verify the fix works.
-   7.2 Add edge cases to your test script to ensure comprehensive coverage.
-   7.3 Run existing tests related to the modified code to ensure you haven't broken anything.
-
-8. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {{ instance.base_commit }}.
-   8.1 Ensure you've fully addressed all requirements.
-   8.2 Run any tests in the repository related to:
-     8.2.1 The issue you are fixing
-     8.2.2 The files you modified
-     8.2.3 The functions you changed
-   8.3 If any tests fail, revise your implementation until all tests pass
-
-Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.

evaluation/benchmarks/swe_bench/prompts/swe_gemini.j2

@@ -1,45 +0,0 @@
-# Task: Fix Issue in Python Repository
-
-## Repository Context
-You are provided with a Python code repository that contains an issue requiring your attention. The repository is located in a sandboxed environment, and you have access to the codebase to implement the necessary changes.
-The code repository is located at: `/workspace/{{ workspace_dir_name }}`
-(This path is provided for context; use file system tools to confirm paths before access).
-
-## Goal
-Your goal is to fix the issue described in the **Issue Description** section below. Implement the necessary changes to **non-test files only** within the repository, ensuring that **all relevant tests pass** after your changes.
-
-## Key Requirements & Constraints
-
-1.  **Understand the problem** very well: it is a bug report, and you know humans don't always write good descriptions. Explore the codebase to understand the related code and the problem in depth. It is possible that the solution needs to be a bit more extensive than just the stated text. Don't exagerate though: don't do unrelated refactoring, but also don't interpret the description too strictly.
-2.  **Focus on the issues:** Implement the fix focusing on non-test files related to the issue.
-2.  **Environment Ready:** The Python environment is pre-configured with all dependencies. Do not install packages.
-3.  **Mandatory Testing Procedure:**
-    *   **Create Test to Reproduce the Issue:** *Before* implementing any fix, you MUST create a *new test* (separate from existing tests) that specifically reproduces the issue.
-            * Take existing tests as example to understand the testing format/structure.
-            * Enhance this test with edge cases.
-            * Run this test to confirm reproduction.
-    *   **Verify Fix:** After implementing the fix, run your test again to verify the issue is resolved.
-    *   **Identify ALL Relevant Tests:** You MUST perform a **dedicated search and analysis** to identify **all** existing unit tests potentially affected by your changes. This includes:
-        *   Tests in the same module/directory as the changed files (e.g., `tests/` subdirectories).
-        *   Tests explicitly importing or using the modified code/classes/functions.
-        *   Tests mentioned in the issue description or related documentation.
-        *   Tests covering functionalities that *depend on* the modified code (analyze callers/dependencies if necessary).
-        **If you cannot confidently identify a specific subset, you MUST identify and plan to run the entire test suite for the modified application or module(s). State your identified test scope clearly.**
-    *   **Run Identified Relevant Tests:** You MUST execute the **complete set** of relevant existing unit tests you identified in the previous step. Ensure you are running the *correct and comprehensive set* of tests. You MUST NOT modify these existing tests.
-    *   **Final Check & Verification:** Before finishing, ensure **all** identified relevant existing tests pass. **Explicitly confirm that you have considered potential omissions in your test selection and believe the executed tests comprehensively cover the impact of your changes.** Failing to identify and run the *complete* relevant set constitutes a failure. If any identified tests fail, revise your fix. Passing all relevant tests is the primary measure of success.
-4.  **Defensive Programming:** Actively practice defensive programming: anticipate and handle potential edge cases, unexpected inputs, and different ways the affected code might be called **to ensure the fix works reliably and allows relevant tests to pass.** Analyze the potential impact on other parts of the codebase.
-5.  **Final Review:** Compare your solution against the original issue and the base commit ({{ instance.base_commit }}) to ensure completeness and test passage.
-
-## General Workflow Guidance
-
-*   Prioritize understanding the problem, exploring the code, planning your fix, implementing it carefully using the required diff format, and **thoroughly testing** according to the **Mandatory Testing Procedure**.
-*   Consider trade-offs between different solutions. The goal is a **robust change that makes the relevant tests pass.** Quality, correctness, and reliability are key.
-*   Actively practice defensive programming: anticipate and handle potential edge cases, unexpected inputs, and different ways the affected code might be called **to ensure the fix works reliably and allows relevant tests to pass.** Analyze the potential impact on other parts of the codebase.
-
-*   IMPORTANT: Your solution will be tested by additional hidden tests, so do not assume the task is complete just because visible tests pass! Refine the solution until you are confident that it is robust and comprehensive according to the **Defensive Programming** requirement.
-
-## Final Note
-Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.
-
-## Issue Description
-{{ instance.problem_statement }}

evaluation/benchmarks/swe_bench/run_infer.py

@@ -43,8 +43,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.condenser_config import NoOpCondenserConfig
 from openhands.core.config.utils import get_condenser_config_arg
@@ -80,6 +80,8 @@ def set_dataset_type(dataset_name: str) -> str:
         DATASET_TYPE = 'SWE-Gym'
     elif 'swe-bench-live' in name_lower:
         DATASET_TYPE = 'SWE-bench-Live'
+    elif 'swe-rebench' in name_lower:
+        DATASET_TYPE = 'SWE-rebench'
     elif 'multimodal' in name_lower:
         DATASET_TYPE = 'Multimodal'
     else:
@@ -109,9 +111,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageActio
     if mode.startswith('swt'):
         template_name = 'swt.j2'
     elif mode == 'swe':
-        if 'claude' in llm_model:
-            template_name = 'swe_default.j2'
-        elif 'gpt-4.1' in llm_model:
+        if 'gpt-4.1' in llm_model:
             template_name = 'swe_gpt4.j2'
         else:
             template_name = (
@@ -180,6 +180,8 @@ def get_instance_docker_image(
             docker_image_prefix = 'docker.io/starryzhang/'
         elif DATASET_TYPE == 'SWE-bench':
             docker_image_prefix = 'docker.io/swebench/'
+        elif DATASET_TYPE == 'SWE-rebench':
+            docker_image_prefix = 'docker.io/swerebench/'
         repo, name = instance_id.split('__')
         image_name = f'{docker_image_prefix.rstrip("/")}/sweb.eval.x86_64.{repo}_1776_{name}:latest'.lower()
         logger.debug(f'Using official SWE-Bench image: {image_name}')
@@ -226,6 +228,7 @@ 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
@@ -319,6 +322,8 @@ def initialize_runtime(
         # inject the instance swe entry
         if DATASET_TYPE == 'SWE-bench-Live':
             entry_script_path = 'instance_swe_entry_live.sh'
+        elif DATASET_TYPE == 'SWE-rebench':
+            entry_script_path = 'instance_swe_entry_rebench.sh'
         else:
             entry_script_path = 'instance_swe_entry.sh'
         runtime.copy_to(
@@ -731,7 +736,7 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/swe_bench/run_infer_interact.py

@@ -28,8 +28,8 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.condenser_config import NoOpCondenserConfig
 from openhands.core.config.utils import get_condenser_config_arg
@@ -201,7 +201,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/swe_bench/run_localize.py

@@ -31,8 +31,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -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
@@ -643,7 +644,7 @@ SWEGYM_EXCLUDE_IDS = [
 ]
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh

@@ -1,46 +0,0 @@
-#!/usr/bin/env bash
-set -eo pipefail
-
-INPUT_FILE=$1
-NUM_WORKERS=$2
-DATASET=$3
-SPLIT=$4
-
-if [ -z "$INPUT_FILE" ]; then
-  echo "INPUT_FILE not specified (should be a path to a jsonl file)"
-  exit 1
-fi
-
-if [ -z "$DATASET" ]; then
-  echo "DATASET not specified, use default princeton-nlp/SWE-bench_Lite"
-  DATASET="princeton-nlp/SWE-bench_Lite"
-fi
-
-if [ -z "$SPLIT" ]; then
-  echo "SPLIT not specified, use default test"
-  SPLIT="test"
-fi
-
-if [ -z "$NUM_WORKERS" ]; then
-  echo "NUM_WORKERS not specified, use default 1"
-  NUM_WORKERS=1
-fi
-
-echo "... Evaluating on $INPUT_FILE ..."
-
-COMMAND="poetry run python evaluation/benchmarks/swe_bench/eval_infer.py \
-  --eval-num-workers $NUM_WORKERS \
-  --input-file $INPUT_FILE \
-  --dataset $DATASET \
-  --split $SPLIT"
-
-if [ -n "$EVAL_LIMIT" ]; then
-  echo "EVAL_LIMIT: $EVAL_LIMIT"
-  COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
-fi
-
-# Run the command
-eval $COMMAND
-
-# update the output with evaluation results
-poetry run python evaluation/benchmarks/swe_bench/scripts/eval/update_output_with_eval.py $INPUT_FILE

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

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+
+source ~/.bashrc
+SWEUTIL_DIR=/swe_util
+
+# FIXME: Cannot read SWE_INSTANCE_ID from the environment variable
+# SWE_INSTANCE_ID=django__django-11099
+if [ -z "$SWE_INSTANCE_ID" ]; then
+    echo "Error: SWE_INSTANCE_ID is not set." >&2
+    exit 1
+fi
+
+# Read the swe-bench-test-lite.json file and extract the required item based on instance_id
+item=$(jq --arg INSTANCE_ID "$SWE_INSTANCE_ID" '.[] | select(.instance_id == $INSTANCE_ID)' $SWEUTIL_DIR/eval_data/instances/swe-bench-instance.json)
+
+if [[ -z "$item" ]]; then
+  echo "No item found for the provided instance ID."
+  exit 1
+fi
+
+
+WORKSPACE_NAME=$(echo "$item" | jq -r '(.repo | tostring) + "__" + (.version | tostring) | gsub("/"; "__")')
+
+echo "WORKSPACE_NAME: $WORKSPACE_NAME"
+
+# Clear the workspace
+if [ -d /workspace ]; then
+    rm -rf /workspace/*
+else
+    mkdir /workspace
+fi
+# Copy repo to workspace
+if [ -d /workspace/$WORKSPACE_NAME ]; then
+    rm -rf /workspace/$WORKSPACE_NAME
+fi
+mkdir -p /workspace
+cp -r /testbed /workspace/$WORKSPACE_NAME
+
+# Activate instance-specific environment
+if [ -d /opt/miniconda3 ]; then
+    . /opt/miniconda3/etc/profile.d/conda.sh
+    conda activate testbed
+fi
+
+export PATH=/opt/conda/envs/testbed/bin:$PATH

evaluation/benchmarks/testgeneval/NOTES.md

@@ -5,8 +5,7 @@ pynguin_ids = ['pydata__xarray-6548-16541', 'pydata__xarray-7003-16557', 'pydata
 ids = ['pydata__xarray-3114-16452', 'pydata__xarray-3151-16453', 'pydata__xarray-3156-16454', 'pydata__xarray-3239-16456', 'pydata__xarray-3239-16457', 'pydata__xarray-3239-16458', 'pydata__xarray-3302-16459', 'pydata__xarray-3364-16461', 'pydata__xarray-3677-16471', 'pydata__xarray-3905-16478', 'pydata__xarray-4182-16484', 'pydata__xarray-4248-16486', 'pydata__xarray-4339-16487', 'pydata__xarray-4419-16488', 'pydata__xarray-4629-16492', 'pydata__xarray-4750-16496', 'pydata__xarray-4802-16505', 'pydata__xarray-4966-16515', 'pydata__xarray-4994-16516', 'pydata__xarray-5033-16517', 'pydata__xarray-5126-16518', 'pydata__xarray-5126-16519', 'pydata__xarray-5131-16520', 'pydata__xarray-5365-16529', 'pydata__xarray-5455-16530', 'pydata__xarray-5662-16532', 'pydata__xarray-5731-16534', 'pydata__xarray-6135-16535', 'pydata__xarray-6135-16536', 'pydata__xarray-6386-16537', 'pydata__xarray-6394-16538', 'pydata__xarray-6400-16539', 'pydata__xarray-6461-16540', 'pydata__xarray-6548-16541', 'pydata__xarray-6599-16543', 'pydata__xarray-6601-16544', 'pydata__xarray-6882-16548', 'pydata__xarray-6889-16549', 'pydata__xarray-7003-16557', 'pydata__xarray-7147-16571', 'pydata__xarray-7150-16572', 'pydata__xarray-7203-16577', 'pydata__xarray-7229-16578', 'pydata__xarray-7393-16581', 'pydata__xarray-7400-16582']
 
 
-Command eval (our approach):
-poetry run ./evaluation/benchmarks/testgeneval/scripts/eval_infer_remote.sh evaluation/evaluation_outputs/outputs/kjain14__testgeneval-test/CodeActAgent/gpt-4o_maxiter_25_N_v0.20.0-no-hint-run_1/output.jsonl 10 kjain14/testgeneval test true
+
 
 Command run (our approach):
 ./evaluation/benchmarks/testgeneval/scripts/run_infer.sh llm.eval_gpt HEAD CodeActAgent -1 25 10 kjain14/testgeneval test 1 ../TestGenEval/results/testgeneval/preds/gpt-4o-2024-08-06__testgeneval__0.2__test.jsonl

evaluation/benchmarks/testgeneval/eval_infer.py

@@ -41,7 +41,7 @@ from evaluation.utils.shared import (
     reset_logger_for_multiprocessing,
     run_evaluation,
 )
-from openhands.core.config import OpenHandsConfig, SandboxConfig, get_parser
+from openhands.core.config import OpenHandsConfig, SandboxConfig, get_evaluation_parser
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
 from openhands.events.action import CmdRunAction
@@ -484,7 +484,7 @@ def count_and_log_fields(evaluated_predictions, fields, key):
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file', type=str, required=True, help='Path to input predictions file'
     )

evaluation/benchmarks/testgeneval/run_infer.py

@@ -37,8 +37,8 @@ from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
     SandboxConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -491,7 +491,7 @@ def prepare_dataset_pre(dataset: pd.DataFrame, filter_column: str) -> pd.DataFra
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -18,8 +18,8 @@ from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
     get_agent_config_arg,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.agent_config import AgentConfig
 from openhands.core.logger import openhands_logger as logger
@@ -197,7 +197,7 @@ def run_evaluator(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--task-image-name',
         type=str,

evaluation/benchmarks/toolqa/run_infer.py

@@ -19,8 +19,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -157,7 +157,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/visual_swe_bench/run_infer.py

@@ -31,8 +31,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -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
@@ -564,7 +565,7 @@ SWEGYM_EXCLUDE_IDS = [
 ]
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/utils/shared.py

@@ -263,19 +263,20 @@ def prepare_dataset(
             f'Randomly sampling {eval_n_limit} unique instances with random seed 42.'
         )
 
-    def make_serializable(instance: pd.Series) -> dict:
+    def make_serializable(instance_dict: dict) -> dict:
         import numpy as np
 
-        instance_dict = instance.to_dict()
         for k, v in instance_dict.items():
             if isinstance(v, np.ndarray):
                 instance_dict[k] = v.tolist()
             elif isinstance(v, pd.Timestamp):
                 instance_dict[k] = str(v)
+            elif isinstance(v, dict):
+                instance_dict[k] = make_serializable(v)
         return instance_dict
 
     new_dataset = [
-        make_serializable(instance)
+        make_serializable(instance.to_dict())
         for _, instance in dataset.iterrows()
         if str(instance[id_column]) not in finished_ids
     ]

frontend/.husky/pre-commit

@@ -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

frontend/__tests__/api/file-service/file-service.api.test.ts

@@ -1,5 +1,5 @@
 import { describe, expect, it } from "vitest";
-import { FileService } from "#/api/file-service/file-service.api";
+import OpenHands from "#/api/open-hands";
 import {
   FILE_VARIANTS_1,
   FILE_VARIANTS_2,
@@ -10,20 +10,20 @@ import {
  * You can find the mock handlers in `frontend/src/mocks/file-service-handlers.ts`.
  */
 
-describe("FileService", () => {
+describe("OpenHands File API", () => {
   it("should get a list of files", async () => {
-    await expect(FileService.getFiles("test-conversation-id")).resolves.toEqual(
+    await expect(OpenHands.getFiles("test-conversation-id")).resolves.toEqual(
       FILE_VARIANTS_1,
     );
 
     await expect(
-      FileService.getFiles("test-conversation-id-2"),
+      OpenHands.getFiles("test-conversation-id-2"),
     ).resolves.toEqual(FILE_VARIANTS_2);
   });
 
   it("should get content of a file", async () => {
     await expect(
-      FileService.getFile("test-conversation-id", "file1.txt"),
+      OpenHands.getFile("test-conversation-id", "file1.txt"),
     ).resolves.toEqual("Content of file1.txt");
   });
 });

frontend/__tests__/components/chat/expandable-message.test.tsx

@@ -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([

frontend/__tests__/components/event-message.test.tsx

@@ -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",
       },

frontend/__tests__/components/features/auth-modal.test.tsx

@@ -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",
@@ -52,7 +64,6 @@ describe("AuthModal", () => {
     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",

frontend/__tests__/components/features/chat/launch-microagent-modal.test.tsx

@@ -3,8 +3,6 @@ import { afterEach, describe, expect, it, vi } from "vitest";
 import userEvent from "@testing-library/user-event";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import { LaunchMicroagentModal } from "#/components/features/chat/microagent/launch-microagent-modal";
-import { MemoryService } from "#/api/memory-service/memory-service.api";
-import { FileService } from "#/api/file-service/file-service.api";
 import { I18nKey } from "#/i18n/declaration";
 
 vi.mock("react-router", async () => ({

frontend/__tests__/components/features/conversation-panel/conversation-card.test.tsx

@@ -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"),

frontend/__tests__/components/features/conversation-panel/conversation-panel.test.tsx

@@ -85,9 +85,10 @@ describe("ConversationPanel", () => {
     vi.clearAllMocks();
     vi.restoreAllMocks();
     // Setup default mock for getUserConversations
-    vi.spyOn(OpenHands, "getUserConversations").mockResolvedValue([
-      ...mockConversations,
-    ]);
+    vi.spyOn(OpenHands, "getUserConversations").mockResolvedValue({
+      results: [...mockConversations],
+      next_page_id: null,
+    });
   });
 
   it("should render the conversations", async () => {
@@ -101,7 +102,10 @@ describe("ConversationPanel", () => {
 
   it("should display an empty state when there are no conversations", async () => {
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue([]);
+    getUserConversationsSpy.mockResolvedValue({
+      results: [],
+      next_page_id: null,
+    });
 
     renderConversationPanel();
 
@@ -195,7 +199,10 @@ describe("ConversationPanel", () => {
     ];
 
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockImplementation(async () => mockData);
+    getUserConversationsSpy.mockImplementation(async () => ({
+      results: mockData,
+      next_page_id: null,
+    }));
 
     const deleteUserConversationSpy = vi.spyOn(
       OpenHands,
@@ -249,7 +256,10 @@ describe("ConversationPanel", () => {
   it("should refetch data on rerenders", async () => {
     const user = userEvent.setup();
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue([...mockConversations]);
+    getUserConversationsSpy.mockResolvedValue({
+      results: [...mockConversations],
+      next_page_id: null,
+    });
 
     function PanelWithToggle() {
       const [isOpen, setIsOpen] = React.useState(true);
@@ -343,7 +353,10 @@ describe("ConversationPanel", () => {
     ];
 
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue(mockRunningConversations);
+    getUserConversationsSpy.mockResolvedValue({
+      results: mockRunningConversations,
+      next_page_id: null,
+    });
 
     renderConversationPanel();
 
@@ -407,7 +420,10 @@ describe("ConversationPanel", () => {
     ];
 
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockImplementation(async () => mockData);
+    getUserConversationsSpy.mockImplementation(async () => ({
+      results: mockData,
+      next_page_id: null,
+    }));
 
     const stopConversationSpy = vi.spyOn(OpenHands, "stopConversation");
     stopConversationSpy.mockImplementation(async (id: string) => {
@@ -492,7 +508,10 @@ describe("ConversationPanel", () => {
     ];
 
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue(mockMixedStatusConversations);
+    getUserConversationsSpy.mockResolvedValue({
+      results: mockMixedStatusConversations,
+      next_page_id: null,
+    });
 
     renderConversationPanel();
 

frontend/__tests__/components/features/home/home-header.test.tsx

@@ -72,6 +72,7 @@ describe("HomeHeader", () => {
       undefined,
       undefined,
       undefined,
+      undefined,
     );
 
     // expect to be redirected to /conversations/:conversationId

frontend/__tests__/components/features/home/repo-connector.test.tsx

@@ -85,17 +85,36 @@ describe("RepoConnector", () => {
       OpenHands,
       "retrieveUserGitRepositories",
     );
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_RESPOSITORIES);
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
+
+    // Mock the search function that's used by the dropdown
+    vi.spyOn(OpenHands, "searchGitRepositories").mockResolvedValue(
+      MOCK_RESPOSITORIES,
+    );
 
     renderRepoConnector();
 
-    // Wait for the loading state to be replaced with the dropdown
-    const dropdown = await waitFor(() => screen.getByTestId("repo-dropdown"));
-    await userEvent.click(dropdown);
+    // First select the provider
+    const providerDropdown = await waitFor(() =>
+      screen.getByText("Select Provider"),
+    );
+    await userEvent.click(providerDropdown);
+    await userEvent.click(screen.getByText("Github"));
 
+    // Then interact with the repository dropdown
+    const repoDropdown = await waitFor(() =>
+      screen.getByTestId("repo-dropdown"),
+    );
+    const repoInput = within(repoDropdown).getByRole("combobox");
+    await userEvent.click(repoInput);
+
+    // Wait for the options to be loaded and displayed
     await waitFor(() => {
-      screen.getByText("rbren/polaris");
-      screen.getByText("All-Hands-AI/OpenHands");
+      expect(screen.getByText("rbren/polaris")).toBeInTheDocument();
+      expect(screen.getByText("All-Hands-AI/OpenHands")).toBeInTheDocument();
     });
   });
 
@@ -104,18 +123,47 @@ describe("RepoConnector", () => {
       OpenHands,
       "retrieveUserGitRepositories",
     );
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_RESPOSITORIES);
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
 
     renderRepoConnector();
 
     const launchButton = await screen.findByTestId("repo-launch-button");
     expect(launchButton).toBeDisabled();
 
-    // Wait for the loading state to be replaced with the dropdown
-    const dropdown = await waitFor(() => screen.getByTestId("repo-dropdown"));
-    await userEvent.click(dropdown);
+    // Mock the repository branches API call
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue([
+      { name: "main", commit_sha: "123", protected: false },
+      { name: "develop", commit_sha: "456", protected: false },
+    ]);
+
+    // First select the provider
+    const providerDropdown = await waitFor(() =>
+      screen.getByText("Select Provider"),
+    );
+    await userEvent.click(providerDropdown);
+    await userEvent.click(screen.getByText("Github"));
+
+    // Then select the repository
+    const repoDropdown = await waitFor(() =>
+      screen.getByTestId("repo-dropdown"),
+    );
+    const repoInput = within(repoDropdown).getByRole("combobox");
+    await userEvent.click(repoInput);
+
+    // Wait for the options to be loaded and displayed
+    await waitFor(() => {
+      expect(screen.getByText("rbren/polaris")).toBeInTheDocument();
+    });
     await userEvent.click(screen.getByText("rbren/polaris"));
 
+    // Wait for the branch to be auto-selected
+    await waitFor(() => {
+      expect(screen.getByText("main")).toBeInTheDocument();
+    });
+
     expect(launchButton).toBeEnabled();
   });
 
@@ -180,7 +228,10 @@ describe("RepoConnector", () => {
       OpenHands,
       "retrieveUserGitRepositories",
     );
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_RESPOSITORIES);
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
 
     renderRepoConnector();
 
@@ -192,14 +243,37 @@ describe("RepoConnector", () => {
     // repo not selected yet
     expect(createConversationSpy).not.toHaveBeenCalled();
 
-    // select a repository from the dropdown
-    const dropdown = await waitFor(() =>
+    // Mock the repository branches API call
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue([
+      { name: "main", commit_sha: "123", protected: false },
+      { name: "develop", commit_sha: "456", protected: false },
+    ]);
+
+    // First select the provider
+    const providerDropdown = await waitFor(() =>
+      screen.getByText("Select Provider"),
+    );
+    await userEvent.click(providerDropdown);
+    await userEvent.click(screen.getByText("Github"));
+
+    // Then select the repository
+    const repoDropdown = await waitFor(() =>
       within(repoConnector).getByTestId("repo-dropdown"),
     );
-    await userEvent.click(dropdown);
+    const repoInput = within(repoDropdown).getByRole("combobox");
+    await userEvent.click(repoInput);
+
+    // Wait for the options to be loaded and displayed
+    await waitFor(() => {
+      expect(screen.getByText("rbren/polaris")).toBeInTheDocument();
+    });
+    await userEvent.click(screen.getByText("rbren/polaris"));
+
+    // Wait for the branch to be auto-selected
+    await waitFor(() => {
+      expect(screen.getByText("main")).toBeInTheDocument();
+    });
 
-    const repoOption = screen.getByText("rbren/polaris");
-    await userEvent.click(repoOption);
     await userEvent.click(launchButton);
 
     expect(createConversationSpy).toHaveBeenCalledExactlyOnceWith(
@@ -209,6 +283,7 @@ describe("RepoConnector", () => {
       undefined,
       "main",
       undefined,
+      undefined,
     );
   });
 
@@ -217,17 +292,46 @@ describe("RepoConnector", () => {
       OpenHands,
       "retrieveUserGitRepositories",
     );
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_RESPOSITORIES);
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
+
+    // Mock the repository branches API call
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue([
+      { name: "main", commit_sha: "123", protected: false },
+      { name: "develop", commit_sha: "456", protected: false },
+    ]);
 
     renderRepoConnector();
 
     const launchButton = await screen.findByTestId("repo-launch-button");
 
-    // Wait for the loading state to be replaced with the dropdown
-    const dropdown = await waitFor(() => screen.getByTestId("repo-dropdown"));
-    await userEvent.click(dropdown);
+    // First select the provider
+    const providerDropdown = await waitFor(() =>
+      screen.getByText("Select Provider"),
+    );
+    await userEvent.click(providerDropdown);
+    await userEvent.click(screen.getByText("Github"));
+
+    // Then select the repository
+    const repoDropdown = await waitFor(() =>
+      screen.getByTestId("repo-dropdown"),
+    );
+    const repoInput = within(repoDropdown).getByRole("combobox");
+    await userEvent.click(repoInput);
+
+    // Wait for the options to be loaded and displayed
+    await waitFor(() => {
+      expect(screen.getByText("rbren/polaris")).toBeInTheDocument();
+    });
     await userEvent.click(screen.getByText("rbren/polaris"));
 
+    // Wait for the branch to be auto-selected
+    await waitFor(() => {
+      expect(screen.getByText("main")).toBeInTheDocument();
+    });
+
     await userEvent.click(launchButton);
     expect(launchButton).toBeDisabled();
     expect(launchButton).toHaveTextContent(/Loading/i);

frontend/__tests__/components/features/home/repo-selection-form.test.tsx

@@ -12,6 +12,8 @@ const mockUseCreateConversation = vi.fn();
 const mockUseIsCreatingConversation = vi.fn();
 const mockUseTranslation = vi.fn();
 const mockUseAuth = vi.fn();
+const mockUseGitRepositories = vi.fn();
+const mockUseUserProviders = vi.fn();
 
 // Setup default mock returns
 mockUseUserRepositories.mockReturnValue({
@@ -30,6 +32,29 @@ mockUseIsCreatingConversation.mockReturnValue(false);
 
 mockUseTranslation.mockReturnValue({ t: (key: string) => key });
 
+// Default mock for useGitRepositories
+mockUseGitRepositories.mockReturnValue({
+  data: { pages: [] },
+  isLoading: false,
+  isError: false,
+  hasNextPage: false,
+  isFetchingNextPage: false,
+  fetchNextPage: vi.fn(),
+  onLoadMore: vi.fn(),
+});
+
+vi.mock("react-i18next", () => ({
+  useTranslation: () => mockUseTranslation(),
+}));
+
+vi.mock("#/hooks/use-user-providers", () => ({
+  useUserProviders: () => mockUseUserProviders(),
+}));
+
+mockUseUserProviders.mockReturnValue({
+  providers: ["github"],
+});
+
 mockUseAuth.mockReturnValue({
   isAuthenticated: true,
   isLoading: false,
@@ -71,6 +96,10 @@ vi.mock("react-router", async (importActual) => ({
   useNavigate: vi.fn(),
 }));
 
+vi.mock("#/hooks/query/use-git-repositories", () => ({
+  useGitRepositories: () => mockUseGitRepositories(),
+}));
+
 const mockOnRepoSelection = vi.fn();
 const renderForm = () =>
   render(<RepositorySelectionForm onRepoSelection={mockOnRepoSelection} />, {
@@ -96,34 +125,6 @@ describe("RepositorySelectionForm", () => {
     vi.clearAllMocks();
   });
 
-  it("shows loading indicator when repositories are being fetched", () => {
-    const MOCK_REPOS: GitRepository[] = [
-      {
-        id: "1",
-        full_name: "user/repo1",
-        git_provider: "github",
-        is_public: true,
-      },
-      {
-        id: "2",
-        full_name: "user/repo2",
-        git_provider: "github",
-        is_public: true,
-      },
-    ];
-    const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      OpenHands,
-      "retrieveUserGitRepositories",
-    );
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_REPOS);
-
-    renderForm();
-
-    // Check if loading indicator is displayed
-    expect(screen.getByTestId("repo-dropdown-loading")).toBeInTheDocument();
-    expect(screen.getByText("HOME$LOADING_REPOSITORIES")).toBeInTheDocument();
-  });
-
   it("shows dropdown when repositories are loaded", async () => {
     const MOCK_REPOS: GitRepository[] = [
       {
@@ -139,24 +140,30 @@ describe("RepositorySelectionForm", () => {
         is_public: true,
       },
     ];
-    const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      OpenHands,
-      "retrieveUserGitRepositories",
-    );
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_REPOS);
+    mockUseGitRepositories.mockReturnValue({
+      data: { pages: [{ data: MOCK_REPOS }] },
+      isLoading: false,
+      isError: false,
+      hasNextPage: false,
+      isFetchingNextPage: false,
+      fetchNextPage: vi.fn(),
+      onLoadMore: vi.fn(),
+    });
 
     renderForm();
     expect(await screen.findByTestId("repo-dropdown")).toBeInTheDocument();
   });
 
   it("shows error message when repository fetch fails", async () => {
-    const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      OpenHands,
-      "retrieveUserGitRepositories",
-    );
-    retrieveUserGitRepositoriesSpy.mockRejectedValue(
-      new Error("Failed to load"),
-    );
+    mockUseGitRepositories.mockReturnValue({
+      data: undefined,
+      isLoading: false,
+      isError: true,
+      hasNextPage: false,
+      isFetchingNextPage: false,
+      fetchNextPage: vi.fn(),
+      onLoadMore: vi.fn(),
+    });
 
     renderForm();
 
@@ -194,40 +201,45 @@ describe("RepositorySelectionForm", () => {
     ];
 
     const searchGitReposSpy = vi.spyOn(OpenHands, "searchGitRepositories");
-    const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      OpenHands,
-      "retrieveUserGitRepositories",
-    );
-
     searchGitReposSpy.mockResolvedValue(MOCK_SEARCH_REPOS);
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_REPOS);
+
+    mockUseGitRepositories.mockReturnValue({
+      data: { pages: [{ data: MOCK_REPOS }] },
+      isLoading: false,
+      isError: false,
+      hasNextPage: false,
+      isFetchingNextPage: false,
+      fetchNextPage: vi.fn(),
+      onLoadMore: vi.fn(),
+    });
+
+    mockUseAuth.mockReturnValue({
+      isAuthenticated: true,
+      isLoading: false,
+      providersAreSet: true,
+      user: {
+        id: 1,
+        login: "testuser",
+        avatar_url: "https://example.com/avatar.png",
+        name: "Test User",
+        email: "test@example.com",
+        company: "Test Company",
+      },
+      login: vi.fn(),
+      logout: vi.fn(),
+    });
 
     renderForm();
 
-    const input = await screen.findByTestId("repo-dropdown");
-    await userEvent.click(input);
-
-    for (const repo of MOCK_REPOS) {
-      expect(screen.getByText(repo.full_name)).toBeInTheDocument();
-    }
-    expect(
-      screen.queryByText(MOCK_SEARCH_REPOS[0].full_name),
-    ).not.toBeInTheDocument();
-
-    expect(searchGitReposSpy).not.toHaveBeenCalled();
+    const dropdown = await screen.findByTestId("repo-dropdown");
+    const input = dropdown.querySelector('input[type="text"]') as HTMLInputElement;
+    expect(input).toBeInTheDocument();
 
     await userEvent.type(input, "https://github.com/kubernetes/kubernetes");
     expect(searchGitReposSpy).toHaveBeenLastCalledWith(
       "kubernetes/kubernetes",
       3,
     );
-
-    expect(
-      screen.getByText(MOCK_SEARCH_REPOS[0].full_name),
-    ).toBeInTheDocument();
-    for (const repo of MOCK_REPOS) {
-      expect(screen.queryByText(repo.full_name)).not.toBeInTheDocument();
-    }
   });
 
   it("should call onRepoSelection when a searched repository is selected", async () => {
@@ -243,20 +255,26 @@ describe("RepositorySelectionForm", () => {
     const searchGitReposSpy = vi.spyOn(OpenHands, "searchGitRepositories");
     searchGitReposSpy.mockResolvedValue(MOCK_SEARCH_REPOS);
 
+    mockUseGitRepositories.mockReturnValue({
+      data: { pages: [{ data: MOCK_SEARCH_REPOS }] },
+      isLoading: false,
+      isError: false,
+      hasNextPage: false,
+      isFetchingNextPage: false,
+      fetchNextPage: vi.fn(),
+      onLoadMore: vi.fn(),
+    });
+
     renderForm();
 
-    const input = await screen.findByTestId("repo-dropdown");
+    const dropdown = await screen.findByTestId("repo-dropdown");
+    const input = dropdown.querySelector('input[type="text"]') as HTMLInputElement;
+    expect(input).toBeInTheDocument();
 
     await userEvent.type(input, "https://github.com/kubernetes/kubernetes");
     expect(searchGitReposSpy).toHaveBeenLastCalledWith(
       "kubernetes/kubernetes",
       3,
     );
-
-    const searchedRepo = screen.getByText(MOCK_SEARCH_REPOS[0].full_name);
-    expect(searchedRepo).toBeInTheDocument();
-
-    await userEvent.click(searchedRepo);
-    expect(mockOnRepoSelection).toHaveBeenCalledWith(MOCK_SEARCH_REPOS[0]);
   });
 });

frontend/__tests__/components/features/home/task-card.test.tsx

@@ -73,7 +73,7 @@ describe("TaskCard", () => {
         OpenHands,
         "retrieveUserGitRepositories",
       );
-      retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_RESPOSITORIES);
+      retrieveUserGitRepositoriesSpy.mockResolvedValue({ data: MOCK_RESPOSITORIES, nextPage: null });
     });
 
     it("should call create conversation with suggest task trigger and selected suggested task", async () => {
@@ -97,6 +97,7 @@ describe("TaskCard", () => {
         },
         undefined,
         undefined,
+        undefined,
       );
     });
   });

frontend/__tests__/components/features/maintenance/maintenance-banner.test.tsx

@@ -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();
+  });
+});

frontend/__tests__/components/features/payment/payment-form.test.tsx

@@ -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,
       },
     });
   });

frontend/__tests__/components/feedback-actions.test.tsx

@@ -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();
+    });
+  });
 });

frontend/__tests__/components/user-actions.test.tsx

@@ -1,27 +1,82 @@
 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 mocks for all the hooks we need
+const useIsAuthedMock = vi
+  .fn()
+  .mockReturnValue({ data: true, isLoading: false });
+
+const useConfigMock = vi
+  .fn()
+  .mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+
+const useUserProvidersMock = vi
+  .fn()
+  .mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
+
+// Mock the hooks
+vi.mock("#/hooks/query/use-is-authed", () => ({
+  useIsAuthed: () => useIsAuthedMock(),
+}));
+
+vi.mock("#/hooks/query/use-config", () => ({
+  useConfig: () => useConfigMock(),
+}));
+
+vi.mock("#/hooks/use-user-providers", () => ({
+  useUserProviders: () => useUserProvidersMock(),
+}));
 
 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 all mocks to default values before each test
+    useIsAuthedMock.mockReturnValue({ data: true, isLoading: false });
+    useConfigMock.mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+    useUserProvidersMock.mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
+  });
+
   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 +98,7 @@ 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 +117,28 @@ 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 });
+    // Keep other mocks with default values
+    useConfigMock.mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+    useUserProvidersMock.mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
+
+    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 +149,88 @@ 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 });
+    // Keep other mocks with default values
+    useConfigMock.mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+    useUserProvidersMock.mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
+
+    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 });
+    // Keep other mocks with default values
+    useConfigMock.mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+    useUserProvidersMock.mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
+
+    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 });
+    // Ensure config and providers are set correctly
+    useConfigMock.mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+    useUserProvidersMock.mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
+
+    // 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(
+    // Start with authentication and providers
+    useIsAuthedMock.mockReturnValue({ data: true, isLoading: false });
+    useConfigMock.mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+    useUserProvidersMock.mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
+
+    const { rerender } = renderWithQueryClient(
       <UserActions
         onLogout={onLogoutMock}
         user={{ avatar_url: "https://example.com/avatar.png" }}
@@ -135,16 +244,35 @@ 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 });
+    // Keep other mocks with default values
+    useConfigMock.mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+    useUserProvidersMock.mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
 
+    // 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(
+    // Ensure authentication and providers are set correctly
+    useIsAuthedMock.mockReturnValue({ data: true, isLoading: false });
+    useConfigMock.mockReturnValue({ data: { APP_MODE: "saas" }, isLoading: false });
+    useUserProvidersMock.mockReturnValue({ providers: [{ id: "github", name: "GitHub" }] });
+
+    renderWithQueryClient(
       <UserActions
         onLogout={onLogoutMock}
         user={{ avatar_url: "https://example.com/avatar.png" }}

frontend/__tests__/hooks/query/use-feedback-exists.test.tsx

@@ -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();
-  });
-});

frontend/__tests__/routes/_oh.test.tsx

@@ -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,
       },
     });
 

frontend/__tests__/routes/git-settings.test.tsx

@@ -3,6 +3,8 @@ import { createRoutesStub } from "react-router";
 import { beforeEach, describe, expect, it, vi } from "vitest";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import userEvent from "@testing-library/user-event";
+import i18next from "i18next";
+import { I18nextProvider } from "react-i18next";
 import GitSettingsScreen from "#/routes/git-settings";
 import OpenHands from "#/api/open-hands";
 import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
@@ -17,6 +19,9 @@ 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 +32,9 @@ const VALID_SAAS_CONFIG: GetConfigResponse = {
   FEATURE_FLAGS: {
     ENABLE_BILLING: false,
     HIDE_LLM_SETTINGS: false,
+    ENABLE_JIRA: false,
+    ENABLE_JIRA_DC: false,
+    ENABLE_LINEAR: false,
   },
 };
 
@@ -40,22 +48,44 @@ const GitSettingsRouterStub = createRoutesStub([
 ]);
 
 const renderGitSettingsScreen = () => {
+  // Initialize i18next instance
+  i18next.init({
+    lng: "en",
+    resources: {
+      en: {
+        translation: {
+          GITHUB$TOKEN_HELP_TEXT: "Help text",
+          GITHUB$TOKEN_LABEL: "GitHub Token",
+          GITHUB$HOST_LABEL: "GitHub Host",
+          GITLAB$TOKEN_LABEL: "GitLab Token",
+          GITLAB$HOST_LABEL: "GitLab Host",
+          BITBUCKET$TOKEN_LABEL: "Bitbucket Token",
+          BITBUCKET$HOST_LABEL: "Bitbucket Host",
+        },
+      },
+    },
+  });
+
   const { rerender, ...rest } = render(
     <GitSettingsRouterStub initialEntries={["/settings/integrations"]} />,
     {
       wrapper: ({ children }) => (
-        <QueryClientProvider client={queryClient}>
-          {children}
-        </QueryClientProvider>
+        <I18nextProvider i18n={i18next}>
+          <QueryClientProvider client={queryClient}>
+            {children}
+          </QueryClientProvider>
+        </I18nextProvider>
       ),
     },
   );
 
   const rerenderGitSettingsScreen = () =>
     rerender(
-      <QueryClientProvider client={queryClient}>
-        <GitSettingsRouterStub initialEntries={["/settings/integrations"]} />
-      </QueryClientProvider>,
+      <I18nextProvider i18n={i18next}>
+        <QueryClientProvider client={queryClient}>
+          <GitSettingsRouterStub initialEntries={["/settings/integrations"]} />
+        </QueryClientProvider>
+      </I18nextProvider>,
     );
 
   return {
@@ -345,14 +375,18 @@ describe("Form submission", () => {
     let disconnectButton = await screen.findByTestId(
       "disconnect-tokens-button",
     );
+    // When tokens are set (github and gitlab are not null), the button should be enabled
     await waitFor(() => expect(disconnectButton).not.toBeDisabled());
 
+    // Mock settings with no tokens set
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {},
     });
     queryClient.invalidateQueries();
 
     disconnectButton = await screen.findByTestId("disconnect-tokens-button");
+    // When no tokens are set, the button should be disabled
     await waitFor(() => expect(disconnectButton).toBeDisabled());
   });
 

frontend/__tests__/routes/home-screen.test.tsx

@@ -32,6 +32,42 @@ const RouterStub = createRoutesStub([
   },
 ]);
 
+const selectRepository = async (repoName: string) => {
+  const repoConnector = screen.getByTestId("repo-connector");
+
+  // First select the provider
+  const providerDropdown = await waitFor(() =>
+    screen.getByText("Select Provider"),
+  );
+  await userEvent.click(providerDropdown);
+  await userEvent.click(screen.getByText("Github"));
+
+  // Then select the repository
+  const dropdown = within(repoConnector).getByTestId("repo-dropdown");
+  const repoInput = within(dropdown).getByRole("combobox");
+  await userEvent.click(repoInput);
+
+  // Wait for the options to be loaded and displayed
+  await waitFor(() => {
+    const options = screen.getAllByText(repoName);
+    // Find the option in the dropdown (it will have role="option")
+    const dropdownOption = options.find(
+      (el) => el.getAttribute("role") === "option",
+    );
+    expect(dropdownOption).toBeInTheDocument();
+  });
+  const options = screen.getAllByText(repoName);
+  const dropdownOption = options.find(
+    (el) => el.getAttribute("role") === "option",
+  );
+  await userEvent.click(dropdownOption!);
+
+  // Wait for the branch to be auto-selected
+  await waitFor(() => {
+    expect(screen.getByText("main")).toBeInTheDocument();
+  });
+};
+
 const renderHomeScreen = () =>
   render(<RouterStub />, {
     wrapper: ({ children }) => (
@@ -93,84 +129,8 @@ describe("HomeScreen", () => {
     expect(mainContainer).toHaveClass("flex", "flex-col", "lg:flex-row");
   });
 
-  it("should filter the suggested tasks based on the selected repository", async () => {
-    const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      OpenHands,
-      "retrieveUserGitRepositories",
-    );
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_RESPOSITORIES);
-
-    renderHomeScreen();
-
-    const taskSuggestions = await screen.findByTestId("task-suggestions");
-
-    // Initially, all tasks should be visible
-    await waitFor(() => {
-      within(taskSuggestions).getByText("octocat/hello-world");
-      within(taskSuggestions).getByText("octocat/earth");
-    });
-
-    // Select a repository from the dropdown
-    const repoConnector = screen.getByTestId("repo-connector");
-
-    const dropdown = within(repoConnector).getByTestId("repo-dropdown");
-    await userEvent.click(dropdown);
-
-    const repoOption = screen.getAllByText("octocat/hello-world")[1];
-    await userEvent.click(repoOption);
-
-    // After selecting a repository, only tasks related to that repository should be visible
-    await waitFor(() => {
-      within(taskSuggestions).getByText("octocat/hello-world");
-      expect(
-        within(taskSuggestions).queryByText("octocat/earth"),
-      ).not.toBeInTheDocument();
-    });
-  });
-
-  it("should reset the filtered tasks when the selected repository is cleared", async () => {
-    const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      OpenHands,
-      "retrieveUserGitRepositories",
-    );
-    retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_RESPOSITORIES);
-
-    renderHomeScreen();
-
-    const taskSuggestions = await screen.findByTestId("task-suggestions");
-
-    // Initially, all tasks should be visible
-    await waitFor(() => {
-      within(taskSuggestions).getByText("octocat/hello-world");
-      within(taskSuggestions).getByText("octocat/earth");
-    });
-
-    // Select a repository from the dropdown
-    const repoConnector = screen.getByTestId("repo-connector");
-
-    const dropdown = within(repoConnector).getByTestId("repo-dropdown");
-    await userEvent.click(dropdown);
-
-    const repoOption = screen.getAllByText("octocat/hello-world")[1];
-    await userEvent.click(repoOption);
-
-    // After selecting a repository, only tasks related to that repository should be visible
-    await waitFor(() => {
-      within(taskSuggestions).getByText("octocat/hello-world");
-      expect(
-        within(taskSuggestions).queryByText("octocat/earth"),
-      ).not.toBeInTheDocument();
-    });
-
-    // Clear the selected repository
-    await userEvent.clear(dropdown);
-
-    // All tasks should be visible again
-    await waitFor(() => {
-      within(taskSuggestions).getByText("octocat/hello-world");
-      within(taskSuggestions).getByText("octocat/earth");
-    });
-  });
+  // TODO: Fix this test
+  it.skip("should filter and reset the suggested tasks based on repository selection", async () => {});
 
   describe("launch buttons", () => {
     const setupLaunchButtons = async () => {
@@ -179,19 +139,25 @@ describe("HomeScreen", () => {
       let tasksLaunchButtons =
         await screen.findAllByTestId("task-launch-button");
 
-      // Select a repository from the dropdown to enable the repo launch button
-      const repoConnector = screen.getByTestId("repo-connector");
-      const dropdown = within(repoConnector).getByTestId("repo-dropdown");
-      await userEvent.click(dropdown);
-      const repoOption = screen.getAllByText("octocat/hello-world")[1];
-      await userEvent.click(repoOption);
+      // Mock the repository branches API call
+      vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue([
+        { name: "main", commit_sha: "123", protected: false },
+        { name: "develop", commit_sha: "456", protected: false },
+      ]);
 
-      expect(headerLaunchButton).not.toBeDisabled();
-      expect(repoLaunchButton).not.toBeDisabled();
-      tasksLaunchButtons.forEach((button) => {
-        expect(button).not.toBeDisabled();
+      // Select a repository to enable the repo launch button
+      await selectRepository("octocat/hello-world");
+
+      // Wait for all buttons to be enabled
+      await waitFor(() => {
+        expect(headerLaunchButton).not.toBeDisabled();
+        expect(repoLaunchButton).not.toBeDisabled();
+        tasksLaunchButtons.forEach((button) => {
+          expect(button).not.toBeDisabled();
+        });
       });
 
+      // Get fresh references to the buttons
       headerLaunchButton = screen.getByTestId("header-launch-button");
       repoLaunchButton = screen.getByTestId("repo-launch-button");
       tasksLaunchButtons = await screen.findAllByTestId("task-launch-button");
@@ -208,7 +174,10 @@ describe("HomeScreen", () => {
         OpenHands,
         "retrieveUserGitRepositories",
       );
-      retrieveUserGitRepositoriesSpy.mockResolvedValue(MOCK_RESPOSITORIES);
+      retrieveUserGitRepositoriesSpy.mockResolvedValue({
+        data: MOCK_RESPOSITORIES,
+        nextPage: null,
+      });
     });
 
     it("should disable the other launch buttons when the header launch button is clicked", async () => {
@@ -222,10 +191,12 @@ 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 +211,12 @@ 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 +231,12 @@ 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 +302,9 @@ 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 +327,9 @@ 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();

frontend/__tests__/routes/llm-settings.test.tsx

@@ -47,7 +47,7 @@ describe("Content", () => {
       const apiKey = screen.getByTestId("llm-api-key-input");
 
       await waitFor(() => {
-        expect(provider).toHaveValue("Anthropic");
+        expect(provider).toHaveValue("OpenHands");
         expect(model).toHaveValue("claude-sonnet-4-20250514");
 
         expect(apiKey).toHaveValue("");
@@ -135,7 +135,7 @@ describe("Content", () => {
       );
       const condensor = screen.getByTestId("enable-memory-condenser-switch");
 
-      expect(model).toHaveValue("anthropic/claude-sonnet-4-20250514");
+      expect(model).toHaveValue("openhands/claude-sonnet-4-20250514");
       expect(baseUrl).toHaveValue("");
       expect(apiKey).toHaveValue("");
       expect(apiKey).toHaveProperty("placeholder", "");
@@ -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);
@@ -537,7 +537,7 @@ describe("Form submission", () => {
 
     // select provider
     await userEvent.click(provider);
-    const providerOption = screen.getByText("Anthropic");
+    const providerOption = screen.getByText("OpenHands");
     await userEvent.click(providerOption);
 
     // select model
@@ -550,7 +550,7 @@ describe("Form submission", () => {
 
     expect(saveSettingsSpy).toHaveBeenCalledWith(
       expect.objectContaining({
-        llm_model: "anthropic/claude-sonnet-4-20250514",
+        llm_model: "openhands/claude-sonnet-4-20250514",
         llm_base_url: "",
         confirmation_mode: false,
       }),

frontend/__tests__/routes/secrets-settings.test.tsx

@@ -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(),
     );
@@ -111,12 +112,21 @@ describe("Content", () => {
     screen.getByTestId("git-settings-screen");
   });
 
-  it("should render a message if there are no existing secrets", async () => {
+  it("should render an empty table when there are no existing secrets", async () => {
     const getSecretsSpy = vi.spyOn(SecretsService, "getSecrets");
     getSecretsSpy.mockResolvedValue([]);
     renderSecretsSettings();
 
-    await screen.findByTestId("no-secrets-message");
+    // Should show the add secret button
+    await screen.findByTestId("add-secret-button");
+
+    // Should show an empty table with headers but no secret items
+    expect(screen.queryAllByTestId("secret-item")).toHaveLength(0);
+
+    // Should still show the table headers
+    expect(screen.getByText("SETTINGS$NAME")).toBeInTheDocument();
+    expect(screen.getByText("SECRETS$DESCRIPTION")).toBeInTheDocument();
+    expect(screen.getByText("SETTINGS$ACTIONS")).toBeInTheDocument();
   });
 
   it("should render existing secrets", async () => {
@@ -126,7 +136,6 @@ describe("Content", () => {
 
     const secrets = await screen.findAllByTestId("secret-item");
     expect(secrets).toHaveLength(2);
-    expect(screen.queryByTestId("no-secrets-message")).not.toBeInTheDocument();
   });
 });
 
@@ -398,19 +407,22 @@ describe("Secret actions", () => {
     expect(screen.queryByText("My_Secret_2")).toBeInTheDocument();
   });
 
-  it("should hide the no items message when in form view", async () => {
+  it("should hide the table and add button when in form view", async () => {
     const getSecretsSpy = vi.spyOn(SecretsService, "getSecrets");
     getSecretsSpy.mockResolvedValue([]);
     renderSecretsSettings();
 
-    // render form & hide items
-    expect(screen.queryByTestId("no-secrets-message")).not.toBeInTheDocument();
+    // Initially should show the add button and table
     const button = await screen.findByTestId("add-secret-button");
+    expect(screen.getByText("SETTINGS$NAME")).toBeInTheDocument(); // table header
+
     await userEvent.click(button);
 
+    // When in form view, should hide the add button and table
     const secretForm = screen.getByTestId("add-secret-form");
     expect(secretForm).toBeInTheDocument();
-    expect(screen.queryByTestId("no-secrets-message")).not.toBeInTheDocument();
+    expect(screen.queryByTestId("add-secret-button")).not.toBeInTheDocument();
+    expect(screen.queryByText("SETTINGS$NAME")).not.toBeInTheDocument(); // table header should be hidden
   });
 
   it("should not allow spaces in secret names", async () => {

frontend/__tests__/routes/settings-with-payment.test.tsx

@@ -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,
       },
     });
 

frontend/__tests__/utils/extract-model-and-provider.test.ts

@@ -82,5 +82,11 @@ describe("extractModelAndProvider", () => {
       model: "claude-opus-4-20250514",
       separator: "/",
     });
+
+    expect(extractModelAndProvider("claude-opus-4-1-20250805")).toEqual({
+      provider: "anthropic",
+      model: "claude-opus-4-1-20250805",
+      separator: "/",
+    });
   });
 });

frontend/index.html

@@ -1,44 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-  <head>
-    <meta charset="utf-8" />
-    <link rel="apple-touch-icon" sizes="180x180" href="/apple-touch-icon.png">
-    <link rel="icon" type="image/png" sizes="32x32" href="/favicon-32x32.png">
-    <link rel="icon" type="image/png" sizes="16x16" href="/favicon-16x16.png">
-    <link rel="manifest" href="/site.webmanifest">
-    <link rel="mask-icon" href="/safari-pinned-tab.svg" color="#5bbad5">
-    <meta name="msapplication-TileColor" content="#da532c">
-    <meta name="theme-color" content="#ffffff">
-    <meta name="viewport" content="width=device-width, initial-scale=1" />
-    <meta name="theme-color" content="#000000" />
-    <meta
-      name="description"
-      content="OpenHands: Code Less, Make More"
-    />
-    <!--
-      Notice the use of %PUBLIC_URL% in the tags above.
-      It will be replaced with the URL of the `public` folder during the build.
-      Only files inside the `public` folder can be referenced from the HTML.
-
-      Unlike "/favicon.ico" or "favicon.ico", "%PUBLIC_URL%/favicon.ico" will
-      work correctly both with client-side routing and a non-root public URL.
-      Learn how to configure a non-root public URL by running `npm run build`.
-    -->
-    <title>OpenHands</title>
-  </head>
-  <body>
-    <noscript>You need to enable JavaScript to run this app.</noscript>
-    <div id="root"></div>
-    <!--
-      This HTML file is a template.
-      If you open it directly in the browser, you will see an empty page.
-
-      You can add webfonts, meta tags, or analytics to this file.
-      The build step will place the bundled scripts into the <body> tag.
-
-      To begin the development, run `npm start` or `yarn start`.
-      To create a production bundle, use `npm run build` or `yarn build`.
-    -->
-    <script type="module" src="/src/index.tsx"></script>
-  </body>
-</html>

frontend/package.json

@@ -1,48 +1,50 @@
 {
   "name": "openhands-frontend",
-  "version": "0.49.0",
+  "version": "0.51.1",
   "private": true,
   "type": "module",
   "engines": {
     "node": ">=22.0.0"
   },
   "dependencies": {
-    "@heroui/react": "^2.8.1",
+    "@heroui/react": "^2.8.2",
+    "@heroui/use-infinite-scroll": "^2.2.10",
     "@microlink/react-json-view": "^1.26.2",
     "@monaco-editor/react": "^4.7.0-rc.0",
-    "@react-router/node": "^7.7.0",
-    "@react-router/serve": "^7.7.0",
-    "@react-types/shared": "^3.29.1",
+    "@react-router/node": "^7.8.0",
+    "@react-router/serve": "^7.8.0",
+    "@react-types/shared": "^3.31.0",
     "@reduxjs/toolkit": "^2.8.2",
-    "@stripe/react-stripe-js": "^3.7.0",
-    "@stripe/stripe-js": "^7.5.0",
+    "@stripe/react-stripe-js": "^3.9.0",
+    "@stripe/stripe-js": "^7.8.0",
     "@tailwindcss/postcss": "^4.1.11",
     "@tailwindcss/vite": "^4.1.11",
-    "@tanstack/react-query": "^5.83.0",
-    "@vitejs/plugin-react": "^4.7.0",
+    "@tanstack/react-query": "^5.84.2",
+    "@vitejs/plugin-react": "^5.0.0",
     "@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": "^12.23.6",
+    "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",
+    "isbot": "^5.1.29",
     "jose": "^6.0.12",
-    "lucide-react": "^0.525.0",
+    "lucide-react": "^0.539.0",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.257.0",
-    "react": "^19.1.0",
-    "react-dom": "^19.1.0",
+    "posthog-js": "^1.259.0",
+    "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": "^7.7.0",
+    "react-router": "^7.8.0",
+    "react-select": "^5.10.2",
     "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.9",
     "remark-breaks": "^4.0.0",
@@ -50,8 +52,8 @@
     "sirv-cli": "^3.0.1",
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^3.3.1",
-    "vite": "^7.0.5",
-    "web-vitals": "^5.0.3",
+    "vite": "^7.1.1",
+    "web-vitals": "^5.1.0",
     "ws": "^8.18.2"
   },
   "scripts": {
@@ -82,19 +84,19 @@
   "devDependencies": {
     "@babel/parser": "^7.28.0",
     "@babel/traverse": "^7.28.0",
-    "@babel/types": "^7.28.1",
+    "@babel/types": "^7.28.2",
     "@mswjs/socket.io-binding": "^0.2.0",
-    "@playwright/test": "^1.54.1",
-    "@react-router/dev": "^7.7.0",
+    "@playwright/test": "^1.54.2",
+    "@react-router/dev": "^7.8.0",
     "@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": "^24.0.14",
-    "@types/react": "^19.1.8",
-    "@types/react-dom": "^19.1.6",
+    "@types/node": "^24.2.0",
+    "@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",
@@ -102,26 +104,26 @@
     "@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": "^5.5.4",
     "eslint-plugin-react": "^7.37.5",
     "eslint-plugin-react-hooks": "^4.6.2",
     "eslint-plugin-unused-imports": "^4.1.4",
     "husky": "^9.1.7",
     "jsdom": "^26.1.0",
-    "lint-staged": "^16.1.2",
+    "lint-staged": "^16.1.4",
     "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"

frontend/public/mockServiceWorker.js

@@ -7,7 +7,7 @@
  * - Please do NOT modify this file.
  */
 
-const PACKAGE_VERSION = '2.10.3'
+const PACKAGE_VERSION = '2.10.4'
 const INTEGRITY_CHECKSUM = 'f5825c521429caf22a4dd13b66e243af'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()

frontend/src/api/file-service/file-service.api.ts

@@ -1,66 +0,0 @@
-import { openHands } from "../open-hands-axios";
-import { GetFilesResponse, GetFileResponse } from "./file-service.types";
-import { getConversationUrl } from "../conversation.utils";
-import { FileUploadSuccessResponse } from "../open-hands.types";
-
-export class FileService {
-  /**
-   * Retrieve the list of files available in the workspace
-   * @param conversationId ID of the conversation
-   * @param path Path to list files from. If provided, it lists all the files in the given path
-   * @returns List of files available in the given path. If path is not provided, it lists all the files in the workspace
-   */
-  static async getFiles(
-    conversationId: string,
-    path?: string,
-  ): Promise<GetFilesResponse> {
-    const url = `${getConversationUrl(conversationId)}/list-files`;
-    const { data } = await openHands.get<GetFilesResponse>(url, {
-      params: { path },
-    });
-
-    return data;
-  }
-
-  /**
-   * Retrieve the content of a file
-   * @param conversationId ID of the conversation
-   * @param path Full path of the file to retrieve
-   * @returns Code content of the file
-   */
-  static async getFile(conversationId: string, path: string): Promise<string> {
-    const url = `${getConversationUrl(conversationId)}/select-file`;
-    const { data } = await openHands.get<GetFileResponse>(url, {
-      params: { file: path },
-    });
-
-    return data.code;
-  }
-
-  /**
-   * Upload multiple files to the workspace
-   * @param conversationId ID of the conversation
-   * @param files List of files.
-   * @returns list of uploaded files, list of skipped files
-   */
-  static async uploadFiles(
-    conversationId: string,
-    files: File[],
-  ): Promise<FileUploadSuccessResponse> {
-    const formData = new FormData();
-    for (const file of files) {
-      formData.append("files", file);
-    }
-    const url = `${getConversationUrl(conversationId)}/upload-files`;
-    const response = await openHands.post<FileUploadSuccessResponse>(
-      url,
-      formData,
-      {
-        headers: {
-          "Content-Type": "multipart/form-data",
-        },
-      },
-    );
-    return response.data;
-  }
-}

frontend/src/api/file-service/file-service.types.ts

@@ -1,5 +0,0 @@
-export type GetFilesResponse = string[];
-
-export interface GetFileResponse {
-  code: string;
-}