From 44bd66fc9a60b43fbb9ce25519842277c125b95f Mon Sep 17 00:00:00 2001
From: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
Date: Fri, 18 Jul 2025 14:16:16 +0000
Subject: [PATCH] Increase timeout for page load stability in Chrome evaluator

- Updated the timeout for the page load state from 10 seconds to 60 seconds to ensure better stability during page processing.
- Removed redundant retry mechanisms from the active tab checks to streamline the code while maintaining existing functionality.
- Enhanced logging to provide clearer insights into the page loading process.

These changes aim to improve the reliability of the Chrome evaluator without altering the core logic.
---
 desktop_env/evaluators/getters/chrome.py |  2 +-
 desktop_env/evaluators/metrics/chrome.py | 75 ++++--------------------
 2 files changed, 14 insertions(+), 63 deletions(-)

diff --git a/desktop_env/evaluators/getters/chrome.py b/desktop_env/evaluators/getters/chrome.py
index 129c460..7d6d4d7 100644
--- a/desktop_env/evaluators/getters/chrome.py
+++ b/desktop_env/evaluators/getters/chrome.py
@@ -1523,7 +1523,7 @@ def get_active_tab_html_parse(env, config: Dict[str, Any]):
             for page in context.pages:
                 try:
                     # Wait for page to be stable before checking URL
-                    page.wait_for_load_state("networkidle", timeout=10000)
+                    page.wait_for_load_state("networkidle", timeout=60000)
                     
                     # Check if page is still valid before accessing properties
                     if page.is_closed():
diff --git a/desktop_env/evaluators/metrics/chrome.py b/desktop_env/evaluators/metrics/chrome.py
index bc8467c..dd6009a 100644
--- a/desktop_env/evaluators/metrics/chrome.py
+++ b/desktop_env/evaluators/metrics/chrome.py
@@ -3,6 +3,7 @@ import os
 import re
 import shutil
 import io
+import time
 from itertools import product
 from typing import Any, Dict, List, Union
 
@@ -21,30 +22,6 @@ def is_expected_active_tab(active_tab_info: Dict[str, str], rule: Dict[str, Any]
     if not active_tab_info:
         return 0.
 
-    # 添加重试机制
-    max_retries = 3
-    retry_delay = 2  # seconds
-    
-    for attempt in range(max_retries):
-        # 添加HTTP状态码检查
-        if 'status' in active_tab_info and active_tab_info['status'] >= 400:
-            logger.warning(f"Page load failed (attempt {attempt+1}/{max_retries}), HTTP status: {active_tab_info['status']}")
-            
-            if attempt < max_retries - 1:
-                # 重试前刷新页面
-                logger.info(f"Refreshing page and retrying in {retry_delay} seconds...")
-                time.sleep(retry_delay)
-                # 这里需要调用刷新页面的函数（实际实现取决于您的环境）
-                # 伪代码: refresh_active_tab()
-                # 然后重新获取 active_tab_info
-                # 伪代码: active_tab_info = get_active_tab_info()
-                continue
-            else:
-                logger.error(f"Page load failed after {max_retries} attempts")
-                return 0.
-
-        break  # 如果状态码正常，跳出重试循环
-
     match_type = rule['type']
 
     if match_type == "url":
@@ -68,26 +45,6 @@ def is_expected_active_tab_approximate(active_tab_info: Dict[str, str], rule: Di
     if not active_tab_info:
         return 0.
 
-    # 添加相同的重试机制
-    max_retries = 3
-    retry_delay = 2  # seconds
-    
-    for attempt in range(max_retries):
-        if 'status' in active_tab_info and active_tab_info['status'] >= 400:
-            logger.warning(f"Page load failed (attempt {attempt+1}/{max_retries}), HTTP status: {active_tab_info['status']}")
-            
-            if attempt < max_retries - 1:
-                logger.info(f"Refreshing page and retrying in {retry_delay} seconds...")
-                time.sleep(retry_delay)
-                # 伪代码: refresh_active_tab()
-                # 伪代码: active_tab_info = get_active_tab_info()
-                continue
-            else:
-                logger.error(f"Page load failed after {max_retries} attempts")
-                return 0.
-
-        break
-
     match_type = rule['type']
 
     if match_type == "url":
@@ -118,25 +75,19 @@ def is_expected_url_pattern_match(result, rules) -> float:
     if not result:
         return 0.
 
-    # 添加相同的重试机制
-    max_retries = 3
-    retry_delay = 2  # seconds
-    
-    for attempt in range(max_retries):
-        if isinstance(result, dict) and 'status' in result and result['status'] >= 400:
-            logger.warning(f"Page load failed (attempt {attempt+1}/{max_retries}), HTTP status: {result['status']}")
-            
-            if attempt < max_retries - 1:
-                logger.info(f"Refreshing page and retrying in {retry_delay} seconds...")
-                time.sleep(retry_delay)
-                # 伪代码: refresh_active_tab()
-                # 伪代码: result = get_active_tab_info()
-                continue
-            else:
-                logger.error(f"Page load failed after {max_retries} attempts")
-                return 0.
+    # Extract URL from result parameter - result can be either a string URL or a dict with 'url' field
+    if isinstance(result, str):
+        result_url = result
+        logger.info("result url: {}".format(result_url))
+    elif isinstance(result, dict) and 'url' in result:
+        result_url = result['url']
+        logger.info("result url: {}".format(result_url))
+    else:
+        logger.error(f"Invalid result format: {type(result)}, expected string URL or dict with 'url' field")
+        return 0.
 
-        break
+    logger.info(f"Result URL to match: {result_url}")
+    
     # expect_regex = re.compile(rules["expected"])
     patterns = rules["expected"]
     logger.info("expected_regex: {}".format(patterns))