Feat/stagehand

apps/sim/app/api/tools/stagehand/agent/route.ts

@@ -774,13 +774,12 @@ IMPORTANT: For any form fields that require sensitive information like usernames
 1. If you see placeholders like %username% or %password% in the task, DO NOT ask for the actual values.
 2. If you need to type in login forms, use the EXACT placeholder text (e.g., "%username%" or "%password%") UNLESS instructed otherwise.
 3. The system will automatically substitute the real values when you use these placeholders IF direct login was not attempted.
-4. Example correct approach: "type %username% in the username field".${
-          variablesObject && Object.keys(variablesObject).length > 0
+4. Example correct approach: "type %username% in the username field".${variablesObject && Object.keys(variablesObject).length > 0
             ? `\n5. Available variables: ${Object.keys(variablesObject)
-                .map((k) => `%${k}%`)
-                .join(', ')}`
+              .map((k) => `%${k}%`)
+              .join(', ')}`
             : ''
-        }\n
+          }\n
 WEBSITE NAVIGATION GUIDANCE:
 1. If you need to log in but don't see a login form, LOOK for login buttons or links (they might say "Login" or "Sign in").
 2. If you're on a login page but don't see a username/password form, try scrolling or looking for "Continue with email" or similar options.

apps/sim/app/api/tools/stagehand/extract/route.ts

@@ -18,6 +18,32 @@ const requestSchema = z.object({
   selector: z.string().nullable().optional(),
   apiKey: z.string(),
   url: z.string().url(),
+  model: z.enum([
+    "gpt-4o",
+    "gpt-4o-mini",
+    "gpt-4o-2024-08-06",
+    "gpt-4.5-preview",
+    "claude-3-5-sonnet-latest",
+    "claude-3-5-sonnet-20241022",
+    "claude-3-5-sonnet-20240620",
+    "claude-3-7-sonnet-latest",
+    "claude-3-7-sonnet-20250219",
+    "o1-mini",
+    "o1-preview",
+    "o3-mini",
+    "gemini-2.0-flash",
+    "gemini-1.5-flash",
+    "gemini-1.5-pro",
+    "gemini-1.5-flash-8b",
+    "gemini-2.0-flash-lite",
+    "gemini-2.0-flash",
+    "gemini-2.5-pro-preview-03-25",
+    "cerebras-llama-3.3-70b",
+    "cerebras-llama-3.1-8b",
+    "groq-llama-3.3-70b-versatile",
+    "groq-llama-3.3-70b-specdec"
+  ]),
+  env: z.enum(['browserbase', 'local']),
 })
 
 export async function POST(request: NextRequest) {
@@ -34,6 +60,7 @@ export async function POST(request: NextRequest) {
     const validationResult = requestSchema.safeParse(body)
 
     if (!validationResult.success) {
+
       logger.error('Invalid request body', { errors: validationResult.error.errors })
       return NextResponse.json(
         { error: 'Invalid request parameters', details: validationResult.error.errors },
@@ -42,7 +69,7 @@ export async function POST(request: NextRequest) {
     }
 
     const params = validationResult.data
-    const { url: rawUrl, instruction, selector, useTextExtract, apiKey, schema } = params
+    const { url: rawUrl, instruction, selector, useTextExtract, apiKey, schema, model, env } = params
     const url = normalizeUrl(rawUrl)
 
     logger.info('Starting Stagehand extraction process', {
@@ -61,7 +88,7 @@ export async function POST(request: NextRequest) {
       )
     }
 
-    if (!BROWSERBASE_API_KEY || !BROWSERBASE_PROJECT_ID) {
+    if (env === 'browserbase' && (!BROWSERBASE_API_KEY || !BROWSERBASE_PROJECT_ID)) {
       logger.error('Missing required environment variables', {
         hasBrowserbaseApiKey: !!BROWSERBASE_API_KEY,
         hasBrowserbaseProjectId: !!BROWSERBASE_PROJECT_ID,
@@ -73,24 +100,30 @@ export async function POST(request: NextRequest) {
       )
     }
 
-    if (!apiKey || typeof apiKey !== 'string' || !apiKey.startsWith('sk-')) {
-      logger.error('Invalid OpenAI API key format')
-      return NextResponse.json({ error: 'Invalid OpenAI API key format' }, { status: 400 })
+    if (!apiKey || typeof apiKey !== 'string') {
+      logger.error('Invalid API key format')
+      return NextResponse.json({ error: 'Invalid API key format' }, { status: 400 })
     }
 
     try {
       logger.info('Initializing Stagehand with Browserbase')
       stagehand = new Stagehand({
-        env: 'BROWSERBASE',
+        env: env === 'browserbase' ? 'BROWSERBASE' : 'LOCAL',
         apiKey: BROWSERBASE_API_KEY,
         projectId: BROWSERBASE_PROJECT_ID,
         verbose: 1,
         logger: (msg) => logger.info(typeof msg === 'string' ? msg : JSON.stringify(msg)),
         disablePino: true,
-        modelName: 'gpt-4o',
+        modelName: model,
         modelClientOptions: {
           apiKey: apiKey,
         },
+        ...(env === 'local' && {
+          localBrowserLaunchOptions: {
+            headless: true,
+            executablePath: "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe",
+          }
+        })
       })
 
       logger.info('Starting stagehand.init()')

apps/sim/blocks/blocks/stagehand.ts

@@ -33,12 +33,55 @@ export const StagehandBlock: BlockConfig<StagehandExtractResponse> = {
       layout: 'full',
       placeholder: 'Enter detailed instructions for what data to extract from the page...',
     },
+    {
+      id: "env",
+      title: 'Environment',
+      type: 'combobox',
+      layout: 'full',
+      placeholder: 'Select the environment for extraction',
+      options: [
+        { id: 'browserbase', label: 'Browserbase' },
+        { id: "local", label: 'Local (Chromium)' },
+      ],
+    },
+    {
+      id: "model",
+      title: 'Model',
+      type: "combobox",
+      placeholder: 'Select the model to use for extraction',
+      layout: 'full',
+      options: [
+        { id: 'gpt-4o', label: 'gpt-4o' },
+        { id: 'gpt-4o-mini', label: 'gpt-4o-mini' },
+        { id: 'gpt-4o-2024-08-06', label: 'gpt-4o-2024-08-06' },
+        { id: 'gpt-4.5-preview', label: 'gpt-4.5-preview' },
+        { id: 'claude-3-5-sonnet-latest', label: 'claude-3-5-sonnet-latest' },
+        { id: 'claude-3-5-sonnet-20241022', label: 'claude-3-5-sonnet-20241022' },
+        { id: 'claude-3-5-sonnet-20240620', label: 'claude-3-5-sonnet-20240620' },
+        { id: 'claude-3-7-sonnet-latest', label: 'claude-3-7-sonnet-latest' },
+        { id: 'claude-3-7-sonnet-20250219', label: 'claude-3-7-sonnet-20250219' },
+        { id: 'o1-mini', label: 'o1-mini' },
+        { id: 'o1-preview', label: 'o1-preview' },
+        { id: 'o3-mini', label: 'o3-mini' },
+        { id: 'gemini-2.0-flash', label: 'gemini-2.0-flash' },
+        { id: 'gemini-1.5-flash', label: 'gemini-1.5-flash' },
+        { id: 'gemini-1.5-pro', label: 'gemini-1.5-pro' },
+        { id: 'gemini-1.5-flash-8b', label: 'gemini-1.5-flash-8b' },
+        { id: 'gemini-2.0-flash-lite', label: 'gemini-2.0-flash-lite' },
+        { id: 'gemini-2.0-flash', label: 'gemini-2.0-flash' },
+        { id: 'gemini-2.5-pro-preview-03-25', label: 'gemini-2.5-pro-preview-03-25' },
+        { id: 'cerebras-llama-3.3-70b', label: 'cerebras-llama-3.3-70b' },
+        { id: 'cerebras-llama-3.1-8b', label: 'cerebras-llama-3.1-8b' },
+        { id: 'groq-llama-3.3-70b-versatile', label: 'groq-llama-3.3-70b-versatile' },
+        { id: 'groq-llama-3.3-70b-specdec', label: 'groq-llama-3.3-70b-specdec' }
+      ]
+    },
     {
       id: 'apiKey',
-      title: 'OpenAI API Key',
+      title: 'API Key',
       type: 'short-input',
       layout: 'full',
-      placeholder: 'Enter your OpenAI API key',
+      placeholder: 'Enter your API key',
       password: true,
     },
     {
@@ -62,6 +105,8 @@ export const StagehandBlock: BlockConfig<StagehandExtractResponse> = {
     instruction: { type: 'string', required: true },
     schema: { type: 'json', required: true },
     apiKey: { type: 'string', required: true },
+    model: { type: 'string', required: true },
+    env: { type: 'string', required: true, },
   },
   outputs: {
     response: {

apps/sim/drizzle.config.ts

@@ -8,4 +8,5 @@ export default {
   dbCredentials: {
     url: env.DATABASE_URL,
   },
+
 } satisfies Config

apps/sim/tools/stagehand/extract.ts

@@ -21,6 +21,16 @@ export const extractTool: ToolConfig<StagehandExtractParams, StagehandExtractRes
       required: true,
       description: 'JSON schema defining the structure of the data to extract',
     },
+    model: {
+      type: 'string',
+      required: true,
+      description: 'Model to use for extraction (e.g., gpt-4o, claude-3-5-sonnet)',
+    },
+    env: {
+      type: 'string',
+      required: true,
+      description: 'Environment for extraction (browserbase or local)',
+    },
     apiKey: {
       type: 'string',
       required: true,
@@ -44,6 +54,8 @@ export const extractTool: ToolConfig<StagehandExtractParams, StagehandExtractRes
       schema: params.schema,
       apiKey: params.apiKey,
       url: params.url,
+      model: params.model,
+      env: params.env,
     }),
   },
 

apps/sim/tools/stagehand/types.ts

@@ -6,6 +6,8 @@ export interface StagehandExtractParams {
   schema: Record<string, any>
   apiKey: string
   url: string
+  model: string
+  env: 'browserbase' | 'local'
 }
 
 export interface StagehandExtractResponse extends ToolResponse {

bun.lock

@@ -173,7 +173,7 @@
     },
     "packages/cli": {
       "name": "simstudio",
-      "version": "0.1.18",
+      "version": "0.1.19",
       "bin": {
         "simstudio": "dist/index.js",
       },

docker-compose.prod.yml

@@ -3,7 +3,7 @@ services:
     image: ghcr.io/simstudioai/simstudio:latest
     restart: unless-stopped
     ports:
-      - '3000:3000'
+      - "3000:3000"
     deploy:
       resources:
         limits:
@@ -30,7 +30,7 @@ services:
       realtime:
         condition: service_healthy
     healthcheck:
-      test: ['CMD', 'wget', '--spider', '--quiet', 'http://127.0.0.1:3000']
+      test: ["CMD", "wget", "--spider", "--quiet", "http://127.0.0.1:3000"]
       interval: 90s
       timeout: 5s
       retries: 3
@@ -40,7 +40,7 @@ services:
     image: ghcr.io/simstudioai/realtime:latest
     restart: unless-stopped
     ports:
-      - '3002:3002'
+      - "3002:3002"
     deploy:
       resources:
         limits:
@@ -54,7 +54,7 @@ services:
       db:
         condition: service_healthy
     healthcheck:
-      test: ['CMD', 'wget', '--spider', '--quiet', 'http://127.0.0.1:3002']
+      test: ["CMD", "wget", "--spider", "--quiet", "http://127.0.0.1:3002"]
       interval: 90s
       timeout: 5s
       retries: 3
@@ -67,22 +67,22 @@ services:
     depends_on:
       db:
         condition: service_healthy
-    command: ['bun', 'run', 'db:migrate']
-    restart: 'no'
+    command: ["bun", "run", "db:migrate"]
+    restart: "no"
 
   db:
     image: pgvector/pgvector:pg17
     restart: unless-stopped
     ports:
-      - '5432:5432'
+      - "5432:5432"
     environment:
       - POSTGRES_USER=${POSTGRES_USER:-postgres}
       - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-postgres}
       - POSTGRES_DB=${POSTGRES_DB:-simstudio}
     volumes:
       - postgres_data:/var/lib/postgresql/data
     healthcheck:
-      test: ['CMD-SHELL', 'pg_isready -U postgres']
+      test: ["CMD-SHELL", "pg_isready -U postgres"]
       interval: 5s
       timeout: 5s
       retries: 5