add section for gitlab in docs

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

.github/workflows/dummy-agent-test.yml

@@ -1,53 +0,0 @@
-# Workflow that uses the DummyAgent to run a simple task
-name: Run E2E test with dummy agent
-
-# Always run on "main"
-# Always run on PRs
-on:
-  push:
-    branches:
-    - main
-  pull_request:
-
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  test:
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Install tmux
-        run: sudo apt-get update && sudo apt-get install -y tmux
-      - name: Setup Node.js
-        uses: useblacksmith/setup-node@v5
-        with:
-          node-version: '22.x'
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Set up Python
-        uses: useblacksmith/setup-python@v6
-        with:
-          python-version: '3.12'
-          cache: 'poetry'
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation
-      - name: Build Environment
-        run: make build
-      - name: Run tests
-        run: |
-          set -e
-          SANDBOX_FORCE_REBUILD_RUNTIME=True poetry run python3 openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
-      - name: Check exit code
-        run: |
-          if [ $? -ne 0 ]; then
-            echo "Test failed"
-            exit 1
-          else
-            echo "Test passed"
-          fi

.github/workflows/openhands-resolver.yml

@@ -24,7 +24,7 @@ on:
       LLM_MODEL:
         required: false
         type: string
-        default: "anthropic/claude-3-5-sonnet-20241022"
+        default: "anthropic/claude-3-7-sonnet-20250219"
       LLM_API_VERSION:
         required: false
         type: string
@@ -179,7 +179,7 @@ jobs:
 
           echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
           echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.PAT_TOKEN || github.token }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
+          echo "SANDBOX_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
 
           # Set branch variables
           echo "TARGET_BRANCH=${{ inputs.target_branch || 'main' }}" >> $GITHUB_ENV

.openhands/microagents/repo.md

@@ -54,3 +54,20 @@ Frontend:
 ## Template for Github Pull Request
 
 If you are starting a pull request (PR), please follow the template in `.github/pull_request_template.md`.
+
+## Implementation Details
+
+These details may or may not be useful for your current task.
+
+### Frontend
+
+#### Action Handling:
+- Actions are defined in `frontend/src/types/action-type.ts`
+- The `HANDLED_ACTIONS` array in `frontend/src/state/chat-slice.ts` determines which actions are displayed as collapsible UI elements
+- To add a new action type to the UI:
+  1. Add the action type to the `HANDLED_ACTIONS` array
+  2. Implement the action handling in `addAssistantAction` function in chat-slice.ts
+  3. Add a translation key in the format `ACTION_MESSAGE$ACTION_NAME` to the i18n files
+- Actions with `thought` property are displayed in the UI based on their action type:
+  - Regular actions (like "run", "edit") display the thought as a separate message
+  - Special actions (like "think") are displayed as collapsible elements only

Development.md

@@ -118,7 +118,7 @@ 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:0.32-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.34-nikolaik`
 
 ## Develop inside Docker container
 

Makefile

@@ -39,6 +39,7 @@ ifeq ($(INSTALL_DOCKER),)
 	@$(MAKE) -s check-docker
 endif
 	@$(MAKE) -s check-poetry
+	@$(MAKE) -s check-tmux
 	@echo "$(GREEN)Dependencies checked successfully.$(RESET)"
 
 check-system:
@@ -101,6 +102,18 @@ check-docker:
 		exit 1; \
 	fi
 
+check-tmux:
+	@echo "$(YELLOW)Checking tmux installation...$(RESET)"
+	@if command -v tmux > /dev/null; then \
+		echo "$(BLUE)$(shell tmux -V) is already installed.$(RESET)"; \
+	else \
+		echo "$(YELLOW)╔════════════════════════════════════════════════════════════════════════════╗$(RESET)"; \
+		echo "$(YELLOW)║ OPTIONAL: tmux is not installed.                                          ║$(RESET)"; \
+		echo "$(YELLOW)║ Some advanced terminal features may not work without tmux.                ║$(RESET)"; \
+		echo "$(YELLOW)║ You can install it if needed, but it's not required for development.      ║$(RESET)"; \
+		echo "$(YELLOW)╚════════════════════════════════════════════════════════════════════════════╝$(RESET)"; \
+	fi
+
 check-poetry:
 	@echo "$(YELLOW)Checking Poetry installation...$(RESET)"
 	@if command -v poetry > /dev/null; then \
@@ -175,7 +188,7 @@ install-pre-commit-hooks:
 
 lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files openhands/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
 
 lint-frontend:
 	@echo "$(YELLOW)Running linters for frontend...$(RESET)"

README.md

@@ -18,7 +18,7 @@
   <br/>
   <a href="https://docs.all-hands.dev/modules/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
   <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
-  <a href="https://huggingface.co/spaces/OpenHands/evaluation"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
+  <a href="https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=0#gid=0"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
   <hr>
 </div>
 
@@ -52,17 +52,17 @@ system requirements and more information.
 
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32
+    docker.all-hands.dev/all-hands-ai/openhands:0.34
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

config.template.toml

@@ -221,9 +221,22 @@ enable_browsing = true
 # Whether the LLM draft editor is enabled
 enable_llm_editor = false
 
+# Whether the standard editor tool (str_replace_editor) is enabled
+# Only has an effect if enable_llm_editor is False
+enable_editor = true
+
 # Whether the IPython tool is enabled
 enable_jupyter = true
 
+# Whether the command tool is enabled
+enable_cmd = true
+
+# Whether the think tool is enabled
+enable_think = true
+
+# Whether the finish tool is enabled
+enable_finish = true
+
 # LLM config group to use
 #llm_config = 'your-llm-config-group'
 

containers/dev/Dockerfile

@@ -61,8 +61,8 @@ RUN add-apt-repository ppa:deadsnakes/ppa \
     && apt-get install -y python3.12 python3.12-venv python3.12-dev python3-pip \
     && ln -s /usr/bin/python3.12 /usr/bin/python
 
-# NodeJS >= 18.17.1
-RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash - \
+# NodeJS >= 22.x
+RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
     && apt-get install -y nodejs
 
 # Poetry >= 1.8
@@ -108,7 +108,7 @@ WORKDIR /app
 
 # cache build dependencies
 RUN \
-  --mount=type=bind,source=./,target=/app/ \
+  --mount=type=bind,source=./,target=/app/,rw \
   <<EOF
 #!/bin/bash
 make -s clean

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.32-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.34-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik}
       #- SANDBOX_USER_ID=${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-state for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/.gitignore

@@ -3,6 +3,7 @@
 
 # Production
 /build
+/static/swagger-ui
 
 # Generated files
 .docusaurus

docs/docusaurus.config.ts

@@ -36,6 +36,7 @@ const config: Config = {
     mermaid: true,
   },
   themes: ['@docusaurus/theme-mermaid'],
+  plugins: [],
   presets: [
     [
       'classic',
@@ -75,6 +76,11 @@ const config: Config = {
           position: 'left',
           label: 'User Guides',
         },
+        {
+          href: 'https://docs.all-hands.dev/swagger-ui/', // FIXME: this should be a relative path, but docusarus steals the click
+          label: 'API',
+          position: 'left',
+        },
         {
           type: 'localeDropdown',
           position: 'left',

docs/generate-swagger-ui.js

@@ -0,0 +1,102 @@
+const fs = require('fs');
+const path = require('path');
+const swaggerUiDist = require('swagger-ui-dist');
+
+/**
+ * This script manually sets up Swagger UI for the Docusaurus documentation.
+ *
+ * Why we need this approach:
+ * 1. Docusaurus doesn't have a built-in way to integrate Swagger UI
+ * 2. We need to copy the necessary files from swagger-ui-dist to our static directory
+ * 3. We need to create a custom index.html file that points to our OpenAPI spec
+ * 4. This approach allows us to customize the Swagger UI to match our documentation style
+ */
+
+// Get the absolute path to the swagger-ui-dist package
+const swaggerUiDistPath = swaggerUiDist.getAbsoluteFSPath();
+
+// Create the target directory if it doesn't exist
+const targetDir = path.join(__dirname, 'static', 'swagger-ui');
+if (!fs.existsSync(targetDir)) {
+  fs.mkdirSync(targetDir, { recursive: true });
+}
+
+// Copy all files from swagger-ui-dist to our target directory
+const files = fs.readdirSync(swaggerUiDistPath);
+files.forEach(file => {
+  const sourcePath = path.join(swaggerUiDistPath, file);
+  const targetPath = path.join(targetDir, file);
+
+  // Skip directories and non-essential files
+  if (fs.statSync(sourcePath).isDirectory() ||
+      file === 'package.json' ||
+      file === 'README.md' ||
+      file.endsWith('.map')) {
+    return;
+  }
+
+  fs.copyFileSync(sourcePath, targetPath);
+});
+
+// Create a custom index.html file that points to our OpenAPI spec
+const indexHtml = `
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <title>OpenHands API Documentation</title>
+  <link rel="stylesheet" type="text/css" href="./swagger-ui.css" />
+  <link rel="icon" type="image/png" href="./favicon-32x32.png" sizes="32x32" />
+  <link rel="icon" type="image/png" href="./favicon-16x16.png" sizes="16x16" />
+  <style>
+    html {
+      box-sizing: border-box;
+      overflow: -moz-scrollbars-vertical;
+      overflow-y: scroll;
+    }
+
+    *,
+    *:before,
+    *:after {
+      box-sizing: inherit;
+    }
+
+    body {
+      margin: 0;
+      background: #fafafa;
+    }
+  </style>
+</head>
+
+<body>
+  <div id="swagger-ui"></div>
+
+  <script src="./swagger-ui-bundle.js" charset="UTF-8"> </script>
+  <script src="./swagger-ui-standalone-preset.js" charset="UTF-8"> </script>
+  <script>
+    window.onload = function() {
+      // Begin Swagger UI call region
+      const ui = SwaggerUIBundle({
+        url: "/openapi.json",
+        dom_id: '#swagger-ui',
+        deepLinking: true,
+        presets: [
+          SwaggerUIBundle.presets.apis,
+          SwaggerUIStandalonePreset
+        ],
+        plugins: [
+          SwaggerUIBundle.plugins.DownloadUrl
+        ],
+        layout: "StandaloneLayout"
+      });
+      // End Swagger UI call region
+      window.ui = ui;
+    };
+  </script>
+</body>
+</html>
+`;
+
+fs.writeFileSync(path.join(targetDir, 'index.html'), indexHtml);
+
+console.log('Swagger UI files generated successfully in static/swagger-ui/');

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.cli
 ```
 

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32
+    docker.all-hands.dev/all-hands-ai/openhands:0.34
 ```
 
 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -34,7 +34,7 @@ Docker で OpenHands を CLI モードで実行するには:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -44,7 +44,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.cli
 ```
 

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -31,7 +31,7 @@ DockerでOpenHandsをヘッドレスモードで実行するには:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -42,7 +42,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/runtimes/docker.md

@@ -25,7 +25,7 @@ nikolaik の `SANDBOX_RUNTIME_CONTAINER_IMAGE` は、ランタイムサーバー
 
     ```bash
     docker run # ...
-        -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+        -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
         -e SANDBOX_USER_ID=$(id -u) \
         -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
         -v $WORKSPACE_BASE:/opt/workspace_base \
@@ -82,5 +82,5 @@ docker network create openhands-network
 # 分離されたネットワークで OpenHands を実行
 docker run # ... \
     --network openhands-network \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32
+    docker.all-hands.dev/all-hands-ai/openhands:0.34
 ```

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -35,7 +35,7 @@ Para executar o OpenHands no modo CLI com Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.cli
 ```
 

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -32,7 +32,7 @@ Para executar o OpenHands no modo Headless com Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.main -t "escreva um script bash que imprima oi"
 ```
 

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -58,17 +58,17 @@
 A maneira mais fácil de executar o OpenHands é no Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32
+    docker.all-hands.dev/all-hands-ai/openhands:0.34
 ```
 
 Você encontrará o OpenHands em execução em http://localhost:3000!

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/prompting/microagents-public.md

@@ -4,7 +4,7 @@
 
 Microagentes públicos são diretrizes especializadas acionadas por palavras-chave para todos os usuários do OpenHands.
 Eles são definidos em arquivos markdown no diretório
-[`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge).
+[`microagents/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge).
 
 Microagentes públicos:
 - Monitoram comandos recebidos em busca de suas palavras-chave de acionamento.
@@ -15,7 +15,7 @@ Microagentes públicos:
 ## Microagentes Públicos Atuais
 
 Para mais informações sobre microagentes específicos, consulte seus arquivos de documentação individuais no
-diretório [`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge/).
+diretório [`microagents/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/).
 
 ### Agente GitHub
 **Arquivo**: `github.md`
@@ -59,7 +59,7 @@ yes | npm install package-name
 ## Contribuindo com um Microagente Público
 
 Você pode criar seus próprios microagentes públicos adicionando novos arquivos markdown ao
-diretório [`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge/).
+diretório [`microagents/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/).
 
 ### Melhores Práticas para Microagentes Públicos
 
@@ -81,7 +81,7 @@ Antes de criar um microagente público, considere:
 
 #### 2. Crie o Arquivo
 
-Crie um novo arquivo markdown em [`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge/)
+Crie um novo arquivo markdown em [`microagents/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/)
 com um nome descritivo (por exemplo, `docker.md` para um agente focado em Docker).
 
 Atualize o arquivo com o frontmatter necessário [de acordo com o formato exigido](./microagents-overview#microagent-format)

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -13,7 +13,7 @@ Este é o Runtime padrão que é usado quando você inicia o OpenHands. Você po
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.cli
 ```
 

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32
+    docker.all-hands.dev/all-hands-ai/openhands:0.34
 ```
 
 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/modules/usage/cloud/openhands-cloud.mdx

@@ -8,18 +8,22 @@ OpenHands Cloud can be accessed at https://app.all-hands.dev/.
 
 ## Getting Started
 
-After visiting OpenHands Cloud, you will be asked to connect with your GitHub account:
-1. After reading and accepting the terms of service, click `Connect to GitHub`.
+After visiting OpenHands Cloud, you will be asked to connect with your GitHub or GitLab account:
+
+1. After reading and accepting the terms of service, click `Log in with GitHub` or `Log in with GitLab`.
 2. Review the permissions requested by OpenHands and then click `Authorize OpenHands AI`.
-   - OpenHands will require some permissions from your GitHub account. To read more about these permissions,
-     you can click the `Learn more` link on the GitHub authorize page.
+   - OpenHands will require some permissions from your GitHub or GitLab account. To read more about these permissions:
+     - GitHub: You can click the `Learn more` link on the GitHub authorize page.
+     - GitLab: You can expand each permission request on the GitLab authorize page.
 
 ## Repository Access
 
-### Adding Repository Access
+### GitHub
+
+#### Adding Repository Access
 
 You can grant OpenHands specific repository access:
-1. Click the `Select a GitHub project` dropdown, select `Add more repositories...`.
+1. Click `Add GitHub repos` on the Home page.
 2. Select the organization, then choose the specific repositories to grant OpenHands access to.
    <details>
      <summary>Permission Details for Repository Access</summary>
@@ -42,11 +46,15 @@ You can grant OpenHands specific repository access:
 
 3. Click on `Install & Authorize`.
 
-### Modifying Repository Access
+#### Modifying Repository Access
 
-You can modify repository access at any time by:
-* Using the same `Select a GitHub project > Add more repositories` workflow, or
-* Visiting the Settings page and selecting `Configure GitHub Repositories` under the `GitHub Settings` section.
+You can modify GitHub repository access at any time by:
+* Using the same `Add GitHub repos` workflow, or
+* Visiting the Settings page and selecting `Configure GitHub Repositories` under the `Git Settings` section.
+
+### GitLab
+
+When using your GitLab account, OpenHands will automatically have access to your repositories.
 
 ## Conversation Persistence
 

docs/modules/usage/customization/repository.md

@@ -1,18 +1,17 @@
 # Repository Customization
 
-You can customize how OpenHands works with your repository by creating a
+You can customize how OpenHands interacts with your repository by creating a
 `.openhands` directory at the root level.
 
 ## Microagents
-You can use microagents to extend the OpenHands prompts with information
-about your project and how you want OpenHands to work. See
-[Repository Microagents](../prompting/microagents-repo) for more information.
+
+Microagents allow you to extend OpenHands prompts with information specific to your project and define how OpenHands
+should function. See [Microagents Overview](../prompting/microagents-overview) for more information.
 
 
 ## Setup Script
-You can add `.openhands/setup.sh`, which will be run every time OpenHands begins
-working with your repository. This is a good place to install dependencies, set
-environment variables, etc.
+You can add a `.openhands/setup.sh` file, which will run every time OpenHands begins working with your repository.
+This is an ideal location for installing dependencies, setting environment variables, and performing other setup tasks.
 
 For example:
 ```bash

docs/modules/usage/how-to/cli-mode.md

@@ -35,7 +35,7 @@ To run OpenHands in CLI mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.cli
 ```
 

docs/modules/usage/how-to/custom-sandbox-guide.md

@@ -1,7 +1,8 @@
 # Custom Sandbox
 
 :::note
-This guide is for users that would like to use their own custom Docker image for the runtime, e.g. with certain tools or programming languages pre-installed
+This guide is for users that would like to use their own custom Docker image for the runtime. For example
+with certain tools or programming languages pre-installed.
 :::
 
 The sandbox is where the agent performs its tasks. Instead of running commands directly on your computer

docs/modules/usage/how-to/gitlab-runner.md

@@ -0,0 +1 @@
+# Using GitLab CI Runners

docs/modules/usage/how-to/gui-mode.md

@@ -24,9 +24,8 @@ OpenHands supports multiple version control providers. You can configure tokens
 
 #### GitHub Token Setup
 
-OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it is available. This can happen in two ways:
+OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if provided:
 
-**Local Installation**: The user directly inputs their GitHub token.
 <details>
   <summary>Setting Up a GitHub Token</summary>
 
@@ -40,9 +39,8 @@ OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it
      - Minimal Permissions ( Select `Meta Data = Read-only` read for search, `Pull Requests = Read and Write` and `Content = Read and Write` for branch creation)
   2. **Enter Token in OpenHands**:
    - Click the Settings button (gear icon).
-   - Navigate to the `Git Provider Settings` section.
    - Paste your token in the `GitHub Token` field.
-   - Click `Save Changes` to apply the changes.
+   - Click `Save` to apply the changes.
 </details>
 
 <details>
@@ -83,26 +81,9 @@ OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it
      - Check the browser console for any error messages.
 </details>
 
-**OpenHands Cloud**: The token is obtained through GitHub OAuth authentication.
-
-<details>
-  <summary>OAuth Authentication</summary>
-
-  When using OpenHands Cloud, the GitHub OAuth flow requests the following permissions:
-   - Repository access (read/write)
-   - Workflow management
-   - Organization read access
-
-  To authenticate OpenHands:
-   - Click `Sign in with GitHub` when prompted.
-   - Review the requested permissions.
-   - Authorize OpenHands to access your GitHub account.
-   - If using an organization, authorize organization access if prompted.
-</details>
-
 #### GitLab Token Setup
 
-OpenHands automatically exports a `GITLAB_TOKEN` to the shell environment, for local installations only, if it is available.
+OpenHands automatically exports a `GITLAB_TOKEN` to the shell environment if provided:
 
 <details>
   <summary>Setting Up a GitLab Token</summary>
@@ -117,10 +98,9 @@ OpenHands automatically exports a `GITLAB_TOKEN` to the shell environment, for l
    - Set an expiration date or leave it blank for a non-expiring token.
   2. **Enter Token in OpenHands**:
    - Click the Settings button (gear icon).
-   - Navigate to the `Git Provider Settings` section.
    - Paste your token in the `GitLab Token` field.
    - Enter your GitLab instance URL if using self-hosted GitLab.
-   - Click `Save Changes` to apply the changes.
+   - Click `Save` to apply the changes.
 </details>
 
 <details>

docs/modules/usage/how-to/headless-mode.md

@@ -32,7 +32,7 @@ To run OpenHands in Headless mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/modules/usage/installation.mdx

@@ -58,17 +58,17 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.32
+    docker.all-hands.dev/all-hands-ai/openhands:0.34
 ```
 
 You'll find OpenHands running at http://localhost:3000!

docs/modules/usage/key-features.md

@@ -6,23 +6,26 @@
 - Displays the conversation between the user and OpenHands.
 - OpenHands explains its actions in this panel.
 
+### Changes
+- Shows the file changes performed by OpenHands.
+
 ### Workspace
 - Browse project files and directories.
 - Use the `Open in VS Code` option to:
   * Modify files
   * Upload and download files
 
+### Terminal
+- A space for OpenHands and users to run terminal commands.
+
 ### Jupyter
 - Shows all Python commands that were executed by OpenHands.
 - Particularly handy when using OpenHands to perform data visualization tasks.
 
 ### App
-- Shows the web server when OpenHands runs an application.
+- Displays the web server when OpenHands runs an application.
 - Users can interact with the running application.
 
 ### Browser
 - Used by OpenHands to browse websites.
 - The browser is non-interactive.
-
-### Terminal
-- A space for OpenHands and users to run terminal commands.

docs/modules/usage/llms/llms.md

@@ -17,6 +17,8 @@ Based on these findings and community feedback, the following models have been v
 - [gemini/gemini-2.5-pro](https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025/)
 - [deepseek/deepseek-chat](https://api-docs.deepseek.com/)
 - [openai/o3-mini](https://openai.com/index/openai-o3-mini/)
+- [openai/o3](https://openai.com/index/introducing-o3-and-o4-mini/)
+- [openai/o4-mini](https://openai.com/index/introducing-o3-and-o4-mini/)
 - [all-hands/openhands-lm-32b-v0.1](https://www.all-hands.dev/blog/introducing-openhands-lm-32b----a-strong-open-coding-agent-model) -- available through [OpenRouter](https://openrouter.ai/all-hands/openhands-lm-32b-v0.1)
 
 

docs/modules/usage/llms/local-llms.md

@@ -15,7 +15,7 @@ It is highly recommended that you use GPUs to serve local models for optimal exp
 For example, to download [OpenHands LM 32B v0.1](https://huggingface.co/all-hands/openhands-lm-32b-v0.1):
 
 ```bash
-huggingface-cli download all-hands/openhands-lm-32b-v0.1 --local-dir my_folder/openhands-lm-32b-v0.1
+huggingface-cli download all-hands/openhands-lm-32b-v0.1 --local-dir all-hands/openhands-lm-32b-v0.1
 ```
 
 ## Create an OpenAI-Compatible Endpoint With a Model Serving Framework
@@ -27,7 +27,7 @@ huggingface-cli download all-hands/openhands-lm-32b-v0.1 --local-dir my_folder/o
 
 ```bash
 SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python3 -m sglang.launch_server \
-    --model my_folder/openhands-lm-32b-v0.1 \
+    --model all-hands/openhands-lm-32b-v0.1 \
     --served-model-name openhands-lm-32b-v0.1 \
     --port 8000 \
     --tp 2 --dp 1 \
@@ -41,7 +41,7 @@ SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python3 -m sglang.launch_server \
 - Example launch command for OpenHands LM 32B (with at least 2 GPUs):
 
 ```bash
-vllm serve my_folder/openhands-lm-32b-v0.1 \
+vllm serve all-hands/openhands-lm-32b-v0.1 \
     --host 0.0.0.0 --port 8000 \
     --api-key mykey \
     --tensor-parallel-size 2 \
@@ -67,7 +67,7 @@ Ensure `config.toml` exists by running `make setup-config` which will create one
 workspace_base="/path/to/your/workspace"
 
 [llm]
-embedding_model="local"
+model="openhands-lm-32b-v0.1"
 ollama_base_url="http://localhost:8000"
 ```
 

docs/modules/usage/prompting/microagents-keyword.md

@@ -0,0 +1,49 @@
+# Keyword-Triggered Microagents
+
+## Purpose
+
+Keyword-triggered microagents provide OpenHands with specific instructions that are activated when certain keywords
+appear in the prompt. This is useful for tailoring behavior based on particular tools, languages, or frameworks.
+
+## Microagent File
+
+Create a keyword-triggered microagent (example: `.openhands/microagents/trigger-keyword.md`) to include instructions
+that activate only for prompts with specific keywords.
+
+## Frontmatter Syntax
+
+Frontmatter is required for keyword-triggered microagents. It must be placed at the top of the file,
+above the guidelines.
+
+Enclose the frontmatter in triple dashes (---) and include the following fields:
+
+| Field      | Description                                      | Required | Default          |
+|------------|--------------------------------------------------|----------|------------------|
+| `name`     | A unique identifier for the microagent.          | Yes      | 'default'        |
+| `type`     | Type of microagent. Must be set to `knowledge`.  | Yes      | 'repo'           |
+| `triggers` | A list of keywords that activate the microagent. | Yes      | None             |
+| `agent`    | The agent this microagent applies to.            | No       | 'CodeActAgent'   |
+
+
+## Example
+
+```
+---
+name: magic_word
+type: knowledge
+triggers:
+- yummyhappy
+- happyyummy
+agent: CodeActAgent
+---
+
+The user has said the magic word. Respond with "That was delicious!"
+```
+
+Keyword-triggered microagents:
+- Monitor incoming prompts for specified trigger words.
+- Activate when relevant triggers are detected.
+- Apply their specialized knowledge and capabilities.
+- Follow defined guidelines and restrictions.
+
+[See examples of microagents triggered by keywords in the official OpenHands repository](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge)

docs/modules/usage/prompting/microagents-overview.md

@@ -1,31 +1,40 @@
 # Microagents Overview
 
-Microagents are specialized prompts that enhance OpenHands with domain-specific knowledge, repository-specific context
-and task-specific workflows. They help by providing expert guidance, automating common tasks, and ensuring
-consistent practices across projects.
+Microagents are specialized prompts that enhance OpenHands with domain-specific knowledge.
+They provide expert guidance, automate common tasks, and ensure consistent practices across projects.
 
-## Microagent Categories
+## Microagent Types
 
-Currently OpenHands supports two categories of microagents:
+Currently OpenHands supports the following types of microagents:
 
-- [Repository-specific Microagents](./microagents-repo): Repository-specific context and guidelines for OpenHands.
-- [Public Microagents](./microagents-public): General guidelines triggered by keywords for all OpenHands users.
+- [General Repository Microagents](./microagents-repo): General guidelines for OpenHands about the repository.
+- [Keyword-Triggered Microagents](./microagents-keyword): Guidelines activated by specific keywords in prompts.
 
-A microagent is classified as repository-specific or public depending on its location:
+To customize OpenHands' behavior, create a .openhands/microagents/ directory in the root of your repository and
+add `<microagent_name>.md` files inside.
 
-- Repository-specific microagents are located in a repository's `.openhands/microagents/` directory
-- Public microagents are located in the official OpenHands repository inside the `/microagents` folder
+:::note
+Loaded microagents take up space in the context window.
+These microagents, alongside user messages, inform OpenHands about the task and the environment.
+:::
 
-When OpenHands works with a repository, it:
+Example repository structure:
 
-1. Loads **repository-specific** microagents from `.openhands/microagents/` if present in the repository.
-2. Loads **public knowledge** microagents triggered by keywords in conversations
-3. Loads **public tasks** microagents when explicitly requested by the user
+```
+some-repository/
+└── .openhands/
+    └── microagents/
+        └── repo.md            # General repository guidelines
+        └── trigger_this.md    # Microagent triggered by specific keywords
+        └── trigger_that.md    # Microagent triggered by specific keywords
+```
 
-You can check out the existing public microagents at the [official OpenHands repository](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/).
+## Microagents Frontmatter Requirements
 
-## Microagent Format
+Each microagent file may include frontmatter that provides additional information. In some cases, this frontmatter
+is required:
 
-All microagents use markdown files with YAML frontmatter that have special instructions to help OpenHands activate them.
-
-Check out the [syntax documentation](./microagents-syntax) for a comprehensive guide on how to configure your microagents.
+| Microagent Type                  | Frontmatter Requirement                               |
+|----------------------------------|-------------------------------------------------------|
+| `General Repository Microagents` | Required only if more than one of this type exists.   |
+| `Keyword-Triggered Microagents`  | Required.                                             |

docs/modules/usage/prompting/microagents-public.md

@@ -1,35 +1,16 @@
-# Public Microagents
+# Global Microagents
 
 ## Overview
 
-Public microagents provide specialized context and capabilities for all OpenHands users, regardless of their repository configuration. Unlike repository-specific microagents, public microagents are globally available across all repositories.
+Global microagents are [keyword-triggered microagents](./microagents-keyword) that apply to all OpenHands users.
 
-Public microagents come in two types:
+## Contributing a Global Microagent
 
-- **Knowledge microagents**: Automatically activated when keywords in conversations match their triggers
-- **Task microagents**: Explicitly invoked by users to guide through specific workflows
-
-Both types follow the same syntax and structure as repository-specific microagents, using markdown files with YAML frontmatter that define their behavior and capabilities. They are located in the official OpenHands repository under:
-
-- [`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge) for knowledge microagents
-- [`microagents/tasks/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/tasks) for task microagents
-
-Public microagents:
-
-- Monitor incoming commands for their trigger words.
-- Activate when relevant triggers are detected.
-- Apply their specialized knowledge and capabilities.
-- Follow their specific guidelines and restrictions.
-
-When loading public microagents, OpenHands scans the official repository's microagents directories recursively, processing all markdown files except README.md. The system categorizes each microagent based on its `type` field in the YAML frontmatter, regardless of its exact file location within the knowledge or tasks directories.
-
-## Contributing a Public Microagent
-
-You can create public microagents and share with the community by opening a pull request to the official repository.
+You can create global microagents and share with the community by opening a pull request to the official repository.
 
 See the [CONTRIBUTING.md](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md) for specific instructions on how to contribute to OpenHands.
 
-### Public Microagents Best Practices
+### Global Microagents Best Practices
 
 - **Clear Scope**: Keep the microagent focused on a specific domain or task.
 - **Explicit Instructions**: Provide clear, unambiguous guidelines.
@@ -37,11 +18,11 @@ See the [CONTRIBUTING.md](https://github.com/All-Hands-AI/OpenHands/blob/main/CO
 - **Safety First**: Include necessary warnings and constraints.
 - **Integration Awareness**: Consider how the microagent interacts with other components.
 
-### Steps to Contribute a Public Microagent
+### Steps to Contribute a Global Microagent
 
-#### 1. Plan the Public Microagent
+#### 1. Plan the Global Microagent
 
-Before creating a public microagent, consider:
+Before creating a global microagent, consider:
 
 - What specific problem or use case will it address?
 - What unique capabilities or knowledge should it have?
@@ -51,23 +32,19 @@ Before creating a public microagent, consider:
 #### 2. Create File
 
 Create a new Markdown file with a descriptive name in the appropriate directory:
+[`microagents/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents)
 
-- [`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge) for knowledge microagents
-- [`microagents/tasks/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/tasks) for task microagents
+#### 3. Testing the Global Microagent
 
-Ensure it follows the correct [syntax](./microagents-syntax.md) and [best practices](./microagents-syntax.md#markdown-content-best-practices).
-
-#### 3. Testing the Public Microagent
-
-- Test the agent with various prompts
-- Verify trigger words activate the agent correctly
-- Ensure instructions are clear and comprehensive
-- Check for potential conflicts and overlaps with existing agents
+- Test the agent with various prompts.
+- Verify trigger words activate the agent correctly.
+- Ensure instructions are clear and comprehensive.
+- Check for potential conflicts and overlaps with existing agents.
 
 #### 4. Submission Process
 
 Submit a pull request with:
 
-- The new microagent file
-- Updated documentation if needed
-- Description of the agent's purpose and capabilities
+- The new microagent file.
+- Updated documentation if needed.
+- Description of the agent's purpose and capabilities.

docs/modules/usage/prompting/microagents-repo.md

@@ -1,117 +1,38 @@
-# Repository-specific Microagents
+# General Repository Microagents
 
-## Overview
+## Purpose
 
-OpenHands can be customized to work more effectively with specific repositories by providing repository-specific context and guidelines.
+General guidelines for OpenHands to work more effectively with the repository.
 
-This section explains how to optimize OpenHands for your project.
+## Microagent File
 
-## Creating Repository Microagents
+Create a general repository microagent (example: `.openhands/microagents/repo.md`) to include
+project-specific instructions, team practices, coding standards, and architectural guidelines that are relevant for
+**all** prompts in that repository.
 
-You can customize OpenHands' behavior for your repository by creating a `.openhands/microagents/` directory in your repository's root.
+## Frontmatter Syntax
 
-You can enhance OpenHands' performance by adding custom microagents to your repository:
+The frontmatter for this type of microagent is optional, unless you plan to include more than one general
+repository microagent.
 
-1. For overall repository-specific instructions, create a `.openhands/microagents/repo.md` file
-2. For reusable domain knowledge triggered by keywords, add multiple `.md` files to `.openhands/microagents/knowledge/`
-3. For common workflows and tasks, create multiple `.md` files to `.openhands/microagents/tasks/`
+Frontmatter should be enclosed in triple dashes (---) and may include the following fields:
 
-Check out the [best practices](./microagents-syntax.md#markdown-content-best-practices) for formatting the content of your custom microagent.
+| Field     | Description                             | Required                                                           | Default        |
+|-----------|-----------------------------------------|--------------------------------------------------------------------|----------------|
+| `name`    | A unique identifier for the microagent  | Required only if using more than one general repository microagent | 'default'      |
+| `agent`   | The agent this microagent applies to    | No                                                                 | 'CodeActAgent' |
 
-Keep in mind that loaded microagents take up space in the context window. It's crucial to strike a balance between the additional context provided by microagents and the instructions provided in the user's inputs.
-
-Note that you can use OpenHands to create new microagents. The public microagent [`add_agent`](https://github.com/All-Hands-AI/OpenHands/blob/main/microagents/knowledge/add_agent.md) is loaded to all OpenHands instance and can support you on this.
-
-## Types of Microagents
-
-OpenHands supports three primary types of microagents, each with specific purposes and features to enhance agent performance:
-
-- [repository](#repository-microagents)
-- [knowledge](#knowledge-microagents)
-- [tasks](#tasks-microagents)
-
-The standard directory structure within a repository is:
-
-- One main `repo.md` file containing repository-specific instructions
-- Additional `Knowledge` agents in `.openhands/microagents/knowledge/` directory
-- Additional `Task` agents in `.openhands/microagents/tasks/` directory
-
-When processing the `.openhands/microagents/` directory, OpenHands will recursively scan all subfolders and process any `.md` files (except `README.md`) it finds. The system determines the microagent type based on the `type` field in the YAML frontmatter, not by the file's location. However, for organizational clarity, it's recommended to follow the standard directory structure.
-
-### Repository Microagents
-
-The `Repository` microagent is loaded specifically from `.openhands/microagents/repo.md` and serves as the main
-repository-specific instruction file. This single file is automatically loaded whenever OpenHands works with that repository
-without requiring any keyword matching or explicit call from the user.
-
-OpenHands does not support multiple `repo.md` files in different locations or multiple microagents with type `repo`.
-
-If you need to organize different types of repository information, the recommended approach is to use a single `repo.md` file with well-structured sections rather than trying to create multiple microagents with the type `repo`.
-
-The best practice is to include project-specific instructions, team practices, coding standards, and architectural guidelines that are relevant for **all** prompts in that repository.
-
-Example structure:
+## Example
 
 ```
-your-repository/
-└── .openhands/
-    └── microagents/
-        └── repo.md    # Repository-specific instructions
+---
+name: repo
+---
+
+This project is a TODO application that allows users to track TODO items.
+
+To set it up, you can run `npm run build`.
+Always make sure the tests are passing before committing changes. You can run the tests by running `npm run test`.
 ```
 
-[See the example in the official OpenHands repository](https://github.com/All-Hands-AI/OpenHands/blob/main/.openhands/microagents/repo.md?plain=1)
-
-### Knowledge Microagents
-
-Knowledge microagents provide specialized domain expertise:
-
-- Recommended to be located in `.openhands/microagents/knowledge/`
-- Triggered by specific keywords in conversations
-- Contain expertise on tools, languages, frameworks, and common practices
-
-Use knowledge microagents to trigger additional context relevant to specific technologies, tools, or workflows. For example, mentioning "git" in your conversation will automatically trigger git-related expertise to help with Git operations.
-
-Examples structure:
-
-```
-your-repository/
-└── .openhands/
-    └── microagents/
-        └── knowledge/
-            └── git.md
-            └── docker.md
-            └── python.md
-            └── ...
-        └── repo.md
-```
-
-You can find several real examples of `Knowledge` microagents in the [offical OpenHands repository](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge)
-
-### Tasks Microagents
-
-Task microagents guide users through interactive workflows:
-
-- Recommended to be located in `.openhands/microagents/tasks/`
-- Provide step-by-step processes for common development tasks
-- Accept inputs and adapt to different scenarios
-- Ensure consistent outcomes for complex operations
-
-Task microagents are a convenient way to store multi-step processes you perform regularly. For instance, you can create a `update_pr_description.md` microagent to automatically generate better pull request descriptions based on code changes.
-
-Examples structure:
-
-```
-your-repository/
-└── .openhands/
-    └── microagents/
-        └── tasks/
-            └── update_pr_description.md
-            └── address_pr_comments.md
-            └── get_test_to_pass.md
-            └── ...
-        └── knowledge/
-            └── ...
-        └── repo.md
-```
-
-You can find several real examples of `Tasks` microagents in the [offical OpenHands repository](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/tasks)
+[See more examples of general repository microagents here.](https://github.com/All-Hands-AI/OpenHands/tree/main/.openhands/microagents)

docs/modules/usage/prompting/microagents-syntax.md

@@ -1,128 +0,0 @@
-# Microagents Syntax
-
-Microagents are defined using markdown files with YAML frontmatter that specify their behavior, triggers, and capabilities.
-
-Find below a comprehensive description of the frontmatter syntax and other details about how to use each type of microagent available at OpenHands.
-
-## Frontmatter Schema
-
-Every microagent requires a YAML frontmatter section at the beginning of the file, enclosed by triple dashes (`---`). The fields are:
-
-| Field      | Description                                        | Required                 | Used By          |
-| ---------- | -------------------------------------------------- | ------------------------ | ---------------- |
-| `name`     | Unique identifier for the microagent               | Yes                      | All types        |
-| `type`     | Type of microagent: `repo`, `knowledge`, or `task` | Yes                      | All types        |
-| `version`  | Version number (Semantic versioning recommended)   | Yes                      | All types        |
-| `agent`    | The agent type (typically `CodeActAgent`)          | Yes                      | All types        |
-| `author`   | Creator of the microagent                          | No                       | All types        |
-| `triggers` | List of keywords that activate the microagent      | Yes for knowledge agents | Knowledge agents |
-| `inputs`   | Defines required user inputs for task execution    | Yes for task agents      | Task agents      |
-
-## Core Fields
-
-### `agent`
-
-**Purpose**: Specifies which agent implementation processes the microagent (typically `CodeActAgent`).
-
-- Defines a single agent responsible for processing the microagent
-- Must be available in the OpenHands system (see the [agent hub](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub))
-- If the specified agent is not active, the microagent will not be used
-
-### `triggers`
-
-**Purpose**: Defines keywords that activate the `knowledge` microagent.
-
-**Example**:
-
-```yaml
-triggers:
-  - kubernetes
-  - k8s
-  - docker
-  - security
-  - containers cluster
-```
-
-**Key points**:
-
-- Can include both single words and multi-word phrases
-- Case-insensitive matching is typically used
-- More specific triggers (like "docker compose") prevent false activations
-- Multiple triggers increase the chance of activation in relevant contexts
-- Unique triggers like "flarglebargle" can be used for testing or special functionality
-- Triggers should be carefully chosen to avoid unwanted activations or conflicts with other microagents
-- Common terms used in many conversations may cause the microagent to be activated too frequently
-
-When using multiple triggers, the microagent will be activated if any of the trigger words or phrases appear in the
-conversation.
-
-### `inputs`
-
-**Purpose**: Defines parameters required from the user when a `task` microagent is activated.
-
-**Schema**:
-
-```yaml
-inputs:
-  - name: INPUT_NAME # Used with {{ INPUT_NAME }}
-    description: 'Description of what this input is for'
-    required: true # Optional, defaults to true
-```
-
-**Key points**:
-
-- The `name` and `description` properties are required for each input
-- The `required` property is optional and defaults to `true`
-- Input values are referenced in the microagent body using double curly braces (e.g., `{{ INPUT_NAME }}`)
-- All inputs defined will be collected from the user before the task microagent executes
-
-**Variable Usage**: Reference input values using double curly braces `{{ INPUT_NAME }}`.
-
-## Example Formats
-
-### Repository Microagent
-
-Repository microagents provide context and guidelines for a specific repository.
-
-- Located at: `.openhands/microagents/repo.md`
-- Automatically loaded when working with the repository
-- Only one per repository
-
-The `Repository` microagent is loaded specifically from `.openhands/microagents/repo.md` and serves as the main
-repository-specific instruction file. This single file is automatically loaded whenever OpenHands works with that repository
-without requiring any keyword matching or explicit call from the user.
-
-[See the example in the official OpenHands repository](https://github.com/All-Hands-AI/OpenHands/blob/main/.openhands/microagents/repo.md?plain=1)
-
-### Knowledge Microagent
-
-Provides specialized domain expertise triggered by keywords.
-
-You can find several real examples of `Knowledge` microagents in the [offical OpenHands repository](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge)
-
-### Task Microagent
-
-When explicitly asked by the user, will guide through interactive workflows with specific inputs.
-
-You can find several real examples of `Tasks` microagents in the [offical OpenHands repository](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/tasks)
-
-## Markdown Content Best Practices
-
-After the frontmatter, compose the microagent body using Markdown syntax. Examples of elements you can include are:
-
-- Clear, concise instructions outlining the microagent's purpose and responsibilities
-- Specific guidelines and constraints the microagent should adhere to
-- Relevant code snippets and practical examples to illustrate key points
-- Step-by-step procedures for task agents, guiding users through workflows
-
-**Design Tips**:
-
-- Keep microagents focused with a clear purpose
-- Provide specific guidelines rather than general advice
-- Use distinctive triggers for knowledge agents
-- Keep content concise to minimize context window usage
-- Break large microagents into smaller, focused ones
-
-Aim for clarity, brevity, and practicality in your writing. Use formatting like bullet points, code blocks, and emphasis to enhance readability and comprehension.
-
-Remember that balancing microagents details with user input space is important for maintaining effective interactions.

docs/package-lock.json

@@ -24,6 +24,8 @@
         "@docusaurus/module-type-aliases": "^3.5.1",
         "@docusaurus/tsconfig": "^3.7.0",
         "@docusaurus/types": "^3.5.1",
+        "swagger-cli": "^4.0.4",
+        "swagger-ui-dist": "^5.21.0",
         "typescript": "~5.8.3"
       },
       "engines": {
@@ -273,6 +275,273 @@
         "node": ">=6.0.0"
       }
     },
+    "node_modules/@apidevtools/openapi-schemas": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/@apidevtools/openapi-schemas/-/openapi-schemas-2.1.0.tgz",
+      "integrity": "sha512-Zc1AlqrJlX3SlpupFGpiLi2EbteyP7fXmUOGup6/DnkRgjP9bgMM/ag+n91rsv0U1Gpz0H3VILA/o3bW7Ua6BQ==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli": {
+      "version": "4.0.4",
+      "resolved": "https://registry.npmjs.org/@apidevtools/swagger-cli/-/swagger-cli-4.0.4.tgz",
+      "integrity": "sha512-hdDT3B6GLVovCsRZYDi3+wMcB1HfetTU20l2DC8zD3iFRNMC6QNAZG5fo/6PYeHWBEv7ri4MvnlKodhNB0nt7g==",
+      "deprecated": "This package has been abandoned. Please switch to using the actively maintained @redocly/cli",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@apidevtools/swagger-parser": "^10.0.1",
+        "chalk": "^4.1.0",
+        "js-yaml": "^3.14.0",
+        "yargs": "^15.4.1"
+      },
+      "bin": {
+        "swagger-cli": "bin/swagger-cli.js"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/argparse": {
+      "version": "1.0.10",
+      "resolved": "https://registry.npmjs.org/argparse/-/argparse-1.0.10.tgz",
+      "integrity": "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "sprintf-js": "~1.0.2"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/camelcase": {
+      "version": "5.3.1",
+      "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz",
+      "integrity": "sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=6"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/cliui": {
+      "version": "6.0.0",
+      "resolved": "https://registry.npmjs.org/cliui/-/cliui-6.0.0.tgz",
+      "integrity": "sha512-t6wbgtoCXvAzst7QgXxJYqPt0usEfbgQdftEPbLL/cvv6HPE5VgvqCuAIDR0NgU52ds6rFwqrgakNLrHEjCbrQ==",
+      "dev": true,
+      "license": "ISC",
+      "dependencies": {
+        "string-width": "^4.2.0",
+        "strip-ansi": "^6.0.0",
+        "wrap-ansi": "^6.2.0"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/emoji-regex": {
+      "version": "8.0.0",
+      "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
+      "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/find-up": {
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/find-up/-/find-up-4.1.0.tgz",
+      "integrity": "sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "locate-path": "^5.0.0",
+        "path-exists": "^4.0.0"
+      },
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/js-yaml": {
+      "version": "3.14.1",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.1.tgz",
+      "integrity": "sha512-okMH7OXXJ7YrN9Ok3/SXrnu4iX9yOk+25nqX4imS2npuvTYDmo/QEZoqwZkYaIDk3jVvBOTOIEgEhaLOynBS9g==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "argparse": "^1.0.7",
+        "esprima": "^4.0.0"
+      },
+      "bin": {
+        "js-yaml": "bin/js-yaml.js"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/locate-path": {
+      "version": "5.0.0",
+      "resolved": "https://registry.npmjs.org/locate-path/-/locate-path-5.0.0.tgz",
+      "integrity": "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "p-locate": "^4.1.0"
+      },
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/p-limit": {
+      "version": "2.3.0",
+      "resolved": "https://registry.npmjs.org/p-limit/-/p-limit-2.3.0.tgz",
+      "integrity": "sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "p-try": "^2.0.0"
+      },
+      "engines": {
+        "node": ">=6"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/p-locate": {
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/p-locate/-/p-locate-4.1.0.tgz",
+      "integrity": "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "p-limit": "^2.2.0"
+      },
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/path-exists": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/path-exists/-/path-exists-4.0.0.tgz",
+      "integrity": "sha512-ak9Qy5Q7jYb2Wwcey5Fpvg2KoAc/ZIhLSLOSBmRmygPsGwkVVt0fZa0qrtMz+m6tJTAHfZQ8FnmB4MG4LWy7/w==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/string-width": {
+      "version": "4.2.3",
+      "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
+      "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "emoji-regex": "^8.0.0",
+        "is-fullwidth-code-point": "^3.0.0",
+        "strip-ansi": "^6.0.1"
+      },
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/wrap-ansi": {
+      "version": "6.2.0",
+      "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-6.2.0.tgz",
+      "integrity": "sha512-r6lPcBGxZXlIcymEu7InxDMhdW0KDxpLgoFLcguasxCaJ/SOIZwINatK9KY/tf+ZrlywOKU0UDj3ATXUBfxJXA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "ansi-styles": "^4.0.0",
+        "string-width": "^4.1.0",
+        "strip-ansi": "^6.0.0"
+      },
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/y18n": {
+      "version": "4.0.3",
+      "resolved": "https://registry.npmjs.org/y18n/-/y18n-4.0.3.tgz",
+      "integrity": "sha512-JKhqTOwSrqNA1NY5lSztJ1GrBiUodLMmIZuLiDaMRJ+itFd+ABVE8XBjOvIWL+rSqNDC74LCSFmlb/U4UZ4hJQ==",
+      "dev": true,
+      "license": "ISC"
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/yargs": {
+      "version": "15.4.1",
+      "resolved": "https://registry.npmjs.org/yargs/-/yargs-15.4.1.tgz",
+      "integrity": "sha512-aePbxDmcYW++PaqBsJ+HYUFwCdv4LVvdnhBy78E57PIor8/OVvhMrADFFEDh8DHDFRv/O9i3lPhsENjO7QX0+A==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "cliui": "^6.0.0",
+        "decamelize": "^1.2.0",
+        "find-up": "^4.1.0",
+        "get-caller-file": "^2.0.1",
+        "require-directory": "^2.1.1",
+        "require-main-filename": "^2.0.0",
+        "set-blocking": "^2.0.0",
+        "string-width": "^4.2.0",
+        "which-module": "^2.0.0",
+        "y18n": "^4.0.0",
+        "yargs-parser": "^18.1.2"
+      },
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/@apidevtools/swagger-cli/node_modules/yargs-parser": {
+      "version": "18.1.3",
+      "resolved": "https://registry.npmjs.org/yargs-parser/-/yargs-parser-18.1.3.tgz",
+      "integrity": "sha512-o50j0JeToy/4K6OZcaQmW6lyXXKhq7csREXcDwk2omFPJEwUNOVtJKvmDr9EI1fAJZUyZcRF7kxGBWmRXudrCQ==",
+      "dev": true,
+      "license": "ISC",
+      "dependencies": {
+        "camelcase": "^5.0.0",
+        "decamelize": "^1.2.0"
+      },
+      "engines": {
+        "node": ">=6"
+      }
+    },
+    "node_modules/@apidevtools/swagger-methods": {
+      "version": "3.0.2",
+      "resolved": "https://registry.npmjs.org/@apidevtools/swagger-methods/-/swagger-methods-3.0.2.tgz",
+      "integrity": "sha512-QAkD5kK2b1WfjDS/UQn/qQkbwF31uqRjPTrsCs5ZG9BQGAkjwvqGFjjPqAuzac/IYzpPtRzjCP1WrTuAIjMrXg==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/@apidevtools/swagger-parser": {
+      "version": "10.1.1",
+      "resolved": "https://registry.npmjs.org/@apidevtools/swagger-parser/-/swagger-parser-10.1.1.tgz",
+      "integrity": "sha512-u/kozRnsPO/x8QtKYJOqoGtC4kH6yg1lfYkB9Au0WhYB0FNLpyFusttQtvhlwjtG3rOwiRz4D8DnnXa8iEpIKA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@apidevtools/json-schema-ref-parser": "11.7.2",
+        "@apidevtools/openapi-schemas": "^2.1.0",
+        "@apidevtools/swagger-methods": "^3.0.2",
+        "@jsdevtools/ono": "^7.1.3",
+        "ajv": "^8.17.1",
+        "ajv-draft-04": "^1.0.0",
+        "call-me-maybe": "^1.0.2"
+      },
+      "peerDependencies": {
+        "openapi-types": ">=7"
+      }
+    },
+    "node_modules/@apidevtools/swagger-parser/node_modules/@apidevtools/json-schema-ref-parser": {
+      "version": "11.7.2",
+      "resolved": "https://registry.npmjs.org/@apidevtools/json-schema-ref-parser/-/json-schema-ref-parser-11.7.2.tgz",
+      "integrity": "sha512-4gY54eEGEstClvEkGnwVkTkrx0sqwemEFG5OSRRn3tD91XH0+Q8XIkYIfo7IwEWPpJZwILb9GUXeShtplRc/eA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@jsdevtools/ono": "^7.1.3",
+        "@types/json-schema": "^7.0.15",
+        "js-yaml": "^4.1.0"
+      },
+      "engines": {
+        "node": ">= 16"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/philsturgeon"
+      }
+    },
     "node_modules/@babel/code-frame": {
       "version": "7.26.2",
       "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
@@ -3835,6 +4104,13 @@
         "@jridgewell/sourcemap-codec": "^1.4.14"
       }
     },
+    "node_modules/@jsdevtools/ono": {
+      "version": "7.1.3",
+      "resolved": "https://registry.npmjs.org/@jsdevtools/ono/-/ono-7.1.3.tgz",
+      "integrity": "sha512-4JQNk+3mVzK3xh2rqd6RB4J46qUR19azEHBneZyTZM+c456qOrbbM/5xcR8huNCCcbVt7+UmizG6GuUvPvKUYg==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/@leichtgewicht/ip-codec": {
       "version": "2.0.5",
       "resolved": "https://registry.npmjs.org/@leichtgewicht/ip-codec/-/ip-codec-2.0.5.tgz",
@@ -3970,6 +4246,14 @@
       "integrity": "sha512-8LduaNlMZGwdZ6qWrKlfa+2M4gahzFkprZiAt2TF8uS0qQgBizKXpXURqvTJ4WtmupWxaLqjRb2UCTe72mu+Aw==",
       "license": "MIT"
     },
+    "node_modules/@scarf/scarf": {
+      "version": "1.4.0",
+      "resolved": "https://registry.npmjs.org/@scarf/scarf/-/scarf-1.4.0.tgz",
+      "integrity": "sha512-xxeapPiUXdZAE3che6f3xogoJPeZgig6omHEy1rIY5WVsB3H2BHNnZH+gHG6x91SCWyQCzWGsuL2Hh3ClO5/qQ==",
+      "dev": true,
+      "hasInstallScript": true,
+      "license": "Apache-2.0"
+    },
     "node_modules/@sideway/address": {
       "version": "4.1.5",
       "resolved": "https://registry.npmjs.org/@sideway/address/-/address-4.1.5.tgz",
@@ -4967,6 +5251,21 @@
         "url": "https://github.com/sponsors/epoberezkin"
       }
     },
+    "node_modules/ajv-draft-04": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/ajv-draft-04/-/ajv-draft-04-1.0.0.tgz",
+      "integrity": "sha512-mv00Te6nmYbRp5DCwclxtt7yV/joXJPGS7nM+97GdxvuttCOfgI3K4U25zboyeX0O+myI8ERluxQe5wljMmVIw==",
+      "dev": true,
+      "license": "MIT",
+      "peerDependencies": {
+        "ajv": "^8.5.0"
+      },
+      "peerDependenciesMeta": {
+        "ajv": {
+          "optional": true
+        }
+      }
+    },
     "node_modules/ajv-formats": {
       "version": "2.1.1",
       "resolved": "https://registry.npmjs.org/ajv-formats/-/ajv-formats-2.1.1.tgz",
@@ -5549,6 +5848,13 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
+    "node_modules/call-me-maybe": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/call-me-maybe/-/call-me-maybe-1.0.2.tgz",
+      "integrity": "sha512-HpX65o1Hnr9HH25ojC1YGs7HCQLq0GCOibSaWER0eNpgJ/Z1MZv2mTc7+xh6WOPxbRVcmgbv4hGU+uSQ/2xFZQ==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/callsites": {
       "version": "3.1.0",
       "resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz",
@@ -7192,6 +7498,16 @@
         }
       }
     },
+    "node_modules/decamelize": {
+      "version": "1.2.0",
+      "resolved": "https://registry.npmjs.org/decamelize/-/decamelize-1.2.0.tgz",
+      "integrity": "sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
     "node_modules/decode-named-character-reference": {
       "version": "1.0.2",
       "resolved": "https://registry.npmjs.org/decode-named-character-reference/-/decode-named-character-reference-1.0.2.tgz",
@@ -8600,6 +8916,16 @@
         "node": ">=6.9.0"
       }
     },
+    "node_modules/get-caller-file": {
+      "version": "2.0.5",
+      "resolved": "https://registry.npmjs.org/get-caller-file/-/get-caller-file-2.0.5.tgz",
+      "integrity": "sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg==",
+      "dev": true,
+      "license": "ISC",
+      "engines": {
+        "node": "6.* || 8.* || >= 10.*"
+      }
+    },
     "node_modules/get-intrinsic": {
       "version": "1.2.7",
       "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.2.7.tgz",
@@ -13110,15 +13436,16 @@
       }
     },
     "node_modules/nanoid": {
-      "version": "3.3.7",
-      "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.7.tgz",
-      "integrity": "sha512-eSRppjcPIatRIMC1U6UngP8XFcz8MQWGQdt1MTBQ7NaAmvXDfvNxbvWV3x2y6CdEUciCSsDHDQZbhYaB8QEo2g==",
+      "version": "3.3.11",
+      "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.11.tgz",
+      "integrity": "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w==",
       "funding": [
         {
           "type": "github",
           "url": "https://github.com/sponsors/ai"
         }
       ],
+      "license": "MIT",
       "bin": {
         "nanoid": "bin/nanoid.cjs"
       },
@@ -13427,6 +13754,14 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
+    "node_modules/openapi-types": {
+      "version": "12.1.3",
+      "resolved": "https://registry.npmjs.org/openapi-types/-/openapi-types-12.1.3.tgz",
+      "integrity": "sha512-N4YtSYJqghVu4iek2ZUvcN/0aqH1kRDuNqzcycDxhOUpg7GdvLa2F3DgS6yBNhInhv2r/6I0Flkn7CqL8+nIcw==",
+      "dev": true,
+      "license": "MIT",
+      "peer": true
+    },
     "node_modules/opener": {
       "version": "1.5.2",
       "resolved": "https://registry.npmjs.org/opener/-/opener-1.5.2.tgz",
@@ -13809,9 +14144,9 @@
       }
     },
     "node_modules/postcss": {
-      "version": "8.4.38",
-      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.4.38.tgz",
-      "integrity": "sha512-Wglpdk03BSfXkHoQa3b/oulrotAkwrlLDRSOb9D0bN86FdRyE9lppSp33aHNPgBa0JKCoB+drFLZkQoRRYae5A==",
+      "version": "8.4.49",
+      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.4.49.tgz",
+      "integrity": "sha512-OCVPnIObs4N29kxTjzLfUryOkvZEq+pf8jTF0lg8E7uETuWHA+v7j3c/xJmiqpX450191LlmZfUKkXxkTry7nA==",
       "funding": [
         {
           "type": "opencollective",
@@ -13826,10 +14161,11 @@
           "url": "https://github.com/sponsors/ai"
         }
       ],
+      "license": "MIT",
       "dependencies": {
         "nanoid": "^3.3.7",
-        "picocolors": "^1.0.0",
-        "source-map-js": "^1.2.0"
+        "picocolors": "^1.1.1",
+        "source-map-js": "^1.2.1"
       },
       "engines": {
         "node": "^10 || ^12 || >=14"
@@ -15367,6 +15703,15 @@
         "node": ">= 0.10"
       }
     },
+    "node_modules/punycode": {
+      "version": "2.3.1",
+      "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz",
+      "integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=6"
+      }
+    },
     "node_modules/pupa": {
       "version": "3.1.0",
       "resolved": "https://registry.npmjs.org/pupa/-/pupa-3.1.0.tgz",
@@ -16205,6 +16550,16 @@
         "node": ">=0.10"
       }
     },
+    "node_modules/require-directory": {
+      "version": "2.1.1",
+      "resolved": "https://registry.npmjs.org/require-directory/-/require-directory-2.1.1.tgz",
+      "integrity": "sha512-fGxEI7+wsG9xrvdjsrlmL22OMTTiHRwAMroiEeMgq8gzoLC/PQr7RsRDSTLUg/bZAZtF+TVIkHc6/4RIKrui+Q==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
     "node_modules/require-from-string": {
       "version": "2.0.2",
       "resolved": "https://registry.npmjs.org/require-from-string/-/require-from-string-2.0.2.tgz",
@@ -16222,6 +16577,13 @@
         "node": "*"
       }
     },
+    "node_modules/require-main-filename": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/require-main-filename/-/require-main-filename-2.0.0.tgz",
+      "integrity": "sha512-NKN5kMDylKuldxYLSUfrbo5Tuzh4hd+2E8NPPX02mZtn1VuREQToYe/ZdlJy+J3uCpfaiGF05e7B8W0iXbQHmg==",
+      "dev": true,
+      "license": "ISC"
+    },
     "node_modules/requires-port": {
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/requires-port/-/requires-port-1.0.0.tgz",
@@ -16702,6 +17064,13 @@
         "node": ">= 0.8.0"
       }
     },
+    "node_modules/set-blocking": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/set-blocking/-/set-blocking-2.0.0.tgz",
+      "integrity": "sha512-KiKBS8AnWGEyLzofFfmvKwpdPzqiy16LvQfK3yv/fVH7Bj13/wl3JSR1J+rfgRE9q7xUJK4qvgS8raSOeLUehw==",
+      "dev": true,
+      "license": "ISC"
+    },
     "node_modules/set-function-length": {
       "version": "1.2.2",
       "resolved": "https://registry.npmjs.org/set-function-length/-/set-function-length-1.2.2.tgz",
@@ -16980,9 +17349,10 @@
       }
     },
     "node_modules/source-map-js": {
-      "version": "1.2.0",
-      "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.0.tgz",
-      "integrity": "sha512-itJW8lvSA0TXEphiRoawsCksnlf8SyvmFzIhltqAHluXd88pkCd+cXJVHTDwdCr0IzwptSm035IHQktUu1QUMg==",
+      "version": "1.2.1",
+      "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz",
+      "integrity": "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==",
+      "license": "BSD-3-Clause",
       "engines": {
         "node": ">=0.10.0"
       }
@@ -17347,6 +17717,32 @@
       "resolved": "https://registry.npmjs.org/mdn-data/-/mdn-data-2.0.30.tgz",
       "integrity": "sha512-GaqWWShW4kv/G9IEucWScBx9G1/vsFZZJUO+tD26M8J8z3Kw5RDQjaoZe03YAClgeS/SWPOcb4nkFBTEi5DUEA=="
     },
+    "node_modules/swagger-cli": {
+      "version": "4.0.4",
+      "resolved": "https://registry.npmjs.org/swagger-cli/-/swagger-cli-4.0.4.tgz",
+      "integrity": "sha512-Cp8YYuLny3RJFQ4CvOBTaqmOOgYsem52dPx1xM5S4EUWFblIh2Q8atppMZvXKUr1e9xH5RwipYpmdUzdPcxWcA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@apidevtools/swagger-cli": "4.0.4"
+      },
+      "bin": {
+        "swagger-cli": "swagger-cli.js"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/swagger-ui-dist": {
+      "version": "5.21.0",
+      "resolved": "https://registry.npmjs.org/swagger-ui-dist/-/swagger-ui-dist-5.21.0.tgz",
+      "integrity": "sha512-E0K3AB6HvQd8yQNSMR7eE5bk+323AUxjtCz/4ZNKiahOlPhPJxqn3UPIGs00cyY/dhrTDJ61L7C/a8u6zhGrZg==",
+      "dev": true,
+      "license": "Apache-2.0",
+      "dependencies": {
+        "@scarf/scarf": "=1.4.0"
+      }
+    },
     "node_modules/tapable": {
       "version": "2.2.1",
       "resolved": "https://registry.npmjs.org/tapable/-/tapable-2.2.1.tgz",
@@ -17949,14 +18345,6 @@
         "punycode": "^2.1.0"
       }
     },
-    "node_modules/uri-js/node_modules/punycode": {
-      "version": "2.3.1",
-      "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz",
-      "integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==",
-      "engines": {
-        "node": ">=6"
-      }
-    },
     "node_modules/url-loader": {
       "version": "4.1.1",
       "resolved": "https://registry.npmjs.org/url-loader/-/url-loader-4.1.1.tgz",
@@ -18610,6 +18998,13 @@
         "node": ">= 8"
       }
     },
+    "node_modules/which-module": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/which-module/-/which-module-2.0.1.tgz",
+      "integrity": "sha512-iBdZ57RDvnOR9AGBhML2vFZf7h8vmBjhoaZqODJBFWHVtKkDmKuHai3cx5PgVMrX5YDNp27AofYbAwctSS+vhQ==",
+      "dev": true,
+      "license": "ISC"
+    },
     "node_modules/widest-line": {
       "version": "4.0.1",
       "resolved": "https://registry.npmjs.org/widest-line/-/widest-line-4.0.1.tgz",

docs/package.json

@@ -4,16 +4,18 @@
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",
-    "start": "docusaurus start",
-    "build": "docusaurus build",
+    "start": "node generate-swagger-ui.js && docusaurus start",
+    "build": "node generate-swagger-ui.js && docusaurus build",
     "swizzle": "docusaurus swizzle",
     "deploy": "docusaurus deploy",
     "clear": "docusaurus clear",
     "serve": "docusaurus serve",
     "write-translations": "docusaurus write-translations",
     "write-heading-ids": "docusaurus write-heading-ids",
-    "typecheck": "tsc"
+    "typecheck": "tsc",
+    "generate-swagger-ui": "node generate-swagger-ui.js"
   },
+  "// Note": "The OpenAPI spec is stored in docs/static/openapi.json so it's accessible at /openapi.json in the deployed site",
   "dependencies": {
     "@docusaurus/core": "^3.7.0",
     "@docusaurus/plugin-content-pages": "^3.7.0",
@@ -31,6 +33,8 @@
     "@docusaurus/module-type-aliases": "^3.5.1",
     "@docusaurus/tsconfig": "^3.7.0",
     "@docusaurus/types": "^3.5.1",
+    "swagger-cli": "^4.0.4",
+    "swagger-ui-dist": "^5.21.0",
     "typescript": "~5.8.3"
   },
   "browserslist": {
@@ -47,5 +51,6 @@
   },
   "engines": {
     "node": ">=18.0"
-  }
+  },
+  "packageManager": "yarn@1.22.22+sha512.a6b2f7906b721bba3d67d4aff083df04dad64c399707841b7acf00f6b133b7ac24255f2652fa22ae3534329dc6180534e98d17432037ff6fd140556e2bb3137e"
 }

docs/sidebars.ts

@@ -66,18 +66,18 @@ const sidebars: SidebarsConfig = {
             },
             {
               type: 'doc',
-              label: 'Repository-specific',
+              label: 'General Repository Microagents',
               id: 'usage/prompting/microagents-repo',
             },
             {
               type: 'doc',
-              label: 'Public',
-              id: 'usage/prompting/microagents-public',
+              label: 'Keyword-Triggered Microagents',
+              id: 'usage/prompting/microagents-keyword',
             },
             {
               type: 'doc',
-              label: 'Syntax',
-              id: 'usage/prompting/microagents-syntax',
+              label: 'Global Microagents',
+              id: 'usage/prompting/microagents-public',
             },
           ],
         },

docs/static/README.md

@@ -0,0 +1,15 @@
+# Static Files for OpenHands Documentation
+
+This directory contains static files that are copied directly to the build output of the Docusaurus documentation.
+
+## OpenAPI Specification
+
+The `openapi.json` file in this directory is the OpenAPI specification for the OpenHands API. It is copied to the build output and is accessible at `/openapi.json` in the deployed site.
+
+This file is used by the Swagger UI interface, which is accessible at `/swagger-ui/` in the deployed site.
+
+## Why is the OpenAPI spec in the static directory?
+
+The OpenAPI specification is placed in the static directory so that it's accessible at a predictable URL in the deployed site. This allows the Swagger UI to reference it directly.
+
+We only need one copy of the OpenAPI spec file, which is this one in the static directory.

evaluation/benchmarks/lca_ci_build_repair/.gitignore

@@ -0,0 +1 @@
+config.yaml

evaluation/benchmarks/lca_ci_build_repair/README.MD

@@ -0,0 +1,35 @@
+# CI Builds Repair Benchmark Integration
+
+This module integrates the CI Builds Repair benchmark developed by [JetBrains-Research](https://github.com/JetBrains-Research/lca-baselines/tree/main/ci-builds-repair/ci-builds-repair-benchmark).
+
+For more information, refer to the [GitHub repository](https://github.com/JetBrains-Research/lca-baselines/tree/main/ci-builds-repair/ci-builds-repair-benchmark) and the associated [research paper](https://arxiv.org/abs/2406.11612).
+See notice below for details
+
+## Setup
+
+Before running any scripts, make sure to configure the benchmark by setting up `config.yaml`.
+This benchmark pushes to JetBrains' private GitHub repository. You will to request a `token_gh` provided by their team, to run this benchmark.
+
+## Inference
+
+To run inference with your model:
+
+```bash
+./evaluation/benchmarks/lca_ci_build_repair/scripts/run_infer.sh llm.yourmodel
+```
+
+## Evaluation
+
+To evaluate the predictions:
+
+```bash
+./evaluation/benchmarks/lca_ci_build_repair/scripts/eval_infer.sh predictions_path_containing_output
+```
+
+## Results
+The benchmark contains 68 instances, we skip instances #126 and #145, and only run 66 instances due to dockerization errors.
+
+Due to running in live GitHub machines, the benchmark is sensitive to the date it is run. Even the golden patches in the dataset might present failures due to updates.
+For example, on 2025-04-09, running the benchmark against the golden patches gave 57/67 successes, with 1 job left in the waiting list.
+
+On 2025-04-10, running the benchmark full with OH and no oracle, 37 succeeded. That is 54% of the complete set of 68 instances and 64% of the 57 that succeed with golden patches.

evaluation/benchmarks/lca_ci_build_repair/config_template.yaml

@@ -0,0 +1,11 @@
+LCA_PATH: path #where to clone lca-ci rep
+model_name: OpenHands
+benchmark_owner: ICML-25-BenchName-builds-repair
+token_gh: your_token
+#for lca-ci-repo
+repos_folder: /path/to/repos # here the cloned repos would be stored
+out_folder: /out/folder # here the result files would be stored
+data_cache_dir: /data/cache/dir/ # here the cached dataset would be stored
+username_gh: username-gh # your GitHub username
+# test_username: test_user # username that would be displayed in the benchmark. Optional. If ommitted, username_gh would be used
+language: Python # dataset language (now only Python is available)

evaluation/benchmarks/lca_ci_build_repair/eval_infer.py

@@ -0,0 +1,242 @@
+"""Implements evaluation on JetBrains CI builds repair baselines
+
+Please see https://github.com/JetBrains-Research/lca-baselines/tree/main/ci-builds-repair
+and https://huggingface.co/datasets/JetBrains-Research/lca-ci-builds-repair
+
+TODOs:
+- Add more flags
+"""
+
+import json
+import os
+from pathlib import Path
+
+import ruamel.yaml
+
+from evaluation.utils.shared import (
+    EvalMetadata,
+    get_default_sandbox_config_for_eval,
+    make_metadata,
+)
+from openhands.core.config import (
+    AppConfig,
+    LLMConfig,
+    get_parser,
+    load_app_config,
+)
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.main import create_runtime
+from openhands.events.action import CmdRunAction
+from openhands.events.observation import CmdOutputObservation
+from openhands.runtime.base import Runtime
+from openhands.utils.async_utils import call_async_from_sync
+
+
+def get_config(
+    metadata: EvalMetadata,
+) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
+    config = AppConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        runtime='docker',
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
+    )
+    config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.enable_prompt_extensions = False
+    return config
+
+
+config = load_app_config()
+
+
+def load_bench_config():
+    script_dir = os.path.dirname(
+        os.path.abspath(__file__)
+    )  # Get the absolute path of the script
+    config_path = os.path.join(script_dir, 'config.yaml')
+    yaml = ruamel.yaml.YAML(typ='rt')
+    with open(config_path, 'r') as file:
+        return yaml.load(file)
+
+
+bench_config = load_bench_config()
+
+
+def run_eval(
+    runtime: Runtime,
+):
+    """Run the evaluation and create report"""
+    logger.info(f"{'-' * 50} BEGIN Runtime Initialization Fn {'-' * 50}")
+    obs: CmdOutputObservation
+
+    lca_path = bench_config['LCA_PATH']
+    lca_ci_path = os.path.join(
+        lca_path, 'lca-baselines', 'ci-builds-repair', 'ci-builds-repair-benchmark'
+    )
+
+    model_name = bench_config['model_name']
+
+    action = CmdRunAction(command=f'mkdir {lca_path}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    action = CmdRunAction(command=f'cd {lca_path}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    lca_repo_url = 'https://github.com/juanmichelini/lca-baselines'
+    action = CmdRunAction(command=f'git clone {lca_repo_url}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    action = CmdRunAction(command=f'cd {lca_ci_path}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    action = CmdRunAction(command='git switch open-hands-integration')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    script_dir = os.path.dirname(
+        os.path.abspath(__file__)
+    )  # Get the absolute path of the script
+    config_path = os.path.join(script_dir, 'config.yaml')
+    runtime.copy_to(config_path, lca_ci_path)
+
+    token_gh = bench_config['token_gh']
+    commandf = f'export TOKEN_GH={token_gh}'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+
+    action = CmdRunAction(command='poetry install')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+
+    # Set up the task environment
+    commandf = f'poetry run python run_eval_jobs.py --model-name "{model_name}" --config-path "{lca_ci_path}/config.yaml" --job-ids-file "/tmp/output_lca.jsonl" --result-filename "testfile.jsonl"  > /tmp/single_output.txt'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(f'run_eval_jobs.py gave {obs.content} !')
+    # assert obs.exit_code == 0
+
+    commandf = 'cat /tmp/single_output.txt'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(f' {commandf} gave {obs.content}!')
+
+    testfile_path = os.path.join(bench_config['out_folder'], 'testfile.jsonl')
+    commandf = f'cat {testfile_path}'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    report_str = obs.content
+
+    logger.info(f"{'-' * 50} END Runtime Initialization Fn {'-' * 50}")
+    return report_str
+
+
+def process_predictions(predictions_path: str):
+    output_path = Path(predictions_path)
+    if output_path.suffix != '.jsonl':
+        raise ValueError('output_path must end in .jsonl')
+
+    output_lca_path = output_path.with_name(output_path.stem + '_lca.jsonl')
+
+    with output_path.open() as infile, output_lca_path.open('w') as outfile:
+        for line in infile:
+            data = json.loads(line)
+            json.dump(data.get('test_result'), outfile)
+            outfile.write('\n')
+
+    return str(output_lca_path)
+
+
+if __name__ == '__main__':
+    parser = get_parser()
+    parser.add_argument(
+        '-s',
+        '--eval-split',
+        type=str,
+        default='test',
+        choices=['test'],
+        help='data split to evaluate on, must be test',
+    )
+    parser.add_argument(
+        '--predictions-path',
+        type=str,
+        help='Path to the directory containing the output.jsonl with the predictions.',
+    )
+    args, _ = parser.parse_known_args()
+
+    data_split = args.eval_split
+
+    llm_config = LLMConfig(model='dummy_model')
+
+    metadata = make_metadata(
+        llm_config,
+        f'jetbrains-lca-ci--{data_split}',
+        args.agent_cls,
+        args.max_iterations,
+        args.eval_note,
+        args.predictions_path,
+    )
+
+    # prepare image
+    config = get_config(metadata)
+    runtime = create_runtime(config)
+    call_async_from_sync(runtime.connect)
+    logger.info('Converting output.jsonl into output_lca.jsonl')
+    predictions_lca_path = process_predictions(
+        os.path.join(args.predictions_path, 'output.jsonl')
+    )
+    runtime.copy_to(predictions_lca_path, '/tmp')
+
+    # get results
+    results_str = run_eval(runtime)
+    results_path = os.path.join(args.predictions_path, 'results.jsonl')
+    with open(results_path, 'w') as file:
+        file.write(results_str)
+    logger.info(f'Saved results to {results_path}')
+
+    # make a summary
+    resolved_instances = []
+    unresolved_instances = []
+    for line in results_str.strip().splitlines():
+        data = json.loads(line)
+        conclusion = data.get('conclusion')
+        if conclusion == 'success':
+            resolved_instances.append(data)
+        elif conclusion == 'failure':
+            unresolved_instances.append(data)
+
+    completed_instances = resolved_instances + unresolved_instances
+
+    report = {
+        'success': len(resolved_instances),
+        'failure': len(unresolved_instances),
+        'resolved_instances': resolved_instances,
+        'unresolved_instances': unresolved_instances,
+        'completed_instances': completed_instances,
+    }
+
+    print(f'Results: {report}')
+    report_path = os.path.join(args.predictions_path, 'report.jsonl')
+    with open(report_path, 'w') as out_f:
+        out_f.write(json.dumps(report) + '\n')
+
+    logger.info(f'Saved report of results in swebench format to {report_path}')

evaluation/benchmarks/lca_ci_build_repair/run_infer.py

@@ -0,0 +1,406 @@
+"""Implements inference on JetBrains CI builds repair baselines
+
+Please see https://github.com/JetBrains-Research/lca-baselines/tree/main/ci-builds-repair
+and https://huggingface.co/datasets/JetBrains-Research/lca-ci-builds-repair
+
+TODOs:
+- Add EXP_NAME
+"""
+
+import asyncio
+import json
+import os
+from typing import Any
+
+import pandas as pd
+import ruamel.yaml
+from datasets import load_dataset
+
+from evaluation.utils.shared import (
+    EvalMetadata,
+    EvalOutput,
+    codeact_user_response,
+    compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
+    make_metadata,
+    prepare_dataset,
+    reset_logger_for_multiprocessing,
+    run_evaluation,
+)
+from openhands.controller.state.state import State
+from openhands.core.config import (
+    AppConfig,
+    get_llm_config_arg,
+    get_parser,
+    load_app_config,
+)
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.main import create_runtime, run_controller
+from openhands.events.action import CmdRunAction, MessageAction
+from openhands.events.observation import CmdOutputObservation
+from openhands.runtime.base import Runtime
+from openhands.utils.async_utils import call_async_from_sync
+
+
+def get_config(
+    metadata: EvalMetadata,
+) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
+    config = AppConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        runtime='docker',
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
+    )
+    config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.enable_prompt_extensions = False
+    return config
+
+
+config = load_app_config()
+
+
+def load_bench_config():
+    script_dir = os.path.dirname(
+        os.path.abspath(__file__)
+    )  # Get the absolute path of the script
+    config_path = os.path.join(script_dir, 'config.yaml')
+    yaml = ruamel.yaml.YAML(typ='rt')
+    with open(config_path, 'r') as file:
+        return yaml.load(file)
+
+
+bench_config = load_bench_config()
+
+AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
+    'CodeActAgent': codeact_user_response,
+}
+
+AGENT_CLS_TO_INST_SUFFIX = {
+    'CodeActAgent': 'When you think you have completed the task, please finish the interaction using the "finish" tool.\n'
+}
+
+
+def initialize_runtime(
+    runtime: Runtime,
+    instance: pd.Series,
+):
+    """Initialize the runtime for the agent.
+
+    This function is called before the runtime is used to run the agent.
+    """
+    logger.info(f"{'-' * 50} BEGIN Runtime Initialization Fn {'-' * 50}")
+    obs: CmdOutputObservation
+
+    lca_path = bench_config['LCA_PATH']
+    lca_ci_path = os.path.join(
+        lca_path, 'lca-baselines', 'ci-builds-repair', 'ci-builds-repair-benchmark'
+    )
+
+    repo_name = instance['repo_name']
+    repos_path = bench_config['repos_folder']
+    repo_owner = instance['repo_owner']
+    repo_path = os.path.join(repos_path, f'{repo_owner}__{repo_name}')
+    model_name = bench_config['model_name']
+
+    action = CmdRunAction(command=f'mkdir {lca_path}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    action = CmdRunAction(command=f'cd {lca_path}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    lca_repo_url = 'https://github.com/juanmichelini/lca-baselines'
+    action = CmdRunAction(command=f'git clone {lca_repo_url}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    action = CmdRunAction(command=f'cd {lca_ci_path}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    action = CmdRunAction(command='git switch open-hands-integration')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    script_dir = os.path.dirname(
+        os.path.abspath(__file__)
+    )  # Get the absolute path of the script
+    config_path = os.path.join(script_dir, 'config.yaml')
+    with open(config_path, 'r') as file:
+        config_as_text = file.read()
+
+    commandf = f"echo '{config_as_text}' > config.yaml"
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+
+    token_gh = bench_config['token_gh']
+    commandf = f'export TOKEN_GH={token_gh}'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+
+    action = CmdRunAction(command='poetry install')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+
+    # Set up the task environment
+    commandf = f'poetry run python run_get_datapoint.py --model-name {model_name} --id {instance["id"]} > branch_name.txt'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    if obs.exit_code != 0:
+        print(f'run_get_datapoint.py failed at {instance["id"]} with {obs.content}')
+    assert obs.exit_code == 0
+
+    commandf = 'cat branch_name.txt'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    bench_config['user_branch_name'] = obs.content
+
+    # Navigate to the task's code path
+    action = CmdRunAction(command=f'cd {repo_path}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+
+    logger.info(f"{'-' * 50} END Runtime Initialization Fn {'-' * 50}")
+
+
+def complete_runtime(
+    runtime: Runtime,
+    instance: pd.Series,
+) -> 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(f"{'-' * 50} BEGIN Runtime Completion Fn {'-' * 50}")
+    obs: CmdOutputObservation
+
+    model_name = bench_config['model_name']
+
+    lca_path = bench_config['LCA_PATH']
+    lca_ci_path = os.path.join(
+        lca_path, 'lca-baselines', 'ci-builds-repair', 'ci-builds-repair-benchmark'
+    )
+
+    user_branch_name = bench_config['user_branch_name']
+
+    token_gh = bench_config['token_gh']
+    commandf = f'export TOKEN_GH={token_gh}'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+
+    # Navigate to the lca-baseslines scripts path
+    action = CmdRunAction(command=f'cd {lca_ci_path}')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    assert obs.exit_code == 0
+
+    commandf = f'poetry run python run_push_datapoint.py --id {instance["id"]} --model-name {model_name} --user-branch-name {user_branch_name} > single_output.json'
+    logger.info(f'Running push script: {commandf}')
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    # assert obs.exit_code == 0
+
+    commandf = 'cat single_output.json'
+    action = CmdRunAction(command=commandf)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    result = json.loads(obs.content)
+
+    logger.info(f"{'-' * 50} END Runtime Completion Fn {'-' * 50}")
+
+    return result
+
+
+def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool = True):
+    config = get_config(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"]}.')
+
+    repo_name = instance['repo_name']
+    repo_workflow = instance['workflow_path']
+    repo_logs = instance['logs']
+    repos_path = bench_config['repos_folder']
+    repo_owner = instance['repo_owner']
+    repo_path = os.path.join(repos_path, f'{repo_owner}__{repo_name}')
+
+    # Prepare the task instruction
+    instruction_no_oracle = f"""
+<uploaded_files>
+{repo_path}
+</uploaded_files>
+
+I've uploaded a python code repository in the directory {repo_path}, Consider the following issue:
+
+<issue_description>
+The repository must pass the CI workflow {repo_workflow}.
+but it gave the following error
+{repo_logs}
+</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 {repo_path} directory to ensure the <issue_description> is satisfied.
+
+Follow these phases to resolve the issue:
+
+Phase 1. READING: read the problem and reword it in clearer terms
+   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
+   1.2 Hightlight message errors, method names, variables, file names, stack traces, and technical details.
+   1.3 Explain the problem in clear terms.
+   1.4 Enumerate the steps to reproduce the problem.
+   1.5 Hightlight any best practices to take into account when testing and fixing the issue
+
+Phase 2. RUNNING: install and run the tests on the repository
+   2.1 Follow the readme
+   2.2 Install the environment and anything needed
+   2.2 Iterate and figure out how to run the tests
+
+Phase 3. EXPLORATION: find the files that are related to the problem and possible solutions
+   3.1 Use `grep` to search for relevant methods, classes, keywords and error messages.
+   3.2 Identify all files related to the problem statement.
+   3.3 Propose the methods and files to fix the issue and explain why.
+   3.4 From the possible file locations, select the most likely location to fix the issue.
+
+Phase 4. TEST CREATION: before implementing any fix, create a script to reproduce and verify the issue.
+   4.1 Look at existing test files in the repository to understand the test format/structure.
+   4.2 Create a minimal reproduction script that reproduces the located issue.
+   4.3 Run the reproduction script to confirm you are reproducing the issue.
+   4.4 Adjust the reproduction script as necessary.
+
+Phase 5. FIX ANALYSIS: state clearly the problem and how to fix it
+   5.1 State clearly what the problem is.
+   5.2 State clearly where the problem is located.
+   5.3 State clearly how the test reproduces the issue.
+   5.4 State clearly the best practices to take into account in the fix.
+   5.5 State clearly how to fix the problem.
+
+Phase 6. FIX IMPLEMENTATION: Edit the source code to implement your chosen solution.
+   6.1 Make minimal, focused changes to fix the issue.
+
+Phase 7. VERIFICATION: Test your implementation thoroughly.
+   7.1 Run your reproduction script to verify the fix works.
+   7.2 Add edge cases to your test script to ensure comprehensive coverage.
+   7.3 Run existing tests related to the modified code to ensure you haven't broken anything. Run any tests in the repository related to:
+     7.2.1 The issue you are fixing
+     7.2.2 The files you modified
+     7.2.3 The functions you changed
+   7.4 If any tests fail, revise your implementation until all tests pass
+
+Phase 8. REVIEW: Carefully re-read the problem description and compare your changes with the base commit {instance["sha_fail"]}.
+   8.1 Ensure you've fully addressed all requirements.
+
+Once all phases are done, announce: 'Agent Task Complete'.
+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.
+"""
+    runtime = create_runtime(config)
+    call_async_from_sync(runtime.connect)
+    initialize_runtime(runtime, instance)
+
+    # Run the agent
+    state: State | None = asyncio.run(
+        run_controller(
+            config=config,
+            initial_user_action=MessageAction(content=instruction_no_oracle),
+            runtime=runtime,
+            fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN.get(
+                metadata.agent_class
+            ),
+        )
+    )
+    assert state is not None
+    metrics = state.metrics.get() if state.metrics else {}
+
+    test_result = complete_runtime(runtime, instance)
+
+    # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
+    # for compatibility with the existing output format, we can remake the pairs here
+    # remove when it becomes unnecessary
+    histories = compatibility_for_eval_history_pairs(state.history)
+
+    # Save the output
+    output = EvalOutput(
+        instance_id=instance['instance_id'],
+        # instance=instance.to_dict(orient='recorods'),
+        instruction=instruction_no_oracle,
+        metadata=metadata,
+        history=histories,
+        test_result=test_result,
+        metrics=metrics,
+    )
+    return output
+
+
+if __name__ == '__main__':
+    parser = get_parser()
+    parser.add_argument(
+        '-s',
+        '--eval-split',
+        type=str,
+        default='test',
+        choices=['test'],
+        help='data split to evaluate on, must be test',
+    )
+    args, _ = parser.parse_known_args()
+
+    data_split = args.eval_split
+
+    bench = load_dataset(
+        'JetBrains-Research/lca-ci-builds-repair', split=data_split
+    ).to_pandas()
+    # todo: see why 126 is giving problems on inference
+    # todo: see why 145 is giving problems on eval
+    bench = bench[bench['id'] != 126]
+    bench = bench[bench['id'] != 145]
+    # bench = bench.iloc[0:56]
+    # add column instnace_id for compatibility with oh repo, old id column must be kept for lca repo
+    bench['instance_id'] = bench['id'].astype(str)
+
+    llm_config = None
+    if args.llm_config:
+        llm_config = get_llm_config_arg(args.llm_config)
+        # 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}')
+
+    metadata = make_metadata(
+        llm_config,
+        f'jetbrains-lca-ci--{data_split}',
+        args.agent_cls,
+        args.max_iterations,
+        args.eval_note,
+        args.eval_output_dir,
+    )
+    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+    instances = prepare_dataset(bench, output_file, args.eval_n_limit)
+
+    run_evaluation(
+        instances, metadata, output_file, args.eval_num_workers, process_instance
+    )

evaluation/benchmarks/lca_ci_build_repair/scripts/eval_infer.sh

@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+source "evaluation/utils/version_control.sh"
+
+PROCESS_FILEPATH=$1
+if [ -z "$PROCESS_FILEPATH" ]; then
+    echo "Error: PROCESS_FILEPATH is empty. Usage: ./eval_infer.sh <output_file> [instance_id] [dataset_name] [split]"
+    exit 1
+fi
+
+get_openhands_version
+
+PROCESS_FILEPATH=$(realpath $PROCESS_FILEPATH)
+echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "PROCESS_FILEPATH: $PROCESS_FILEPATH"
+
+EVAL_NOTE="$OPENHANDS_VERSION"
+if [ -n "$EXP_NAME" ]; then
+  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
+fi
+
+function run_eval() {
+  COMMAND="poetry run python ./evaluation/benchmarks/lca_ci_build_repair/eval_infer.py \
+    --predictions-path $PROCESS_FILEPATH "
+
+  echo "RUNNING: $COMMAND"
+  # Run the command
+  eval $COMMAND
+}
+
+unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
+run_eval

evaluation/benchmarks/lca_ci_build_repair/scripts/run_infer.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+source "evaluation/utils/version_control.sh"
+
+MODEL_CONFIG=$1
+
+get_openhands_version
+
+echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "MODEL_CONFIG: $MODEL_CONFIG"
+
+EVAL_NOTE="$OPENHANDS_VERSION"
+if [ -n "$EXP_NAME" ]; then
+  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
+fi
+
+function run_eval() {
+  COMMAND="poetry run python ./evaluation/benchmarks/lca_ci_build_repair/run_infer.py \
+    --llm-config $MODEL_CONFIG "
+
+  # Run the command
+  eval $COMMAND
+}
+
+#unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
+run_eval

evaluation/benchmarks/lca_ci_build_repair/setup.py

@@ -0,0 +1,60 @@
+"""Installs LCA CI Build Repair benchmark with scripts for OH integration."""
+
+import os
+import shutil
+import subprocess
+
+import yaml
+
+
+def setup():
+    # Read config.yaml
+    print('Reading config.yaml')
+    script_dir = os.path.dirname(
+        os.path.abspath(__file__)
+    )  # Get the absolute path of the script
+    config_path = os.path.join(script_dir, 'config.yaml')
+    with open(config_path, 'r') as f:
+        config = yaml.safe_load(f)
+
+    lca_path = config['LCA_PATH']
+    lca_ci_path = os.path.join(
+        lca_path, 'lca-baselines', 'ci-builds-repair', 'ci-builds-repair-benchmark'
+    )
+    repo_url = 'https://github.com/juanmichelini/lca-baselines'
+
+    # Clone the repository to LCA_CI_PATH
+    print(f'Cloning lca-baselines repository from {repo_url} into {lca_path}')
+    result = subprocess.run(
+        ['git', 'clone', repo_url], cwd=lca_path, capture_output=True, text=True
+    )
+    if result.returncode != 0:
+        print(f'Warning cloning repository: {result.stderr}')
+
+    # Clone the repository to LCA_CI_PATH
+    print('Switching branches')
+    result = subprocess.run(
+        ['git', 'switch', 'open-hands-integration'],
+        cwd=lca_ci_path,
+        capture_output=True,
+        text=True,
+    )
+    if result.returncode != 0:
+        print(f'Warning switching repository: {result.stderr}')
+
+    # Move and rename config_lca.yaml (overwrite if exists)
+    lca_ci_config_path = os.path.join(lca_ci_path, 'config.yaml')
+    print(f'Copying config.yaml to {lca_ci_config_path}')
+    shutil.copy(config_path, lca_ci_config_path)
+
+    # Run poetry install in LCA_CI_PATH
+    print(f"Running 'poetry install' in {lca_ci_path}")
+    result = subprocess.run(
+        ['poetry', 'install'], cwd=lca_ci_path, capture_output=True, text=True
+    )
+    if result.returncode != 0:
+        print(f'Warning during poetry install: {result.stderr}')
+
+
+if __name__ == '__main__':
+    setup()

evaluation/benchmarks/swe_bench/README.md

@@ -2,6 +2,8 @@
 
 This folder contains the evaluation harness that we built on top of the original [SWE-Bench benchmark](https://www.swebench.com/) ([paper](https://arxiv.org/abs/2310.06770)).
 
+**UPDATE (4/8/2025): We now support running SWT-Bench evaluation! For more details, checkout [the corresponding section](#SWT-Bench-Evaluation).**
+
 **UPDATE (03/27/2025): We now support SWE-Bench multimodal evaluation! Simply use "princeton-nlp/SWE-bench_Multimodal" as the dataset name in the `run_infer.sh` script to evaluate on multimodal instances.**
 
 **UPDATE (2/18/2025): We now support running SWE-Gym using the same evaluation harness here. For more details, checkout [this README](./SWE-Gym.md).**
@@ -141,7 +143,7 @@ With `output.jsonl` file, you can run `eval_infer.sh` to evaluate generated patc
 ./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh $YOUR_OUTPUT_JSONL [instance_id] [dataset_name] [split]
 
 # Example
-./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh evaluation/evaluation_outputs/outputs/swe_bench/CodeActAgent/gpt-4-1106-preview_maxiter_50_N_v1.0/output.jsonl
+./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Lite/CodeActAgent/gpt-4-1106-preview_maxiter_50_N_v1.0/output.jsonl
 ```
 
 The script now accepts optional arguments:
@@ -182,3 +184,58 @@ To clean-up all existing runtimes that you've already started, run:
 ```bash
 ALLHANDS_API_KEY="YOUR-API-KEY" ./evaluation/utils/scripts/cleanup_remote_runtime.sh
 ```
+
+## SWT-Bench Evaluation
+
+[SWT-Bench](https://swtbench.com/) ([paper](https://arxiv.org/abs/2406.12952)) is a benchmark for evaluating the capability of LLMs at creating unit tests. It is performed on the same instances as SWE-Bench, but requires a separate evaluation harness to capture coverage and issue reproduction. We therefore detail below how to leverage the inference script in this folder to run inference on SWT-Bench and how to use the SWT-Bench evaluation harness to evaluate them.
+
+### Run inference on SWT-Bench
+
+To run inference on SWT-Bench, you can use the same `run_infer.sh` script as described for evaluation on plain SWE-Bench. The only differences is that you need to specify the `mode` parameter to `swt` or `swt-ci` when running the script. For example, to run inference on SWT-Bench Verified, run the following command:
+
+```bash
+./evaluation/benchmarks/swe_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [swe-dataset] test 1 swt
+
+# Example - This runs evaluation on CodeActAgent for 500 instances on "SWT-bench_Verified"'s test set (corresponding to SWE-bench_Verified), with max 100 iteration per instances, with 1 number of workers running in parallel
+./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4o-2024-11-20 HEAD CodeActAgent 500 100 1 princeton-nlp/SWE-bench_Verified test 1 swt
+```
+
+The two modes `swt` and `swt-ci` have the following effect:
+- `swt`: This mode will change the prompt to instruct the agent to generate reproducing test cases instead of resolving the issue.
+- `swt-ci`: In addition to the changes by `swt`, this mode sets up the CI environment by i) pre-installing the environment in the docker image, such that the test framework can be executed without errors and ii) telling the model the exact command to run the test framework.
+
+### Run evaluation for SWT-bench
+
+The evaluation of these results is done leveraging [the SWT-Bench evaluation harness](https://github.com/logic-star-ai/swt-bench/tree/master).
+
+#### Extracting results into SWT-Bench harness format
+In order to run evaluation of the obtained inference results in the SWT-Bench harness, we transform the results to a format that the SWT-Bench evaluation harness expects.
+
+```bash
+python3 evaluation/benchmarks/swe_bench/scripts/swtbench/convert.py --prediction_file [output.jsonl] > [output_swt.jsonl]
+
+# Example
+python3 evaluation/benchmarks/swe_bench/scripts/swtbench/convert.py --prediction_file "evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Verified-test/CodeActAgent/gpt-4o-2024-11-20_maxiter_100_N_v0.31.0-no-hint-swt-run_1/output.jsonl" > OpenHands-gpt-4o-2024-11-20.jsonl
+```
+
+#### Running the results in SWT-Bench
+
+Next, we run the [SWT-Bench evaluation harness](https://github.com/logic-star-ai/swt-bench/tree/master) with these results.
+First set-up and validate the setup as described in the harness [here](https://github.com/logic-star-ai/swt-bench/tree/master?tab=readme-ov-file#-set-up).
+Then, run the evaluation with the following command:
+
+```bash
+# Example
+python3 -m src.main \
+    --dataset_name princeton-nlp/SWE-bench_Verified \
+    --predictions_path <pathTo>/OpenHands-gpt-4o-2024-11-20.jsonl \
+    --max_workers 12 \
+    --run_id OpenHands-CodeAct-gpt-4o-2024-11-20  --patch_types vanilla  --build_mode api
+```
+
+The results of the evaluation can be obtained by running the reporting script of the harness.
+
+```bash
+# Example
+python -m src.report run_instance_swt_logs/OpenHands-CodeAct-gpt-4o-2024-11-20/OpenHands__CodeActAgent__gpt-4o-2024-11-20 --dataset verified
+```

evaluation/benchmarks/swe_bench/resource/swt_bench_constants.py

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

evaluation/benchmarks/swe_bench/run_infer.py

@@ -3,7 +3,7 @@ import copy
 import json
 import os
 import tempfile
-from typing import Any
+from typing import Any, Literal
 
 import pandas as pd
 import toml
@@ -17,6 +17,11 @@ from evaluation.benchmarks.swe_bench.binary_patch_utils import (
 from evaluation.benchmarks.swe_bench.resource.mapping import (
     get_instance_resource_factor,
 )
+from evaluation.benchmarks.swe_bench.resource.swt_bench_constants import (
+    MAP_REPO_TO_INSTALL,
+    MAP_REPO_TO_TEST_FRAMEWORK_VERBOSE,
+    MAP_VERSION_TO_INSTALL,
+)
 from evaluation.utils.shared import (
     EvalException,
     EvalMetadata,
@@ -55,6 +60,7 @@ 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'
+BenchMode = Literal['swe', 'swt', 'swt-ci']
 
 
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
@@ -68,7 +74,36 @@ def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
 
 def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageAction:
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
-    instruction = f"""
+    mode = metadata.details['mode']
+    if mode.startswith('swt'):
+        test_instructions = (
+            f'The following command can be used to run the tests: `{list(MAP_REPO_TO_TEST_FRAMEWORK_VERBOSE[instance.repo].values())[0]}`. Make sure they fail in the expected way.\n'
+            if mode.endswith('ci')
+            else ''
+        )
+        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}
+</issue_description>
+
+
+Can you help me implement the necessary changes to the repository to test whether the issue in <issue_description> was resolved?
+I will take care of all changes to any of the non-test files. This means you DON'T have to modify the actual logic and ONLY have to update test logic and tests!
+Your task is to make the minimal changes to tests files in the /workspace directory to reproduce the issue in the <issue_description>, i.e., such that the generated tests fail in the current state (where the issue is unresolved) and pass when the issue will be resolved.
+Follow these steps to reproduce the issue:
+1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.
+2. Create a script `reproduction.py` to reproduce the error and execute it with `python reproduction.py` using the BashTool, to confirm the error
+3. Edit the sourcecode of the repo to integrate your reproduction script into the test framework
+4. Run the test framework and make sure your tests fail! Only submit FAILING tests! Never submit passing tests.
+{test_instructions}Your thinking should be thorough and so it's fine if it's very long.
+"""
+    else:
+        instruction = f"""
 <uploaded_files>
 /workspace/{workspace_dir_name}
 </uploaded_files>
@@ -356,6 +391,30 @@ def initialize_runtime(
     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'})
+
     if 'multimodal' not in metadata.dataset.lower():
         # Only for non-multimodal datasets, we need to activate the testbed environment for Python
         # SWE-Bench multimodal datasets are not using the testbed environment
@@ -678,6 +737,13 @@ if __name__ == '__main__':
         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
@@ -714,7 +780,7 @@ if __name__ == '__main__':
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 
-    details = {}
+    details = {'mode': args.mode}
     _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
 
     dataset_descrption = (

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

@@ -12,6 +12,7 @@ NUM_WORKERS=$6
 DATASET=$7
 SPLIT=$8
 N_RUNS=$9
+MODE=${10}
 
 if [ -z "$NUM_WORKERS" ]; then
   NUM_WORKERS=1
@@ -45,6 +46,11 @@ if [ -z "$SPLIT" ]; then
   SPLIT="test"
 fi
 
+if [ -z "$MODE" ]; then
+  MODE="swe"
+  echo "MODE not specified, use default $MODE"
+fi
+
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 
@@ -55,6 +61,10 @@ 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"
 
 # Default to NOT use Hint
 if [ -z "$USE_HINT_TEXT" ]; then
@@ -74,9 +84,13 @@ fi
 if [ -n "$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
 
 function run_eval() {
-  local eval_note=$1
+  local eval_note="${1}"
   COMMAND="poetry run python evaluation/benchmarks/swe_bench/run_infer.py \
     --agent-cls $AGENT \
     --llm-config $MODEL_CONFIG \
@@ -84,7 +98,8 @@ function run_eval() {
     --eval-num-workers $NUM_WORKERS \
     --eval-note $eval_note \
     --dataset $DATASET \
-    --split $SPLIT"
+    --split $SPLIT \
+    --mode $MODE"
 
   if [ -n "$EVAL_LIMIT" ]; then
     echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/swe_bench/scripts/swtbench/convert.py

@@ -0,0 +1,95 @@
+import argparse
+import json
+import logging
+
+import unidiff
+
+from evaluation.benchmarks.swe_bench.resource.swt_bench_constants import (
+    MAP_VERSION_TO_INSTALL,
+)
+
+_LOGGER = logging.getLogger(__name__)
+
+
+def remove_setup_files(model_patch: str, instance: dict, delete_setup_changes: bool):
+    """Discard all changes that a patch applies to files changes by the pre_install script and that are reproduction scripts (top-level script)"""
+    setup_files = ['setup.py', 'tox.ini', 'pyproject.toml']
+    pre_install = (
+        MAP_VERSION_TO_INSTALL.get(instance['repo'], {})
+        .get(instance['version'], {})
+        .get('pre_install', [])
+    )
+    relevant_files = (
+        [
+            file
+            for file in setup_files
+            if any(file in install and 'sed' in install for install in pre_install)
+        ]
+        if delete_setup_changes
+        else []
+    )
+    for i in range(10):
+        try:
+            # Appearently outputs.jsonl has .strip() applied, so we try to reconstruct the original patch by adding auxiliary whitespace
+            patch = unidiff.PatchSet(model_patch + i * '\n')
+            break
+        except unidiff.UnidiffParseError:
+            pass
+
+    to_delete = []
+    for i, file in enumerate(patch):
+        if (
+            any(f in file.source_file for f in relevant_files)
+            or file.target_file.count('/') == 1
+        ):
+            to_delete.append(i)
+    for i in reversed(to_delete):
+        del patch[i]
+    return str(patch)
+
+
+def main(
+    prediction_file: str,
+):
+    """Main function to extract the model patches from the OpenHands prediction file and turn them into the expected SWT-Bench format."""
+    with open(prediction_file) as f:
+        for line in f:
+            pred = json.loads(line)
+            try:
+                git_diff = pred['test_result']['git_patch']
+            except KeyError:
+                _LOGGER.warning(
+                    'Warning: No git diff found for instance %s', pred['instance_id']
+                )
+                continue
+            ci_mode = pred['metadata']['details'].get('mode', '') == 'swt-ci'
+            try:
+                git_diff = remove_setup_files(git_diff, pred['instance'], ci_mode)
+            except:  # noqa: E722
+                _LOGGER.warning(
+                    'Warning: Invalid git diff found for instance %s',
+                    pred['instance_id'],
+                )
+            print(
+                json.dumps(
+                    {
+                        'instance_id': pred['instance_id'],
+                        'model_name_or_path': f'{pred["metadata"]["llm_config"]["openrouter_app_name"]}__{pred["metadata"]["agent_class"]}__{pred["metadata"]["llm_config"]["model"]}',
+                        'model_patch': git_diff,
+                        'full_output': json.dumps(pred),
+                    }
+                )
+            )
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--prediction_file',
+        type=str,
+        required=True,
+        help='Path to the prediction file (.../outputs.jsonl)',
+    )
+    args = parser.parse_args()
+
+    main(args.prediction_file)

frontend/.husky/pre-commit

@@ -1,3 +1,10 @@
+# Run frontend checks
+echo "Running frontend checks..."
 cd frontend
 npm run check-unlocalized-strings
 npx lint-staged
+
+# Run backend pre-commit
+echo "Running backend pre-commit..."
+cd ..
+pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

frontend/__tests__/components/chat/chat-input.test.tsx

@@ -223,7 +223,7 @@ describe("ChatInput", () => {
     render(<ChatInput onSubmit={onSubmitMock} />);
     const textarea = screen.getByRole("textbox");
     expect(textarea).toBeInTheDocument();
-    
+
     // The actual verification of maxRows=16 is handled internally by the TextareaAutosize component
     // and affects how many rows the textarea can expand to
   });

frontend/__tests__/components/chat/chat-interface.test.tsx

@@ -1,8 +1,8 @@
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
-import type { Message } from "#/message";
 import { act, screen, waitFor, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { renderWithProviders } from "test-utils";
+import type { Message } from "#/message";
 import { addUserMessage } from "#/state/chat-slice";
 import { SUGGESTIONS } from "#/utils/suggestions";
 import * as ChatSlice from "#/state/chat-slice";
@@ -45,7 +45,15 @@ describe("Empty state", () => {
   it("should render suggestions if empty", () => {
     const { store } = renderWithProviders(<ChatInterface />, {
       preloadedState: {
-        chat: { messages: [] },
+        chat: {
+          messages: [],
+          systemMessage: {
+            content: "",
+            tools: [],
+            openhands_version: null,
+            agent_class: null
+          }
+        },
       },
     });
 
@@ -68,7 +76,15 @@ describe("Empty state", () => {
   it("should render the default suggestions", () => {
     renderWithProviders(<ChatInterface />, {
       preloadedState: {
-        chat: { messages: [] },
+        chat: {
+          messages: [],
+          systemMessage: {
+            content: "",
+            tools: [],
+            openhands_version: null,
+            agent_class: null
+          }
+        },
       },
     });
 
@@ -98,7 +114,15 @@ describe("Empty state", () => {
       const user = userEvent.setup();
       const { store } = renderWithProviders(<ChatInterface />, {
         preloadedState: {
-          chat: { messages: [] },
+          chat: {
+            messages: [],
+            systemMessage: {
+              content: "",
+              tools: [],
+              openhands_version: null,
+              agent_class: null
+            }
+          },
         },
       });
 
@@ -127,7 +151,15 @@ describe("Empty state", () => {
       const user = userEvent.setup();
       const { rerender } = renderWithProviders(<ChatInterface />, {
         preloadedState: {
-          chat: { messages: [] },
+          chat: {
+            messages: [],
+            systemMessage: {
+              content: "",
+              tools: [],
+              openhands_version: null,
+              agent_class: null
+            }
+          },
         },
       });
 

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

@@ -95,6 +95,23 @@ describe("ExpandableMessage", () => {
     expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
   });
 
+  it("should render with neutral border and no icon for action messages with undefined success (timeout case)", () => {
+    renderWithProviders(
+      <ExpandableMessage
+        id="OBSERVATION_MESSAGE$RUN"
+        message="Command timed out"
+        type="action"
+        success={undefined}
+      />,
+    );
+    const element = screen.getByText("OBSERVATION_MESSAGE$RUN");
+    const container = element.closest(
+      "div.flex.gap-2.items-center.justify-start",
+    );
+    expect(container).toHaveClass("border-neutral-300");
+    expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
+  });
+
   it("should render the out of credits message when the user is out of credits", async () => {
     const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     // @ts-expect-error - We only care about the APP_MODE and FEATURE_FLAGS fields

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

@@ -3,34 +3,46 @@ import { it, describe, expect, vi, beforeAll, afterAll } from "vitest";
 import userEvent from "@testing-library/user-event";
 import { AuthModal } from "#/components/features/waitlist/auth-modal";
 import * as CaptureConsent from "#/utils/handle-capture-consent";
+import * as AuthHook from "#/context/auth-context";
 
 describe("AuthModal", () => {
   beforeAll(() => {
     vi.stubGlobal("location", { href: "" });
+    vi.spyOn(AuthHook, "useAuth").mockReturnValue({
+      providersAreSet: false,
+      setProvidersAreSet: vi.fn(),
+      providerTokensSet: [],
+      setProviderTokensSet: vi.fn()
+    });
   });
 
   afterAll(() => {
     vi.unstubAllGlobals();
+    vi.restoreAllMocks();
   });
 
   it("should render a tos checkbox that is unchecked by default", () => {
-    render(<AuthModal githubAuthUrl={null} />);
+    render(<AuthModal githubAuthUrl={null} appMode="saas" />);
     const checkbox = screen.getByRole("checkbox");
 
     expect(checkbox).not.toBeChecked();
   });
 
-  it("should only enable the GitHub button if the tos checkbox is checked", async () => {
+  it("should only enable the identity provider buttons if the tos checkbox is checked", async () => {
     const user = userEvent.setup();
-    render(<AuthModal githubAuthUrl={null} />);
-    const checkbox = screen.getByRole("checkbox");
-    const button = screen.getByRole("button", { name: "GITHUB$CONNECT_TO_GITHUB" });
+    render(<AuthModal githubAuthUrl={null} appMode="saas" />);
 
-    expect(button).toBeDisabled();
+    const checkbox = screen.getByRole("checkbox");
+    const githubButton = screen.getByRole("button", { name: "GITHUB$CONNECT_TO_GITHUB" });
+    const gitlabButton = screen.getByRole("button", { name: "GITLAB$CONNECT_TO_GITLAB" });
+
+    expect(githubButton).toBeDisabled();
+    expect(gitlabButton).toBeDisabled();
 
     await user.click(checkbox);
 
-    expect(button).not.toBeDisabled();
+    expect(githubButton).not.toBeDisabled();
+    expect(gitlabButton).not.toBeDisabled();
   });
 
   it("should set user analytics consent to true when the user checks the tos checkbox", async () => {
@@ -40,7 +52,7 @@ describe("AuthModal", () => {
     );
 
     const user = userEvent.setup();
-    render(<AuthModal githubAuthUrl="mock-url" />);
+    render(<AuthModal githubAuthUrl="mock-url" appMode="saas" />);
 
     const checkbox = screen.getByRole("checkbox");
     await user.click(checkbox);

frontend/__tests__/components/features/git/git-repo-selector.test.tsx

@@ -56,12 +56,16 @@ describe("GitRepositorySelector", () => {
         full_name: "test/repo1",
         git_provider: "github" as Provider,
         stargazers_count: 100,
+        is_public: true,
+        pushed_at: "2023-01-01T00:00:00Z",
       },
       {
         id: 2,
         full_name: "test/repo2",
         git_provider: "github" as Provider,
         stargazers_count: 200,
+        is_public: true,
+        pushed_at: "2023-01-02T00:00:00Z",
       },
     ];
 

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

@@ -0,0 +1,72 @@
+import { QueryClientProvider, QueryClient } from "@tanstack/react-query";
+import { render, screen } from "@testing-library/react";
+import { Provider } from "react-redux";
+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 { AuthProvider } from "#/context/auth-context";
+import { HomeHeader } from "#/components/features/home/home-header";
+import OpenHands from "#/api/open-hands";
+
+const renderHomeHeader = () => {
+  const RouterStub = createRoutesStub([
+    {
+      Component: HomeHeader,
+      path: "/",
+    },
+    {
+      Component: () => <div data-testid="conversation-screen" />,
+      path: "/conversations/:conversationId",
+    },
+  ]);
+
+  return render(<RouterStub />, {
+    wrapper: ({ children }) => (
+      <Provider store={setupStore()}>
+        <AuthProvider initialProvidersAreSet>
+          <QueryClientProvider client={new QueryClient()}>
+            {children}
+          </QueryClientProvider>
+        </AuthProvider>
+      </Provider>
+    ),
+  });
+};
+
+describe("HomeHeader", () => {
+  it("should create an empty conversation and redirect when pressing the launch from scratch button", async () => {
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
+
+    renderHomeHeader();
+
+    const launchButton = screen.getByRole("button", {
+      name: /launch from scratch/i,
+    });
+    await userEvent.click(launchButton);
+
+    expect(createConversationSpy).toHaveBeenCalledExactlyOnceWith(
+      "gui",
+      undefined,
+      undefined,
+      [],
+      undefined,
+      undefined,
+    );
+
+    // expect to be redirected to /conversations/:conversationId
+    await screen.findByTestId("conversation-screen");
+  });
+
+  it("should change the launch button text to 'Loading...' when creating a conversation", async () => {
+    renderHomeHeader();
+
+    const launchButton = screen.getByRole("button", {
+      name: /launch from scratch/i,
+    });
+    await userEvent.click(launchButton);
+
+    expect(launchButton).toHaveTextContent(/Loading/i);
+    expect(launchButton).toBeDisabled();
+  });
+});

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

@@ -0,0 +1,231 @@
+import { render, screen, waitFor, within } from "@testing-library/react";
+import { describe, expect, it, vi } from "vitest";
+import userEvent from "@testing-library/user-event";
+import { QueryClientProvider, QueryClient } from "@tanstack/react-query";
+import { setupStore } from "test-utils";
+import { Provider } from "react-redux";
+import { createRoutesStub } from "react-router";
+import OpenHands from "#/api/open-hands";
+import { AuthProvider } from "#/context/auth-context";
+import { GitRepository } from "#/types/git";
+import * as GitService from "#/api/git";
+import { RepoConnector } from "#/components/features/home/repo-connector";
+
+const renderRepoConnector = (initialProvidersAreSet = true) => {
+  const mockRepoSelection = vi.fn();
+  const RouterStub = createRoutesStub([
+    {
+      Component: () => <RepoConnector onRepoSelection={mockRepoSelection} />,
+      path: "/",
+    },
+    {
+      Component: () => <div data-testid="conversation-screen" />,
+      path: "/conversations/:conversationId",
+    },
+    {
+      Component: () => <div data-testid="settings-screen" />,
+      path: "/settings",
+    },
+  ]);
+
+  return render(<RouterStub />, {
+    wrapper: ({ children }) => (
+      <Provider store={setupStore()}>
+        <AuthProvider initialProvidersAreSet={initialProvidersAreSet}>
+          <QueryClientProvider client={new QueryClient()}>
+            {children}
+          </QueryClientProvider>
+        </AuthProvider>
+      </Provider>
+    ),
+  });
+};
+
+const MOCK_RESPOSITORIES: GitRepository[] = [
+  {
+    id: 1,
+    full_name: "rbren/polaris",
+    git_provider: "github",
+    is_public: true,
+  },
+  {
+    id: 2,
+    full_name: "All-Hands-AI/OpenHands",
+    git_provider: "github",
+    is_public: true,
+  },
+];
+
+describe("RepoConnector", () => {
+  it("should render the repository connector section", () => {
+    renderRepoConnector();
+    screen.getByTestId("repo-connector");
+  });
+
+  it("should render the available repositories in the dropdown", async () => {
+    const retrieveUserGitRepositoriesSpy = vi.spyOn(
+      GitService,
+      "retrieveUserGitRepositories",
+    );
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
+
+    renderRepoConnector();
+
+    // Wait for the loading state to be replaced with the dropdown
+    const dropdown = await waitFor(() => screen.getByTestId("repo-dropdown"));
+    await userEvent.click(dropdown);
+
+    await waitFor(() => {
+      screen.getByText("rbren/polaris");
+      screen.getByText("All-Hands-AI/OpenHands");
+    });
+  });
+
+  it("should only enable the launch button if a repo is selected", async () => {
+    const retrieveUserGitRepositoriesSpy = vi.spyOn(
+      GitService,
+      "retrieveUserGitRepositories",
+    );
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
+
+    renderRepoConnector();
+
+    const launchButton = screen.getByTestId("repo-launch-button");
+    expect(launchButton).toBeDisabled();
+
+    // Wait for the loading state to be replaced with the dropdown
+    const dropdown = await waitFor(() => screen.getByTestId("repo-dropdown"));
+    await userEvent.click(dropdown);
+    await userEvent.click(screen.getByText("rbren/polaris"));
+
+    expect(launchButton).toBeEnabled();
+  });
+
+  it("should render the 'add git(hub|lab) repos' links if saas mode", async () => {
+    const getConfiSpy = vi.spyOn(OpenHands, "getConfig");
+    // @ts-expect-error - only return the APP_MODE
+    getConfiSpy.mockResolvedValue({
+      APP_MODE: "saas",
+    });
+
+    renderRepoConnector();
+
+    await screen.findByText("Add GitHub repos");
+  });
+
+  it("should not render the 'add git(hub|lab) repos' links if oss mode", async () => {
+    const getConfiSpy = vi.spyOn(OpenHands, "getConfig");
+    // @ts-expect-error - only return the APP_MODE
+    getConfiSpy.mockResolvedValue({
+      APP_MODE: "oss",
+    });
+
+    renderRepoConnector();
+
+    expect(screen.queryByText("Add GitHub repos")).not.toBeInTheDocument();
+    expect(screen.queryByText("Add GitLab repos")).not.toBeInTheDocument();
+  });
+
+  it("should create a conversation and redirect with the selected repo when pressing the launch button", async () => {
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
+    const retrieveUserGitRepositoriesSpy = vi.spyOn(
+      GitService,
+      "retrieveUserGitRepositories",
+    );
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
+
+    renderRepoConnector();
+
+    const repoConnector = screen.getByTestId("repo-connector");
+    const launchButton =
+      within(repoConnector).getByTestId("repo-launch-button");
+    await userEvent.click(launchButton);
+
+    // repo not selected yet
+    expect(createConversationSpy).not.toHaveBeenCalled();
+
+    // select a repository from the dropdown
+    const dropdown = await waitFor(() =>
+      within(repoConnector).getByTestId("repo-dropdown"),
+    );
+    await userEvent.click(dropdown);
+
+    const repoOption = screen.getByText("rbren/polaris");
+    await userEvent.click(repoOption);
+    await userEvent.click(launchButton);
+
+    expect(createConversationSpy).toHaveBeenCalledExactlyOnceWith(
+      "gui",
+      {
+        full_name: "rbren/polaris",
+        git_provider: "github",
+        id: 1,
+        is_public: true,
+      },
+      undefined,
+      [],
+      undefined,
+      undefined,
+    );
+  });
+
+  it("should change the launch button text to 'Loading...' when creating a conversation", async () => {
+    const retrieveUserGitRepositoriesSpy = vi.spyOn(
+      GitService,
+      "retrieveUserGitRepositories",
+    );
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
+
+    renderRepoConnector();
+
+    const launchButton = screen.getByTestId("repo-launch-button");
+
+    // Wait for the loading state to be replaced with the dropdown
+    const dropdown = await waitFor(() => screen.getByTestId("repo-dropdown"));
+    await userEvent.click(dropdown);
+    await userEvent.click(screen.getByText("rbren/polaris"));
+
+    await userEvent.click(launchButton);
+    expect(launchButton).toBeDisabled();
+    expect(launchButton).toHaveTextContent(/Loading/i);
+  });
+
+  it("should not display a button to settings if the user is signed in with their git provider", async () => {
+    renderRepoConnector(true);
+    expect(
+      screen.queryByTestId("navigate-to-settings-button"),
+    ).not.toBeInTheDocument();
+  });
+
+  it("should display a button to settings if the user needs to sign in with their git provider", async () => {
+    renderRepoConnector(false);
+
+    const goToSettingsButton = await screen.findByTestId(
+      "navigate-to-settings-button",
+    );
+    const dropdown = screen.queryByTestId("repo-dropdown");
+    const launchButton = screen.queryByTestId("repo-launch-button");
+    const providerLinks = screen.queryAllByText(/add git(hub|lab) repos/i);
+
+    expect(dropdown).not.toBeInTheDocument();
+    expect(launchButton).not.toBeInTheDocument();
+    expect(providerLinks.length).toBe(0);
+
+    expect(goToSettingsButton).toBeInTheDocument();
+
+    await userEvent.click(goToSettingsButton);
+    await screen.findByTestId("settings-screen");
+  });
+});

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

@@ -0,0 +1,138 @@
+import { render, screen } from "@testing-library/react";
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
+import userEvent from "@testing-library/user-event";
+import { Provider } from "react-redux";
+import { createRoutesStub } from "react-router";
+import { setupStore } from "test-utils";
+import { SuggestedTask } from "#/components/features/home/tasks/task.types";
+import OpenHands from "#/api/open-hands";
+import { AuthProvider } from "#/context/auth-context";
+import { TaskCard } from "#/components/features/home/tasks/task-card";
+import * as GitService from "#/api/git";
+import { GitRepository } from "#/types/git";
+
+const MOCK_TASK_1: SuggestedTask = {
+  issue_number: 123,
+  repo: "repo1",
+  title: "Task 1",
+  task_type: "MERGE_CONFLICTS",
+  git_provider: "github",
+};
+
+const MOCK_TASK_2: SuggestedTask = {
+  issue_number: 456,
+  repo: "repo2",
+  title: "Task 2",
+  task_type: "FAILING_CHECKS",
+  git_provider: "github",
+};
+
+const MOCK_TASK_3: SuggestedTask = {
+  issue_number: 789,
+  repo: "repo3",
+  title: "Task 3",
+  task_type: "UNRESOLVED_COMMENTS",
+  git_provider: "gitlab",
+};
+
+const MOCK_TASK_4: SuggestedTask = {
+  issue_number: 101112,
+  repo: "repo4",
+  title: "Task 4",
+  task_type: "OPEN_ISSUE",
+  git_provider: "gitlab",
+};
+
+const MOCK_RESPOSITORIES: GitRepository[] = [
+  { id: 1, full_name: "repo1", git_provider: "github", is_public: true },
+  { id: 2, full_name: "repo2", git_provider: "github", is_public: true },
+  { id: 3, full_name: "repo3", git_provider: "gitlab", is_public: true },
+  { id: 4, full_name: "repo4", git_provider: "gitlab", is_public: true },
+];
+
+const renderTaskCard = (task = MOCK_TASK_1) => {
+  const RouterStub = createRoutesStub([
+    {
+      Component: () => <TaskCard task={task} />,
+      path: "/",
+    },
+    {
+      Component: () => <div data-testid="conversation-screen" />,
+      path: "/conversations/:conversationId",
+    },
+  ]);
+
+  return render(<RouterStub />, {
+    wrapper: ({ children }) => (
+      <Provider store={setupStore()}>
+        <AuthProvider initialProvidersAreSet>
+          <QueryClientProvider client={new QueryClient()}>
+            {children}
+          </QueryClientProvider>
+        </AuthProvider>
+      </Provider>
+    ),
+  });
+};
+
+describe("TaskCard", () => {
+  it("format the issue id", async () => {
+    renderTaskCard();
+
+    const taskId = screen.getByTestId("task-id");
+    expect(taskId).toHaveTextContent(/#123/i);
+  });
+
+  it("should call createConversation when clicking the launch button", async () => {
+    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
+
+    renderTaskCard();
+
+    const launchButton = screen.getByTestId("task-launch-button");
+    await userEvent.click(launchButton);
+
+    expect(createConversationSpy).toHaveBeenCalled();
+  });
+
+  describe("creating suggested task conversation", () => {
+    beforeEach(() => {
+      const retrieveUserGitRepositoriesSpy = vi.spyOn(
+        GitService,
+        "retrieveUserGitRepositories",
+      );
+      retrieveUserGitRepositoriesSpy.mockResolvedValue({
+        data: MOCK_RESPOSITORIES,
+        nextPage: null,
+      });
+    });
+
+    it("should call create conversation with suggest task trigger and selected suggested task", async () => {
+      const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
+
+      renderTaskCard(MOCK_TASK_1);
+
+      const launchButton = screen.getByTestId("task-launch-button");
+      await userEvent.click(launchButton);
+
+      expect(createConversationSpy).toHaveBeenCalledWith(
+        "suggested_task",
+        MOCK_RESPOSITORIES[0],
+        undefined,
+        [],
+        undefined,
+        MOCK_TASK_1,
+      );
+    });
+  });
+
+  it("should disable the launch button and update text content when creating a conversation", async () => {
+    renderTaskCard();
+
+    const launchButton = screen.getByTestId("task-launch-button");
+    await userEvent.click(launchButton);
+
+    expect(launchButton).toHaveTextContent(/Loading/i);
+    expect(launchButton).toBeDisabled();
+  });
+});

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

@@ -0,0 +1,113 @@
+import { render, screen, waitFor } from "@testing-library/react";
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
+import { Provider } from "react-redux";
+import { createRoutesStub } from "react-router";
+import { setupStore } from "test-utils";
+import userEvent from "@testing-library/user-event";
+import { TaskSuggestions } from "#/components/features/home/tasks/task-suggestions";
+import { SuggestionsService } from "#/api/suggestions-service/suggestions-service.api";
+import { MOCK_TASKS } from "#/mocks/task-suggestions-handlers";
+import { AuthProvider } from "#/context/auth-context";
+
+const renderTaskSuggestions = (initialProvidersAreSet = true) => {
+  const RouterStub = createRoutesStub([
+    {
+      Component: TaskSuggestions,
+      path: "/",
+    },
+    {
+      Component: () => <div data-testid="conversation-screen" />,
+      path: "/conversations/:conversationId",
+    },
+    {
+      Component: () => <div data-testid="settings-screen" />,
+      path: "/settings",
+    },
+  ]);
+
+  return render(<RouterStub />, {
+    wrapper: ({ children }) => (
+      <Provider store={setupStore()}>
+        <AuthProvider initialProvidersAreSet={initialProvidersAreSet}>
+          <QueryClientProvider client={new QueryClient()}>
+            {children}
+          </QueryClientProvider>
+        </AuthProvider>
+      </Provider>
+    ),
+  });
+};
+
+describe("TaskSuggestions", () => {
+  const getSuggestedTasksSpy = vi.spyOn(
+    SuggestionsService,
+    "getSuggestedTasks",
+  );
+
+  afterEach(() => {
+    vi.clearAllMocks();
+  });
+
+  it("should render the task suggestions section", () => {
+    renderTaskSuggestions();
+    screen.getByTestId("task-suggestions");
+  });
+
+  it("should render an empty message if there are no tasks", async () => {
+    getSuggestedTasksSpy.mockResolvedValue([]);
+    renderTaskSuggestions();
+    await screen.findByText(/No tasks available/i);
+  });
+
+  it("should render the task groups with the correct titles", async () => {
+    getSuggestedTasksSpy.mockResolvedValue(MOCK_TASKS);
+    renderTaskSuggestions();
+
+    await waitFor(() => {
+      MOCK_TASKS.forEach((taskGroup) => {
+        screen.getByText(taskGroup.title);
+      });
+    });
+  });
+
+  it("should render the task cards with the correct task details", async () => {
+    getSuggestedTasksSpy.mockResolvedValue(MOCK_TASKS);
+    renderTaskSuggestions();
+
+    await waitFor(() => {
+      MOCK_TASKS.forEach((task) => {
+        screen.getByText(task.title);
+      });
+    });
+  });
+
+  it("should render skeletons when loading", async () => {
+    getSuggestedTasksSpy.mockResolvedValue(MOCK_TASKS);
+    renderTaskSuggestions();
+
+    const skeletons = screen.getAllByTestId("task-group-skeleton");
+    expect(skeletons.length).toBeGreaterThan(0);
+
+    await waitFor(() => {
+      MOCK_TASKS.forEach((taskGroup) => {
+        screen.getByText(taskGroup.title);
+      });
+    });
+
+    expect(screen.queryByTestId("task-group-skeleton")).not.toBeInTheDocument();
+  });
+
+  it("should display a button to settings if the user needs to sign in with their git provider", async () => {
+    renderTaskSuggestions(false);
+
+    expect(getSuggestedTasksSpy).not.toHaveBeenCalled();
+    const goToSettingsButton = await screen.findByTestId(
+      "navigate-to-settings-button",
+    );
+    expect(goToSettingsButton).toBeInTheDocument();
+
+    await userEvent.click(goToSettingsButton);
+    await screen.findByTestId("settings-screen");
+  });
+});

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

@@ -61,25 +61,25 @@ describe("PaymentForm", () => {
     renderPaymentForm();
 
     const topUpInput = await screen.findByTestId("top-up-input");
-    await user.type(topUpInput, "50.12");
+    await user.type(topUpInput, "50");
 
     const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
     await user.click(topUpButton);
 
-    expect(createCheckoutSessionSpy).toHaveBeenCalledWith(50.12);
+    expect(createCheckoutSessionSpy).toHaveBeenCalledWith(50);
   });
 
-  it("should round the top-up amount to two decimal places", async () => {
+  it("should only accept integer values", async () => {
     const user = userEvent.setup();
     renderPaymentForm();
 
     const topUpInput = await screen.findByTestId("top-up-input");
-    await user.type(topUpInput, "50.125456");
+    await user.type(topUpInput, "50");
 
     const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
     await user.click(topUpButton);
 
-    expect(createCheckoutSessionSpy).toHaveBeenCalledWith(50.13);
+    expect(createCheckoutSessionSpy).toHaveBeenCalledWith(50);
   });
 
   it("should disable the top-up button if the user enters an invalid amount", async () => {
@@ -100,7 +100,7 @@ describe("PaymentForm", () => {
     renderPaymentForm();
 
     const topUpInput = await screen.findByTestId("top-up-input");
-    await user.type(topUpInput, "50.12");
+    await user.type(topUpInput, "50");
 
     const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
     await user.click(topUpButton);
@@ -114,7 +114,7 @@ describe("PaymentForm", () => {
       renderPaymentForm();
 
       const topUpInput = await screen.findByTestId("top-up-input");
-      await user.type(topUpInput, "-50.12");
+      await user.type(topUpInput, "-50");
 
       const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
       await user.click(topUpButton);
@@ -139,6 +139,8 @@ describe("PaymentForm", () => {
       const user = userEvent.setup();
       renderPaymentForm();
 
+      // With type="number", the browser would prevent non-numeric input,
+      // but we'll test the validation logic anyway
       const topUpInput = await screen.findByTestId("top-up-input");
       await user.type(topUpInput, "abc");
 
@@ -160,5 +162,19 @@ describe("PaymentForm", () => {
 
       expect(createCheckoutSessionSpy).not.toHaveBeenCalled();
     });
+
+    test("user enters a decimal value", async () => {
+      const user = userEvent.setup();
+      renderPaymentForm();
+
+      // With step="1", the browser would validate this, but we'll test our validation logic
+      const topUpInput = await screen.findByTestId("top-up-input");
+      await user.type(topUpInput, "50.5");
+
+      const topUpButton = screen.getByText("PAYMENT$ADD_CREDIT");
+      await user.click(topUpButton);
+
+      expect(createCheckoutSessionSpy).not.toHaveBeenCalled();
+    });
   });
 });

frontend/__tests__/components/file-explorer/explorer-tree.test.tsx

@@ -1,28 +0,0 @@
-import { screen } from "@testing-library/react";
-import { renderWithProviders } from "test-utils";
-import { describe, afterEach, vi, it, expect } from "vitest";
-import { ExplorerTree } from "#/components/features/file-explorer/explorer-tree";
-
-const FILES = ["file-1-1.ts", "folder-1-2"];
-
-describe.skip("ExplorerTree", () => {
-  afterEach(() => {
-    vi.resetAllMocks();
-  });
-
-  it("should render the explorer", () => {
-    renderWithProviders(<ExplorerTree files={FILES} defaultOpen />);
-
-    expect(screen.getByText("file-1-1.ts")).toBeInTheDocument();
-    expect(screen.getByText("folder-1-2")).toBeInTheDocument();
-    // TODO: make sure children render
-  });
-
-  it("should render the explorer given the defaultExpanded prop", () => {
-    renderWithProviders(<ExplorerTree files={FILES} />);
-
-    expect(screen.queryByText("file-1-1.ts")).toBeInTheDocument();
-    expect(screen.queryByText("folder-1-2")).toBeInTheDocument();
-    // TODO: make sure children don't render
-  });
-});

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

@@ -1,64 +0,0 @@
-import { screen } from "@testing-library/react";
-import userEvent from "@testing-library/user-event";
-import { renderWithProviders } from "test-utils";
-import { describe, it, expect, vi, afterEach } from "vitest";
-import { AgentState } from "#/types/agent-state";
-import { FileExplorer } from "#/components/features/file-explorer/file-explorer";
-import { FileService } from "#/api/file-service/file-service.api";
-
-const getFilesSpy = vi.spyOn(FileService, "getFiles");
-
-vi.mock("../../services/fileService", async () => ({
-  uploadFiles: vi.fn(),
-}));
-
-const renderFileExplorerWithRunningAgentState = () =>
-  renderWithProviders(<FileExplorer isOpen onToggle={() => {}} />, {
-    preloadedState: {
-      agent: {
-        curAgentState: AgentState.RUNNING,
-      },
-    },
-  });
-
-describe.skip("FileExplorer", () => {
-  afterEach(() => {
-    vi.clearAllMocks();
-  });
-
-  it("should get the workspace directory", async () => {
-    renderFileExplorerWithRunningAgentState();
-
-    expect(await screen.findByText("folder1")).toBeInTheDocument();
-    expect(await screen.findByText("file1.ts")).toBeInTheDocument();
-    expect(getFilesSpy).toHaveBeenCalledTimes(1); // once for root
-  });
-
-  it("should refetch the workspace when clicking the refresh button", async () => {
-    const user = userEvent.setup();
-    renderFileExplorerWithRunningAgentState();
-
-    expect(await screen.findByText("folder1")).toBeInTheDocument();
-    expect(await screen.findByText("file1.ts")).toBeInTheDocument();
-    expect(getFilesSpy).toHaveBeenCalledTimes(1); // once for root
-
-    const refreshButton = screen.getByTestId("refresh");
-    await user.click(refreshButton);
-
-    expect(getFilesSpy).toHaveBeenCalledTimes(2); // once for root, once for refresh button
-  });
-
-  it("should toggle the explorer visibility when clicking the toggle button", async () => {
-    const user = userEvent.setup();
-    renderFileExplorerWithRunningAgentState();
-
-    const folder1 = await screen.findByText("folder1");
-    expect(folder1).toBeInTheDocument();
-
-    const toggleButton = screen.getByTestId("toggle");
-    await user.click(toggleButton);
-
-    expect(folder1).toBeInTheDocument();
-    expect(folder1).not.toBeVisible();
-  });
-});

frontend/__tests__/components/file-explorer/tree-node.test.tsx

@@ -1,110 +0,0 @@
-import { screen } from "@testing-library/react";
-import userEvent from "@testing-library/user-event";
-import { renderWithProviders } from "test-utils";
-import { vi, describe, afterEach, it, expect } from "vitest";
-import TreeNode from "#/components/features/file-explorer/tree-node";
-import { FileService } from "#/api/file-service/file-service.api";
-
-const getFileSpy = vi.spyOn(FileService, "getFile");
-const getFilesSpy = vi.spyOn(FileService, "getFiles");
-
-vi.mock("../../services/fileService", async () => ({
-  uploadFile: vi.fn(),
-}));
-
-describe.skip("TreeNode", () => {
-  afterEach(() => {
-    vi.clearAllMocks();
-  });
-
-  it("should render a file if property has no children", () => {
-    renderWithProviders(<TreeNode path="/file.ts" defaultOpen />);
-    expect(screen.getByText("file.ts")).toBeInTheDocument();
-  });
-
-  it("should render a folder if it's in a subdir", async () => {
-    renderWithProviders(<TreeNode path="/folder1/" defaultOpen />);
-    expect(getFilesSpy).toHaveBeenCalledWith("/folder1/");
-
-    expect(await screen.findByText("folder1")).toBeInTheDocument();
-    expect(await screen.findByText("file2.ts")).toBeInTheDocument();
-  });
-
-  it("should close a folder when clicking on it", async () => {
-    const user = userEvent.setup();
-    renderWithProviders(<TreeNode path="/folder1/" defaultOpen />);
-
-    const folder1 = await screen.findByText("folder1");
-    const file2 = await screen.findByText("file2.ts");
-
-    expect(folder1).toBeInTheDocument();
-    expect(file2).toBeInTheDocument();
-
-    await user.click(folder1);
-
-    expect(folder1).toBeInTheDocument();
-    expect(screen.queryByText("file2.ts")).not.toBeInTheDocument();
-  });
-
-  it("should open a folder when clicking on it", async () => {
-    const user = userEvent.setup();
-    renderWithProviders(<TreeNode path="/folder1/" />);
-
-    const folder1 = await screen.findByText("folder1");
-
-    expect(folder1).toBeInTheDocument();
-    expect(screen.queryByText("file2.ts")).not.toBeInTheDocument();
-
-    await user.click(folder1);
-    expect(getFilesSpy).toHaveBeenCalledWith("/folder1/");
-
-    expect(folder1).toBeInTheDocument();
-    expect(await screen.findByText("file2.ts")).toBeInTheDocument();
-  });
-
-  it("should call `OpenHands.getFile` and return the full path of a file when clicking on a file", async () => {
-    const user = userEvent.setup();
-    renderWithProviders(<TreeNode path="/folder1/file2.ts" defaultOpen />);
-
-    const file2 = screen.getByText("file2.ts");
-    await user.click(file2);
-
-    expect(getFileSpy).toHaveBeenCalledWith("/folder1/file2.ts");
-  });
-
-  it("should render the full explorer given the defaultOpen prop", async () => {
-    const user = userEvent.setup();
-    renderWithProviders(<TreeNode path="/" defaultOpen />);
-
-    expect(getFilesSpy).toHaveBeenCalledWith("/");
-
-    const file1 = await screen.findByText("file1.ts");
-    const folder1 = await screen.findByText("folder1");
-
-    expect(file1).toBeInTheDocument();
-    expect(folder1).toBeInTheDocument();
-    expect(screen.queryByText("file2.ts")).not.toBeInTheDocument();
-
-    await user.click(folder1);
-    expect(getFilesSpy).toHaveBeenCalledWith("folder1/");
-
-    expect(file1).toBeInTheDocument();
-    expect(folder1).toBeInTheDocument();
-    expect(await screen.findByText("file2.ts")).toBeInTheDocument();
-  });
-
-  it("should render all children as collapsed when defaultOpen is false", async () => {
-    renderWithProviders(<TreeNode path="/folder1/" defaultOpen={false} />);
-
-    const folder1 = await screen.findByText("folder1");
-
-    expect(folder1).toBeInTheDocument();
-    expect(screen.queryByText("file2.ts")).not.toBeInTheDocument();
-
-    await userEvent.click(folder1);
-    expect(getFilesSpy).toHaveBeenCalledWith("/folder1/");
-
-    expect(folder1).toBeInTheDocument();
-    expect(await screen.findByText("file2.ts")).toBeInTheDocument();
-  });
-});

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

@@ -1,9 +1,18 @@
 import { render, screen } from "@testing-library/react";
-import { describe, it, expect } from "vitest";
+import { describe, it, expect, vi } from "vitest";
 import { Messages } from "#/components/features/chat/messages";
 import type { Message } from "#/message";
 import { renderWithProviders } from "test-utils";
 
+// Mock the useParams hook to provide a conversationId
+vi.mock("react-router", async () => {
+  const actual = await vi.importActual<typeof import("react-router")>("react-router");
+  return {
+    ...actual,
+    useParams: () => ({ conversationId: "test-conversation-id" }),
+  };
+});
+
 describe("File Operations Messages", () => {
   it("should show success indicator for successful file read operation", () => {
     const messages: Message[] = [

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

@@ -5,7 +5,7 @@ import { Command, appendInput, appendOutput } from "#/state/command-slice";
 import Terminal from "#/components/features/terminal/terminal";
 
 const renderTerminal = (commands: Command[] = []) =>
-  renderWithProviders(<Terminal secrets={[]} />, {
+  renderWithProviders(<Terminal />, {
     preloadedState: {
       cmd: {
         commands,
@@ -121,7 +121,7 @@ describe.skip("Terminal", () => {
 
   // This test fails because it expects `disposeMock` to have been called before the component is unmounted.
   it.skip("should dispose the terminal on unmount", () => {
-    const { unmount } = renderWithProviders(<Terminal secrets={[]} />);
+    const { unmount } = renderWithProviders(<Terminal />);
 
     expect(mockTerminal.dispose).not.toHaveBeenCalled();
 

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

@@ -1,31 +1,31 @@
 import { beforeAll, describe, expect, it, vi } from "vitest";
-import { render } from "@testing-library/react";
 import { afterEach } from "node:test";
-import { ReactNode } from "react";
 import { useTerminal } from "#/hooks/use-terminal";
 import { Command } from "#/state/command-slice";
+import { AgentState } from "#/types/agent-state";
+import { renderWithProviders } from "../../test-utils";
+
+// Mock the WsClient context
+vi.mock("#/context/ws-client-provider", () => ({
+  useWsClient: () => ({
+    send: vi.fn(),
+    status: "CONNECTED",
+    isLoadingMessages: false,
+    events: [],
+  }),
+}));
 
 interface TestTerminalComponentProps {
   commands: Command[];
-  secrets: string[];
 }
 
 function TestTerminalComponent({
   commands,
-  secrets,
 }: TestTerminalComponentProps) {
-  const ref = useTerminal({ commands, secrets, disabled: false });
+  const ref = useTerminal({ commands });
   return <div ref={ref} />;
 }
 
-interface WrapperProps {
-  children: ReactNode;
-}
-
-function Wrapper({ children }: WrapperProps) {
-  return <div>{children}</div>;
-}
-
 describe("useTerminal", () => {
   const mockTerminal = vi.hoisted(() => ({
     loadAddon: vi.fn(),
@@ -57,8 +57,11 @@ describe("useTerminal", () => {
   });
 
   it("should render", () => {
-    render(<TestTerminalComponent commands={[]} secrets={[]} />, {
-      wrapper: Wrapper,
+    renderWithProviders(<TestTerminalComponent commands={[]} />, {
+      preloadedState: {
+        agent: { curAgentState: AgentState.RUNNING },
+        cmd: { commands: [] },
+      },
     });
   });
 
@@ -68,15 +71,19 @@ describe("useTerminal", () => {
       { content: "hello", type: "output" },
     ];
 
-    render(<TestTerminalComponent commands={commands} secrets={[]} />, {
-      wrapper: Wrapper,
+    renderWithProviders(<TestTerminalComponent commands={commands} />, {
+      preloadedState: {
+        agent: { curAgentState: AgentState.RUNNING },
+        cmd: { commands },
+      },
     });
 
     expect(mockTerminal.writeln).toHaveBeenNthCalledWith(1, "echo hello");
     expect(mockTerminal.writeln).toHaveBeenNthCalledWith(2, "hello");
   });
 
-  it("should hide secrets in the terminal", () => {
+  // This test is no longer relevant as secrets filtering has been removed
+  it.skip("should hide secrets in the terminal", () => {
     const secret = "super_secret_github_token";
     const anotherSecret = "super_secret_another_token";
     const commands: Command[] = [
@@ -87,23 +94,18 @@ describe("useTerminal", () => {
       { content: secret, type: "output" },
     ];
 
-    render(
+    renderWithProviders(
       <TestTerminalComponent
         commands={commands}
-        secrets={[secret, anotherSecret]}
       />,
       {
-        wrapper: Wrapper,
+        preloadedState: {
+          agent: { curAgentState: AgentState.RUNNING },
+          cmd: { commands },
+        },
       },
     );
 
-    // BUG: `vi.clearAllMocks()` does not clear the number of calls
-    // therefore, we need to assume the order of the calls based
-    // on the test order
-    expect(mockTerminal.writeln).toHaveBeenNthCalledWith(
-      3,
-      `export GITHUB_TOKEN=${"*".repeat(10)},${"*".repeat(10)},${"*".repeat(10)}`,
-    );
-    expect(mockTerminal.writeln).toHaveBeenNthCalledWith(4, "*".repeat(10));
+    // This test is no longer relevant as secrets filtering has been removed
   });
 });

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

@@ -0,0 +1,291 @@
+import { render, screen, waitFor } from "@testing-library/react";
+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 OpenHands from "#/api/open-hands";
+import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
+import { AuthProvider } from "#/context/auth-context";
+import { AvailableLanguages } from "#/i18n";
+import * as CaptureConsent from "#/utils/handle-capture-consent";
+import * as ToastHandlers from "#/utils/custom-toast-handlers";
+
+const renderAppSettingsScreen = () =>
+  render(<AppSettingsScreen />, {
+    wrapper: ({ children }) => (
+      <QueryClientProvider client={new QueryClient()}>
+        <AuthProvider>{children}</AuthProvider>
+      </QueryClientProvider>
+    ),
+  });
+
+describe("Content", () => {
+  it("should render the screen", () => {
+    renderAppSettingsScreen();
+    screen.getByTestId("app-settings-screen");
+  });
+
+  it("should render the correct default values", async () => {
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      language: "no",
+      user_consents_to_analytics: true,
+      enable_sound_notifications: true,
+    });
+
+    renderAppSettingsScreen();
+
+    await waitFor(() => {
+      const language = screen.getByTestId("language-input");
+      const analytics = screen.getByTestId("enable-analytics-switch");
+      const sound = screen.getByTestId("enable-sound-notifications-switch");
+
+      expect(language).toHaveValue("Norsk");
+      expect(analytics).toBeChecked();
+      expect(sound).toBeChecked();
+    });
+  });
+
+  it("should render the language options", async () => {
+    renderAppSettingsScreen();
+
+    const language = await screen.findByTestId("language-input");
+    await userEvent.click(language);
+
+    AvailableLanguages.forEach((lang) => {
+      const option = screen.getByText(lang.label);
+      expect(option).toBeInTheDocument();
+    });
+  });
+});
+
+describe("Form submission", () => {
+  afterEach(() => {
+    vi.clearAllMocks();
+  });
+
+  it("should submit the form with the correct values", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
+
+    renderAppSettingsScreen();
+
+    const language = await screen.findByTestId("language-input");
+    const analytics = await screen.findByTestId("enable-analytics-switch");
+    const sound = await screen.findByTestId(
+      "enable-sound-notifications-switch",
+    );
+
+    expect(language).toHaveValue("English");
+    expect(analytics).not.toBeChecked();
+    expect(sound).not.toBeChecked();
+
+    // change language
+    await userEvent.click(language);
+    const norsk = screen.getByText("Norsk");
+    await userEvent.click(norsk);
+    expect(language).toHaveValue("Norsk");
+
+    // toggle options
+    await userEvent.click(analytics);
+    expect(analytics).toBeChecked();
+    await userEvent.click(sound);
+    expect(sound).toBeChecked();
+
+    // submit the form
+    const submit = await screen.findByTestId("submit-button");
+    await userEvent.click(submit);
+    expect(saveSettingsSpy).toHaveBeenCalledWith(
+      expect.objectContaining({
+        language: "no",
+        user_consents_to_analytics: true,
+        enable_sound_notifications: true,
+      }),
+    );
+  });
+
+  it("should only enable the submit button when there are changes", async () => {
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
+
+    renderAppSettingsScreen();
+
+    const submit = await screen.findByTestId("submit-button");
+    expect(submit).toBeDisabled();
+
+    // Language check
+    const language = await screen.findByTestId("language-input");
+    await userEvent.click(language);
+    const norsk = screen.getByText("Norsk");
+    await userEvent.click(norsk);
+    expect(submit).not.toBeDisabled();
+
+    await userEvent.click(language);
+    const english = screen.getByText("English");
+    await userEvent.click(english);
+    expect(submit).toBeDisabled();
+
+    // Analytics check
+    const analytics = await screen.findByTestId("enable-analytics-switch");
+    await userEvent.click(analytics);
+    expect(submit).not.toBeDisabled();
+
+    await userEvent.click(analytics);
+    expect(submit).toBeDisabled();
+
+    // Sound check
+    const sound = await screen.findByTestId(
+      "enable-sound-notifications-switch",
+    );
+    await userEvent.click(sound);
+    expect(submit).not.toBeDisabled();
+
+    await userEvent.click(sound);
+    expect(submit).toBeDisabled();
+  });
+
+  it("should call handleCaptureConsents with true when the analytics switch is toggled", async () => {
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
+
+    const handleCaptureConsentsSpy = vi.spyOn(
+      CaptureConsent,
+      "handleCaptureConsent",
+    );
+
+    renderAppSettingsScreen();
+
+    const analytics = await screen.findByTestId("enable-analytics-switch");
+    const submit = await screen.findByTestId("submit-button");
+
+    await userEvent.click(analytics);
+    await userEvent.click(submit);
+
+    await waitFor(() =>
+      expect(handleCaptureConsentsSpy).toHaveBeenCalledWith(true),
+    );
+  });
+
+  it("should call handleCaptureConsents with false when the analytics switch is toggled", async () => {
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      user_consents_to_analytics: true,
+    });
+
+    const handleCaptureConsentsSpy = vi.spyOn(
+      CaptureConsent,
+      "handleCaptureConsent",
+    );
+
+    renderAppSettingsScreen();
+
+    const analytics = await screen.findByTestId("enable-analytics-switch");
+    const submit = await screen.findByTestId("submit-button");
+
+    await userEvent.click(analytics);
+    await userEvent.click(submit);
+
+    await waitFor(() =>
+      expect(handleCaptureConsentsSpy).toHaveBeenCalledWith(false),
+    );
+  });
+
+  // flaky test
+  it.skip("should disable the button when submitting changes", async () => {
+    renderAppSettingsScreen();
+
+    const submit = await screen.findByTestId("submit-button");
+    expect(submit).toBeDisabled();
+
+    const sound = await screen.findByTestId(
+      "enable-sound-notifications-switch",
+    );
+    await userEvent.click(sound);
+    expect(submit).not.toBeDisabled();
+
+    // submit the form
+    await userEvent.click(submit);
+
+    expect(submit).toHaveTextContent("Saving...");
+    expect(submit).toBeDisabled();
+
+    await waitFor(() => expect(submit).toHaveTextContent("Save"));
+  });
+
+  it("should disable the button after submitting changes", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
+
+    renderAppSettingsScreen();
+
+    const submit = await screen.findByTestId("submit-button");
+    expect(submit).toBeDisabled();
+
+    const sound = await screen.findByTestId(
+      "enable-sound-notifications-switch",
+    );
+    await userEvent.click(sound);
+    expect(submit).not.toBeDisabled();
+
+    // submit the form
+    await userEvent.click(submit);
+    expect(saveSettingsSpy).toHaveBeenCalled();
+
+    await waitFor(() => expect(submit).toBeDisabled());
+  });
+});
+
+describe("Status toasts", () => {
+  it("should call displaySuccessToast when the settings are saved", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
+
+    const displaySuccessToastSpy = vi.spyOn(
+      ToastHandlers,
+      "displaySuccessToast",
+    );
+
+    renderAppSettingsScreen();
+
+    // Toggle setting to change
+    const sound = await screen.findByTestId(
+      "enable-sound-notifications-switch",
+    );
+    await userEvent.click(sound);
+
+    const submit = await screen.findByTestId("submit-button");
+    await userEvent.click(submit);
+
+    expect(saveSettingsSpy).toHaveBeenCalled();
+    await waitFor(() => expect(displaySuccessToastSpy).toHaveBeenCalled());
+  });
+
+  it("should call displayErrorToast when the settings fail to save", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
+
+    const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
+
+    saveSettingsSpy.mockRejectedValue(new Error("Failed to save settings"));
+
+    renderAppSettingsScreen();
+
+    // Toggle setting to change
+    const sound = await screen.findByTestId(
+      "enable-sound-notifications-switch",
+    );
+    await userEvent.click(sound);
+
+    const submit = await screen.findByTestId("submit-button");
+    await userEvent.click(submit);
+
+    expect(saveSettingsSpy).toHaveBeenCalled();
+    expect(displayErrorToastSpy).toHaveBeenCalled();
+  });
+});

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

@@ -0,0 +1,461 @@
+import { render, screen, waitFor } from "@testing-library/react";
+import { createRoutesStub } from "react-router";
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
+import userEvent from "@testing-library/user-event";
+import GitSettingsScreen from "#/routes/git-settings";
+import OpenHands from "#/api/open-hands";
+import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
+import { AuthProvider } from "#/context/auth-context";
+import { GetConfigResponse } from "#/api/open-hands.types";
+import * as ToastHandlers from "#/utils/custom-toast-handlers";
+
+const VALID_OSS_CONFIG: GetConfigResponse = {
+  APP_MODE: "oss",
+  GITHUB_CLIENT_ID: "123",
+  POSTHOG_CLIENT_KEY: "456",
+  FEATURE_FLAGS: {
+    ENABLE_BILLING: false,
+    HIDE_LLM_SETTINGS: false,
+  },
+};
+
+const VALID_SAAS_CONFIG: GetConfigResponse = {
+  APP_MODE: "saas",
+  GITHUB_CLIENT_ID: "123",
+  POSTHOG_CLIENT_KEY: "456",
+  FEATURE_FLAGS: {
+    ENABLE_BILLING: false,
+    HIDE_LLM_SETTINGS: false,
+  },
+};
+
+const queryClient = new QueryClient();
+
+const GitSettingsRouterStub = createRoutesStub([
+  {
+    Component: GitSettingsScreen,
+    path: "/settings/github",
+  },
+]);
+
+const renderGitSettingsScreen = () => {
+  const { rerender, ...rest } = render(
+    <GitSettingsRouterStub initialEntries={["/settings/github"]} />,
+    {
+      wrapper: ({ children }) => (
+        <QueryClientProvider client={queryClient}>
+          <AuthProvider>{children}</AuthProvider>
+        </QueryClientProvider>
+      ),
+    },
+  );
+
+  const rerenderGitSettingsScreen = () =>
+    rerender(
+      <QueryClientProvider client={queryClient}>
+        <AuthProvider>
+          <GitSettingsRouterStub initialEntries={["/settings/github"]} />
+        </AuthProvider>
+      </QueryClientProvider>,
+    );
+
+  return {
+    ...rest,
+    rerender: rerenderGitSettingsScreen,
+  };
+};
+
+beforeEach(() => {
+  // Since we don't recreate the query client on every test, we need to
+  // reset the query client before each test to avoid state leaks
+  // between tests.
+  queryClient.invalidateQueries();
+});
+
+describe("Content", () => {
+  it("should render", async () => {
+    renderGitSettingsScreen();
+    await screen.findByTestId("git-settings-screen");
+  });
+
+  it("should render the inputs if OSS mode", async () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
+
+    const { rerender } = renderGitSettingsScreen();
+
+    await screen.findByTestId("github-token-input");
+    await screen.findByTestId("github-token-help-anchor");
+
+    await screen.findByTestId("gitlab-token-input");
+    await screen.findByTestId("gitlab-token-help-anchor");
+
+    getConfigSpy.mockResolvedValue(VALID_SAAS_CONFIG);
+    queryClient.invalidateQueries();
+    rerender();
+
+    await waitFor(() => {
+      expect(
+        screen.queryByTestId("github-token-input"),
+      ).not.toBeInTheDocument();
+      expect(
+        screen.queryByTestId("github-token-help-anchor"),
+      ).not.toBeInTheDocument();
+
+      expect(
+        screen.queryByTestId("gitlab-token-input"),
+      ).not.toBeInTheDocument();
+      expect(
+        screen.queryByTestId("gitlab-token-help-anchor"),
+      ).not.toBeInTheDocument();
+    });
+  });
+
+  it("should set '<hidden>' placeholder and indicator if the GitHub token is set", async () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+
+    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        github: false,
+        gitlab: false,
+      },
+    });
+
+    const { rerender } = renderGitSettingsScreen();
+
+    await waitFor(() => {
+      const githubInput = screen.getByTestId("github-token-input");
+      expect(githubInput).toHaveProperty("placeholder", "");
+      expect(
+        screen.queryByTestId("gh-set-token-indicator"),
+      ).not.toBeInTheDocument();
+
+      const gitlabInput = screen.getByTestId("gitlab-token-input");
+      expect(gitlabInput).toHaveProperty("placeholder", "");
+      expect(
+        screen.queryByTestId("gl-set-token-indicator"),
+      ).not.toBeInTheDocument();
+    });
+
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        github: true,
+        gitlab: true,
+      },
+    });
+    queryClient.invalidateQueries();
+
+    rerender();
+
+    await waitFor(() => {
+      const githubInput = screen.getByTestId("github-token-input");
+      expect(githubInput).toHaveProperty("placeholder", "<hidden>");
+      expect(
+        screen.queryByTestId("gh-set-token-indicator"),
+      ).toBeInTheDocument();
+
+      const gitlabInput = screen.getByTestId("gitlab-token-input");
+      expect(gitlabInput).toHaveProperty("placeholder", "<hidden>");
+      expect(
+        screen.queryByTestId("gl-set-token-indicator"),
+      ).toBeInTheDocument();
+    });
+
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        github: false,
+        gitlab: true,
+      },
+    });
+    queryClient.invalidateQueries();
+
+    rerender();
+
+    await waitFor(() => {
+      const githubInput = screen.getByTestId("github-token-input");
+      expect(githubInput).toHaveProperty("placeholder", "");
+      expect(
+        screen.queryByTestId("gh-set-token-indicator"),
+      ).not.toBeInTheDocument();
+
+      const gitlabInput = screen.getByTestId("gitlab-token-input");
+      expect(gitlabInput).toHaveProperty("placeholder", "<hidden>");
+      expect(
+        screen.queryByTestId("gl-set-token-indicator"),
+      ).toBeInTheDocument();
+    });
+  });
+
+  it("should render the 'Configure GitHub Repositories' button if SaaS mode and app slug exists", async () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
+
+    const { rerender } = renderGitSettingsScreen();
+
+    let button = screen.queryByTestId("configure-github-repositories-button");
+    expect(button).not.toBeInTheDocument();
+
+    expect(screen.getByTestId("submit-button")).toBeInTheDocument();
+    expect(screen.getByTestId("disconnect-tokens-button")).toBeInTheDocument();
+
+    getConfigSpy.mockResolvedValue(VALID_SAAS_CONFIG);
+    queryClient.invalidateQueries();
+    rerender();
+
+    await waitFor(() => {
+      // wait until queries are resolved
+      expect(queryClient.isFetching()).toBe(0);
+      button = screen.queryByTestId("configure-github-repositories-button");
+      expect(button).not.toBeInTheDocument();
+    });
+
+    getConfigSpy.mockResolvedValue({
+      ...VALID_SAAS_CONFIG,
+      APP_SLUG: "test-slug",
+    });
+    queryClient.invalidateQueries();
+    rerender();
+
+    await waitFor(() => {
+      button = screen.getByTestId("configure-github-repositories-button");
+      expect(button).toBeInTheDocument();
+      expect(screen.queryByTestId("submit-button")).not.toBeInTheDocument();
+      expect(
+        screen.queryByTestId("disconnect-tokens-button"),
+      ).not.toBeInTheDocument();
+    });
+  });
+});
+
+describe("Form submission", () => {
+  it("should save the GitHub token", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
+
+    renderGitSettingsScreen();
+
+    const githubInput = await screen.findByTestId("github-token-input");
+    const submit = await screen.findByTestId("submit-button");
+
+    await userEvent.type(githubInput, "test-token");
+    await userEvent.click(submit);
+
+    expect(saveSettingsSpy).toHaveBeenCalledWith(
+      expect.objectContaining({
+        provider_tokens: {
+          github: "test-token",
+          gitlab: "",
+        },
+      }),
+    );
+
+    const gitlabInput = await screen.findByTestId("gitlab-token-input");
+    await userEvent.type(gitlabInput, "test-token");
+    await userEvent.click(submit);
+
+    expect(saveSettingsSpy).toHaveBeenCalledWith(
+      expect.objectContaining({
+        provider_tokens: {
+          github: "",
+          gitlab: "test-token",
+        },
+      }),
+    );
+  });
+
+  it("should disable the button if there is no input", async () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
+
+    renderGitSettingsScreen();
+
+    const submit = await screen.findByTestId("submit-button");
+    expect(submit).toBeDisabled();
+
+    const githubInput = await screen.findByTestId("github-token-input");
+    await userEvent.type(githubInput, "test-token");
+
+    expect(submit).not.toBeDisabled();
+
+    await userEvent.clear(githubInput);
+    expect(submit).toBeDisabled();
+
+    const gitlabInput = await screen.findByTestId("gitlab-token-input");
+    await userEvent.type(gitlabInput, "test-token");
+
+    expect(submit).not.toBeDisabled();
+
+    await userEvent.clear(gitlabInput);
+    expect(submit).toBeDisabled();
+  });
+
+  it("should enable a disconnect tokens button if there is at least one token set", async () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+
+    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        github: true,
+        gitlab: false,
+      },
+    });
+
+    renderGitSettingsScreen();
+    await screen.findByTestId("git-settings-screen");
+
+    let disconnectButton = await screen.findByTestId(
+      "disconnect-tokens-button",
+    );
+    await waitFor(() => expect(disconnectButton).not.toBeDisabled());
+
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        github: false,
+        gitlab: false,
+      },
+    });
+    queryClient.invalidateQueries();
+
+    disconnectButton = await screen.findByTestId("disconnect-tokens-button");
+    await waitFor(() => expect(disconnectButton).toBeDisabled());
+  });
+
+  it("should call logout when pressing the disconnect tokens button", async () => {
+    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({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      provider_tokens_set: {
+        github: true,
+        gitlab: false,
+      },
+    });
+
+    renderGitSettingsScreen();
+
+    const disconnectButton = await screen.findByTestId(
+      "disconnect-tokens-button",
+    );
+    await waitFor(() => expect(disconnectButton).not.toBeDisabled());
+    await userEvent.click(disconnectButton);
+
+    expect(logoutSpy).toHaveBeenCalled();
+  });
+
+  // flaky test
+  it.skip("should disable the button when submitting changes", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
+
+    renderGitSettingsScreen();
+
+    const submit = await screen.findByTestId("submit-button");
+    expect(submit).toBeDisabled();
+
+    const githubInput = await screen.findByTestId("github-token-input");
+    await userEvent.type(githubInput, "test-token");
+    expect(submit).not.toBeDisabled();
+
+    // submit the form
+    await userEvent.click(submit);
+    expect(saveSettingsSpy).toHaveBeenCalled();
+
+    expect(submit).toHaveTextContent("Saving...");
+    expect(submit).toBeDisabled();
+
+    await waitFor(() => expect(submit).toHaveTextContent("Save"));
+  });
+
+  it("should disable the button after submitting changes", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
+
+    renderGitSettingsScreen();
+    await screen.findByTestId("git-settings-screen");
+
+    const submit = await screen.findByTestId("submit-button");
+    expect(submit).toBeDisabled();
+
+    const githubInput = await screen.findByTestId("github-token-input");
+    await userEvent.type(githubInput, "test-token");
+    expect(submit).not.toBeDisabled();
+
+    // submit the form
+    await userEvent.click(submit);
+    expect(saveSettingsSpy).toHaveBeenCalled();
+    expect(submit).toBeDisabled();
+
+    const gitlabInput = await screen.findByTestId("gitlab-token-input");
+    await userEvent.type(gitlabInput, "test-token");
+    expect(gitlabInput).toHaveValue("test-token");
+    expect(submit).not.toBeDisabled();
+
+    // submit the form
+    await userEvent.click(submit);
+    expect(saveSettingsSpy).toHaveBeenCalled();
+
+    await waitFor(() => expect(submit).toBeDisabled());
+  });
+});
+
+describe("Status toasts", () => {
+  it("should call displaySuccessToast when the settings are saved", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
+
+    const displaySuccessToastSpy = vi.spyOn(
+      ToastHandlers,
+      "displaySuccessToast",
+    );
+
+    renderGitSettingsScreen();
+
+    // Toggle setting to change
+    const githubInput = await screen.findByTestId("github-token-input");
+    await userEvent.type(githubInput, "test-token");
+
+    const submit = await screen.findByTestId("submit-button");
+    await userEvent.click(submit);
+
+    expect(saveSettingsSpy).toHaveBeenCalled();
+    await waitFor(() => expect(displaySuccessToastSpy).toHaveBeenCalled());
+  });
+
+  it("should call displayErrorToast when the settings fail to save", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
+
+    const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
+
+    saveSettingsSpy.mockRejectedValue(new Error("Failed to save settings"));
+
+    renderGitSettingsScreen();
+
+    // Toggle setting to change
+    const gitlabInput = await screen.findByTestId("gitlab-token-input");
+    await userEvent.type(gitlabInput, "test-token");
+
+    const submit = await screen.findByTestId("submit-button");
+    await userEvent.click(submit);
+
+    expect(saveSettingsSpy).toHaveBeenCalled();
+    expect(displayErrorToastSpy).toHaveBeenCalled();
+  });
+});

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

@@ -0,0 +1,377 @@
+import { render, screen, waitFor, within } from "@testing-library/react";
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import { QueryClientProvider, QueryClient } from "@tanstack/react-query";
+import userEvent from "@testing-library/user-event";
+import { createRoutesStub } from "react-router";
+import { Provider } from "react-redux";
+import { setupStore } from "test-utils";
+import { AxiosError } from "axios";
+import HomeScreen from "#/routes/home";
+import { AuthProvider } from "#/context/auth-context";
+import * as GitService from "#/api/git";
+import { GitRepository } from "#/types/git";
+import OpenHands from "#/api/open-hands";
+import MainApp from "#/routes/root-layout";
+
+const createAxiosNotFoundErrorObject = () =>
+  new AxiosError(
+    "Request failed with status code 404",
+    "ERR_BAD_REQUEST",
+    undefined,
+    undefined,
+    {
+      status: 404,
+      statusText: "Not Found",
+      data: { message: "Settings not found" },
+      headers: {},
+      // @ts-expect-error - we only need the response object for this test
+      config: {},
+    },
+  );
+
+const RouterStub = createRoutesStub([
+  {
+    Component: MainApp,
+    path: "/",
+    children: [
+      {
+        Component: HomeScreen,
+        path: "/",
+      },
+      {
+        Component: () => <div data-testid="conversation-screen" />,
+        path: "/conversations/:conversationId",
+      },
+      {
+        Component: () => <div data-testid="settings-screen" />,
+        path: "/settings",
+      },
+    ],
+  },
+]);
+
+const renderHomeScreen = (initialProvidersAreSet = true) =>
+  render(<RouterStub />, {
+    wrapper: ({ children }) => (
+      <Provider store={setupStore()}>
+        <AuthProvider initialProvidersAreSet={initialProvidersAreSet}>
+          <QueryClientProvider client={new QueryClient()}>
+            {children}
+          </QueryClientProvider>
+        </AuthProvider>
+      </Provider>
+    ),
+  });
+
+const MOCK_RESPOSITORIES: GitRepository[] = [
+  {
+    id: 1,
+    full_name: "octocat/hello-world",
+    git_provider: "github",
+    is_public: true,
+  },
+  {
+    id: 2,
+    full_name: "octocat/earth",
+    git_provider: "github",
+    is_public: true,
+  },
+];
+
+describe("HomeScreen", () => {
+  it("should render", () => {
+    renderHomeScreen();
+    screen.getByTestId("home-screen");
+  });
+
+  it("should render the repository connector and suggested tasks sections", async () => {
+    renderHomeScreen();
+
+    screen.getByTestId("repo-connector");
+    screen.getByTestId("task-suggestions");
+  });
+
+  it("should have responsive layout for mobile and desktop screens", async () => {
+    renderHomeScreen();
+    
+    const mainContainer = screen.getByTestId("home-screen").querySelector("main");
+    expect(mainContainer).toHaveClass("flex", "flex-col", "md:flex-row");
+  });
+
+  it("should filter the suggested tasks based on the selected repository", async () => {
+    const retrieveUserGitRepositoriesSpy = vi.spyOn(
+      GitService,
+      "retrieveUserGitRepositories",
+    );
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
+
+    renderHomeScreen();
+
+    const taskSuggestions = screen.getByTestId("task-suggestions");
+
+    // Initially, all tasks should be visible
+    await waitFor(() => {
+      within(taskSuggestions).getByText("octocat/hello-world");
+      within(taskSuggestions).getByText("octocat/earth");
+    });
+
+    // Select a repository from the dropdown
+    const repoConnector = screen.getByTestId("repo-connector");
+
+    const dropdown = within(repoConnector).getByTestId("repo-dropdown");
+    await userEvent.click(dropdown);
+
+    const repoOption = screen.getAllByText("octocat/hello-world")[1];
+    await userEvent.click(repoOption);
+
+    // After selecting a repository, only tasks related to that repository should be visible
+    await waitFor(() => {
+      within(taskSuggestions).getByText("octocat/hello-world");
+      expect(
+        within(taskSuggestions).queryByText("octocat/earth"),
+      ).not.toBeInTheDocument();
+    });
+  });
+
+  it("should reset the filtered tasks when the selected repository is cleared", async () => {
+    const retrieveUserGitRepositoriesSpy = vi.spyOn(
+      GitService,
+      "retrieveUserGitRepositories",
+    );
+    retrieveUserGitRepositoriesSpy.mockResolvedValue({
+      data: MOCK_RESPOSITORIES,
+      nextPage: null,
+    });
+
+    renderHomeScreen();
+
+    const taskSuggestions = screen.getByTestId("task-suggestions");
+
+    // Initially, all tasks should be visible
+    await waitFor(() => {
+      within(taskSuggestions).getByText("octocat/hello-world");
+      within(taskSuggestions).getByText("octocat/earth");
+    });
+
+    // Select a repository from the dropdown
+    const repoConnector = screen.getByTestId("repo-connector");
+
+    const dropdown = within(repoConnector).getByTestId("repo-dropdown");
+    await userEvent.click(dropdown);
+
+    const repoOption = screen.getAllByText("octocat/hello-world")[1];
+    await userEvent.click(repoOption);
+
+    // After selecting a repository, only tasks related to that repository should be visible
+    await waitFor(() => {
+      within(taskSuggestions).getByText("octocat/hello-world");
+      expect(
+        within(taskSuggestions).queryByText("octocat/earth"),
+      ).not.toBeInTheDocument();
+    });
+
+    // Clear the selected repository
+    await userEvent.clear(dropdown);
+
+    // All tasks should be visible again
+    await waitFor(() => {
+      within(taskSuggestions).getByText("octocat/hello-world");
+      within(taskSuggestions).getByText("octocat/earth");
+    });
+  });
+
+  describe("launch buttons", () => {
+    const setupLaunchButtons = async () => {
+      let headerLaunchButton = screen.getByTestId("header-launch-button");
+      let repoLaunchButton = screen.getByTestId("repo-launch-button");
+      let tasksLaunchButtons =
+        await screen.findAllByTestId("task-launch-button");
+
+      // Select a repository from the dropdown to enable the repo launch button
+      const repoConnector = screen.getByTestId("repo-connector");
+      const dropdown = within(repoConnector).getByTestId("repo-dropdown");
+      await userEvent.click(dropdown);
+      const repoOption = screen.getAllByText("octocat/hello-world")[1];
+      await userEvent.click(repoOption);
+
+      expect(headerLaunchButton).not.toBeDisabled();
+      expect(repoLaunchButton).not.toBeDisabled();
+      tasksLaunchButtons.forEach((button) => {
+        expect(button).not.toBeDisabled();
+      });
+
+      headerLaunchButton = screen.getByTestId("header-launch-button");
+      repoLaunchButton = screen.getByTestId("repo-launch-button");
+      tasksLaunchButtons = await screen.findAllByTestId("task-launch-button");
+
+      return {
+        headerLaunchButton,
+        repoLaunchButton,
+        tasksLaunchButtons,
+      };
+    };
+
+    beforeEach(() => {
+      const retrieveUserGitRepositoriesSpy = vi.spyOn(
+        GitService,
+        "retrieveUserGitRepositories",
+      );
+      retrieveUserGitRepositoriesSpy.mockResolvedValue({
+        data: MOCK_RESPOSITORIES,
+        nextPage: null,
+      });
+    });
+
+    it("should disable the other launch buttons when the header launch button is clicked", async () => {
+      renderHomeScreen();
+      const { headerLaunchButton, repoLaunchButton } =
+        await setupLaunchButtons();
+
+      const tasksLaunchButtonsAfter =
+        await screen.findAllByTestId("task-launch-button");
+
+      // All other buttons should be disabled when the header button is clicked
+      await userEvent.click(headerLaunchButton);
+
+      expect(headerLaunchButton).toBeDisabled();
+      expect(repoLaunchButton).toBeDisabled();
+      tasksLaunchButtonsAfter.forEach((button) => {
+        expect(button).toBeDisabled();
+      });
+    });
+
+    it("should disable the other launch buttons when the repo launch button is clicked", async () => {
+      renderHomeScreen();
+      const { headerLaunchButton, repoLaunchButton } =
+        await setupLaunchButtons();
+
+      const tasksLaunchButtonsAfter =
+        await screen.findAllByTestId("task-launch-button");
+
+      // All other buttons should be disabled when the repo button is clicked
+      await userEvent.click(repoLaunchButton);
+
+      expect(headerLaunchButton).toBeDisabled();
+      expect(repoLaunchButton).toBeDisabled();
+      tasksLaunchButtonsAfter.forEach((button) => {
+        expect(button).toBeDisabled();
+      });
+    });
+
+    it("should disable the other launch buttons when any task launch button is clicked", async () => {
+      renderHomeScreen();
+      const { headerLaunchButton, repoLaunchButton, tasksLaunchButtons } =
+        await setupLaunchButtons();
+
+      const tasksLaunchButtonsAfter =
+        await screen.findAllByTestId("task-launch-button");
+
+      // All other buttons should be disabled when the task button is clicked
+      await userEvent.click(tasksLaunchButtons[0]);
+
+      expect(headerLaunchButton).toBeDisabled();
+      expect(repoLaunchButton).toBeDisabled();
+      tasksLaunchButtonsAfter.forEach((button) => {
+        expect(button).toBeDisabled();
+      });
+    });
+  });
+
+  it("should hide the suggested tasks section if not authed with git(hub|lab)", async () => {
+    renderHomeScreen(false);
+
+    const taskSuggestions = screen.queryByTestId("task-suggestions");
+    const repoConnector = screen.getByTestId("repo-connector");
+
+    expect(taskSuggestions).not.toBeInTheDocument();
+    expect(repoConnector).toBeInTheDocument();
+  });
+});
+
+describe("Settings 404", () => {
+  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();
+    getSettingsSpy.mockRejectedValue(error);
+
+    renderHomeScreen();
+
+    const settingsModal = await screen.findByTestId("ai-config-modal");
+    expect(settingsModal).toBeInTheDocument();
+  });
+
+  it("should navigate to the settings screen when clicking the advanced settings button", async () => {
+    const error = createAxiosNotFoundErrorObject();
+    getSettingsSpy.mockRejectedValue(error);
+
+    const user = userEvent.setup();
+    renderHomeScreen();
+
+    const settingsScreen = screen.queryByTestId("settings-screen");
+    expect(settingsScreen).not.toBeInTheDocument();
+
+    const settingsModal = await screen.findByTestId("ai-config-modal");
+    expect(settingsModal).toBeInTheDocument();
+
+    const advancedSettingsButton = await screen.findByTestId(
+      "advanced-settings-link",
+    );
+    await user.click(advancedSettingsButton);
+
+    const settingsScreenAfter = await screen.findByTestId("settings-screen");
+    expect(settingsScreenAfter).toBeInTheDocument();
+
+    const settingsModalAfter = screen.queryByTestId("ai-config-modal");
+    expect(settingsModalAfter).not.toBeInTheDocument();
+  });
+
+  it("should not open the settings modal if GET /settings fails but is SaaS mode", async () => {
+    // @ts-expect-error - we only need APP_MODE for this test
+    getConfigSpy.mockResolvedValue({
+      APP_MODE: "saas",
+      FEATURE_FLAGS: {
+        ENABLE_BILLING: false,
+        HIDE_LLM_SETTINGS: false,
+      },
+    });
+    const error = createAxiosNotFoundErrorObject();
+    getSettingsSpy.mockRejectedValue(error);
+
+    renderHomeScreen();
+
+    // small hack to wait for the modal to not appear
+    await expect(
+      screen.findByTestId("ai-config-modal", {}, { timeout: 1000 }),
+    ).rejects.toThrow();
+  });
+});
+
+describe("Setup Payment modal", () => {
+  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
+    getConfigSpy.mockResolvedValue({
+      APP_MODE: "saas",
+      FEATURE_FLAGS: {
+        ENABLE_BILLING: true,
+        HIDE_LLM_SETTINGS: false,
+      },
+    });
+    const error = createAxiosNotFoundErrorObject();
+    getSettingsSpy.mockRejectedValue(error);
+
+    renderHomeScreen();
+
+    const setupPaymentModal = await screen.findByTestId(
+      "proceed-to-stripe-button",
+    );
+    expect(setupPaymentModal).toBeInTheDocument();
+  });
+});

frontend/__tests__/routes/home.test.tsx

@@ -1,177 +0,0 @@
-import { createRoutesStub } from "react-router";
-import { afterEach, describe, expect, it, vi } from "vitest";
-import { renderWithProviders } from "test-utils";
-import userEvent from "@testing-library/user-event";
-import { screen } from "@testing-library/react";
-import { AxiosError } from "axios";
-import MainApp from "#/routes/root-layout";
-import SettingsScreen from "#/routes/settings";
-import Home from "#/routes/home";
-import OpenHands from "#/api/open-hands";
-
-const createAxiosNotFoundErrorObject = () =>
-  new AxiosError(
-    "Request failed with status code 404",
-    "ERR_BAD_REQUEST",
-    undefined,
-    undefined,
-    {
-      status: 404,
-      statusText: "Not Found",
-      data: { message: "Settings not found" },
-      headers: {},
-      // @ts-expect-error - we only need the response object for this test
-      config: {},
-    },
-  );
-
-const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-
-const RouterStub = createRoutesStub([
-  {
-    // layout route
-    Component: MainApp,
-    path: "/",
-    children: [
-      {
-        // home route
-        Component: Home,
-        path: "/",
-      },
-      {
-        Component: SettingsScreen,
-        path: "/settings",
-      },
-    ],
-  },
-]);
-
-afterEach(() => {
-  vi.clearAllMocks();
-});
-
-describe("Home Screen", () => {
-  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-
-  it("should render the home screen", () => {
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-  });
-
-  it("should navigate to the settings screen when the settings button is clicked", async () => {
-    const user = userEvent.setup();
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    const settingsButton = await screen.findByTestId("settings-button");
-    await user.click(settingsButton);
-
-    const settingsScreen = await screen.findByTestId("settings-screen");
-    expect(settingsScreen).toBeInTheDocument();
-  });
-
-  it("should navigate to the settings when pressing 'Connect to GitHub' if the user isn't authenticated", async () => {
-    // @ts-expect-error - we only need APP_MODE for this test
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "oss",
-      FEATURE_FLAGS: {
-        ENABLE_BILLING: false,
-        HIDE_LLM_SETTINGS: false,
-      },
-    });
-    const user = userEvent.setup();
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    const connectToGitHubButton =
-      await screen.findByTestId("connect-to-github");
-    await user.click(connectToGitHubButton);
-
-    const settingsScreen = await screen.findByTestId("settings-screen");
-    expect(settingsScreen).toBeInTheDocument();
-  });
-});
-
-describe("Settings 404", () => {
-  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-
-  it("should open the settings modal if GET /settings fails with a 404", async () => {
-    const error = createAxiosNotFoundErrorObject();
-    getSettingsSpy.mockRejectedValue(error);
-
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    const settingsModal = await screen.findByTestId("ai-config-modal");
-    expect(settingsModal).toBeInTheDocument();
-  });
-
-  it("should navigate to the settings screen when clicking the advanced settings button", async () => {
-    const error = createAxiosNotFoundErrorObject();
-    getSettingsSpy.mockRejectedValue(error);
-
-    const user = userEvent.setup();
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    const settingsScreen = screen.queryByTestId("settings-screen");
-    expect(settingsScreen).not.toBeInTheDocument();
-
-    const settingsModal = await screen.findByTestId("ai-config-modal");
-    expect(settingsModal).toBeInTheDocument();
-
-    const advancedSettingsButton = await screen.findByTestId(
-      "advanced-settings-link",
-    );
-    await user.click(advancedSettingsButton);
-
-    const settingsScreenAfter = await screen.findByTestId("settings-screen");
-    expect(settingsScreenAfter).toBeInTheDocument();
-
-    const settingsModalAfter = screen.queryByTestId("ai-config-modal");
-    expect(settingsModalAfter).not.toBeInTheDocument();
-  });
-
-  it("should not open the settings modal if GET /settings fails but is SaaS mode", async () => {
-    // @ts-expect-error - we only need APP_MODE for this test
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
-      FEATURE_FLAGS: {
-        ENABLE_BILLING: false,
-        HIDE_LLM_SETTINGS: false,
-      },
-    });
-    const error = createAxiosNotFoundErrorObject();
-    getSettingsSpy.mockRejectedValue(error);
-
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    // small hack to wait for the modal to not appear
-    await expect(
-      screen.findByTestId("ai-config-modal", {}, { timeout: 1000 }),
-    ).rejects.toThrow();
-  });
-});
-
-describe("Setup Payment modal", () => {
-  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-
-  afterEach(() => {
-    vi.resetAllMocks();
-  });
-
-  it("should only render if SaaS mode and is new user", async () => {
-    // @ts-expect-error - we only need the APP_MODE for this test
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
-      FEATURE_FLAGS: {
-        ENABLE_BILLING: true,
-        HIDE_LLM_SETTINGS: false,
-      },
-    });
-    const error = createAxiosNotFoundErrorObject();
-    getSettingsSpy.mockRejectedValue(error);
-
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    const setupPaymentModal = await screen.findByTestId(
-      "proceed-to-stripe-button",
-    );
-    expect(setupPaymentModal).toBeInTheDocument();
-  });
-});

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

@@ -0,0 +1,674 @@
+import { render, screen, waitFor, within } from "@testing-library/react";
+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 OpenHands from "#/api/open-hands";
+import {
+  MOCK_DEFAULT_USER_SETTINGS,
+  resetTestHandlersMockSettings,
+} from "#/mocks/handlers";
+import { AuthProvider } from "#/context/auth-context";
+import * as AdvancedSettingsUtlls from "#/utils/has-advanced-settings-set";
+import * as ToastHandlers from "#/utils/custom-toast-handlers";
+
+const renderLlmSettingsScreen = () =>
+  render(<LlmSettingsScreen />, {
+    wrapper: ({ children }) => (
+      <QueryClientProvider client={new QueryClient()}>
+        <AuthProvider>{children}</AuthProvider>
+      </QueryClientProvider>
+    ),
+  });
+
+beforeEach(() => {
+  vi.resetAllMocks();
+  resetTestHandlersMockSettings();
+});
+
+describe("Content", () => {
+  describe("Basic form", () => {
+    it("should render the basic form by default", async () => {
+      renderLlmSettingsScreen();
+      await screen.findByTestId("llm-settings-screen");
+
+      const basicFom = screen.getByTestId("llm-settings-form-basic");
+      within(basicFom).getByTestId("llm-provider-input");
+      within(basicFom).getByTestId("llm-model-input");
+      within(basicFom).getByTestId("llm-api-key-input");
+      within(basicFom).getByTestId("llm-api-key-help-anchor");
+    });
+
+    it("should render the default values if non exist", async () => {
+      renderLlmSettingsScreen();
+      await screen.findByTestId("llm-settings-screen");
+
+      const provider = screen.getByTestId("llm-provider-input");
+      const model = screen.getByTestId("llm-model-input");
+      const apiKey = screen.getByTestId("llm-api-key-input");
+
+      await waitFor(() => {
+        expect(provider).toHaveValue("Anthropic");
+        expect(model).toHaveValue("claude-3-5-sonnet-20241022");
+
+        expect(apiKey).toHaveValue("");
+        expect(apiKey).toHaveProperty("placeholder", "");
+      });
+    });
+
+    it("should render the existing settings values", async () => {
+      const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+      getSettingsSpy.mockResolvedValue({
+        ...MOCK_DEFAULT_USER_SETTINGS,
+        llm_model: "openai/gpt-4o",
+        llm_api_key_set: true,
+      });
+
+      renderLlmSettingsScreen();
+      await screen.findByTestId("llm-settings-screen");
+
+      const provider = screen.getByTestId("llm-provider-input");
+      const model = screen.getByTestId("llm-model-input");
+      const apiKey = screen.getByTestId("llm-api-key-input");
+
+      await waitFor(() => {
+        expect(provider).toHaveValue("OpenAI");
+        expect(model).toHaveValue("gpt-4o");
+
+        expect(apiKey).toHaveValue("");
+        expect(apiKey).toHaveProperty("placeholder", "<hidden>");
+        expect(screen.getByTestId("set-indicator")).toBeInTheDocument();
+      });
+    });
+  });
+
+  describe("Advanced form", () => {
+    it("should render the advanced form if the switch is toggled", async () => {
+      renderLlmSettingsScreen();
+      await screen.findByTestId("llm-settings-screen");
+
+      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+      const basicForm = screen.getByTestId("llm-settings-form-basic");
+
+      expect(
+        screen.queryByTestId("llm-settings-form-advanced"),
+      ).not.toBeInTheDocument();
+      expect(basicForm).toBeInTheDocument();
+
+      await userEvent.click(advancedSwitch);
+
+      expect(
+        screen.queryByTestId("llm-settings-form-advanced"),
+      ).toBeInTheDocument();
+      expect(basicForm).not.toBeInTheDocument();
+
+      const advancedForm = screen.getByTestId("llm-settings-form-advanced");
+      within(advancedForm).getByTestId("llm-custom-model-input");
+      within(advancedForm).getByTestId("base-url-input");
+      within(advancedForm).getByTestId("llm-api-key-input");
+      within(advancedForm).getByTestId("llm-api-key-help-anchor");
+      within(advancedForm).getByTestId("agent-input");
+      within(advancedForm).getByTestId("enable-confirmation-mode-switch");
+      within(advancedForm).getByTestId("enable-memory-condenser-switch");
+
+      await userEvent.click(advancedSwitch);
+      expect(
+        screen.queryByTestId("llm-settings-form-advanced"),
+      ).not.toBeInTheDocument();
+      expect(screen.getByTestId("llm-settings-form-basic")).toBeInTheDocument();
+    });
+
+    it("should render the default advanced settings", async () => {
+      renderLlmSettingsScreen();
+      await screen.findByTestId("llm-settings-screen");
+
+      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+      expect(advancedSwitch).not.toBeChecked();
+
+      await userEvent.click(advancedSwitch);
+
+      const model = screen.getByTestId("llm-custom-model-input");
+      const baseUrl = screen.getByTestId("base-url-input");
+      const apiKey = screen.getByTestId("llm-api-key-input");
+      const agent = screen.getByTestId("agent-input");
+      const confirmation = screen.getByTestId(
+        "enable-confirmation-mode-switch",
+      );
+      const condensor = screen.getByTestId("enable-memory-condenser-switch");
+
+      expect(model).toHaveValue("anthropic/claude-3-5-sonnet-20241022");
+      expect(baseUrl).toHaveValue("");
+      expect(apiKey).toHaveValue("");
+      expect(apiKey).toHaveProperty("placeholder", "");
+      expect(agent).toHaveValue("CodeActAgent");
+      expect(confirmation).not.toBeChecked();
+      expect(condensor).toBeChecked();
+
+      // check that security analyzer is present
+      expect(
+        screen.queryByTestId("security-analyzer-input"),
+      ).not.toBeInTheDocument();
+      await userEvent.click(confirmation);
+      screen.getByTestId("security-analyzer-input");
+    });
+
+    it("should render the advanced form if existings settings are advanced", async () => {
+      const hasAdvancedSettingsSetSpy = vi.spyOn(
+        AdvancedSettingsUtlls,
+        "hasAdvancedSettingsSet",
+      );
+      hasAdvancedSettingsSetSpy.mockReturnValue(true);
+
+      renderLlmSettingsScreen();
+
+      await waitFor(() => {
+        const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+        expect(advancedSwitch).toBeChecked();
+        screen.getByTestId("llm-settings-form-advanced");
+      });
+    });
+
+    it("should render existing advanced settings correctly", async () => {
+      const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+      getSettingsSpy.mockResolvedValue({
+        ...MOCK_DEFAULT_USER_SETTINGS,
+        llm_model: "openai/gpt-4o",
+        llm_base_url: "https://api.openai.com/v1/chat/completions",
+        llm_api_key_set: true,
+        agent: "CoActAgent",
+        confirmation_mode: true,
+        enable_default_condenser: false,
+        security_analyzer: "mock-invariant",
+      });
+
+      renderLlmSettingsScreen();
+      await screen.findByTestId("llm-settings-screen");
+
+      const model = screen.getByTestId("llm-custom-model-input");
+      const baseUrl = screen.getByTestId("base-url-input");
+      const apiKey = screen.getByTestId("llm-api-key-input");
+      const agent = screen.getByTestId("agent-input");
+      const confirmation = screen.getByTestId(
+        "enable-confirmation-mode-switch",
+      );
+      const condensor = screen.getByTestId("enable-memory-condenser-switch");
+      const securityAnalyzer = screen.getByTestId("security-analyzer-input");
+
+      await waitFor(() => {
+        expect(model).toHaveValue("openai/gpt-4o");
+        expect(baseUrl).toHaveValue(
+          "https://api.openai.com/v1/chat/completions",
+        );
+        expect(apiKey).toHaveValue("");
+        expect(apiKey).toHaveProperty("placeholder", "<hidden>");
+        expect(agent).toHaveValue("CoActAgent");
+        expect(confirmation).toBeChecked();
+        expect(condensor).not.toBeChecked();
+        expect(securityAnalyzer).toHaveValue("mock-invariant");
+      });
+    });
+  });
+
+  it.todo("should render an indicator if the llm api key is set");
+});
+
+describe("Form submission", () => {
+  it("should submit the basic form with the correct values", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+
+    const provider = screen.getByTestId("llm-provider-input");
+    const model = screen.getByTestId("llm-model-input");
+    const apiKey = screen.getByTestId("llm-api-key-input");
+
+    // select provider
+    await userEvent.click(provider);
+    const providerOption = screen.getByText("OpenAI");
+    await userEvent.click(providerOption);
+    expect(provider).toHaveValue("OpenAI");
+
+    // enter api key
+    await userEvent.type(apiKey, "test-api-key");
+
+    // select model
+    await userEvent.click(model);
+    const modelOption = screen.getByText("gpt-4o");
+    await userEvent.click(modelOption);
+    expect(model).toHaveValue("gpt-4o");
+
+    const submitButton = screen.getByTestId("submit-button");
+    await userEvent.click(submitButton);
+
+    expect(saveSettingsSpy).toHaveBeenCalledWith(
+      expect.objectContaining({
+        llm_model: "openai/gpt-4o",
+        llm_api_key: "test-api-key",
+      }),
+    );
+  });
+
+  it("should submit the advanced form with the correct values", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+
+    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+    await userEvent.click(advancedSwitch);
+
+    const model = screen.getByTestId("llm-custom-model-input");
+    const baseUrl = screen.getByTestId("base-url-input");
+    const apiKey = screen.getByTestId("llm-api-key-input");
+    const agent = screen.getByTestId("agent-input");
+    const confirmation = screen.getByTestId("enable-confirmation-mode-switch");
+    const condensor = screen.getByTestId("enable-memory-condenser-switch");
+
+    // enter custom model
+    await userEvent.clear(model);
+    await userEvent.type(model, "openai/gpt-4o");
+    expect(model).toHaveValue("openai/gpt-4o");
+
+    // enter base url
+    await userEvent.type(baseUrl, "https://api.openai.com/v1/chat/completions");
+    expect(baseUrl).toHaveValue("https://api.openai.com/v1/chat/completions");
+
+    // enter api key
+    await userEvent.type(apiKey, "test-api-key");
+
+    // toggle confirmation mode
+    await userEvent.click(confirmation);
+    expect(confirmation).toBeChecked();
+
+    // toggle memory condensor
+    await userEvent.click(condensor);
+    expect(condensor).not.toBeChecked();
+
+    // select agent
+    await userEvent.click(agent);
+    const agentOption = screen.getByText("CoActAgent");
+    await userEvent.click(agentOption);
+    expect(agent).toHaveValue("CoActAgent");
+
+    // select security analyzer
+    const securityAnalyzer = screen.getByTestId("security-analyzer-input");
+    await userEvent.click(securityAnalyzer);
+    const securityAnalyzerOption = screen.getByText("mock-invariant");
+    await userEvent.click(securityAnalyzerOption);
+
+    const submitButton = screen.getByTestId("submit-button");
+    await userEvent.click(submitButton);
+
+    expect(saveSettingsSpy).toHaveBeenCalledWith(
+      expect.objectContaining({
+        llm_model: "openai/gpt-4o",
+        llm_base_url: "https://api.openai.com/v1/chat/completions",
+        agent: "CoActAgent",
+        confirmation_mode: true,
+        enable_default_condenser: false,
+        security_analyzer: "mock-invariant",
+      }),
+    );
+  });
+
+  it("should disable the button if there are no changes in the basic form", async () => {
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      llm_model: "openai/gpt-4o",
+      llm_api_key_set: true,
+    });
+
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+    screen.getByTestId("llm-settings-form-basic");
+
+    const submitButton = screen.getByTestId("submit-button");
+    expect(submitButton).toBeDisabled();
+
+    const model = screen.getByTestId("llm-model-input");
+    const apiKey = screen.getByTestId("llm-api-key-input");
+
+    // select model
+    await userEvent.click(model);
+    const modelOption = screen.getByText("gpt-4o-mini");
+    await userEvent.click(modelOption);
+    expect(model).toHaveValue("gpt-4o-mini");
+    expect(submitButton).not.toBeDisabled();
+
+    // reset model
+    await userEvent.click(model);
+    const modelOption2 = screen.getByText("gpt-4o");
+    await userEvent.click(modelOption2);
+    expect(model).toHaveValue("gpt-4o");
+    expect(submitButton).toBeDisabled();
+
+    // set api key
+    await userEvent.type(apiKey, "test-api-key");
+    expect(apiKey).toHaveValue("test-api-key");
+    expect(submitButton).not.toBeDisabled();
+
+    // reset api key
+    await userEvent.clear(apiKey);
+    expect(apiKey).toHaveValue("");
+    expect(submitButton).toBeDisabled();
+  });
+
+  it("should disable the button if there are no changes in the advanced form", async () => {
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    getSettingsSpy.mockResolvedValue({
+      ...MOCK_DEFAULT_USER_SETTINGS,
+      llm_model: "openai/gpt-4o",
+      llm_base_url: "https://api.openai.com/v1/chat/completions",
+      llm_api_key_set: true,
+      confirmation_mode: true,
+    });
+
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+    screen.getByTestId("llm-settings-form-advanced");
+
+    const submitButton = screen.getByTestId("submit-button");
+    expect(submitButton).toBeDisabled();
+
+    const model = screen.getByTestId("llm-custom-model-input");
+    const baseUrl = screen.getByTestId("base-url-input");
+    const apiKey = screen.getByTestId("llm-api-key-input");
+    const agent = screen.getByTestId("agent-input");
+    const confirmation = screen.getByTestId("enable-confirmation-mode-switch");
+    const condensor = screen.getByTestId("enable-memory-condenser-switch");
+
+    // enter custom model
+    await userEvent.type(model, "-mini");
+    expect(model).toHaveValue("openai/gpt-4o-mini");
+    expect(submitButton).not.toBeDisabled();
+
+    // reset model
+    await userEvent.clear(model);
+    expect(model).toHaveValue("");
+    expect(submitButton).toBeDisabled();
+
+    await userEvent.type(model, "openai/gpt-4o");
+    expect(model).toHaveValue("openai/gpt-4o");
+    expect(submitButton).toBeDisabled();
+
+    // enter base url
+    await userEvent.type(baseUrl, "/extra");
+    expect(baseUrl).toHaveValue(
+      "https://api.openai.com/v1/chat/completions/extra",
+    );
+    expect(submitButton).not.toBeDisabled();
+
+    await userEvent.clear(baseUrl);
+    expect(baseUrl).toHaveValue("");
+    expect(submitButton).not.toBeDisabled();
+
+    await userEvent.type(baseUrl, "https://api.openai.com/v1/chat/completions");
+    expect(baseUrl).toHaveValue("https://api.openai.com/v1/chat/completions");
+    expect(submitButton).toBeDisabled();
+
+    // set api key
+    await userEvent.type(apiKey, "test-api-key");
+    expect(apiKey).toHaveValue("test-api-key");
+    expect(submitButton).not.toBeDisabled();
+
+    // reset api key
+    await userEvent.clear(apiKey);
+    expect(apiKey).toHaveValue("");
+    expect(submitButton).toBeDisabled();
+
+    // set agent
+    await userEvent.clear(agent);
+    await userEvent.type(agent, "test-agent");
+    expect(agent).toHaveValue("test-agent");
+    expect(submitButton).not.toBeDisabled();
+
+    // reset agent
+    await userEvent.clear(agent);
+    expect(agent).toHaveValue("");
+    expect(submitButton).toBeDisabled();
+
+    await userEvent.type(agent, "CodeActAgent");
+    expect(agent).toHaveValue("CodeActAgent");
+    expect(submitButton).toBeDisabled();
+
+    // toggle confirmation mode
+    await userEvent.click(confirmation);
+    expect(confirmation).not.toBeChecked();
+    expect(submitButton).not.toBeDisabled();
+    await userEvent.click(confirmation);
+    expect(confirmation).toBeChecked();
+    expect(submitButton).toBeDisabled();
+
+    // toggle memory condensor
+    await userEvent.click(condensor);
+    expect(condensor).not.toBeChecked();
+    expect(submitButton).not.toBeDisabled();
+    await userEvent.click(condensor);
+    expect(condensor).toBeChecked();
+    expect(submitButton).toBeDisabled();
+
+    // select security analyzer
+    const securityAnalyzer = screen.getByTestId("security-analyzer-input");
+    await userEvent.click(securityAnalyzer);
+    const securityAnalyzerOption = screen.getByText("mock-invariant");
+    await userEvent.click(securityAnalyzerOption);
+    expect(securityAnalyzer).toHaveValue("mock-invariant");
+
+    expect(submitButton).not.toBeDisabled();
+
+    await userEvent.clear(securityAnalyzer);
+    expect(securityAnalyzer).toHaveValue("");
+    expect(submitButton).toBeDisabled();
+  });
+
+  it("should reset button state when switching between forms", async () => {
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+
+    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+    const submitButton = screen.getByTestId("submit-button");
+
+    expect(submitButton).toBeDisabled();
+
+    // dirty the basic form
+    const apiKey = screen.getByTestId("llm-api-key-input");
+    await userEvent.type(apiKey, "test-api-key");
+    expect(submitButton).not.toBeDisabled();
+
+    await userEvent.click(advancedSwitch);
+    expect(submitButton).toBeDisabled();
+
+    // dirty the advanced form
+    const model = screen.getByTestId("llm-custom-model-input");
+    await userEvent.type(model, "openai/gpt-4o");
+    expect(submitButton).not.toBeDisabled();
+
+    await userEvent.click(advancedSwitch);
+    expect(submitButton).toBeDisabled();
+  });
+
+  // flaky test
+  it.skip("should disable the button when submitting changes", async () => {
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+
+    const apiKey = screen.getByTestId("llm-api-key-input");
+    await userEvent.type(apiKey, "test-api-key");
+
+    const submitButton = screen.getByTestId("submit-button");
+    await userEvent.click(submitButton);
+
+    expect(saveSettingsSpy).toHaveBeenCalledWith(
+      expect.objectContaining({
+        llm_api_key: "test-api-key",
+      }),
+    );
+
+    expect(submitButton).toHaveTextContent("Saving...");
+    expect(submitButton).toBeDisabled();
+
+    await waitFor(() => {
+      expect(submitButton).toHaveTextContent("Save");
+      expect(submitButton).toBeDisabled();
+    });
+  });
+});
+
+describe("Status toasts", () => {
+  describe("Basic form", () => {
+    it("should call displaySuccessToast when the settings are saved", async () => {
+      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+      const displaySuccessToastSpy = vi.spyOn(
+        ToastHandlers,
+        "displaySuccessToast",
+      );
+
+      renderLlmSettingsScreen();
+
+      // Toggle setting to change
+      const apiKeyInput = await screen.findByTestId("llm-api-key-input");
+      await userEvent.type(apiKeyInput, "test-api-key");
+
+      const submit = await screen.findByTestId("submit-button");
+      await userEvent.click(submit);
+
+      expect(saveSettingsSpy).toHaveBeenCalled();
+      await waitFor(() => expect(displaySuccessToastSpy).toHaveBeenCalled());
+    });
+
+    it("should call displayErrorToast when the settings fail to save", async () => {
+      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+      const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
+
+      saveSettingsSpy.mockRejectedValue(new Error("Failed to save settings"));
+
+      renderLlmSettingsScreen();
+
+      // Toggle setting to change
+      const apiKeyInput = await screen.findByTestId("llm-api-key-input");
+      await userEvent.type(apiKeyInput, "test-api-key");
+
+      const submit = await screen.findByTestId("submit-button");
+      await userEvent.click(submit);
+
+      expect(saveSettingsSpy).toHaveBeenCalled();
+      expect(displayErrorToastSpy).toHaveBeenCalled();
+    });
+  });
+
+  describe("Advanced form", () => {
+    it("should call displaySuccessToast when the settings are saved", async () => {
+      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+      const displaySuccessToastSpy = vi.spyOn(
+        ToastHandlers,
+        "displaySuccessToast",
+      );
+
+      renderLlmSettingsScreen();
+      await screen.findByTestId("llm-settings-screen");
+
+      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+      await userEvent.click(advancedSwitch);
+      await screen.findByTestId("llm-settings-form-advanced");
+
+      // Toggle setting to change
+      const apiKeyInput = await screen.findByTestId("llm-api-key-input");
+      await userEvent.type(apiKeyInput, "test-api-key");
+
+      const submit = await screen.findByTestId("submit-button");
+      await userEvent.click(submit);
+
+      expect(saveSettingsSpy).toHaveBeenCalled();
+      await waitFor(() => expect(displaySuccessToastSpy).toHaveBeenCalled());
+    });
+
+    it("should call displayErrorToast when the settings fail to save", async () => {
+      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+      const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
+
+      saveSettingsSpy.mockRejectedValue(new Error("Failed to save settings"));
+
+      renderLlmSettingsScreen();
+      await screen.findByTestId("llm-settings-screen");
+
+      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+      await userEvent.click(advancedSwitch);
+      await screen.findByTestId("llm-settings-form-advanced");
+
+      // Toggle setting to change
+      const apiKeyInput = await screen.findByTestId("llm-api-key-input");
+      await userEvent.type(apiKeyInput, "test-api-key");
+
+      const submit = await screen.findByTestId("submit-button");
+      await userEvent.click(submit);
+
+      expect(saveSettingsSpy).toHaveBeenCalled();
+      expect(displayErrorToastSpy).toHaveBeenCalled();
+    });
+  });
+});
+
+describe("SaaS mode", () => {
+  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",
+    });
+
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+
+    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+    await userEvent.click(advancedSwitch);
+    await screen.findByTestId("llm-settings-form-advanced");
+
+    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
+    expect(runtimeSettingsInput).not.toBeInTheDocument();
+  });
+
+  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",
+    });
+
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+
+    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+    await userEvent.click(advancedSwitch);
+    await screen.findByTestId("llm-settings-form-advanced");
+
+    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
+    expect(runtimeSettingsInput).toBeInTheDocument();
+  });
+
+  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",
+    });
+
+    renderLlmSettingsScreen();
+    await screen.findByTestId("llm-settings-screen");
+
+    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
+    await userEvent.click(advancedSwitch);
+    await screen.findByTestId("llm-settings-form-advanced");
+
+    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
+    expect(runtimeSettingsInput).toBeInTheDocument();
+    expect(runtimeSettingsInput).toBeDisabled();
+  });
+});

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

@@ -1,4 +1,4 @@
-import { screen, waitFor, within } from "@testing-library/react";
+import { screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
 import { createRoutesStub } from "react-router";
@@ -7,6 +7,30 @@ import OpenHands from "#/api/open-hands";
 import SettingsScreen from "#/routes/settings";
 import { PaymentForm } from "#/components/features/payment/payment-form";
 
+// Mock the i18next hook
+vi.mock("react-i18next", async () => {
+  const actual = await vi.importActual<typeof import("react-i18next")>("react-i18next");
+  return {
+    ...actual,
+    useTranslation: () => ({
+      t: (key: string) => {
+        const translations: Record<string, string> = {
+          "SETTINGS$NAV_GIT": "Git",
+          "SETTINGS$NAV_APPLICATION": "Application",
+          "SETTINGS$NAV_CREDITS": "Credits",
+          "SETTINGS$NAV_API_KEYS": "API Keys",
+          "SETTINGS$NAV_LLM": "LLM",
+          "SETTINGS$TITLE": "Settings"
+        };
+        return translations[key] || key;
+      },
+      i18n: {
+        changeLanguage: vi.fn(),
+      },
+    }),
+  };
+});
+
 describe("Settings Billing", () => {
   const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
 
@@ -19,18 +43,22 @@ describe("Settings Billing", () => {
           Component: () => <PaymentForm />,
           path: "/settings/billing",
         },
+        {
+          Component: () => <div data-testid="git-settings-screen" />,
+          path: "/settings/git",
+        },
       ],
     },
   ]);
 
   const renderSettingsScreen = () =>
-    renderWithProviders(<RoutesStub initialEntries={["/settings"]} />);
+    renderWithProviders(<RoutesStub initialEntries={["/settings/billing"]} />);
 
   afterEach(() => {
     vi.clearAllMocks();
   });
 
-  it("should not render the navbar if OSS mode", async () => {
+  it("should not render the credits tab if OSS mode", async () => {
     getConfigSpy.mockResolvedValue({
       APP_MODE: "oss",
       GITHUB_CLIENT_ID: "123",
@@ -43,13 +71,12 @@ describe("Settings Billing", () => {
 
     renderSettingsScreen();
 
-    await waitFor(() => {
-      const navbar = screen.queryByTestId("settings-navbar");
-      expect(navbar).not.toBeInTheDocument();
-    });
+    const navbar = await screen.findByTestId("settings-navbar");
+    const credits = within(navbar).queryByText("Credits");
+    expect(credits).not.toBeInTheDocument();
   });
 
-  it("should render the navbar if SaaS mode", async () => {
+  it("should render the credits tab if SaaS mode and billing is enabled", async () => {
     getConfigSpy.mockResolvedValue({
       APP_MODE: "saas",
       GITHUB_CLIENT_ID: "123",
@@ -62,11 +89,8 @@ describe("Settings Billing", () => {
 
     renderSettingsScreen();
 
-    await waitFor(() => {
-      const navbar = screen.getByTestId("settings-navbar");
-      within(navbar).getByText("Account");
-      within(navbar).getByText("Credits");
-    });
+    const navbar = await screen.findByTestId("settings-navbar");
+    within(navbar).getByText("Credits");
   });
 
   it("should render the billing settings if clicking the credits item", async () => {
@@ -88,6 +112,6 @@ describe("Settings Billing", () => {
     await user.click(credits);
 
     const billingSection = await screen.findByTestId("billing-settings");
-    within(billingSection).getByText("PAYMENT$MANAGE_CREDITS");
+    expect(billingSection).toBeInTheDocument();
   });
 });

frontend/__tests__/services/observations.test.ts

@@ -48,4 +48,4 @@ describe("Observations Service", () => {
       });
     });
   });
-});
+});

frontend/__tests__/utils/group-suggested-tasks.test.ts

@@ -0,0 +1,101 @@
+import { expect, test } from "vitest";
+import {
+  SuggestedTask,
+  SuggestedTaskGroup,
+} from "#/components/features/home/tasks/task.types";
+import { groupSuggestedTasks } from "#/utils/group-suggested-tasks";
+
+const rawTasks: SuggestedTask[] = [
+  {
+    issue_number: 1,
+    repo: "repo1",
+    title: "Task 1",
+    task_type: "MERGE_CONFLICTS",
+    git_provider: "github",
+  },
+  {
+    issue_number: 2,
+    repo: "repo1",
+    title: "Task 2",
+    task_type: "FAILING_CHECKS",
+    git_provider: "github",
+  },
+  {
+    issue_number: 3,
+    repo: "repo2",
+    title: "Task 3",
+    task_type: "UNRESOLVED_COMMENTS",
+    git_provider: "github",
+  },
+  {
+    issue_number: 4,
+    repo: "repo2",
+    title: "Task 4",
+    task_type: "OPEN_ISSUE",
+    git_provider: "github",
+  },
+  {
+    issue_number: 5,
+    repo: "repo3",
+    title: "Task 5",
+    task_type: "FAILING_CHECKS",
+    git_provider: "github",
+  },
+];
+
+const groupedTasks: SuggestedTaskGroup[] = [
+  {
+    title: "repo1",
+    tasks: [
+      {
+        issue_number: 1,
+        repo: "repo1",
+        title: "Task 1",
+        task_type: "MERGE_CONFLICTS",
+        git_provider: "github",
+      },
+      {
+        issue_number: 2,
+        repo: "repo1",
+        title: "Task 2",
+        task_type: "FAILING_CHECKS",
+        git_provider: "github",
+      },
+    ],
+  },
+  {
+    title: "repo2",
+    tasks: [
+      {
+        issue_number: 3,
+        repo: "repo2",
+        title: "Task 3",
+        task_type: "UNRESOLVED_COMMENTS",
+        git_provider: "github",
+      },
+      {
+        issue_number: 4,
+        repo: "repo2",
+        title: "Task 4",
+        task_type: "OPEN_ISSUE",
+        git_provider: "github",
+      },
+    ],
+  },
+  {
+    title: "repo3",
+    tasks: [
+      {
+        issue_number: 5,
+        repo: "repo3",
+        title: "Task 5",
+        task_type: "FAILING_CHECKS",
+        git_provider: "github",
+      },
+    ],
+  },
+];
+
+test("groupSuggestedTasks", () => {
+  expect(groupSuggestedTasks(rawTasks)).toEqual(groupedTasks);
+});

frontend/__tests__/utils/has-advanced-settings-set.test.ts

@@ -7,6 +7,10 @@ describe("hasAdvancedSettingsSet", () => {
     expect(hasAdvancedSettingsSet(DEFAULT_SETTINGS)).toBe(false);
   });
 
+  it("should return false if an empty object", () => {
+    expect(hasAdvancedSettingsSet({})).toBe(false);
+  });
+
   describe("should be true if", () => {
     test("LLM_BASE_URL is set", () => {
       expect(
@@ -26,15 +30,6 @@ describe("hasAdvancedSettingsSet", () => {
       ).toBe(true);
     });
 
-    test("REMOTE_RUNTIME_RESOURCE_FACTOR is not default value", () => {
-      expect(
-        hasAdvancedSettingsSet({
-          ...DEFAULT_SETTINGS,
-          REMOTE_RUNTIME_RESOURCE_FACTOR: 999,
-        }),
-      ).toBe(true);
-    });
-
     test("CONFIRMATION_MODE is true", () => {
       expect(
         hasAdvancedSettingsSet({

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.32.0",
+  "version": "0.34.0",
   "private": true,
   "type": "module",
   "engines": {
@@ -8,44 +8,46 @@
   },
   "dependencies": {
     "@heroui/react": "2.7.6",
+    "@microlink/react-json-view": "^1.26.1",
     "@monaco-editor/react": "^4.7.0-rc.0",
-    "@react-router/node": "^7.5.0",
-    "@react-router/serve": "^7.5.0",
-    "@react-types/shared": "^3.28.0",
-    "@reduxjs/toolkit": "^2.6.1",
+    "@react-router/node": "^7.5.2",
+    "@react-router/serve": "^7.5.2",
+    "@react-types/shared": "^3.29.0",
+    "@reduxjs/toolkit": "^2.7.0",
     "@stripe/react-stripe-js": "^3.6.0",
-    "@stripe/stripe-js": "^7.0.0",
-    "@tanstack/react-query": "^5.72.1",
-    "@vitejs/plugin-react": "^4.3.2",
+    "@stripe/stripe-js": "^7.2.0",
+    "@tanstack/react-query": "^5.74.7",
+    "@vitejs/plugin-react": "^4.4.0",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
-    "axios": "^1.8.4",
+    "axios": "^1.9.0",
     "clsx": "^2.1.1",
     "eslint-config-airbnb-typescript": "^18.0.0",
-    "framer-motion": "^12.6.3",
-    "i18next": "^24.2.3",
-    "i18next-browser-languagedetector": "^8.0.4",
+    "framer-motion": "^12.9.2",
+    "i18next": "^25.0.1",
+    "i18next-browser-languagedetector": "^8.0.5",
     "i18next-http-backend": "^3.0.2",
-    "isbot": "^5.1.25",
+    "isbot": "^5.1.27",
     "jose": "^6.0.10",
+    "lucide-react": "^0.503.0",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.235.0",
+    "posthog-js": "^1.236.7",
     "react": "^19.1.0",
     "react-dom": "^19.1.0",
     "react-highlight": "^0.15.0",
     "react-hot-toast": "^2.5.1",
-    "react-i18next": "^15.4.1",
+    "react-i18next": "^15.5.1",
     "react-icons": "^5.5.0",
     "react-markdown": "^10.1.0",
     "react-redux": "^9.2.0",
-    "react-router": "^7.5.0",
+    "react-router": "^7.5.2",
     "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.9",
     "remark-gfm": "^4.0.1",
     "sirv-cli": "^3.0.1",
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^3.2.0",
-    "vite": "^6.2.5",
+    "vite": "^6.3.3",
     "web-vitals": "^3.5.2",
     "ws": "^8.18.1"
   },
@@ -79,29 +81,29 @@
     "@babel/traverse": "^7.27.0",
     "@babel/types": "^7.27.0",
     "@mswjs/socket.io-binding": "^0.1.1",
-    "@playwright/test": "^1.51.1",
-    "@react-router/dev": "^7.5.0",
+    "@playwright/test": "^1.52.0",
+    "@react-router/dev": "^7.5.2",
     "@tailwindcss/typography": "^0.5.16",
-    "@tanstack/eslint-plugin-query": "^5.72.1",
+    "@tanstack/eslint-plugin-query": "^5.74.7",
     "@testing-library/dom": "^10.4.0",
     "@testing-library/jest-dom": "^6.6.1",
     "@testing-library/react": "^16.3.0",
     "@testing-library/user-event": "^14.6.1",
-    "@types/node": "^22.14.0",
-    "@types/react": "^19.1.0",
+    "@types/node": "^22.15.3",
+    "@types/react": "^19.1.2",
     "@types/react-dom": "^19.1.1",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
     "@types/ws": "^8.18.1",
     "@typescript-eslint/eslint-plugin": "^7.18.0",
     "@typescript-eslint/parser": "^7.18.0",
-    "@vitest/coverage-v8": "^3.1.1",
+    "@vitest/coverage-v8": "^3.1.2",
     "autoprefixer": "^10.4.21",
     "cross-env": "^7.0.3",
     "eslint": "^8.57.0",
     "eslint-config-airbnb": "^19.0.4",
     "eslint-config-airbnb-typescript": "^18.0.0",
-    "eslint-config-prettier": "^10.1.1",
+    "eslint-config-prettier": "^10.1.2",
     "eslint-plugin-import": "^2.29.1",
     "eslint-plugin-jsx-a11y": "^6.10.2",
     "eslint-plugin-prettier": "^5.2.6",
@@ -109,8 +111,8 @@
     "eslint-plugin-react-hooks": "^4.6.2",
     "eslint-plugin-unused-imports": "^4.1.4",
     "husky": "^9.1.7",
-    "jsdom": "^26.0.0",
-    "lint-staged": "^15.5.0",
+    "jsdom": "^26.1.0",
+    "lint-staged": "^15.5.1",
     "msw": "^2.6.6",
     "postcss": "^8.5.2",
     "prettier": "^3.5.3",

frontend/public/mockServiceWorker.js

@@ -8,7 +8,7 @@
  * - Please do NOT serve this file on production.
  */
 
-const PACKAGE_VERSION = '2.7.3'
+const PACKAGE_VERSION = '2.7.5'
 const INTEGRITY_CHECKSUM = '00729d72e3b82faf54ca8b9621dbb96f'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()

frontend/scripts/check-unlocalized-strings.cjs

@@ -39,6 +39,7 @@ const IGNORE_PATHS = [
   "entry.client.tsx", // Client entry point
   "utils/scan-unlocalized-strings.ts", // Original scanner
   "utils/scan-unlocalized-strings-ast.ts", // This file itself
+  "frontend/src/components/features/home/tasks/get-prompt-for-query.ts", // Only contains agent prompts
 ];
 
 // Extensions to scan
@@ -105,6 +106,11 @@ function isRawTranslationKey(str) {
 // Specific technical strings that should be excluded from localization
 const EXCLUDED_TECHNICAL_STRINGS = [
   "openid email profile", // OAuth scope string - not user-facing
+  "OPEN_ISSUE", // Task type identifier, not a UI string
+  "Merge Request", // Git provider specific terminology
+  "GitLab API", // Git provider specific terminology
+  "Pull Request", // Git provider specific terminology
+  "GitHub API", // Git provider specific terminology
 ];
 
 function isExcludedTechnicalString(str) {
@@ -275,8 +281,8 @@ function isCommonDevelopmentString(str) {
 
   // HTML tags and attributes
   if (
-    /^<[a-z0-9]+>.*<\/[a-z0-9]+>$/.test(str) ||
-    /^<[a-z0-9]+ [^>]+\/>$/.test(str)
+    /^<[a-z0-9]+(?:\s[^>]*)?>.*<\/[a-z0-9]+>$/i.test(str) ||
+    /^<[a-z0-9]+ [^>]+\/>$/i.test(str)
   ) {
     return true;
   }

frontend/src/api/api-keys.ts

@@ -0,0 +1,49 @@
+import { openHands } from "./open-hands-axios";
+
+export interface ApiKey {
+  id: string;
+  name: string;
+  prefix: string;
+  created_at: string;
+  last_used_at: string | null;
+}
+
+export interface CreateApiKeyResponse {
+  id: string;
+  name: string;
+  key: string; // Full key, only returned once upon creation
+  prefix: string;
+  created_at: string;
+}
+
+class ApiKeysClient {
+  /**
+   * Get all API keys for the current user
+   */
+  static async getApiKeys(): Promise<ApiKey[]> {
+    const { data } = await openHands.get<unknown>("/api/keys");
+    // Ensure we always return an array, even if the API returns something else
+    return Array.isArray(data) ? (data as ApiKey[]) : [];
+  }
+
+  /**
+   * Create a new API key
+   * @param name - A descriptive name for the API key
+   */
+  static async createApiKey(name: string): Promise<CreateApiKeyResponse> {
+    const { data } = await openHands.post<CreateApiKeyResponse>("/api/keys", {
+      name,
+    });
+    return data;
+  }
+
+  /**
+   * Delete an API key
+   * @param id - The ID of the API key to delete
+   */
+  static async deleteApiKey(id: string): Promise<void> {
+    await openHands.delete(`/api/keys/${id}`);
+  }
+}
+
+export default ApiKeysClient;

frontend/src/api/open-hands.ts

@@ -8,10 +8,14 @@ import {
   Conversation,
   ResultSet,
   GetTrajectoryResponse,
+  GitChangeDiff,
+  GitChange,
+  ConversationTrigger,
 } from "./open-hands.types";
 import { openHands } from "./open-hands-axios";
 import { ApiSettings, PostApiSettings } from "#/types/settings";
 import { GitUser, GitRepository } from "#/types/git";
+import { SuggestedTask } from "#/components/features/home/tasks/task.types";
 
 class OpenHands {
   /**
@@ -147,17 +151,21 @@ class OpenHands {
   }
 
   static async createConversation(
+    conversation_trigger: ConversationTrigger = "gui",
     selectedRepository?: GitRepository,
     initialUserMsg?: string,
     imageUrls?: string[],
     replayJson?: string,
+    suggested_task?: SuggestedTask,
   ): Promise<Conversation> {
     const body = {
+      conversation_trigger,
       selected_repository: selectedRepository,
       selected_branch: undefined,
       initial_user_msg: initialUserMsg,
       image_urls: imageUrls,
       replay_json: replayJson,
+      suggested_task,
     };
 
     const { data } = await openHands.post<Conversation>(
@@ -197,14 +205,6 @@ class OpenHands {
     return data.status === 200;
   }
 
-  /**
-   * Reset user settings in server
-   */
-  static async resetSettings(): Promise<boolean> {
-    const response = await openHands.post("/api/reset-settings");
-    return response.status === 200;
-  }
-
   static async createCheckoutSession(amount: number): Promise<string> {
     const { data } = await openHands.post(
       "/api/billing/create-checkout-session",
@@ -277,6 +277,26 @@ class OpenHands {
       appMode === "saas" ? "/api/logout" : "/api/unset-settings-tokens";
     await openHands.post(endpoint);
   }
+
+  static async getGitChanges(conversationId: string): Promise<GitChange[]> {
+    const { data } = await openHands.get<GitChange[]>(
+      `/api/conversations/${conversationId}/git/changes`,
+    );
+    return data;
+  }
+
+  static async getGitChangeDiff(
+    conversationId: string,
+    path: string,
+  ): Promise<GitChangeDiff> {
+    const { data } = await openHands.get<GitChangeDiff>(
+      `/api/conversations/${conversationId}/git/diff`,
+      {
+        params: { path },
+      },
+    );
+    return data;
+  }
 }
 
 export default OpenHands;

frontend/src/api/open-hands.types.ts

@@ -70,6 +70,8 @@ export interface AuthenticateResponse {
   error?: string;
 }
 
+export type ConversationTrigger = "resolver" | "gui" | "suggested_task";
+
 export interface Conversation {
   conversation_id: string;
   title: string;
@@ -77,9 +79,22 @@ export interface Conversation {
   last_updated_at: string;
   created_at: string;
   status: ProjectStatus;
+  trigger?: ConversationTrigger;
 }
 
 export interface ResultSet<T> {
   results: T[];
   next_page_id: string | null;
 }
+
+export type GitChangeStatus = "M" | "A" | "D" | "R" | "U";
+
+export interface GitChange {
+  status: GitChangeStatus;
+  path: string;
+}
+
+export interface GitChangeDiff {
+  modified: string;
+  original: string;
+}

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

@@ -0,0 +1,9 @@
+import { SuggestedTask } from "#/components/features/home/tasks/task.types";
+import { openHands } from "../open-hands-axios";
+
+export class SuggestionsService {
+  static async getSuggestedTasks(): Promise<SuggestedTask[]> {
+    const { data } = await openHands.get("/api/user/suggested-tasks");
+    return data;
+  }
+}