Merge branch 'main' into ray/docker-scan

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/workflows/ghcr-build.yml

@@ -59,6 +59,7 @@ jobs:
     permissions:
       contents: read
       packages: write
+      security-events: write
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -85,14 +86,35 @@ jobs:
         run: |
           ./containers/build.sh -i openhands -o ${{ env.REPO_OWNER }} --push
 
+      - name: Run Trivy vulnerability scanner
+        if: github.event_name != 'pull_request'
+        uses: aquasecurity/trivy-action@master
+        # This only reports, does not fail the build on CVE.
+        with:
+          image-ref: ghcr.io/${{ env.REPO_OWNER }}/openhands:${{ env.RELEVANT_SHA }}
+          format: 'sarif'
+          output: 'trivy-results.sarif'
+          timeout: '10m'
+          scanners: 'vuln'  # Only scan vulnerabilities, not secrets/config
+          severity: 'CRITICAL,HIGH,MEDIUM'  # Skip LOW severity
+
+      - name: Upload Trivy results to GitHub Security tab
+        if: github.event_name != 'pull_request'
+        uses: github/codeql-action/upload-sarif@v3
+        with:
+          sarif_file: 'trivy-results.sarif'
+          category: 'security/container-openhands-${{ matrix.base_image.tag }}'
+          sha: "${{ env.RELEVANT_SHA }}"
+          ref: refs/heads/${{ github.event.pull_request.head.ref || github.ref_name }}
   # Builds the runtime Docker images
   ghcr_build_runtime:
-    name: Build Image
+    name: Build Runtime Image
     runs-on: blacksmith-8vcpu-ubuntu-2204
     if: "!(github.event_name == 'push' && startsWith(github.ref, 'refs/tags/ext-v'))"
     permissions:
       contents: read
       packages: write
+      security-events: write
     needs: define-matrix
     strategy:
       matrix:
@@ -166,12 +188,41 @@ jobs:
           name: runtime-src-${{ matrix.base_image.tag }}
           path: containers/runtime
 
+      - name: Run Trivy vulnerability scanner
+        if: github.event_name != 'pull_request'
+        uses: aquasecurity/trivy-action@master
+        # This only reports, does not fail the build on CVE.
+        with:
+          image-ref: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          format: 'sarif'
+          output: 'trivy-results-raw.sarif'
+          timeout: '10m'
+          scanners: 'vuln'  # Only scan vulnerabilities, not secrets/config
+          severity: 'CRITICAL,HIGH,MEDIUM'  # Skip LOW severity
+      - name: Customize SARIF with image flavor
+        if: github.event_name != 'pull_request'
+        run: |
+          # Modify the tool name to include the image flavor
+          jq --arg flavor "${{ matrix.base_image.tag }}" \
+            '.runs[0].tool.driver.name = "Trivy (" + $flavor + ")"' \
+            trivy-results-raw.sarif > trivy-results.sarif
+
+          echo "Modified tool name to: $(jq -r '.runs[0].tool.driver.name' trivy-results.sarif)"
+
+      - name: Upload Trivy results to GitHub Security tab
+        if: github.event_name != 'pull_request'
+        uses: github/codeql-action/upload-sarif@v3
+        with:
+          sarif_file: 'trivy-results.sarif'
+          category: 'security/container-runtime-${{ matrix.base_image.tag }}'
+
   ghcr_build_enterprise:
-    name: Push Enterprise Image
+    name: Build Enterprise Image
     runs-on: blacksmith-8vcpu-ubuntu-2204
     permissions:
       contents: read
       packages: write
+      security-events: write
     needs: [define-matrix, ghcr_build_app]
     # Do not build enterprise in forks
     if: github.event.pull_request.head.repo.fork != true
@@ -211,14 +262,16 @@ jobs:
             latest=auto
             prefix=
             suffix=
+        env:
+          DOCKER_METADATA_PR_HEAD_SHA: true
       - name: Determine app image tag
         shell: bash
         run: |
           # Duplicated with build.sh
-          sanitized_ref_name=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
-          OPENHANDS_BUILD_VERSION=$sanitized_ref_name
+          sanitized_ref_name=$(echo "${{github.event.pull_request.head.sha}}" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
           sanitized_ref_name=$(echo "$sanitized_ref_name" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
-          echo "OPENHANDS_DOCKER_TAG=${sanitized_ref_name}" >> $GITHUB_ENV
+          echo "OPENHANDS_BUILD_VERSION=${sanitized_ref_name}" >> $GITHUB_ENV
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
       - name: Build and push Docker image
         uses: useblacksmith/build-push-action@v1
         with:
@@ -228,12 +281,30 @@ jobs:
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
           build-args: |
-            OPENHANDS_VERSION=${{ env.OPENHANDS_DOCKER_TAG }}
+            OPENHANDS_VERSION=${{ env.OPENHANDS_BUILD_VERSION }}
           platforms: linux/amd64
           # Add build provenance
           provenance: true
           # Add build attestations for better security
           sbom: true
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        if: github.event_name != 'pull_request'
+        # This only reports, does not fail the build on CVE.
+        with:
+          image-ref: "ghcr.io/${{ env.REPO_OWNER }}/enterprise-server:sha-${{ env.RELEVANT_SHA }}"
+          format: 'sarif'
+          output: 'trivy-results.sarif'
+          timeout: '10m'
+          scanners: 'vuln'  # Only scan vulnerabilities, not secrets/config
+          severity: 'CRITICAL,HIGH,MEDIUM'  # Skip LOW severity
+
+      - name: Upload Trivy results to GitHub Security tab
+        if: github.event_name != 'pull_request'
+        uses: github/codeql-action/upload-sarif@v3
+        with:
+          sarif_file: 'trivy-results.sarif'
+          category: 'security/container-enterprise-server'
 
   enterprise-preview:
     name: Enterprise preview

.github/workflows/py-tests.yml

@@ -19,12 +19,16 @@ jobs:
   # Run python tests on Linux
   test-on-linux:
     name: Python Tests on Linux
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: blacksmith-4vcpu-ubuntu-2404
     env:
       INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
     strategy:
       matrix:
         python-version: ["3.12"]
+    permissions:
+      # For coverage comment and python-coverage-comment-action branch
+      pull-requests: write
+      contents: write
     steps:
       - uses: actions/checkout@v4
       - name: Set up Docker Buildx
@@ -48,10 +52,21 @@ jobs:
       - name: Build Environment
         run: make build
       - name: Run Unit Tests
-        run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest --forked -n auto -svv ./tests/unit
+        run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest --forked -n auto -s ./tests/unit --cov=openhands --cov-branch
+        env:
+          COVERAGE_FILE: ".coverage.${{ matrix.python_version }}"
       - name: Run Runtime Tests with CLIRuntime
-        run: PYTHONPATH=".:$PYTHONPATH" TEST_RUNTIME=cli poetry run pytest -svv tests/runtime/test_bash.py
-
+        run: PYTHONPATH=".:$PYTHONPATH" TEST_RUNTIME=cli poetry run pytest -s tests/runtime/test_bash.py --cov=openhands --cov-branch
+        env:
+          COVERAGE_FILE: ".coverage.runtime.${{ matrix.python_version }}"
+      - name: Store coverage file
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-openhands
+          path: |
+            .coverage.${{ matrix.python_version }}
+            .coverage.runtime.${{ matrix.python_version }}
+          include-hidden-files: true
   # Run specific Windows python tests
   test-on-windows:
     name: Python Tests on Windows
@@ -85,7 +100,7 @@ jobs:
           DEBUG: "1"
   test-enterprise:
     name: Enterprise Python Unit Tests
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: blacksmith-4vcpu-ubuntu-2404
     strategy:
       matrix:
         python-version: ["3.12"]
@@ -102,5 +117,37 @@ jobs:
         working-directory: ./enterprise
         run: poetry install --with dev,test
       - name: Run Unit Tests
-        working-directory: ./enterprise
-        run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest --forked -n auto -svv -p no:ddtrace -p no:ddtrace.pytest_bdd -p no:ddtrace.pytest_benchmark ./tests/unit
+        # Use base working directory for coverage paths to line up.
+        run: PYTHONPATH=".:$PYTHONPATH" poetry run --project=enterprise pytest --forked -n auto -s -p no:ddtrace -p no:ddtrace.pytest_bdd -p no:ddtrace.pytest_benchmark ./enterprise/tests/unit --cov=enterprise --cov-branch
+        env:
+          COVERAGE_FILE: ".coverage.enterprise.${{ matrix.python_version }}"
+      - name: Store coverage file
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-enterprise
+          path: ".coverage.enterprise.${{ matrix.python_version }}"
+          include-hidden-files: true
+  coverage-comment:
+    name: Coverage Comment
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    needs: [test-on-linux, test-enterprise]
+
+    permissions:
+      pull-requests: write
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/download-artifact@v5
+        id: download
+        with:
+          pattern: coverage-*
+          merge-multiple: true
+
+      - name: Coverage comment
+        id: coverage_comment
+        uses: py-cov-action/python-coverage-comment-action@v3
+        with:
+          GITHUB_TOKEN: ${{ github.token }}
+          MERGE_COVERAGE_FILES: true

.github/workflows/stale.yml

@@ -15,7 +15,7 @@ jobs:
           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,backlog
+          exempt-issue-labels: roadmap,backlog,app-team
           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

Development.md

@@ -159,7 +159,7 @@ poetry run pytest ./tests/unit/test_*.py
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker
 container image by setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.56-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.57-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -79,17 +79,17 @@ You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)
 You can also run OpenHands directly with Docker:
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.57-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.57-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:0.56
+    docker.all-hands.dev/all-hands-ai/openhands:0.57
 ```
 
 </details>

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:0.56-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.57-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.57-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:0.56
+    docker.all-hands.dev/all-hands-ai/openhands:0.57
 ```
 
 > **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:0.56-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.57-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.57-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:0.56
+    docker.all-hands.dev/all-hands-ai/openhands:0.57
 ```
 
 **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。

config.template.toml

@@ -489,6 +489,47 @@ type = "noop"
 # Run the runtime sandbox container in privileged mode for use with docker-in-docker
 #privileged = false
 
+#################################### MCP #####################################
+# Configuration for Model Context Protocol (MCP) servers
+# MCP allows OpenHands to communicate with external tool servers
+##############################################################################
+[mcp]
+# SSE servers - Server-Sent Events transport (legacy)
+#sse_servers = [
+#    # Basic SSE server with just a URL
+#    "http://localhost:8080/mcp/sse",
+#
+#    # SSE server with authentication
+#    {url = "https://api.example.com/mcp/sse", api_key = "your-api-key"}
+#]
+
+# SHTTP servers - Streamable HTTP transport (recommended)
+#shttp_servers = [
+#    # Basic SHTTP server with default 60s timeout
+#    "https://api.example.com/mcp/shttp",
+#
+#    # SHTTP server with custom timeout for long-running tools
+#    {
+#        url = "https://api.example.com/mcp/shttp",
+#        api_key = "your-api-key",
+#        timeout = 180  # 3 minutes for processing-heavy tools (1-3600 seconds)
+#    }
+#]
+
+# Stdio servers - Direct process communication (development only)
+#stdio_servers = [
+#    # Basic stdio server
+#    {name = "filesystem", command = "npx", args = ["@modelcontextprotocol/server-filesystem", "/"]},
+#
+#    # Stdio server with environment variables
+#    {
+#        name = "fetch",
+#        command = "uvx",
+#        args = ["mcp-server-fetch"],
+#        env = {DEBUG = "true"}
+#    }
+#]
+
 #################################### Model Routing ############################
 # Configuration for experimental model routing feature
 # Enables intelligent switching between different LLM models for specific purposes

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=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.56-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.57-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.57-nikolaik}
       #- SANDBOX_USER_ID=${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/usage/cloud/bitbucket-installation.mdx

@@ -8,9 +8,21 @@ 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).
 
+## Adding Bitbucket Repository Access
+
+Upon signing into OpenHands Cloud with a Bitbucket account, OpenHands will have access to your repositories.
+
+## Working With Bitbucket Repos in Openhands Cloud
+
+After signing in with a Bitbucket account, use the `Open Repository` section to select the appropriate repository and
+branch you'd like OpenHands to work on. Then click on `Launch` to start the conversation!
+
+![Connect Repo](/static/img/connect-repo.png)
+
 ## 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:
+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
 ```
@@ -31,17 +43,6 @@ If your Bitbucket Cloud instance has IP restrictions, you'll need to whitelist t
 34.60.55.59
 ```
 
-## Adding Bitbucket Repository Access
-
-Upon signing into OpenHands Cloud with a Bitbucket account, OpenHands will have access to your repositories.
-
-## Working With Bitbucket Repos in Openhands Cloud
-
-After signing in with a Bitbucket account, use the `select a repo` and `select a branch` dropdowns to select the
-appropriate repository and branch you'd like OpenHands to work on. Then click on `Launch` to start the conversation!
-
-![Connect Repo](/static/img/connect-repo-no-github.png)
-
 ## Next Steps
 
 - [Learn about the Cloud UI](/usage/cloud/cloud-ui).

docs/usage/cloud/cloud-api.mdx

@@ -12,13 +12,10 @@ For the available API endpoints, refer to the
 To use the OpenHands Cloud API, you'll need to generate an API key:
 
 1. Log in to your [OpenHands Cloud](https://app.all-hands.dev) account.
-2. Navigate to the [Settings page](https://app.all-hands.dev/settings).
-3. Select the `API Keys` tab.
-4. Click `Create API Key`.
-5. Give your key a descriptive name (Example: "Development" or "Production") and select `Create`.
-6. Copy the generated API key and store it securely. It will only be shown once.
-
-![API Key Generation](/static/img/api-key-generation.png)
+2. Navigate to the [Settings > API Keys](https://app.all-hands.dev/settings/api-keys) page.
+3. Click `Create API Key`.
+4. Give your key a descriptive name (Example: "Development" or "Production") and select `Create`.
+5. Copy the generated API key and store it securely. It will only be shown once.
 
 ## API Usage
 

docs/usage/cloud/cloud-ui.mdx

@@ -8,24 +8,39 @@ description: The Cloud UI provides a web interface for interacting with OpenHand
 
 The landing page is where you can:
 
-- [Add GitHub repository access](/usage/cloud/github-installation#adding-github-repository-access) to OpenHands.
 - [Select a GitHub repo](/usage/cloud/github-installation#working-with-github-repos-in-openhands-cloud),
   [a GitLab repo](/usage/cloud/gitlab-installation#working-with-gitlab-repos-in-openhands-cloud) or
   [a Bitbucket repo](/usage/cloud/bitbucket-installation#working-with-bitbucket-repos-in-openhands-cloud) to start working on.
+- Launch an empty conversation using `New Conversation`.
 - See `Suggested Tasks` for repositories that OpenHands has access to.
-- Launch an empty conversation using `Launch from Scratch`.
+- See your `Recent Conversations`.
 
 ## Settings
 
-The Settings page allows you to:
+Settings are divided across tabs, with each tab focusing on a specific area of configuration.
 
-- [Configure GitHub repository access](/usage/cloud/github-installation#modifying-repository-access) for OpenHands.
-- [Install the OpenHands Slack app](/usage/cloud/slack-installation).
-- Set application settings like your preferred language, notifications and other preferences.
-- Add credits to your account.
-- [Generate custom secrets](/usage/common-settings#secrets-management).
-- [Create API keys to work with OpenHands programmatically](/usage/cloud/cloud-api).
-- Change your email address.
+- `User`
+  - Change your email address.
+- `Integrations`
+  - [Configure GitHub repository access](/usage/cloud/github-installation#modifying-repository-access) for OpenHands.
+  - [Install the OpenHands Slack app](/usage/cloud/slack-installation).
+- `Application`
+  - Set your preferred language, notifications and other preferences.
+  - Toggle task suggestions on GitHub.
+  - Toggle Solvability Analysis.
+  - Set a maximum budget per conversation.
+  - Configure the username and email that OpenHands uses for commits.
+- `LLM` (Available for `Pro Users`)
+  - Choose to use another LLM or use different models from the OpenHands provider.
+- `Billing`
+  - Add credits for using the OpenHands provider.
+  - Cancel your `Pro` subscription.
+- `Secrets`
+  - [Generate custom secrets](/usage/common-settings#secrets-management).
+- `API Keys`
+  - [Create API keys to work with OpenHands programmatically](/usage/cloud/cloud-api).
+- `MCP`
+  - [Setup an MCP server](/usage/mcp)
 
 ## Key Features
 

docs/usage/cloud/github-installation.mdx

@@ -12,7 +12,7 @@ description: This guide walks you through the process of installing OpenHands Cl
 
 You can grant OpenHands access to specific GitHub repositories:
 
-1. Click on `Add GitHub repos` on the landing page.
+1. Click on `+ Add GitHub Repos` in the repository selection dropdown.
 2. Select your organization and choose the specific repositories to grant OpenHands access to.
 <Accordion title="OpenHands permissions">
   - OpenHands requests short-lived tokens (8-hour expiration) with these permissions:
@@ -34,20 +34,22 @@ You can grant OpenHands access to specific GitHub repositories:
 ## Modifying Repository Access
 
 You can modify GitHub repository access at any time by:
-- Selecting `Add GitHub repos` on the landing page or
-- Visiting the Settings page and selecting `Configure GitHub Repositories` under the `Integrations` tab
+- Selecting `+ Add GitHub Repos` in the repository selection dropdown or
+- Visiting the `Settings > Integrations` page and selecting `Configure GitHub Repositories`
 
 ## Working With GitHub Repos in Openhands Cloud
 
-Once you've granted GitHub repository access, you can start working with your GitHub repository. Use the `select a repo`
-and `select a branch` dropdowns to select the appropriate repository and branch you'd like OpenHands to work on. Then
-click on `Launch` to start the conversation!
+Once you've granted GitHub repository access, you can start working with your GitHub repository. Use the
+`Open Repository` section to select the appropriate repository and branch you'd like OpenHands to work on. Then click
+on `Launch` to start the conversation!
 
 ![Connect Repo](/static/img/connect-repo.png)
 
-## Working on Github Issues and Pull Requests Using Openhands
+## Working on GitHub Issues and Pull Requests Using Openhands
 
-Giving GitHub repository access to OpenHands also allows you to work on GitHub issues and pull requests directly.
+To allow OpenHands to work directly from GitHub directly, you must
+[give OpenHands access to your repository](/usage/cloud/github-installation#modifying-repository-access). Once access is
+given, you can use OpenHands by labeling the issue or by tagging `@openhands`.
 
 ### Working with Issues
 
@@ -64,7 +66,12 @@ To get OpenHands to work on pull requests, mention `@openhands` in the comments
 - Request updates
 - Get code explanations
 
-**Important Note**: The `@openhands` mention functionality in pull requests only works if the pull request is both *to* and *from* a repository that you have added through the interface. This is because OpenHands needs appropriate permissions to access both repositories.
+<Note>
+The `@openhands` mention functionality in pull requests only works if the pull request is both
+*to* and *from* a repository that you have added through the interface. This is because OpenHands needs appropriate
+permissions to access both repositories.
+</Note>
+
 
 ## Next Steps
 

docs/usage/cloud/gitlab-installation.mdx

@@ -14,16 +14,17 @@ Upon signing into OpenHands Cloud with a GitLab account, OpenHands will have acc
 
 ## Working With GitLab Repos in Openhands Cloud
 
-After signing in with a Gitlab account, use the `select a repo` and `select a branch` dropdowns to select the
-appropriate repository and branch you'd like OpenHands to work on. Then click on `Launch` to start the conversation!
+After signing in with a Gitlab account, use the `Open Repository` section to select the appropriate repository and
+branch you'd like OpenHands to work on. Then click on `Launch` to start the conversation!
 
-![Connect Repo](/static/img/connect-repo-no-github.png)
+![Connect Repo](/static/img/connect-repo.png)
 
 ## Using Tokens with Reduced Scopes
 
 OpenHands requests an API-scoped token during OAuth authentication. By default, this token is provided to the agent.
-To restrict the agent's permissions, you can define a custom secret `GITLAB_TOKEN`, which will override the default token assigned to the agent.
-While the high-permission API token is still requested and used for other components of the application (e.g. opening merge requests), the agent will not have access to it.
+To restrict the agent's permissions, you can define a custom secret `GITLAB_TOKEN`, which will override the default
+token assigned to the agent. While the high-permission API token is still requested and used for other components of
+the application (e.g. opening merge requests), the agent will not have access to it.
 
 ## Working on GitLab Issues and Merge Requests Using Openhands
 
@@ -32,7 +33,8 @@ This feature works for personal projects and is available for group projects wit
 [Premium or Ultimate tier subscription](https://docs.gitlab.com/user/project/integrations/webhooks/#group-webhooks).
 
 A webhook is automatically installed within a few minutes after the owner/maintainer of the project or group logs into
-OpenHands Cloud. If you decide to delete the webhook, then re-installing will require the support of All Hands AI but we are planning to improve this in a future release.
+OpenHands Cloud. If you decide to delete the webhook, then re-installing will require the support of All Hands AI but
+we are planning to improve this in a future release.
 </Note>
 
 Giving GitLab repository access to OpenHands also allows you to work on GitLab issues and merge requests directly.

docs/usage/cloud/slack-installation.mdx

@@ -13,7 +13,9 @@ description: This guide walks you through installing the OpenHands Slack app.
 </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.
+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

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

@@ -113,7 +113,7 @@ 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:0.56-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.57-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -122,7 +122,7 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.56 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.57 \
     python -m openhands.cli.entry --override-cli-mode true
 ```
 

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:0.56-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.57-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:0.56 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.57 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

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:0.56-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.57-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.57-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:0.56
+    docker.all-hands.dev/all-hands-ai/openhands:0.57
 ```
 
 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:0.56
+Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.57
 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

@@ -30,6 +30,20 @@ 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. Below are the current pricing details for OpenHands models:
 
-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.
+| Model | Input Cost (per 1M tokens) | Cached Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Max Input Tokens | Max Output Tokens |
+|-------|----------------------------|-----------------------------------|------------------------------|------------------|-------------------|
+| claude-opus-4-20250514 | $15.00 | $1.50 | $75.00 | 200,000 | 32,000 |
+| claude-sonnet-4-20250514 | $3.00 | $0.30 | $15.00 | 200,000 | 64,000 |
+| devstral-medium-2507 | $0.40 | N/A | $2.00 | 128,000 | 128,000 |
+| devstral-small-2505 | $0.10 | N/A | $0.30 | 128,000 | 128,000 |
+| devstral-small-2507 | $0.10 | N/A | $0.30 | 128,000 | 128,000 |
+| gemini-2.5-pro | $1.25 | $0.31 | $10.00 | 1,048,576 | 65,535 |
+| gpt-5-2025-08-07 | $1.25 | $0.125 | $10.00 | 400,000 | 128,000 |
+| gpt-5-mini-2025-08-07 | $0.25 | $0.025 | $2.00 | 400,000 | 128,000 |
+| o3 | $2.00 | $0.50 | $8.00 | 200,000 | 100,000 |
+| o4-mini | $1.10 | $0.28 | $4.40 | 200,000 | 100,000 |
+| qwen3-coder-480b | $0.40 | N/A | $1.60 | N/A | N/A |
+
+**Note:** Cached input tokens are charged at a reduced rate when the same content is reused across requests. Models that don't support prompt caching show "N/A" for cached input cost.

docs/usage/local-setup.mdx

@@ -116,17 +116,17 @@ Note that you'll still need `uv` installed for the default MCP servers to work p
 <Accordion title="Docker Command (Click to expand)">
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.57-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.57-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:0.56
+    docker.all-hands.dev/all-hands-ai/openhands:0.57
 ```
 
 </Accordion>

docs/usage/mcp.mdx

@@ -67,6 +67,19 @@ sse_servers = [
     # External MCP service with authentication
     {url="https://api.example.com/mcp/sse", api_key="your-api-key"}
 ]
+
+# SHTTP Servers - Modern streamable HTTP transport (recommended)
+shttp_servers = [
+    # Basic SHTTP server with default 60s timeout
+    "https://api.example.com/mcp/shttp",
+    
+    # Server with custom timeout for heavy operations
+    {
+        url = "https://files.example.com/mcp/shttp",
+        api_key = "your-api-key",
+        timeout = 1800  # 30 minutes for large file processing
+    }
+]
 ```
 
 
@@ -118,6 +131,17 @@ SHTTP (Streamable HTTP) servers are configured using either a string URL or an o
   - Type: `str`
   - Description: API key for authentication
 
+- `timeout` (optional)
+  - Type: `int`
+  - Default: `60`
+  - Range: `1-3600` seconds (1 hour maximum)
+  - Description: Timeout in seconds for tool execution. This prevents tool calls from hanging indefinitely.
+  - **Use Cases:**
+    - **Short timeout (1-30s)**: For lightweight operations like status checks or simple queries
+    - **Medium timeout (30-300s)**: For standard processing tasks like data analysis or API calls  
+    - **Long timeout (300-3600s)**: For heavy operations like file processing, complex calculations, or batch operations
+  - **Note**: This timeout only applies to individual tool calls, not server connection establishment.
+
 ### Stdio Servers
 
 **Note**: While stdio servers are supported, we recommend using MCP proxies (see above) for better reliability and performance.
@@ -192,5 +216,27 @@ SHTTP is the modern HTTP-based transport protocol that provides enhanced feature
 
 SHTTP is the recommended transport for HTTP-based MCP servers as it provides better reliability and features compared to the legacy SSE transport.
 
+#### SHTTP Timeout Best Practices
+
+When configuring SHTTP timeouts, consider these guidelines:
+
+**Timeout Selection:**
+- **Database queries**: 30-60 seconds
+- **File operations**: 60-300 seconds (depending on file size)
+- **Web scraping**: 60-120 seconds
+- **Complex calculations**: 300-1800 seconds
+- **Batch processing**: 1800-3600 seconds (maximum)
+
+**Error Handling:**
+When a tool call exceeds the configured timeout:
+- The operation is cancelled with an `asyncio.TimeoutError`
+- The agent receives a timeout error message
+- The server connection remains active for subsequent requests
+
+**Monitoring:**
+- Set timeouts based on your tool's actual performance characteristics
+- Monitor timeout occurrences to optimize timeout values
+- Consider implementing server-side timeout handling for graceful degradation
+
 ### Standard Input/Output (stdio)
 Stdio transport enables communication through standard input and output streams, making it ideal for local integrations and command-line tools. This transport is used for locally executed MCP servers that run as separate processes.

enterprise/Dockerfile

@@ -7,14 +7,28 @@ LABEL com.datadoghq.tags.service="deploy"
 LABEL com.datadoghq.tags.env="${DD_ENV}"
 
 # Install Node.js v20+ and npm (which includes npx)
+# Apply security updates to fix CVEs
 RUN apt-get update && \
     apt-get install -y curl && \
     curl -fsSL https://deb.nodesource.com/setup_20.x | bash - && \
     apt-get install -y nodejs && \
     apt-get install -y jq gettext && \
-    apt-get clean
+    # Apply security updates for packages with available fixes
+    apt-get upgrade -y \
+        libc-bin \
+        libc6 \
+        libgnutls30 \
+        libsqlite3-0 \
+        perl-base && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
 
-RUN pip install alembic psycopg2-binary cloud-sql-python-connector pg8000 gspread stripe python-keycloak asyncpg sqlalchemy[asyncio] resend tenacity slack-sdk ddtrace posthog "limits==5.2.0" coredis prometheus-client shap scikit-learn pandas numpy
+# Install Python packages with security fixes
+RUN pip install alembic psycopg2-binary cloud-sql-python-connector pg8000 gspread stripe python-keycloak asyncpg sqlalchemy[asyncio] resend tenacity slack-sdk ddtrace posthog "limits==5.2.0" coredis prometheus-client shap scikit-learn pandas numpy && \
+    # Update packages with known CVE fixes
+    pip install --upgrade \
+        "mcp>=1.10.0" \
+        "pillow>=11.3.0"
 
 WORKDIR /app
 COPY enterprise .

enterprise/experiments/experiment_manager.py

@@ -2,7 +2,6 @@ from experiments.constants import (
     ENABLE_EXPERIMENT_MANAGER,
 )
 from experiments.experiment_versions import (
-    handle_claude4_vs_gpt5_experiment,
     handle_condenser_max_step_experiment,
     handle_system_prompt_experiment,
 )
@@ -44,9 +43,6 @@ class SaaSExperimentManager(ExperimentManager):
             return conversation_settings
 
         # Apply conversation-scoped experiments
-        conversation_settings = handle_claude4_vs_gpt5_experiment(
-            user_id, conversation_id, conversation_settings
-        )
         conversation_settings = handle_condenser_max_step_experiment(
             user_id, conversation_id, conversation_settings
         )

enterprise/poetry.lock

@@ -766,7 +766,7 @@ version = "1.17.1"
 description = "Foreign Function Interface for Python calling C code."
 optional = false
 python-versions = ">=3.8"
-groups = ["main"]
+groups = ["main", "test"]
 files = [
     {file = "cffi-1.17.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:df8b1c11f177bc2313ec4b2d46baec87a5f3e71fc8b45dab2ee7cae86d9aba14"},
     {file = "cffi-1.17.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8f2cdc858323644ab277e9bb925ad72ae0e67f69e804f4898c070998d50b1a67"},
@@ -836,6 +836,7 @@ files = [
     {file = "cffi-1.17.1-cp39-cp39-win_amd64.whl", hash = "sha256:d016c76bdd850f3c626af19b0542c9677ba156e4ee4fccfdd7848803533ef662"},
     {file = "cffi-1.17.1.tar.gz", hash = "sha256:1c39c6016c32bc48dd54561950ebd6836e1670f2ae46128f67cf49e789c52824"},
 ]
+markers = {test = "platform_python_implementation == \"CPython\" and sys_platform == \"win32\""}
 
 [package.dependencies]
 pycparser = "*"
@@ -1901,25 +1902,25 @@ files = [
 
 [[package]]
 name = "fastapi"
-version = "0.116.1"
+version = "0.117.1"
 description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "fastapi-0.116.1-py3-none-any.whl", hash = "sha256:c46ac7c312df840f0c9e220f7964bada936781bc4e2e6eb71f1c4d7553786565"},
-    {file = "fastapi-0.116.1.tar.gz", hash = "sha256:ed52cbf946abfd70c5a0dccb24673f0670deeb517a88b3544d03c2a6bf283143"},
+    {file = "fastapi-0.117.1-py3-none-any.whl", hash = "sha256:33c51a0d21cab2b9722d4e56dbb9316f3687155be6b276191790d8da03507552"},
+    {file = "fastapi-0.117.1.tar.gz", hash = "sha256:fb2d42082d22b185f904ca0ecad2e195b851030bd6c5e4c032d1c981240c631a"},
 ]
 
 [package.dependencies]
 pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<2.0.0 || >2.0.0,<2.0.1 || >2.0.1,<2.1.0 || >2.1.0,<3.0.0"
-starlette = ">=0.40.0,<0.48.0"
+starlette = ">=0.40.0,<0.49.0"
 typing-extensions = ">=4.8.0"
 
 [package.extras]
-all = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>=0.23.0)", "itsdangerous (>=1.1.0)", "jinja2 (>=3.1.5)", "orjson (>=3.2.1)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.18)", "pyyaml (>=5.3.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0)", "uvicorn[standard] (>=0.12.0)"]
-standard = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>=0.23.0)", "jinja2 (>=3.1.5)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]
-standard-no-fastapi-cloud-cli = ["email-validator (>=2.0.0)", "fastapi-cli[standard-no-fastapi-cloud-cli] (>=0.0.8)", "httpx (>=0.23.0)", "jinja2 (>=3.1.5)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]
+all = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>=0.23.0,<1.0.0)", "itsdangerous (>=1.1.0)", "jinja2 (>=3.1.5)", "orjson (>=3.2.1)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.18)", "pyyaml (>=5.3.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0)", "uvicorn[standard] (>=0.12.0)"]
+standard = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>=0.23.0,<1.0.0)", "jinja2 (>=3.1.5)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]
+standard-no-fastapi-cloud-cli = ["email-validator (>=2.0.0)", "fastapi-cli[standard-no-fastapi-cloud-cli] (>=0.0.8)", "httpx (>=0.23.0,<1.0.0)", "jinja2 (>=3.1.5)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]
 
 [[package]]
 name = "fastjsonschema"
@@ -2291,6 +2292,72 @@ test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask[dataframe,test]", "moto
 test-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas", "panel", "paramiko", "pyarrow", "pyarrow (>=1)", "pyftpdlib", "pygit2", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "python-snappy", "requests", "smbprotocol", "tqdm", "urllib3", "zarr", "zstandard ; python_version < \"3.14\""]
 tqdm = ["tqdm"]
 
+[[package]]
+name = "gevent"
+version = "25.9.1"
+description = "Coroutine-based network library"
+optional = false
+python-versions = ">=3.9"
+groups = ["test"]
+files = [
+    {file = "gevent-25.9.1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:856b990be5590e44c3a3dc6c8d48a40eaccbb42e99d2b791d11d1e7711a4297e"},
+    {file = "gevent-25.9.1-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:fe1599d0b30e6093eb3213551751b24feeb43db79f07e89d98dd2f3330c9063e"},
+    {file = "gevent-25.9.1-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:f0d8b64057b4bf1529b9ef9bd2259495747fba93d1f836c77bfeaacfec373fd0"},
+    {file = "gevent-25.9.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:b56cbc820e3136ba52cd690bdf77e47a4c239964d5f80dc657c1068e0fe9521c"},
+    {file = "gevent-25.9.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:c5fa9ce5122c085983e33e0dc058f81f5264cebe746de5c401654ab96dddfca8"},
+    {file = "gevent-25.9.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:03c74fec58eda4b4edc043311fca8ba4f8744ad1632eb0a41d5ec25413581975"},
+    {file = "gevent-25.9.1-cp310-cp310-win_amd64.whl", hash = "sha256:a8ae9f895e8651d10b0a8328a61c9c53da11ea51b666388aa99b0ce90f9fdc27"},
+    {file = "gevent-25.9.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:18e5aff9e8342dc954adb9c9c524db56c2f3557999463445ba3d9cbe3dada7b7"},
+    {file = "gevent-25.9.1-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:1cdf6db28f050ee103441caa8b0448ace545364f775059d5e2de089da975c457"},
+    {file = "gevent-25.9.1-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:812debe235a8295be3b2a63b136c2474241fa5c58af55e6a0f8cfc29d4936235"},
+    {file = "gevent-25.9.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:b28b61ff9216a3d73fe8f35669eefcafa957f143ac534faf77e8a19eb9e6883a"},
+    {file = "gevent-25.9.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:5e4b6278b37373306fc6b1e5f0f1cf56339a1377f67c35972775143d8d7776ff"},
+    {file = "gevent-25.9.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:d99f0cb2ce43c2e8305bf75bee61a8bde06619d21b9d0316ea190fc7a0620a56"},
+    {file = "gevent-25.9.1-cp311-cp311-win_amd64.whl", hash = "sha256:72152517ecf548e2f838c61b4be76637d99279dbaa7e01b3924df040aa996586"},
+    {file = "gevent-25.9.1-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:46b188248c84ffdec18a686fcac5dbb32365d76912e14fda350db5dc0bfd4f86"},
+    {file = "gevent-25.9.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f2b54ea3ca6f0c763281cd3f96010ac7e98c2e267feb1221b5a26e2ca0b9a692"},
+    {file = "gevent-25.9.1-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:7a834804ac00ed8a92a69d3826342c677be651b1c3cd66cc35df8bc711057aa2"},
+    {file = "gevent-25.9.1-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:323a27192ec4da6b22a9e51c3d9d896ff20bc53fdc9e45e56eaab76d1c39dd74"},
+    {file = "gevent-25.9.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:6ea78b39a2c51d47ff0f130f4c755a9a4bbb2dd9721149420ad4712743911a51"},
+    {file = "gevent-25.9.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:dc45cd3e1cc07514a419960af932a62eb8515552ed004e56755e4bf20bad30c5"},
+    {file = "gevent-25.9.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:34e01e50c71eaf67e92c186ee0196a039d6e4f4b35670396baed4a2d8f1b347f"},
+    {file = "gevent-25.9.1-cp312-cp312-win_amd64.whl", hash = "sha256:4acd6bcd5feabf22c7c5174bd3b9535ee9f088d2bbce789f740ad8d6554b18f3"},
+    {file = "gevent-25.9.1-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:4f84591d13845ee31c13f44bdf6bd6c3dbf385b5af98b2f25ec328213775f2ed"},
+    {file = "gevent-25.9.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:9cdbb24c276a2d0110ad5c978e49daf620b153719ac8a548ce1250a7eb1b9245"},
+    {file = "gevent-25.9.1-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:88b6c07169468af631dcf0fdd3658f9246d6822cc51461d43f7c44f28b0abb82"},
+    {file = "gevent-25.9.1-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:b7bb0e29a7b3e6ca9bed2394aa820244069982c36dc30b70eb1004dd67851a48"},
+    {file = "gevent-25.9.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2951bb070c0ee37b632ac9134e4fdaad70d2e660c931bb792983a0837fe5b7d7"},
+    {file = "gevent-25.9.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:e4e17c2d57e9a42e25f2a73d297b22b60b2470a74be5a515b36c984e1a246d47"},
+    {file = "gevent-25.9.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:8d94936f8f8b23d9de2251798fcb603b84f083fdf0d7f427183c1828fb64f117"},
+    {file = "gevent-25.9.1-cp313-cp313-win_amd64.whl", hash = "sha256:eb51c5f9537b07da673258b4832f6635014fee31690c3f0944d34741b69f92fa"},
+    {file = "gevent-25.9.1-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:1a3fe4ea1c312dbf6b375b416925036fe79a40054e6bf6248ee46526ea628be1"},
+    {file = "gevent-25.9.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0adb937f13e5fb90cca2edf66d8d7e99d62a299687400ce2edee3f3504009356"},
+    {file = "gevent-25.9.1-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:427f869a2050a4202d93cf7fd6ab5cffb06d3e9113c10c967b6e2a0d45237cb8"},
+    {file = "gevent-25.9.1-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:c049880175e8c93124188f9d926af0a62826a3b81aa6d3074928345f8238279e"},
+    {file = "gevent-25.9.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:b5a67a0974ad9f24721034d1e008856111e0535f1541499f72a733a73d658d1c"},
+    {file = "gevent-25.9.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:1d0f5d8d73f97e24ea8d24d8be0f51e0cf7c54b8021c1fddb580bf239474690f"},
+    {file = "gevent-25.9.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:ddd3ff26e5c4240d3fbf5516c2d9d5f2a998ef87cfb73e1429cfaeaaec860fa6"},
+    {file = "gevent-25.9.1-cp314-cp314-win_amd64.whl", hash = "sha256:bb63c0d6cb9950cc94036a4995b9cc4667b8915366613449236970f4394f94d7"},
+    {file = "gevent-25.9.1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f18f80aef6b1f6907219affe15b36677904f7cfeed1f6a6bc198616e507ae2d7"},
+    {file = "gevent-25.9.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:b274a53e818124a281540ebb4e7a2c524778f745b7a99b01bdecf0ca3ac0ddb0"},
+    {file = "gevent-25.9.1-cp39-cp39-win32.whl", hash = "sha256:c6c91f7e33c7f01237755884316110ee7ea076f5bdb9aa0982b6dc63243c0a38"},
+    {file = "gevent-25.9.1-cp39-cp39-win_amd64.whl", hash = "sha256:012a44b0121f3d7c800740ff80351c897e85e76a7e4764690f35c5ad9ec17de5"},
+    {file = "gevent-25.9.1.tar.gz", hash = "sha256:adf9cd552de44a4e6754c51ff2e78d9193b7fa6eab123db9578a210e657235dd"},
+]
+
+[package.dependencies]
+cffi = {version = ">=1.17.1", markers = "platform_python_implementation == \"CPython\" and sys_platform == \"win32\""}
+greenlet = {version = ">=3.2.2", markers = "platform_python_implementation == \"CPython\""}
+"zope.event" = "*"
+"zope.interface" = "*"
+
+[package.extras]
+dnspython = ["dnspython (>=1.16.0,<2.0) ; python_version < \"3.10\"", "idna ; python_version < \"3.10\""]
+docs = ["furo", "repoze.sphinx.autointerface", "sphinx", "sphinxcontrib-programoutput", "zope.schema"]
+monitor = ["psutil (>=5.7.0) ; sys_platform != \"win32\" or platform_python_implementation == \"CPython\""]
+recommended = ["cffi (>=1.17.1) ; platform_python_implementation == \"CPython\"", "dnspython (>=1.16.0,<2.0) ; python_version < \"3.10\"", "idna ; python_version < \"3.10\"", "psutil (>=5.7.0) ; sys_platform != \"win32\" or platform_python_implementation == \"CPython\""]
+test = ["cffi (>=1.17.1) ; platform_python_implementation == \"CPython\"", "coverage (>=5.0) ; sys_platform != \"win32\"", "dnspython (>=1.16.0,<2.0) ; python_version < \"3.10\"", "idna ; python_version < \"3.10\"", "objgraph", "psutil (>=5.7.0) ; sys_platform != \"win32\" or platform_python_implementation == \"CPython\"", "requests"]
+
 [[package]]
 name = "gitdb"
 version = "4.0.12"
@@ -2707,7 +2774,7 @@ version = "3.2.4"
 description = "Lightweight in-process concurrent programming"
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "test"]
 files = [
     {file = "greenlet-3.2.4-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:8c68325b0d0acf8d91dde4e6f930967dd52a5302cd4062932a6b2e7c2969f47c"},
     {file = "greenlet-3.2.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:94385f101946790ae13da500603491f04a76b6e4c059dab271b3ce2e283b2590"},
@@ -2764,6 +2831,7 @@ files = [
     {file = "greenlet-3.2.4-cp39-cp39-win_amd64.whl", hash = "sha256:d2e685ade4dafd447ede19c31277a224a239a0a1a4eca4e6390efedf20260cfb"},
     {file = "greenlet-3.2.4.tar.gz", hash = "sha256:0dca0d95ff849f9a364385f36ab49f50065d76964944638be9691e1832e9f86d"},
 ]
+markers = {test = "platform_python_implementation == \"CPython\""}
 
 [package.extras]
 docs = ["Sphinx", "furo"]
@@ -5363,7 +5431,7 @@ llama = ["llama-index (>=0.12.29,<0.13.0)", "llama-index-core (>=0.12.29,<0.13.0
 
 [[package]]
 name = "openhands-ai"
-version = "0.55.0"
+version = "0.57.0"
 description = "OpenHands: Code Less, Make More"
 optional = false
 python-versions = "^3.12,<3.14"
@@ -5397,7 +5465,7 @@ json-repair = "*"
 jupyter_kernel_gateway = "*"
 kubernetes = "^33.1.0"
 libtmux = ">=0.37,<0.40"
-litellm = "^1.74.3, !=1.64.4, !=1.67.*"
+litellm = ">=1.74.3, <1.77.2, !=1.64.4, !=1.67.*"
 memory-profiler = "^0.61.0"
 numpy = "*"
 openai = "1.99.9"
@@ -5406,6 +5474,7 @@ opentelemetry-api = "^1.33.1"
 opentelemetry-exporter-otlp-proto-grpc = "^1.33.1"
 pathspec = "^0.12.1"
 pexpect = "*"
+pillow = "^11.3.0"
 poetry = "^2.1.2"
 prompt-toolkit = "^3.0.50"
 protobuf = "^5.0.0,<6.0.0"
@@ -5413,6 +5482,7 @@ psutil = "*"
 pygithub = "^2.5.0"
 pyjwt = "^2.9.0"
 pylatexenc = "*"
+pypdf = "^6.0.0"
 PyPDF2 = "*"
 python-docx = "*"
 python-dotenv = "*"
@@ -5426,13 +5496,17 @@ pyyaml = "^6.0.2"
 qtconsole = "^5.6.1"
 rapidfuzz = "^3.9.0"
 redis = ">=5.2,<7.0"
+requests = "^2.32.5"
+setuptools = ">=78.1.1"
 shellingham = "^1.5.4"
-sse-starlette = "^2.1.3"
+sse-starlette = "^3.0.2"
+starlette = "^0.48.0"
 tenacity = ">=8.5,<10.0"
 termcolor = "*"
 toml = "*"
 tornado = "*"
 types-toml = "*"
+urllib3 = "^2.5.0"
 uvicorn = "*"
 whatthepatch = "^1.0.6"
 zope-interface = "7.2"
@@ -6471,11 +6545,12 @@ version = "2.22"
 description = "C parser in Python"
 optional = false
 python-versions = ">=3.8"
-groups = ["main"]
+groups = ["main", "test"]
 files = [
     {file = "pycparser-2.22-py3-none-any.whl", hash = "sha256:c3702b6d3dd8c7abc1afa565d7e63d53a1d0bd86cdc24edd75470f4de499cfcc"},
     {file = "pycparser-2.22.tar.gz", hash = "sha256:491c8be9c040f5390f5bf44a5b07752bd07f56edf992381b05c701439eec10f6"},
 ]
+markers = {test = "platform_python_implementation == \"CPython\" and sys_platform == \"win32\""}
 
 [[package]]
 name = "pydantic"
@@ -8265,7 +8340,7 @@ version = "80.9.0"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "test"]
 files = [
     {file = "setuptools-80.9.0-py3-none-any.whl", hash = "sha256:062d34222ad13e0cc312a4c02d73f059e86a4acbfbdea8f8f76b28c99f306922"},
     {file = "setuptools-80.9.0.tar.gz", hash = "sha256:f36b47402ecde768dbfafc46e8e4207b4360c654f1f3bb84475f0a28628fb19c"},
@@ -8631,14 +8706,14 @@ sqlcipher = ["sqlcipher3_binary"]
 
 [[package]]
 name = "sse-starlette"
-version = "2.4.1"
+version = "3.0.2"
 description = "SSE plugin for Starlette"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "sse_starlette-2.4.1-py3-none-any.whl", hash = "sha256:08b77ea898ab1a13a428b2b6f73cfe6d0e607a7b4e15b9bb23e4a37b087fd39a"},
-    {file = "sse_starlette-2.4.1.tar.gz", hash = "sha256:7c8a800a1ca343e9165fc06bbda45c78e4c6166320707ae30b416c42da070926"},
+    {file = "sse_starlette-3.0.2-py3-none-any.whl", hash = "sha256:16b7cbfddbcd4eaca11f7b586f3b8a080f1afe952c15813455b162edea619e5a"},
+    {file = "sse_starlette-3.0.2.tar.gz", hash = "sha256:ccd60b5765ebb3584d0de2d7a6e4f745672581de4f5005ab31c3a25d10b52b3a"},
 ]
 
 [package.dependencies]
@@ -8646,7 +8721,7 @@ anyio = ">=4.7.0"
 
 [package.extras]
 daphne = ["daphne (>=4.2.0)"]
-examples = ["aiosqlite (>=0.21.0)", "fastapi (>=0.115.12)", "sqlalchemy[asyncio,examples] (>=2.0.41)", "starlette (>=0.41.3)", "uvicorn (>=0.34.0)"]
+examples = ["aiosqlite (>=0.21.0)", "fastapi (>=0.115.12)", "sqlalchemy[asyncio] (>=2.0.41)", "starlette (>=0.41.3)", "uvicorn (>=0.34.0)"]
 granian = ["granian (>=2.3.1)"]
 uvicorn = ["uvicorn (>=0.34.0)"]
 
@@ -8702,14 +8777,14 @@ files = [
 
 [[package]]
 name = "starlette"
-version = "0.47.3"
+version = "0.48.0"
 description = "The little ASGI library that shines."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "starlette-0.47.3-py3-none-any.whl", hash = "sha256:89c0778ca62a76b826101e7c709e70680a1699ca7da6b44d38eb0a7e61fe4b51"},
-    {file = "starlette-0.47.3.tar.gz", hash = "sha256:6bc94f839cc176c4858894f1f8908f0ab79dfec1a6b8402f6da9be26ebea52e9"},
+    {file = "starlette-0.48.0-py3-none-any.whl", hash = "sha256:0764ca97b097582558ecb498132ed0c7d942f233f365b86ba37770e026510659"},
+    {file = "starlette-0.48.0.tar.gz", hash = "sha256:7e8cee469a8ab2352911528110ce9088fdc6a37d9876926e73da7ce4aa4c7a46"},
 ]
 
 [package.dependencies]
@@ -9838,13 +9913,32 @@ enabler = ["pytest-enabler (>=2.2)"]
 test = ["big-O", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more_itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
 type = ["pytest-mypy"]
 
+[[package]]
+name = "zope-event"
+version = "6.0"
+description = "Very basic event publishing system"
+optional = false
+python-versions = ">=3.9"
+groups = ["test"]
+files = [
+    {file = "zope_event-6.0-py3-none-any.whl", hash = "sha256:6f0922593407cc673e7d8766b492c519f91bdc99f3080fe43dcec0a800d682a3"},
+    {file = "zope_event-6.0.tar.gz", hash = "sha256:0ebac894fa7c5f8b7a89141c272133d8c1de6ddc75ea4b1f327f00d1f890df92"},
+]
+
+[package.dependencies]
+setuptools = ">=75.8.2"
+
+[package.extras]
+docs = ["Sphinx"]
+test = ["zope.testrunner (>=6.4)"]
+
 [[package]]
 name = "zope-interface"
 version = "7.2"
 description = "Interfaces for Python"
 optional = false
 python-versions = ">=3.8"
-groups = ["main"]
+groups = ["main", "test"]
 files = [
     {file = "zope.interface-7.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ce290e62229964715f1011c3dbeab7a4a1e4971fd6f31324c4519464473ef9f2"},
     {file = "zope.interface-7.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:05b910a5afe03256b58ab2ba6288960a2892dfeef01336dc4be6f1b9ed02ab0a"},
@@ -10008,4 +10102,4 @@ cffi = ["cffi (>=1.17) ; python_version >= \"3.13\" and platform_python_implemen
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.12,<3.14"
-content-hash = "5771671ef2acc36e7b0931c73fa035ca1d329e8dac6827f7a349e1a569c3fd23"
+content-hash = "8c460070dce6bdec5ee0ee7bc0c2246fcf2602d1e64a0867b4f5e3a0e334fe93"

enterprise/pyproject.toml

@@ -63,6 +63,7 @@ openai = "*"
 opencv-python = "*"
 pandas = "*"
 reportlab = "*"
+gevent = ">=24.2.1,<26.0.0"
 
 [tool.poetry-dynamic-versioning]
 enable = true
@@ -85,3 +86,7 @@ lint.pydocstyle.convention = "google"
 [tool.pytest.ini_options]
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "function"
+
+[tool.coverage.run]
+relative_files = true
+omit = [ "tests/*" ]

evaluation/benchmarks/multi_swe_bench/SWE-Gym.md

@@ -0,0 +1,152 @@
+<h1 align="center"> Training Software Engineering Agents and Verifiers with SWE-Gym </h1>
+
+A Multi-SWE-bench implementation of SWE-Gym.
+
+<p align="center">
+  <a href="https://www.jiayipan.com/" style="text-decoration: none;">Jiayi Pan<sup>*,1</sup></a>,
+  <a href="https://xwang.dev/" style="text-decoration: none;">Xingyao Wang<sup>*,2</sup></a>,
+  <a href="https://www.phontron.com/" style="text-decoration: none;">Graham Neubig<sup>3</sup></a>,
+  <a href="https://www.cs.toronto.edu/~ndjaitly/" style="text-decoration: none;">Navdeep Jaitly<sup>4</sup></a>,
+  <a href="https://blender.cs.illinois.edu/hengji.html" style="text-decoration: none;">Heng Ji<sup>2</sup></a>,
+  <a href="https://www.alanesuhr.com/" style="text-decoration: none;">Alane Suhr<sup>^,1</sup></a>,
+  <a href="https://dreasysnail.github.io/" style="text-decoration: none;">Yizhe Zhang<sup>^,4</sup></a>
+</p>
+
+<p align="center">
+  <sup>1</sup>UC Berkeley, <sup>2</sup>UIUC, <sup>3</sup>CMU, <sup>4</sup>Apple </br>
+  <sub><sup>*</sup>Equal contribution, <sup>^</sup>Equal supervision</sub>
+</p>
+
+<p align="center">
+<a href="https://arxiv.org/abs/2412.21139">📃 Paper</a>
+•
+<a href="https://huggingface.co/SWE-Gym" >🤗 Data & Models</a>
+</p>
+
+We present **SWE-Gym**, the first environment for training real-world software engineering agents.
+We use it to train strong LM agents that achieve state-of-the-art open results on SWE-Bench, with early, promising scaling characteristics as we increase training and inference-time compute.
+
+<p align="center">
+  <img src="https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/teaser.jpg?raw=true" width="100%" alt="teaser">
+</p>
+
+---
+# Run SWE-Gym with OpenHands
+
+The process of running SWE-Gym is very similar to how you'd run SWE-Bench evaluation.
+
+
+1. First, clone OpenHands repo `git clone https://github.com/All-Hands-AI/OpenHands.git`
+2. Then setup the repo following [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md)
+3. Then you can simply serve your own model as an OpenAI compatible endpoint, put those info in config.toml. You can do this by following instruction [here](../../README.md#setup).
+4. And then simply do the following to sample for 16x parallelism:
+
+```bash
+export ALLHANDS_API_KEY=ah-yourkey  # You don't need to set this when running these in local docker container
+./evaluation/benchmarks/multi_swe_bench/scripts/rollout_swegym.sh llm.mymodel-temp05 'train-t05' 16
+```
+
+NOTE: SWE-Gym sampling with parallelism is currently only tested with AllHands RemoteRuntime (limited beta). Fill [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply for access.
+
+
+5. When `rollout_swegym.sh` finishes, you will get a file called `output.with_completions.jsonl.gz`. Then you can use [`./scripts/swegym/convert_data.ipynb`](./scripts/swegym/convert_data.ipynb) to convert them into SFT data format.
+
+## Running the Jupyter Notebook
+
+To run the data conversion notebook, follow these steps:
+
+1. Navigate to the OpenHands repository root:
+```bash
+cd openhands_repo
+```
+
+2. Set the PYTHONPATH and start Jupyter notebook:
+```bash
+PYTHONPATH=$(pwd) jupyter notebook
+```
+
+3. In the Jupyter interface, navigate to `evaluation/benchmarks/swe_bench/scripts/swegym/convert_data.ipynb`
+
+4. Update the file paths in the notebook:
+   - Set `FILE_PATHS` to point to your `output.with_completions.jsonl.gz` files
+   - Set `YOUR_OUTPUT_FOLDER` to your desired output directory
+
+5. Run the notebook cells sequentially to process your data and generate the SFT training format.
+
+---
+# More info about SWE-Gym
+
+Progress in agents for software engineering has been limited by the lack of training environments that both include rigorous verification for reinforcement learning and cover the expansive tasks encountered in real-world repository-level engineering.
+
+We introduce SWE-Gym: An Open Environment for Training Software Engineering Agents & Verifiers.
+Our baselines achieve new open SOTA - 32%/26% on SWE-Bench Verified/Lite, with promising scaling trends.
+
+![SWE-Gym Scaling](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/scaling.jpg?raw=true)
+*SWE-Gym enables scalable improvements for software engineering agents at both training and inference time. Our current results is primarily bottlenecked by training and inference compute, rather than the size of our environment.*
+
+## SWE-Gym Environment
+
+We create SWE-Gym, the first environment for training SWE agents, with **2.4K real tasks from 11 Python repos** & a Lite split of 234 instances. SWE-Gym combines real-world Python tasks, repository context, executable environments, and test verification to train agents for solving software engineering problems.
+
+![SWE-Gym Repo Distribution](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/swe-gym.jpg?raw=true)
+
+
+## SWE-Gym trains LMs as agents
+
+When fine-tuned on less than 500 agent-environment interaction trajectories sampled from it from GPT-4o and Claude 3.5 Sonnet, we achieve **+14%** absolute gains on SWE-Bench Verified with an 32B LM-powered OpenHands agent.
+
+![OpenHands Performance diff before and after training](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/oh-agent.jpg?raw=true)
+
+
+## SWE-Gym enables self-improvement
+
+SWE-Gym is also effective across agent scaffolds. With rejection sampling fine-tuning and MoatlessTools scaffold, our 32B and 7B models achieve 20% and 10% respectively on SWE-Bench Lite through self-improvement.
+
+<p align="center">
+  <img src="https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/ml-agent.jpg?raw=true" width="80%" alt="Moatless self-improvement">
+</p>
+
+
+
+## SWE-Gym enables inference-time scaling
+
+SWE-Gym enables inference-time scaling through verifiers trained on agent trajectories.
+These verifiers identify most promising solutions via best-of-n selection, together with our learned agents, they achieve 32%/26% on SWE-Bench Verified/Lite, a new open SoTA.
+
+
+![Inference Time Scaling for Moatless Agent](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/inference-ml.jpg?raw=true)
+*Inference Time Scaling for Moatless Agent*
+
+![Inference Time Scaling for OpenHands Agent](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/inference-oh.jpg?raw=true)
+*Inference Time Scaling for OpenHands Agent*
+
+
+## Our baselines on SWE-Gym shows strong scaling trends
+
+Lastly, our ablations reveal strong scaling trends - performance is now bottlenecked by train and inference compute, rather than the size of our dataset. Pushing and improving these scaling trends further is an exciting direction for future work.
+
+![](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/scaling.jpg?raw=true)
+
+## Reproducing Results
+**The Dataset**
+
+To access SWE-Gym dataset, checkout our huggingface hub page [SWE-Gym](https://huggingface.co/SWE-Gym)
+
+The environment constants are currently saved at [SWE-Bench-Fork](https://github.com/SWE-Gym/SWE-Bench-Fork)
+
+We also have pre-built docker images for each instance under [xingyaoww/sweb.eval.x86_64](https://hub.docker.com/search?q=xingyaoww%2Fsweb.eval.x86_64.) prefix at docker hub.
+
+
+## 📚 Citation
+
+```bibtex
+@misc{pan2024trainingsoftwareengineeringagents,
+      title={Training Software Engineering Agents and Verifiers with SWE-Gym},
+      author={Jiayi Pan and Xingyao Wang and Graham Neubig and Navdeep Jaitly and Heng Ji and Alane Suhr and Yizhe Zhang},
+      year={2024},
+      eprint={2412.21139},
+      archivePrefix={arXiv},
+      primaryClass={cs.SE},
+      url={https://arxiv.org/abs/2412.21139},
+}
+```

evaluation/benchmarks/multi_swe_bench/run_infer.py

@@ -51,8 +51,8 @@ RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'tru
 
 # TODO: migrate all swe-bench docker to ghcr.io/openhands
 # TODO: 适应所有的语言
-DOCKER_IMAGE_PREFIX = os.environ.get('EVAL_DOCKER_IMAGE_PREFIX', '')
-LANGUAGE = os.environ.get('LANGUAGE', 'python')
+DOCKER_IMAGE_PREFIX = os.environ.get('EVAL_DOCKER_IMAGE_PREFIX', 'mswebench')
+LANGUAGE = os.environ.get('LANGUAGE', 'java')
 logger.info(f'Using docker image prefix: {DOCKER_IMAGE_PREFIX}')
 
 
@@ -305,31 +305,19 @@ def get_instance_docker_image(instance: pd.Series):
         instance_id = instance.get('instance_id', '')
         tag_suffix = instance_id.split('-')[-1] if instance_id else ''
         container_tag = f'pr-{tag_suffix}'
-        # pdb.set_trace()
-        return f'mswebench/{container_name}:{container_tag}'
-        # return "kong/insomnia:pr-8284"
-        # return "'sweb.eval.x86_64.local_insomnia"
-        # return "local_insomnia_why"
-        # return "local/kong-insomnia:pr-8117"
+        return f'{DOCKER_IMAGE_PREFIX}/{container_name}:{container_tag}'
 
 
 def get_config(
     instance: pd.Series,
     metadata: EvalMetadata,
 ) -> OpenHandsConfig:
-    SWE_BENCH_CONTAINER_IMAGE = 'ghcr.io/opendevin/eval-swe-bench:full-v1.2.1'
-    if USE_INSTANCE_IMAGE:
-        # We use a different instance image for the each instance of swe-bench eval
-        # base_container_image = get_instance_docker_image(instance['instance_id'])
-        base_container_image = get_instance_docker_image(instance)
-        logger.info(
-            f'Using instance container image: {base_container_image}. '
-            f'Please make sure this image exists. '
-            f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
-        )
-    else:
-        base_container_image = SWE_BENCH_CONTAINER_IMAGE
-        logger.info(f'Using swe-bench container image: {base_container_image}')
+    base_container_image = get_instance_docker_image(instance)
+    logger.info(
+        f'Using instance container image: {base_container_image}. '
+        f'Please make sure this image exists. '
+        f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
+    )
 
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = base_container_image
@@ -772,7 +760,6 @@ if __name__ == '__main__':
     parser.add_argument(
         '--dataset',
         type=str,
-        default='princeton-nlp/SWE-bench',
         help='data set to evaluate on, either full-test or lite-test',
     )
     parser.add_argument(
@@ -787,6 +774,7 @@ if __name__ == '__main__':
     # so we don't need to manage file uploading to OpenHands's repo
     # dataset = load_dataset(args.dataset, split=args.split)
     # dataset = load_dataset(args.dataset)
+    logger.info(f'Loading dataset {args.dataset} with split {args.split} ')
     dataset = load_dataset('json', data_files=args.dataset)
     dataset = dataset[args.split]
     swe_bench_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
@@ -839,7 +827,7 @@ if __name__ == '__main__':
         args.eval_num_workers,
         process_instance,
         timeout_seconds=120 * 60,  # 2 hour PER instance should be more than enough
-        max_retries=5,
+        max_retries=3,
     )
     # Check if any instances reached maximum retries
     check_maximum_retries_exceeded(metadata.eval_output_dir)

evaluation/benchmarks/multi_swe_bench/scripts/data/data_change.py

@@ -1,37 +1,54 @@
+import argparse
 import json
 
-input_file = 'XXX.jsonl'
-output_file = 'YYY.jsonl'
 
-with (
-    open(input_file, 'r', encoding='utf-8') as fin,
-    open(output_file, 'w', encoding='utf-8') as fout,
-):
-    for line in fin:
-        line = line.strip()
-        if not line:
-            continue
+def main(input_file, output_file):
+    with (
+        open(input_file, 'r', encoding='utf-8') as fin,
+        open(output_file, 'w', encoding='utf-8') as fout,
+    ):
+        for line in fin:
+            line = line.strip()
+            if not line:
+                continue
 
-        data = json.loads(line)
-        item = data
+            data = json.loads(line)
+            item = data
 
-        # 提取原始数据
-        org = item.get('org', '')
-        repo = item.get('repo', '')
-        number = str(item.get('number', ''))
+            # Skip instances that don't have resolved_issues or have empty resolved_issues
+            if not item.get('resolved_issues') or len(item['resolved_issues']) == 0:
+                print(
+                    f'Skipping instance {item.get("org", "")}/{item.get("repo", "")}-{item.get("number", "")} - no resolved_issues'
+                )
+                continue
 
-        new_item = {}
-        new_item['repo'] = f'{org}/{repo}'
-        new_item['instance_id'] = f'{org}__{repo}-{number}'
-        new_item['problem_statement'] = (
-            item['resolved_issues'][0].get('title', '')
-            + '\n'
-            + item['resolved_issues'][0].get('body', '')
-        )
-        new_item['FAIL_TO_PASS'] = []
-        new_item['PASS_TO_PASS'] = []
-        new_item['base_commit'] = item['base'].get('sha', '')
-        new_item['version'] = '0.1'  # depends
+            # 提取原始数据
+            org = item.get('org', '')
+            repo = item.get('repo', '')
+            number = str(item.get('number', ''))
 
-        output_data = new_item
-        fout.write(json.dumps(output_data, ensure_ascii=False) + '\n')
+            new_item = {}
+            new_item['repo'] = f'{org}/{repo}'
+            new_item['instance_id'] = f'{org}__{repo}-{number}'
+
+            # Get the first resolved issue
+            resolved_issue = item['resolved_issues'][0]
+            title = resolved_issue.get('title') or ''
+            body = resolved_issue.get('body') or ''
+
+            new_item['problem_statement'] = title + '\n' + body
+            new_item['FAIL_TO_PASS'] = []
+            new_item['PASS_TO_PASS'] = []
+            new_item['base_commit'] = item['base'].get('sha', '')
+            new_item['version'] = '0.1'  # depends
+
+            output_data = new_item
+            fout.write(json.dumps(output_data, ensure_ascii=False) + '\n')
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--input', required=True, help='Input .jsonl file path')
+    parser.add_argument('--output', required=True, help='Output .jsonl file path')
+    args = parser.parse_args()
+    main(args.input, args.output)

evaluation/benchmarks/multi_swe_bench/scripts/eval/combine_final_completions.py

@@ -0,0 +1,69 @@
+import argparse
+import gzip
+import json
+import os
+from glob import glob
+
+from tqdm import tqdm
+
+tqdm.pandas()
+
+
+# Load trajectories for resolved instances
+def load_completions(output_dir: str, instance_id: str):
+    glob_path = os.path.join(output_dir, 'llm_completions', instance_id, '*.json')
+    files = sorted(glob(glob_path))  # this is ascending order
+    # pick the last file (last turn)
+    try:
+        file_path = files[-1]
+    except IndexError:
+        # print(f'No files found for instance {instance_id}: files={files}')
+        return None
+    with open(file_path, 'r') as f:
+        result = json.load(f)
+    # create messages
+    messages = result['messages']
+    messages.append(result['response']['choices'][0]['message'])
+    tools = result['kwargs'].get('tools', [])
+    return {
+        'messages': messages,
+        'tools': tools,
+    }
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument('jsonl_path', type=str)
+args = parser.parse_args()
+
+output_dir = os.path.dirname(args.jsonl_path)
+output_path = os.path.join(output_dir, 'output.with_completions.jsonl.gz')
+
+# Check if output would be different from input
+needs_update = False
+with open(args.jsonl_path, 'r') as f_in:
+    for line in tqdm(f_in, desc='Checking for changes'):
+        data = json.loads(line)
+        new_completions = load_completions(output_dir, data['instance_id'])
+        current_completions = data.get('raw_completions')
+        if current_completions != new_completions:
+            needs_update = True
+            break
+
+if not needs_update:
+    print('No updates required. Skipping file update.')
+    exit(0)
+
+if os.path.exists(output_path):
+    print(f'Output file already exists at {output_path}, overwriting? (y/n)')
+    if input() != 'y':
+        print('Exiting...')
+        exit(0)
+
+# Process line by line
+with open(args.jsonl_path, 'r') as f_in, gzip.open(output_path, 'wt') as f_out:
+    for line in tqdm(f_in):
+        data = json.loads(line)
+        data['raw_completions'] = load_completions(output_dir, data['instance_id'])
+        f_out.write(json.dumps(data) + '\n')
+
+print(f'Saved compressed output to {output_path}')

evaluation/benchmarks/multi_swe_bench/scripts/eval/convert.py

@@ -1,13 +1,11 @@
+import argparse
 import json
 import re
 
-IN_FILE = 'output.jsonl'
-OUT_FILE = 'patch.jsonl'
 
-
-def main():
-    with open(IN_FILE, 'r') as fin:
-        with open(OUT_FILE, 'w') as fout:
+def main(input_file, output_file):
+    with open(input_file, 'r') as fin:
+        with open(output_file, 'w') as fout:
             for line in fin:
                 data = json.loads(line)
                 groups = re.match(r'(.*)__(.*)-(.*)', data['instance_id'])
@@ -15,10 +13,14 @@ def main():
                     'org': groups.group(1),
                     'repo': groups.group(2),
                     'number': groups.group(3),
-                    'fix_patch': data['test_result']['git_patch'],
+                    'fix_patch': data.get('test_result', {}).get('git_patch', '') or '',
                 }
                 fout.write(json.dumps(patch) + '\n')
 
 
 if __name__ == '__main__':
-    main()
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--input', required=True, help='Input .jsonl file path')
+    parser.add_argument('--output', required=True, help='Output .jsonl file path')
+    args = parser.parse_args()
+    main(args.input, args.output)

evaluation/benchmarks/multi_swe_bench/scripts/eval/update_multi_swe_bench_config.py

@@ -0,0 +1,70 @@
+import argparse
+import json
+import os
+import subprocess
+
+
+def update_multi_swe_config(output_jsonl_path, config_path, dataset):
+    path_to_parent = os.path.dirname(os.path.abspath(output_jsonl_path))
+    converted_path = os.path.join(path_to_parent, 'output_converted.jsonl')
+
+    # Run the conversion script
+    subprocess.run(
+        [
+            'python3',
+            './evaluation/benchmarks/multi_swe_bench/scripts/eval/convert.py',
+            '--input',
+            output_jsonl_path,
+            '--output',
+            converted_path,
+        ],
+        check=True,
+    )
+
+    # Create required directories
+    os.makedirs(os.path.join(path_to_parent, 'eval_files', 'dataset'), exist_ok=True)
+    os.makedirs(os.path.join(path_to_parent, 'eval_files', 'workdir'), exist_ok=True)
+    os.makedirs(os.path.join(path_to_parent, 'eval_files', 'repos'), exist_ok=True)
+    os.makedirs(os.path.join(path_to_parent, 'eval_files', 'logs'), exist_ok=True)
+
+    # Prepare config dict
+    config = {
+        'mode': 'evaluation',
+        'workdir': os.path.join(path_to_parent, 'eval_files', 'workdir'),
+        'patch_files': [converted_path],
+        'dataset_files': [dataset],
+        'force_build': True,
+        'output_dir': os.path.join(path_to_parent, 'eval_files', 'dataset'),
+        'specifics': [],
+        'skips': [],
+        'repo_dir': os.path.join(path_to_parent, 'eval_files', 'repos'),
+        'need_clone': True,
+        'global_env': [],
+        'clear_env': True,
+        'stop_on_error': False,
+        'max_workers': 5,
+        'max_workers_build_image': 5,
+        'max_workers_run_instance': 5,
+        'log_dir': os.path.join(path_to_parent, 'eval_files', 'logs'),
+        'log_level': 'DEBUG',
+        'fix_patch_run_cmd': (
+            'bash -c "apt update ; apt install -y patch ; '
+            "sed -i 's@git apply.*@patch --batch --fuzz=5 -p1 -i /home/test.patch;"
+            'patch --batch --fuzz=5 -p1 -i /home/fix.patch@g\' /home/fix-run.sh ; chmod +x /home/*.sh  ; /home/fix-run.sh"'
+        ),
+    }
+
+    # Save to multibench.config
+    os.makedirs(os.path.dirname(config_path), exist_ok=True)
+    with open(config_path, 'w') as f:
+        json.dump(config, f, indent=4)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--input', required=True, help='Path to input file')
+    parser.add_argument('--output', required=True, help='Path to create config')
+    parser.add_argument('--dataset', required=True, help='Path to dataset')
+    args = parser.parse_args()
+
+    update_multi_swe_config(args.input, args.output, args.dataset)

evaluation/benchmarks/multi_swe_bench/scripts/eval/update_output_with_eval.py

@@ -0,0 +1,176 @@
+import argparse
+import json
+import os
+from collections import defaultdict
+
+from tqdm import tqdm
+
+parser = argparse.ArgumentParser()
+parser.add_argument('input_file', type=str)
+parser.add_argument(
+    '--force',
+    action='store_true',
+    help='Force update all reports even if no changes are detected',
+)
+parser.add_argument(
+    '--overwrite-backup',
+    action='store_true',
+    help='Automatically overwrite existing backup files without prompting',
+)
+args = parser.parse_args()
+
+dirname = os.path.dirname(args.input_file)
+
+# Initialize counters and data structures
+instance_id_to_status = defaultdict(
+    lambda: {
+        'empty_generation': False,
+        'resolved': False,
+        'failed_apply_patch': False,
+        'error_eval': False,
+        'test_timeout': False,
+    }
+)
+
+# Process official report if it exists
+swebench_official_report_json = os.path.join(
+    dirname, 'eval_files/dataset/final_report.json'
+)
+openhands_remote_report_jsonl = args.input_file.replace(
+    '.jsonl', '.swebench_eval.jsonl'
+)
+
+if os.path.exists(swebench_official_report_json):
+    output_md_filepath = os.path.join(dirname, 'README.md')
+    with open(swebench_official_report_json, 'r') as f:
+        report = json.load(f)
+
+    # Convert instance IDs from "repo/name:pr-123" format to "repo__name-123" format
+    def convert_instance_id(instance_id):
+        """Convert instance ID from slash/colon-pr format to double underscore/dash format."""
+        if '/' in instance_id and ':pr-' in instance_id:
+            # Split on '/' and ':pr-'
+            parts = instance_id.split('/')
+            if len(parts) == 2:
+                repo_part = parts[0]
+                name_and_pr = parts[1]
+                if ':pr-' in name_and_pr:
+                    name, pr_number = name_and_pr.split(':pr-')
+                    return f'{repo_part}__{name}-{pr_number}'
+        return instance_id
+
+    # Convert all instance ID lists in the report
+    for key in [
+        'resolved_ids',
+        'unresolved_ids',
+        'error_ids',
+        'empty_patch_ids',
+        'incomplete_ids',
+    ]:
+        if key in report:
+            report[key] = [
+                convert_instance_id(instance_id) for instance_id in report[key]
+            ]
+
+    output_md = (
+        '# Multi-SWE-bench Report\n'
+        'This folder contains the evaluation results of the SWE-bench using the [official evaluation docker containerization](https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md#choosing-the-right-cache_level).\n\n'
+        '## Summary\n'
+        f'- total instances: {report["total_instances"]}\n'
+        f'- submitted instances: {report["submitted_instances"]}\n'
+        f'- completed instances: {report["completed_instances"]}\n'
+        f'- empty patch instances: {report["empty_patch_instances"]}\n'
+        f'- resolved instances: {report["resolved_instances"]}\n'
+        f'- unresolved instances: {report["unresolved_instances"]}\n'
+        f'- error instances: {report["error_instances"]}\n'
+    )
+
+    output_md += '\n## Resolved Instances\n'
+    # instance_id to status
+    for instance_id in report['resolved_ids']:
+        instance_id_to_status[instance_id]['resolved'] = True
+        output_md += (
+            f'- [{instance_id}](./eval_outputs/{instance_id}/run_instance.log)\n'
+        )
+
+    output_md += '\n## Unresolved Instances\n'
+    for instance_id in report['unresolved_ids']:
+        output_md += (
+            f'- [{instance_id}](./eval_outputs/{instance_id}/run_instance.log)\n'
+        )
+
+    output_md += '\n## Error Instances\n'
+    for instance_id in report['error_ids']:
+        instance_id_to_status[instance_id]['error_eval'] = True
+        output_md += (
+            f'- [{instance_id}](./eval_outputs/{instance_id}/run_instance.log)\n'
+        )
+
+    output_md += '\n## Empty Patch Instances\n'
+    for instance_id in report['empty_patch_ids']:
+        instance_id_to_status[instance_id]['empty_generation'] = True
+        output_md += (
+            f'- [{instance_id}](./eval_outputs/{instance_id}/run_instance.log)\n'
+        )
+
+    output_md += '\n## Incomplete Instances\n'
+    for instance_id in report['incomplete_ids']:
+        output_md += (
+            f'- [{instance_id}](./eval_outputs/{instance_id}/run_instance.log)\n'
+        )
+
+    with open(output_md_filepath, 'w') as f:
+        f.write(output_md)
+
+else:
+    print(
+        f'No report file found: Both {swebench_official_report_json} and {openhands_remote_report_jsonl} do not exist.'
+    )
+    exit()
+
+# Before backup and update, check if any changes would be made (unless --force is used)
+if not args.force:
+    needs_update = False
+    with open(args.input_file, 'r') as infile:
+        for line in tqdm(infile, desc='Checking for changes'):
+            data = json.loads(line)
+            instance_id = data['instance_id']
+            current_report = data.get('report', {})
+            new_report = instance_id_to_status[
+                instance_id
+            ]  # if no report, it's not resolved
+            if current_report != new_report:
+                needs_update = True
+                break
+
+    if not needs_update:
+        print('No updates detected. Skipping file update.')
+        exit()
+else:
+    print('Force flag enabled. Updating all reports regardless of changes.')
+
+# Backup and update the original file row by row
+if os.path.exists(args.input_file + '.bak'):
+    if args.overwrite_backup:
+        print(
+            'Existing backup file found. Overwriting automatically due to --overwrite-backup flag.'
+        )
+        os.remove(args.input_file + '.bak')
+    else:
+        conf = input('Existing backup file found. Do you want to overwrite it? (y/n)')
+        if conf != 'y':
+            exit()
+        os.remove(args.input_file + '.bak')
+
+os.rename(args.input_file, args.input_file + '.bak')
+
+# Process and write file row by row
+with (
+    open(args.input_file + '.bak', 'r') as infile,
+    open(args.input_file, 'w') as outfile,
+):
+    for line in tqdm(infile, desc='Updating output file'):
+        data = json.loads(line)
+        instance_id = data['instance_id']
+        data['report'] = instance_id_to_status[instance_id]
+        outfile.write(json.dumps(data) + '\n')

evaluation/benchmarks/multi_swe_bench/scripts/rollout_multi_swegym.sh

@@ -0,0 +1,146 @@
+#!/bin/bash
+
+# NOTE: this script is for rolling out the Multi-SWE-Gym dataset for **TRAINING**
+# For more information, please refer to
+# 1. the Github Repo: https://github.com/SWE-Gym/SWE-Gym
+# 2. the paper: https://arxiv.org/abs/2412.21139
+
+MODEL=$1  # eg your llm config name in config.toml (eg: "llm.claude-3-5-sonnet-20241022-t05")
+EXP_NAME=$2 # "train-t05"
+EVAL_DATASET=$3  # path to original dataset (jsonl file)
+N_WORKERS=${4:-64}
+N_RUNS=${5:-1}
+
+export EXP_NAME=$EXP_NAME
+# use 2x resources for rollout since some codebases are pretty resource-intensive
+export DEFAULT_RUNTIME_RESOURCE_FACTOR=2
+echo "MODEL: $MODEL"
+echo "EXP_NAME: $EXP_NAME"
+echo "EVAL_DATASET: $EVAL_DATASET"
+# Generate DATASET path by adding _with_runtime_ before .jsonl extension
+DATASET="${EVAL_DATASET%.jsonl}_with_runtime_.jsonl"  # path to converted dataset
+
+# Create the converted dataset file
+echo "Creating converted dataset at: $DATASET"
+poetry run python ./evaluation/benchmarks/multi_swe_bench/scripts/data/data_change.py --input "$EVAL_DATASET" --output "$DATASET"
+
+SPLIT="train"
+export LANGUAGE=java
+
+if [ -z "$ALLHANDS_API_KEY" ] || [ "$RUNTIME" != "remote" ]; then
+    echo "ALLHANDS_API_KEY is not set or RUNTIME is not set to remote. Will rollout and evaluate locally using Docker. WARNING: A large value of N_WORKERS will result in a large number of Docker containers being spun up and may crash your machine."
+    export RUNTIME=docker
+else
+    echo "ALLHANDS_API_KEY is set and RUNTIME is set to remote. Continuing rollout and evaluation with remote runtime..."
+    export SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev"
+fi
+
+#EVAL_LIMIT=3000
+MAX_ITER=100
+
+
+# ===== Run inference =====
+source "evaluation/utils/version_control.sh"
+get_openhands_version
+
+echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "MODEL_CONFIG: $MODEL_CONFIG"
+echo "DATASET: $DATASET"
+echo "EVAL_DOCKER_IMAGE_PREFIX: $EVAL_DOCKER_IMAGE_PREFIX"
+
+# Default to NOT use Hint
+export USE_INSTANCE_IMAGE=true
+export USE_HINT_TEXT=false
+export RUN_WITH_BROWSING=false
+echo "USE_HINT_TEXT: $USE_HINT_TEXT"
+EVAL_NOTE="$OPENHANDS_VERSION-no-hint-$EXP_NAME"
+
+function run_eval() {
+  local eval_note=$1
+  export LANGUAGE=java
+  echo "About to run command"
+  COMMAND="EVAL_DOCKER_IMAGE_PREFIX=$EVAL_DOCKER_IMAGE_PREFIX; LANGUAGE=java;
+    poetry run python evaluation/benchmarks/multi_swe_bench/run_infer.py \
+    --agent-cls CodeActAgent \
+    --llm-config $MODEL \
+    --max-iterations $MAX_ITER \
+    --eval-num-workers $N_WORKERS \
+    --eval-note $eval_note \
+    --dataset $DATASET \
+    --split $SPLIT"
+
+  echo "Running command: $COMMAND"
+  if [ -n "$EVAL_LIMIT" ]; then
+    echo "EVAL_LIMIT: $EVAL_LIMIT"
+    COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+  fi
+
+  # Run the command
+  eval $COMMAND
+}
+
+for run_idx in $(seq 1 $N_RUNS); do
+
+    while true; do
+        echo "### Running inference... ###"
+        unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
+        current_eval_note="$EVAL_NOTE-run_$run_idx"
+        echo "EVAL_NOTE: $current_eval_note"
+        echo "DATASET command: $DATASET"
+        #INFER_OUTPUT=$(run_eval $current_eval_note)
+        INFER_OUTPUT=$(run_eval $current_eval_note | tee /dev/stderr)
+        INFER_STATUS=$?  # Capture the exit status of run_infer.sh
+        echo "INFER_STATUS: $INFER_STATUS"
+
+        echo "### Cleaning up remote runtime... ###"
+        ./evaluation/utils/scripts/cleanup_remote_runtime.sh
+
+        if [ $INFER_STATUS -eq 0 ]; then
+            echo "### Inference completed successfully. ###"
+            break
+        else
+            echo "### Inference failed with exit code $INFER_STATUS. Retrying... ###"
+        fi
+    done
+
+    # Extract the output directory using the special delimiters
+    OUTPUT_FILE=$(echo "$INFER_OUTPUT" | grep -o '### OUTPUT FILE:.* ###' | sed 's/### OUTPUT FILE: \(.*\) ###/\1/')
+    echo "Got OUTPUT_FILE: $OUTPUT_FILE"
+
+    while true; do
+        echo "### Evaluating on $OUTPUT_FILE ... ###"
+        OUTPUT_CONFIG_FILE="${OUTPUT_FILE%.jsonl}_config.json"
+        export EVAL_SKIP_BUILD_ERRORS=true
+        pip install multi-swe-bench --quiet --disable-pip-version-check > /dev/null 2>&1
+        COMMAND="poetry run python ./evaluation/benchmarks/multi_swe_bench/scripts/eval/update_multi_swe_bench_config.py --input $OUTPUT_FILE --output $OUTPUT_CONFIG_FILE --dataset $EVAL_DATASET;
+        python -m multi_swe_bench.harness.run_evaluation --config $OUTPUT_CONFIG_FILE
+        "
+
+        if [ -n "$EVAL_LIMIT" ]; then
+        echo "EVAL_LIMIT: $EVAL_LIMIT"
+        COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+        fi
+        echo "Running command: $COMMAND"
+        # Run the command
+        eval $COMMAND
+        EVAL_STATUS=$?
+        if [ $EVAL_STATUS -eq 0 ]; then
+            echo "### Evaluation completed successfully. ###"
+            break
+        else
+            echo "### Evaluation failed with exit code $EVAL_STATUS. Retrying... ###"
+        fi
+
+        ./evaluation/utils/scripts/cleanup_remote_runtime.sh
+    done
+
+    # update the output with evaluation results
+    echo "### Updating the output with evaluation results... ###"
+    poetry run python evaluation/benchmarks/multi_swe_bench/scripts/eval/update_output_with_eval.py $OUTPUT_FILE
+
+    echo "### Combining the final completions... ###"
+    poetry run python evaluation/benchmarks/multi_swe_bench/scripts/eval/combine_final_completions.py $OUTPUT_FILE
+
+    echo "### DONE for run $run_idx! ###"
+    echo "You can find the final output at $(dirname $OUTPUT_FILE)/$FINAL_OUTPUT_FILE"
+done

evaluation/benchmarks/multi_swe_bench/scripts/run_infer.sh

@@ -47,8 +47,8 @@ if [ -z "$DATASET" ]; then
 fi
 
 if [ -z "$LANGUAGE" ]; then
-  echo "LANUGUAGE not specified, use default python"
-  LANGUAGE="python"
+  echo "LANGUAGE not specified, use default python"
+  LANGUAGE="java"
 fi
 
 if [ -z "$SPLIT" ]; then
@@ -69,10 +69,10 @@ fi
 
 if [ -z "$EVAL_DOCKER_IMAGE_PREFIX" ]; then
   if [ "$LANGUAGE" = "python" ]; then
-  echo "EVAL_DOCKER_IMAGE_PREFIX is docker.io/xingyaoww/ as default as LANUGUAGE is python"
+  echo "EVAL_DOCKER_IMAGE_PREFIX is docker.io/xingyaoww/ as default as LANGUAGE is python"
     EVAL_DOCKER_IMAGE_PREFIX="docker.io/xingyaoww/"
   elif [ "$LANGUAGE" = "java" ]; then
-  echo "EVAL_DOCKER_IMAGE_PREFIX is java_verified as LANUGUAGE is java"
+  echo "EVAL_DOCKER_IMAGE_PREFIX is empty as LANGUAGE is java"
     EVAL_DOCKER_IMAGE_PREFIX=""
   fi
 fi

evaluation/benchmarks/multi_swe_bench/scripts/swegym/convert_data.ipynb

@@ -0,0 +1,344 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "import pandas as pd\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "tqdm.pandas()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 1. Load raw data and convert to training data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gzip\n",
+    "import json\n",
+    "\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "FILE_PATHS = [\n",
+    "    'YOURPATH-no-hint-train-t05-run_1/output.with_completions.jsonl.gz',\n",
+    "    'YOURPATH-no-hint-train-t05-run_2/output.with_completions.jsonl.gz',\n",
+    "]\n",
+    "\n",
+    "# More memory efficient for large files\n",
+    "# Initialize lists to store the data\n",
+    "data = []\n",
+    "\n",
+    "\n",
+    "# Read file line by line\n",
+    "for FILE_PATH in FILE_PATHS:\n",
+    "    with gzip.open(FILE_PATH, 'rb') as f:  # Use 'rb' for gzipped files\n",
+    "        for i, line in tqdm(\n",
+    "            enumerate(f), desc=f'Processing {FILE_PATH.split(\"/\")[-1]}'\n",
+    "        ):\n",
+    "            # Parse only the fields we need\n",
+    "            raw_data = json.loads(line)\n",
+    "            data.append(\n",
+    "                {\n",
+    "                    'resolved': raw_data['report']['resolved'],\n",
+    "                    'messages': raw_data['raw_completions']['messages']\n",
+    "                    if raw_data['raw_completions'] is not None\n",
+    "                    else None,\n",
+    "                    'git_patch': raw_data['test_result'].get('git_patch', ''),\n",
+    "                    'tools': raw_data['raw_completions']['tools']\n",
+    "                    if raw_data['raw_completions'] is not None\n",
+    "                    and 'tools' in raw_data['raw_completions']\n",
+    "                    else None,\n",
+    "                }\n",
+    "            )\n",
+    "\n",
+    "# Convert to DataFrame after collecting all data\n",
+    "df = pd.DataFrame(data)\n",
+    "print(f'#total amount of data={len(df)}')\n",
+    "df = df[~df['messages'].isna()]\n",
+    "print(f'#total amount of data after removing nan={len(df)}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Filter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _contains_multiple_tool_calls(messages: list[dict]) -> bool:\n",
+    "    return any(\n",
+    "        message.get('tool_calls') and len(message['tool_calls']) > 1\n",
+    "        for message in messages\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "df['contains_multiple_tool_calls'] = df['messages'].apply(_contains_multiple_tool_calls)\n",
+    "display(df.groupby(['contains_multiple_tool_calls'])['resolved'].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "import copy\n",
+    "\n",
+    "# Convert function calling messages to non-function calling messages\n",
+    "from openhands.llm.fn_call_converter import (\n",
+    "    FunctionCallConversionError,\n",
+    "    convert_fncall_messages_to_non_fncall_messages,\n",
+    "    convert_from_multiple_tool_calls_to_single_tool_call_messages,\n",
+    ")\n",
+    "\n",
+    "total_failed = 0\n",
+    "\n",
+    "\n",
+    "def _convert_messages(messages: list[dict], tools: list[dict]) -> list[dict]:\n",
+    "    global total_failed\n",
+    "    message_copy = copy.deepcopy(messages)\n",
+    "    for message in message_copy:\n",
+    "        if message['content'] is None:\n",
+    "            message['content'] = ''\n",
+    "    try:\n",
+    "        return convert_fncall_messages_to_non_fncall_messages(\n",
+    "            message_copy, tools, add_in_context_learning_example=False\n",
+    "        )\n",
+    "    except FunctionCallConversionError:\n",
+    "        total_failed += 1\n",
+    "        # print(f'Failed to convert messages: {messages}\\nTools: {tools}')\n",
+    "        # traceback.print_exc()\n",
+    "        return None\n",
+    "\n",
+    "\n",
+    "df['converted_messages'] = df.apply(\n",
+    "    lambda row: convert_from_multiple_tool_calls_to_single_tool_call_messages(\n",
+    "        row['messages'], ignore_final_tool_result=True\n",
+    "    ),\n",
+    "    axis=1,\n",
+    ")\n",
+    "df['nonfncall_messages'] = df.apply(\n",
+    "    lambda row: _convert_messages(row['converted_messages'], row['tools']), axis=1\n",
+    ")\n",
+    "print('total nan', df['nonfncall_messages'].isna().sum())\n",
+    "df = df[~df['nonfncall_messages'].isna()]\n",
+    "print(df['nonfncall_messages'].iloc[0])\n",
+    "\n",
+    "print(f'Total failed: {total_failed}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Tokenization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pandarallel import pandarallel\n",
+    "from transformers import AutoTokenizer\n",
+    "\n",
+    "os.environ['TOKENIZERS_PARALLELISM'] = 'false'\n",
+    "pandarallel.initialize(progress_bar=True, verbose=1, nb_workers=16)\n",
+    "tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen2.5-7B-Instruct')\n",
+    "\n",
+    "\n",
+    "def clean_messages(messages):\n",
+    "    clean = []\n",
+    "    for msg in messages:\n",
+    "        if not isinstance(msg, dict):\n",
+    "            continue\n",
+    "        role = msg.get('role')\n",
+    "        content = msg.get('content')\n",
+    "        if isinstance(content, str):\n",
+    "            text = content\n",
+    "        elif isinstance(content, dict):\n",
+    "            text = content.get('text')\n",
+    "        elif (\n",
+    "            isinstance(content, list)\n",
+    "            and len(content) == 1\n",
+    "            and isinstance(content[0], dict)\n",
+    "        ):\n",
+    "            text = content[0].get('text')\n",
+    "        else:\n",
+    "            print(f'Format not accepted {content}')\n",
+    "        clean.append({'role': role, 'content': text})\n",
+    "    return clean\n",
+    "\n",
+    "\n",
+    "# Step 1: Clean the messages\n",
+    "df['nonfncall_messages'] = df['nonfncall_messages'].apply(clean_messages)\n",
+    "\n",
+    "# Step 2: Compute token count\n",
+    "df['n_tokens'] = df['nonfncall_messages'].parallel_apply(\n",
+    "    lambda x: len(tokenizer.apply_chat_template(x))\n",
+    ")\n",
+    "\n",
+    "# print(df['nonfncall_messages'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(f'BEFORE: #total={len(df)}')\n",
+    "df_selected = df[df['n_tokens'] < 131072]\n",
+    "print(f'AFTER(truncated to 128k): #total={len(df_selected)}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected['n_tokens'].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ecdf of n_tokens\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "\n",
+    "display(df.groupby(['resolved'])['n_tokens'].describe())\n",
+    "sns.ecdfplot(x='n_tokens', data=df, hue='resolved')\n",
+    "plt.show()\n",
+    "\n",
+    "print(f'#total={len(df)}')\n",
+    "df_selected = df[df['n_tokens'] < 131072]\n",
+    "print(f'#selected={len(df_selected)}')\n",
+    "display(df_selected.groupby(['resolved'])['n_tokens'].describe())\n",
+    "sns.ecdfplot(x='n_tokens', data=df_selected, hue='resolved')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected[~df_selected['resolved']]['n_tokens'].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected['resolved'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected.groupby(['resolved'])['n_tokens'].describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Save Resolved Messages for SFT"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Flatten messages and change format to {\"content\": \"\", \"role\": \"\"}\n",
+    "df_selected[df_selected['resolved']][['nonfncall_messages']].rename(\n",
+    "    columns={'nonfncall_messages': 'messages'}\n",
+    ").to_json(\n",
+    "    os.path.join(\n",
+    "        'PATH_TO_FILE',\n",
+    "        f'policy_traj_128k_swegym_{df_selected[\"resolved\"].value_counts()[True]}i.jsonl',\n",
+    "    ),\n",
+    "    lines=True,\n",
+    "    orient='records',\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

evaluation/benchmarks/swe_perf/README.md

@@ -0,0 +1,81 @@
+# SWE-Perf Evaluation
+
+This folder contains the OpenHands inference generation of the [SWE-Perf benchmark](https://swe-perf.github.io/) ([paper](https://arxiv.org/pdf/2507.12415v1)).
+
+The evaluation consists of three steps:
+
+1. Environment setup: [install python environment](../../README.md#development-environment) and [configure LLM config](../../README.md#configure-openhands-and-your-llm).
+2. [Run inference](#running-inference-locally-with-docker): Generate a edit patch for each Github issue
+3. [Evaluate patches](#evaluate-generated-patches)
+
+## Setup Environment and LLM Configuration
+
+Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
+
+## Running inference Locally with Docker
+
+Make sure your Docker daemon is running, and you have ample disk space (at least 200-500GB, depends on the SWE-PErf set you are running on) for the instance-level docker image.
+
+When the `run_infer.sh` script is started, it will automatically pull the relevant SWE-Perf images.
+For example, for instance ID `scikit-learn_scikit-learn-11674`, it will try to pull our pre-build docker image `betty1202/sweb.eval.x86_64.scikit-learn_s_scikit-learn-11674` from DockerHub.
+This image will be used create an OpenHands runtime image where the agent will operate on.
+
+```bash
+./evaluation/benchmarks/swe_perf/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split] [n_runs] [mode]
+
+# Example
+./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 500 100 1 SWE-Perf/SWE-Perf test
+```
+
+where `model_config` is mandatory, and the rest are optional.
+
+- `model_config`, e.g. `eval_gpt4_1106_preview`, is the config group name for your
+LLM settings, as defined in your `config.toml`.
+- `git-version`, e.g. `HEAD`, is the git commit hash of the OpenHands version you would
+like to evaluate. It could also be a release tag like `0.6.2`.
+- `agent`, e.g. `CodeActAgent`, is the name of the agent for benchmarks, defaulting
+to `CodeActAgent`.
+- `eval_limit`, e.g. `10`, limits the evaluation to the first `eval_limit` instances. By
+default, the script evaluates the entire SWE-Perf test set (140 issues). Note:
+in order to use `eval_limit`, you must also set `agent`.
+- `max_iter`, e.g. `20`, is the maximum number of iterations for the agent to run. By
+default, it is set to 100.
+- `num_workers`, e.g. `3`, is the number of parallel workers to run the evaluation. By
+default, it is set to 1.
+- `dataset`, a huggingface dataset name. e.g. `SWE-Perf/SWE-Perf`, specifies which dataset to evaluate on.
+- `dataset_split`, split for the huggingface dataset. e.g., `test`, `dev`. Default to `test`.
+
+- `n_runs`, e.g. `3`, is the number of times to run the evaluation. Default is 1.
+- `mode`, e.g. `swt`, `swt-ci`, or `swe`, specifies the evaluation mode. Default is `swe`.
+
+> [!CAUTION]
+> Setting `num_workers` larger than 1 is not officially tested, YMMV.
+
+
+Let's say you'd like to run 10 instances using `llm.eval_gpt4_1106_preview` and CodeActAgent,
+
+then your command would be:
+
+```bash
+./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 10
+```
+
+## Evaluate Generated Patches
+
+
+To evaluate the generated patch, follow these steps:
+
+### 1. Convert output to the evaluation standard format
+Run the following command:
+```bash
+python -m evaluation.benchmarks.swe_perf.format_conversion \
+    --input_path [input_path] \
+    --output_path [output_path]
+```
+
+* `input_path`: Path to the raw generated patch file.
+* `output_path`: Path where the converted file will be saved.
+
+### 2. Run the SWE-Perf benchmark official evaluation
+
+Once the output is converted, use the [official SWE-Perf benchmark evaluation](https://github.com/SWE-Perf/SWE-Perf/tree/main/evaluation) to evaluate it.

evaluation/benchmarks/swe_perf/binary_patch_utils.py

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

evaluation/benchmarks/swe_perf/format_conversion.py

@@ -0,0 +1,45 @@
+import json
+import os
+from argparse import ArgumentParser
+
+parser = ArgumentParser()
+parser.add_argument('--input_path', type=str, help='Name of input path to JSON file.')
+parser.add_argument('--output_path', type=str, help='Name of output path to JSON file.')
+args = parser.parse_args()
+
+input_path = args.input_path
+output_path = args.output_path
+os.makedirs(output_path, exist_ok=True)
+
+
+def load_jsonl(file_path):
+    """Load JSONL file into a list of dictionaries."""
+    data = []
+    with open(file_path, 'r') as f:
+        for line in f:
+            data.append(json.loads(line))
+    return data
+
+
+dataset = load_jsonl(input_path)
+ooutput_dataset = []
+for data in dataset:
+    instance_id = data['instance_id']
+    model_name_or_path = 'openhands'
+    model_patch = (
+        data['test_result']['git_patch']
+        if 'test_result' in data and 'git_patch' in data['test_result']
+        else None
+    )
+    ooutput_dataset.append(
+        {
+            'instance_id': instance_id,
+            'model_name_or_path': model_name_or_path,
+            'model_patch': model_patch,
+        }
+    )
+
+with open(os.path.join(output_path, 'output.jsonl'), 'w') as f:
+    for item in ooutput_dataset:
+        json_line = json.dumps(item, ensure_ascii=False)
+        f.write(json_line + '\n')

evaluation/benchmarks/swe_perf/resource/mapping.py

@@ -0,0 +1,39 @@
+"""Mapping instance_id to resource_factor.
+
+Different instances may have different resource requirements.
+e.g., some instances may require more memory/CPU to run inference.
+This file tracks the resource requirements of different instances.
+"""
+
+import json
+import os
+
+from openhands.core.logger import openhands_logger as logger
+
+CUR_DIR = os.path.dirname(os.path.abspath(__file__))
+DEFAULT_RUNTIME_RESOURCE_FACTOR = int(
+    os.environ.get('DEFAULT_RUNTIME_RESOURCE_FACTOR', 1)
+)
+
+# dataset to resource mapping
+_global_resource_mapping: dict[str, dict[str, float]] = {}
+
+
+def get_resource_mapping(dataset_name: str) -> dict[str, float]:
+    if dataset_name not in _global_resource_mapping:
+        file_path = os.path.join(CUR_DIR, f'{dataset_name}.json')
+        if not os.path.exists(file_path):
+            logger.info(f'Resource mapping for {dataset_name} not found.')
+            return None
+
+        with open(file_path, 'r') as f:
+            _global_resource_mapping[dataset_name] = json.load(f)
+        logger.debug(f'Loaded resource mapping for {dataset_name}')
+    return _global_resource_mapping[dataset_name]
+
+
+def get_instance_resource_factor(dataset_name: str, instance_id: str) -> int:
+    resource_mapping = get_resource_mapping(dataset_name)
+    if resource_mapping is None:
+        return DEFAULT_RUNTIME_RESOURCE_FACTOR
+    return int(resource_mapping.get(instance_id, DEFAULT_RUNTIME_RESOURCE_FACTOR))

evaluation/benchmarks/swe_perf/resource/swt_bench_constants.py

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

evaluation/benchmarks/swe_perf/run_infer.py

@@ -0,0 +1,978 @@
+import asyncio
+import copy
+import json
+import os
+import tempfile
+from typing import Any, Literal
+
+import pandas as pd
+import toml
+from datasets import load_dataset
+
+import openhands.agenthub
+from evaluation.benchmarks.swe_perf.binary_patch_utils import (
+    remove_binary_diffs,
+    remove_binary_files_from_git,
+)
+from evaluation.benchmarks.swe_perf.resource.mapping import (
+    get_instance_resource_factor,
+)
+from evaluation.benchmarks.swe_perf.resource.swt_bench_constants import (
+    MAP_REPO_TO_INSTALL,
+    MAP_VERSION_TO_INSTALL,
+)
+from evaluation.utils.shared import (
+    EvalException,
+    EvalMetadata,
+    EvalOutput,
+    assert_and_raise,
+    check_maximum_retries_exceeded,
+    codeact_user_response,
+    get_default_sandbox_config_for_eval,
+    get_metrics,
+    is_fatal_evaluation_error,
+    make_metadata,
+    prepare_dataset,
+    reset_logger_for_multiprocessing,
+    run_evaluation,
+    update_llm_config_for_completions_logging,
+)
+from openhands.controller.state.state import State
+from openhands.core.config import (
+    AgentConfig,
+    OpenHandsConfig,
+    get_evaluation_parser,
+    get_llm_config_arg,
+)
+from openhands.core.config.condenser_config import NoOpCondenserConfig
+from openhands.core.config.utils import get_condenser_config_arg
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.main import create_runtime, run_controller
+from openhands.critic import AgentFinishedCritic
+from openhands.events.action import CmdRunAction, FileReadAction, MessageAction
+from openhands.events.observation import (
+    CmdOutputObservation,
+    ErrorObservation,
+    FileReadObservation,
+)
+from openhands.events.serialization.event import event_from_dict, event_to_dict
+from openhands.runtime.base import Runtime
+from openhands.utils.async_utils import call_async_from_sync
+from openhands.utils.shutdown_listener import sleep_if_should_continue
+
+USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
+RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
+ENABLE_LLM_EDITOR = os.environ.get('ENABLE_LLM_EDITOR', 'false').lower() == 'true'
+BenchMode = Literal['swe', 'swt', 'swt-ci']
+
+# Global variable to track dataset type
+DATASET_TYPE = 'SWE-Perf'
+
+
+AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
+    'CodeActAgent': codeact_user_response,
+}
+
+
+def _get_sweperf_workspace_dir_name(instance: pd.Series) -> str:
+    return f'{instance.repo}__{instance.version}'.replace('/', '__')
+
+
+def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageAction:
+    workspace_dir_name = _get_sweperf_workspace_dir_name(instance)
+
+    # The instruction
+    instruction = f"""
+<uploaded_files>
+/workspace/{workspace_dir_name}
+</uploaded_files>
+
+I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following issue description:
+
+
+<issue_description>
+{instance.problem_statement_realistic}
+</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: Understand the Problem & Test Reuse
+
+**1.1. Install the package locally:**
+
+```bash
+python -m pip install pyinstrument
+python -m pip install -e .
+```
+
+> Only proceed to README-based install if the above fails.
+
+**1.2. Identify relevant modules and logic:**
+
+* Use test cases mentioned in `<issue_description>` to locate the functions and files involved.
+* Focus on potential performance bottlenecks: loops, I/O, locks, cache access, data structures, etc.
+
+**1.3. Run initial benchmark:**
+
+```bash
+pytest -rA --durations=0 --disable-warnings -p no:warnings --tb=no <test_case>
+```
+
+## 📊 Phase 2: Localization (Hierarchical Bottleneck Detection)
+
+**2.1. Global profiling using `pyinstrument`:**
+
+```bash
+pyinstrument -m pytest -rA --durations=0 --disable-warnings --tb=no --continue-on-collection-errors -p no:warnings <test_case>
+```
+
+**2.2. Analyze performance stack if necessary:**
+
+* 🔍 **Module level**: Identify hot files and methods.
+* 🔬 **Function level**: Focus on top-consuming classes/functions.
+* 🧬 **Line level**: Add fine-grained sampling/logging if needed.
+
+**2.3. Output a layered summary** showing where time is spent and why.
+
+
+## 🧠 Phase 3: Repair (Design Candidate Fixes)
+
+**3.1. Propose multiple optimization ideas:**
+
+* Algorithm refinement
+* Data structure improvement
+* Parallelism / async
+* Caching / batching
+
+**3.2. For each candidate:**
+
+* Describe the idea using pseudocode or `diff`
+* Evaluate expected gain vs implementation complexity
+
+---
+
+## 🔬 Phase 4: Patch Validation (Quantitative Benchmarking)
+
+**4.1. Apply each patch separately**
+
+**4.2. Re-run benchmark using the same test case**
+
+**4.3. Record improvements in pytest `call` phase**
+
+**4.4. Build a comparison table:**
+
+| Patch | Call Time (s) | % Improvement | Notes |
+| ----- | ------------- | ------------- | ----- |
+
+**4.5. Select the best-performing, low-risk patch**
+
+---
+
+## 📌 Phase 5: Fix Analysis (Explain the Fix)
+
+**5.1.** Clearly describe the **problem**
+
+**5.2.** Identify the **exact location** in the code
+
+**5.3.** Describe **how the test reveals** the problem
+
+**5.4.** State **best practices** relevant to the fix
+
+**5.5.** Explain **how the fix resolves** the issue
+
+---
+
+## 🧩 Phase 6: Fix Implementation
+
+**6.1.** Implement the selected fix in the non-test source files
+**6.2.** Ensure the changes are minimal and performance-focused
+
+---
+
+## ✅ Phase 7: Final Verification & Review
+
+**7.1.** Run **full regression tests** to ensure correctness
+
+**7.2.** Re-benchmark performance and compare with base commit `{instance['base_commit']}`
+
+**7.3.** Ensure `call` time is significantly improved in `pytest` output
+
+**7.4.** If gain is limited, consider deeper optimization
+
+**7.5.** Write a concise final report including:
+
+* Bottleneck path
+* Fix alternatives considered
+* Final solution and metrics
+* Code diff summary
+
+## Important ##
+1. Please do not optimize specifically for certain test cases, as this may be considered cheating.
+2. Delete all files unrelated to optimization, including temporary files, auxiliary test code, and so on.
+3. Avoid excessive optimization and unnecessary divergence; if the improvement is not significant, stop promptly to maintain efficiency and focus.
+
+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.
+"""
+
+    if RUN_WITH_BROWSING:
+        instruction += (
+            '<IMPORTANT!>\nYou SHOULD NEVER attempt to browse the web. </IMPORTANT!>\n'
+        )
+
+    if 'image_assets' in instance:
+        assets = json.loads(instance['image_assets'])
+        assert 'problem_statement' in assets, (
+            'problem_statement is required in image_assets'
+        )
+        image_urls = assets['problem_statement']
+        return MessageAction(content=instruction, image_urls=image_urls)
+    return MessageAction(content=instruction)
+
+
+def get_instance_docker_image(
+    instance_id: str,
+) -> str:
+    docker_image_prefix = 'docker.io/betty1202/'
+    image_name = 'sweb.eval.x86_64.' + instance_id
+    image_name = image_name.replace(
+        '__', '_s_'
+    )  # to comply with docker image naming convention
+    return (docker_image_prefix.rstrip('/') + '/' + image_name).lower()
+
+
+def get_config(
+    instance: pd.Series,
+    metadata: EvalMetadata,
+) -> OpenHandsConfig:
+    base_container_image = get_instance_docker_image(
+        instance['instance_id'],
+    )
+    logger.info(
+        f'Using instance container image: {base_container_image}. '
+        f'Please make sure this image exists. '
+        f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
+    )
+
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = base_container_image
+    sandbox_config.enable_auto_lint = True
+    sandbox_config.use_host_network = False
+    # Add platform to the sandbox config to solve issue 4401
+    sandbox_config.platform = 'linux/amd64'
+    sandbox_config.remote_runtime_resource_factor = get_instance_resource_factor(
+        dataset_name=metadata.dataset,
+        instance_id=instance['instance_id'],
+    )
+
+    config = OpenHandsConfig(
+        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
+        workspace_base=None,
+        workspace_mount_path=None,
+    )
+
+    config.set_llm_config(
+        update_llm_config_for_completions_logging(
+            metadata.llm_config, metadata.eval_output_dir, instance['instance_id']
+        )
+    )
+    # get 'draft_editor' config if exists
+    config.set_llm_config(get_llm_config_arg('draft_editor'), 'draft_editor')
+
+    agent_config = AgentConfig(
+        enable_jupyter=False,
+        enable_browsing=RUN_WITH_BROWSING,
+        enable_llm_editor=ENABLE_LLM_EDITOR,
+        enable_mcp=False,
+        condenser=metadata.condenser_config,
+        enable_prompt_extensions=False,
+    )
+    config.set_agent_config(agent_config)
+    return config
+
+
+def initialize_runtime(
+    runtime: Runtime,
+    instance: pd.Series,  # this argument is not required
+    metadata: EvalMetadata,
+):
+    """Initialize the runtime for the agent.
+
+    This function is called before the runtime is used to run the agent.
+    """
+    logger.info('-' * 30)
+    logger.info('BEGIN Runtime Initialization Fn')
+    logger.info('-' * 30)
+    workspace_dir_name = _get_sweperf_workspace_dir_name(instance)
+    obs: CmdOutputObservation
+
+    # Set instance id and git configuration
+    action = CmdRunAction(
+        command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc && git config --global core.pager "" && git config --global diff.binary false"""
+    )
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to export SWE_INSTANCE_ID and configure git: {str(obs)}',
+    )
+
+    action = CmdRunAction(command="""export USER=$(whoami); echo USER=${USER} """)
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to export USER: {str(obs)}')
+
+    # inject the init script
+    script_dir = os.path.dirname(__file__)
+
+    # inject the instance info
+    action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to create /swe_util/eval_data/instances: {str(obs)}',
+    )
+
+    swe_instance_json_name = 'swe-perf-instance.json'
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Construct the full path for the desired file name within the temporary directory
+        temp_file_path = os.path.join(temp_dir, swe_instance_json_name)
+        # Write to the file with the desired name within the temporary directory
+        with open(temp_file_path, 'w') as f:
+            if not isinstance(instance, dict):
+                json.dump([instance.to_dict()], f)
+            else:
+                json.dump([instance], f)
+
+        # Copy the file to the desired location
+        runtime.copy_to(temp_file_path, '/swe_util/eval_data/instances/')
+
+        # inject the instance swe entry
+        entry_script_path = 'instance_swe_entry.sh'
+        runtime.copy_to(
+            str(os.path.join(script_dir, f'scripts/setup/{entry_script_path}')),
+            '/swe_util/',
+        )
+
+    action = CmdRunAction(command='cat ~/.bashrc')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
+
+    action = CmdRunAction(command='source ~/.bashrc')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    if isinstance(obs, ErrorObservation):
+        logger.error(f'Failed to source ~/.bashrc: {str(obs)}')
+    assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
+
+    action = CmdRunAction(command=f'source /swe_util/{entry_script_path}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to source /swe_util/{entry_script_path}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command='git reset --hard')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to git reset --hard: {str(obs)}')
+
+    action = CmdRunAction(
+        command='for remote_name in $(git remote); do git remote remove "${remote_name}"; done'
+    )
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
+
+    if metadata.details['mode'] == 'swt-ci':
+        # set up repo
+        setup_commands = []
+        if instance['repo'] in MAP_REPO_TO_INSTALL:
+            setup_commands.append(MAP_REPO_TO_INSTALL[instance['repo']])
+
+        # Run pre-install set up if provided
+        install = MAP_VERSION_TO_INSTALL.get(instance['repo'], {}).get(
+            instance['version'], []
+        )
+        if 'pre_install' in install:
+            for pre_install in install['pre_install']:
+                setup_commands.append(pre_install)
+
+        if 'install' in install:
+            setup_commands.append(install['install'])
+
+        for command in setup_commands:
+            action = CmdRunAction(command=command)
+            action.set_hard_timeout(600)
+            logger.info(action, extra={'msg_type': 'ACTION'})
+            obs = runtime.run_action(action)
+            logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    action = CmdRunAction(command='which python')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0 and 'testbed' in obs.content,
+        f'Expected to find python interpreter from testbed, but got: {str(obs)}',
+    )
+
+    logger.info('-' * 30)
+    logger.info('END Runtime Initialization Fn')
+    logger.info('-' * 30)
+
+
+def complete_runtime(
+    runtime: Runtime,
+    instance: pd.Series,  # this argument is not required, but it is used to get the workspace_dir_name
+) -> dict[str, Any]:
+    """Complete the runtime for the agent.
+
+    This function is called before the runtime is used to run the agent.
+    If you need to do something in the sandbox to get the correctness metric after
+    the agent has run, modify this function.
+    """
+    logger.info('-' * 30)
+    logger.info('BEGIN Runtime Completion Fn')
+    logger.info('-' * 30)
+    obs: CmdOutputObservation
+    workspace_dir_name = _get_sweperf_workspace_dir_name(instance)
+
+    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    if obs.exit_code == -1:
+        # The previous command is still running
+        # We need to kill previous command
+        logger.info('The previous command is still running, trying to kill it...')
+        action = CmdRunAction(command='C-c')
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+        # Then run the command again
+        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    if obs.exit_code == -1:
+        # The previous command is still running
+        # We need to kill previous command
+        logger.info('The previous command is still running, trying to ctrl+z it...')
+        action = CmdRunAction(command='C-z')
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+        # Then run the command again
+        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command='git config --global core.pager ""')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to git config --global core.pager "": {str(obs)}',
+    )
+
+    # First check for any git repositories in subdirectories
+    action = CmdRunAction(command='find . -type d -name .git -not -path "./.git"')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to find git repositories: {str(obs)}',
+    )
+
+    git_dirs = [p for p in obs.content.strip().split('\n') if p]
+    if git_dirs:
+        # Remove all .git directories in subdirectories
+        for git_dir in git_dirs:
+            action = CmdRunAction(command=f'rm -rf "{git_dir}"')
+            action.set_hard_timeout(600)
+            logger.info(action, extra={'msg_type': 'ACTION'})
+            obs = runtime.run_action(action)
+            logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+            assert_and_raise(
+                isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+                f'Failed to remove git directory {git_dir}: {str(obs)}',
+            )
+
+    # add all files
+    action = CmdRunAction(command='git add -A')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to git add -A: {str(obs)}',
+    )
+
+    # Remove binary files from git staging
+    action = CmdRunAction(command=remove_binary_files_from_git())
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to remove binary files: {str(obs)}',
+    )
+
+    n_retries = 0
+    git_patch = None
+    while n_retries < 5:
+        action = CmdRunAction(
+            command=f'git diff --no-color --cached {instance["base_commit"]} > patch.diff'
+        )
+        action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+        n_retries += 1
+        if isinstance(obs, CmdOutputObservation):
+            if obs.exit_code == 0:
+                # Read the patch file
+                action = FileReadAction(path='patch.diff')
+                action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+                logger.info(action, extra={'msg_type': 'ACTION'})
+                obs = runtime.run_action(action)
+                logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+                if isinstance(obs, FileReadObservation):
+                    git_patch = obs.content
+                    break
+                elif isinstance(obs, ErrorObservation):
+                    # Fall back to cat "patch.diff" to get the patch
+                    assert 'File could not be decoded as utf-8' in obs.content
+                    action = CmdRunAction(command='cat patch.diff')
+                    action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+                    logger.info(action, extra={'msg_type': 'ACTION'})
+                    obs = runtime.run_action(action)
+                    assert isinstance(obs, CmdOutputObservation) and obs.exit_code == 0
+                    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+                    git_patch = obs.content
+                    break
+                else:
+                    assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
+            else:
+                logger.info('Failed to get git diff, retrying...')
+                sleep_if_should_continue(10)
+        elif isinstance(obs, ErrorObservation):
+            logger.error(f'Error occurred: {obs.content}. Retrying...')
+            sleep_if_should_continue(10)
+        else:
+            assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
+
+    assert_and_raise(git_patch is not None, 'Failed to get git diff (None)')
+
+    # Remove binary diffs from the patch
+    git_patch = remove_binary_diffs(git_patch)
+
+    logger.info('-' * 30)
+    logger.info('END Runtime Completion Fn')
+    logger.info('-' * 30)
+    return {'git_patch': git_patch}
+
+
+def process_instance(
+    instance: pd.Series,
+    metadata: EvalMetadata,
+    reset_logger: bool = True,
+    runtime_failure_count: int = 0,
+) -> EvalOutput:
+    config = get_config(instance, metadata)
+
+    # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
+    if reset_logger:
+        log_dir = os.path.join(metadata.eval_output_dir, 'infer_logs')
+        reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
+    else:
+        logger.info(f'Starting evaluation for instance {instance.instance_id}.')
+
+    # Increase resource_factor with increasing attempt_id
+    if runtime_failure_count > 0:
+        config.sandbox.remote_runtime_resource_factor = min(
+            config.sandbox.remote_runtime_resource_factor * (2**runtime_failure_count),
+            8,
+        )
+        logger.warning(
+            f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
+        )
+
+    metadata = copy.deepcopy(metadata)
+    metadata.details['runtime_failure_count'] = runtime_failure_count
+    metadata.details['remote_runtime_resource_factor'] = (
+        config.sandbox.remote_runtime_resource_factor
+    )
+
+    runtime = create_runtime(config)
+    call_async_from_sync(runtime.connect)
+
+    try:
+        initialize_runtime(runtime, instance, metadata)
+
+        message_action = get_instruction(instance, metadata)
+
+        # Here's how you can run the agent (similar to the `main` function) and get the final task state
+        state: State | None = asyncio.run(
+            run_controller(
+                config=config,
+                initial_user_action=message_action,
+                runtime=runtime,
+                fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
+                    metadata.agent_class
+                ],
+            )
+        )
+
+        # if fatal error, throw EvalError to trigger re-run
+        if is_fatal_evaluation_error(state.last_error):
+            raise EvalException('Fatal error detected: ' + state.last_error)
+
+        # Get git patch
+        complete_runtime_fn = complete_runtime
+        return_val = complete_runtime_fn(runtime, instance)
+        git_patch = return_val['git_patch']
+        logger.info(
+            f'Got git diff for instance {instance.instance_id}:\n--------\n{git_patch}\n--------'
+        )
+    finally:
+        runtime.close()
+    # ==========================================
+
+    # ======= Attempt to evaluate the agent's edits =======
+    # we use eval_infer.sh to evaluate the agent's edits, not here
+    # because the agent may alter the environment / testcases
+    test_result = {
+        'git_patch': git_patch,
+    }
+
+    # If you are working on some simpler benchmark that only evaluates the final model output (e.g., in a MessageAction)
+    # You can simply get the LAST `MessageAction` from the returned `state.history` and parse it for evaluation.
+    if state is None:
+        raise ValueError('State should not be None.')
+
+    # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
+    histories = [event_to_dict(event) for event in state.history]
+    metrics = get_metrics(state)
+
+    # Save the output
+    instruction = message_action.content
+    if message_action.image_urls:
+        instruction += (
+            '\n\n<image_urls>' + '\n'.join(message_action.image_urls) + '</image_urls>'
+        )
+    output = EvalOutput(
+        instance_id=instance.instance_id,
+        instruction=instruction,
+        instance=instance.to_dict(),  # SWE Bench specific
+        test_result=test_result,
+        metadata=metadata,
+        history=histories,
+        metrics=metrics,
+        error=state.last_error if state and state.last_error else None,
+    )
+    return output
+
+
+def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
+    file_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'config.toml')
+    if os.path.exists(file_path):
+        with open(file_path, 'r') as file:
+            data = toml.load(file)
+            if 'selected_ids' in data:
+                selected_ids = data['selected_ids']
+                logger.info(
+                    f'Filtering {len(selected_ids)} tasks from "selected_ids"...'
+                )
+                subset = dataset[dataset[filter_column].isin(selected_ids)]
+                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
+                return subset
+            if 'selected_repos' in data:
+                selected_repos = data['selected_repos']
+                if isinstance(selected_repos, str):
+                    selected_repos = [selected_repos]
+                assert isinstance(selected_repos, list)
+                logger.info(
+                    f'Filtering {selected_repos} tasks from "selected_repos"...'
+                )
+                subset = dataset[dataset['repo'].isin(selected_repos)]
+                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
+                return subset
+
+    skip_ids = os.environ.get('SKIP_IDS', '').split(',')
+    if len(skip_ids) > 0:
+        logger.info(f'Filtering {len(skip_ids)} tasks from "SKIP_IDS"...')
+        return dataset[~dataset[filter_column].isin(skip_ids)]
+    return dataset
+
+
+if __name__ == '__main__':
+    parser = get_evaluation_parser()
+    parser.add_argument(
+        '--dataset',
+        type=str,
+        default='SWE-Perf/SWE-Perf',
+        help='data set to evaluate on, either full-test or lite-test',
+    )
+    parser.add_argument(
+        '--split',
+        type=str,
+        default='test',
+        help='split to evaluate on',
+    )
+    parser.add_argument(
+        '--mode',
+        type=str,
+        default='swe',
+        choices=['swe', 'swt', 'swt-ci'],
+        help="mode to run the evaluation, either 'swe', 'swt', or 'swt-ci'",
+    )
+
+    args, _ = parser.parse_known_args()
+
+    # NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
+    # so we don't need to manage file uploading to OpenHands's repo
+    dataset = load_dataset(args.dataset, split=args.split)
+
+    swe_perf_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
+    logger.info(
+        f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_perf_tests)} tasks'
+    )
+
+    llm_config = None
+    if args.llm_config:
+        llm_config = get_llm_config_arg(args.llm_config)
+        llm_config.log_completions = True
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
+
+    if llm_config is None:
+        raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
+
+    # Get condenser config from environment variable
+    condenser_name = os.environ.get('EVAL_CONDENSER')
+    if condenser_name:
+        condenser_config = get_condenser_config_arg(condenser_name)
+        if condenser_config is None:
+            raise ValueError(
+                f'Could not find Condenser config: EVAL_CONDENSER={condenser_name}'
+            )
+    else:
+        # If no specific condenser config is provided via env var, default to NoOpCondenser
+        condenser_config = NoOpCondenserConfig()
+        logger.debug(
+            'No Condenser config provided via EVAL_CONDENSER, using NoOpCondenser.'
+        )
+
+    details = {'mode': args.mode}
+    _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
+
+    dataset_descrption = (
+        args.dataset.replace('/', '__') + '-' + args.split.replace('/', '__')
+    )
+    metadata = make_metadata(
+        llm_config,
+        dataset_descrption,
+        args.agent_cls,
+        args.max_iterations,
+        args.eval_note,
+        args.eval_output_dir,
+        details=details,
+        condenser_config=condenser_config,
+    )
+
+    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+    print(f'### OUTPUT FILE: {output_file} ###')
+
+    # Run evaluation in iterative mode:
+    # If a rollout fails to output AgentFinishAction, we will try again until it succeeds OR total 3 attempts have been made.
+    ITERATIVE_EVAL_MODE = (
+        os.environ.get('ITERATIVE_EVAL_MODE', 'false').lower() == 'true'
+    )
+    ITERATIVE_EVAL_MODE_MAX_ATTEMPTS = int(
+        os.environ.get('ITERATIVE_EVAL_MODE_MAX_ATTEMPTS', '3')
+    )
+
+    if not ITERATIVE_EVAL_MODE:
+        # load the dataset
+        instances = prepare_dataset(swe_perf_tests, output_file, args.eval_n_limit)
+
+        run_evaluation(
+            instances,
+            metadata,
+            output_file,
+            args.eval_num_workers,
+            process_instance,
+            timeout_seconds=8
+            * 60
+            * 60,  # 8 hour PER instance should be more than enough
+            max_retries=5,
+        )
+    else:
+        critic = AgentFinishedCritic()
+
+        def get_cur_output_file_path(attempt: int) -> str:
+            return (
+                f'{output_file.removesuffix(".jsonl")}.critic_attempt_{attempt}.jsonl'
+            )
+
+        eval_ids = None
+        for attempt in range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1):
+            cur_output_file = get_cur_output_file_path(attempt)
+            logger.info(
+                f'Running evaluation with critic {critic.__class__.__name__} for attempt {attempt} of {ITERATIVE_EVAL_MODE_MAX_ATTEMPTS}.'
+            )
+
+            # For deterministic eval, we set temperature to 0.1 for (>1) attempt
+            # so hopefully we get slightly different results
+            if attempt > 1 and metadata.llm_config.temperature == 0:
+                logger.info(
+                    f'Detected temperature is 0 for (>1) attempt {attempt}. Setting temperature to 0.1...'
+                )
+                metadata.llm_config.temperature = 0.1
+
+            # Load instances - at first attempt, we evaluate all instances
+            # On subsequent attempts, we only evaluate the instances that failed the previous attempt determined by critic
+            instances = prepare_dataset(
+                swe_perf_tests, cur_output_file, args.eval_n_limit, eval_ids=eval_ids
+            )
+
+            # Run evaluation - but save them to cur_output_file
+            logger.info(
+                f'Evaluating {len(instances)} instances for attempt {attempt}...'
+            )
+            run_evaluation(
+                instances,
+                metadata,
+                cur_output_file,
+                args.eval_num_workers,
+                process_instance,
+                timeout_seconds=8
+                * 60
+                * 60,  # 8 hour PER instance should be more than enough
+                max_retries=5,
+            )
+
+            # When eval is done, we update eval_ids to the instances that failed the current attempt
+            instances_failed = []
+            logger.info(
+                f'Use critic {critic.__class__.__name__} to check {len(instances)} instances for attempt {attempt}...'
+            )
+            with open(cur_output_file, 'r') as f:
+                for line in f:
+                    instance = json.loads(line)
+                    try:
+                        history = [
+                            event_from_dict(event) for event in instance['history']
+                        ]
+                        critic_result = critic.evaluate(
+                            history, instance['test_result'].get('git_patch', '')
+                        )
+                        if not critic_result.success:
+                            instances_failed.append(instance['instance_id'])
+                    except Exception as e:
+                        logger.error(
+                            f'Error loading history for instance {instance["instance_id"]}: {e}'
+                        )
+                        instances_failed.append(instance['instance_id'])
+            logger.info(
+                f'{len(instances_failed)} instances failed the current attempt {attempt}: {instances_failed}'
+            )
+            eval_ids = instances_failed
+
+            # If no instances failed, we break
+            if len(instances_failed) == 0:
+                break
+
+        # Then we should aggregate the results from all attempts into the original output file
+        # and remove the intermediate files
+        logger.info(
+            'Aggregating results from all attempts into the original output file...'
+        )
+        fout = open(output_file, 'w')
+        added_instance_ids = set()
+        for attempt in reversed(range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1)):
+            cur_output_file = get_cur_output_file_path(attempt)
+            if not os.path.exists(cur_output_file):
+                logger.warning(
+                    f'Intermediate output file {cur_output_file} does not exist. Skipping...'
+                )
+                continue
+
+            with open(cur_output_file, 'r') as f:
+                for line in f:
+                    instance = json.loads(line)
+                    # Also make sure git_patch is not empty - otherwise we fall back to previous attempt (empty patch is worse than anything else)
+                    if (
+                        instance['instance_id'] not in added_instance_ids
+                        and instance['test_result'].get('git_patch', '').strip()
+                    ):
+                        fout.write(line)
+                        added_instance_ids.add(instance['instance_id'])
+            logger.info(
+                f'Aggregated instances from {cur_output_file}. Total instances added so far: {len(added_instance_ids)}'
+            )
+        fout.close()
+        logger.info(
+            f'Done! Total {len(added_instance_ids)} instances added to {output_file}'
+        )
+        # Check if any instances reached maximum retries
+        check_maximum_retries_exceeded(metadata.eval_output_dir)

evaluation/benchmarks/swe_perf/scripts/run_infer.sh

@@ -0,0 +1,146 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+source "evaluation/utils/version_control.sh"
+
+MODEL_CONFIG=$1
+COMMIT_HASH=$2
+AGENT=$3
+EVAL_LIMIT=$4
+MAX_ITER=$5
+NUM_WORKERS=$6
+DATASET=$7
+SPLIT=$8
+N_RUNS=$9
+MODE=${10}
+
+
+if [ -z "$NUM_WORKERS" ]; then
+  NUM_WORKERS=1
+  echo "Number of workers not specified, use default $NUM_WORKERS"
+fi
+checkout_eval_branch
+
+if [ -z "$AGENT" ]; then
+  echo "Agent not specified, use default CodeActAgent"
+  AGENT="CodeActAgent"
+fi
+
+if [ -z "$MAX_ITER" ]; then
+  echo "MAX_ITER not specified, use default 100"
+  MAX_ITER=100
+fi
+
+if [ -z "$RUN_WITH_BROWSING" ]; then
+  echo "RUN_WITH_BROWSING not specified, use default false"
+  RUN_WITH_BROWSING=false
+fi
+
+
+if [ -z "$DATASET" ]; then
+  echo "DATASET not specified, use default SWE-Perf/SWE-Perf"
+  DATASET="SWE-Perf/SWE-Perf"
+fi
+
+if [ -z "$SPLIT" ]; then
+  echo "SPLIT not specified, use default test"
+  SPLIT="test"
+fi
+
+if [ -z "$MODE" ]; then
+  MODE="swe"
+  echo "MODE not specified, use default $MODE"
+fi
+
+if [ -n "$EVAL_CONDENSER" ]; then
+  echo "Using Condenser Config: $EVAL_CONDENSER"
+else
+  echo "No Condenser Config provided via EVAL_CONDENSER, use default (NoOpCondenser)."
+fi
+
+export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
+echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
+
+get_openhands_version
+
+echo "AGENT: $AGENT"
+echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "MODEL_CONFIG: $MODEL_CONFIG"
+echo "DATASET: $DATASET"
+echo "SPLIT: $SPLIT"
+echo "MAX_ITER: $MAX_ITER"
+echo "NUM_WORKERS: $NUM_WORKERS"
+echo "COMMIT_HASH: $COMMIT_HASH"
+echo "MODE: $MODE"
+echo "EVAL_CONDENSER: $EVAL_CONDENSER"
+
+# Default to NOT use Hint
+if [ -z "$USE_HINT_TEXT" ]; then
+  export USE_HINT_TEXT=false
+fi
+echo "USE_HINT_TEXT: $USE_HINT_TEXT"
+EVAL_NOTE="$OPENHANDS_VERSION"
+# if not using Hint, add -no-hint to the eval note
+if [ "$USE_HINT_TEXT" = false ]; then
+  EVAL_NOTE="$EVAL_NOTE-no-hint"
+fi
+
+if [ "$RUN_WITH_BROWSING" = true ]; then
+  EVAL_NOTE="$EVAL_NOTE-with-browsing"
+fi
+
+if [ -n "$EXP_NAME" ]; then
+  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
+fi
+# if mode != swe, add mode to the eval note
+if [ "$MODE" != "swe" ]; then
+  EVAL_NOTE="${EVAL_NOTE}-${MODE}"
+fi
+# Add condenser config to eval note if provided
+if [ -n "$EVAL_CONDENSER" ]; then
+  EVAL_NOTE="${EVAL_NOTE}-${EVAL_CONDENSER}"
+fi
+
+function run_eval() {
+  local eval_note="${1}"
+  COMMAND="poetry run python evaluation/benchmarks/swe_perf/run_infer.py \
+    --agent-cls $AGENT \
+    --llm-config $MODEL_CONFIG \
+    --max-iterations $MAX_ITER \
+    --eval-num-workers $NUM_WORKERS \
+    --eval-note $eval_note \
+    --dataset $DATASET \
+    --split $SPLIT \
+    --mode $MODE"
+
+
+
+  if [ -n "$EVAL_LIMIT" ]; then
+    echo "EVAL_LIMIT: $EVAL_LIMIT"
+    COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+  fi
+
+  # Run the command
+  eval $COMMAND
+}
+
+unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
+if [ -z "$N_RUNS" ]; then
+  N_RUNS=1
+  echo "N_RUNS not specified, use default $N_RUNS"
+fi
+
+# Skip runs if the run number is in the SKIP_RUNS list
+# read from env variable SKIP_RUNS as a comma separated list of run numbers
+SKIP_RUNS=(${SKIP_RUNS//,/ })
+for i in $(seq 1 $N_RUNS); do
+  if [[ " ${SKIP_RUNS[@]} " =~ " $i " ]]; then
+    echo "Skipping run $i"
+    continue
+  fi
+  current_eval_note="$EVAL_NOTE-run_$i"
+  echo "EVAL_NOTE: $current_eval_note"
+  run_eval $current_eval_note
+done
+
+checkout_original_branch

evaluation/benchmarks/swe_perf/scripts/setup/compare_patch_filename.py

@@ -0,0 +1,54 @@
+"""This script compares gold patches with OpenHands-generated patches and check whether
+OpenHands found the right (set of) files to modify.
+"""
+
+import argparse
+import json
+import re
+
+
+def extract_modified_files(patch):
+    modified_files = set()
+    file_pattern = re.compile(r'^diff --git a/(.*?) b/')
+
+    for line in patch.split('\n'):
+        match = file_pattern.match(line)
+        if match:
+            modified_files.add(match.group(1))
+
+    return modified_files
+
+
+def process_report(oh_output_file):
+    succ = 0
+    fail = 0
+    for line in open(oh_output_file):
+        line = json.loads(line)
+        instance_id = line['instance_id']
+        gold_patch = line['swe_instance']['patch']
+        generated_patch = line['git_patch']
+        gold_modified_files = extract_modified_files(gold_patch)
+        # swe-bench lite only: a gold patch always contains exactly one file
+        assert len(gold_modified_files) == 1
+        generated_modified_files = extract_modified_files(generated_patch)
+
+        # Check if all files in gold_patch are also in generated_patch
+        all_files_in_generated = gold_modified_files.issubset(generated_modified_files)
+        if all_files_in_generated:
+            succ += 1
+        else:
+            fail += 1
+            print(
+                f'{instance_id}: file mismatch, gold = {gold_modified_files}, generated = {generated_modified_files}'
+            )
+    print(
+        f'\nSUMMARY: {succ} out of {succ + fail} instances found correct files to edit, success rate = {succ / float(succ + fail)}'
+    )
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--oh_output_file', help='Path to the OH output file')
+    args = parser.parse_args()
+
+    process_report(args.oh_output_file)

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

@@ -0,0 +1,43 @@
+#!/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

frontend/__tests__/components/browser.test.tsx

@@ -13,7 +13,8 @@ vi.mock("react-router", async () => {
 
 vi.mock("#/context/conversation-context", () => ({
   useConversation: () => ({ conversationId: "test-conversation-id" }),
-  ConversationProvider: ({ children }: { children: React.ReactNode }) => children,
+  ConversationProvider: ({ children }: { children: React.ReactNode }) =>
+    children,
 }));
 
 vi.mock("react-i18next", async () => {
@@ -29,21 +30,18 @@ vi.mock("react-i18next", async () => {
   };
 });
 
-// Mock redux
-const mockDispatch = vi.fn();
+// Mock Zustand browser store
 let mockBrowserState = {
   url: "https://example.com",
   screenshotSrc: "",
+  setUrl: vi.fn(),
+  setScreenshotSrc: vi.fn(),
+  reset: vi.fn(),
 };
 
-vi.mock("react-redux", async () => {
-  const actual = await vi.importActual("react-redux");
-  return {
-    ...actual,
-    useDispatch: () => mockDispatch,
-    useSelector: () => mockBrowserState,
-  };
-});
+vi.mock("#/stores/browser-store", () => ({
+  useBrowserStore: () => mockBrowserState,
+}));
 
 // Import the component after all mocks are set up
 import { BrowserPanel } from "#/components/features/browser/browser";
@@ -55,6 +53,9 @@ describe("Browser", () => {
     mockBrowserState = {
       url: "https://example.com",
       screenshotSrc: "",
+      setUrl: vi.fn(),
+      setScreenshotSrc: vi.fn(),
+      reset: vi.fn(),
     };
   });
 
@@ -63,6 +64,9 @@ describe("Browser", () => {
     mockBrowserState = {
       url: "https://example.com",
       screenshotSrc: "",
+      setUrl: vi.fn(),
+      setScreenshotSrc: vi.fn(),
+      reset: vi.fn(),
     };
 
     render(<BrowserPanel />);
@@ -75,7 +79,11 @@ describe("Browser", () => {
     // Set the mock state for this test
     mockBrowserState = {
       url: "https://example.com",
-      screenshotSrc: "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mN0uGvyHwAFCAJS091fQwAAAABJRU5ErkJggg==",
+      screenshotSrc:
+        "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mN0uGvyHwAFCAJS091fQwAAAABJRU5ErkJggg==",
+      setUrl: vi.fn(),
+      setScreenshotSrc: vi.fn(),
+      reset: vi.fn(),
     };
 
     render(<BrowserPanel />);

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

@@ -357,69 +357,6 @@ describe("ConversationCard", () => {
     expect(onClick).not.toHaveBeenCalled();
   });
 
-  it("should show display cost button only when showOptions is true", async () => {
-    const onContextMenuToggle = vi.fn();
-    const { rerender } = renderWithProviders(
-      <ConversationCard
-        onDelete={onDelete}
-        onChangeTitle={onChangeTitle}
-        title="Conversation 1"
-        selectedRepository={null}
-        lastUpdatedAt="2021-10-01T12:00:00Z"
-        contextMenuOpen
-        onContextMenuToggle={onContextMenuToggle}
-      />,
-    );
-
-    // Wait for context menu to appear
-    const menu = await screen.findByTestId("context-menu");
-    expect(
-      within(menu).queryByTestId("display-cost-button"),
-    ).not.toBeInTheDocument();
-
-    rerender(
-      <ConversationCard
-        onDelete={onDelete}
-        onChangeTitle={onChangeTitle}
-        showOptions
-        title="Conversation 1"
-        selectedRepository={null}
-        lastUpdatedAt="2021-10-01T12:00:00Z"
-        contextMenuOpen
-        onContextMenuToggle={onContextMenuToggle}
-      />,
-    );
-
-    // 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");
-  });
-
-  it("should show metrics modal when clicking the display cost button", async () => {
-    const user = userEvent.setup();
-    const onContextMenuToggle = vi.fn();
-    renderWithProviders(
-      <ConversationCard
-        onDelete={onDelete}
-        onChangeTitle={onChangeTitle}
-        title="Conversation 1"
-        selectedRepository={null}
-        lastUpdatedAt="2021-10-01T12:00:00Z"
-        showOptions
-        contextMenuOpen
-        onContextMenuToggle={onContextMenuToggle}
-      />,
-    );
-
-    const menu = screen.getByTestId("context-menu");
-    const displayCostButton = within(menu).getByTestId("display-cost-button");
-
-    await user.click(displayCostButton);
-
-    // Verify if metrics modal is displayed by checking for the modal content
-    expect(screen.getByTestId("metrics-modal")).toBeInTheDocument();
-  });
-
   it("should not display the edit or delete options if the handler is not provided", async () => {
     const onContextMenuToggle = vi.fn();
     const { rerender } = renderWithProviders(

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

@@ -1,10 +1,9 @@
 import { screen, waitFor, within } from "@testing-library/react";
 import { beforeAll, beforeEach, describe, expect, it, vi } from "vitest";
-import { QueryClientConfig } from "@tanstack/react-query";
 import userEvent from "@testing-library/user-event";
 import { createRoutesStub } from "react-router";
 import React from "react";
-import { renderWithProviders } from "test-utils";
+import { renderWithQueryAndI18n } from "test-utils";
 import { ConversationPanel } from "#/components/features/conversation-panel/conversation-panel";
 import ConversationService from "#/api/conversation-service/conversation-service.api";
 import { Conversation } from "#/api/open-hands.types";
@@ -18,16 +17,7 @@ describe("ConversationPanel", () => {
     },
   ]);
 
-  const renderConversationPanel = (config?: QueryClientConfig) =>
-    renderWithProviders(<RouterStub />, {
-      preloadedState: {
-        metrics: {
-          cost: null,
-          max_budget_per_task: null,
-          usage: null,
-        },
-      },
-    });
+  const renderConversationPanel = () => renderWithQueryAndI18n(<RouterStub />);
 
   beforeAll(() => {
     vi.mock("react-router", async (importOriginal) => ({
@@ -297,15 +287,7 @@ describe("ConversationPanel", () => {
       },
     ]);
 
-    renderWithProviders(<MyRouterStub />, {
-      preloadedState: {
-        metrics: {
-          cost: null,
-          max_budget_per_task: null,
-          usage: null,
-        },
-      },
-    });
+    renderWithQueryAndI18n(<MyRouterStub />);
 
     const toggleButton = screen.getByText("Toggle");
 

frontend/__tests__/components/features/microagent-management/microagent-management.test.tsx

@@ -12,6 +12,7 @@ import GitService from "#/api/git-service/git-service.api";
 import { GitRepository } from "#/types/git";
 import { RepositoryMicroagent } from "#/types/microagent-management";
 import { Conversation } from "#/api/open-hands.types";
+import { useMicroagentManagementStore } from "#/state/microagent-management-store";
 
 // Mock hooks
 const mockUseUserProviders = vi.fn();
@@ -55,25 +56,47 @@ describe("MicroagentManagement", () => {
   ]);
 
   const renderMicroagentManagement = (config?: QueryClientConfig) =>
-    renderWithProviders(<RouterStub />, {
-      preloadedState: {
-        metrics: {
-          cost: null,
-          max_budget_per_task: null,
-          usage: null,
-        },
-        microagentManagement: {
-          addMicroagentModalVisible: false,
-          updateMicroagentModalVisible: false,
-          selectedRepository: null,
-          personalRepositories: [],
-          organizationRepositories: [],
-          repositories: [],
-          selectedMicroagentItem: null,
-          learnThisRepoModalVisible: false,
-        },
-      },
+    renderWithProviders(<RouterStub />);
+
+  // Common test data
+  const testRepository = {
+    id: "1",
+    full_name: "user/test-repo",
+    git_provider: "github" as const,
+    is_public: true,
+    owner_type: "user" as const,
+    pushed_at: "2021-10-01T12:00:00Z",
+  };
+
+  // Helper function to render with custom Zustand store state
+  const renderWithCustomStore = (storeOverrides: Partial<any>) => {
+    useMicroagentManagementStore.setState(storeOverrides);
+    return renderWithProviders(<RouterStub />);
+  };
+
+  // Helper function to render with update modal visible
+  const renderWithUpdateModal = (additionalState: Partial<any> = {}) => {
+    return renderWithCustomStore({
+      updateMicroagentModalVisible: true,
+      selectedRepository: testRepository,
+      ...additionalState,
     });
+  };
+
+  // Helper function to render with selected microagent
+  const renderWithSelectedMicroagent = (
+    microagent: any,
+    additionalState: Partial<any> = {},
+  ) => {
+    return renderWithCustomStore({
+      selectedRepository: testRepository,
+      selectedMicroagentItem: {
+        microagent,
+        conversation: null,
+      },
+      ...additionalState,
+    });
+  };
 
   beforeAll(() => {
     vi.mock("react-router", async (importOriginal) => ({
@@ -186,6 +209,23 @@ describe("MicroagentManagement", () => {
     vi.clearAllMocks();
     vi.restoreAllMocks();
 
+    // Reset Zustand store to default state
+    useMicroagentManagementStore.setState({
+      // Modal visibility states
+      addMicroagentModalVisible: false,
+      updateMicroagentModalVisible: false,
+      learnThisRepoModalVisible: false,
+
+      // Repository states
+      selectedRepository: null,
+      personalRepositories: [],
+      organizationRepositories: [],
+      repositories: [],
+
+      // Microagent states
+      selectedMicroagentItem: null,
+    });
+
     // Setup default hook mocks
     mockUseUserProviders.mockReturnValue({
       providers: ["github"],
@@ -1347,33 +1387,10 @@ describe("MicroagentManagement", () => {
       });
     });
 
-    it("should render modal when Redux state is set to visible", async () => {
-      // Render with modal already visible in Redux state
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: null,
-            addMicroagentModalVisible: true, // Start with modal visible
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            updateMicroagentModalVisible: false,
-            learnThisRepoModalVisible: false,
-          },
-        },
+    it("should render modal when Zustand state is set to visible", async () => {
+      // Render with modal already visible in Zustand state
+      renderWithCustomStore({
+        addMicroagentModalVisible: true,
       });
 
       // Check that modal is rendered
@@ -1643,34 +1660,16 @@ describe("MicroagentManagement", () => {
       pr_number: null,
     };
 
-    const renderMicroagentManagementMain = (selectedMicroagentItem: any) =>
-      renderWithProviders(<MicroagentManagementMain />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            addMicroagentModalVisible: false,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            selectedMicroagentItem,
-            updateMicroagentModalVisible: false,
-            learnThisRepoModalVisible: false,
-          },
-        },
+    const renderMicroagentManagementMain = (selectedMicroagentItem: any) => {
+      // Set the store with the selected microagent item and a repository
+      useMicroagentManagementStore.setState({
+        selectedMicroagentItem,
+        selectedRepository: testRepository,
       });
 
+      return renderWithProviders(<MicroagentManagementMain />);
+    };
+
     it("should render MicroagentManagementDefault when no microagent or conversation is selected", async () => {
       renderMicroagentManagementMain(null);
 
@@ -1995,36 +1994,8 @@ describe("MicroagentManagement", () => {
     });
 
     it("should render update microagent modal when updateMicroagentModalVisible is true", async () => {
-      // Render with update modal visible in Redux state
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForUpdate,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true, // Start with update modal visible
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      // Render with update modal visible in Zustand state
+      renderWithUpdateModal();
 
       // Check that update modal is rendered
       expect(screen.getByTestId("add-microagent-modal")).toBeInTheDocument();
@@ -2035,35 +2006,7 @@ describe("MicroagentManagement", () => {
 
     it("should display update microagent title when isUpdate is true", async () => {
       // Render with update modal visible and selected microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForUpdate,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithUpdateModal();
 
       // Check that the update title is displayed
       expect(
@@ -2073,33 +2016,10 @@ describe("MicroagentManagement", () => {
 
     it("should populate form fields with existing microagent data when updating", async () => {
       // Render with update modal visible and selected microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForUpdate,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
+      renderWithUpdateModal({
+        selectedMicroagentItem: {
+          microagent: mockMicroagentForUpdate,
+          conversation: null,
         },
       });
 
@@ -2116,35 +2036,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Render with update modal visible and selected microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForUpdate,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithUpdateModal();
 
       // Wait for modal to be rendered
       await waitFor(() => {
@@ -2172,35 +2064,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Render with update modal visible
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForUpdate,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithUpdateModal();
 
       // Wait for modal to be rendered
       await waitFor(() => {
@@ -2223,35 +2087,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Render with update modal visible
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForUpdate,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithUpdateModal();
 
       // Wait for modal to be rendered
       await waitFor(() => {
@@ -2277,32 +2113,7 @@ describe("MicroagentManagement", () => {
 
     it("should handle update modal with empty microagent data", async () => {
       // Render with update modal visible but no microagent data
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: null,
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithUpdateModal();
 
       // Check that update modal is still rendered
       expect(screen.getByTestId("add-microagent-modal")).toBeInTheDocument();
@@ -2323,35 +2134,7 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with update modal visible and microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForUpdate,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithUpdateModal();
 
       // Wait for the content to be loaded and check that the form field is empty
       await waitFor(() => {
@@ -2372,35 +2155,7 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with update modal visible and microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForUpdate,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: true,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithUpdateModal();
 
       // Check that the modal is rendered correctly
       expect(screen.getByTestId("add-microagent-modal")).toBeInTheDocument();
@@ -2559,35 +2314,7 @@ describe("MicroagentManagement", () => {
 
     it("should render learn something new button in microagent view", async () => {
       // Render with selected microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForLearn,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: false,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithSelectedMicroagent(mockMicroagentForLearn);
 
       // Check that the learn something new button is displayed
       expect(
@@ -2599,35 +2326,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Render with selected microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForLearn,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: false,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithSelectedMicroagent(mockMicroagentForLearn);
 
       // Find and click the learn something new button
       const learnButton = screen.getByText("COMMON$LEARN_SOMETHING_NEW");
@@ -2656,35 +2355,7 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with selected microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForLearn,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: false,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithSelectedMicroagent(mockMicroagentForLearn);
 
       // Find and click the learn something new button
       const learnButton = screen.getByText("COMMON$LEARN_SOMETHING_NEW");
@@ -2716,35 +2387,7 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with selected microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForLearn,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: false,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithSelectedMicroagent(mockMicroagentForLearn);
 
       // Find and click the learn something new button
       const learnButton = screen.getByText("COMMON$LEARN_SOMETHING_NEW");
@@ -2774,35 +2417,7 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with selected microagent
-      renderWithProviders(<RouterStub />, {
-        preloadedState: {
-          metrics: {
-            cost: null,
-            max_budget_per_task: null,
-            usage: null,
-          },
-          microagentManagement: {
-            selectedMicroagentItem: {
-              microagent: mockMicroagentForLearn,
-              conversation: undefined,
-            },
-            addMicroagentModalVisible: false,
-            updateMicroagentModalVisible: false,
-            selectedRepository: {
-              id: "1",
-              full_name: "user/test-repo",
-              git_provider: "github",
-              is_public: true,
-              owner_type: "user",
-              pushed_at: "2021-10-01T12:00:00Z",
-            },
-            personalRepositories: [],
-            organizationRepositories: [],
-            repositories: [],
-            learnThisRepoModalVisible: false,
-          },
-        },
-      });
+      renderWithSelectedMicroagent(mockMicroagentForLearn);
 
       // Find and click the learn something new button
       const learnButton = screen.getByText("COMMON$LEARN_SOMETHING_NEW");

frontend/__tests__/components/interactive-chat-box.test.tsx

@@ -342,13 +342,7 @@ describe("InteractiveChatBox", () => {
     // Simulate parent component updating the value prop
     rerender(
       <MemoryRouter>
-        <InteractiveChatBox
-          onSubmit={onSubmit}
-          onStop={onStop}
-          isWaitingForUserInput={true}
-          hasSubstantiveAgentActions={true}
-          optimisticUserMessage={false}
-        />
+        <InteractiveChatBox onSubmit={onSubmit} onStop={onStop} />
       </MemoryRouter>,
     );
 

frontend/__tests__/components/jupyter/jupyter.test.tsx

@@ -2,8 +2,8 @@ import { render, screen } from "@testing-library/react";
 import { Provider } from "react-redux";
 import { configureStore } from "@reduxjs/toolkit";
 import { JupyterEditor } from "#/components/features/jupyter/jupyter";
-import { jupyterReducer } from "#/state/jupyter-slice";
-import { vi, describe, it, expect } from "vitest";
+import { useJupyterStore } from "#/state/jupyter-store";
+import { vi, describe, it, expect, beforeEach } from "vitest";
 
 describe("JupyterEditor", () => {
   const mockStore = configureStore({
@@ -15,19 +15,20 @@ describe("JupyterEditor", () => {
       code: () => ({}),
       cmd: () => ({}),
       agent: () => ({}),
-      jupyter: jupyterReducer,
       securityAnalyzer: () => ({}),
       status: () => ({}),
     },
-    preloadedState: {
-      jupyter: {
-        cells: Array(20).fill({
-          content: "Test cell content",
-          type: "input",
-          output: "Test output",
-        }),
-      },
-    },
+  });
+
+  beforeEach(() => {
+    // Reset the Zustand store before each test
+    useJupyterStore.setState({
+      cells: Array(20).fill({
+        content: "Test cell content",
+        type: "input",
+        imageUrls: undefined,
+      }),
+    });
   });
 
   it("should have a scrollable container", () => {
@@ -36,7 +37,7 @@ describe("JupyterEditor", () => {
         <div style={{ height: "100vh" }}>
           <JupyterEditor maxWidth={800} />
         </div>
-      </Provider>
+      </Provider>,
     );
 
     const container = screen.getByTestId("jupyter-container");

frontend/__tests__/components/terminal/terminal.test.tsx

@@ -1,17 +1,14 @@
 import { act, screen } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import { vi, describe, afterEach, it, expect } from "vitest";
-import { Command, appendInput, appendOutput } from "#/state/command-slice";
+import { Command, useCommandStore } from "#/state/command-store";
 import Terminal from "#/components/features/terminal/terminal";
 
-const renderTerminal = (commands: Command[] = []) =>
-  renderWithProviders(<Terminal />, {
-    preloadedState: {
-      cmd: {
-        commands,
-      },
-    },
-  });
+const renderTerminal = (commands: Command[] = []) => {
+  // Set initial commands in Zustand store
+  useCommandStore.setState({ commands });
+  return renderWithProviders(<Terminal />);
+};
 
 describe.skip("Terminal", () => {
   global.ResizeObserver = vi.fn().mockImplementation(() => ({
@@ -58,25 +55,25 @@ describe.skip("Terminal", () => {
   });
 
   it("should write commands to the terminal", () => {
-    const { store } = renderTerminal();
+    renderTerminal();
 
     act(() => {
-      store.dispatch(appendInput("echo Hello"));
-      store.dispatch(appendOutput("Hello"));
+      useCommandStore.getState().appendInput("echo Hello");
+      useCommandStore.getState().appendOutput("Hello");
     });
 
     expect(mockTerminal.writeln).toHaveBeenNthCalledWith(1, "echo Hello");
     expect(mockTerminal.writeln).toHaveBeenNthCalledWith(2, "Hello");
 
     act(() => {
-      store.dispatch(appendInput("echo World"));
+      useCommandStore.getState().appendInput("echo World");
     });
 
     expect(mockTerminal.writeln).toHaveBeenNthCalledWith(3, "echo World");
   });
 
   it("should load and write commands to the terminal", () => {
-    const { store } = renderTerminal([
+    renderTerminal([
       { type: "input", content: "echo Hello" },
       { type: "output", content: "Hello" },
     ]);
@@ -85,17 +82,17 @@ describe.skip("Terminal", () => {
     expect(mockTerminal.writeln).toHaveBeenNthCalledWith(2, "Hello");
 
     act(() => {
-      store.dispatch(appendInput("echo Hello"));
+      useCommandStore.getState().appendInput("echo Hello");
     });
 
     expect(mockTerminal.writeln).toHaveBeenNthCalledWith(3, "echo Hello");
   });
 
   it("should end the line with a dollar sign after writing a command", () => {
-    const { store } = renderTerminal();
+    renderTerminal();
 
     act(() => {
-      store.dispatch(appendInput("echo Hello"));
+      useCommandStore.getState().appendInput("echo Hello");
     });
 
     expect(mockTerminal.writeln).toHaveBeenCalledWith("echo Hello");

frontend/__tests__/hooks/use-terminal.test.tsx

@@ -1,7 +1,7 @@
 import { beforeAll, describe, expect, it, vi } from "vitest";
 import { afterEach } from "node:test";
 import { useTerminal } from "#/hooks/use-terminal";
-import { Command } from "#/state/command-slice";
+import { Command, useCommandStore } from "#/state/command-store";
 import { AgentState } from "#/types/agent-state";
 import { renderWithProviders } from "../../test-utils";
 
@@ -19,10 +19,10 @@ interface TestTerminalComponentProps {
   commands: Command[];
 }
 
-function TestTerminalComponent({
-  commands,
-}: TestTerminalComponentProps) {
-  const ref = useTerminal({ commands });
+function TestTerminalComponent({ commands }: TestTerminalComponentProps) {
+  // Set commands in Zustand store
+  useCommandStore.setState({ commands });
+  const ref = useTerminal();
   return <div ref={ref} />;
 }
 
@@ -60,7 +60,6 @@ describe("useTerminal", () => {
     renderWithProviders(<TestTerminalComponent commands={[]} />, {
       preloadedState: {
         agent: { curAgentState: AgentState.RUNNING },
-        cmd: { commands: [] },
       },
     });
   });
@@ -74,7 +73,6 @@ describe("useTerminal", () => {
     renderWithProviders(<TestTerminalComponent commands={commands} />, {
       preloadedState: {
         agent: { curAgentState: AgentState.RUNNING },
-        cmd: { commands },
       },
     });
 
@@ -94,17 +92,11 @@ describe("useTerminal", () => {
       { content: secret, type: "output" },
     ];
 
-    renderWithProviders(
-      <TestTerminalComponent
-        commands={commands}
-      />,
-      {
-        preloadedState: {
-          agent: { curAgentState: AgentState.RUNNING },
-          cmd: { commands },
-        },
+    renderWithProviders(<TestTerminalComponent commands={commands} />, {
+      preloadedState: {
+        agent: { curAgentState: AgentState.RUNNING },
       },
-    );
+    });
 
     // This test is no longer relevant as secrets filtering has been removed
   });

frontend/__tests__/initial-query.test.tsx

@@ -1,20 +1,24 @@
-import { describe, it, expect } from "vitest";
-import store from "../src/store";
-import {
-  setInitialPrompt,
-  clearInitialPrompt,
-} from "../src/state/initial-query-slice";
+import { describe, it, expect, beforeEach } from "vitest";
+import { useInitialQueryStore } from "../src/stores/initial-query-store";
 
 describe("Initial Query Behavior", () => {
-  it("should clear initial query when clearInitialPrompt is dispatched", () => {
+  beforeEach(() => {
+    // Reset the store before each test
+    useInitialQueryStore.getState().reset();
+  });
+
+  it("should clear initial query when clearInitialPrompt is called", () => {
+    const { setInitialPrompt, clearInitialPrompt, initialPrompt } =
+      useInitialQueryStore.getState();
+
     // Set up initial query in the store
-    store.dispatch(setInitialPrompt("test query"));
-    expect(store.getState().initialQuery.initialPrompt).toBe("test query");
+    setInitialPrompt("test query");
+    expect(useInitialQueryStore.getState().initialPrompt).toBe("test query");
 
     // Clear the initial query
-    store.dispatch(clearInitialPrompt());
+    clearInitialPrompt();
 
     // Verify initial query is cleared
-    expect(store.getState().initialQuery.initialPrompt).toBeNull();
+    expect(useInitialQueryStore.getState().initialPrompt).toBeNull();
   });
 });

frontend/__tests__/services/actions.test.tsx

@@ -13,12 +13,28 @@ vi.mock("#/store", () => ({
   },
 }));
 
-vi.mock("#/state/command-slice", () => ({
-  appendInput: mockAppendInput,
+vi.mock("#/state/command-store", () => ({
+  useCommandStore: {
+    getState: () => ({
+      appendInput: mockAppendInput,
+    }),
+  },
 }));
 
-vi.mock("#/state/jupyter-slice", () => ({
-  appendJupyterInput: mockAppendJupyterInput,
+vi.mock("#/state/jupyter-store", () => ({
+  useJupyterStore: {
+    getState: () => ({
+      appendJupyterInput: mockAppendJupyterInput,
+    }),
+  },
+}));
+
+vi.mock("#/state/metrics-slice", () => ({
+  setMetrics: vi.fn(),
+}));
+
+vi.mock("#/state/security-analyzer-slice", () => ({
+  appendSecurityAnalyzerInput: vi.fn(),
 }));
 
 describe("handleActionMessage", () => {
@@ -45,7 +61,8 @@ describe("handleActionMessage", () => {
     handleActionMessage(runAction);
 
     // Check that appendInput was called with the command
-    expect(mockDispatch).toHaveBeenCalledWith(mockAppendInput("ls -la"));
+    expect(mockAppendInput).toHaveBeenCalledWith("ls -la");
+    expect(mockDispatch).not.toHaveBeenCalled();
     expect(mockAppendJupyterInput).not.toHaveBeenCalled();
   });
 
@@ -59,7 +76,8 @@ describe("handleActionMessage", () => {
       args: {
         code: "print('Hello from Jupyter!')",
       },
-      message: "Running Python code interactively: print('Hello from Jupyter!')",
+      message:
+        "Running Python code interactively: print('Hello from Jupyter!')",
       timestamp: "2023-01-01T00:00:00Z",
     };
 
@@ -67,7 +85,9 @@ describe("handleActionMessage", () => {
     handleActionMessage(ipythonAction);
 
     // Check that appendJupyterInput was called with the code
-    expect(mockDispatch).toHaveBeenCalledWith(mockAppendJupyterInput("print('Hello from Jupyter!')"));
+    expect(mockAppendJupyterInput).toHaveBeenCalledWith(
+      "print('Hello from Jupyter!')",
+    );
     expect(mockAppendInput).not.toHaveBeenCalled();
   });
 
@@ -89,7 +109,9 @@ describe("handleActionMessage", () => {
     // Handle the action
     handleActionMessage(hiddenAction);
 
-    // Check that nothing was dispatched
+    // Check that nothing was dispatched or called
     expect(mockDispatch).not.toHaveBeenCalled();
+    expect(mockAppendInput).not.toHaveBeenCalled();
+    expect(mockAppendJupyterInput).not.toHaveBeenCalled();
   });
 });

frontend/__tests__/utils/check-hardcoded-strings.test.tsx

@@ -60,13 +60,7 @@ describe("Check for hardcoded English strings", () => {
   test("InteractiveChatBox should not have hardcoded English strings", () => {
     const { container } = renderWithProviders(
       <MemoryRouter>
-        <InteractiveChatBox
-          onSubmit={() => {}}
-          onStop={() => {}}
-          isWaitingForUserInput={false}
-          hasSubstantiveAgentActions={false}
-          optimisticUserMessage={false}
-        />
+        <InteractiveChatBox onSubmit={() => {}} onStop={() => {}} />
       </MemoryRouter>,
     );
 

frontend/package.json

@@ -1,44 +1,44 @@
 {
   "name": "openhands-frontend",
-  "version": "0.56.0",
+  "version": "0.57.0",
   "private": true,
   "type": "module",
   "engines": {
     "node": ">=22.0.0"
   },
   "dependencies": {
-    "@heroui/react": "^2.8.3",
+    "@heroui/react": "^2.8.4",
     "@heroui/use-infinite-scroll": "^2.2.11",
     "@microlink/react-json-view": "^1.26.2",
     "@monaco-editor/react": "^4.7.0-rc.0",
-    "@react-router/node": "^7.8.2",
-    "@react-router/serve": "^7.8.2",
+    "@react-router/node": "^7.9.1",
+    "@react-router/serve": "^7.9.1",
     "@react-types/shared": "^3.32.0",
     "@reduxjs/toolkit": "^2.9.0",
-    "@stripe/react-stripe-js": "^4.0.0",
+    "@stripe/react-stripe-js": "^4.0.2",
     "@stripe/stripe-js": "^7.9.0",
     "@tailwindcss/postcss": "^4.1.13",
     "@tailwindcss/vite": "^4.1.13",
-    "@tanstack/react-query": "^5.87.0",
+    "@tanstack/react-query": "^5.90.2",
     "@uidotdev/usehooks": "^2.4.1",
-    "@vitejs/plugin-react": "^5.0.2",
+    "@vitejs/plugin-react": "^5.0.3",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
-    "axios": "^1.11.0",
+    "axios": "^1.12.2",
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
     "date-fns": "^4.1.0",
     "downshift": "^9.0.10",
     "eslint-config-airbnb-typescript": "^18.0.0",
-    "framer-motion": "^12.23.12",
+    "framer-motion": "^12.23.19",
     "i18next": "^25.5.2",
     "i18next-browser-languagedetector": "^8.2.0",
     "i18next-http-backend": "^3.0.2",
     "isbot": "^5.1.30",
     "jose": "^6.1.0",
-    "lucide-react": "^0.542.0",
-    "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.261.7",
+    "lucide-react": "^0.544.0",
+    "monaco-editor": "^0.53.0",
+    "posthog-js": "^1.268.1",
     "react": "^19.1.1",
     "react-dom": "^19.1.1",
     "react-highlight": "^0.15.0",
@@ -47,8 +47,7 @@
     "react-icons": "^5.5.0",
     "react-markdown": "^10.1.0",
     "react-redux": "^9.2.0",
-    "react-resizable-panels": "^3.0.5",
-    "react-router": "^7.8.2",
+    "react-router": "^7.9.1",
     "react-syntax-highlighter": "^15.6.6",
     "remark-breaks": "^4.0.0",
     "remark-gfm": "^4.0.1",
@@ -56,9 +55,10 @@
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^3.3.1",
     "tailwind-scrollbar": "^4.0.2",
-    "vite": "^7.1.4",
+    "vite": "^7.1.7",
     "web-vitals": "^5.1.0",
-    "ws": "^8.18.2"
+    "ws": "^8.18.2",
+    "zustand": "^5.0.8"
   },
   "scripts": {
     "dev": "npm run make-i18n && cross-env VITE_MOCK_API=false react-router dev",
@@ -97,16 +97,16 @@
     "@babel/traverse": "^7.28.3",
     "@babel/types": "^7.28.2",
     "@mswjs/socket.io-binding": "^0.2.0",
-    "@playwright/test": "^1.55.0",
-    "@react-router/dev": "^7.8.2",
-    "@tailwindcss/typography": "^0.5.16",
-    "@tanstack/eslint-plugin-query": "^5.86.0",
+    "@playwright/test": "^1.55.1",
+    "@react-router/dev": "^7.9.1",
+    "@tailwindcss/typography": "^0.5.18",
+    "@tanstack/eslint-plugin-query": "^5.90.1",
     "@testing-library/dom": "^10.4.1",
     "@testing-library/jest-dom": "^6.8.0",
     "@testing-library/react": "^16.3.0",
     "@testing-library/user-event": "^14.6.1",
-    "@types/node": "^24.3.1",
-    "@types/react": "^19.1.12",
+    "@types/node": "^24.5.2",
+    "@types/react": "^19.1.13",
     "@types/react-dom": "^19.1.9",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
@@ -128,8 +128,8 @@
     "eslint-plugin-react-hooks": "^4.6.2",
     "eslint-plugin-unused-imports": "^4.2.0",
     "husky": "^9.1.7",
-    "jsdom": "^26.1.0",
-    "lint-staged": "^16.1.6",
+    "jsdom": "^27.0.0",
+    "lint-staged": "^16.2.0",
     "msw": "^2.6.6",
     "prettier": "^3.6.2",
     "stripe": "^18.5.0",

frontend/public/mockServiceWorker.js

@@ -7,7 +7,7 @@
  * - Please do NOT modify this file.
  */
 
-const PACKAGE_VERSION = '2.10.5'
+const PACKAGE_VERSION = '2.11.1'
 const INTEGRITY_CHECKSUM = 'f5825c521429caf22a4dd13b66e243af'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()

frontend/src/components/features/browser/browser.tsx

@@ -1,26 +1,16 @@
 import { useEffect } from "react";
-import { useSelector, useDispatch } from "react-redux";
-import { RootState } from "#/store";
 import { BrowserSnapshot } from "./browser-snapshot";
 import { EmptyBrowserMessage } from "./empty-browser-message";
 import { useConversationId } from "#/hooks/use-conversation-id";
-import {
-  initialState as browserInitialState,
-  setUrl,
-  setScreenshotSrc,
-} from "#/state/browser-slice";
+import { useBrowserStore } from "#/stores/browser-store";
 
 export function BrowserPanel() {
-  const { url, screenshotSrc } = useSelector(
-    (state: RootState) => state.browser,
-  );
+  const { url, screenshotSrc, reset } = useBrowserStore();
   const { conversationId } = useConversationId();
-  const dispatch = useDispatch();
 
   useEffect(() => {
-    dispatch(setUrl(browserInitialState.url));
-    dispatch(setScreenshotSrc(browserInitialState.screenshotSrc));
-  }, [conversationId]);
+    reset();
+  }, [conversationId, reset]);
 
   const imgSrc =
     screenshotSrc && screenshotSrc.startsWith("data:image/png;base64,")

frontend/src/components/features/chat/chat-interface.tsx

@@ -1,4 +1,4 @@
-import { useSelector, useDispatch } from "react-redux";
+import { useSelector } from "react-redux";
 import React from "react";
 import posthog from "posthog-js";
 import { useParams } from "react-router";
@@ -18,6 +18,7 @@ import { useWsClient } from "#/context/ws-client-provider";
 import { Messages } from "./messages";
 import { ChatSuggestions } from "./chat-suggestions";
 import { ScrollProvider } from "#/context/scroll-context";
+import { useInitialQueryStore } from "#/stores/initial-query-store";
 
 import { ScrollToBottomButton } from "#/components/shared/buttons/scroll-to-bottom-button";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
@@ -32,7 +33,8 @@ import {
 import { useUploadFiles } from "#/hooks/mutation/use-upload-files";
 import { useConfig } from "#/hooks/query/use-config";
 import { validateFiles } from "#/utils/file-validation";
-import { setMessageToSend } from "#/state/conversation-slice";
+import { useConversationStore } from "#/state/conversation-store";
+import ConfirmationModeEnabled from "./confirmation-mode-enabled";
 
 function getEntryPoint(
   hasRepository: boolean | null,
@@ -44,7 +46,7 @@ function getEntryPoint(
 }
 
 export function ChatInterface() {
-  const dispatch = useDispatch();
+  const { setMessageToSend } = useConversationStore();
   const { getErrorMessage } = useWSErrorMessage();
   const { send, isLoadingMessages, parsedEvents } = useWsClient();
   const { setOptimisticUserMessage, getOptimisticUserMessage } =
@@ -67,9 +69,7 @@ export function ChatInterface() {
     "positive" | "negative"
   >("positive");
   const [feedbackModalIsOpen, setFeedbackModalIsOpen] = React.useState(false);
-  const { selectedRepository, replayJson } = useSelector(
-    (state: RootState) => state.initialQuery,
-  );
+  const { selectedRepository, replayJson } = useInitialQueryStore();
   const params = useParams();
   const { mutateAsync: uploadFiles } = useUploadFiles();
 
@@ -141,7 +141,7 @@ export function ChatInterface() {
 
     send(createChatMessage(prompt, imageUrls, uploadedFiles, timestamp));
     setOptimisticUserMessage(content);
-    dispatch(setMessageToSend(null));
+    setMessageToSend("");
   };
 
   const handleStop = () => {
@@ -156,10 +156,6 @@ export function ChatInterface() {
     setFeedbackPolarity(polarity);
   };
 
-  const isWaitingForUserInput =
-    curAgentState === AgentState.AWAITING_USER_INPUT ||
-    curAgentState === AgentState.FINISHED;
-
   // Create a ScrollProvider with the scroll hook values
   const scrollProviderValue = {
     scrollRef,
@@ -180,9 +176,7 @@ export function ChatInterface() {
           !optimisticUserMessage &&
           !userEventsExist && (
             <ChatSuggestions
-              onSuggestionsClick={(message) =>
-                dispatch(setMessageToSend(message))
-              }
+              onSuggestionsClick={(message) => setMessageToSend(message)}
             />
           )}
         {/* Note: We only hide chat suggestions when there's a user message */}
@@ -210,17 +204,20 @@ export function ChatInterface() {
 
         <div className="flex flex-col gap-[6px]">
           <div className="flex justify-between relative">
-            {events.length > 0 && (
-              <TrajectoryActions
-                onPositiveFeedback={() =>
-                  onClickShareFeedbackActionButton("positive")
-                }
-                onNegativeFeedback={() =>
-                  onClickShareFeedbackActionButton("negative")
-                }
-                isSaasMode={config?.APP_MODE === "saas"}
-              />
-            )}
+            <div className="flex items-center gap-1">
+              <ConfirmationModeEnabled />
+              {events.length > 0 && (
+                <TrajectoryActions
+                  onPositiveFeedback={() =>
+                    onClickShareFeedbackActionButton("positive")
+                  }
+                  onNegativeFeedback={() =>
+                    onClickShareFeedbackActionButton("negative")
+                  }
+                  isSaasMode={config?.APP_MODE === "saas"}
+                />
+              )}
+            </div>
 
             <div className="absolute left-1/2 transform -translate-x-1/2 bottom-0">
               {curAgentState === AgentState.RUNNING && <TypingIndicator />}
@@ -234,9 +231,6 @@ export function ChatInterface() {
           <InteractiveChatBox
             onSubmit={handleSendMessage}
             onStop={handleStop}
-            isWaitingForUserInput={isWaitingForUserInput}
-            hasSubstantiveAgentActions={hasSubstantiveAgentActions}
-            optimisticUserMessage={!!optimisticUserMessage}
           />
         </div>
 

frontend/src/components/features/chat/chat-message.tsx

@@ -55,7 +55,7 @@ export function ChatMessage({
       onMouseEnter={() => setIsHovering(true)}
       onMouseLeave={() => setIsHovering(false)}
       className={cn(
-        "rounded-xl relative w-fit max-w-full",
+        "rounded-xl relative w-fit max-w-full last:mb-4",
         "flex flex-col gap-2",
         type === "user" && " p-4 bg-tertiary self-end",
         type === "agent" && "mt-6 max-w-full bg-transparent",

frontend/src/components/features/chat/chat-suggestions.tsx

@@ -1,11 +1,10 @@
 import { useTranslation } from "react-i18next";
-import { useSelector } from "react-redux";
 import { motion, AnimatePresence } from "framer-motion";
 import { Suggestions } from "#/components/features/suggestions/suggestions";
 import { I18nKey } from "#/i18n/declaration";
 import BuildIt from "#/icons/build-it.svg?react";
 import { SUGGESTIONS } from "#/utils/suggestions";
-import { RootState } from "#/store";
+import { useConversationStore } from "#/state/conversation-store";
 
 interface ChatSuggestionsProps {
   onSuggestionsClick: (value: string) => void;
@@ -13,9 +12,7 @@ interface ChatSuggestionsProps {
 
 export function ChatSuggestions({ onSuggestionsClick }: ChatSuggestionsProps) {
   const { t } = useTranslation();
-  const shouldHideSuggestions = useSelector(
-    (state: RootState) => state.conversation.shouldHideSuggestions,
-  );
+  const { shouldHideSuggestions } = useConversationStore();
 
   return (
     <AnimatePresence>

frontend/src/components/features/chat/components/chat-input-actions.tsx

@@ -0,0 +1,34 @@
+import { ConversationStatus } from "#/types/conversation-status";
+import { ServerStatus } from "#/components/features/controls/server-status";
+import { AgentStatus } from "#/components/features/controls/agent-status";
+import { Tools } from "../../controls/tools";
+
+interface ChatInputActionsProps {
+  conversationStatus: ConversationStatus | null;
+  disabled: boolean;
+  handleStop: (onStop?: () => void) => void;
+  handleResumeAgent: () => void;
+  onStop?: () => void;
+}
+
+export function ChatInputActions({
+  conversationStatus,
+  disabled,
+  handleStop,
+  handleResumeAgent,
+  onStop,
+}: ChatInputActionsProps) {
+  return (
+    <div className="w-full flex items-center justify-between">
+      <div className="flex items-center gap-1">
+        <Tools />
+        <ServerStatus conversationStatus={conversationStatus} />
+      </div>
+      <AgentStatus
+        handleStop={() => handleStop(onStop)}
+        handleResumeAgent={handleResumeAgent}
+        disabled={disabled}
+      />
+    </div>
+  );
+}

frontend/src/components/features/chat/components/chat-input-container.tsx

@@ -0,0 +1,89 @@
+import React from "react";
+import { ConversationStatus } from "#/types/conversation-status";
+import { DragOver } from "../drag-over";
+import { UploadedFiles } from "../uploaded-files";
+import { ChatInputRow } from "./chat-input-row";
+import { ChatInputActions } from "./chat-input-actions";
+
+interface ChatInputContainerProps {
+  chatContainerRef: React.RefObject<HTMLDivElement | null>;
+  isDragOver: boolean;
+  disabled: boolean;
+  showButton: boolean;
+  buttonClassName: string;
+  conversationStatus: ConversationStatus | null;
+  chatInputRef: React.RefObject<HTMLDivElement | null>;
+  handleFileIconClick: (isDisabled: boolean) => void;
+  handleSubmit: () => void;
+  handleStop: (onStop?: () => void) => void;
+  handleResumeAgent: () => void;
+  onDragOver: (e: React.DragEvent, isDisabled: boolean) => void;
+  onDragLeave: (e: React.DragEvent, isDisabled: boolean) => void;
+  onDrop: (e: React.DragEvent, isDisabled: boolean) => void;
+  onInput: () => void;
+  onPaste: (e: React.ClipboardEvent) => void;
+  onKeyDown: (e: React.KeyboardEvent) => void;
+  onFocus?: () => void;
+  onBlur?: () => void;
+  onStop?: () => void;
+}
+
+export function ChatInputContainer({
+  chatContainerRef,
+  isDragOver,
+  disabled,
+  showButton,
+  buttonClassName,
+  conversationStatus,
+  chatInputRef,
+  handleFileIconClick,
+  handleSubmit,
+  handleStop,
+  handleResumeAgent,
+  onDragOver,
+  onDragLeave,
+  onDrop,
+  onInput,
+  onPaste,
+  onKeyDown,
+  onFocus,
+  onBlur,
+  onStop,
+}: ChatInputContainerProps) {
+  return (
+    <div
+      ref={chatContainerRef}
+      className="bg-[#25272D] box-border content-stretch flex flex-col items-start justify-center p-4 pt-3 relative rounded-[15px] w-full"
+      onDragOver={(e) => onDragOver(e, disabled)}
+      onDragLeave={(e) => onDragLeave(e, disabled)}
+      onDrop={(e) => onDrop(e, disabled)}
+    >
+      {/* Drag Over UI */}
+      {isDragOver && <DragOver />}
+
+      <UploadedFiles />
+
+      <ChatInputRow
+        chatInputRef={chatInputRef}
+        disabled={disabled}
+        showButton={showButton}
+        buttonClassName={buttonClassName}
+        handleFileIconClick={handleFileIconClick}
+        handleSubmit={handleSubmit}
+        onInput={onInput}
+        onPaste={onPaste}
+        onKeyDown={onKeyDown}
+        onFocus={onFocus}
+        onBlur={onBlur}
+      />
+
+      <ChatInputActions
+        conversationStatus={conversationStatus}
+        disabled={disabled}
+        handleStop={handleStop}
+        handleResumeAgent={handleResumeAgent}
+        onStop={onStop}
+      />
+    </div>
+  );
+}

frontend/src/components/features/chat/components/chat-input-field.tsx

@@ -0,0 +1,44 @@
+import React from "react";
+import { useTranslation } from "react-i18next";
+
+interface ChatInputFieldProps {
+  chatInputRef: React.RefObject<HTMLDivElement | null>;
+  onInput: () => void;
+  onPaste: (e: React.ClipboardEvent) => void;
+  onKeyDown: (e: React.KeyboardEvent) => void;
+  onFocus?: () => void;
+  onBlur?: () => void;
+}
+
+export function ChatInputField({
+  chatInputRef,
+  onInput,
+  onPaste,
+  onKeyDown,
+  onFocus,
+  onBlur,
+}: ChatInputFieldProps) {
+  const { t } = useTranslation();
+
+  return (
+    <div
+      className="box-border content-stretch flex flex-row items-center justify-start min-h-6 p-0 relative shrink-0 flex-1"
+      data-name="Text & caret"
+    >
+      <div className="basis-0 flex flex-col font-normal grow justify-center leading-[0] min-h-px min-w-px overflow-ellipsis overflow-hidden relative shrink-0 text-[#d0d9fa] text-[16px] text-left">
+        <div
+          ref={chatInputRef}
+          className="chat-input bg-transparent text-white text-[16px] font-normal leading-[20px] outline-none resize-none custom-scrollbar min-h-[20px] max-h-[400px] [text-overflow:inherit] [text-wrap-mode:inherit] [white-space-collapse:inherit] block whitespace-pre-wrap"
+          contentEditable
+          data-placeholder={t("SUGGESTIONS$WHAT_TO_BUILD")}
+          data-testid="chat-input"
+          onInput={onInput}
+          onPaste={onPaste}
+          onKeyDown={onKeyDown}
+          onFocus={onFocus}
+          onBlur={onBlur}
+        />
+      </div>
+    </div>
+  );
+}

frontend/src/components/features/chat/components/chat-input-grip.tsx

@@ -0,0 +1,38 @@
+import React from "react";
+import { cn } from "#/utils/utils";
+
+interface ChatInputGripProps {
+  gripRef: React.RefObject<HTMLDivElement | null>;
+  isGripVisible: boolean;
+  handleTopEdgeClick: (e: React.MouseEvent) => void;
+  handleGripMouseDown: (e: React.MouseEvent) => void;
+  handleGripTouchStart: (e: React.TouchEvent) => void;
+}
+
+export function ChatInputGrip({
+  gripRef,
+  isGripVisible,
+  handleTopEdgeClick,
+  handleGripMouseDown,
+  handleGripTouchStart,
+}: ChatInputGripProps) {
+  return (
+    <div
+      className="absolute -top-[12px] left-0 w-full h-6 lg:h-3 z-20 group"
+      id="resize-grip"
+      onClick={handleTopEdgeClick}
+    >
+      {/* Resize Grip - appears on hover of top edge area, when dragging, or when clicked */}
+      <div
+        ref={gripRef}
+        className={cn(
+          "absolute top-[4px] left-0 w-full h-[3px] bg-white cursor-ns-resize z-10 transition-opacity duration-200",
+          isGripVisible ? "opacity-100" : "opacity-0 group-hover:opacity-100",
+        )}
+        onMouseDown={handleGripMouseDown}
+        onTouchStart={handleGripTouchStart}
+        style={{ userSelect: "none" }}
+      />
+    </div>
+  );
+}

frontend/src/components/features/chat/components/chat-input-row.tsx

@@ -0,0 +1,62 @@
+import React from "react";
+import { cn } from "#/utils/utils";
+import { ChatAddFileButton } from "../chat-add-file-button";
+import { ChatSendButton } from "../chat-send-button";
+import { ChatInputField } from "./chat-input-field";
+
+interface ChatInputRowProps {
+  chatInputRef: React.RefObject<HTMLDivElement | null>;
+  disabled: boolean;
+  showButton: boolean;
+  buttonClassName: string;
+  handleFileIconClick: (isDisabled: boolean) => void;
+  handleSubmit: () => void;
+  onInput: () => void;
+  onPaste: (e: React.ClipboardEvent) => void;
+  onKeyDown: (e: React.KeyboardEvent) => void;
+  onFocus?: () => void;
+  onBlur?: () => void;
+}
+
+export function ChatInputRow({
+  chatInputRef,
+  disabled,
+  showButton,
+  buttonClassName,
+  handleFileIconClick,
+  handleSubmit,
+  onInput,
+  onPaste,
+  onKeyDown,
+  onFocus,
+  onBlur,
+}: ChatInputRowProps) {
+  return (
+    <div className="box-border content-stretch flex flex-row items-end justify-between p-0 relative shrink-0 w-full pb-[18px] gap-2">
+      <div className="basis-0 box-border content-stretch flex flex-row gap-4 grow items-end justify-start min-h-px min-w-px p-0 relative shrink-0">
+        <ChatAddFileButton
+          disabled={disabled}
+          handleFileIconClick={() => handleFileIconClick(disabled)}
+        />
+
+        <ChatInputField
+          chatInputRef={chatInputRef}
+          onInput={onInput}
+          onPaste={onPaste}
+          onKeyDown={onKeyDown}
+          onFocus={onFocus}
+          onBlur={onBlur}
+        />
+      </div>
+
+      {/* Send Button */}
+      {showButton && (
+        <ChatSendButton
+          buttonClassName={cn(buttonClassName, "translate-y-[3px]")}
+          handleSubmit={handleSubmit}
+          disabled={disabled}
+        />
+      )}
+    </div>
+  );
+}

frontend/src/components/features/chat/components/hidden-file-input.tsx

@@ -0,0 +1,23 @@
+import React from "react";
+
+interface HiddenFileInputProps {
+  fileInputRef: React.RefObject<HTMLInputElement | null>;
+  onChange: (e: React.ChangeEvent<HTMLInputElement>) => void;
+}
+
+export function HiddenFileInput({
+  fileInputRef,
+  onChange,
+}: HiddenFileInputProps) {
+  return (
+    <input
+      type="file"
+      ref={fileInputRef}
+      multiple
+      accept="*/*"
+      style={{ display: "none" }}
+      onChange={onChange}
+      data-testid="upload-image-input"
+    />
+  );
+}

frontend/src/components/features/chat/confirmation-mode-enabled.tsx

@@ -0,0 +1,29 @@
+import { useTranslation } from "react-i18next";
+import { Tooltip } from "@heroui/react";
+import { I18nKey } from "#/i18n/declaration";
+import LockIcon from "#/icons/lock.svg?react";
+import { useSettings } from "#/hooks/query/use-settings";
+
+function ConfirmationModeEnabled() {
+  const { t } = useTranslation();
+
+  const { data: settings } = useSettings();
+
+  if (!settings?.CONFIRMATION_MODE) {
+    return null;
+  }
+
+  return (
+    <Tooltip
+      content={t(I18nKey.COMMON$CONFIRMATION_MODE_ENABLED)}
+      closeDelay={100}
+      className="bg-white text-black hover:bg-transparent"
+    >
+      <div className="flex items-center justify-center w-[26px] h-[26px] rounded-lg bg-[#25272D]">
+        <LockIcon width={15} height={15} />
+      </div>
+    </Tooltip>
+  );
+}
+
+export default ConfirmationModeEnabled;

frontend/src/components/features/chat/custom-chat-input.tsx

@@ -1,25 +1,14 @@
-import React, { useRef, useCallback, useState, useEffect } from "react";
-import { useDispatch, useSelector } from "react-redux";
-import { useTranslation } from "react-i18next";
+import React, { useEffect } from "react";
 import { ConversationStatus } from "#/types/conversation-status";
-import { ChatSendButton } from "./chat-send-button";
-import { ChatAddFileButton } from "./chat-add-file-button";
-import { cn, isMobileDevice } from "#/utils/utils";
-import { useAutoResize } from "#/hooks/use-auto-resize";
-import { DragOver } from "./drag-over";
-import { UploadedFiles } from "./uploaded-files";
-import { Tools } from "../controls/tools";
-import {
-  clearAllFiles,
-  setShouldHideSuggestions,
-  setSubmittedMessage,
-  setMessageToSend,
-  setIsRightPanelShown,
-} from "#/state/conversation-slice";
-import { CHAT_INPUT } from "#/utils/constants";
-import { RootState } from "#/store";
-import { ServerStatus } from "../controls/server-status";
-import { AgentStatus } from "../controls/agent-status";
+import { useChatInputLogic } from "#/hooks/chat/use-chat-input-logic";
+import { useFileHandling } from "#/hooks/chat/use-file-handling";
+import { useGripResize } from "#/hooks/chat/use-grip-resize";
+import { useChatInputEvents } from "#/hooks/chat/use-chat-input-events";
+import { useChatSubmission } from "#/hooks/chat/use-chat-submission";
+import { ChatInputGrip } from "./components/chat-input-grip";
+import { ChatInputContainer } from "./components/chat-input-container";
+import { HiddenFileInput } from "./components/hidden-file-input";
+import { useConversationStore } from "#/state/conversation-store";
 
 export interface CustomChatInputProps {
   disabled?: boolean;
@@ -46,14 +35,12 @@ export function CustomChatInput({
   className = "",
   buttonClassName = "",
 }: CustomChatInputProps) {
-  const [isDragOver, setIsDragOver] = useState(false);
-  const [isGripVisible, setIsGripVisible] = useState(false);
-
-  const { messageToSend, submittedMessage, hasRightPanelToggled } = useSelector(
-    (state: RootState) => state.conversation,
-  );
-
-  const dispatch = useDispatch();
+  const {
+    submittedMessage,
+    clearAllFiles,
+    setShouldHideSuggestions,
+    setSubmittedMessage,
+  } = useConversationStore();
 
   // Disable input when conversation is stopped
   const isConversationStopped = conversationStatus === "STOPPED";
@@ -65,377 +52,108 @@ export function CustomChatInput({
       return;
     }
     onSubmit(submittedMessage);
-    dispatch(setSubmittedMessage(null));
-  }, [submittedMessage, disabled, onSubmit, dispatch]);
+    setSubmittedMessage(null);
+  }, [submittedMessage, disabled, onSubmit, setSubmittedMessage]);
 
-  const { t } = useTranslation();
-
-  const chatInputRef = useRef<HTMLDivElement>(null);
-  const fileInputRef = useRef<HTMLInputElement>(null);
-  const chatContainerRef = useRef<HTMLDivElement>(null);
-  const gripRef = useRef<HTMLDivElement>(null);
-
-  // Save current input value when drawer state changes
-  useEffect(() => {
-    if (chatInputRef.current) {
-      const currentText = chatInputRef.current?.innerText || "";
-      // Dispatch to save current input value when drawer state changes
-      dispatch(setMessageToSend(currentText));
-      dispatch(setIsRightPanelShown(hasRightPanelToggled));
-    }
-  }, [hasRightPanelToggled, dispatch]);
-
-  // Helper function to check if contentEditable is truly empty
-  const isContentEmpty = useCallback((): boolean => {
-    if (!chatInputRef.current) return true;
-    const text =
-      chatInputRef.current.innerText || chatInputRef.current.textContent || "";
-    return text.trim() === "";
-  }, []);
-
-  // Helper function to properly clear contentEditable for placeholder display
-  const clearEmptyContent = useCallback((): void => {
-    if (chatInputRef.current && isContentEmpty()) {
-      chatInputRef.current.innerHTML = "";
-      chatInputRef.current.textContent = "";
-    }
-  }, [isContentEmpty]);
-
-  // Drag state management callbacks
-  const handleDragStart = useCallback(() => {
-    // Keep grip visible during drag by adding a CSS class
-    if (gripRef.current) {
-      gripRef.current.classList.add("opacity-100");
-      gripRef.current.classList.remove("opacity-0");
-    }
-  }, []);
-
-  const handleDragEnd = useCallback(() => {
-    // Restore hover-based visibility
-    if (gripRef.current) {
-      gripRef.current.classList.remove("opacity-100");
-      gripRef.current.classList.add("opacity-0");
-    }
-  }, []);
-
-  // Handle click on top edge area to toggle grip visibility
-  const handleTopEdgeClick = (e: React.MouseEvent) => {
-    e.stopPropagation();
-    setIsGripVisible((prev) => !prev);
-  };
-
-  // Callback to handle height changes and manage suggestions visibility
-  const handleHeightChange = useCallback(
-    (height: number) => {
-      // Hide suggestions when input height exceeds the threshold
-      const shouldHideChatSuggestions = height > CHAT_INPUT.HEIGHT_THRESHOLD;
-      dispatch(setShouldHideSuggestions(shouldHideChatSuggestions));
-    },
-    [dispatch],
-  );
-
-  // Use the auto-resize hook with height change callback
+  // Custom hooks
   const {
+    chatInputRef,
+    messageToSend,
+    checkIsContentEmpty,
+    clearEmptyContentHandler,
+  } = useChatInputLogic();
+
+  const {
+    fileInputRef,
+    chatContainerRef,
+    isDragOver,
+    handleFileIconClick,
+    handleFileInputChange,
+    handleDragOver,
+    handleDragLeave,
+    handleDrop,
+  } = useFileHandling(onFilesPaste);
+
+  const {
+    gripRef,
+    isGripVisible,
+    handleTopEdgeClick,
     smartResize,
     handleGripMouseDown,
     handleGripTouchStart,
     increaseHeightForEmptyContent,
-  } = useAutoResize(chatInputRef, {
-    minHeight: 20,
-    maxHeight: 400,
-    onHeightChange: handleHeightChange,
-    onGripDragStart: handleDragStart,
-    onGripDragEnd: handleDragEnd,
-    value: messageToSend ?? undefined,
-    enableManualResize: true,
-  });
+  } = useGripResize(
+    chatInputRef as React.RefObject<HTMLDivElement | null>,
+    messageToSend,
+  );
+
+  const { handleSubmit, handleResumeAgent, handleStop } = useChatSubmission(
+    chatInputRef as React.RefObject<HTMLDivElement | null>,
+    fileInputRef as React.RefObject<HTMLInputElement | null>,
+    smartResize,
+    onSubmit,
+  );
+
+  const { handleInput, handlePaste, handleKeyDown, handleBlur, handleFocus } =
+    useChatInputEvents(
+      chatInputRef as React.RefObject<HTMLDivElement | null>,
+      smartResize,
+      increaseHeightForEmptyContent,
+      checkIsContentEmpty,
+      clearEmptyContentHandler,
+      onFocus,
+      onBlur,
+    );
 
   // Cleanup: reset suggestions visibility when component unmounts
   useEffect(
     () => () => {
-      dispatch(setShouldHideSuggestions(false));
-      dispatch(clearAllFiles());
+      setShouldHideSuggestions(false);
+      clearAllFiles();
     },
-    [dispatch],
+    [setShouldHideSuggestions, clearAllFiles],
   );
 
-  // Function to add files and notify parent
-  const addFiles = useCallback(
-    (files: File[]) => {
-      // Call onFilesPaste if provided with the new files
-      if (onFilesPaste && files.length > 0) {
-        onFilesPaste(files);
-      }
-    },
-    [onFilesPaste],
-  );
-
-  // File icon click handler
-  const handleFileIconClick = () => {
-    if (!isDisabled && fileInputRef.current) {
-      fileInputRef.current.click();
-    }
-  };
-
-  // File input change handler
-  const handleFileInputChange = (e: React.ChangeEvent<HTMLInputElement>) => {
-    const files = Array.from(e.target.files || []);
-    addFiles(files);
-  };
-
-  // Drag and drop event handlers
-  const handleDragOver = (e: React.DragEvent) => {
-    if (isDisabled) return;
-    e.preventDefault();
-    setIsDragOver(true);
-  };
-
-  const handleDragLeave = (e: React.DragEvent) => {
-    if (isDisabled) return;
-    e.preventDefault();
-    // Only remove drag-over class if we're leaving the container entirely
-    if (!chatContainerRef.current?.contains(e.relatedTarget as Node)) {
-      setIsDragOver(false);
-    }
-  };
-
-  const handleDrop = (e: React.DragEvent) => {
-    if (isDisabled) return;
-    e.preventDefault();
-    setIsDragOver(false);
-
-    const files = Array.from(e.dataTransfer.files);
-    addFiles(files);
-  };
-
-  // Send button click handler
-  const handleSubmit = () => {
-    const message = chatInputRef.current?.innerText || "";
-
-    if (message.trim()) {
-      onSubmit(message);
-
-      // Clear the input
-      if (chatInputRef.current) {
-        chatInputRef.current.textContent = "";
-      }
-      if (fileInputRef.current) {
-        fileInputRef.current.value = "";
-      }
-
-      // Reset height and show suggestions again
-      smartResize();
-    }
-  };
-
-  // Resume agent button click handler
-  const handleResumeAgent = () => {
-    const message = chatInputRef.current?.innerText || "continue";
-
-    onSubmit(message.trim());
-
-    // Clear the input
-    if (chatInputRef.current) {
-      chatInputRef.current.textContent = "";
-    }
-    if (fileInputRef.current) {
-      fileInputRef.current.value = "";
-    }
-
-    // Reset height and show suggestions again
-    smartResize();
-  };
-
-  // Handle stop button click
-  const handleStop = () => {
-    if (onStop) {
-      onStop();
-    }
-  };
-
-  // Handle input events
-  const handleInput = () => {
-    smartResize();
-
-    // Clear empty content to ensure placeholder shows
-    if (chatInputRef.current) {
-      clearEmptyContent();
-    }
-
-    // Ensure cursor stays visible when content is scrollable
-    if (!chatInputRef.current) {
-      return;
-    }
-
-    const selection = window.getSelection();
-    if (!selection || selection.rangeCount === 0) {
-      return;
-    }
-
-    const range = selection.getRangeAt(0);
-    if (
-      !range.getBoundingClientRect ||
-      !chatInputRef.current.getBoundingClientRect
-    ) {
-      return;
-    }
-
-    const rect = range.getBoundingClientRect();
-    const inputRect = chatInputRef.current.getBoundingClientRect();
-
-    // If cursor is below the visible area, scroll to show it
-    if (rect.bottom > inputRect.bottom) {
-      chatInputRef.current.scrollTop =
-        chatInputRef.current.scrollHeight - chatInputRef.current.clientHeight;
-    }
-  };
-
-  // Handle paste events to clean up formatting
-  const handlePaste = (e: React.ClipboardEvent) => {
-    e.preventDefault();
-
-    // Get plain text from clipboard
-    const text = e.clipboardData.getData("text/plain");
-
-    // Insert plain text
-    document.execCommand("insertText", false, text);
-
-    // Trigger resize
-    setTimeout(smartResize, 0);
-  };
-
-  // Handle key events
-  const handleKeyDown = (e: React.KeyboardEvent) => {
-    if (e.key !== "Enter") {
-      return;
-    }
-
-    if (isContentEmpty()) {
-      e.preventDefault();
-      increaseHeightForEmptyContent();
-      return;
-    }
-
-    // Original submit logic - only for desktop without shift key
-    if (!isMobileDevice() && !e.shiftKey && !disabled) {
-      e.preventDefault();
-      handleSubmit();
-    }
-  };
-
-  // Handle blur events to ensure placeholder shows when empty
-  const handleBlur = () => {
-    // Clear empty content to ensure placeholder shows
-    if (chatInputRef.current) {
-      clearEmptyContent();
-    }
-
-    // Call the original onBlur callback if provided
-    if (onBlur) {
-      onBlur();
-    }
-  };
-
   return (
     <div className={`w-full ${className}`}>
       {/* Hidden file input */}
-      <input
-        type="file"
-        ref={fileInputRef}
-        multiple
-        accept="*/*"
-        style={{ display: "none" }}
+      <HiddenFileInput
+        fileInputRef={fileInputRef}
         onChange={handleFileInputChange}
-        data-testid="upload-image-input"
       />
 
       {/* Container with grip */}
       <div className="relative w-full">
-        {/* Top edge hover area - invisible area that triggers grip visibility */}
-        <div
-          className="absolute -top-[12px] left-0 w-full h-6 lg:h-3 z-20 group"
-          id="resize-grip"
-          onClick={handleTopEdgeClick}
-        >
-          {/* Resize Grip - appears on hover of top edge area, when dragging, or when clicked */}
-          <div
-            ref={gripRef}
-            className={cn(
-              "absolute top-[4px] left-0 w-full h-[3px] bg-white cursor-ns-resize z-10 transition-opacity duration-200",
-              isGripVisible
-                ? "opacity-100"
-                : "opacity-0 group-hover:opacity-100",
-            )}
-            onMouseDown={handleGripMouseDown}
-            onTouchStart={handleGripTouchStart}
-            style={{ userSelect: "none" }}
-          />
-        </div>
+        <ChatInputGrip
+          gripRef={gripRef}
+          isGripVisible={isGripVisible}
+          handleTopEdgeClick={handleTopEdgeClick}
+          handleGripMouseDown={handleGripMouseDown}
+          handleGripTouchStart={handleGripTouchStart}
+        />
 
-        {/* Chat Input Component */}
-        <div
-          ref={chatContainerRef}
-          className="bg-[#25272D] box-border content-stretch flex flex-col items-start justify-center p-4 pt-3 relative rounded-[15px] w-full"
+        <ChatInputContainer
+          chatContainerRef={chatContainerRef}
+          isDragOver={isDragOver}
+          disabled={isDisabled}
+          showButton={showButton}
+          buttonClassName={buttonClassName}
+          conversationStatus={conversationStatus}
+          chatInputRef={chatInputRef}
+          handleFileIconClick={handleFileIconClick}
+          handleSubmit={handleSubmit}
+          handleStop={handleStop}
+          handleResumeAgent={handleResumeAgent}
           onDragOver={handleDragOver}
           onDragLeave={handleDragLeave}
           onDrop={handleDrop}
-        >
-          {/* Drag Over UI */}
-          {isDragOver && <DragOver />}
-
-          <UploadedFiles />
-          {/* Main Input Row */}
-          <div className="box-border content-stretch flex flex-row items-end justify-between p-0 relative shrink-0 w-full pb-[18px] gap-2">
-            <div className="basis-0 box-border content-stretch flex flex-row gap-4 grow items-end justify-start min-h-px min-w-px p-0 relative shrink-0">
-              <ChatAddFileButton
-                disabled={disabled}
-                handleFileIconClick={handleFileIconClick}
-              />
-
-              {/* Chat Input Area */}
-              <div
-                className="box-border content-stretch flex flex-row items-center justify-start min-h-6 p-0 relative shrink-0 flex-1"
-                data-name="Text & caret"
-              >
-                <div className="basis-0 flex flex-col font-normal grow justify-center leading-[0] min-h-px min-w-px overflow-ellipsis overflow-hidden relative shrink-0 text-[#d0d9fa] text-[16px] text-left">
-                  <div
-                    ref={chatInputRef}
-                    className="chat-input bg-transparent text-white text-[16px] font-normal leading-[20px] outline-none resize-none custom-scrollbar min-h-[20px] max-h-[400px] [text-overflow:inherit] [text-wrap-mode:inherit] [white-space-collapse:inherit] block whitespace-pre-wrap"
-                    contentEditable
-                    data-placeholder={t("SUGGESTIONS$WHAT_TO_BUILD")}
-                    data-testid="chat-input"
-                    onInput={handleInput}
-                    onPaste={handlePaste}
-                    onKeyDown={handleKeyDown}
-                    onFocus={onFocus}
-                    onBlur={handleBlur}
-                  />
-                </div>
-              </div>
-            </div>
-
-            {/* Send Button */}
-            {showButton && (
-              <ChatSendButton
-                buttonClassName={cn(buttonClassName, "translate-y-[3px]")}
-                handleSubmit={handleSubmit}
-                disabled={disabled}
-              />
-            )}
-          </div>
-
-          <div className="w-full flex items-center justify-between">
-            <div className="flex items-center gap-1">
-              <Tools />
-              <ServerStatus conversationStatus={conversationStatus} />
-            </div>
-            <AgentStatus
-              handleStop={handleStop}
-              handleResumeAgent={handleResumeAgent}
-              disabled={disabled}
-            />
-          </div>
-        </div>
+          onInput={handleInput}
+          onPaste={handlePaste}
+          onKeyDown={(e) => handleKeyDown(e, isDisabled, handleSubmit)}
+          onFocus={handleFocus}
+          onBlur={handleBlur}
+          onStop={onStop}
+        />
       </div>
     </div>
   );

frontend/src/components/features/chat/event-content-helpers/get-action-content.ts

@@ -1,4 +1,4 @@
-import { ActionSecurityRisk } from "#/state/security-analyzer-slice";
+import { ActionSecurityRisk } from "#/stores/security-analyzer-store";
 import {
   FileWriteAction,
   CommandAction,

frontend/src/components/features/chat/event-message-components/error-event-message.tsx

@@ -0,0 +1,68 @@
+import React from "react";
+import { OpenHandsObservation } from "#/types/core/observations";
+import { isErrorObservation } from "#/types/core/guards";
+import { ErrorMessage } from "../error-message";
+import { MicroagentStatusWrapper } from "./microagent-status-wrapper";
+import { LikertScaleWrapper } from "./likert-scale-wrapper";
+import { MicroagentStatus } from "#/types/microagent-status";
+
+interface ErrorEventMessageProps {
+  event: OpenHandsObservation;
+  microagentStatus?: MicroagentStatus | null;
+  microagentConversationId?: string;
+  microagentPRUrl?: string;
+  actions?: Array<{
+    icon: React.ReactNode;
+    onClick: () => void;
+    tooltip?: string;
+  }>;
+  isLastMessage: boolean;
+  isInLast10Actions: boolean;
+  config?: { APP_MODE?: string } | null;
+  isCheckingFeedback: boolean;
+  feedbackData: {
+    exists: boolean;
+    rating?: number;
+    reason?: string;
+  };
+}
+
+export function ErrorEventMessage({
+  event,
+  microagentStatus,
+  microagentConversationId,
+  microagentPRUrl,
+  actions,
+  isLastMessage,
+  isInLast10Actions,
+  config,
+  isCheckingFeedback,
+  feedbackData,
+}: ErrorEventMessageProps) {
+  if (!isErrorObservation(event)) {
+    return null;
+  }
+
+  return (
+    <div>
+      <ErrorMessage
+        errorId={event.extras.error_id}
+        defaultMessage={event.message}
+      />
+      <MicroagentStatusWrapper
+        microagentStatus={microagentStatus}
+        microagentConversationId={microagentConversationId}
+        microagentPRUrl={microagentPRUrl}
+        actions={actions}
+      />
+      <LikertScaleWrapper
+        event={event}
+        isLastMessage={isLastMessage}
+        isInLast10Actions={isInLast10Actions}
+        config={config}
+        isCheckingFeedback={isCheckingFeedback}
+        feedbackData={feedbackData}
+      />
+    </div>
+  );
+}

frontend/src/components/features/chat/event-message-components/finish-event-message.tsx

@@ -0,0 +1,70 @@
+import React from "react";
+import { OpenHandsAction } from "#/types/core/actions";
+import { isFinishAction } from "#/types/core/guards";
+import { ChatMessage } from "../chat-message";
+import { MicroagentStatusWrapper } from "./microagent-status-wrapper";
+import { LikertScaleWrapper } from "./likert-scale-wrapper";
+import { getEventContent } from "../event-content-helpers/get-event-content";
+import { MicroagentStatus } from "#/types/microagent-status";
+
+interface FinishEventMessageProps {
+  event: OpenHandsAction;
+  microagentStatus?: MicroagentStatus | null;
+  microagentConversationId?: string;
+  microagentPRUrl?: string;
+  actions?: Array<{
+    icon: React.ReactNode;
+    onClick: () => void;
+    tooltip?: string;
+  }>;
+  isLastMessage: boolean;
+  isInLast10Actions: boolean;
+  config?: { APP_MODE?: string } | null;
+  isCheckingFeedback: boolean;
+  feedbackData: {
+    exists: boolean;
+    rating?: number;
+    reason?: string;
+  };
+}
+
+export function FinishEventMessage({
+  event,
+  microagentStatus,
+  microagentConversationId,
+  microagentPRUrl,
+  actions,
+  isLastMessage,
+  isInLast10Actions,
+  config,
+  isCheckingFeedback,
+  feedbackData,
+}: FinishEventMessageProps) {
+  if (!isFinishAction(event)) {
+    return null;
+  }
+
+  return (
+    <>
+      <ChatMessage
+        type="agent"
+        message={getEventContent(event).details}
+        actions={actions}
+      />
+      <MicroagentStatusWrapper
+        microagentStatus={microagentStatus}
+        microagentConversationId={microagentConversationId}
+        microagentPRUrl={microagentPRUrl}
+        actions={actions}
+      />
+      <LikertScaleWrapper
+        event={event}
+        isLastMessage={isLastMessage}
+        isInLast10Actions={isInLast10Actions}
+        config={config}
+        isCheckingFeedback={isCheckingFeedback}
+        feedbackData={feedbackData}
+      />
+    </>
+  );
+}

frontend/src/components/features/chat/event-message-components/generic-event-message-wrapper.tsx

@@ -0,0 +1,45 @@
+import React from "react";
+import { OpenHandsAction } from "#/types/core/actions";
+import { OpenHandsObservation } from "#/types/core/observations";
+import { isOpenHandsAction, isOpenHandsObservation } from "#/types/core/guards";
+import { ChatMessage } from "../chat-message";
+import { GenericEventMessage } from "../generic-event-message";
+import { ConfirmationButtons } from "#/components/shared/buttons/confirmation-buttons";
+import { getEventContent } from "../event-content-helpers/get-event-content";
+import { getObservationResult } from "../event-content-helpers/get-observation-result";
+
+const hasThoughtProperty = (
+  obj: Record<string, unknown>,
+): obj is { thought: string } => "thought" in obj && !!obj.thought;
+
+interface GenericEventMessageWrapperProps {
+  event: OpenHandsAction | OpenHandsObservation;
+  shouldShowConfirmationButtons: boolean;
+}
+
+export function GenericEventMessageWrapper({
+  event,
+  shouldShowConfirmationButtons,
+}: GenericEventMessageWrapperProps) {
+  return (
+    <div>
+      {isOpenHandsAction(event) &&
+        hasThoughtProperty(event.args) &&
+        event.action !== "think" && (
+          <ChatMessage type="agent" message={event.args.thought} />
+        )}
+
+      <GenericEventMessage
+        title={getEventContent(event).title}
+        details={getEventContent(event).details}
+        success={
+          isOpenHandsObservation(event)
+            ? getObservationResult(event)
+            : undefined
+        }
+      />
+
+      {shouldShowConfirmationButtons && <ConfirmationButtons />}
+    </div>
+  );
+}

frontend/src/components/features/chat/event-message-components/index.ts

@@ -0,0 +1,10 @@
+export { ErrorEventMessage } from "./error-event-message";
+export { UserAssistantEventMessage } from "./user-assistant-event-message";
+export { FinishEventMessage } from "./finish-event-message";
+export { RejectEventMessage } from "./reject-event-message";
+export { McpEventMessage } from "./mcp-event-message";
+export { TaskTrackingEventMessage } from "./task-tracking-event-message";
+export { ObservationPairEventMessage } from "./observation-pair-event-message";
+export { GenericEventMessageWrapper } from "./generic-event-message-wrapper";
+export { MicroagentStatusWrapper } from "./microagent-status-wrapper";
+export { LikertScaleWrapper } from "./likert-scale-wrapper";

frontend/src/components/features/chat/event-message-components/likert-scale-wrapper.tsx

@@ -0,0 +1,50 @@
+import React from "react";
+import { OpenHandsAction } from "#/types/core/actions";
+import { OpenHandsObservation } from "#/types/core/observations";
+import { isErrorObservation } from "#/types/core/guards";
+import { LikertScale } from "../../feedback/likert-scale";
+
+interface LikertScaleWrapperProps {
+  event: OpenHandsAction | OpenHandsObservation;
+  isLastMessage: boolean;
+  isInLast10Actions: boolean;
+  config?: { APP_MODE?: string } | null;
+  isCheckingFeedback: boolean;
+  feedbackData: {
+    exists: boolean;
+    rating?: number;
+    reason?: string;
+  };
+}
+
+export function LikertScaleWrapper({
+  event,
+  isLastMessage,
+  isInLast10Actions,
+  config,
+  isCheckingFeedback,
+  feedbackData,
+}: LikertScaleWrapperProps) {
+  if (config?.APP_MODE !== "saas" || isCheckingFeedback) {
+    return null;
+  }
+
+  // For error observations, show if in last 10 actions
+  // For other events, show only if it's the last message
+  const shouldShow = isErrorObservation(event)
+    ? isInLast10Actions
+    : isLastMessage;
+
+  if (!shouldShow) {
+    return null;
+  }
+
+  return (
+    <LikertScale
+      eventId={event.id}
+      initiallySubmitted={feedbackData.exists}
+      initialRating={feedbackData.rating}
+      initialReason={feedbackData.reason}
+    />
+  );
+}

frontend/src/components/features/chat/event-message-components/mcp-event-message.tsx

@@ -0,0 +1,33 @@
+import React from "react";
+import { OpenHandsObservation } from "#/types/core/observations";
+import { isMcpObservation } from "#/types/core/guards";
+import { GenericEventMessage } from "../generic-event-message";
+import { MCPObservationContent } from "../mcp-observation-content";
+import { ConfirmationButtons } from "#/components/shared/buttons/confirmation-buttons";
+import { getEventContent } from "../event-content-helpers/get-event-content";
+import { getObservationResult } from "../event-content-helpers/get-observation-result";
+
+interface McpEventMessageProps {
+  event: OpenHandsObservation;
+  shouldShowConfirmationButtons: boolean;
+}
+
+export function McpEventMessage({
+  event,
+  shouldShowConfirmationButtons,
+}: McpEventMessageProps) {
+  if (!isMcpObservation(event)) {
+    return null;
+  }
+
+  return (
+    <div>
+      <GenericEventMessage
+        title={getEventContent(event).title}
+        details={<MCPObservationContent event={event} />}
+        success={getObservationResult(event)}
+      />
+      {shouldShowConfirmationButtons && <ConfirmationButtons />}
+    </div>
+  );
+}

frontend/src/components/features/chat/event-message-components/microagent-status-wrapper.tsx

@@ -0,0 +1,33 @@
+import React from "react";
+import { MicroagentStatus } from "#/types/microagent-status";
+import { MicroagentStatusIndicator } from "../microagent/microagent-status-indicator";
+
+interface MicroagentStatusWrapperProps {
+  microagentStatus?: MicroagentStatus | null;
+  microagentConversationId?: string;
+  microagentPRUrl?: string;
+  actions?: Array<{
+    icon: React.ReactNode;
+    onClick: () => void;
+    tooltip?: string;
+  }>;
+}
+
+export function MicroagentStatusWrapper({
+  microagentStatus,
+  microagentConversationId,
+  microagentPRUrl,
+  actions,
+}: MicroagentStatusWrapperProps) {
+  if (!microagentStatus || !actions) {
+    return null;
+  }
+
+  return (
+    <MicroagentStatusIndicator
+      status={microagentStatus}
+      conversationId={microagentConversationId}
+      prUrl={microagentPRUrl}
+    />
+  );
+}

frontend/src/components/features/chat/event-message-components/observation-pair-event-message.tsx

@@ -0,0 +1,61 @@
+import React from "react";
+import { OpenHandsAction } from "#/types/core/actions";
+import { isOpenHandsAction } from "#/types/core/guards";
+import { ChatMessage } from "../chat-message";
+import { MicroagentStatusWrapper } from "./microagent-status-wrapper";
+import { MicroagentStatus } from "#/types/microagent-status";
+
+const hasThoughtProperty = (
+  obj: Record<string, unknown>,
+): obj is { thought: string } => "thought" in obj && !!obj.thought;
+
+interface ObservationPairEventMessageProps {
+  event: OpenHandsAction;
+  microagentStatus?: MicroagentStatus | null;
+  microagentConversationId?: string;
+  microagentPRUrl?: string;
+  actions?: Array<{
+    icon: React.ReactNode;
+    onClick: () => void;
+    tooltip?: string;
+  }>;
+}
+
+export function ObservationPairEventMessage({
+  event,
+  microagentStatus,
+  microagentConversationId,
+  microagentPRUrl,
+  actions,
+}: ObservationPairEventMessageProps) {
+  if (!isOpenHandsAction(event)) {
+    return null;
+  }
+
+  if (hasThoughtProperty(event.args) && event.action !== "think") {
+    return (
+      <div>
+        <ChatMessage
+          type="agent"
+          message={event.args.thought}
+          actions={actions}
+        />
+        <MicroagentStatusWrapper
+          microagentStatus={microagentStatus}
+          microagentConversationId={microagentConversationId}
+          microagentPRUrl={microagentPRUrl}
+          actions={actions}
+        />
+      </div>
+    );
+  }
+
+  return (
+    <MicroagentStatusWrapper
+      microagentStatus={microagentStatus}
+      microagentConversationId={microagentConversationId}
+      microagentPRUrl={microagentPRUrl}
+      actions={actions}
+    />
+  );
+}

frontend/src/components/features/chat/event-message-components/reject-event-message.tsx

@@ -0,0 +1,20 @@
+import React from "react";
+import { OpenHandsObservation } from "#/types/core/observations";
+import { isRejectObservation } from "#/types/core/guards";
+import { ChatMessage } from "../chat-message";
+
+interface RejectEventMessageProps {
+  event: OpenHandsObservation;
+}
+
+export function RejectEventMessage({ event }: RejectEventMessageProps) {
+  if (!isRejectObservation(event)) {
+    return null;
+  }
+
+  return (
+    <div>
+      <ChatMessage type="agent" message={event.content} />
+    </div>
+  );
+}

frontend/src/components/features/chat/event-message-components/task-tracking-event-message.tsx

@@ -0,0 +1,50 @@
+import React from "react";
+import { useTranslation } from "react-i18next";
+import { OpenHandsObservation } from "#/types/core/observations";
+import { isTaskTrackingObservation } from "#/types/core/guards";
+import { GenericEventMessage } from "../generic-event-message";
+import { TaskTrackingObservationContent } from "../task-tracking-observation-content";
+import { ConfirmationButtons } from "#/components/shared/buttons/confirmation-buttons";
+import { getObservationResult } from "../event-content-helpers/get-observation-result";
+
+interface TaskTrackingEventMessageProps {
+  event: OpenHandsObservation;
+  shouldShowConfirmationButtons: boolean;
+}
+
+export function TaskTrackingEventMessage({
+  event,
+  shouldShowConfirmationButtons,
+}: TaskTrackingEventMessageProps) {
+  const { t } = useTranslation();
+
+  if (!isTaskTrackingObservation(event)) {
+    return null;
+  }
+
+  const { command } = event.extras;
+  let title: React.ReactNode;
+  let initiallyExpanded = false;
+
+  // Determine title and expansion state based on command
+  if (command === "plan") {
+    title = t("OBSERVATION_MESSAGE$TASK_TRACKING_PLAN");
+    initiallyExpanded = true;
+  } else {
+    // command === "view"
+    title = t("OBSERVATION_MESSAGE$TASK_TRACKING_VIEW");
+    initiallyExpanded = false;
+  }
+
+  return (
+    <div>
+      <GenericEventMessage
+        title={title}
+        details={<TaskTrackingObservationContent event={event} />}
+        success={getObservationResult(event)}
+        initiallyExpanded={initiallyExpanded}
+      />
+      {shouldShowConfirmationButtons && <ConfirmationButtons />}
+    </div>
+  );
+}

frontend/src/components/features/chat/event-message-components/user-assistant-event-message.tsx

@@ -0,0 +1,83 @@
+import React from "react";
+import { OpenHandsAction } from "#/types/core/actions";
+import { isUserMessage, isAssistantMessage } from "#/types/core/guards";
+import { ChatMessage } from "../chat-message";
+import { ImageCarousel } from "../../images/image-carousel";
+import { FileList } from "../../files/file-list";
+import { ConfirmationButtons } from "#/components/shared/buttons/confirmation-buttons";
+import { MicroagentStatusWrapper } from "./microagent-status-wrapper";
+import { LikertScaleWrapper } from "./likert-scale-wrapper";
+import { parseMessageFromEvent } from "../event-content-helpers/parse-message-from-event";
+import { MicroagentStatus } from "#/types/microagent-status";
+
+interface UserAssistantEventMessageProps {
+  event: OpenHandsAction;
+  shouldShowConfirmationButtons: boolean;
+  microagentStatus?: MicroagentStatus | null;
+  microagentConversationId?: string;
+  microagentPRUrl?: string;
+  actions?: Array<{
+    icon: React.ReactNode;
+    onClick: () => void;
+    tooltip?: string;
+  }>;
+  isLastMessage: boolean;
+  isInLast10Actions: boolean;
+  config?: { APP_MODE?: string } | null;
+  isCheckingFeedback: boolean;
+  feedbackData: {
+    exists: boolean;
+    rating?: number;
+    reason?: string;
+  };
+}
+
+export function UserAssistantEventMessage({
+  event,
+  shouldShowConfirmationButtons,
+  microagentStatus,
+  microagentConversationId,
+  microagentPRUrl,
+  actions,
+  isLastMessage,
+  isInLast10Actions,
+  config,
+  isCheckingFeedback,
+  feedbackData,
+}: UserAssistantEventMessageProps) {
+  if (!isUserMessage(event) && !isAssistantMessage(event)) {
+    return null;
+  }
+
+  const message = parseMessageFromEvent(event);
+
+  return (
+    <>
+      <ChatMessage type={event.source} message={message} actions={actions}>
+        {event.args.image_urls && event.args.image_urls.length > 0 && (
+          <ImageCarousel size="small" images={event.args.image_urls} />
+        )}
+        {event.args.file_urls && event.args.file_urls.length > 0 && (
+          <FileList files={event.args.file_urls} />
+        )}
+        {shouldShowConfirmationButtons && <ConfirmationButtons />}
+      </ChatMessage>
+      <MicroagentStatusWrapper
+        microagentStatus={microagentStatus}
+        microagentConversationId={microagentConversationId}
+        microagentPRUrl={microagentPRUrl}
+        actions={actions}
+      />
+      {isAssistantMessage(event) && event.action === "message" && (
+        <LikertScaleWrapper
+          event={event}
+          isLastMessage={isLastMessage}
+          isInLast10Actions={isInLast10Actions}
+          config={config}
+          isCheckingFeedback={isCheckingFeedback}
+          feedbackData={feedbackData}
+        />
+      )}
+    </>
+  );
+}

frontend/src/components/features/chat/event-message.tsx

@@ -1,39 +1,29 @@
 import React from "react";
-import { useTranslation } from "react-i18next";
-import { ConfirmationButtons } from "#/components/shared/buttons/confirmation-buttons";
 import { OpenHandsAction } from "#/types/core/actions";
 import {
   isUserMessage,
   isErrorObservation,
   isAssistantMessage,
   isOpenHandsAction,
-  isOpenHandsObservation,
   isFinishAction,
   isRejectObservation,
   isMcpObservation,
   isTaskTrackingObservation,
 } from "#/types/core/guards";
 import { OpenHandsObservation } from "#/types/core/observations";
-import { ImageCarousel } from "../images/image-carousel";
-import { ChatMessage } from "./chat-message";
-import { ErrorMessage } from "./error-message";
-import { MCPObservationContent } from "./mcp-observation-content";
-import { TaskTrackingObservationContent } from "./task-tracking-observation-content";
-import { getObservationResult } from "./event-content-helpers/get-observation-result";
-import { getEventContent } from "./event-content-helpers/get-event-content";
-import { GenericEventMessage } from "./generic-event-message";
 import { MicroagentStatus } from "#/types/microagent-status";
-import { MicroagentStatusIndicator } from "./microagent/microagent-status-indicator";
-import { FileList } from "../files/file-list";
-import { parseMessageFromEvent } from "./event-content-helpers/parse-message-from-event";
-import { LikertScale } from "../feedback/likert-scale";
-
 import { useConfig } from "#/hooks/query/use-config";
 import { useFeedbackExists } from "#/hooks/query/use-feedback-exists";
-
-const hasThoughtProperty = (
-  obj: Record<string, unknown>,
-): obj is { thought: string } => "thought" in obj && !!obj.thought;
+import {
+  ErrorEventMessage,
+  UserAssistantEventMessage,
+  FinishEventMessage,
+  RejectEventMessage,
+  McpEventMessage,
+  TaskTrackingEventMessage,
+  ObservationPairEventMessage,
+  GenericEventMessageWrapper,
+} from "./event-message-components";
 
 interface EventMessageProps {
   event: OpenHandsAction | OpenHandsObservation;
@@ -51,6 +41,7 @@ interface EventMessageProps {
   isInLast10Actions: boolean;
 }
 
+/* eslint-disable react/jsx-props-no-spreading */
 export function EventMessage({
   event,
   hasObservationPair,
@@ -62,7 +53,6 @@ export function EventMessage({
   actions,
   isInLast10Actions,
 }: EventMessageProps) {
-  const { t } = useTranslation();
   const shouldShowConfirmationButtons =
     isLastMessage && event.source === "agent" && isAwaitingUserConfirmation;
 
@@ -73,194 +63,83 @@ export function EventMessage({
     isLoading: isCheckingFeedback,
   } = useFeedbackExists(event.id);
 
-  const renderLikertScale = () => {
-    if (config?.APP_MODE !== "saas" || isCheckingFeedback) {
-      return null;
-    }
-
-    // For error observations, show if in last 10 actions
-    // For other events, show only if it's the last message
-    const shouldShow = isErrorObservation(event)
-      ? isInLast10Actions
-      : isLastMessage;
-
-    if (!shouldShow) {
-      return null;
-    }
-
-    return (
-      <LikertScale
-        eventId={event.id}
-        initiallySubmitted={feedbackData.exists}
-        initialRating={feedbackData.rating}
-        initialReason={feedbackData.reason}
-      />
-    );
+  // Common props for components that need them
+  const commonProps = {
+    microagentStatus,
+    microagentConversationId,
+    microagentPRUrl,
+    actions,
+    isLastMessage,
+    isInLast10Actions,
+    config,
+    isCheckingFeedback,
+    feedbackData,
   };
 
+  // Error observations
   if (isErrorObservation(event)) {
-    return (
-      <div>
-        <ErrorMessage
-          errorId={event.extras.error_id}
-          defaultMessage={event.message}
-        />
-        {microagentStatus && actions && (
-          <MicroagentStatusIndicator
-            status={microagentStatus}
-            conversationId={microagentConversationId}
-            prUrl={microagentPRUrl}
-          />
-        )}
-        {renderLikertScale()}
-      </div>
-    );
+    return <ErrorEventMessage event={event} {...commonProps} />;
   }
 
+  // Observation pairs with OpenHands actions
   if (hasObservationPair && isOpenHandsAction(event)) {
-    if (hasThoughtProperty(event.args) && event.action !== "think") {
-      return (
-        <div>
-          <ChatMessage
-            type="agent"
-            message={event.args.thought}
-            actions={actions}
-          />
-          {microagentStatus && actions && (
-            <MicroagentStatusIndicator
-              status={microagentStatus}
-              conversationId={microagentConversationId}
-              prUrl={microagentPRUrl}
-            />
-          )}
-        </div>
-      );
-    }
-    return microagentStatus && actions ? (
-      <MicroagentStatusIndicator
-        status={microagentStatus}
-        conversationId={microagentConversationId}
-        prUrl={microagentPRUrl}
+    return (
+      <ObservationPairEventMessage
+        event={event}
+        microagentStatus={microagentStatus}
+        microagentConversationId={microagentConversationId}
+        microagentPRUrl={microagentPRUrl}
+        actions={actions}
       />
-    ) : null;
+    );
   }
 
+  // Finish actions
   if (isFinishAction(event)) {
-    return (
-      <>
-        <ChatMessage
-          type="agent"
-          message={getEventContent(event).details}
-          actions={actions}
-        />
-        {microagentStatus && actions && (
-          <MicroagentStatusIndicator
-            status={microagentStatus}
-            conversationId={microagentConversationId}
-            prUrl={microagentPRUrl}
-          />
-        )}
-        {renderLikertScale()}
-      </>
-    );
+    return <FinishEventMessage event={event} {...commonProps} />;
   }
 
+  // User and assistant messages
   if (isUserMessage(event) || isAssistantMessage(event)) {
-    const message = parseMessageFromEvent(event);
-
     return (
-      <>
-        <ChatMessage type={event.source} message={message} actions={actions}>
-          {event.args.image_urls && event.args.image_urls.length > 0 && (
-            <ImageCarousel size="small" images={event.args.image_urls} />
-          )}
-          {event.args.file_urls && event.args.file_urls.length > 0 && (
-            <FileList files={event.args.file_urls} />
-          )}
-          {shouldShowConfirmationButtons && <ConfirmationButtons />}
-        </ChatMessage>
-        {microagentStatus && actions && (
-          <MicroagentStatusIndicator
-            status={microagentStatus}
-            conversationId={microagentConversationId}
-            prUrl={microagentPRUrl}
-          />
-        )}
-        {isAssistantMessage(event) &&
-          event.action === "message" &&
-          renderLikertScale()}
-      </>
+      <UserAssistantEventMessage
+        event={event}
+        shouldShowConfirmationButtons={shouldShowConfirmationButtons}
+        {...commonProps}
+      />
     );
   }
 
+  // Reject observations
   if (isRejectObservation(event)) {
-    return (
-      <div>
-        <ChatMessage type="agent" message={event.content} />
-      </div>
-    );
+    return <RejectEventMessage event={event} />;
   }
 
+  // MCP observations
   if (isMcpObservation(event)) {
     return (
-      <div>
-        <GenericEventMessage
-          title={getEventContent(event).title}
-          details={<MCPObservationContent event={event} />}
-          success={getObservationResult(event)}
-        />
-        {shouldShowConfirmationButtons && <ConfirmationButtons />}
-      </div>
-    );
-  }
-
-  if (isTaskTrackingObservation(event)) {
-    const { command } = event.extras;
-    let title: React.ReactNode;
-    let initiallyExpanded = false;
-
-    // Determine title and expansion state based on command
-    if (command === "plan") {
-      title = t("OBSERVATION_MESSAGE$TASK_TRACKING_PLAN");
-      initiallyExpanded = true;
-    } else {
-      // command === "view"
-      title = t("OBSERVATION_MESSAGE$TASK_TRACKING_VIEW");
-      initiallyExpanded = false;
-    }
-
-    return (
-      <div>
-        <GenericEventMessage
-          title={title}
-          details={<TaskTrackingObservationContent event={event} />}
-          success={getObservationResult(event)}
-          initiallyExpanded={initiallyExpanded}
-        />
-        {shouldShowConfirmationButtons && <ConfirmationButtons />}
-      </div>
-    );
-  }
-
-  return (
-    <div>
-      {isOpenHandsAction(event) &&
-        hasThoughtProperty(event.args) &&
-        event.action !== "think" && (
-          <ChatMessage type="agent" message={event.args.thought} />
-        )}
-
-      <GenericEventMessage
-        title={getEventContent(event).title}
-        details={getEventContent(event).details}
-        success={
-          isOpenHandsObservation(event)
-            ? getObservationResult(event)
-            : undefined
-        }
+      <McpEventMessage
+        event={event}
+        shouldShowConfirmationButtons={shouldShowConfirmationButtons}
       />
+    );
+  }
 
-      {shouldShowConfirmationButtons && <ConfirmationButtons />}
-    </div>
+  // Task tracking observations
+  if (isTaskTrackingObservation(event)) {
+    return (
+      <TaskTrackingEventMessage
+        event={event}
+        shouldShowConfirmationButtons={shouldShowConfirmationButtons}
+      />
+    );
+  }
+
+  // Generic fallback
+  return (
+    <GenericEventMessageWrapper
+      event={event}
+      shouldShowConfirmationButtons={shouldShowConfirmationButtons}
+    />
   );
 }

frontend/src/components/features/chat/git-control-bar-pr-button.tsx

@@ -8,14 +8,12 @@ import { Provider } from "#/types/settings";
 
 interface GitControlBarPrButtonProps {
   onSuggestionsClick: (value: string) => void;
-  isEnabled: boolean;
   hasRepository: boolean;
   currentGitProvider: Provider;
 }
 
 export function GitControlBarPrButton({
   onSuggestionsClick,
-  isEnabled,
   hasRepository,
   currentGitProvider,
 }: GitControlBarPrButtonProps) {
@@ -24,7 +22,7 @@ export function GitControlBarPrButton({
   const { providers } = useUserProviders();
 
   const providersAreSet = providers.length > 0;
-  const isButtonEnabled = isEnabled && providersAreSet && hasRepository;
+  const isButtonEnabled = providersAreSet && hasRepository;
 
   const handlePrClick = () => {
     posthog.capture("create_pr_button_clicked");

frontend/src/components/features/chat/git-control-bar-pull-button.tsx

@@ -8,12 +8,10 @@ import { I18nKey } from "#/i18n/declaration";
 
 interface GitControlBarPullButtonProps {
   onSuggestionsClick: (value: string) => void;
-  isEnabled: boolean;
 }
 
 export function GitControlBarPullButton({
   onSuggestionsClick,
-  isEnabled,
 }: GitControlBarPullButtonProps) {
   const { t } = useTranslation();
 
@@ -22,7 +20,7 @@ export function GitControlBarPullButton({
 
   const providersAreSet = providers.length > 0;
   const hasRepository = conversation?.selected_repository;
-  const isButtonEnabled = isEnabled && providersAreSet && hasRepository;
+  const isButtonEnabled = providersAreSet && hasRepository;
 
   const handlePullClick = () => {
     posthog.capture("pull_button_clicked");

frontend/src/components/features/chat/git-control-bar-push-button.tsx

@@ -8,14 +8,12 @@ import { Provider } from "#/types/settings";
 
 interface GitControlBarPushButtonProps {
   onSuggestionsClick: (value: string) => void;
-  isEnabled: boolean;
   hasRepository: boolean;
   currentGitProvider: Provider;
 }
 
 export function GitControlBarPushButton({
   onSuggestionsClick,
-  isEnabled,
   hasRepository,
   currentGitProvider,
 }: GitControlBarPushButtonProps) {
@@ -24,7 +22,7 @@ export function GitControlBarPushButton({
   const { providers } = useUserProviders();
 
   const providersAreSet = providers.length > 0;
-  const isButtonEnabled = isEnabled && providersAreSet && hasRepository;
+  const isButtonEnabled = providersAreSet && hasRepository;
 
   const handlePushClick = () => {
     posthog.capture("push_button_clicked");

frontend/src/components/features/chat/git-control-bar.tsx

@@ -11,17 +11,9 @@ import { GitControlBarTooltipWrapper } from "./git-control-bar-tooltip-wrapper";
 
 interface GitControlBarProps {
   onSuggestionsClick: (value: string) => void;
-  isWaitingForUserInput: boolean;
-  hasSubstantiveAgentActions: boolean;
-  optimisticUserMessage: boolean;
 }
 
-export function GitControlBar({
-  onSuggestionsClick,
-  isWaitingForUserInput,
-  hasSubstantiveAgentActions,
-  optimisticUserMessage,
-}: GitControlBarProps) {
+export function GitControlBar({ onSuggestionsClick }: GitControlBarProps) {
   const { t } = useTranslation();
 
   const { data: conversation } = useActiveConversation();
@@ -30,12 +22,6 @@ export function GitControlBar({
   const gitProvider = conversation?.git_provider as Provider;
   const selectedBranch = conversation?.selected_branch;
 
-  // Button is enabled when the agent is waiting for user input, has substantive actions, and no optimistic message
-  const isButtonEnabled =
-    isWaitingForUserInput &&
-    hasSubstantiveAgentActions &&
-    !optimisticUserMessage;
-
   const hasRepository = !!selectedRepository;
 
   return (
@@ -73,7 +59,6 @@ export function GitControlBar({
             >
               <GitControlBarPullButton
                 onSuggestionsClick={onSuggestionsClick}
-                isEnabled={isButtonEnabled}
               />
             </GitControlBarTooltipWrapper>
 
@@ -84,7 +69,6 @@ export function GitControlBar({
             >
               <GitControlBarPushButton
                 onSuggestionsClick={onSuggestionsClick}
-                isEnabled={isButtonEnabled}
                 hasRepository={hasRepository}
                 currentGitProvider={gitProvider}
               />
@@ -97,7 +81,6 @@ export function GitControlBar({
             >
               <GitControlBarPrButton
                 onSuggestionsClick={onSuggestionsClick}
-                isEnabled={isButtonEnabled}
                 hasRepository={hasRepository}
                 currentGitProvider={gitProvider}
               />

frontend/src/components/features/chat/interactive-chat-box.tsx

@@ -1,44 +1,38 @@
-import { useSelector, useDispatch } from "react-redux";
+import { useSelector } from "react-redux";
 import { isFileImage } from "#/utils/is-file-image";
 import { displayErrorToast } from "#/utils/custom-toast-handlers";
 import { validateFiles } from "#/utils/file-validation";
 import { CustomChatInput } from "./custom-chat-input";
-import { RootState } from "#/store";
 import { AgentState } from "#/types/agent-state";
 import { useActiveConversation } from "#/hooks/query/use-active-conversation";
 import { GitControlBar } from "./git-control-bar";
-import {
-  addImages,
-  addFiles,
-  clearAllFiles,
-  addFileLoading,
-  removeFileLoading,
-  addImageLoading,
-  removeImageLoading,
-} from "#/state/conversation-slice";
+import { useConversationStore } from "#/state/conversation-store";
 import { processFiles, processImages } from "#/utils/file-processing";
+import { RootState } from "#/store";
 
 interface InteractiveChatBoxProps {
   onSubmit: (message: string, images: File[], files: File[]) => void;
   onStop: () => void;
-  isWaitingForUserInput: boolean;
-  hasSubstantiveAgentActions: boolean;
-  optimisticUserMessage: boolean;
 }
 
 export function InteractiveChatBox({
   onSubmit,
   onStop,
-  isWaitingForUserInput,
-  hasSubstantiveAgentActions,
-  optimisticUserMessage,
 }: InteractiveChatBoxProps) {
-  const dispatch = useDispatch();
+  const {
+    images,
+    files,
+    addImages,
+    addFiles,
+    clearAllFiles,
+    addFileLoading,
+    removeFileLoading,
+    addImageLoading,
+    removeImageLoading,
+  } = useConversationStore();
   const curAgentState = useSelector(
     (state: RootState) => state.agent.curAgentState,
   );
-  const images = useSelector((state: RootState) => state.conversation.images);
-  const files = useSelector((state: RootState) => state.conversation.files);
   const { data: conversation } = useActiveConversation();
 
   // Helper function to validate and filter files
@@ -58,26 +52,24 @@ export function InteractiveChatBox({
 
   // Helper function to show loading indicators for files
   const showLoadingIndicators = (validFiles: File[], validImages: File[]) => {
-    validFiles.forEach((file) => dispatch(addFileLoading(file.name)));
-    validImages.forEach((image) => dispatch(addImageLoading(image.name)));
+    validFiles.forEach((file) => addFileLoading(file.name));
+    validImages.forEach((image) => addImageLoading(image.name));
   };
 
   // Helper function to handle successful file processing results
   const handleSuccessfulFiles = (fileResults: { successful: File[] }) => {
     if (fileResults.successful.length > 0) {
-      dispatch(addFiles(fileResults.successful));
-      fileResults.successful.forEach((file) =>
-        dispatch(removeFileLoading(file.name)),
-      );
+      addFiles(fileResults.successful);
+      fileResults.successful.forEach((file) => removeFileLoading(file.name));
     }
   };
 
   // Helper function to handle successful image processing results
   const handleSuccessfulImages = (imageResults: { successful: File[] }) => {
     if (imageResults.successful.length > 0) {
-      dispatch(addImages(imageResults.successful));
+      addImages(imageResults.successful);
       imageResults.successful.forEach((image) =>
-        dispatch(removeImageLoading(image.name)),
+        removeImageLoading(image.name),
       );
     }
   };
@@ -88,14 +80,14 @@ export function InteractiveChatBox({
     imageResults: { failed: { file: File; error: Error }[] },
   ) => {
     fileResults.failed.forEach(({ file, error }) => {
-      dispatch(removeFileLoading(file.name));
+      removeFileLoading(file.name);
       displayErrorToast(
         `Failed to process file ${file.name}: ${error.message}`,
       );
     });
 
     imageResults.failed.forEach(({ file, error }) => {
-      dispatch(removeImageLoading(file.name));
+      removeImageLoading(file.name);
       displayErrorToast(
         `Failed to process image ${file.name}: ${error.message}`,
       );
@@ -104,8 +96,8 @@ export function InteractiveChatBox({
 
   // Helper function to clear loading states on error
   const clearLoadingStates = (validFiles: File[], validImages: File[]) => {
-    validFiles.forEach((file) => dispatch(removeFileLoading(file.name)));
-    validImages.forEach((image) => dispatch(removeImageLoading(image.name)));
+    validFiles.forEach((file) => removeFileLoading(file.name));
+    validImages.forEach((image) => removeImageLoading(image.name));
   };
 
   const handleUpload = async (selectedFiles: File[]) => {
@@ -140,7 +132,7 @@ export function InteractiveChatBox({
 
   const handleSubmit = (message: string) => {
     onSubmit(message, images, files);
-    dispatch(clearAllFiles());
+    clearAllFiles();
   };
 
   const handleSuggestionsClick = (suggestion: string) => {
@@ -161,12 +153,7 @@ export function InteractiveChatBox({
         conversationStatus={conversation?.status || null}
       />
       <div className="mt-4">
-        <GitControlBar
-          onSuggestionsClick={handleSuggestionsClick}
-          isWaitingForUserInput={isWaitingForUserInput}
-          hasSubstantiveAgentActions={hasSubstantiveAgentActions}
-          optimisticUserMessage={optimisticUserMessage}
-        />
+        <GitControlBar onSuggestionsClick={handleSuggestionsClick} />
       </div>
     </div>
   );

frontend/src/components/features/chat/microagent/launch-microagent-modal.tsx

@@ -13,6 +13,7 @@ import { useHandleRuntimeActive } from "#/hooks/use-handle-runtime-active";
 import { LoadingMicroagentBody } from "./loading-microagent-body";
 import { LoadingMicroagentTextarea } from "./loading-microagent-textarea";
 import { useGetMicroagents } from "#/hooks/query/use-get-microagents";
+import { Typography } from "#/ui/typography";
 
 interface LaunchMicroagentModalProps {
   onClose: () => void;
@@ -76,9 +77,9 @@ export function LaunchMicroagentModal({
             </button>
           </div>
 
-          <span className="text-sm text-[#A3A3A3] font-normal leading-5">
+          <Typography.Text className="text-sm text-[#A3A3A3] font-normal leading-5">
             {t("MICROAGENT$DEFINITION")}
-          </span>
+          </Typography.Text>
 
           <form
             data-testid="launch-microagent-modal"

frontend/src/components/features/chat/microagent/loading-microagent-body.tsx

@@ -1,6 +1,7 @@
 import { Spinner } from "@heroui/react";
 import { useTranslation } from "react-i18next";
 import { ModalBody } from "#/components/shared/modals/modal-body";
+import { Typography } from "#/ui/typography";
 
 export function LoadingMicroagentBody() {
   const { t } = useTranslation();
@@ -10,7 +11,7 @@ export function LoadingMicroagentBody() {
         {t("MICROAGENT$ADD_TO_MICROAGENT")}
       </h2>
       <Spinner size="lg" />
-      <p>{t("MICROAGENT$WAIT_FOR_RUNTIME")}</p>
+      <Typography.Text>{t("MICROAGENT$WAIT_FOR_RUNTIME")}</Typography.Text>
     </ModalBody>
   );
 }

frontend/src/components/features/chat/microagent/microagent-status-indicator.tsx

@@ -3,6 +3,7 @@ import { useTranslation } from "react-i18next";
 import { Spinner } from "@heroui/react";
 import { MicroagentStatus } from "#/types/microagent-status";
 import { SuccessIndicator } from "../success-indicator";
+import { Typography } from "#/ui/typography";
 
 interface MicroagentStatusIndicatorProps {
   status: MicroagentStatus;
@@ -81,7 +82,9 @@ export function MicroagentStatusIndicator({
       );
     }
 
-    return <span className="underline">{statusText}</span>;
+    return (
+      <Typography.Text className="underline">{statusText}</Typography.Text>
+    );
   };
 
   return (

frontend/src/components/features/chat/task-tracking-observation-content.tsx

@@ -1,6 +1,6 @@
-import React from "react";
-import { useTranslation } from "react-i18next";
 import { TaskTrackingObservation } from "#/types/core/observations";
+import { TaskListSection } from "./task-tracking/task-list-section";
+import { ResultSection } from "./task-tracking/result-section";
 
 interface TaskTrackingObservationContentProps {
   event: TaskTrackingObservation;
@@ -9,101 +9,17 @@ interface TaskTrackingObservationContentProps {
 export function TaskTrackingObservationContent({
   event,
 }: TaskTrackingObservationContentProps) {
-  const { t } = useTranslation();
-
   const { command, task_list: taskList } = event.extras;
   const shouldShowTaskList = command === "plan" && taskList.length > 0;
 
-  const getStatusIcon = (status: string) => {
-    switch (status) {
-      case "todo":
-        return "⏳";
-      case "in_progress":
-        return "🔄";
-      case "done":
-        return "✅";
-      default:
-        return "❓";
-    }
-  };
-
-  const getStatusClassName = (status: string) => {
-    if (status === "done") {
-      return "bg-green-800 text-green-200";
-    }
-    if (status === "in_progress") {
-      return "bg-yellow-800 text-yellow-200";
-    }
-    return "bg-gray-700 text-gray-300";
-  };
-
   return (
     <div className="flex flex-col gap-4">
       {/* Task List section - only show for 'plan' command */}
-      {shouldShowTaskList && (
-        <div className="flex flex-col gap-2">
-          <div className="flex items-center justify-between">
-            <h3 className="text-sm font-semibold text-gray-300">
-              {t("TASK_TRACKING_OBSERVATION$TASK_LIST")} ({taskList.length}{" "}
-              {taskList.length === 1 ? "item" : "items"})
-            </h3>
-          </div>
-          <div className="p-3 bg-gray-900 rounded-md overflow-auto text-gray-300 max-h-[400px] shadow-inner">
-            <div className="space-y-3">
-              {taskList.map((task, index) => (
-                <div key={task.id} className="border-l-2 border-gray-600 pl-3">
-                  <div className="flex items-start gap-2">
-                    <span className="text-lg">
-                      {getStatusIcon(task.status)}
-                    </span>
-                    <div className="flex-1">
-                      <div className="flex items-center gap-2 mb-1">
-                        <span className="text-sm text-gray-400">
-                          {index + 1}.
-                        </span>
-                        <span
-                          className={`text-xs px-2 py-1 rounded uppercase font-semibold ${getStatusClassName(
-                            task.status,
-                          )}`}
-                        >
-                          {task.status.replace("_", " ")}
-                        </span>
-                      </div>
-                      <h4 className="font-medium text-white mb-1">
-                        {task.title}
-                      </h4>
-                      <p className="text-xs text-gray-400 mb-1">
-                        {t("TASK_TRACKING_OBSERVATION$TASK_ID")}: {task.id}
-                      </p>
-                      {task.notes && (
-                        <p className="text-sm text-gray-300 italic">
-                          {t("TASK_TRACKING_OBSERVATION$TASK_NOTES")}:{" "}
-                          {task.notes}
-                        </p>
-                      )}
-                    </div>
-                  </div>
-                </div>
-              ))}
-            </div>
-          </div>
-        </div>
-      )}
+      {shouldShowTaskList && <TaskListSection taskList={taskList} />}
 
       {/* Result message - only show if there's meaningful content */}
       {event.content && event.content.trim() && (
-        <div className="flex flex-col gap-2">
-          <div className="flex items-center justify-between">
-            <h3 className="text-sm font-semibold text-gray-300">
-              {t("TASK_TRACKING_OBSERVATION$RESULT")}
-            </h3>
-          </div>
-          <div className="p-3 bg-gray-900 rounded-md overflow-auto text-gray-300 shadow-inner">
-            <pre className="whitespace-pre-wrap text-sm">
-              {event.content.trim()}
-            </pre>
-          </div>
-        </div>
+        <ResultSection content={event.content} />
       )}
     </div>
   );

frontend/src/components/features/chat/task-tracking/result-section.tsx

@@ -0,0 +1,21 @@
+import { useTranslation } from "react-i18next";
+import { Typography } from "#/ui/typography";
+
+interface ResultSectionProps {
+  content: string;
+}
+
+export function ResultSection({ content }: ResultSectionProps) {
+  const { t } = useTranslation();
+
+  return (
+    <div className="flex flex-col gap-2">
+      <div className="flex items-center justify-between">
+        <Typography.H3>{t("TASK_TRACKING_OBSERVATION$RESULT")}</Typography.H3>
+      </div>
+      <div className="p-3 bg-gray-900 rounded-md overflow-auto text-gray-300 shadow-inner">
+        <pre className="whitespace-pre-wrap text-sm">{content.trim()}</pre>
+      </div>
+    </div>
+  );
+}