Set conversation as stopped

- Enable source maps in Vite configuration (frontend/vite.config.ts)
- Add source map artifact upload to existing fe-unit-tests workflow
- Create dedicated frontend-source-maps workflow for production builds
- Source maps will be available as downloadable artifacts from GitHub Actions

Co-authored-by: openhands <openhands@all-hands.dev>

.github/workflows/cli-build-test.yml

@@ -1,58 +0,0 @@
-# Workflow that builds and tests the CLI binary executable
-name: CLI - Build and Test Binary
-
-# Run on pushes to main branch and all pull requests, but only when CLI files change
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - "openhands-cli/**"
-  pull_request:
-    paths:
-      - "openhands-cli/**"
-
-# Cancel previous runs if a new commit is pushed
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  build-and-test-binary:
-    name: Build and test binary executable
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: 3.12
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v3
-        with:
-          version: "latest"
-
-      - name: Install dependencies
-        working-directory: openhands-cli
-        run: |
-          uv sync
-
-      - name: Build binary executable
-        working-directory: openhands-cli
-        run: |
-          ./build.sh --install-pyinstaller | tee output.log
-          echo "Full output:"
-          cat output.log
-
-          if grep -q "❌" output.log; then
-            echo "❌ Found failure marker in output"
-            exit 1
-          fi
-
-          echo "✅ Build & test finished without ❌ markers"

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

@@ -42,3 +42,10 @@ jobs:
       - name: Run tests and collect coverage
         working-directory: ./frontend
         run: npm run test:coverage
+      - name: Upload source maps as artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: frontend-source-maps-${{ github.sha }}
+          path: frontend/build/**/*.map
+          retention-days: 30
+          if-no-files-found: warn

.github/workflows/frontend-source-maps.yml

@@ -0,0 +1,76 @@
+# Workflow that builds frontend and uploads source maps as artifacts
+name: Build Frontend Source Maps
+
+# Run on main branch pushes, releases, and manual triggers
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "frontend/**"
+      - ".github/workflows/frontend-source-maps.yml"
+  release:
+    types: [published]
+  workflow_dispatch:
+
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  build-source-maps:
+    name: Build Frontend and Upload Source Maps
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    strategy:
+      matrix:
+        node-version: [22]
+      fail-fast: true
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      
+      - name: Set up Node.js
+        uses: useblacksmith/setup-node@v5
+        with:
+          node-version: ${{ matrix.node-version }}
+      
+      - name: Install dependencies
+        working-directory: ./frontend
+        run: npm ci
+      
+      - name: Build frontend with source maps
+        working-directory: ./frontend
+        run: npm run build
+      
+      - name: Upload source maps as artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: frontend-source-maps-${{ github.sha }}
+          path: frontend/build/**/*.map
+          retention-days: 90
+          if-no-files-found: error
+      
+      - name: Upload complete build artifacts (for debugging)
+        uses: actions/upload-artifact@v4
+        with:
+          name: frontend-build-${{ github.sha }}
+          path: |
+            frontend/build/**/*
+            !frontend/build/**/*.map
+          retention-days: 30
+          if-no-files-found: error
+      
+      - name: Create source maps summary
+        run: |
+          echo "## Source Maps Generated 🗺️" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "Source maps have been generated and uploaded as artifacts." >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### Statistics:" >> $GITHUB_STEP_SUMMARY
+          echo "- **Total source map files:** $(find frontend/build -name "*.map" | wc -l)" >> $GITHUB_STEP_SUMMARY
+          echo "- **Total size:** $(du -sh frontend/build/**/*.map 2>/dev/null | tail -1 | cut -f1 || echo 'N/A')" >> $GITHUB_STEP_SUMMARY
+          echo "- **Commit SHA:** ${{ github.sha }}" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### Download:" >> $GITHUB_STEP_SUMMARY
+          echo "Source maps are available as workflow artifacts and can be downloaded from the Actions tab." >> $GITHUB_STEP_SUMMARY

.github/workflows/lint.yml

@@ -37,7 +37,7 @@ jobs:
           npm run make-i18n && tsc
           npm run check-translation-completeness
 
-  # Run lint on the python code (excluding CLI and enterprise)
+  # Run lint on the python code
   lint-python:
     name: Lint python
     runs-on: blacksmith-4vcpu-ubuntu-2204
@@ -73,24 +73,6 @@ jobs:
         working-directory: ./enterprise
         run: pre-commit run --all-files --config ./dev_config/python/.pre-commit-config.yaml
 
-  lint-cli-python:
-    name: Lint CLI python
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-      - name: Set up python
-        uses: useblacksmith/setup-python@v6
-        with:
-          python-version: 3.12
-          cache: "pip"
-      - name: Install pre-commit
-        run: pip install pre-commit==3.7.0
-      - name: Run pre-commit hooks
-        working-directory: ./openhands-cli
-        run: pre-commit run --all-files --config ../dev_config/python/.pre-commit-config.yaml
-
   # Check version consistency across documentation
   check-version-consistency:
     name: Check version consistency

.github/workflows/py-tests.yml

@@ -104,33 +104,3 @@ jobs:
       - 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
-
-  # Run CLI unit tests
-  test-cli-python:
-    name: CLI Unit Tests
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up Python
-        uses: useblacksmith/setup-python@v6
-        with:
-          python-version: 3.12
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v3
-        with:
-          version: "latest"
-
-      - name: Install dependencies
-        working-directory: ./openhands-cli
-        run: |
-          uv sync --group dev
-
-      - name: Run CLI unit tests
-        working-directory: ./openhands-cli
-        run: |
-          uv run pytest -v

.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,app-team
+          exempt-issue-labels: roadmap,backlog
           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

.gitignore

@@ -31,8 +31,7 @@ requirements.txt
 #  Usually these files are written by a python script from a template
 #  before PyInstaller builds the exe, so as to inject date/other infos into it.
 *.manifest
-# Note: openhands-cli.spec is intentionally tracked for CLI builds
-# *.spec
+*.spec
 
 # Installer logs
 pip-log.txt

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

@@ -489,47 +489,6 @@ 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=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.57-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.56-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

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

@@ -3,9 +3,9 @@ repos:
     rev: v5.0.0
     hooks:
       - id: trailing-whitespace
-        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/|openhands-cli/)
+        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/)
       - id: end-of-file-fixer
-        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/|openhands-cli/)
+        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/)
       - id: check-yaml
         args: ["--allow-multiple-documents"]
       - id: debug-statements
@@ -28,12 +28,12 @@ repos:
         entry: ruff check --config dev_config/python/ruff.toml
         types_or: [python, pyi, jupyter]
         args: [--fix, --unsafe-fixes]
-        exclude: ^(third_party/|enterprise/|openhands-cli/)
+        exclude: ^(third_party/|enterprise/)
       # Run the formatter.
       - id: ruff-format
         entry: ruff format --config dev_config/python/ruff.toml
         types_or: [python, pyi, jupyter]
-        exclude: ^(third_party/|enterprise/|openhands-cli/)
+        exclude: ^(third_party/|enterprise/)
 
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.15.0

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:0.57-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.56-nikolaik}
       #- SANDBOX_USER_ID=${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/configuration-options.mdx

@@ -8,11 +8,6 @@ description: This page outlines all available configuration options for OpenHand
    In GUI Mode, any settings applied through the Settings UI will take precedence.
 </Note>
 
-<Note>
-   **Looking for Environment Variables?** All configuration options can also be set using environment variables. 
-   See the [Environment Variables Reference](./environment-variables) for a complete list with examples.
-</Note>
-
 ## Location of the `config.toml` File
 
 When running OpenHands in CLI, headless, or development mode, you can use a project-specific `config.toml` file for configuration, which must be
@@ -23,11 +18,6 @@ specify a different path to the `config.toml` file.
 
 The core configuration options are defined in the `[core]` section of the `config.toml` file.
 
-Core configuration options can be set as environment variables by converting to uppercase. For example:
-- `debug` → `DEBUG`
-- `cache_dir` → `CACHE_DIR`
-- `runtime` → `RUNTIME`
-
 ### Workspace
 - `workspace_base` **(Deprecated)**
   - Type: `str`
@@ -151,11 +141,6 @@ The LLM (Large Language Model) configuration options are defined in the `[llm]`
 
 To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LLM_NUM_RETRIES`.
 
-All LLM configuration options can be set as environment variables by prefixing with `LLM_` and converting to uppercase. For example:
-- `model` → `LLM_MODEL`
-- `api_key` → `LLM_API_KEY`
-- `base_url` → `LLM_BASE_URL`
-
 <Note>
 For development setups, you can also define custom named LLM configurations. See [Custom LLM Configurations](./llms/custom-llm-configs) for details.
 </Note>
@@ -292,11 +277,6 @@ For development setups, you can also define custom named LLM configurations. See
 
 The agent configuration options are defined in the `[agent]` and `[agent.<agent_name>]` sections of the `config.toml` file.
 
-Agent configuration options can be set as environment variables by prefixing with `AGENT_` and converting to uppercase. For example:
-- `enable_browsing` → `AGENT_ENABLE_BROWSING`
-- `function_calling` → `AGENT_FUNCTION_CALLING`
-- `llm_config` → `AGENT_LLM_CONFIG`
-
 ### LLM Configuration
 - `llm_config`
   - Type: `str`
@@ -348,11 +328,6 @@ The sandbox configuration options are defined in the `[sandbox]` section of the
 
 To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-e SANDBOX_TIMEOUT`.
 
-All sandbox configuration options can be set as environment variables by prefixing with `SANDBOX_` and converting to uppercase. For example:
-- `timeout` → `SANDBOX_TIMEOUT`
-- `user_id` → `SANDBOX_USER_ID`
-- `base_container_image` → `SANDBOX_BASE_CONTAINER_IMAGE`
-
 ### Execution
 - `timeout`
   - Type: `int`
@@ -415,10 +390,6 @@ The security configuration options are defined in the `[security]` section of th
 
 To use these with the docker command, pass in `-e SECURITY_<option>`. Example: `-e SECURITY_CONFIRMATION_MODE`.
 
-All security configuration options can be set as environment variables by prefixing with `SECURITY_` and converting to uppercase. For example:
-- `confirmation_mode` → `SECURITY_CONFIRMATION_MODE`
-- `security_analyzer` → `SECURITY_SECURITY_ANALYZER`
-
 ### Confirmation Mode
 - `confirmation_mode`
   - Type: `bool`

docs/usage/environment-variables.mdx

@@ -1,251 +0,0 @@
----
-title: Environment Variables Reference
-description: Complete reference of all environment variables supported by OpenHands
----
-
-This page provides a reference of environment variables that can be used to configure OpenHands. Environment variables provide an alternative to TOML configuration files and are particularly useful for containerized deployments, CI/CD pipelines, and cloud environments.
-
-## Environment Variable Naming Convention
-
-OpenHands follows a consistent naming pattern for environment variables:
-
-- **Core settings**: Direct uppercase mapping (e.g., `debug` → `DEBUG`)
-- **LLM settings**: Prefixed with `LLM_` (e.g., `model` → `LLM_MODEL`)
-- **Agent settings**: Prefixed with `AGENT_` (e.g., `enable_browsing` → `AGENT_ENABLE_BROWSING`)
-- **Sandbox settings**: Prefixed with `SANDBOX_` (e.g., `timeout` → `SANDBOX_TIMEOUT`)
-- **Security settings**: Prefixed with `SECURITY_` (e.g., `confirmation_mode` → `SECURITY_CONFIRMATION_MODE`)
-
-## Core Configuration Variables
-
-These variables correspond to the `[core]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `DEBUG` | boolean | `false` | Enable debug logging throughout the application |
-| `DISABLE_COLOR` | boolean | `false` | Disable colored output in terminal |
-| `CACHE_DIR` | string | `"/tmp/cache"` | Directory path for caching |
-| `SAVE_TRAJECTORY_PATH` | string | `"./trajectories"` | Path to store conversation trajectories |
-| `REPLAY_TRAJECTORY_PATH` | string | `""` | Path to load and replay a trajectory file |
-| `FILE_STORE_PATH` | string | `"/tmp/file_store"` | File store directory path |
-| `FILE_STORE` | string | `"memory"` | File store type (`memory`, `local`, etc.) |
-| `FILE_UPLOADS_MAX_FILE_SIZE_MB` | integer | `0` | Maximum file upload size in MB (0 = no limit) |
-| `FILE_UPLOADS_RESTRICT_FILE_TYPES` | boolean | `false` | Whether to restrict file upload types |
-| `FILE_UPLOADS_ALLOWED_EXTENSIONS` | list | `[".*"]` | List of allowed file extensions for uploads |
-| `MAX_BUDGET_PER_TASK` | float | `0.0` | Maximum budget per task (0.0 = no limit) |
-| `MAX_ITERATIONS` | integer | `100` | Maximum number of iterations per task |
-| `RUNTIME` | string | `"docker"` | Runtime environment (`docker`, `local`, `cli`, etc.) |
-| `DEFAULT_AGENT` | string | `"CodeActAgent"` | Default agent class to use |
-| `JWT_SECRET` | string | auto-generated | JWT secret for authentication |
-| `RUN_AS_OPENHANDS` | boolean | `true` | Whether to run as the openhands user |
-| `VOLUMES` | string | `""` | Volume mounts in format `host:container[:mode]` |
-
-## LLM Configuration Variables
-
-These variables correspond to the `[llm]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `LLM_MODEL` | string | `"claude-3-5-sonnet-20241022"` | LLM model to use |
-| `LLM_API_KEY` | string | `""` | API key for the LLM provider |
-| `LLM_BASE_URL` | string | `""` | Custom API base URL |
-| `LLM_API_VERSION` | string | `""` | API version to use |
-| `LLM_TEMPERATURE` | float | `0.0` | Sampling temperature |
-| `LLM_TOP_P` | float | `1.0` | Top-p sampling parameter |
-| `LLM_MAX_INPUT_TOKENS` | integer | `0` | Maximum input tokens (0 = no limit) |
-| `LLM_MAX_OUTPUT_TOKENS` | integer | `0` | Maximum output tokens (0 = no limit) |
-| `LLM_MAX_MESSAGE_CHARS` | integer | `30000` | Maximum characters that will be sent to the model in observation content |
-| `LLM_TIMEOUT` | integer | `0` | API timeout in seconds (0 = no timeout) |
-| `LLM_NUM_RETRIES` | integer | `8` | Number of retry attempts |
-| `LLM_RETRY_MIN_WAIT` | integer | `15` | Minimum wait time between retries (seconds) |
-| `LLM_RETRY_MAX_WAIT` | integer | `120` | Maximum wait time between retries (seconds) |
-| `LLM_RETRY_MULTIPLIER` | float | `2.0` | Exponential backoff multiplier |
-| `LLM_DROP_PARAMS` | boolean | `false` | Drop unsupported parameters without error |
-| `LLM_CACHING_PROMPT` | boolean | `true` | Enable prompt caching if supported |
-| `LLM_DISABLE_VISION` | boolean | `false` | Disable vision capabilities for cost reduction |
-| `LLM_CUSTOM_LLM_PROVIDER` | string | `""` | Custom LLM provider name |
-| `LLM_OLLAMA_BASE_URL` | string | `""` | Base URL for Ollama API |
-| `LLM_INPUT_COST_PER_TOKEN` | float | `0.0` | Cost per input token |
-| `LLM_OUTPUT_COST_PER_TOKEN` | float | `0.0` | Cost per output token |
-| `LLM_REASONING_EFFORT` | string | `""` | Reasoning effort for o-series models (`low`, `medium`, `high`) |
-
-### AWS Configuration
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `LLM_AWS_ACCESS_KEY_ID` | string | `""` | AWS access key ID |
-| `LLM_AWS_SECRET_ACCESS_KEY` | string | `""` | AWS secret access key |
-| `LLM_AWS_REGION_NAME` | string | `""` | AWS region name |
-
-## Agent Configuration Variables
-
-These variables correspond to the `[agent]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `AGENT_LLM_CONFIG` | string | `""` | Name of LLM config group to use |
-| `AGENT_FUNCTION_CALLING` | boolean | `true` | Enable function calling |
-| `AGENT_ENABLE_BROWSING` | boolean | `false` | Enable browsing delegate |
-| `AGENT_ENABLE_LLM_EDITOR` | boolean | `false` | Enable LLM-based editor |
-| `AGENT_ENABLE_JUPYTER` | boolean | `false` | Enable Jupyter integration |
-| `AGENT_ENABLE_HISTORY_TRUNCATION` | boolean | `true` | Enable history truncation |
-| `AGENT_ENABLE_PROMPT_EXTENSIONS` | boolean | `true` | Enable microagents (prompt extensions) |
-| `AGENT_DISABLED_MICROAGENTS` | list | `[]` | List of microagents to disable |
-
-## Sandbox Configuration Variables
-
-These variables correspond to the `[sandbox]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `SANDBOX_TIMEOUT` | integer | `120` | Sandbox timeout in seconds |
-| `SANDBOX_USER_ID` | integer | `1000` | User ID for sandbox processes |
-| `SANDBOX_BASE_CONTAINER_IMAGE` | string | `"nikolaik/python-nodejs:python3.12-nodejs22"` | Base container image |
-| `SANDBOX_USE_HOST_NETWORK` | boolean | `false` | Use host networking |
-| `SANDBOX_RUNTIME_BINDING_ADDRESS` | string | `"0.0.0.0"` | Runtime binding address |
-| `SANDBOX_ENABLE_AUTO_LINT` | boolean | `false` | Enable automatic linting |
-| `SANDBOX_INITIALIZE_PLUGINS` | boolean | `true` | Initialize sandbox plugins |
-| `SANDBOX_RUNTIME_EXTRA_DEPS` | string | `""` | Extra dependencies to install |
-| `SANDBOX_RUNTIME_STARTUP_ENV_VARS` | dict | `{}` | Environment variables for runtime |
-| `SANDBOX_BROWSERGYM_EVAL_ENV` | string | `""` | BrowserGym evaluation environment |
-| `SANDBOX_VOLUMES` | string | `""` | Volume mounts (replaces deprecated workspace settings) |
-| `SANDBOX_RUNTIME_CONTAINER_IMAGE` | string | `""` | Pre-built runtime container image |
-| `SANDBOX_KEEP_RUNTIME_ALIVE` | boolean | `false` | Keep runtime alive after session ends |
-| `SANDBOX_PAUSE_CLOSED_RUNTIMES` | boolean | `false` | Pause instead of stopping closed runtimes |
-| `SANDBOX_CLOSE_DELAY` | integer | `300` | Delay before closing idle runtimes (seconds) |
-| `SANDBOX_RM_ALL_CONTAINERS` | boolean | `false` | Remove all containers when stopping |
-| `SANDBOX_ENABLE_GPU` | boolean | `false` | Enable GPU support |
-| `SANDBOX_CUDA_VISIBLE_DEVICES` | string | `""` | Specify GPU devices by ID |
-| `SANDBOX_VSCODE_PORT` | integer | auto | Specific port for VSCode server |
-
-### Sandbox Environment Variables
-Variables prefixed with `SANDBOX_ENV_` are passed through to the sandbox environment:
-
-| Environment Variable | Description |
-|---------------------|-------------|
-| `SANDBOX_ENV_*` | Any variable with this prefix is passed to the sandbox (e.g., `SANDBOX_ENV_OPENAI_API_KEY`) |
-
-## Security Configuration Variables
-
-These variables correspond to the `[security]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `SECURITY_CONFIRMATION_MODE` | boolean | `false` | Enable confirmation mode for actions |
-| `SECURITY_SECURITY_ANALYZER` | string | `"llm"` | Security analyzer to use (`llm`, `invariant`) |
-| `SECURITY_ENABLE_SECURITY_ANALYZER` | boolean | `true` | Enable security analysis |
-
-## Debug and Logging Variables
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `DEBUG` | boolean | `false` | Enable general debug logging |
-| `DEBUG_LLM` | boolean | `false` | Enable LLM-specific debug logging |
-| `DEBUG_RUNTIME` | boolean | `false` | Enable runtime debug logging |
-| `LOG_TO_FILE` | boolean | auto | Log to file (auto-enabled when DEBUG=true) |
-
-## Runtime-Specific Variables
-
-### Docker Runtime
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `SANDBOX_VOLUME_OVERLAYS` | string | `""` | Volume overlay configurations |
-
-### Remote Runtime
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `SANDBOX_API_KEY` | string | `""` | API key for remote runtime |
-| `SANDBOX_REMOTE_RUNTIME_API_URL` | string | `""` | Remote runtime API URL |
-
-### Local Runtime
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `RUNTIME_URL` | string | `""` | Runtime URL for local runtime |
-| `RUNTIME_URL_PATTERN` | string | `""` | Runtime URL pattern |
-| `RUNTIME_ID` | string | `""` | Runtime identifier |
-| `LOCAL_RUNTIME_MODE` | string | `""` | Enable local runtime mode (`1` to enable) |
-
-## Integration Variables
-
-### GitHub Integration
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `GITHUB_TOKEN` | string | `""` | GitHub personal access token |
-
-### Third-Party API Keys
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `OPENAI_API_KEY` | string | `""` | OpenAI API key |
-| `ANTHROPIC_API_KEY` | string | `""` | Anthropic API key |
-| `GOOGLE_API_KEY` | string | `""` | Google API key |
-| `AZURE_API_KEY` | string | `""` | Azure API key |
-| `TAVILY_API_KEY` | string | `""` | Tavily search API key |
-
-## Server Configuration Variables
-
-These are primarily used when running OpenHands as a server:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `FRONTEND_PORT` | integer | `3000` | Frontend server port |
-| `BACKEND_PORT` | integer | `8000` | Backend server port |
-| `FRONTEND_HOST` | string | `"localhost"` | Frontend host address |
-| `BACKEND_HOST` | string | `"localhost"` | Backend host address |
-| `WEB_HOST` | string | `"localhost"` | Web server host |
-| `SERVE_FRONTEND` | boolean | `true` | Whether to serve frontend |
-
-## Deprecated Variables
-
-These variables are deprecated and should be replaced:
-
-| Environment Variable | Replacement | Description |
-|---------------------|-------------|-------------|
-| `WORKSPACE_BASE` | `SANDBOX_VOLUMES` | Use volume mounting instead |
-| `WORKSPACE_MOUNT_PATH` | `SANDBOX_VOLUMES` | Use volume mounting instead |
-| `WORKSPACE_MOUNT_PATH_IN_SANDBOX` | `SANDBOX_VOLUMES` | Use volume mounting instead |
-| `WORKSPACE_MOUNT_REWRITE` | `SANDBOX_VOLUMES` | Use volume mounting instead |
-
-## Usage Examples
-
-### Basic Setup with OpenAI
-```bash
-export LLM_MODEL="gpt-4o"
-export LLM_API_KEY="your-openai-api-key"
-export DEBUG=true
-```
-
-### Docker Deployment with Custom Volumes
-```bash
-export RUNTIME="docker"
-export SANDBOX_VOLUMES="/host/workspace:/workspace:rw,/host/data:/data:ro"
-export SANDBOX_TIMEOUT=300
-```
-
-### Remote Runtime Configuration
-```bash
-export RUNTIME="remote"
-export SANDBOX_API_KEY="your-remote-api-key"
-export SANDBOX_REMOTE_RUNTIME_API_URL="https://your-runtime-api.com"
-```
-
-### Security-Enhanced Setup
-```bash
-export SECURITY_CONFIRMATION_MODE=true
-export SECURITY_SECURITY_ANALYZER="llm"
-export DEBUG_RUNTIME=true
-```
-
-## Notes
-
-1. **Boolean Values**: Environment variables expecting boolean values accept `true`/`false`, `1`/`0`, or `yes`/`no` (case-insensitive).
-
-2. **List Values**: Lists should be provided as Python literal strings, e.g., `AGENT_DISABLED_MICROAGENTS='["microagent1", "microagent2"]'`.
-
-3. **Dictionary Values**: Dictionaries should be provided as Python literal strings, e.g., `SANDBOX_RUNTIME_STARTUP_ENV_VARS='{"KEY": "value"}'`.
-
-4. **Precedence**: Environment variables take precedence over TOML configuration files.
-
-5. **Docker Usage**: When using Docker, pass environment variables with the `-e` flag:
-   ```bash
-   docker run -e LLM_API_KEY="your-key" -e DEBUG=true openhands/openhands
-   ```
-
-6. **Validation**: Invalid environment variable values will be logged as errors and fall back to defaults.

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

@@ -30,20 +30,6 @@ When running OpenHands, you'll need to set the following in the OpenHands UI thr
 
 ## Pricing
 
-Pricing follows official API provider rates. Below are the current pricing details for OpenHands models:
+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)
 
-| 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.
+For `qwen3-coder-480b`, we charge the cheapest FP8 rate available on openrouter: \$0.4 per million input tokens and \$1.6 per million output tokens.

docs/usage/local-setup.mdx

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

docs/usage/mcp.mdx

@@ -67,19 +67,6 @@ 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
-    }
-]
 ```
 
 
@@ -131,17 +118,6 @@ 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.
@@ -216,27 +192,5 @@ 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

@@ -7,28 +7,14 @@ 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 && \
-    # 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/*
+    apt-get clean
 
-# 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"
+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
 
 WORKDIR /app
 COPY enterprise .

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

@@ -46,8 +46,7 @@ repos:
           - types-toml
           - types-redis
           - lxml
-          # OpenHands package in repo root
-          - ./
+          # TODO: Add OpenHands in parent
           - stripe==11.5.0
           - pygithub==2.6.1
         # To see gaps add `--html-report mypy-report/`

enterprise/dev_config/python/mypy.ini

@@ -7,11 +7,15 @@ warn_unreachable = True
 warn_redundant_casts = True
 no_implicit_optional = True
 strict_optional = True
-disable_error_code = type-abstract
-exclude = (^enterprise/migrations/.*)
+exclude = (^enterprise/migrations/.*|^openhands/.*)
 
 [mypy-enterprise.tests.unit.test_auth_routes.*]
 disable_error_code = union-attr
 
 [mypy-enterprise.sync.install_gitlab_webhooks.*]
 disable_error_code = redundant-cast
+
+# Let the other config check base openhands packages
+[mypy-openhands.*]
+follow_imports = skip
+ignore_missing_imports = True

enterprise/experiments/experiment_manager.py

@@ -2,6 +2,7 @@ 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,
 )
@@ -43,6 +44,9 @@ 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
         )
@@ -51,7 +55,7 @@ class SaaSExperimentManager(ExperimentManager):
 
     @staticmethod
     def run_config_variant_test(
-        user_id: str | None, conversation_id: str, config: OpenHandsConfig
+        user_id: str, conversation_id: str, config: OpenHandsConfig
     ) -> OpenHandsConfig:
         """
         Run agent config variant test and potentially modify the OpenHands config

enterprise/integrations/gitlab/gitlab_manager.py

@@ -62,13 +62,7 @@ class GitlabManager(Manager):
             logger.warning(f'Got invalid keyloak user id for GitLab User {user_id}')
             return False
 
-        # Importing here prevents circular import
-        from integrations.gitlab.gitlab_service import SaaSGitLabService
-
-        gitlab_service: SaaSGitLabService = GitLabServiceImpl(
-            external_auth_id=keycloak_user_id
-        )
-
+        gitlab_service = GitLabServiceImpl(external_auth_id=keycloak_user_id)
         return await gitlab_service.user_has_write_access(project_id)
 
     async def receive_message(self, message: Message):
@@ -125,13 +119,7 @@ class GitlabManager(Manager):
             gitlab_view: The GitLab view object containing issue/PR/comment info
         """
         keycloak_user_id = gitlab_view.user_info.keycloak_user_id
-
-        # Importing here prevents circular import
-        from integrations.gitlab.gitlab_service import SaaSGitLabService
-
-        gitlab_service: SaaSGitLabService = GitLabServiceImpl(
-            external_auth_id=keycloak_user_id
-        )
+        gitlab_service = GitLabServiceImpl(external_auth_id=keycloak_user_id)
 
         outgoing_message = message.message
 

enterprise/integrations/gitlab/gitlab_view.py

@@ -47,14 +47,14 @@ class GitlabIssue(ResolverViewInterface):
         )
 
         self.previous_comments = await gitlab_service.get_issue_or_mr_comments(
-            str(self.project_id), self.issue_number, is_mr=self.is_mr
+            self.project_id, self.issue_number, is_mr=self.is_mr
         )
 
         (
             self.title,
             self.description,
         ) = await gitlab_service.get_issue_or_mr_title_and_body(
-            str(self.project_id), self.issue_number, is_mr=self.is_mr
+            self.project_id, self.issue_number, is_mr=self.is_mr
         )
 
     async def _get_instructions(self, jinja_env: Environment) -> tuple[str, str]:
@@ -199,11 +199,11 @@ class GitlabInlineMRComment(GitlabMRComment):
             self.title,
             self.description,
         ) = await gitlab_service.get_issue_or_mr_title_and_body(
-            str(self.project_id), self.issue_number, is_mr=self.is_mr
+            self.project_id, self.issue_number, is_mr=self.is_mr
         )
 
         self.previous_comments = await gitlab_service.get_review_thread_comments(
-            str(self.project_id), self.issue_number, self.discussion_id
+            self.project_id, self.issue_number, self.discussion_id
         )
 
     async def _get_instructions(self, jinja_env: Environment) -> tuple[str, str]:

enterprise/integrations/utils.py

@@ -172,17 +172,6 @@ def get_summary_for_agent_state(
 
         return f'OpenHands encountered an error: **{reason}**.\n\n[See the conversation]({conversation_link}) for more information.'
 
-    if state == AgentState.AWAITING_USER_INPUT:
-        logger.info(
-            'Agent is awaiting user input',
-            extra={
-                'agent_state': state.value,
-                'conversation_link': conversation_link,
-                'observation_reason': getattr(observation, 'reason', None),
-            },
-        )
-        return f'OpenHands is waiting for your input. [Continue the conversation]({conversation_link}) to provide additional instructions.'
-
     # Log unknown agent state as error
     logger.error(
         'Unknown error: Unhandled agent state',

enterprise/migrations/versions/075_add_cancellation_fields_to_subscription_access.py

@@ -1,50 +0,0 @@
-"""add cancellation fields to subscription_access
-
-Revision ID: 075
-Revises: 074
-Create Date: 2025-01-11
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = '075'
-down_revision: Union[str, None] = '074'
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Add cancelled_at field to track cancellation timestamp
-    op.add_column(
-        'subscription_access',
-        sa.Column('cancelled_at', sa.DateTime(timezone=True), nullable=True),
-    )
-
-    # Add stripe_subscription_id field to enable cancellation via Stripe API
-    op.add_column(
-        'subscription_access',
-        sa.Column('stripe_subscription_id', sa.String(), nullable=True),
-    )
-
-    # Create index on stripe_subscription_id for efficient lookups
-    op.create_index(
-        'ix_subscription_access_stripe_subscription_id',
-        'subscription_access',
-        ['stripe_subscription_id'],
-    )
-
-
-def downgrade() -> None:
-    # Drop index
-    op.drop_index(
-        'ix_subscription_access_stripe_subscription_id', 'subscription_access'
-    )
-
-    # Drop columns
-    op.drop_column('subscription_access', 'stripe_subscription_id')
-    op.drop_column('subscription_access', 'cancelled_at')

enterprise/server/routes/billing.py

@@ -17,13 +17,11 @@ from server.constants import (
     STRIPE_API_KEY,
     STRIPE_WEBHOOK_SECRET,
     SUBSCRIPTION_PRICE_DATA,
-    get_default_litellm_model,
 )
 from server.logger import logger
 from storage.billing_session import BillingSession
 from storage.database import session_maker
 from storage.subscription_access import SubscriptionAccess
-from storage.user_settings import UserSettings
 
 from openhands.server.user_auth import get_user_id
 
@@ -44,8 +42,6 @@ class SubscriptionAccessResponse(BaseModel):
     start_at: datetime
     end_at: datetime
     created_at: datetime
-    cancelled_at: datetime | None = None
-    stripe_subscription_id: str | None = None
 
 
 class CreateCheckoutSessionRequest(BaseModel):
@@ -89,7 +85,7 @@ async def get_credits(user_id: str = Depends(get_user_id)) -> GetCreditsResponse
 async def get_subscription_access(
     user_id: str = Depends(get_user_id),
 ) -> SubscriptionAccessResponse | None:
-    """Get details of the currently valid subscription for the user."""
+    """Get details of the currently valid subscription for the user"""
     with session_maker() as session:
         now = datetime.now(UTC)
         subscription_access = (
@@ -106,8 +102,6 @@ async def get_subscription_access(
             start_at=subscription_access.start_at,
             end_at=subscription_access.end_at,
             created_at=subscription_access.created_at,
-            cancelled_at=subscription_access.cancelled_at,
-            stripe_subscription_id=subscription_access.stripe_subscription_id,
         )
 
 
@@ -119,78 +113,6 @@ async def has_payment_method(user_id: str = Depends(get_user_id)) -> bool:
     return await stripe_service.has_payment_method(user_id)
 
 
-# Endpoint to cancel user's subscription
-@billing_router.post('/cancel-subscription')
-async def cancel_subscription(user_id: str = Depends(get_user_id)) -> JSONResponse:
-    """Cancel user's active subscription at the end of the current billing period."""
-    if not user_id:
-        raise HTTPException(status.HTTP_401_UNAUTHORIZED)
-
-    with session_maker() as session:
-        # Find the user's active subscription
-        now = datetime.now(UTC)
-        subscription_access = (
-            session.query(SubscriptionAccess)
-            .filter(SubscriptionAccess.status == 'ACTIVE')
-            .filter(SubscriptionAccess.user_id == user_id)
-            .filter(SubscriptionAccess.start_at <= now)
-            .filter(SubscriptionAccess.end_at >= now)
-            .filter(SubscriptionAccess.cancelled_at.is_(None))  # Not already cancelled
-            .first()
-        )
-
-        if not subscription_access:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail='No active subscription found',
-            )
-
-        if not subscription_access.stripe_subscription_id:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail='Cannot cancel subscription: missing Stripe subscription ID',
-            )
-
-        try:
-            # Cancel the subscription in Stripe at period end
-            await stripe.Subscription.modify_async(
-                subscription_access.stripe_subscription_id, cancel_at_period_end=True
-            )
-
-            # Update local database
-            subscription_access.cancelled_at = datetime.now(UTC)
-            session.merge(subscription_access)
-            session.commit()
-
-            logger.info(
-                'subscription_cancelled',
-                extra={
-                    'user_id': user_id,
-                    'stripe_subscription_id': subscription_access.stripe_subscription_id,
-                    'subscription_access_id': subscription_access.id,
-                    'end_at': subscription_access.end_at,
-                },
-            )
-
-            return JSONResponse(
-                {'status': 'success', 'message': 'Subscription cancelled successfully'}
-            )
-
-        except stripe.StripeError as e:
-            logger.error(
-                'stripe_cancellation_failed',
-                extra={
-                    'user_id': user_id,
-                    'stripe_subscription_id': subscription_access.stripe_subscription_id,
-                    'error': str(e),
-                },
-            )
-            raise HTTPException(
-                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=f'Failed to cancel subscription: {str(e)}',
-            )
-
-
 # Endpoint to create a new setup intent in stripe
 @billing_router.post('/create-customer-setup-session')
 async def create_customer_setup_session(
@@ -268,27 +190,9 @@ async def create_subscription_checkout_session(
     billing_session_type: BillingSessionType = BillingSessionType.MONTHLY_SUBSCRIPTION,
     user_id: str = Depends(get_user_id),
 ) -> CreateBillingSessionResponse:
-    # Prevent duplicate subscriptions for the same user
-    with session_maker() as session:
-        now = datetime.now(UTC)
-        existing_active_subscription = (
-            session.query(SubscriptionAccess)
-            .filter(SubscriptionAccess.status == 'ACTIVE')
-            .filter(SubscriptionAccess.user_id == user_id)
-            .filter(SubscriptionAccess.start_at <= now)
-            .filter(SubscriptionAccess.end_at >= now)
-            .filter(SubscriptionAccess.cancelled_at.is_(None))  # Not cancelled
-            .first()
-        )
-
-        if existing_active_subscription:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail='Cannot create subscription: User already has an active subscription that has not been cancelled',
-            )
-
     customer_id = await stripe_service.find_or_create_customer(user_id)
     subscription_price_data = SUBSCRIPTION_PRICE_DATA[billing_session_type.value]
+    # TODO: Prevent duplicate subscriptions for the same user
     checkout_session = await stripe.checkout.Session.create_async(
         customer=customer_id,
         line_items=[
@@ -342,7 +246,7 @@ async def create_subscription_checkout_session_via_get(
     billing_session_type: BillingSessionType = BillingSessionType.MONTHLY_SUBSCRIPTION,
     user_id: str = Depends(get_user_id),
 ) -> RedirectResponse:
-    """Create a subscription checkout session using a GET request (For easier copy / paste to URL bar)."""
+    """Create a subscription checkout session using a GET request (For easier copy / paste to URL bar)"""
     response = await create_subscription_checkout_session(
         request, billing_session_type, user_id
     )
@@ -374,7 +278,7 @@ async def success_callback(session_id: str, request: Request):
             != BillingSessionType.DIRECT_PAYMENT.value
         ):
             return RedirectResponse(
-                f'{request.base_url}settings?checkout=success', status_code=302
+                f'{request.base_url}settings/billing?checkout=success', status_code=302
             )
 
         stripe_session = stripe.checkout.Session.retrieve(session_id)
@@ -444,29 +348,14 @@ async def cancel_callback(session_id: str, request: Request):
             session.merge(billing_session)
             session.commit()
 
-            # Redirect credit purchases to billing screen, subscriptions to LLM settings
-            if (
-                billing_session.billing_session_type
-                == BillingSessionType.DIRECT_PAYMENT.value
-            ):
-                return RedirectResponse(
-                    f'{request.base_url}settings/billing?checkout=cancel',
-                    status_code=302,
-                )
-            else:
-                return RedirectResponse(
-                    f'{request.base_url}settings?checkout=cancel', status_code=302
-                )
-
-    # If no billing session found, default to LLM settings (subscription flow)
     return RedirectResponse(
-        f'{request.base_url}settings?checkout=cancel', status_code=302
+        f'{request.base_url}settings/billing?checkout=cancel', status_code=302
     )
 
 
 @billing_router.post('/stripe-webhook')
 async def stripe_webhook(request: Request) -> JSONResponse:
-    """Endpoint for stripe webhooks."""
+    """Endpoint for stripe webhooks"""
     payload = await request.body()
     sig_header = request.headers.get('stripe-signature')
 
@@ -508,111 +397,15 @@ async def stripe_webhook(request: Request) -> JSONResponse:
                 end_at=end_at,
                 amount_paid=amount_paid,
                 stripe_invoice_payment_id=invoice.payment_intent,
-                stripe_subscription_id=invoice.subscription,  # Store Stripe subscription ID
             )
             session.add(subscription_access)
             session.commit()
-    elif event_type == 'customer.subscription.updated':
-        subscription = event['data']['object']
-        subscription_id = subscription['id']
-
-        # Handle subscription cancellation
-        if subscription.get('cancel_at_period_end') is True:
-            with session_maker() as session:
-                subscription_access = (
-                    session.query(SubscriptionAccess)
-                    .filter(
-                        SubscriptionAccess.stripe_subscription_id == subscription_id
-                    )
-                    .filter(SubscriptionAccess.status == 'ACTIVE')
-                    .first()
-                )
-
-                if subscription_access and not subscription_access.cancelled_at:
-                    subscription_access.cancelled_at = datetime.now(UTC)
-                    session.merge(subscription_access)
-                    session.commit()
-
-                    logger.info(
-                        'subscription_cancelled_via_webhook',
-                        extra={
-                            'stripe_subscription_id': subscription_id,
-                            'user_id': subscription_access.user_id,
-                            'subscription_access_id': subscription_access.id,
-                        },
-                    )
-    elif event_type == 'customer.subscription.deleted':
-        subscription = event['data']['object']
-        subscription_id = subscription['id']
-
-        with session_maker() as session:
-            subscription_access = (
-                session.query(SubscriptionAccess)
-                .filter(SubscriptionAccess.stripe_subscription_id == subscription_id)
-                .filter(SubscriptionAccess.status == 'ACTIVE')
-                .first()
-            )
-
-            if subscription_access:
-                subscription_access.status = 'DISABLED'
-                subscription_access.updated_at = datetime.now(UTC)
-                session.merge(subscription_access)
-                session.commit()
-
-                # Reset user settings to free tier defaults
-                reset_user_to_free_tier_settings(subscription_access.user_id)
-
-                logger.info(
-                    'subscription_expired_reset_to_free_tier',
-                    extra={
-                        'stripe_subscription_id': subscription_id,
-                        'user_id': subscription_access.user_id,
-                        'subscription_access_id': subscription_access.id,
-                    },
-                )
     else:
         logger.info('stripe_webhook_unhandled_event_type', extra={'type': event_type})
 
     return JSONResponse({'status': 'success'})
 
 
-def reset_user_to_free_tier_settings(user_id: str) -> None:
-    """Reset user settings to free tier defaults when subscription ends."""
-    with session_maker() as session:
-        user_settings = (
-            session.query(UserSettings)
-            .filter(UserSettings.keycloak_user_id == user_id)
-            .first()
-        )
-
-        if user_settings:
-            user_settings.llm_model = get_default_litellm_model()
-            user_settings.llm_api_key = None
-            user_settings.llm_api_key_for_byor = None
-            user_settings.llm_base_url = LITE_LLM_API_URL
-            user_settings.max_budget_per_task = None
-            user_settings.confirmation_mode = False
-            user_settings.enable_solvability_analysis = False
-            user_settings.security_analyzer = 'llm'
-            user_settings.agent = 'CodeActAgent'
-            user_settings.language = 'en'
-            user_settings.enable_default_condenser = True
-            user_settings.enable_sound_notifications = False
-            user_settings.enable_proactive_conversation_starters = True
-            user_settings.user_consents_to_analytics = False
-
-            session.merge(user_settings)
-            session.commit()
-
-            logger.info(
-                'user_settings_reset_to_free_tier',
-                extra={
-                    'user_id': user_id,
-                    'reset_timestamp': datetime.now(UTC).isoformat(),
-                },
-            )
-
-
 async def _get_litellm_user(client: httpx.AsyncClient, user_id: str) -> dict:
     """Get a user from litellm with the id matching that given.
 

enterprise/server/routes/event_webhook.py

@@ -234,7 +234,7 @@ def _get_user_id(conversation_id: str) -> str:
         return conversation_metadata.user_id
 
 
-async def _get_session_api_key(user_id: str, conversation_id: str) -> str | None:
+async def _get_session_api_key(user_id: str, conversation_id: str) -> str:
     agent_loop_info = await conversation_manager.get_agent_loop_info(
         user_id, filter_to_sids={conversation_id}
     )

enterprise/server/saas_nested_conversation_manager.py

@@ -178,8 +178,10 @@ class SaasNestedConversationManager(ConversationManager):
         redis = self._get_redis_client()
         key = self._get_redis_conversation_key(user_id, sid)
         starting = await redis.get(key)
+        logger.debug(f'maybe_start_agent_loop starting from redis: {starting}')
 
         runtime = await self._get_runtime(sid)
+        logger.debug(f'maybe_start_agent_loop runtime: {runtime}')
 
         nested_url = None
         session_api_key = None
@@ -187,15 +189,20 @@ class SaasNestedConversationManager(ConversationManager):
         event_store = EventStore(sid, self.file_store, user_id)
         if runtime:
             nested_url = self._get_nested_url_for_runtime(runtime['runtime_id'], sid)
+            logger.debug(f'maybe_start_agent_loop nested_url: {nested_url}')
             session_api_key = runtime.get('session_api_key')
+            logger.debug(f'maybe_start_agent_loop session_api_key: {session_api_key}')
             status_str = (runtime.get('status') or 'stopped').upper()
+            logger.debug(f'maybe_start_agent_loop status_str: {status_str}')
             if status_str in ConversationStatus:
                 status = ConversationStatus[status_str]
         if status is ConversationStatus.STOPPED and starting:
+            logger.debug('maybe_start_agent_loop setting status to starting...')
             status = ConversationStatus.STARTING
 
         if status is ConversationStatus.STOPPED:
             # Mark the agentloop as starting in redis
+            logger.debug('maybe_start_agent_loop starting agent...')
             await redis.set(key, 1, ex=_REDIS_ENTRY_TIMEOUT_SECONDS)
 
             # Start the agent loop in the background

enterprise/storage/subscription_access.py

@@ -7,7 +7,7 @@ from storage.base import Base
 class SubscriptionAccess(Base):  # type: ignore
     """
     Represents a user's subscription access record.
-    Tracks subscription status, duration, payment information, and cancellation status.
+    Tracks subscription status, duration, and payment information.
     """
 
     __tablename__ = 'subscription_access'
@@ -27,8 +27,6 @@ class SubscriptionAccess(Base):  # type: ignore
     end_at = Column(DateTime(timezone=True), nullable=True)
     amount_paid = Column(DECIMAL(19, 4), nullable=True)
     stripe_invoice_payment_id = Column(String, nullable=False)
-    cancelled_at = Column(DateTime(timezone=True), nullable=True)
-    stripe_subscription_id = Column(String, nullable=True, index=True)
     created_at = Column(
         DateTime(timezone=True),
         default=lambda: datetime.now(UTC),  # type: ignore[attr-defined]

enterprise/sync/install_gitlab_webhooks.py

@@ -276,12 +276,12 @@ class VerifyWebhookStatus:
                     webhook
                 )
 
-                gitlab_service_impl = GitLabServiceImpl(external_auth_id=user_id)
+                gitlab_service = GitLabServiceImpl(external_auth_id=user_id)
 
-                if not isinstance(gitlab_service_impl, SaaSGitLabService):
+                if not isinstance(gitlab_service, SaaSGitLabService):
                     raise Exception('Only SaaSGitLabService is supported')
                 # Cast needed when mypy can see OpenHands
-                gitlab_service = cast(type[SaaSGitLabService], gitlab_service_impl)
+                gitlab_service = cast(type[SaaSGitLabService], gitlab_service)
 
                 await self.verify_conditions_are_met(
                     gitlab_service=gitlab_service,

enterprise/tests/unit/integrations/test_utils.py

@@ -1,159 +0,0 @@
-"""Tests for enterprise integrations utils module."""
-
-import pytest
-from integrations.utils import get_summary_for_agent_state
-
-from openhands.core.schema.agent import AgentState
-from openhands.events.observation.agent import AgentStateChangedObservation
-
-
-class TestGetSummaryForAgentState:
-    """Test cases for get_summary_for_agent_state function."""
-
-    def setup_method(self):
-        """Set up test fixtures."""
-        self.conversation_link = 'https://example.com/conversation/123'
-
-    def test_empty_observations_list(self):
-        """Test handling of empty observations list."""
-        result = get_summary_for_agent_state([], self.conversation_link)
-
-        assert 'unknown error' in result.lower()
-        assert self.conversation_link in result
-
-    @pytest.mark.parametrize(
-        'state,expected_text,includes_link',
-        [
-            (AgentState.RATE_LIMITED, 'rate limited', False),
-            (AgentState.AWAITING_USER_INPUT, 'waiting for your input', True),
-        ],
-    )
-    def test_handled_agent_states(self, state, expected_text, includes_link):
-        """Test handling of states with specific behavior."""
-        observation = AgentStateChangedObservation(
-            content=f'Agent state: {state.value}', agent_state=state
-        )
-
-        result = get_summary_for_agent_state([observation], self.conversation_link)
-
-        assert expected_text in result.lower()
-        if includes_link:
-            assert self.conversation_link in result
-        else:
-            assert self.conversation_link not in result
-
-    @pytest.mark.parametrize(
-        'state',
-        [
-            AgentState.FINISHED,
-            AgentState.PAUSED,
-            AgentState.STOPPED,
-            AgentState.AWAITING_USER_CONFIRMATION,
-        ],
-    )
-    def test_unhandled_agent_states(self, state):
-        """Test handling of unhandled states (should all return unknown error)."""
-        observation = AgentStateChangedObservation(
-            content=f'Agent state: {state.value}', agent_state=state
-        )
-
-        result = get_summary_for_agent_state([observation], self.conversation_link)
-
-        assert 'unknown error' in result.lower()
-        assert self.conversation_link in result
-
-    @pytest.mark.parametrize(
-        'error_code,expected_text',
-        [
-            (
-                'STATUS$ERROR_LLM_AUTHENTICATION',
-                'authentication with the llm provider failed',
-            ),
-            (
-                'STATUS$ERROR_LLM_SERVICE_UNAVAILABLE',
-                'llm service is temporarily unavailable',
-            ),
-            (
-                'STATUS$ERROR_LLM_INTERNAL_SERVER_ERROR',
-                'llm provider encountered an internal error',
-            ),
-            ('STATUS$ERROR_LLM_OUT_OF_CREDITS', "you've run out of credits"),
-            ('STATUS$ERROR_LLM_CONTENT_POLICY_VIOLATION', 'content policy violation'),
-        ],
-    )
-    def test_error_state_readable_reasons(self, error_code, expected_text):
-        """Test all readable error reason mappings."""
-        observation = AgentStateChangedObservation(
-            content=f'Agent encountered error: {error_code}',
-            agent_state=AgentState.ERROR,
-            reason=error_code,
-        )
-
-        result = get_summary_for_agent_state([observation], self.conversation_link)
-
-        assert 'encountered an error' in result.lower()
-        assert expected_text in result.lower()
-        assert self.conversation_link in result
-
-    def test_error_state_with_custom_reason(self):
-        """Test handling of ERROR state with a custom reason."""
-        observation = AgentStateChangedObservation(
-            content='Agent encountered an error',
-            agent_state=AgentState.ERROR,
-            reason='Test error message',
-        )
-
-        result = get_summary_for_agent_state([observation], self.conversation_link)
-
-        assert 'encountered an error' in result.lower()
-        assert 'test error message' in result.lower()
-        assert self.conversation_link in result
-
-    def test_multiple_observations_uses_first(self):
-        """Test that when multiple observations are provided, only the first is used."""
-        observation1 = AgentStateChangedObservation(
-            content='Agent is awaiting user input',
-            agent_state=AgentState.AWAITING_USER_INPUT,
-        )
-        observation2 = AgentStateChangedObservation(
-            content='Agent encountered an error',
-            agent_state=AgentState.ERROR,
-            reason='Should not be used',
-        )
-
-        result = get_summary_for_agent_state(
-            [observation1, observation2], self.conversation_link
-        )
-
-        # Should handle the first observation (AWAITING_USER_INPUT), not the second (ERROR)
-        assert 'waiting for your input' in result.lower()
-        assert 'error' not in result.lower()
-
-    def test_awaiting_user_input_specific_message(self):
-        """Test that AWAITING_USER_INPUT returns the specific expected message."""
-        observation = AgentStateChangedObservation(
-            content='Agent is awaiting user input',
-            agent_state=AgentState.AWAITING_USER_INPUT,
-        )
-
-        result = get_summary_for_agent_state([observation], self.conversation_link)
-
-        # Test the exact message format
-        assert 'waiting for your input' in result.lower()
-        assert 'continue the conversation' in result.lower()
-        assert self.conversation_link in result
-        assert 'unknown error' not in result.lower()
-
-    def test_rate_limited_specific_message(self):
-        """Test that RATE_LIMITED returns the specific expected message."""
-        observation = AgentStateChangedObservation(
-            content='Agent was rate limited', agent_state=AgentState.RATE_LIMITED
-        )
-
-        result = get_summary_for_agent_state([observation], self.conversation_link)
-
-        # Test the exact message format
-        assert 'rate limited' in result.lower()
-        assert 'try again later' in result.lower()
-        # RATE_LIMITED doesn't include conversation link in response
-        assert self.conversation_link not in result

enterprise/tests/unit/test_billing.py

@@ -5,16 +5,16 @@ import pytest
 import stripe
 from fastapi import HTTPException, Request, status
 from httpx import HTTPStatusError, Response
-from integrations.stripe_service import has_payment_method
+from server.routes import billing
 from server.routes.billing import (
     CreateBillingSessionResponse,
     CreateCheckoutSessionRequest,
     GetCreditsResponse,
     cancel_callback,
-    cancel_subscription,
     create_checkout_session,
-    create_subscription_checkout_session,
+    create_customer_setup_session,
     get_credits,
+    has_payment_method,
     success_callback,
 )
 from sqlalchemy import create_engine
@@ -362,7 +362,8 @@ async def test_cancel_callback_session_not_found():
         response = await cancel_callback('test_session_id', mock_request)
         assert response.status_code == 302
         assert (
-            response.headers['location'] == 'http://test.com/settings?checkout=cancel'
+            response.headers['location']
+            == 'http://test.com/settings/billing?checkout=cancel'
         )
 
         # Verify no database updates occurred
@@ -388,7 +389,8 @@ async def test_cancel_callback_success():
 
         assert response.status_code == 302
         assert (
-            response.headers['location'] == 'http://test.com/settings?checkout=cancel'
+            response.headers['location']
+            == 'http://test.com/settings/billing?checkout=cancel'
         )
 
         # Verify database updates
@@ -400,312 +402,51 @@ async def test_cancel_callback_success():
 @pytest.mark.asyncio
 async def test_has_payment_method_with_payment_method():
     """Test has_payment_method returns True when user has a payment method."""
-    with (
-        patch('integrations.stripe_service.session_maker') as mock_session_maker,
-        patch(
-            'stripe.Customer.list_payment_methods_async',
-            AsyncMock(return_value=MagicMock(data=[MagicMock()])),
-        ) as mock_list_payment_methods,
-    ):
-        # Setup mock session
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.first.return_value = (
-            MagicMock(stripe_customer_id='cus_test123')
-        )
 
+    mock_has_payment_method = AsyncMock(return_value=True)
+    with patch(
+        'integrations.stripe_service.has_payment_method', mock_has_payment_method
+    ):
         result = await has_payment_method('mock_user')
         assert result is True
-        mock_list_payment_methods.assert_called_once_with('cus_test123')
+    mock_has_payment_method.assert_called_once_with('mock_user')
 
 
 @pytest.mark.asyncio
 async def test_has_payment_method_without_payment_method():
     """Test has_payment_method returns False when user has no payment method."""
-    with (
-        patch('integrations.stripe_service.session_maker') as mock_session_maker,
-        patch(
-            'stripe.Customer.list_payment_methods_async',
-            AsyncMock(return_value=MagicMock(data=[])),
-        ) as mock_list_payment_methods,
+    mock_has_payment_method = AsyncMock(return_value=False)
+    with patch(
+        'integrations.stripe_service.has_payment_method', mock_has_payment_method
     ):
-        # Setup mock session
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.first.return_value = (
-            MagicMock(stripe_customer_id='cus_test123')
-        )
-
+        mock_has_payment_method.return_value = False
         result = await has_payment_method('mock_user')
         assert result is False
-        mock_list_payment_methods.assert_called_once_with('cus_test123')
+    mock_has_payment_method.assert_called_once_with('mock_user')
 
 
 @pytest.mark.asyncio
-async def test_cancel_subscription_success():
-    """Test successful subscription cancellation."""
-    from datetime import UTC, datetime
-
-    from storage.subscription_access import SubscriptionAccess
-
-    # Mock active subscription
-    mock_subscription_access = SubscriptionAccess(
-        id=1,
-        status='ACTIVE',
-        user_id='test_user',
-        start_at=datetime.now(UTC),
-        end_at=datetime.now(UTC),
-        amount_paid=2000,
-        stripe_invoice_payment_id='pi_test',
-        stripe_subscription_id='sub_test123',
-        cancelled_at=None,
+async def test_create_customer_setup_session_success():
+    """Test successful creation of customer setup session."""
+    mock_request = Request(
+        scope={'type': 'http', 'state': {'user_id': 'mock_user'}, 'headers': []}
     )
 
-    # Mock Stripe subscription response
-    mock_stripe_subscription = MagicMock()
-    mock_stripe_subscription.cancel_at_period_end = True
-
-    with (
-        patch('server.routes.billing.session_maker') as mock_session_maker,
-        patch(
-            'stripe.Subscription.modify_async',
-            AsyncMock(return_value=mock_stripe_subscription),
-        ) as mock_stripe_modify,
-    ):
-        # Setup mock session
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.first.return_value = mock_subscription_access
-
-        # Call the function
-        result = await cancel_subscription('test_user')
-
-        # Verify Stripe API was called
-        mock_stripe_modify.assert_called_once_with(
-            'sub_test123', cancel_at_period_end=True
-        )
-
-        # Verify database was updated
-        assert mock_subscription_access.cancelled_at is not None
-        mock_session.merge.assert_called_once_with(mock_subscription_access)
-        mock_session.commit.assert_called_once()
-
-        # Verify response
-        assert result.status_code == 200
-
-
-@pytest.mark.asyncio
-async def test_cancel_subscription_no_active_subscription():
-    """Test cancellation when no active subscription exists."""
-    with (
-        patch('server.routes.billing.session_maker') as mock_session_maker,
-    ):
-        # Setup mock session with no subscription found
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.first.return_value = None
-
-        # Call the function and expect HTTPException
-        with pytest.raises(HTTPException) as exc_info:
-            await cancel_subscription('test_user')
-
-        assert exc_info.value.status_code == 404
-        assert 'No active subscription found' in str(exc_info.value.detail)
-
-
-@pytest.mark.asyncio
-async def test_cancel_subscription_missing_stripe_id():
-    """Test cancellation when subscription has no Stripe ID."""
-    from datetime import UTC, datetime
-
-    from storage.subscription_access import SubscriptionAccess
-
-    # Mock subscription without Stripe ID
-    mock_subscription_access = SubscriptionAccess(
-        id=1,
-        status='ACTIVE',
-        user_id='test_user',
-        start_at=datetime.now(UTC),
-        end_at=datetime.now(UTC),
-        amount_paid=2000,
-        stripe_invoice_payment_id='pi_test',
-        stripe_subscription_id=None,  # Missing Stripe ID
-        cancelled_at=None,
+    mock_customer = stripe.Customer(
+        id='mock-customer', metadata={'user_id': 'mock-user'}
     )
+    mock_session = MagicMock()
+    mock_session.url = 'https://checkout.stripe.com/test-session'
+    mock_create = AsyncMock(return_value=mock_session)
 
     with (
-        patch('server.routes.billing.session_maker') as mock_session_maker,
-    ):
-        # Setup mock session
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.first.return_value = mock_subscription_access
-
-        # Call the function and expect HTTPException
-        with pytest.raises(HTTPException) as exc_info:
-            await cancel_subscription('test_user')
-
-        assert exc_info.value.status_code == 400
-        assert 'missing Stripe subscription ID' in str(exc_info.value.detail)
-
-
-@pytest.mark.asyncio
-async def test_cancel_subscription_stripe_error():
-    """Test cancellation when Stripe API fails."""
-    from datetime import UTC, datetime
-
-    from storage.subscription_access import SubscriptionAccess
-
-    # Mock active subscription
-    mock_subscription_access = SubscriptionAccess(
-        id=1,
-        status='ACTIVE',
-        user_id='test_user',
-        start_at=datetime.now(UTC),
-        end_at=datetime.now(UTC),
-        amount_paid=2000,
-        stripe_invoice_payment_id='pi_test',
-        stripe_subscription_id='sub_test123',
-        cancelled_at=None,
-    )
-
-    with (
-        patch('server.routes.billing.session_maker') as mock_session_maker,
-        patch(
-            'stripe.Subscription.modify_async',
-            AsyncMock(side_effect=stripe.StripeError('API Error')),
-        ),
-    ):
-        # Setup mock session
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.first.return_value = mock_subscription_access
-
-        # Call the function and expect HTTPException
-        with pytest.raises(HTTPException) as exc_info:
-            await cancel_subscription('test_user')
-
-        assert exc_info.value.status_code == 500
-        assert 'Failed to cancel subscription' in str(exc_info.value.detail)
-
-
-@pytest.mark.asyncio
-async def test_create_subscription_checkout_session_duplicate_prevention():
-    """Test that creating a subscription when user already has active subscription raises error."""
-    from datetime import UTC, datetime
-
-    from storage.subscription_access import SubscriptionAccess
-
-    # Mock active subscription
-    mock_subscription_access = SubscriptionAccess(
-        id=1,
-        status='ACTIVE',
-        user_id='test_user',
-        start_at=datetime.now(UTC),
-        end_at=datetime.now(UTC),
-        amount_paid=2000,
-        stripe_invoice_payment_id='pi_test',
-        stripe_subscription_id='sub_test123',
-        cancelled_at=None,
-    )
-
-    mock_request = Request(scope={'type': 'http'})
-    mock_request._base_url = URL('http://test.com/')
-
-    with (
-        patch('server.routes.billing.session_maker') as mock_session_maker,
-    ):
-        # Setup mock session to return existing active subscription
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.first.return_value = mock_subscription_access
-
-        # Call the function and expect HTTPException
-        with pytest.raises(HTTPException) as exc_info:
-            await create_subscription_checkout_session(
-                mock_request, user_id='test_user'
-            )
-
-        assert exc_info.value.status_code == 400
-        assert (
-            'user already has an active subscription'
-            in str(exc_info.value.detail).lower()
-        )
-
-
-@pytest.mark.asyncio
-async def test_create_subscription_checkout_session_allows_after_cancellation():
-    """Test that creating a subscription is allowed when previous subscription was cancelled."""
-    mock_request = Request(scope={'type': 'http'})
-    mock_request._base_url = URL('http://test.com/')
-
-    mock_session_obj = MagicMock()
-    mock_session_obj.url = 'https://checkout.stripe.com/test-session'
-    mock_session_obj.id = 'test_session_id'
-
-    with (
-        patch('server.routes.billing.session_maker') as mock_session_maker,
         patch(
             'integrations.stripe_service.find_or_create_customer',
-            AsyncMock(return_value='cus_test123'),
-        ),
-        patch(
-            'stripe.checkout.Session.create_async',
-            AsyncMock(return_value=mock_session_obj),
-        ),
-        patch(
-            'server.routes.billing.SUBSCRIPTION_PRICE_DATA',
-            {'MONTHLY_SUBSCRIPTION': {'unit_amount': 2000}},
+            AsyncMock(return_value=mock_customer),
         ),
+        patch('stripe.checkout.Session.create_async', mock_create),
     ):
-        # Setup mock session - the query should return None because cancelled subscriptions are filtered out
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.first.return_value = None
+        result = await create_customer_setup_session(mock_request)
 
-        # Should succeed
-        result = await create_subscription_checkout_session(
-            mock_request, user_id='test_user'
-        )
-
-        assert isinstance(result, CreateBillingSessionResponse)
-        assert result.redirect_url == 'https://checkout.stripe.com/test-session'
-
-
-@pytest.mark.asyncio
-async def test_create_subscription_checkout_session_success_no_existing():
-    """Test successful subscription creation when no existing subscription."""
-    mock_request = Request(scope={'type': 'http'})
-    mock_request._base_url = URL('http://test.com/')
-
-    mock_session_obj = MagicMock()
-    mock_session_obj.url = 'https://checkout.stripe.com/test-session'
-    mock_session_obj.id = 'test_session_id'
-
-    with (
-        patch('server.routes.billing.session_maker') as mock_session_maker,
-        patch(
-            'integrations.stripe_service.find_or_create_customer',
-            AsyncMock(return_value='cus_test123'),
-        ),
-        patch(
-            'stripe.checkout.Session.create_async',
-            AsyncMock(return_value=mock_session_obj),
-        ),
-        patch(
-            'server.routes.billing.SUBSCRIPTION_PRICE_DATA',
-            {'MONTHLY_SUBSCRIPTION': {'unit_amount': 2000}},
-        ),
-    ):
-        # Setup mock session to return no existing subscription
-        mock_session = MagicMock()
-        mock_session_maker.return_value.__enter__.return_value = mock_session
-        mock_session.query.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.filter.return_value.first.return_value = None
-
-        # Should succeed
-        result = await create_subscription_checkout_session(
-            mock_request, user_id='test_user'
-        )
-
-        assert isinstance(result, CreateBillingSessionResponse)
+        assert isinstance(result, billing.CreateBillingSessionResponse)
         assert result.redirect_url == 'https://checkout.stripe.com/test-session'

evaluation/benchmarks/multi_swe_bench/SWE-Gym.md

@@ -1,152 +0,0 @@
-<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', 'mswebench')
-LANGUAGE = os.environ.get('LANGUAGE', 'java')
+DOCKER_IMAGE_PREFIX = os.environ.get('EVAL_DOCKER_IMAGE_PREFIX', '')
+LANGUAGE = os.environ.get('LANGUAGE', 'python')
 logger.info(f'Using docker image prefix: {DOCKER_IMAGE_PREFIX}')
 
 
@@ -305,19 +305,31 @@ 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}'
-        return f'{DOCKER_IMAGE_PREFIX}/{container_name}:{container_tag}'
+        # 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"
 
 
 def get_config(
     instance: pd.Series,
     metadata: EvalMetadata,
 ) -> OpenHandsConfig:
-    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.'
-    )
+    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}')
 
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = base_container_image
@@ -760,6 +772,7 @@ 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(
@@ -774,7 +787,6 @@ 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')
@@ -827,7 +839,7 @@ if __name__ == '__main__':
         args.eval_num_workers,
         process_instance,
         timeout_seconds=120 * 60,  # 2 hour PER instance should be more than enough
-        max_retries=3,
+        max_retries=5,
     )
     # 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

@@ -1,54 +1,37 @@
-import argparse
 import json
 
+input_file = 'XXX.jsonl'
+output_file = 'YYY.jsonl'
 
-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
+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
 
-            # 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
+        # 提取原始数据
+        org = item.get('org', '')
+        repo = item.get('repo', '')
+        number = str(item.get('number', ''))
 
-            # 提取原始数据
-            org = item.get('org', '')
-            repo = item.get('repo', '')
-            number = str(item.get('number', ''))
+        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
 
-            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)
+        output_data = new_item
+        fout.write(json.dumps(output_data, ensure_ascii=False) + '\n')

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

@@ -1,69 +0,0 @@
-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

@@ -1,11 +1,13 @@
-import argparse
 import json
 import re
 
+IN_FILE = 'output.jsonl'
+OUT_FILE = 'patch.jsonl'
 
-def main(input_file, output_file):
-    with open(input_file, 'r') as fin:
-        with open(output_file, 'w') as fout:
+
+def main():
+    with open(IN_FILE, 'r') as fin:
+        with open(OUT_FILE, 'w') as fout:
             for line in fin:
                 data = json.loads(line)
                 groups = re.match(r'(.*)__(.*)-(.*)', data['instance_id'])
@@ -13,14 +15,10 @@ def main(input_file, output_file):
                     'org': groups.group(1),
                     'repo': groups.group(2),
                     'number': groups.group(3),
-                    'fix_patch': data.get('test_result', {}).get('git_patch', '') or '',
+                    'fix_patch': data['test_result']['git_patch'],
                 }
                 fout.write(json.dumps(patch) + '\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)
+    main()

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

@@ -1,70 +0,0 @@
-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

@@ -1,176 +0,0 @@
-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

@@ -1,146 +0,0 @@
-#!/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 "LANGUAGE not specified, use default python"
-  LANGUAGE="java"
+  echo "LANUGUAGE not specified, use default python"
+  LANGUAGE="python"
 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 LANGUAGE is python"
+  echo "EVAL_DOCKER_IMAGE_PREFIX is docker.io/xingyaoww/ as default as LANUGUAGE is python"
     EVAL_DOCKER_IMAGE_PREFIX="docker.io/xingyaoww/"
   elif [ "$LANGUAGE" = "java" ]; then
-  echo "EVAL_DOCKER_IMAGE_PREFIX is empty as LANGUAGE is java"
+  echo "EVAL_DOCKER_IMAGE_PREFIX is java_verified as LANUGUAGE is java"
     EVAL_DOCKER_IMAGE_PREFIX=""
   fi
 fi

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

@@ -1,344 +0,0 @@
-{
- "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

@@ -1,81 +0,0 @@
-# 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

@@ -1,52 +0,0 @@
-"""
-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

@@ -1,45 +0,0 @@
-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

@@ -1,39 +0,0 @@
-"""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

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

evaluation/benchmarks/swe_perf/run_infer.py

@@ -1,978 +0,0 @@
-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

@@ -1,146 +0,0 @@
-#!/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

@@ -1,54 +0,0 @@
-"""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

@@ -1,43 +0,0 @@
-#!/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/.husky/pre-commit

@@ -1,6 +1,8 @@
 # Run frontend checks
 echo "Running frontend checks..."
 cd frontend
+npm run lint
+npm run check-translation-completeness
 npx lint-staged
 
 # Run backend pre-commit

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

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

frontend/__tests__/components/browser.test.tsx

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

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

@@ -3,7 +3,7 @@ import { screen } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import { createRoutesStub } from "react-router";
 import { ExpandableMessage } from "#/components/features/chat/expandable-message";
-import OptionService from "#/api/option-service/option-service.api";
+import OpenHands from "#/api/open-hands";
 
 vi.mock("react-i18next", async () => {
   const actual = await vi.importActual("react-i18next");
@@ -113,7 +113,7 @@ describe("ExpandableMessage", () => {
   });
 
   it("should render the out of credits message when the user is out of credits", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     // @ts-expect-error - We only care about the APP_MODE and FEATURE_FLAGS fields
     getConfigSpy.mockResolvedValue({
       APP_MODE: "saas",

frontend/__tests__/components/features/analytics/analytics-consent-form-modal.test.tsx

@@ -3,13 +3,13 @@ import { describe, expect, it, vi } from "vitest";
 import { render, screen, waitFor } from "@testing-library/react";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import { AnalyticsConsentFormModal } from "#/components/features/analytics/analytics-consent-form-modal";
-import SettingsService from "#/settings-service/settings-service.api";
+import OpenHands from "#/api/open-hands";
 
 describe("AnalyticsConsentFormModal", () => {
   it("should call saveUserSettings with consent", async () => {
     const user = userEvent.setup();
     const onCloseMock = vi.fn();
-    const saveUserSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+    const saveUserSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
     render(<AnalyticsConsentFormModal onClose={onCloseMock} />, {
       wrapper: ({ children }) => (

frontend/__tests__/components/features/chat/messages.test.tsx

@@ -8,7 +8,7 @@ import {
   UserMessageAction,
 } from "#/types/core/actions";
 import { OpenHandsObservation } from "#/types/core/observations";
-import ConversationService from "#/api/conversation-service/conversation-service.api";
+import OpenHands from "#/api/open-hands";
 import { Conversation } from "#/api/open-hands.types";
 
 vi.mock("react-router", () => ({
@@ -80,7 +80,7 @@ describe("Messages", () => {
   });
 
   it("should render a launch to microagent action button on chat messages only if it is a user message", () => {
-    const getConversationSpy = vi.spyOn(ConversationService, "getConversation");
+    const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
     const mockConversation: Conversation = {
       conversation_id: "123",
       title: "Test Conversation",

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

@@ -357,6 +357,69 @@ 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

@@ -1,11 +1,12 @@
 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 { renderWithQueryAndI18n } from "test-utils";
+import { renderWithProviders } from "test-utils";
 import { ConversationPanel } from "#/components/features/conversation-panel/conversation-panel";
-import ConversationService from "#/api/conversation-service/conversation-service.api";
+import OpenHands from "#/api/open-hands";
 import { Conversation } from "#/api/open-hands.types";
 
 describe("ConversationPanel", () => {
@@ -17,7 +18,16 @@ describe("ConversationPanel", () => {
     },
   ]);
 
-  const renderConversationPanel = () => renderWithQueryAndI18n(<RouterStub />);
+  const renderConversationPanel = (config?: QueryClientConfig) =>
+    renderWithProviders(<RouterStub />, {
+      preloadedState: {
+        metrics: {
+          cost: null,
+          max_budget_per_task: null,
+          usage: null,
+        },
+      },
+    });
 
   beforeAll(() => {
     vi.mock("react-router", async (importOriginal) => ({
@@ -75,7 +85,7 @@ describe("ConversationPanel", () => {
     vi.clearAllMocks();
     vi.restoreAllMocks();
     // Setup default mock for getUserConversations
-    vi.spyOn(ConversationService, "getUserConversations").mockResolvedValue({
+    vi.spyOn(OpenHands, "getUserConversations").mockResolvedValue({
       results: [...mockConversations],
       next_page_id: null,
     });
@@ -91,10 +101,7 @@ describe("ConversationPanel", () => {
   });
 
   it("should display an empty state when there are no conversations", async () => {
-    const getUserConversationsSpy = vi.spyOn(
-      ConversationService,
-      "getUserConversations",
-    );
+    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockResolvedValue({
       results: [],
       next_page_id: null,
@@ -107,10 +114,7 @@ describe("ConversationPanel", () => {
   });
 
   it("should handle an error when fetching conversations", async () => {
-    const getUserConversationsSpy = vi.spyOn(
-      ConversationService,
-      "getUserConversations",
-    );
+    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockRejectedValue(
       new Error("Failed to fetch conversations"),
     );
@@ -199,17 +203,14 @@ describe("ConversationPanel", () => {
       },
     ];
 
-    const getUserConversationsSpy = vi.spyOn(
-      ConversationService,
-      "getUserConversations",
-    );
+    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockImplementation(async () => ({
       results: mockData,
       next_page_id: null,
     }));
 
     const deleteUserConversationSpy = vi.spyOn(
-      ConversationService,
+      OpenHands,
       "deleteUserConversation",
     );
     deleteUserConversationSpy.mockImplementation(async (id: string) => {
@@ -259,10 +260,7 @@ describe("ConversationPanel", () => {
 
   it("should refetch data on rerenders", async () => {
     const user = userEvent.setup();
-    const getUserConversationsSpy = vi.spyOn(
-      ConversationService,
-      "getUserConversations",
-    );
+    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockResolvedValue({
       results: [...mockConversations],
       next_page_id: null,
@@ -287,7 +285,15 @@ describe("ConversationPanel", () => {
       },
     ]);
 
-    renderWithQueryAndI18n(<MyRouterStub />);
+    renderWithProviders(<MyRouterStub />, {
+      preloadedState: {
+        metrics: {
+          cost: null,
+          max_budget_per_task: null,
+          usage: null,
+        },
+      },
+    });
 
     const toggleButton = screen.getByText("Toggle");
 
@@ -351,10 +357,7 @@ describe("ConversationPanel", () => {
       },
     ];
 
-    const getUserConversationsSpy = vi.spyOn(
-      ConversationService,
-      "getUserConversations",
-    );
+    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockResolvedValue({
       results: mockRunningConversations,
       next_page_id: null,
@@ -421,19 +424,13 @@ describe("ConversationPanel", () => {
       },
     ];
 
-    const getUserConversationsSpy = vi.spyOn(
-      ConversationService,
-      "getUserConversations",
-    );
+    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockImplementation(async () => ({
       results: mockData,
       next_page_id: null,
     }));
 
-    const stopConversationSpy = vi.spyOn(
-      ConversationService,
-      "stopConversation",
-    );
+    const stopConversationSpy = vi.spyOn(OpenHands, "stopConversation");
     stopConversationSpy.mockImplementation(async (id: string) => {
       const conversation = mockData.find((conv) => conv.conversation_id === id);
       if (conversation) {
@@ -515,10 +512,7 @@ describe("ConversationPanel", () => {
       },
     ];
 
-    const getUserConversationsSpy = vi.spyOn(
-      ConversationService,
-      "getUserConversations",
-    );
+    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockResolvedValue({
       results: mockMixedStatusConversations,
       next_page_id: null,
@@ -625,10 +619,7 @@ describe("ConversationPanel", () => {
     const user = userEvent.setup();
 
     // Mock the updateConversation API call
-    const updateConversationSpy = vi.spyOn(
-      ConversationService,
-      "updateConversation",
-    );
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
     updateConversationSpy.mockResolvedValue(true);
 
     // Mock the toast function
@@ -665,10 +656,7 @@ describe("ConversationPanel", () => {
   it("should save title when Enter key is pressed", async () => {
     const user = userEvent.setup();
 
-    const updateConversationSpy = vi.spyOn(
-      ConversationService,
-      "updateConversation",
-    );
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
     updateConversationSpy.mockResolvedValue(true);
 
     renderConversationPanel();
@@ -697,10 +685,7 @@ describe("ConversationPanel", () => {
   it("should trim whitespace from title", async () => {
     const user = userEvent.setup();
 
-    const updateConversationSpy = vi.spyOn(
-      ConversationService,
-      "updateConversation",
-    );
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
     updateConversationSpy.mockResolvedValue(true);
 
     renderConversationPanel();
@@ -729,10 +714,7 @@ describe("ConversationPanel", () => {
   it("should revert to original title when empty", async () => {
     const user = userEvent.setup();
 
-    const updateConversationSpy = vi.spyOn(
-      ConversationService,
-      "updateConversation",
-    );
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
     updateConversationSpy.mockResolvedValue(true);
 
     renderConversationPanel();
@@ -758,10 +740,7 @@ describe("ConversationPanel", () => {
   it("should handle API error when updating title", async () => {
     const user = userEvent.setup();
 
-    const updateConversationSpy = vi.spyOn(
-      ConversationService,
-      "updateConversation",
-    );
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
     updateConversationSpy.mockRejectedValue(new Error("API Error"));
 
     vi.mock("#/utils/custom-toast-handlers", () => ({
@@ -828,10 +807,7 @@ describe("ConversationPanel", () => {
   it("should not call API when title is unchanged", async () => {
     const user = userEvent.setup();
 
-    const updateConversationSpy = vi.spyOn(
-      ConversationService,
-      "updateConversation",
-    );
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
     updateConversationSpy.mockResolvedValue(true);
 
     renderConversationPanel();
@@ -857,10 +833,7 @@ describe("ConversationPanel", () => {
   it("should handle special characters in title", async () => {
     const user = userEvent.setup();
 
-    const updateConversationSpy = vi.spyOn(
-      ConversationService,
-      "updateConversation",
-    );
+    const updateConversationSpy = vi.spyOn(OpenHands, "updateConversation");
     updateConversationSpy.mockResolvedValue(true);
 
     renderConversationPanel();

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

@@ -3,7 +3,7 @@ import { render, screen } from "@testing-library/react";
 import { Provider } from "react-redux";
 import { setupStore } from "test-utils";
 import { describe, expect, it, vi } from "vitest";
-import { HomeHeader } from "#/components/features/home/home-header/home-header";
+import { HomeHeader } from "#/components/features/home/home-header";
 
 // Mock the translation function
 vi.mock("react-i18next", async () => {

frontend/__tests__/components/features/home/new-conversation.test.tsx

@@ -5,8 +5,8 @@ import { createRoutesStub } from "react-router";
 import { setupStore } from "test-utils";
 import { describe, expect, it, vi } from "vitest";
 import userEvent from "@testing-library/user-event";
-import ConversationService from "#/api/conversation-service/conversation-service.api";
-import { NewConversation } from "#/components/features/home/new-conversation/new-conversation";
+import { NewConversation } from "#/components/features/home/new-conversation";
+import OpenHands from "#/api/open-hands";
 
 // Mock the translation function
 vi.mock("react-i18next", async () => {
@@ -54,10 +54,7 @@ const renderNewConversation = () => {
 
 describe("NewConversation", () => {
   it("should create an empty conversation and redirect when pressing the launch from scratch button", async () => {
-    const createConversationSpy = vi.spyOn(
-      ConversationService,
-      "createConversation",
-    );
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
 
     renderNewConversation();
 

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

@@ -5,10 +5,7 @@ import { QueryClientProvider, QueryClient } from "@tanstack/react-query";
 import { setupStore } from "test-utils";
 import { Provider } from "react-redux";
 import { createRoutesStub, Outlet } from "react-router";
-import SettingsService from "#/settings-service/settings-service.api";
-import ConversationService from "#/api/conversation-service/conversation-service.api";
-import GitService from "#/api/git-service/git-service.api";
-import OptionService from "#/api/option-service/option-service.api";
+import OpenHands from "#/api/open-hands";
 import { GitRepository } from "#/types/git";
 import { RepoConnector } from "#/components/features/home/repo-connector";
 import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
@@ -69,7 +66,7 @@ const MOCK_RESPOSITORIES: GitRepository[] = [
 ];
 
 beforeEach(() => {
-  const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+  const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
   getSettingsSpy.mockResolvedValue({
     ...MOCK_DEFAULT_USER_SETTINGS,
     provider_tokens_set: {
@@ -87,7 +84,7 @@ describe("RepoConnector", () => {
 
   it("should render the available repositories in the dropdown", async () => {
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -96,7 +93,7 @@ describe("RepoConnector", () => {
     });
 
     // Mock the search function that's used by the dropdown
-    vi.spyOn(GitService, "searchGitRepositories").mockResolvedValue(
+    vi.spyOn(OpenHands, "searchGitRepositories").mockResolvedValue(
       MOCK_RESPOSITORIES,
     );
 
@@ -124,7 +121,7 @@ describe("RepoConnector", () => {
 
   it("should only enable the launch button if a repo is selected", async () => {
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -138,16 +135,10 @@ describe("RepoConnector", () => {
     expect(launchButton).toBeDisabled();
 
     // Mock the repository branches API call
-    vi.spyOn(GitService, "getRepositoryBranches").mockResolvedValue({
-      branches: [
-        { name: "main", commit_sha: "123", protected: false },
-        { name: "develop", commit_sha: "456", protected: false },
-      ],
-      has_next_page: false,
-      current_page: 1,
-      per_page: 30,
-      total_count: 2,
-    });
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({ branches: [
+      { name: "main", commit_sha: "123", protected: false },
+      { name: "develop", commit_sha: "456", protected: false },
+    ], has_next_page: false, current_page: 1, per_page: 30, total_count: 2 });
 
     // First select the provider
     const providerDropdown = await waitFor(() =>
@@ -179,14 +170,14 @@ describe("RepoConnector", () => {
   });
 
   it("should render the 'add github repos' link in dropdown if saas mode and github provider is set", async () => {
-    const getConfiSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfiSpy = vi.spyOn(OpenHands, "getConfig");
     // @ts-expect-error - only return the APP_MODE and APP_SLUG
     getConfiSpy.mockResolvedValue({
       APP_MODE: "saas",
       APP_SLUG: "openhands",
     });
 
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       provider_tokens_set: {
@@ -196,7 +187,7 @@ describe("RepoConnector", () => {
     });
 
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -226,14 +217,14 @@ describe("RepoConnector", () => {
   });
 
   it("should not render the 'add github repos' link if github provider is not set", async () => {
-    const getConfiSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfiSpy = vi.spyOn(OpenHands, "getConfig");
     // @ts-expect-error - only return the APP_MODE and APP_SLUG
     getConfiSpy.mockResolvedValue({
       APP_MODE: "saas",
       APP_SLUG: "openhands",
     });
 
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       provider_tokens_set: {
@@ -243,7 +234,7 @@ describe("RepoConnector", () => {
     });
 
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -271,13 +262,13 @@ describe("RepoConnector", () => {
   });
 
   it("should not render the 'add github repos' link in dropdown if oss mode", async () => {
-    const getConfiSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfiSpy = vi.spyOn(OpenHands, "getConfig");
     // @ts-expect-error - only return the APP_MODE
     getConfiSpy.mockResolvedValue({
       APP_MODE: "oss",
     });
 
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       provider_tokens_set: {
@@ -287,7 +278,7 @@ describe("RepoConnector", () => {
     });
 
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -315,10 +306,7 @@ describe("RepoConnector", () => {
   });
 
   it("should create a conversation and redirect with the selected repo when pressing the launch button", async () => {
-    const createConversationSpy = vi.spyOn(
-      ConversationService,
-      "createConversation",
-    );
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
     createConversationSpy.mockResolvedValue({
       conversation_id: "mock-conversation-id",
       title: "Test Conversation",
@@ -333,7 +321,7 @@ describe("RepoConnector", () => {
       session_api_key: null,
     });
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -352,16 +340,10 @@ describe("RepoConnector", () => {
     expect(createConversationSpy).not.toHaveBeenCalled();
 
     // Mock the repository branches API call
-    vi.spyOn(GitService, "getRepositoryBranches").mockResolvedValue({
-      branches: [
-        { name: "main", commit_sha: "123", protected: false },
-        { name: "develop", commit_sha: "456", protected: false },
-      ],
-      has_next_page: false,
-      current_page: 1,
-      per_page: 30,
-      total_count: 2,
-    });
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({ branches: [
+      { name: "main", commit_sha: "123", protected: false },
+      { name: "develop", commit_sha: "456", protected: false },
+    ], has_next_page: false, current_page: 1, per_page: 30, total_count: 2 });
 
     // First select the provider
     const providerDropdown = await waitFor(() =>
@@ -403,13 +385,10 @@ describe("RepoConnector", () => {
   });
 
   it("should change the launch button text to 'Loading...' when creating a conversation", async () => {
-    const createConversationSpy = vi.spyOn(
-      ConversationService,
-      "createConversation",
-    );
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
     createConversationSpy.mockImplementation(() => new Promise(() => {})); // Never resolves to keep loading state
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -418,16 +397,10 @@ describe("RepoConnector", () => {
     });
 
     // Mock the repository branches API call
-    vi.spyOn(GitService, "getRepositoryBranches").mockResolvedValue({
-      branches: [
-        { name: "main", commit_sha: "123", protected: false },
-        { name: "develop", commit_sha: "456", protected: false },
-      ],
-      has_next_page: false,
-      current_page: 1,
-      per_page: 30,
-      total_count: 2,
-    });
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({ branches: [
+      { name: "main", commit_sha: "123", protected: false },
+      { name: "develop", commit_sha: "456", protected: false },
+    ], has_next_page: false, current_page: 1, per_page: 30, total_count: 2 });
 
     renderRepoConnector();
 
@@ -475,7 +448,7 @@ describe("RepoConnector", () => {
   });
 
   it("should display a button to settings if the user needs to sign in with their git provider", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       provider_tokens_set: {},

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

@@ -2,8 +2,7 @@ import { render, screen } from "@testing-library/react";
 import { describe, expect, vi, beforeEach, it } from "vitest";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import { RepositorySelectionForm } from "../../../../src/components/features/home/repo-selection-form";
-import UserService from "#/api/user-service/user-service.api";
-import GitService from "#/api/git-service/git-service.api";
+import OpenHands from "#/api/open-hands";
 import { GitRepository } from "#/types/git";
 
 // Create mock functions
@@ -205,7 +204,7 @@ describe("RepositorySelectionForm", () => {
     ];
 
     // Create a spy on the API call
-    const searchGitReposSpy = vi.spyOn(GitService, "searchGitRepositories");
+    const searchGitReposSpy = vi.spyOn(OpenHands, "searchGitRepositories");
     searchGitReposSpy.mockResolvedValue(MOCK_SEARCH_REPOS);
 
     mockUseGitRepositories.mockReturnValue({

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

@@ -5,9 +5,7 @@ import userEvent from "@testing-library/user-event";
 import { Provider } from "react-redux";
 import { createRoutesStub } from "react-router";
 import { setupStore } from "test-utils";
-import ConversationService from "#/api/conversation-service/conversation-service.api";
-import UserService from "#/api/user-service/user-service.api";
-import GitService from "#/api/git-service/git-service.api";
+import OpenHands from "#/api/open-hands";
 import { TaskCard } from "#/components/features/home/tasks/task-card";
 import { GitRepository } from "#/types/git";
 import { SuggestedTask } from "#/utils/types";
@@ -59,10 +57,7 @@ describe("TaskCard", () => {
   });
 
   it("should call createConversation when clicking the launch button", async () => {
-    const createConversationSpy = vi.spyOn(
-      ConversationService,
-      "createConversation",
-    );
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
 
     renderTaskCard();
 
@@ -75,7 +70,7 @@ describe("TaskCard", () => {
   describe("creating suggested task conversation", () => {
     beforeEach(() => {
       const retrieveUserGitRepositoriesSpy = vi.spyOn(
-        GitService,
+        OpenHands,
         "retrieveUserGitRepositories",
       );
       retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -85,10 +80,7 @@ describe("TaskCard", () => {
     });
 
     it("should call create conversation with suggest task trigger and selected suggested task", async () => {
-      const createConversationSpy = vi.spyOn(
-        ConversationService,
-        "createConversation",
-      );
+      const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
 
       renderTaskCard(MOCK_TASK_1);
 
@@ -114,10 +106,7 @@ describe("TaskCard", () => {
   });
 
   it("should navigate to the conversation page after creating a conversation", async () => {
-    const createConversationSpy = vi.spyOn(
-      ConversationService,
-      "createConversation",
-    );
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
     createConversationSpy.mockResolvedValue({
       conversation_id: "test-conversation-id",
       title: "Test Conversation",

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

@@ -7,12 +7,10 @@ import React from "react";
 import { renderWithProviders } from "test-utils";
 import MicroagentManagement from "#/routes/microagent-management";
 import { MicroagentManagementMain } from "#/components/features/microagent-management/microagent-management-main";
-import ConversationService from "#/api/conversation-service/conversation-service.api";
-import GitService from "#/api/git-service/git-service.api";
+import OpenHands from "#/api/open-hands";
 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();
@@ -56,47 +54,25 @@ describe("MicroagentManagement", () => {
   ]);
 
   const renderMicroagentManagement = (config?: QueryClientConfig) =>
-    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,
+    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,
+        },
       },
-      ...additionalState,
     });
-  };
 
   beforeAll(() => {
     vi.mock("react-router", async (importOriginal) => ({
@@ -209,23 +185,6 @@ 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"],
@@ -272,20 +231,20 @@ describe("MicroagentManagement", () => {
     });
 
     // Setup default mock for retrieveUserGitRepositories
-    vi.spyOn(GitService, "retrieveUserGitRepositories").mockResolvedValue({
+    vi.spyOn(OpenHands, "retrieveUserGitRepositories").mockResolvedValue({
       data: [...mockRepositories],
       nextPage: null,
     });
     // Setup default mock for getRepositoryMicroagents
-    vi.spyOn(GitService, "getRepositoryMicroagents").mockResolvedValue([
+    vi.spyOn(OpenHands, "getRepositoryMicroagents").mockResolvedValue([
       ...mockMicroagents,
     ]);
     // Setup default mock for searchConversations
-    vi.spyOn(ConversationService, "searchConversations").mockResolvedValue([
+    vi.spyOn(OpenHands, "searchConversations").mockResolvedValue([
       ...mockConversations,
     ]);
     // Setup default mock for getRepositoryMicroagentContent
-    vi.spyOn(GitService, "getRepositoryMicroagentContent").mockResolvedValue({
+    vi.spyOn(OpenHands, "getRepositoryMicroagentContent").mockResolvedValue({
       content: "Original microagent content for testing updates",
       path: ".openhands/microagents/update-test-microagent",
       git_provider: "github",
@@ -1331,7 +1290,7 @@ describe("MicroagentManagement", () => {
   // Add microagent integration tests
   describe("Add microagent functionality", () => {
     beforeEach(() => {
-      vi.spyOn(GitService, "getRepositoryBranches").mockResolvedValue({
+      vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({
         branches: [{ name: "main", commit_sha: "abc123", protected: false }],
         has_next_page: false,
         current_page: 1,
@@ -1387,10 +1346,33 @@ describe("MicroagentManagement", () => {
       });
     });
 
-    it("should render modal when Zustand state is set to visible", async () => {
-      // Render with modal already visible in Zustand state
-      renderWithCustomStore({
-        addMicroagentModalVisible: true,
+    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,
+          },
+        },
       });
 
       // Check that modal is rendered
@@ -1660,16 +1642,34 @@ describe("MicroagentManagement", () => {
       pr_number: null,
     };
 
-    const renderMicroagentManagementMain = (selectedMicroagentItem: any) => {
-      // Set the store with the selected microagent item and a repository
-      useMicroagentManagementStore.setState({
-        selectedMicroagentItem,
-        selectedRepository: testRepository,
+    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,
+          },
+        },
       });
 
-      return renderWithProviders(<MicroagentManagementMain />);
-    };
-
     it("should render MicroagentManagementDefault when no microagent or conversation is selected", async () => {
       renderMicroagentManagementMain(null);
 
@@ -1983,7 +1983,7 @@ describe("MicroagentManagement", () => {
     };
 
     beforeEach(() => {
-      vi.spyOn(GitService, "getRepositoryBranches").mockResolvedValue({
+      vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({
         branches: [{ name: "main", commit_sha: "abc123", protected: false }],
         has_next_page: false,
         current_page: 1,
@@ -1994,8 +1994,36 @@ describe("MicroagentManagement", () => {
     });
 
     it("should render update microagent modal when updateMicroagentModalVisible is true", async () => {
-      // Render with update modal visible in Zustand state
-      renderWithUpdateModal();
+      // 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,
+          },
+        },
+      });
 
       // Check that update modal is rendered
       expect(screen.getByTestId("add-microagent-modal")).toBeInTheDocument();
@@ -2006,7 +2034,35 @@ describe("MicroagentManagement", () => {
 
     it("should display update microagent title when isUpdate is true", async () => {
       // Render with update modal visible and selected microagent
-      renderWithUpdateModal();
+      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,
+          },
+        },
+      });
 
       // Check that the update title is displayed
       expect(
@@ -2016,10 +2072,33 @@ describe("MicroagentManagement", () => {
 
     it("should populate form fields with existing microagent data when updating", async () => {
       // Render with update modal visible and selected microagent
-      renderWithUpdateModal({
-        selectedMicroagentItem: {
-          microagent: mockMicroagentForUpdate,
-          conversation: null,
+      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,
+          },
         },
       });
 
@@ -2036,7 +2115,35 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Render with update modal visible and selected microagent
-      renderWithUpdateModal();
+      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,
+          },
+        },
+      });
 
       // Wait for modal to be rendered
       await waitFor(() => {
@@ -2064,7 +2171,35 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Render with update modal visible
-      renderWithUpdateModal();
+      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,
+          },
+        },
+      });
 
       // Wait for modal to be rendered
       await waitFor(() => {
@@ -2087,7 +2222,35 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Render with update modal visible
-      renderWithUpdateModal();
+      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,
+          },
+        },
+      });
 
       // Wait for modal to be rendered
       await waitFor(() => {
@@ -2113,7 +2276,32 @@ describe("MicroagentManagement", () => {
 
     it("should handle update modal with empty microagent data", async () => {
       // Render with update modal visible but no microagent data
-      renderWithUpdateModal();
+      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,
+          },
+        },
+      });
 
       // Check that update modal is still rendered
       expect(screen.getByTestId("add-microagent-modal")).toBeInTheDocument();
@@ -2126,7 +2314,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Mock the content API to return empty content for this test
-      vi.spyOn(GitService, "getRepositoryMicroagentContent").mockResolvedValue({
+      vi.spyOn(OpenHands, "getRepositoryMicroagentContent").mockResolvedValue({
         content: "",
         path: ".openhands/microagents/update-test-microagent",
         git_provider: "github",
@@ -2134,7 +2322,35 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with update modal visible and microagent
-      renderWithUpdateModal();
+      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,
+          },
+        },
+      });
 
       // Wait for the content to be loaded and check that the form field is empty
       await waitFor(() => {
@@ -2147,7 +2363,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Mock the content API to return content without triggers for this test
-      vi.spyOn(GitService, "getRepositoryMicroagentContent").mockResolvedValue({
+      vi.spyOn(OpenHands, "getRepositoryMicroagentContent").mockResolvedValue({
         content: "Original microagent content for testing updates",
         path: ".openhands/microagents/update-test-microagent",
         git_provider: "github",
@@ -2155,7 +2371,35 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with update modal visible and microagent
-      renderWithUpdateModal();
+      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,
+          },
+        },
+      });
 
       // Check that the modal is rendered correctly
       expect(screen.getByTestId("add-microagent-modal")).toBeInTheDocument();
@@ -2314,7 +2558,35 @@ describe("MicroagentManagement", () => {
 
     it("should render learn something new button in microagent view", async () => {
       // Render with selected microagent
-      renderWithSelectedMicroagent(mockMicroagentForLearn);
+      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,
+          },
+        },
+      });
 
       // Check that the learn something new button is displayed
       expect(
@@ -2326,7 +2598,35 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Render with selected microagent
-      renderWithSelectedMicroagent(mockMicroagentForLearn);
+      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,
+          },
+        },
+      });
 
       // Find and click the learn something new button
       const learnButton = screen.getByText("COMMON$LEARN_SOMETHING_NEW");
@@ -2347,7 +2647,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Mock the content API to return the expected content for this test
-      vi.spyOn(GitService, "getRepositoryMicroagentContent").mockResolvedValue({
+      vi.spyOn(OpenHands, "getRepositoryMicroagentContent").mockResolvedValue({
         content: "Test microagent content for learn functionality",
         path: ".openhands/microagents/learn-test-microagent",
         git_provider: "github",
@@ -2355,7 +2655,35 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with selected microagent
-      renderWithSelectedMicroagent(mockMicroagentForLearn);
+      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,
+          },
+        },
+      });
 
       // Find and click the learn something new button
       const learnButton = screen.getByText("COMMON$LEARN_SOMETHING_NEW");
@@ -2379,7 +2707,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Mock the content API to return empty content for this test
-      vi.spyOn(GitService, "getRepositoryMicroagentContent").mockResolvedValue({
+      vi.spyOn(OpenHands, "getRepositoryMicroagentContent").mockResolvedValue({
         content: "",
         path: ".openhands/microagents/learn-test-microagent",
         git_provider: "github",
@@ -2387,7 +2715,35 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with selected microagent
-      renderWithSelectedMicroagent(mockMicroagentForLearn);
+      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,
+          },
+        },
+      });
 
       // Find and click the learn something new button
       const learnButton = screen.getByText("COMMON$LEARN_SOMETHING_NEW");
@@ -2409,7 +2765,7 @@ describe("MicroagentManagement", () => {
       const user = userEvent.setup();
 
       // Mock the content API to return content without triggers for this test
-      vi.spyOn(GitService, "getRepositoryMicroagentContent").mockResolvedValue({
+      vi.spyOn(OpenHands, "getRepositoryMicroagentContent").mockResolvedValue({
         content: "Test microagent content for learn functionality",
         path: ".openhands/microagents/learn-test-microagent",
         git_provider: "github",
@@ -2417,7 +2773,35 @@ describe("MicroagentManagement", () => {
       });
 
       // Render with selected microagent
-      renderWithSelectedMicroagent(mockMicroagentForLearn);
+      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,
+          },
+        },
+      });
 
       // Find and click the learn something new button
       const learnButton = screen.getByText("COMMON$LEARN_SOMETHING_NEW");

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

@@ -1,30 +1,23 @@
-import { screen, waitFor } from "@testing-library/react";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
+import { render, screen, waitFor } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, beforeEach, describe, expect, it, test, vi } from "vitest";
-import BillingService from "#/api/billing-service/billing-service.api";
-import OptionService from "#/api/option-service/option-service.api";
+import OpenHands from "#/api/open-hands";
 import { PaymentForm } from "#/components/features/payment/payment-form";
-import { renderWithProviders } from "../../../../test-utils";
-
-// Mock the stripe checkout hook to avoid JSDOM navigation issues
-const mockMutate = vi.fn().mockResolvedValue(undefined);
-vi.mock("#/hooks/mutation/stripe/use-create-stripe-checkout-session", () => ({
-  useCreateStripeCheckoutSession: () => ({
-    mutate: mockMutate,
-    mutateAsync: vi.fn().mockResolvedValue(undefined),
-    isPending: false,
-  }),
-}));
 
 describe("PaymentForm", () => {
-  const getBalanceSpy = vi.spyOn(BillingService, "getBalance");
-  const createCheckoutSessionSpy = vi.spyOn(
-    BillingService,
-    "createCheckoutSession",
-  );
-  const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+  const getBalanceSpy = vi.spyOn(OpenHands, "getBalance");
+  const createCheckoutSessionSpy = vi.spyOn(OpenHands, "createCheckoutSession");
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
 
-  const renderPaymentForm = () => renderWithProviders(<PaymentForm />);
+  const renderPaymentForm = () =>
+    render(<PaymentForm />, {
+      wrapper: ({ children }) => (
+        <QueryClientProvider client={new QueryClient()}>
+          {children}
+        </QueryClientProvider>
+      ),
+    });
 
   beforeEach(() => {
     // useBalance hook will return the balance only if the APP_MODE is "saas" and the billing feature is enabled
@@ -44,7 +37,6 @@ describe("PaymentForm", () => {
 
   afterEach(() => {
     vi.clearAllMocks();
-    mockMutate.mockClear();
   });
 
   it("should render the users current balance", async () => {
@@ -77,7 +69,7 @@ describe("PaymentForm", () => {
     const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
     await user.click(topUpButton);
 
-    expect(mockMutate).toHaveBeenCalledWith({ amount: 50 });
+    expect(createCheckoutSessionSpy).toHaveBeenCalledWith(50);
   });
 
   it("should only accept integer values", async () => {
@@ -90,7 +82,7 @@ describe("PaymentForm", () => {
     const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
     await user.click(topUpButton);
 
-    expect(mockMutate).toHaveBeenCalledWith({ amount: 50 });
+    expect(createCheckoutSessionSpy).toHaveBeenCalledWith(50);
   });
 
   it("should disable the top-up button if the user enters an invalid amount", async () => {
@@ -130,7 +122,7 @@ describe("PaymentForm", () => {
       const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
       await user.click(topUpButton);
 
-      expect(mockMutate).not.toHaveBeenCalled();
+      expect(createCheckoutSessionSpy).not.toHaveBeenCalled();
     });
 
     test("user enters an empty string", async () => {
@@ -143,7 +135,7 @@ describe("PaymentForm", () => {
       const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
       await user.click(topUpButton);
 
-      expect(mockMutate).not.toHaveBeenCalled();
+      expect(createCheckoutSessionSpy).not.toHaveBeenCalled();
     });
 
     test("user enters a non-numeric value", async () => {
@@ -158,7 +150,7 @@ describe("PaymentForm", () => {
       const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
       await user.click(topUpButton);
 
-      expect(mockMutate).not.toHaveBeenCalled();
+      expect(createCheckoutSessionSpy).not.toHaveBeenCalled();
     });
 
     test("user enters less than the minimum amount", async () => {
@@ -171,7 +163,7 @@ describe("PaymentForm", () => {
       const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
       await user.click(topUpButton);
 
-      expect(mockMutate).not.toHaveBeenCalled();
+      expect(createCheckoutSessionSpy).not.toHaveBeenCalled();
     });
 
     test("user enters a decimal value", async () => {
@@ -185,175 +177,7 @@ describe("PaymentForm", () => {
       const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
       await user.click(topUpButton);
 
-      expect(mockMutate).not.toHaveBeenCalled();
-    });
-  });
-
-  describe("Cancel Subscription", () => {
-    const getSubscriptionAccessSpy = vi.spyOn(
-      BillingService,
-      "getSubscriptionAccess",
-    );
-    const cancelSubscriptionSpy = vi.spyOn(
-      BillingService,
-      "cancelSubscription",
-    );
-
-    beforeEach(() => {
-      // Mock active subscription
-      getSubscriptionAccessSpy.mockResolvedValue({
-        start_at: "2024-01-01T00:00:00Z",
-        end_at: "2024-12-31T23:59:59Z",
-        created_at: "2024-01-01T00:00:00Z",
-      });
-    });
-
-    it("should render cancel subscription button when user has active subscription", async () => {
-      renderPaymentForm();
-
-      await waitFor(() => {
-        const cancelButton = screen.getByTestId("cancel-subscription-button");
-        expect(cancelButton).toBeInTheDocument();
-        expect(cancelButton).toHaveTextContent("PAYMENT$CANCEL_SUBSCRIPTION");
-      });
-    });
-
-    it("should not render cancel subscription button when user has no subscription", async () => {
-      getSubscriptionAccessSpy.mockResolvedValue(null);
-      renderPaymentForm();
-
-      await waitFor(() => {
-        const cancelButton = screen.queryByTestId("cancel-subscription-button");
-        expect(cancelButton).not.toBeInTheDocument();
-      });
-    });
-
-    it("should show confirmation modal when cancel subscription button is clicked", async () => {
-      const user = userEvent.setup();
-      renderPaymentForm();
-
-      const cancelButton = await screen.findByTestId(
-        "cancel-subscription-button",
-      );
-      await user.click(cancelButton);
-
-      // Should show confirmation modal
-      expect(
-        screen.getByTestId("cancel-subscription-modal"),
-      ).toBeInTheDocument();
-      expect(
-        screen.getByText("PAYMENT$CANCEL_SUBSCRIPTION_TITLE"),
-      ).toBeInTheDocument();
-      // The message should be rendered (either with Trans component or regular text)
-      const modalContent = screen.getByTestId("cancel-subscription-modal");
-      expect(modalContent).toBeInTheDocument();
-      expect(screen.getByTestId("confirm-cancel-button")).toBeInTheDocument();
-      expect(screen.getByTestId("modal-cancel-button")).toBeInTheDocument();
-    });
-
-    it("should close modal when cancel button in modal is clicked", async () => {
-      const user = userEvent.setup();
-      renderPaymentForm();
-
-      const cancelButton = await screen.findByTestId(
-        "cancel-subscription-button",
-      );
-      await user.click(cancelButton);
-
-      // Modal should be visible
-      expect(
-        screen.getByTestId("cancel-subscription-modal"),
-      ).toBeInTheDocument();
-
-      // Click cancel in modal
-      const modalCancelButton = screen.getByTestId("modal-cancel-button");
-      await user.click(modalCancelButton);
-
-      // Modal should be closed
-      expect(
-        screen.queryByTestId("cancel-subscription-modal"),
-      ).not.toBeInTheDocument();
-    });
-
-    it("should call cancel subscription API when confirm button is clicked", async () => {
-      const user = userEvent.setup();
-      renderPaymentForm();
-
-      const cancelButton = await screen.findByTestId(
-        "cancel-subscription-button",
-      );
-      await user.click(cancelButton);
-
-      // Click confirm in modal
-      const confirmButton = screen.getByTestId("confirm-cancel-button");
-      await user.click(confirmButton);
-
-      // Should call the cancel subscription API
-      expect(cancelSubscriptionSpy).toHaveBeenCalled();
-    });
-
-    it("should close modal after successful cancellation", async () => {
-      const user = userEvent.setup();
-      cancelSubscriptionSpy.mockResolvedValue({
-        status: "success",
-        message: "Subscription cancelled successfully",
-      });
-      renderPaymentForm();
-
-      const cancelButton = await screen.findByTestId(
-        "cancel-subscription-button",
-      );
-      await user.click(cancelButton);
-
-      const confirmButton = screen.getByTestId("confirm-cancel-button");
-      await user.click(confirmButton);
-
-      // Wait for API call to complete and modal to close
-      await waitFor(() => {
-        expect(
-          screen.queryByTestId("cancel-subscription-modal"),
-        ).not.toBeInTheDocument();
-      });
-    });
-
-    it("should show next billing date for active subscription", async () => {
-      // Mock active subscription with end_at as next billing date
-      getSubscriptionAccessSpy.mockResolvedValue({
-        start_at: "2024-01-01T00:00:00Z",
-        end_at: "2025-01-01T00:00:00Z",
-        created_at: "2024-01-01T00:00:00Z",
-        cancelled_at: null,
-        stripe_subscription_id: "sub_123",
-      });
-
-      renderPaymentForm();
-
-      await waitFor(() => {
-        const nextBillingInfo = screen.getByTestId("next-billing-date");
-        expect(nextBillingInfo).toBeInTheDocument();
-        // Check that it contains some date-related content (translation key or actual date)
-        expect(nextBillingInfo).toHaveTextContent(
-          /2025|PAYMENT.*BILLING.*DATE/,
-        );
-      });
-    });
-
-    it("should not show next billing date when subscription is cancelled", async () => {
-      // Mock cancelled subscription
-      getSubscriptionAccessSpy.mockResolvedValue({
-        start_at: "2024-01-01T00:00:00Z",
-        end_at: "2025-01-01T00:00:00Z",
-        created_at: "2024-01-01T00:00:00Z",
-        cancelled_at: "2024-06-15T10:30:00Z",
-        stripe_subscription_id: "sub_123",
-      });
-
-      renderPaymentForm();
-
-      await waitFor(() => {
-        const nextBillingInfo = screen.queryByTestId("next-billing-date");
-        expect(nextBillingInfo).not.toBeInTheDocument();
-      });
+      expect(createCheckoutSessionSpy).not.toHaveBeenCalled();
     });
   });
 });

frontend/__tests__/components/features/sidebar/sidebar.test.tsx

@@ -3,7 +3,7 @@ import { renderWithProviders } from "test-utils";
 import { createRoutesStub } from "react-router";
 import { waitFor } from "@testing-library/react";
 import { Sidebar } from "#/components/features/sidebar/sidebar";
-import SettingsService from "#/settings-service/settings-service.api";
+import OpenHands from "#/api/open-hands";
 
 // These tests will now fail because the conversation panel is rendered through a portal
 // and technically not a child of the Sidebar component.
@@ -19,7 +19,7 @@ const renderSidebar = () =>
   renderWithProviders(<RouterStub initialEntries={["/conversation/123"]} />);
 
 describe("Sidebar", () => {
-  const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+  const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
 
   afterEach(() => {
     vi.clearAllMocks();

frontend/__tests__/components/file-operations.test.tsx

@@ -0,0 +1,11 @@
+import { describe, it } from "vitest";
+
+describe("File Operations Messages", () => {
+  it.todo("should show success indicator for successful file read operation");
+
+  it.todo("should show failure indicator for failed file read operation");
+
+  it.todo("should show success indicator for successful file edit operation");
+
+  it.todo("should show failure indicator for failed file edit operation");
+});

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

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

frontend/__tests__/components/modals/microagents/microagent-modal.test.tsx

@@ -3,7 +3,7 @@ import userEvent from "@testing-library/user-event";
 import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
 import { renderWithProviders } from "test-utils";
 import { MicroagentsModal } from "#/components/features/conversation-panel/microagents-modal";
-import ConversationService from "#/api/conversation-service/conversation-service.api";
+import OpenHands from "#/api/open-hands";
 import { AgentState } from "#/types/agent-state";
 
 vi.mock("react-redux", async () => {
@@ -48,7 +48,7 @@ describe("MicroagentsModal - Refresh Button", () => {
     vi.clearAllMocks();
 
     // Setup default mock for getUserConversations
-    vi.spyOn(ConversationService, "getMicroagents").mockResolvedValue({
+    vi.spyOn(OpenHands, "getMicroagents").mockResolvedValue({
       microagents: mockMicroagents,
     });
   });
@@ -73,7 +73,7 @@ describe("MicroagentsModal - Refresh Button", () => {
 
       renderWithProviders(<MicroagentsModal {...defaultProps} />);
 
-      const refreshSpy = vi.spyOn(ConversationService, "getMicroagents");
+      const refreshSpy = vi.spyOn(OpenHands, "getMicroagents");
 
       const refreshButton = screen.getByTestId("refresh-microagents");
       await user.click(refreshButton);

frontend/__tests__/components/shared/modals/settings/settings-form.test.tsx

@@ -3,13 +3,13 @@ import { describe, expect, it, vi } from "vitest";
 import { renderWithProviders } from "test-utils";
 import { createRoutesStub } from "react-router";
 import { screen } from "@testing-library/react";
-import SettingsService from "#/settings-service/settings-service.api";
+import OpenHands from "#/api/open-hands";
 import { SettingsForm } from "#/components/shared/modals/settings/settings-form";
 import { DEFAULT_SETTINGS } from "#/services/settings";
 
 describe("SettingsForm", () => {
   const onCloseMock = vi.fn();
-  const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+  const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
   const RouteStub = createRoutesStub([
     {

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

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

frontend/__tests__/components/upload-image-input.test.tsx

@@ -0,0 +1,58 @@
+import { render, screen } from "@testing-library/react";
+import userEvent from "@testing-library/user-event";
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { UploadImageInput } from "#/components/features/images/upload-image-input";
+
+describe("UploadImageInput", () => {
+  const user = userEvent.setup();
+  const onUploadMock = vi.fn();
+
+  afterEach(() => {
+    vi.clearAllMocks();
+  });
+
+  it("should render an input", () => {
+    render(<UploadImageInput onUpload={onUploadMock} />);
+    expect(screen.getByTestId("upload-image-input")).toBeInTheDocument();
+  });
+
+  it("should call onUpload when a file is selected", async () => {
+    render(<UploadImageInput onUpload={onUploadMock} />);
+
+    const file = new File(["(⌐□_□)"], "chucknorris.png", { type: "image/png" });
+    const input = screen.getByTestId("upload-image-input");
+
+    await user.upload(input, file);
+
+    expect(onUploadMock).toHaveBeenNthCalledWith(1, [file]);
+  });
+
+  it("should call onUpload when multiple files are selected", async () => {
+    render(<UploadImageInput onUpload={onUploadMock} />);
+
+    const files = [
+      new File(["(⌐□_□)"], "chucknorris.png", { type: "image/png" }),
+      new File(["(⌐□_□)"], "chucknorris2.png", { type: "image/png" }),
+    ];
+    const input = screen.getByTestId("upload-image-input");
+
+    await user.upload(input, files);
+
+    expect(onUploadMock).toHaveBeenNthCalledWith(1, files);
+  });
+
+  it("should render custom labels", () => {
+    const { rerender } = render(<UploadImageInput onUpload={onUploadMock} />);
+    expect(screen.getByTestId("default-label")).toBeInTheDocument();
+
+    function CustomLabel() {
+      return <span>Custom label</span>;
+    }
+    rerender(
+      <UploadImageInput onUpload={onUploadMock} label={<CustomLabel />} />,
+    );
+
+    expect(screen.getByText("Custom label")).toBeInTheDocument();
+    expect(screen.queryByTestId("default-label")).not.toBeInTheDocument();
+  });
+});

frontend/__tests__/hooks/mutation/use-save-settings.test.tsx

@@ -1,12 +1,12 @@
 import { renderHook, waitFor } from "@testing-library/react";
 import { describe, expect, it, vi } from "vitest";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
-import SettingsService from "#/settings-service/settings-service.api";
+import OpenHands from "#/api/open-hands";
 import { useSaveSettings } from "#/hooks/mutation/use-save-settings";
 
 describe("useSaveSettings", () => {
   it("should send an empty string for llm_api_key if an empty string is passed, otherwise undefined", async () => {
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
     const { result } = renderHook(() => useSaveSettings(), {
       wrapper: ({ children }) => (
         <QueryClientProvider client={new QueryClient()}>

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

frontend/__tests__/initial-query.test.tsx

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

frontend/__tests__/routes/_oh.test.tsx

@@ -8,9 +8,8 @@ import {
 import userEvent from "@testing-library/user-event";
 import MainApp from "#/routes/root-layout";
 import i18n from "#/i18n";
-import OptionService from "#/api/option-service/option-service.api";
 import * as CaptureConsent from "#/utils/handle-capture-consent";
-import SettingsService from "#/settings-service/settings-service.api";
+import OpenHands from "#/api/open-hands";
 import * as ToastHandlers from "#/utils/custom-toast-handlers";
 
 describe("frontend/routes/_oh", () => {
@@ -63,8 +62,8 @@ describe("frontend/routes/_oh", () => {
   // FIXME: This test fails when it shouldn't be, please investigate
   it.skip("should render and capture the user's consent if oss mode", async () => {
     const user = userEvent.setup();
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     const handleCaptureConsentSpy = vi.spyOn(
       CaptureConsent,
       "handleCaptureConsent",
@@ -107,7 +106,7 @@ describe("frontend/routes/_oh", () => {
   });
 
   it("should not render the user consent form if saas mode", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue({
       APP_MODE: "saas",
       GITHUB_CLIENT_ID: "test-id",
@@ -185,8 +184,8 @@ describe("frontend/routes/_oh", () => {
   });
 
   it("should render a you're in toast if it is a new user and in saas mode", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     const displaySuccessToastSpy = vi.spyOn(
       ToastHandlers,
       "displaySuccessToast",

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

@@ -3,7 +3,7 @@ import { afterEach, describe, expect, it, vi } from "vitest";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import userEvent from "@testing-library/user-event";
 import AppSettingsScreen from "#/routes/app-settings";
-import SettingsService from "#/settings-service/settings-service.api";
+import OpenHands from "#/api/open-hands";
 import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
 import { AvailableLanguages } from "#/i18n";
 import * as CaptureConsent from "#/utils/handle-capture-consent";
@@ -25,7 +25,7 @@ describe("Content", () => {
   });
 
   it("should render the correct default values", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       language: "no",
@@ -65,8 +65,8 @@ describe("Form submission", () => {
   });
 
   it("should submit the form with the correct values", async () => {
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
 
     renderAppSettingsScreen();
@@ -106,7 +106,7 @@ describe("Form submission", () => {
   });
 
   it("should only enable the submit button when there are changes", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
 
     renderAppSettingsScreen();
@@ -146,7 +146,7 @@ describe("Form submission", () => {
   });
 
   it("should call handleCaptureConsents with true when the analytics switch is toggled", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
 
     const handleCaptureConsentsSpy = vi.spyOn(
@@ -168,7 +168,7 @@ describe("Form submission", () => {
   });
 
   it("should call handleCaptureConsents with false when the analytics switch is toggled", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       user_consents_to_analytics: true,
@@ -215,8 +215,8 @@ describe("Form submission", () => {
   });
 
   it("should disable the button after submitting changes", async () => {
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
 
     renderAppSettingsScreen();
@@ -240,8 +240,8 @@ describe("Form submission", () => {
 
 describe("Status toasts", () => {
   it("should call displaySuccessToast when the settings are saved", async () => {
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
 
     const displaySuccessToastSpy = vi.spyOn(
@@ -265,8 +265,8 @@ describe("Status toasts", () => {
   });
 
   it("should call displayErrorToast when the settings fail to save", async () => {
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
 
     const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");

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

@@ -6,11 +6,9 @@ import userEvent from "@testing-library/user-event";
 import i18next from "i18next";
 import { I18nextProvider } from "react-i18next";
 import GitSettingsScreen from "#/routes/git-settings";
-import SettingsService from "#/settings-service/settings-service.api";
-import OptionService from "#/api/option-service/option-service.api";
-import AuthService from "#/api/auth-service/auth-service.api";
+import OpenHands from "#/api/open-hands";
 import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
-import { GetConfigResponse } from "#/api/option-service/option.types";
+import { GetConfigResponse } from "#/api/open-hands.types";
 import * as ToastHandlers from "#/utils/custom-toast-handlers";
 import { SecretsService } from "#/api/secrets-service";
 
@@ -110,7 +108,7 @@ describe("Content", () => {
   });
 
   it("should render the inputs if OSS mode", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
 
     const { rerender } = renderGitSettingsScreen();
@@ -153,8 +151,8 @@ describe("Content", () => {
   });
 
   it("should set '<hidden>' placeholder and indicator if the GitHub token is set", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
 
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
     getSettingsSpy.mockResolvedValue({
@@ -228,7 +226,7 @@ describe("Content", () => {
   });
 
   it("should render the 'Configure GitHub Repositories' button if SaaS mode and app slug exists", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
 
     const { rerender } = renderGitSettingsScreen();
@@ -272,7 +270,7 @@ describe("Form submission", () => {
   it("should save the GitHub token", async () => {
     const saveProvidersSpy = vi.spyOn(SecretsService, "addGitProvider");
     saveProvidersSpy.mockImplementation(() => Promise.resolve(true));
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
 
     renderGitSettingsScreen();
@@ -293,7 +291,7 @@ describe("Form submission", () => {
   it("should save GitLab tokens", async () => {
     const saveProvidersSpy = vi.spyOn(SecretsService, "addGitProvider");
     saveProvidersSpy.mockImplementation(() => Promise.resolve(true));
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
 
     renderGitSettingsScreen();
@@ -314,7 +312,7 @@ describe("Form submission", () => {
   it("should save the Bitbucket token", async () => {
     const saveProvidersSpy = vi.spyOn(SecretsService, "addGitProvider");
     saveProvidersSpy.mockImplementation(() => Promise.resolve(true));
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
 
     renderGitSettingsScreen();
@@ -333,7 +331,7 @@ describe("Form submission", () => {
   });
 
   it("should disable the button if there is no input", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
 
     renderGitSettingsScreen();
@@ -359,8 +357,8 @@ describe("Form submission", () => {
   });
 
   it("should enable a disconnect tokens button if there is at least one token set", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
 
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
     getSettingsSpy.mockResolvedValue({
@@ -393,9 +391,9 @@ describe("Form submission", () => {
   });
 
   it("should call logout when pressing the disconnect tokens button", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-    const logoutSpy = vi.spyOn(AuthService, "logout");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    const logoutSpy = vi.spyOn(OpenHands, "logout");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
 
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
     getSettingsSpy.mockResolvedValue({
@@ -420,7 +418,7 @@ describe("Form submission", () => {
   // flaky test
   it.skip("should disable the button when submitting changes", async () => {
     const saveSettingsSpy = vi.spyOn(SecretsService, "addGitProvider");
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
 
     renderGitSettingsScreen();
@@ -444,7 +442,7 @@ describe("Form submission", () => {
 
   it("should disable the button after submitting changes", async () => {
     const saveProvidersSpy = vi.spyOn(SecretsService, "addGitProvider");
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
 
     renderGitSettingsScreen();
@@ -478,7 +476,7 @@ describe("Form submission", () => {
 describe("Status toasts", () => {
   it("should call displaySuccessToast when the settings are saved", async () => {
     const saveProvidersSpy = vi.spyOn(SecretsService, "addGitProvider");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
 
     const displaySuccessToastSpy = vi.spyOn(
@@ -501,7 +499,7 @@ describe("Status toasts", () => {
 
   it("should call displayErrorToast when the settings fail to save", async () => {
     const saveProvidersSpy = vi.spyOn(SecretsService, "addGitProvider");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
 
     const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");

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

@@ -7,9 +7,7 @@ import { Provider } from "react-redux";
 import { createAxiosNotFoundErrorObject, setupStore } from "test-utils";
 import HomeScreen from "#/routes/home";
 import { GitRepository } from "#/types/git";
-import SettingsService from "#/settings-service/settings-service.api";
-import GitService from "#/api/git-service/git-service.api";
-import OptionService from "#/api/option-service/option-service.api";
+import OpenHands from "#/api/open-hands";
 import MainApp from "#/routes/root-layout";
 import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
 
@@ -93,7 +91,7 @@ const MOCK_RESPOSITORIES: GitRepository[] = [
 
 describe("HomeScreen", () => {
   beforeEach(() => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       provider_tokens_set: {
@@ -141,7 +139,7 @@ describe("HomeScreen", () => {
 
   it("should filter the suggested tasks based on the selected repository", async () => {
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -150,7 +148,7 @@ describe("HomeScreen", () => {
     });
 
     // Mock the repository branches API call
-    vi.spyOn(GitService, "getRepositoryBranches").mockResolvedValue({
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({
       branches: [
         { name: "main", commit_sha: "123", protected: false },
         { name: "develop", commit_sha: "456", protected: false },
@@ -185,7 +183,7 @@ describe("HomeScreen", () => {
 
   it("should filter tasks when different repositories are selected", async () => {
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
-      GitService,
+      OpenHands,
       "retrieveUserGitRepositories",
     );
     retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -194,7 +192,7 @@ describe("HomeScreen", () => {
     });
 
     // Mock the repository branches API call
-    vi.spyOn(GitService, "getRepositoryBranches").mockResolvedValue({
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({
       branches: [
         { name: "main", commit_sha: "123", protected: false },
         { name: "develop", commit_sha: "456", protected: false },
@@ -248,7 +246,7 @@ describe("HomeScreen", () => {
         await screen.findAllByTestId("task-launch-button");
 
       // Mock the repository branches API call
-      vi.spyOn(GitService, "getRepositoryBranches").mockResolvedValue({
+      vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({
         branches: [
           { name: "main", commit_sha: "123", protected: false },
           { name: "develop", commit_sha: "456", protected: false },
@@ -284,7 +282,7 @@ describe("HomeScreen", () => {
 
     beforeEach(() => {
       const retrieveUserGitRepositoriesSpy = vi.spyOn(
-        GitService,
+        OpenHands,
         "retrieveUserGitRepositories",
       );
       retrieveUserGitRepositoriesSpy.mockResolvedValue({
@@ -360,8 +358,8 @@ describe("Settings 404", () => {
     vi.resetAllMocks();
   });
 
-  const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-  const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+  const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
 
   it("should open the settings modal if GET /settings fails with a 404", async () => {
     const error = createAxiosNotFoundErrorObject();
@@ -419,8 +417,8 @@ describe("Settings 404", () => {
 });
 
 describe("Setup Payment modal", () => {
-  const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-  const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+  const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
 
   it("should only render if SaaS mode and is new user", async () => {
     // @ts-expect-error - we only need the APP_MODE for this test

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

@@ -3,27 +3,13 @@ import userEvent from "@testing-library/user-event";
 import { beforeEach, describe, expect, it, vi } from "vitest";
 import { QueryClientProvider, QueryClient } from "@tanstack/react-query";
 import LlmSettingsScreen from "#/routes/llm-settings";
-import SettingsService from "#/settings-service/settings-service.api";
-import OptionService from "#/api/option-service/option-service.api";
+import OpenHands from "#/api/open-hands";
 import {
   MOCK_DEFAULT_USER_SETTINGS,
   resetTestHandlersMockSettings,
 } from "#/mocks/handlers";
 import * as AdvancedSettingsUtlls from "#/utils/has-advanced-settings-set";
 import * as ToastHandlers from "#/utils/custom-toast-handlers";
-import BillingService from "#/api/billing-service/billing-service.api";
-
-// Mock react-router hooks
-const mockUseSearchParams = vi.fn();
-vi.mock("react-router", () => ({
-  useSearchParams: () => mockUseSearchParams(),
-}));
-
-// Mock useIsAuthed hook
-const mockUseIsAuthed = vi.fn();
-vi.mock("#/hooks/query/use-is-authed", () => ({
-  useIsAuthed: () => mockUseIsAuthed(),
-}));
 
 const renderLlmSettingsScreen = () =>
   render(<LlmSettingsScreen />, {
@@ -37,17 +23,6 @@ const renderLlmSettingsScreen = () =>
 beforeEach(() => {
   vi.resetAllMocks();
   resetTestHandlersMockSettings();
-
-  // Default mock for useSearchParams - returns empty params
-  mockUseSearchParams.mockReturnValue([
-    {
-      get: () => null,
-    },
-    vi.fn(),
-  ]);
-
-  // Default mock for useIsAuthed - returns authenticated by default
-  mockUseIsAuthed.mockReturnValue({ data: true, isLoading: false });
 });
 
 describe("Content", () => {
@@ -81,7 +56,7 @@ describe("Content", () => {
     });
 
     it("should render the existing settings values", async () => {
-      const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+      const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
       getSettingsSpy.mockResolvedValue({
         ...MOCK_DEFAULT_USER_SETTINGS,
         llm_model: "openai/gpt-4o",
@@ -109,9 +84,7 @@ describe("Content", () => {
       renderLlmSettingsScreen();
       await screen.findByTestId("llm-settings-screen");
 
-      const confirmation = screen.getByTestId(
-        "enable-confirmation-mode-switch",
-      );
+      const confirmation = screen.getByTestId("enable-confirmation-mode-switch");
 
       // Initially confirmation mode is false, so security analyzer should not be visible
       expect(confirmation).not.toBeChecked();
@@ -212,7 +185,7 @@ describe("Content", () => {
     });
 
     it("should render existing advanced settings correctly", async () => {
-      const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+      const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
       getSettingsSpy.mockResolvedValue({
         ...MOCK_DEFAULT_USER_SETTINGS,
         llm_model: "openai/gpt-4o",
@@ -257,7 +230,7 @@ describe("Content", () => {
 
 describe("Form submission", () => {
   it("should submit the basic form with the correct values", async () => {
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
     renderLlmSettingsScreen();
     await screen.findByTestId("llm-settings-screen");
@@ -293,7 +266,7 @@ describe("Form submission", () => {
   });
 
   it("should submit the advanced form with the correct values", async () => {
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
     renderLlmSettingsScreen();
     await screen.findByTestId("llm-settings-screen");
@@ -337,9 +310,7 @@ describe("Form submission", () => {
     // select security analyzer
     const securityAnalyzer = screen.getByTestId("security-analyzer-input");
     await userEvent.click(securityAnalyzer);
-    const securityAnalyzerOption = screen.getByText(
-      "SETTINGS$SECURITY_ANALYZER_NONE",
-    );
+    const securityAnalyzerOption = screen.getByText("SETTINGS$SECURITY_ANALYZER_NONE");
     await userEvent.click(securityAnalyzerOption);
 
     const submitButton = screen.getByTestId("submit-button");
@@ -358,7 +329,7 @@ describe("Form submission", () => {
   });
 
   it("should disable the button if there are no changes in the basic form", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       llm_model: "openai/gpt-4o",
@@ -401,7 +372,7 @@ describe("Form submission", () => {
   });
 
   it("should disable the button if there are no changes in the advanced form", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       llm_model: "openai/gpt-4o",
@@ -421,14 +392,10 @@ describe("Form submission", () => {
     const baseUrl = await screen.findByTestId("base-url-input");
     const apiKey = await screen.findByTestId("llm-api-key-input");
     const agent = await screen.findByTestId("agent-input");
-    const condensor = await screen.findByTestId(
-      "enable-memory-condenser-switch",
-    );
+    const condensor = await screen.findByTestId("enable-memory-condenser-switch");
 
     // Confirmation mode switch is now in basic settings, always visible
-    const confirmation = await screen.findByTestId(
-      "enable-confirmation-mode-switch",
-    );
+    const confirmation = await screen.findByTestId("enable-confirmation-mode-switch");
 
     // enter custom model
     await userEvent.type(model, "-mini");
@@ -501,13 +468,9 @@ describe("Form submission", () => {
     expect(submitButton).toBeDisabled();
 
     // select security analyzer
-    const securityAnalyzer = await screen.findByTestId(
-      "security-analyzer-input",
-    );
+    const securityAnalyzer = await screen.findByTestId("security-analyzer-input");
     await userEvent.click(securityAnalyzer);
-    const securityAnalyzerOption = screen.getByText(
-      "SETTINGS$SECURITY_ANALYZER_NONE",
-    );
+    const securityAnalyzerOption = screen.getByText("SETTINGS$SECURITY_ANALYZER_NONE");
     await userEvent.click(securityAnalyzerOption);
     expect(securityAnalyzer).toHaveValue("SETTINGS$SECURITY_ANALYZER_NONE");
 
@@ -515,13 +478,9 @@ describe("Form submission", () => {
 
     // revert back to original value
     await userEvent.click(securityAnalyzer);
-    const originalSecurityAnalyzerOption = screen.getByText(
-      "SETTINGS$SECURITY_ANALYZER_LLM_DEFAULT",
-    );
+    const originalSecurityAnalyzerOption = screen.getByText("SETTINGS$SECURITY_ANALYZER_LLM_DEFAULT");
     await userEvent.click(originalSecurityAnalyzerOption);
-    expect(securityAnalyzer).toHaveValue(
-      "SETTINGS$SECURITY_ANALYZER_LLM_DEFAULT",
-    );
+    expect(securityAnalyzer).toHaveValue("SETTINGS$SECURITY_ANALYZER_LLM_DEFAULT");
     expect(submitButton).toBeDisabled();
   });
 
@@ -553,7 +512,7 @@ describe("Form submission", () => {
 
   // flaky test
   it.skip("should disable the button when submitting changes", async () => {
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
     renderLlmSettingsScreen();
     await screen.findByTestId("llm-settings-screen");
@@ -580,7 +539,7 @@ describe("Form submission", () => {
   });
 
   it("should clear advanced settings when saving basic settings", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     getSettingsSpy.mockResolvedValue({
       ...MOCK_DEFAULT_USER_SETTINGS,
       llm_model: "openai/gpt-4o",
@@ -588,7 +547,7 @@ describe("Form submission", () => {
       llm_api_key_set: true,
       confirmation_mode: true,
     });
-    const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
     renderLlmSettingsScreen();
 
     await screen.findByTestId("llm-settings-screen");
@@ -624,7 +583,7 @@ describe("Form submission", () => {
 describe("Status toasts", () => {
   describe("Basic form", () => {
     it("should call displaySuccessToast when the settings are saved", async () => {
-      const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
       const displaySuccessToastSpy = vi.spyOn(
         ToastHandlers,
@@ -645,7 +604,7 @@ describe("Status toasts", () => {
     });
 
     it("should call displayErrorToast when the settings fail to save", async () => {
-      const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
       const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
 
@@ -667,7 +626,7 @@ describe("Status toasts", () => {
 
   describe("Advanced form", () => {
     it("should call displaySuccessToast when the settings are saved", async () => {
-      const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
       const displaySuccessToastSpy = vi.spyOn(
         ToastHandlers,
@@ -693,7 +652,7 @@ describe("Status toasts", () => {
     });
 
     it("should call displayErrorToast when the settings fail to save", async () => {
-      const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
+      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
 
       const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
 
@@ -720,401 +679,58 @@ describe("Status toasts", () => {
 });
 
 describe("SaaS mode", () => {
-  describe("SaaS subscription", () => {
-    // Common mock configurations
-    const MOCK_SAAS_CONFIG = {
-      APP_MODE: "saas" as const,
-      GITHUB_CLIENT_ID: "fake-github-client-id",
-      POSTHOG_CLIENT_KEY: "fake-posthog-client-key",
-      FEATURE_FLAGS: {
-        ENABLE_BILLING: true,
-        HIDE_LLM_SETTINGS: false,
-        ENABLE_JIRA: false,
-        ENABLE_JIRA_DC: false,
-        ENABLE_LINEAR: false,
-      },
-    };
-
-    const MOCK_ACTIVE_SUBSCRIPTION = {
-      start_at: "2024-01-01",
-      end_at: "2024-12-31",
-      created_at: "2024-01-01",
-    };
-
-    it("should show upgrade banner and prevent all interactions for unsubscribed SaaS users", async () => {
-      // Mock SaaS mode without subscription
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
-
-      // Mock subscription access to return null (no subscription)
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(null);
-
-      // Mock saveSettings to ensure it's not called
-      const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Should show upgrade banner
-      expect(screen.getByTestId("upgrade-banner")).toBeInTheDocument();
-
-      // Should have a clickable upgrade button
-      const upgradeButton = screen.getByRole("button", { name: /upgrade/i });
-      expect(upgradeButton).toBeInTheDocument();
-      expect(upgradeButton).not.toBeDisabled();
-
-      // Form should be disabled
-      const form = screen.getByTestId("llm-settings-form-basic");
-      expect(form).toHaveAttribute("aria-disabled", "true");
-
-      // All form inputs should be disabled or non-interactive
-      const providerInput = screen.getByTestId("llm-provider-input");
-      const modelInput = screen.getByTestId("llm-model-input");
-      const apiKeyInput = screen.getByTestId("llm-api-key-input");
-      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-      const confirmationModeSwitch = screen.getByTestId(
-        "enable-confirmation-mode-switch",
-      );
-      const submitButton = screen.getByTestId("submit-button");
-
-      // Inputs should be disabled
-      expect(providerInput).toBeDisabled();
-      expect(modelInput).toBeDisabled();
-      expect(apiKeyInput).toBeDisabled();
-      expect(advancedSwitch).toBeDisabled();
-      expect(confirmationModeSwitch).toBeDisabled();
-      expect(submitButton).toBeDisabled();
-
-      // Try to interact with inputs - they should not respond
-      await userEvent.click(providerInput);
-      await userEvent.type(apiKeyInput, "test-key");
-
-      // Values should not change
-      expect(apiKeyInput).toHaveValue("");
-
-      // Try to submit form - should not call API
-      await userEvent.click(submitButton);
-      expect(saveSettingsSpy).not.toHaveBeenCalled();
+  it("should not render the runtime settings input in oss mode", async () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    // @ts-expect-error - only return mode
+    getConfigSpy.mockResolvedValue({
+      APP_MODE: "oss",
     });
 
-    it("should call subscription checkout API when upgrade button is clicked", async () => {
-      // Mock SaaS mode without subscription
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
 
-      // Mock subscription access to return null (no subscription)
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(null);
+    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+    await userEvent.click(advancedSwitch);
+    await screen.findByTestId("llm-settings-form-advanced");
 
-      // Mock the subscription checkout API call
-      const createSubscriptionCheckoutSessionSpy = vi.spyOn(
-        BillingService,
-        "createSubscriptionCheckoutSession",
-      );
-      createSubscriptionCheckoutSessionSpy.mockResolvedValue({});
+    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
+    expect(runtimeSettingsInput).not.toBeInTheDocument();
+  });
 
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Click the upgrade button
-      const upgradeButton = screen.getByRole("button", { name: /upgrade/i });
-      await userEvent.click(upgradeButton);
-
-      // Should call the subscription checkout API
-      expect(createSubscriptionCheckoutSessionSpy).toHaveBeenCalled();
+  it("should render the runtime settings input in saas mode", async () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    // @ts-expect-error - only return mode
+    getConfigSpy.mockResolvedValue({
+      APP_MODE: "saas",
     });
 
-    it("should disable upgrade button for unauthenticated users in SaaS mode", async () => {
-      // Mock SaaS mode without subscription
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
 
-      // Mock subscription access to return null (no subscription)
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(null);
+    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+    await userEvent.click(advancedSwitch);
+    await screen.findByTestId("llm-settings-form-advanced");
 
-      // Mock subscription checkout API
-      const createSubscriptionCheckoutSessionSpy = vi.spyOn(
-        BillingService,
-        "createSubscriptionCheckoutSession",
-      );
+    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
+    expect(runtimeSettingsInput).toBeInTheDocument();
+  });
 
-      // Mock authentication to return false (unauthenticated) from the start
-      mockUseIsAuthed.mockReturnValue({ data: false, isLoading: false });
-
-      // Mock settings to return default settings even when unauthenticated
-      // This is necessary because the useSettings hook is disabled when user is not authenticated
-      const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
-      getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-      renderLlmSettingsScreen();
-
-      // Wait for either the settings screen or skeleton to appear
-      await waitFor(() => {
-        const settingsScreen = screen.queryByTestId("llm-settings-screen");
-        const skeleton = screen.queryByTestId("app-settings-skeleton");
-        expect(settingsScreen || skeleton).toBeInTheDocument();
-      });
-
-      // If we get the skeleton, the test scenario isn't valid - skip the rest
-      if (screen.queryByTestId("app-settings-skeleton")) {
-        // For unauthenticated users, the settings don't load, so no upgrade banner is shown
-        // This is the expected behavior - unauthenticated users see a skeleton loading state
-        expect(screen.queryByTestId("upgrade-banner")).not.toBeInTheDocument();
-        return;
-      }
-
-      await screen.findByTestId("llm-settings-screen");
-
-      // Should show upgrade banner
-      expect(screen.getByTestId("upgrade-banner")).toBeInTheDocument();
-
-      // Upgrade button should be disabled for unauthenticated users
-      const upgradeButton = screen.getByRole("button", { name: /upgrade/i });
-      expect(upgradeButton).toBeInTheDocument();
-      expect(upgradeButton).toBeDisabled();
-
-      // Clicking disabled button should not call the API
-      await userEvent.click(upgradeButton);
-      expect(createSubscriptionCheckoutSessionSpy).not.toHaveBeenCalled();
+  it("should always render the runtime settings input as disabled", async () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    // @ts-expect-error - only return mode
+    getConfigSpy.mockResolvedValue({
+      APP_MODE: "saas",
     });
 
-    it("should not show upgrade banner and allow form interaction for subscribed SaaS users", async () => {
-      // Mock SaaS mode with subscription
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
 
-      // Mock subscription access to return active subscription
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(MOCK_ACTIVE_SUBSCRIPTION);
+    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+    await userEvent.click(advancedSwitch);
+    await screen.findByTestId("llm-settings-form-advanced");
 
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Wait for subscription data to load
-      await waitFor(() => {
-        expect(getSubscriptionAccessSpy).toHaveBeenCalled();
-      });
-
-      // Should NOT show upgrade banner
-      expect(screen.queryByTestId("upgrade-banner")).not.toBeInTheDocument();
-
-      // Form should NOT be disabled
-      const form = screen.getByTestId("llm-settings-form-basic");
-      expect(form).not.toHaveAttribute("aria-disabled", "true");
-    });
-
-    it("should not call save settings API when making changes in disabled form for unsubscribed users", async () => {
-      // Mock SaaS mode without subscription
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
-
-      // Mock subscription access to return null (no subscription)
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(null);
-
-      // Mock saveSettings to track calls
-      const saveSettingsSpy = vi.spyOn(SettingsService, "saveSettings");
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Verify that form elements are disabled for unsubscribed users
-      const confirmationModeSwitch = screen.getByTestId(
-        "enable-confirmation-mode-switch",
-      );
-      const submitButton = screen.getByTestId("submit-button");
-
-      expect(confirmationModeSwitch).not.toBeChecked();
-      expect(confirmationModeSwitch).toBeDisabled();
-      expect(submitButton).toBeDisabled();
-
-      // Try to click the disabled confirmation mode switch - it should not change state
-      await userEvent.click(confirmationModeSwitch);
-      expect(confirmationModeSwitch).not.toBeChecked(); // Should remain unchecked
-
-      // Try to submit the form - button should remain disabled
-      await userEvent.click(submitButton);
-
-      // Should NOT call save settings API for unsubscribed users
-      expect(saveSettingsSpy).not.toHaveBeenCalled();
-    });
-
-    it("should show backdrop overlay for unsubscribed users", async () => {
-      // Mock SaaS mode without subscription
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
-
-      // Mock subscription access to return null (no subscription)
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(null);
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Wait for subscription data to load
-      await waitFor(() => {
-        expect(getSubscriptionAccessSpy).toHaveBeenCalled();
-      });
-
-      // Should show upgrade banner
-      expect(screen.getByTestId("upgrade-banner")).toBeInTheDocument();
-
-      // Should show backdrop overlay
-      const backdrop = screen.getByTestId("settings-backdrop");
-      expect(backdrop).toBeInTheDocument();
-    });
-
-    it("should not show backdrop overlay for subscribed users", async () => {
-      // Mock SaaS mode with subscription
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
-
-      // Mock subscription access to return active subscription
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(MOCK_ACTIVE_SUBSCRIPTION);
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Wait for subscription data to load
-      await waitFor(() => {
-        expect(getSubscriptionAccessSpy).toHaveBeenCalled();
-      });
-
-      // Should NOT show backdrop overlay
-      expect(screen.queryByTestId("settings-backdrop")).not.toBeInTheDocument();
-    });
-
-    it("should display success toast when redirected back with ?checkout=success parameter", async () => {
-      // Mock SaaS mode
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
-
-      // Mock subscription access
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(MOCK_ACTIVE_SUBSCRIPTION);
-
-      // Mock toast handler
-      const displaySuccessToastSpy = vi.spyOn(
-        ToastHandlers,
-        "displaySuccessToast",
-      );
-
-      // Mock URL search params with ?checkout=success
-      mockUseSearchParams.mockReturnValue([
-        {
-          get: (param: string) => (param === "checkout" ? "success" : null),
-        },
-        vi.fn(),
-      ]);
-
-      // Render component with checkout=success parameter
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Verify success toast is displayed with correct message
-      expect(displaySuccessToastSpy).toHaveBeenCalledWith(
-        "SUBSCRIPTION$SUCCESS",
-      );
-    });
-
-    it("should display error toast when redirected back with ?checkout=cancel parameter", async () => {
-      // Mock SaaS mode
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
-
-      // Mock subscription access
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(MOCK_ACTIVE_SUBSCRIPTION);
-
-      // Mock toast handler
-      const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
-
-      // Mock URL search params with ?checkout=cancel
-      mockUseSearchParams.mockReturnValue([
-        {
-          get: (param: string) => (param === "checkout" ? "cancel" : null),
-        },
-        vi.fn(),
-      ]);
-
-      // Render component with checkout=cancel parameter
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Verify error toast is displayed with correct message
-      expect(displayErrorToastSpy).toHaveBeenCalledWith("SUBSCRIPTION$FAILURE");
-    });
-
-    it("should show upgrade banner when subscription is expired or disabled", async () => {
-      // Mock SaaS mode
-      const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-      getConfigSpy.mockResolvedValue(MOCK_SAAS_CONFIG);
-
-      // Mock subscription access to return null (expired/disabled subscriptions return null from backend)
-      // The backend only returns active subscriptions within their validity period
-      const getSubscriptionAccessSpy = vi.spyOn(
-        BillingService,
-        "getSubscriptionAccess",
-      );
-      getSubscriptionAccessSpy.mockResolvedValue(null);
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      // Wait for subscription data to load
-      await waitFor(() => {
-        expect(getSubscriptionAccessSpy).toHaveBeenCalled();
-      });
-
-      // Should show upgrade banner for expired/disabled subscriptions (when API returns null)
-      expect(screen.getByTestId("upgrade-banner")).toBeInTheDocument();
-
-      // Form should be disabled
-      const form = screen.getByTestId("llm-settings-form-basic");
-      expect(form).toHaveAttribute("aria-disabled", "true");
-
-      // All form inputs should be disabled
-      const providerInput = screen.getByTestId("llm-provider-input");
-      const modelInput = screen.getByTestId("llm-model-input");
-      const apiKeyInput = screen.getByTestId("llm-api-key-input");
-      const confirmationModeSwitch = screen.getByTestId(
-        "enable-confirmation-mode-switch",
-      );
-
-      expect(providerInput).toBeDisabled();
-      expect(modelInput).toBeDisabled();
-      expect(apiKeyInput).toBeDisabled();
-      expect(confirmationModeSwitch).toBeDisabled();
-    });
+    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
+    expect(runtimeSettingsInput).toBeInTheDocument();
+    expect(runtimeSettingsInput).toBeDisabled();
   });
 });

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

@@ -6,8 +6,7 @@ import { createRoutesStub, Outlet } from "react-router";
 import SecretsSettingsScreen from "#/routes/secrets-settings";
 import { SecretsService } from "#/api/secrets-service";
 import { GetSecretsResponse } from "#/api/secrets-service.types";
-import SettingsService from "#/settings-service/settings-service.api";
-import OptionService from "#/api/option-service/option-service.api";
+import OpenHands from "#/api/open-hands";
 import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
 
 const MOCK_GET_SECRETS_RESPONSE: GetSecretsResponse["custom_secrets"] = [
@@ -54,7 +53,7 @@ const renderSecretsSettings = () =>
   });
 
 beforeEach(() => {
-  const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
   // @ts-expect-error - only return the config we need
   getConfigSpy.mockResolvedValue({
     APP_MODE: "oss",
@@ -68,8 +67,8 @@ describe("Content", () => {
   });
 
   it("should NOT render a button to connect with git if they havent already in oss", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
     const getSecretsSpy = vi.spyOn(SecretsService, "getSecrets");
     // @ts-expect-error - only return the config we need
     getConfigSpy.mockResolvedValue({
@@ -88,7 +87,7 @@ describe("Content", () => {
   });
 
   it("should render add secret button in saas mode", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     const getSecretsSpy = vi.spyOn(SecretsService, "getSecrets");
     // @ts-expect-error - only return the config we need
     getConfigSpy.mockResolvedValue({
@@ -477,9 +476,7 @@ describe("Secret actions", () => {
 
     // make POST request
     expect(createSecretSpy).not.toHaveBeenCalled();
-    expect(
-      screen.queryByText("SECRETS$SECRET_ALREADY_EXISTS"),
-    ).toBeInTheDocument();
+    expect(screen.queryByText("SECRETS$SECRET_ALREADY_EXISTS")).toBeInTheDocument();
 
     await userEvent.clear(nameInput);
     await userEvent.type(nameInput, "My_Custom_Secret");
@@ -563,9 +560,7 @@ describe("Secret actions", () => {
 
     // make POST request
     expect(createSecretSpy).not.toHaveBeenCalled();
-    expect(
-      screen.queryByText("SECRETS$SECRET_ALREADY_EXISTS"),
-    ).toBeInTheDocument();
+    expect(screen.queryByText("SECRETS$SECRET_ALREADY_EXISTS")).toBeInTheDocument();
 
     expect(nameInput).toHaveValue(MOCK_GET_SECRETS_RESPONSE[0].name);
     expect(valueInput).toHaveValue("my-custom-secret-value");

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

@@ -3,14 +3,14 @@ import userEvent from "@testing-library/user-event";
 import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
 import { createRoutesStub } from "react-router";
 import { renderWithProviders } from "test-utils";
+import OpenHands from "#/api/open-hands";
 import SettingsScreen from "#/routes/settings";
 import { PaymentForm } from "#/components/features/payment/payment-form";
+import * as useSettingsModule from "#/hooks/query/use-settings";
 
 // Mock the useSettings hook
 vi.mock("#/hooks/query/use-settings", async () => {
-  const actual = await vi.importActual<
-    typeof import("#/hooks/query/use-settings")
-  >("#/hooks/query/use-settings");
+  const actual = await vi.importActual<typeof import("#/hooks/query/use-settings")>("#/hooks/query/use-settings");
   return {
     ...actual,
     useSettings: vi.fn().mockReturnValue({
@@ -24,23 +24,21 @@ vi.mock("#/hooks/query/use-settings", async () => {
 
 // Mock the i18next hook
 vi.mock("react-i18next", async () => {
-  const actual =
-    await vi.importActual<typeof import("react-i18next")>("react-i18next");
+  const actual = await vi.importActual<typeof import("react-i18next")>("react-i18next");
   return {
     ...actual,
     useTranslation: () => ({
       t: (key: string) => {
         const translations: Record<string, string> = {
-          SETTINGS$NAV_INTEGRATIONS: "Integrations",
-          SETTINGS$NAV_APPLICATION: "Application",
-          SETTINGS$NAV_CREDITS: "Credits",
-          SETTINGS$NAV_BILLING: "Billing",
-          SETTINGS$NAV_API_KEYS: "API Keys",
-          SETTINGS$NAV_LLM: "LLM",
-          SETTINGS$NAV_USER: "User",
-          SETTINGS$NAV_SECRETS: "Secrets",
-          SETTINGS$NAV_MCP: "MCP",
-          SETTINGS$TITLE: "Settings",
+          "SETTINGS$NAV_INTEGRATIONS": "Integrations",
+          "SETTINGS$NAV_APPLICATION": "Application",
+          "SETTINGS$NAV_CREDITS": "Credits",
+          "SETTINGS$NAV_API_KEYS": "API Keys",
+          "SETTINGS$NAV_LLM": "LLM",
+          "SETTINGS$NAV_USER": "User",
+          "SETTINGS$NAV_SECRETS": "Secrets",
+          "SETTINGS$NAV_MCP": "MCP",
+          "SETTINGS$TITLE": "Settings"
         };
         return translations[key] || key;
       },
@@ -107,16 +105,16 @@ describe("Settings Billing", () => {
     vi.clearAllMocks();
   });
 
-  it("should not render the billing tab if OSS mode", async () => {
+  it("should not render the credits tab if OSS mode", async () => {
     // OSS mode is set by default in beforeEach
     renderSettingsScreen();
 
     const navbar = await screen.findByTestId("settings-navbar");
-    const credits = within(navbar).queryByText("Billing");
+    const credits = within(navbar).queryByText("Credits");
     expect(credits).not.toBeInTheDocument();
   });
 
-  it("should render the billing tab if SaaS mode and billing is enabled", async () => {
+  it("should render the credits tab if SaaS mode and billing is enabled", async () => {
     mockUseConfig.mockReturnValue({
       data: {
         APP_MODE: "saas",
@@ -136,10 +134,10 @@ describe("Settings Billing", () => {
     renderSettingsScreen();
 
     const navbar = await screen.findByTestId("settings-navbar");
-    within(navbar).getByText("Billing");
+    within(navbar).getByText("Credits");
   });
 
-  it("should render the billing settings if clicking the billing item", async () => {
+  it("should render the billing settings if clicking the credits item", async () => {
     const user = userEvent.setup();
     mockUseConfig.mockReturnValue({
       data: {
@@ -160,7 +158,7 @@ describe("Settings Billing", () => {
     renderSettingsScreen();
 
     const navbar = await screen.findByTestId("settings-navbar");
-    const credits = within(navbar).getByText("Billing");
+    const credits = within(navbar).getByText("Credits");
     await user.click(credits);
 
     const billingSection = await screen.findByTestId("billing-settings");

frontend/__tests__/routes/settings.test.tsx

@@ -3,7 +3,7 @@ import { createRoutesStub } from "react-router";
 import { describe, expect, it, vi } from "vitest";
 import { QueryClientProvider } from "@tanstack/react-query";
 import SettingsScreen, { clientLoader } from "#/routes/settings";
-import OptionService from "#/api/option-service/option-service.api";
+import OpenHands from "#/api/open-hands";
 
 // Mock the i18next hook
 vi.mock("react-i18next", async () => {
@@ -93,7 +93,7 @@ describe("Settings Screen", () => {
   it("should render the navbar", async () => {
     const sectionsToInclude = ["llm", "integrations", "application", "secrets"];
     const sectionsToExclude = ["api keys", "credits", "billing"];
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     // @ts-expect-error - only return app mode
     getConfigSpy.mockResolvedValue({
       APP_MODE: "oss",
@@ -129,15 +129,14 @@ describe("Settings Screen", () => {
     mockQueryClient.setQueryData(["config"], saasConfig);
 
     const sectionsToInclude = [
-      "llm", // LLM settings are now always shown in SaaS mode
       "user",
       "integrations",
       "application",
-      "billing", // The nav item shows "billing" text and routes to /billing
+      "credits", // The nav item shows "credits" text but routes to /billing
       "secrets",
       "api keys",
     ];
-    const sectionsToExclude: string[] = []; // No sections are excluded in SaaS mode now
+    const sectionsToExclude = ["llm"];
 
     renderSettingsScreen();
 
@@ -157,7 +156,7 @@ describe("Settings Screen", () => {
   });
 
   it("should not be able to access saas-only routes in oss mode", async () => {
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     // @ts-expect-error - only return app mode
     getConfigSpy.mockResolvedValue({
       APP_MODE: "oss",

frontend/__tests__/services/actions.test.tsx

@@ -13,26 +13,14 @@ vi.mock("#/store", () => ({
   },
 }));
 
-vi.mock("#/state/command-store", () => ({
-  useCommandStore: {
-    getState: () => ({
-      appendInput: mockAppendInput,
-    }),
-  },
+vi.mock("#/state/command-slice", () => ({
+  appendInput: mockAppendInput,
 }));
 
 vi.mock("#/state/jupyter-slice", () => ({
   appendJupyterInput: mockAppendJupyterInput,
 }));
 
-vi.mock("#/state/metrics-slice", () => ({
-  setMetrics: vi.fn(),
-}));
-
-vi.mock("#/state/security-analyzer-slice", () => ({
-  appendSecurityAnalyzerInput: vi.fn(),
-}));
-
 describe("handleActionMessage", () => {
   beforeEach(() => {
     // Clear all mocks before each test
@@ -57,8 +45,7 @@ describe("handleActionMessage", () => {
     handleActionMessage(runAction);
 
     // Check that appendInput was called with the command
-    expect(mockAppendInput).toHaveBeenCalledWith("ls -la");
-    expect(mockDispatch).not.toHaveBeenCalled();
+    expect(mockDispatch).toHaveBeenCalledWith(mockAppendInput("ls -la"));
     expect(mockAppendJupyterInput).not.toHaveBeenCalled();
   });
 
@@ -72,8 +59,7 @@ 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",
     };
 
@@ -81,9 +67,7 @@ describe("handleActionMessage", () => {
     handleActionMessage(ipythonAction);
 
     // Check that appendJupyterInput was called with the code
-    expect(mockDispatch).toHaveBeenCalledWith(
-      mockAppendJupyterInput("print('Hello from Jupyter!')"),
-    );
+    expect(mockDispatch).toHaveBeenCalledWith(mockAppendJupyterInput("print('Hello from Jupyter!')"));
     expect(mockAppendInput).not.toHaveBeenCalled();
   });
 
@@ -105,9 +89,7 @@ describe("handleActionMessage", () => {
     // Handle the action
     handleActionMessage(hiddenAction);
 
-    // Check that nothing was dispatched or called
+    // Check that nothing was dispatched
     expect(mockDispatch).not.toHaveBeenCalled();
-    expect(mockAppendInput).not.toHaveBeenCalled();
-    expect(mockAppendJupyterInput).not.toHaveBeenCalled();
   });
 });

frontend/__tests__/utils/browser-tab.test.ts

@@ -0,0 +1,51 @@
+import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
+
+import { browserTab } from "#/utils/browser-tab";
+
+// These tests exercise the browser-tab notification flasher behavior.
+// Specifically we verify that when the document title changes externally
+// while a notification is active, the flasher updates its internal
+// baseline so it restores/toggles to the new title instead of an old one.
+
+describe("browserTab notifications", () => {
+  const MESSAGE = "Agent ready";
+  const INITIAL = "Conversation 123 | OpenHands";
+  const RENAMED = "My renamed title | OpenHands";
+
+  beforeEach(() => {
+    vi.useFakeTimers();
+    // reset title for each test
+    document.title = INITIAL;
+  });
+
+  afterEach(() => {
+    browserTab.stopNotification();
+    vi.runOnlyPendingTimers();
+    vi.useRealTimers();
+  });
+
+  it("updates baseline when title changes during an active notification and restores to the new title", () => {
+    // Start flashing
+    browserTab.startNotification(MESSAGE);
+
+    // Tick once: should switch to the message
+    vi.advanceTimersByTime(1000);
+    expect(document.title).toBe(MESSAGE);
+
+    // Simulate an external rename while flashing (e.g., user edits title)
+    document.title = RENAMED;
+
+    // Next tick: flasher observes the external change and updates baseline
+    vi.advanceTimersByTime(1000);
+    // On this tick, we toggle back to the message
+    expect(document.title).toBe(MESSAGE);
+
+    // Next tick should toggle to the updated baseline (renamed title)
+    vi.advanceTimersByTime(1000);
+    expect(document.title).toBe(RENAMED);
+
+    // Stop flashing: title should remain the updated baseline
+    browserTab.stopNotification();
+    expect(document.title).toBe(RENAMED);
+  });
+});

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

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

frontend/__tests__/utils/format-ms.test.ts

@@ -0,0 +1,9 @@
+import { test, expect } from "vitest";
+import { formatMs } from "../../src/utils/format-ms";
+
+test("formatMs", () => {
+  expect(formatMs(1000)).toBe("00:01");
+  expect(formatMs(1000 * 60)).toBe("01:00");
+  expect(formatMs(1000 * 60 * 2.5)).toBe("02:30");
+  expect(formatMs(1000 * 60 * 12)).toBe("12:00");
+});

frontend/__tests__/utils/i18n-test-utils.tsx

@@ -0,0 +1,29 @@
+import { ReactNode } from "react";
+import { I18nextProvider } from "react-i18next";
+
+const mockI18n = {
+  language: "ja",
+  t: (key: string) => {
+    const translations: Record<string, string> = {
+      "SUGGESTIONS$TODO_APP": "ToDoリストアプリを開発する",
+      "LANDING$BUILD_APP_BUTTON": "プルリクエストを表示するアプリを開発する",
+      "SUGGESTIONS$HACKER_NEWS": "Hacker Newsのトップ記事を表示するbashスクリプトを作成する",
+      "LANDING$TITLE": "一緒に開発を始めましょう！",
+      "OPEN_IN_VSCODE": "VS Codeで開く",
+      "INCREASE_TEST_COVERAGE": "テストカバレッジを向上",
+      "AUTO_MERGE_PRS": "PRを自動マージ",
+      "FIX_README": "READMEを修正",
+      "CLEAN_DEPENDENCIES": "依存関係を整理"
+    };
+    return translations[key] || key;
+  },
+  exists: () => true,
+  changeLanguage: () => new Promise(() => {}),
+  use: () => mockI18n,
+};
+
+export function I18nTestProvider({ children }: { children: ReactNode }) {
+  return (
+    <I18nextProvider i18n={mockI18n as any}>{children}</I18nextProvider>
+  );
+}

frontend/__tests__/utils/parse-github-url.test.ts

@@ -0,0 +1,20 @@
+import { expect, test } from "vitest";
+import { parseGithubUrl } from "../../src/utils/parse-github-url";
+
+test("parseGithubUrl", () => {
+  expect(
+    parseGithubUrl("https://github.com/alexreardon/tiny-invariant"),
+  ).toEqual(["alexreardon", "tiny-invariant"]);
+
+  expect(parseGithubUrl("https://github.com/All-Hands-AI/OpenHands")).toEqual([
+    "All-Hands-AI",
+    "OpenHands",
+  ]);
+
+  expect(parseGithubUrl("https://github.com/All-Hands-AI/")).toEqual([
+    "All-Hands-AI",
+    "",
+  ]);
+
+  expect(parseGithubUrl("https://github.com/")).toEqual([]);
+});

frontend/package.json

@@ -1,44 +1,44 @@
 {
   "name": "openhands-frontend",
-  "version": "0.57.0",
+  "version": "0.56.0",
   "private": true,
   "type": "module",
   "engines": {
     "node": ">=22.0.0"
   },
   "dependencies": {
-    "@heroui/react": "^2.8.4",
+    "@heroui/react": "^2.8.3",
     "@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": "^7.9.1",
-    "@react-router/serve": "^7.9.1",
+    "@react-router/node": "^7.8.2",
+    "@react-router/serve": "^7.8.2",
     "@react-types/shared": "^3.32.0",
     "@reduxjs/toolkit": "^2.9.0",
-    "@stripe/react-stripe-js": "^4.0.2",
+    "@stripe/react-stripe-js": "^4.0.0",
     "@stripe/stripe-js": "^7.9.0",
     "@tailwindcss/postcss": "^4.1.13",
     "@tailwindcss/vite": "^4.1.13",
-    "@tanstack/react-query": "^5.90.2",
+    "@tanstack/react-query": "^5.87.0",
     "@uidotdev/usehooks": "^2.4.1",
-    "@vitejs/plugin-react": "^5.0.3",
+    "@vitejs/plugin-react": "^5.0.2",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
-    "axios": "^1.12.2",
+    "axios": "^1.11.0",
     "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": "^12.23.19",
+    "framer-motion": "^12.23.12",
     "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": "^0.544.0",
-    "monaco-editor": "^0.53.0",
-    "posthog-js": "^1.268.1",
+    "lucide-react": "^0.542.0",
+    "monaco-editor": "^0.52.2",
+    "posthog-js": "^1.261.7",
     "react": "^19.1.1",
     "react-dom": "^19.1.1",
     "react-highlight": "^0.15.0",
@@ -47,7 +47,8 @@
     "react-icons": "^5.5.0",
     "react-markdown": "^10.1.0",
     "react-redux": "^9.2.0",
-    "react-router": "^7.9.1",
+    "react-resizable-panels": "^3.0.5",
+    "react-router": "^7.8.2",
     "react-syntax-highlighter": "^15.6.6",
     "remark-breaks": "^4.0.0",
     "remark-gfm": "^4.0.1",
@@ -55,10 +56,9 @@
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^3.3.1",
     "tailwind-scrollbar": "^4.0.2",
-    "vite": "^7.1.7",
+    "vite": "^7.1.4",
     "web-vitals": "^5.1.0",
-    "ws": "^8.18.2",
-    "zustand": "^5.0.8"
+    "ws": "^8.18.2"
   },
   "scripts": {
     "dev": "npm run make-i18n && cross-env VITE_MOCK_API=false react-router dev",
@@ -77,19 +77,12 @@
     "lint:fix": "eslint src --ext .ts,.tsx,.js --fix && prettier --write src/**/*.{ts,tsx}",
     "prepare": "cd .. && husky frontend/.husky",
     "typecheck": "react-router typegen && tsc",
-    "typecheck:staged": "react-router typegen && npx tsc --noEmit --skipLibCheck",
     "check-translation-completeness": "node scripts/check-translation-completeness.cjs"
   },
   "lint-staged": {
     "src/**/*.{ts,tsx,js}": [
       "eslint --fix",
       "prettier --write"
-    ],
-    "src/**/*.{ts,tsx}": [
-      "bash -c 'npm run typecheck:staged'"
-    ],
-    "src/**/*": [
-      "npm run check-translation-completeness"
     ]
   },
   "devDependencies": {
@@ -97,16 +90,16 @@
     "@babel/traverse": "^7.28.3",
     "@babel/types": "^7.28.2",
     "@mswjs/socket.io-binding": "^0.2.0",
-    "@playwright/test": "^1.55.1",
-    "@react-router/dev": "^7.9.1",
-    "@tailwindcss/typography": "^0.5.18",
-    "@tanstack/eslint-plugin-query": "^5.90.1",
+    "@playwright/test": "^1.55.0",
+    "@react-router/dev": "^7.8.2",
+    "@tailwindcss/typography": "^0.5.16",
+    "@tanstack/eslint-plugin-query": "^5.86.0",
     "@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": "^24.5.2",
-    "@types/react": "^19.1.13",
+    "@types/node": "^24.3.1",
+    "@types/react": "^19.1.12",
     "@types/react-dom": "^19.1.9",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
@@ -128,8 +121,8 @@
     "eslint-plugin-react-hooks": "^4.6.2",
     "eslint-plugin-unused-imports": "^4.2.0",
     "husky": "^9.1.7",
-    "jsdom": "^27.0.0",
-    "lint-staged": "^16.2.0",
+    "jsdom": "^26.1.0",
+    "lint-staged": "^16.1.6",
     "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 = '2.11.1'
+const PACKAGE_VERSION = '2.10.5'
 const INTEGRITY_CHECKSUM = 'f5825c521429caf22a4dd13b66e243af'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()