Merge branch 'main' into streaming

.gitignore

@@ -130,6 +130,7 @@ ENV/
 env.bak/
 venv.bak/
 test_env/
+myenv
 
 
 # Spyder project settings

README.md

@@ -107,6 +107,44 @@ playwright install
     - Open the WebUI in a non-Chrome browser, such as Firefox or Edge. This is important because the persistent browser context will use the Chrome data when running the agent.
     - Check the "Use Own Browser" option within the Browser Settings.
 
+### Options:
+
+### `--theme`
+
+- **Type**: `str`
+- **Default**: `Ocean`
+- **Description**: Specifies the theme for the user interface.
+- **Options**:
+  The available themes are defined in the `theme_map` dictionary. Below are the options you can choose from:
+  - **Default**: The standard theme with a balanced design.
+  - **Soft**: A gentle, muted color scheme for a relaxed viewing experience.
+  - **Monochrome**: A grayscale theme with minimal color for simplicity and focus.
+  - **Glass**: A sleek, semi-transparent design for a modern appearance.
+  - **Origin**: A classic, retro-inspired theme for a nostalgic feel.
+  - **Citrus**: A vibrant, citrus-inspired palette with bright and fresh colors.
+  - **Ocean** (default): A blue, ocean-inspired theme providing a calming effect.
+
+**Example**:
+
+```bash
+python webui.py --ip 127.0.0.1 --port 7788 --theme Glass
+```
+
+### `--dark-mode`
+
+- **Type**: `boolean`
+- **Default**: Disabled
+- **Description**: Enables dark mode for the user interface. This is a simple toggle; including the flag activates dark mode, while omitting it keeps the interface in light mode.
+- **Options**:
+  - **Enabled (`--dark-mode`)**: Activates dark mode, switching the interface to a dark color scheme for better visibility in low-light environments.
+  - **Disabled (default)**: Keeps the interface in the default light mode.
+
+**Example**:
+
+```bash
+python webui.py --ip 127.0.0.1 --port 7788 --dark-mode
+```
+
 ## (Optional) Configure Environment Variables
 
 Copy `.env.example` to `.env` and set your environment variables, including API keys for the LLM. With

tests/test_playwright.py

@@ -21,14 +21,14 @@ def test_connect_browser():
         browser = p.chromium.launch_persistent_context(
             user_data_dir=chrome_use_data,
             executable_path=chrome_exe,
-            headless=False  # 保持浏览器窗口可见
+            headless=False  # Keep browser window visible
         )
 
         page = browser.new_page()
         page.goto("https://mail.google.com/mail/u/0/#inbox")
         page.wait_for_load_state()
 
-        input("按下回车键以关闭浏览器...")
+        input("Press the Enter key to close the browser...")
 
         browser.close()
 

webui.py

@@ -47,6 +47,7 @@ async def run_browser_agent(
         window_w,
         window_h,
         save_recording_path,
+        enable_recording,
         task,
         add_infos,
         max_steps,
@@ -98,8 +99,6 @@ async def run_browser_agent(
     else:
         raise ValueError(f"Invalid agent type: {agent_type}")
 
-
-
 async def run_org_agent(
         llm,
         headless,
@@ -567,6 +566,11 @@ def create_ui(theme_name="Ocean"):
                             value=True,
                             info="Disable browser security features",
                         )
+                        enable_recording = gr.Checkbox(
+                            label="Enable Recording",
+                            value=True,
+                            info="Enable saving browser recordings",
+                        )
 
                     with gr.Row():
                         window_w = gr.Number(
@@ -585,6 +589,7 @@ def create_ui(theme_name="Ocean"):
                         placeholder="e.g. ./tmp/record_videos",
                         value="./tmp/record_videos",
                         info="Path to save browser recordings",
+                        interactive=True,  # Allow editing only if recording is enabled
                     )
 
             with gr.TabItem("🤖 Run Agent", id=4):