Merge pull request #158 from vvincent1234/feat/deepseek-r1

fix cutting message bug

.env.example

@@ -22,12 +22,16 @@ CHROME_PATH=
 CHROME_USER_DATA=
 CHROME_DEBUGGING_PORT=9222
 CHROME_DEBUGGING_HOST=localhost
-CHROME_PERSISTENT_SESSION=false  # Set to true to keep browser open between AI tasks
+# Set to true to keep browser open between AI tasks
+CHROME_PERSISTENT_SESSION=false
 
 # Display settings
-RESOLUTION=1920x1080x24  # Format: WIDTHxHEIGHTxDEPTH
-RESOLUTION_WIDTH=1920    # Width in pixels
-RESOLUTION_HEIGHT=1080   # Height in pixels
+# Format: WIDTHxHEIGHTxDEPTH
+RESOLUTION=1920x1080x24
+# Width in pixels
+RESOLUTION_WIDTH=1920
+# Height in pixels
+RESOLUTION_HEIGHT=1080
 
 # VNC settings
 VNC_PASSWORD=youvncpassword

src/agent/custom_agent.py

@@ -89,7 +89,8 @@ class CustomAgent(Agent):
             max_actions_per_step=max_actions_per_step,
             tool_call_in_content=tool_call_in_content,
         )
-        if self.llm.model_name in ["deepseek-reasoner"]:
+        if hasattr(self.llm, 'model_name') and self.llm.model_name in ["deepseek-reasoner"]:
+            # deepseek-reasoner does not support function calling
             self.use_function_calling = False
             # TODO: deepseek-reasoner only support 64000 context
             self.max_input_tokens = 64000
@@ -242,6 +243,7 @@ class CustomAgent(Agent):
                 model_output.action, self.browser_context
             )
             if len(result) != len(model_output.action):
+                # I think something changes, such information should let LLM know
                 for ri in range(len(result), len(model_output.action)):
                     result.append(ActionResult(extracted_content=None,
                                                 include_in_memory=True,

src/agent/custom_massage_manager.py

@@ -88,11 +88,9 @@ class CustomMassageManager(MessageManager):
     def cut_messages(self):
         """Get current message list, potentially trimmed to max tokens"""
         diff = self.history.total_tokens - self.max_input_tokens
-        i = 1  # start from 1 to keep system message in history
-        while diff > 0 and i < len(self.history.messages):
-            self.history.remove_message(i)
+        while diff > 0 and len(self.history.messages) > 1:
+            self.history.remove_message(1) # alway remove the oldest one
             diff = self.history.total_tokens - self.max_input_tokens
-            i += 1
         
     def add_state_message(
             self,

src/utils/default_config_settings.py

@@ -17,7 +17,7 @@ def default_config():
         "llm_temperature": 1.0,
         "llm_base_url": "",
         "llm_api_key": "",
-        "use_own_browser": os.getenv("CHROME_PERSISTENT_SESSION", False),
+        "use_own_browser": os.getenv("CHROME_PERSISTENT_SESSION", "false").lower() == "true",
         "keep_browser_open": False,
         "headless": False,
         "disable_security": True,

webui.py

@@ -34,8 +34,6 @@ from gradio.themes import Citrus, Default, Glass, Monochrome, Ocean, Origin, Sof
 from src.utils.default_config_settings import default_config, load_config_from_file, save_config_to_file, save_current_config, update_ui_from_config
 from src.utils.utils import update_model_dropdown, get_latest_files, capture_screenshot
 
-from dotenv import load_dotenv
-load_dotenv()
 
 # Global variables for persistence
 _global_browser = None