Upgrade browser-use library from v0.1.48 to v0.9.4

Dockerfile

@@ -45,6 +45,7 @@ RUN apt-get update && apt-get install -y \
     fonts-dejavu-core \
     fonts-dejavu-extra \
     vim \
+    pipx \
     && rm -rf /var/lib/apt/lists/*
 
 # Install noVNC
@@ -70,20 +71,28 @@ WORKDIR /app
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Playwright setup
-ENV PLAYWRIGHT_BROWSERS_PATH=/ms-browsers
-RUN mkdir -p $PLAYWRIGHT_BROWSERS_PATH
+# Install uv and uvx for browser-use
+RUN pip install --no-cache-dir uv
 
-# Install Chromium via Playwright without --with-deps
-RUN PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=0 playwright install chromium
+# Install Chromium browser for browser-use
+RUN apt-get update \
+    && apt-get install -y chromium chromium-driver \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set Chrome path for browser-use
+ENV CHROME_BIN=/usr/bin/chromium
+ENV DISPLAY=:99
+
+# Also create a symlink for uvx
+RUN ln -s /usr/local/bin/uv /usr/local/bin/uvx || true
 
 # Copy application code
 COPY . .
 
-# Set up supervisor configuration
-RUN mkdir -p /var/log/supervisor
+# Set up supervisor configuration and DBus
+RUN mkdir -p /var/log/supervisor /run/dbus
 COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
 
-EXPOSE 7788 6080 5901 9222
+EXPOSE 7788 6080 5901 9222 3000
 
 CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

README.md

@@ -55,22 +55,7 @@ Activate the virtual environment:
 source .venv/bin/activate
 ```
 
-#### Step 3: Install Dependencies
-Install Python packages:
-```bash
-uv pip install -r requirements.txt
-```
-
-Install Browsers in playwright. 
-```bash
-playwright install --with-deps
-```
-Or you can install specific browsers by running:
-```bash
-playwright install chromium --with-deps
-```
-
-#### Step 4: Configure Environment
+#### Step 3: Configure Environment
 1. Create a copy of the example environment file:
 - Windows (Command Prompt):
 ```bash
@@ -82,7 +67,7 @@ cp .env.example .env
 ```
 2. Open `.env` in your preferred text editor and add your API keys and other settings
 
-#### Step 5: Enjoy the web-ui
+#### Step 4: Enjoy the web-ui
 1.  **Run the WebUI:**
     ```bash
     python webui.py --ip 127.0.0.1 --port 7788

docker-compose.yml

@@ -54,9 +54,6 @@ services:
 
       # Display Settings
       - DISPLAY=:99
-      # This ENV is used by the Dockerfile during build time if playwright respects it.
-      # It's not strictly needed at runtime by docker-compose unless your app or scripts also read it.
-      - PLAYWRIGHT_BROWSERS_PATH=/ms-browsers # Matches Dockerfile ENV
       - RESOLUTION=${RESOLUTION:-1920x1080x24}
       - RESOLUTION_WIDTH=${RESOLUTION_WIDTH:-1920}
       - RESOLUTION_HEIGHT=${RESOLUTION_HEIGHT:-1080}

requirements.txt

@@ -1,10 +1,5 @@
-browser-use==0.1.48
+browser-use==0.9.4
 pyperclip==1.9.0
-gradio==5.27.0
-json-repair
-langchain-mistralai==0.2.4
+gradio==5.49.1
+json-repair==0.49.0
 MainContentExtractor==0.0.4
-langchain-ibm==0.3.10
-langchain_mcp_adapters==0.0.9
-langgraph==0.3.34
-langchain-community

src/agent/browser_use/browser_use_agent.py

@@ -6,18 +6,18 @@
 
 # from lmnr.sdk.decorators import observe
 from browser_use.agent.gif import create_history_gif
-from browser_use.agent.service import Agent, AgentHookFunc
+from browser_use import Agent
+from browser_use.agent.service import AgentHookFunc
 from browser_use.agent.views import (
     ActionResult,
     AgentHistory,
     AgentHistoryList,
     AgentStepInfo,
-    ToolCallingMethod,
 )
 from browser_use.browser.views import BrowserStateHistory
 from browser_use.utils import time_execution_async
 from dotenv import load_dotenv
-from browser_use.agent.message_manager.utils import is_model_without_tool_support
+# is_model_without_tool_support removed in browser_use 0.6.0
 
 load_dotenv()
 logger = logging.getLogger(__name__)
@@ -28,16 +28,13 @@
 
 
 class BrowserUseAgent(Agent):
-    def _set_tool_calling_method(self) -> ToolCallingMethod | None:
+    def _set_tool_calling_method(self) -> str | None:
         tool_calling_method = self.settings.tool_calling_method
         if tool_calling_method == 'auto':
-            if is_model_without_tool_support(self.model_name):
-                return 'raw'
-            elif self.chat_model_library == 'ChatGoogleGenerativeAI':
+            # Simplified logic for browser_use 0.6.0
+            if self.chat_model_library == 'ChatGoogleGenerativeAI':
                 return None
-            elif self.chat_model_library == 'ChatOpenAI':
-                return 'function_calling'
-            elif self.chat_model_library == 'AzureChatOpenAI':
+            elif self.chat_model_library in ['ChatOpenAI', 'AzureChatOpenAI']:
                 return 'function_calling'
             else:
                 return None
@@ -141,23 +138,6 @@ async def run(
             # Unregister signal handlers before cleanup
             signal_handler.unregister()
 
-            if self.settings.save_playwright_script_path:
-                logger.info(
-                    f'Agent run finished. Attempting to save Playwright script to: {self.settings.save_playwright_script_path}'
-                )
-                try:
-                    # Extract sensitive data keys if sensitive_data is provided
-                    keys = list(self.sensitive_data.keys()) if self.sensitive_data else None
-                    # Pass browser and context config to the saving method
-                    self.state.history.save_as_playwright_script(
-                        self.settings.save_playwright_script_path,
-                        sensitive_data_keys=keys,
-                        browser_config=self.browser.config,
-                        context_config=self.browser_context.config,
-                    )
-                except Exception as script_gen_err:
-                    # Log any error during script generation/saving
-                    logger.error(f'Failed to save Playwright script: {script_gen_err}', exc_info=True)
 
             await self.close()