update to multi-turn conversation, fix behavior when task can definitely not be completed

Author: cuiyuebing

alias/src/alias/agent/agents/_browser_agent.py

@@ -36,6 +36,9 @@
 from alias.agent.agents.common_agent_utils import (
     WorkerResponse,
     get_user_input_to_mem_pre_reply_hook,
+    agent_load_states_pre_reply_hook,
+    save_post_reasoning_state,
+    save_post_action_state,
 )
 from alias.agent.agents._build_in_helper_browser._image_understanding import (
     image_understanding,
@@ -281,6 +284,11 @@ def __init__(
         # Register hooks (kwargs-only signature)
         # compatible with directly using session service,
         # add input msg to memory
+        self.register_instance_hook(
+            "pre_reply",
+            "agent_load_states_pre_reply_hook",
+            agent_load_states_pre_reply_hook,
+        )
         self.register_instance_hook(
             "pre_reply",
             "get_user_input_to_mem_pre_reply_hook",
@@ -291,11 +299,21 @@ def __init__(
             "browser_pre_reply_hook",
             browser_pre_reply_hook,
         )
+        self.register_instance_hook(
+            "post_reasoning",
+            "save_post_reasoning_state",
+            save_post_reasoning_state,
+        )
         self.register_instance_hook(
             "post_acting",
             "browser_post_acting_hook",
             browser_post_acting_hook,
         )
+        self.register_instance_hook(
+            "post_acting",
+            "save_post_action_state",
+            save_post_action_state,
+        )
 
     def _register_skill_tool(
         self,
@@ -1373,7 +1391,9 @@ async def _validate_finish_status(self, summary: str) -> str:
         sys_prompt = (
             "You are an expert in task validation. "
             "Your job is to determine if the agent has completed its task"
-            " based on the provided summary. If the summary is `NO_ANSWER`, this task is not over. If finished, strictly reply "
+            " based on the provided summary. If the summary is `NO_ANSWER`, this task "
+            "is not over unless the task is determined as definitely not completed. "
+            "If finished, strictly reply "
             '"BROWSER_AGENT_TASK_FINISHED" and your reason, otherwise return the remaining '
             "tasks or next steps."
         )

alias/src/alias/agent/agents/_build_in_prompt_browser/browser_agent_evaluate.md

@@ -28,6 +28,7 @@ Your goal is to complete given tasks by controlling a browser to navigate web pa
 - Avoid using Google Scholar. If a researcher is searched, try to use his/her homepage instead.
 - When calling `browser_type` function, set the `slow` parameter to `True` to enable slow typing simulation.
 - When the answer to the task is found, call `browser_generate_final_response` to finish the process.
+- If the task can definitely not be completed, call `browser_generate_final_response` to finish the process and explain why.
 ### Observing Guidelines
 - Always take action based on the elements on the webpage. Never create urls or generate new pages.
 - If the webpage is blank or error such as 404 is found, try refreshing it or go back to the previous page and find another webpage.