fix: step3 _normalize_rule 处理 section 为 list 的 LLM 格式问题 - Closes #69

LLM 输出 section 字段有时为 list 而非 string，导致 .strip() 崩溃。
添加 _clean_section() 将 list→首元素 string，空 list 回退到 rule path。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

skills/ir_generation_skill/step3_merge_and_audit.py

@@ -174,11 +174,25 @@ def _normalize_rule(rule: dict) -> dict:
     sources = rule.get("sources", [])
     valid_types = {"table", "text", "logic_tree"}
 
+    def _clean_section(val):
+        """Normalize section value: list→first element, ensure string."""
+        if isinstance(val, list):
+            return str(val[0]).strip() if val else ""
+        if isinstance(val, str):
+            return val.strip()
+        return str(val).strip() if val else ""
+
+    # Normalize section fields that might be lists (LLM format instability)
+    for s in sources:
+        sec = s.get("section")
+        if sec is not None:
+            s["section"] = _clean_section(sec)
+
     # try to infer a default section from the rule path
     default_section = ""
     for s in sources:
         sec = s.get("section", "")
-        if sec and sec.strip():
+        if sec and isinstance(sec, str) and sec.strip():
             default_section = sec.strip()
             break
     if not default_section:

skills/ir_generation_skill/tests/test_step3.py

@@ -538,3 +538,28 @@ class TestNormalizeRule:
         assert len(normalized["sources"]) == 1
         assert normalized["sources"][0]["type"] == "text"
         assert normalized["sources"][0]["section"] == "3.1 策略"
+
+    def test_normalize_section_is_list(self):
+        """Section field that is a list (LLM format bug) is normalized to string."""
+        rule = {
+            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
+            "sources": [
+                {"type": "table", "section": ["状态", "系统设置"], "row": 1},
+                {"type": "text", "section": ["后台限制"], "text_snippet": "x"},
+            ],
+        }
+        normalized = _normalize_rule(rule)
+        assert normalized["sources"][0]["section"] == "状态"
+        assert normalized["sources"][1]["section"] == "后台限制"
+
+    def test_normalize_section_is_empty_list(self):
+        """Empty list section falls back to rule path."""
+        rule = {
+            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
+            "path": "4.2 关闭流程 > decision",
+            "sources": [
+                {"type": "table", "section": [], "row": 1},
+            ],
+        }
+        normalized = _normalize_rule(rule)
+        assert normalized["sources"][0]["section"] == "4.2 关闭流程"

tests/acceptance/conftest.py

@@ -150,7 +150,20 @@ def ir_data(ir_path: str) -> dict:
     from step3_merge_and_audit import _normalize_rule
     rules = data.get("rules", [])
     if rules:
-        data["rules"] = [_normalize_rule(r) for r in rules]
+        normalized = []
+        for i, r in enumerate(rules):
+            if not isinstance(r, dict):
+                continue  # Skip non-dict entries defensively
+            # Defensive: flatten list-type section fields (LLM produces these sometimes)
+            for src in r.get("sources", []):
+                sec = src.get("section")
+                if isinstance(sec, list):
+                    src["section"] = sec[0] if sec else ""
+            try:
+                normalized.append(_normalize_rule(r))
+            except Exception:
+                normalized.append(r)  # Fallback: use raw rule if normalize crashes
+        data["rules"] = normalized
 
     return data