Task fix batch (#383)

* update 873cafdd-a581-47f6-8b33-b9696ddb7b05 task eval

* c1fa57f3-c3db-4596-8f09-020701085416 fix, add tolerance to url matching

* 8df7e444-8e06-4f93-8a1a-c5c974269d82 add more clear instruction to the filename for compress

* add address string normalization for 6f4073b8-d8ea-4ade-8a18-c5d1d5d5aa9a

---------

Co-authored-by: Jiaqi <dengjiaqi@moonshot.cn>

desktop_env/evaluators/getters/chrome.py

@@ -827,8 +827,8 @@ def get_active_tab_info(env, config: Dict[str, str]):
                 
                 try:
                     logger.info(f"[ACTIVE_TAB_INFO] Navigating to URL: {active_tab_url}")
-                    page.goto(active_tab_url, wait_until='networkidle', timeout=timeout_ms)
-                    page.wait_for_load_state('networkidle', timeout=timeout_ms)  # Wait for the 'load' event to complete
+                    page.goto(active_tab_url, wait_until='load', timeout=timeout_ms)
+                    page.wait_for_load_state('load', timeout=timeout_ms)  # Wait for the 'load' event to complete
                     
                     active_tab_info = {
                         'title': page.title(),

desktop_env/evaluators/metrics/table.py

@@ -2,6 +2,8 @@ import functools
 import itertools
 import logging
 import os.path
+import re
+import unicodedata
 
 # import operator
 from numbers import Number
@@ -744,6 +746,18 @@ def compare_table(result: str, expected: str = None, **options) -> float:
     #  }}} function compare_table #
 
 
+def _normalize_city_string(value: Any) -> str:
+    """Lowercase, strip punctuation, and remove accents for tolerant matching."""
+    if value is None:
+        return ""
+    if not isinstance(value, str):
+        value = str(value)
+    normalized = unicodedata.normalize("NFKD", value)
+    normalized = "".join(ch for ch in normalized if not unicodedata.combining(ch))
+    normalized = re.sub(r"[^a-z0-9]+", " ", normalized.lower())
+    return normalized.strip()
+
+
 def compare_conference_city_in_order(actual_city_list_path, expected_city):
     expected_city_list = expected_city["expected"]
     wb = openpyxl.load_workbook(actual_city_list_path)
@@ -752,38 +766,35 @@ def compare_conference_city_in_order(actual_city_list_path, expected_city):
     for row in sheet["C2:C22"]:
         for cell in row:
             actual_city_list.append(cell.value)
-    # expected_city is the city that we want to compare with the actual city list
-    # must in order index
-    # debug
+
     try:
-        for i in range(len(actual_city_list)):
-            if isinstance(expected_city_list[i], str):
-                if expected_city_list[i] not in actual_city_list[i]:
-                    logger.debug(
-                        f"Expected city {expected_city_list[i]}; Actual city {actual_city_list[i]}"
-                    )
-                    print(
-                        f"Expected city {expected_city_list[i]}; Actual city {actual_city_list[i]}"
-                    )
-                    return 0.0
-
-            elif isinstance(expected_city_list[i], List):
-                if not any(
-                    possible_str in actual_city_list[i]
-                    for possible_str in expected_city_list[i]
-                ):
-                    logger.debug(
-                        f"Expected city {expected_city_list[i]}; Actual city {actual_city_list[i]}"
-                    )
-                    print(
-                        f"Expected city {expected_city_list[i]}; Actual city {actual_city_list[i]}"
-                    )
-                    return 0.0
+        for i, actual_city in enumerate(actual_city_list):
+            actual_normalized = _normalize_city_string(actual_city)
+            expected_entry = expected_city_list[i]
 
+            if isinstance(expected_entry, str):
+                expected_candidates = [expected_entry]
+            elif isinstance(expected_entry, List):
+                expected_candidates = expected_entry
             else:
                 raise TypeError("Expected city should be a string or a list of strings")
 
-    except:
+            matched = False
+            for candidate in expected_candidates:
+                normalized_candidate = _normalize_city_string(candidate)
+                if normalized_candidate and normalized_candidate in actual_normalized:
+                    matched = True
+                    break
+
+            if not matched:
+                logger.debug(
+                    f"Expected city {expected_entry}; Actual city {actual_city}"
+                )
+                print(f"Expected city {expected_entry}; Actual city {actual_city}")
+                return 0.0
+
+    except Exception as exc:
+        logger.error(f"Error comparing conference cities: {exc}")
         return 0.0
 
     return 1.0

evaluation_examples/examples/chrome/c1fa57f3-c3db-4596-8f09-020701085416.json

@@ -52,7 +52,7 @@
       "type": "rule",
       "rules": {
         "expected": [
-          "united.com/en/us/checked-bag-fee-calculator"
+          "united\\.com/en/us/checked-bag-fee-calculator(/.*)?"
         ]
       }
     }

evaluation_examples/examples/multi_apps/873cafdd-a581-47f6-8b33-b9696ddb7b05.json

@@ -60,7 +60,7 @@
       "rules": {
         "expected": [
           "Zoom Chrome Extension",
-          "Speechify Text to Speech Voice Reader",
+          "Speechify — Voice AI Assistant",
           "React Developer Tools",
           "Momentum",
           "Google Translate"

evaluation_examples/examples/multi_apps/8df7e444-8e06-4f93-8a1a-c5c974269d82.json

@@ -40,8 +40,8 @@
     },
     "result": {
       "type": "vm_file",
-      "path": "/home/user/Recruitment_and_retention_of_health_professionals_across_Europe.zip",
-      "dest": "Recruitment_and_retention_of_health_professionals_across_Europe.zip"
+      "path": "/home/user/essay_submission.zip",
+      "dest": "essay_submission.zip"
     }
   },
   "proxy": false,