Audit batch 4: I-6 whitespace audit format, I-7 explicit non-sub2api capability gate, I-8 coord gate attribution, I-10 checked gates, I-11 gate-without-finding escalate, I-13 structured-first classification

cloud/routing_shadow.py

@@ -60,7 +60,16 @@ _DETAIL_RE = re.compile(
     r"^(?P<task_id>\S+)\s+tier=(?P<tier>\S+)\s+source=(?P<source>\S+)"
     r"\s+applied=(?P<applied>\S+)"
     r"(?:\s+suggested=(?P<suggested>\S+))?"
-    r"(?:\s+chosen=(?P<chosen>\S+))?\s*$")
+    # Audit batch 4 (I-6): chosen is the LAST field, so it may
+    # greedily run to end of line — a legacy chosen model name
+    # containing whitespace ("my model") now parses instead of
+    # dropping the whole row. suggested stays \S+ (it is a middle
+    # field); new policy models cannot contain whitespace (the
+    # batch-4 policy whitelist drops them), so new rows always
+    # parse, and legacy suggested-with-whitespace rows still land
+    # in the unparseable bucket (counted, batch 2) rather than
+    # being silently lost.
+    r"(?:\s+chosen=(?P<chosen>.+?))?\s*$")
 
 
 def parse_worker_routing_detail(detail):
@@ -70,9 +79,11 @@ def parse_worker_routing_detail(detail):
     A ``-`` placeholder also means None, never a model named "-".
     Audit batch 2 (I-1): 解析语义本身不变（失败仍返回 None），
     但 evaluate_shadow 不再静默跳过：不可解析的行计入
-    dropped_rows["unparseable"]，报告里可见（例如模型名含
-    空白会使整行匹配失败，见 M7——行不再无声消失，只是
-    不计为样本）。
+    dropped_rows["unparseable"]，报告里可见。
+    Audit batch 4 (I-6): chosen 是行尾字段，含空白的
+    legacy chosen 模型名现在能解析（见 _DETAIL_RE 注释）；
+    suggested 仍要求无空白，legacy suggested 含空白的行
+    仍进 unparseable 桶计数，不静默消失。
     """
     if not isinstance(detail, str):
         return None
@@ -89,7 +100,7 @@ def parse_worker_routing_detail(detail):
         "source": match.group("source"),
         "applied": applied,
         "suggested_model": None if suggested in (None, "-") else suggested,
-        "chosen_model": None if chosen in (None, "-") else chosen,
+        "chosen_model": None if chosen in (None, "-") else chosen.strip(),
     }