refactor: share INFRA stop-reason set from core.evolution

core/evolution/__init__.py

@@ -4,7 +4,7 @@
 只依赖 Protocol 接口和标准库，可搬到无 adapters 的环境用假实现原样运行。
 """
 
-from core.evolution.diagnose import run_diagnosis
+from core.evolution.diagnose import INFRA_STOP_REASONS, run_diagnosis
 from core.evolution.evolve import (
     edit_budget_at,
     evolve_single_skill,
@@ -44,6 +44,7 @@ from core.evolution.types import (
 from core.evolution.validate import classify_quadrants, compute_accuracy, pair_block
 
 __all__ = [
+    "INFRA_STOP_REASONS",
     "CaseSample",
     "DiagnosePrompts",
     "DiagnosisResult",

core/evolution/diagnose.py

@@ -53,7 +53,7 @@ if TYPE_CHECKING:
 _SPAN_EVAL_TOOLS: frozenset[str] = frozenset({"view_node", "search_similar", "observe_frame"})
 """span 级评估涵盖的工具集合。"""
 
-_INFRA_STOP_REASONS: frozenset[str] = frozenset({"error", "parse_error"})
+INFRA_STOP_REASONS: frozenset[str] = frozenset({"error", "parse_error"})
 """执行/解析层失败导致排除的 stop_reason 集合。"""
 
 
@@ -2007,7 +2007,7 @@ def _count_infra_excluded(
     qids = [
         row["question_id"]
         for row in prediction_rows
-        if row.get("stop_reason") in _INFRA_STOP_REASONS
+        if row.get("stop_reason") in INFRA_STOP_REASONS
     ]
     return len(qids), qids
 
@@ -2083,7 +2083,7 @@ async def run_diagnosis(
 
     for row in all_predictions:
         stop_reason = row.get("stop_reason")
-        if stop_reason in _INFRA_STOP_REASONS:
+        if stop_reason in INFRA_STOP_REASONS:
             continue
         if task_type_filter and row.get("task_type") not in task_type_filter:
             continue