fix: step3 _normalize_rule 为缺失 section 的 table/text source 补齐字段 - Closes #53

LLM 生成的 source 有时缺少 section 字段，导致 Layer A schema 验证失败。在 _normalize_rule 中添加防御性处理：从兄弟 source 或 rule path 推断 section。 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-02 15:46:59 +08:00
parent 6d0a5284e7
commit 1477dbdd18
2 changed files with 67 additions and 0 deletions
@@ -169,6 +169,27 @@ def _normalize_rule(rule: dict) -> dict:
            "value": "active"
        }]

+    # Ensure table/text sources have a section field (defensive against LLM omission)
+    sources = rule.get("sources", [])
+    if sources:
+        # try to infer a default section from sibling sources or the rule path
+        default_section = ""
+        for s in sources:
+            sec = s.get("section", "")
+            if sec and sec.strip():
+                default_section = sec.strip()
+                break
+        if not default_section:
+            path = rule.get("path", "")
+            if path:
+                default_section = path.split(" > ")[0] if " > " in path else path
+
+        for src in sources:
+            stype = src.get("type", "")
+            if stype in ("table", "text"):
+                if not src.get("section"):
+                    src["section"] = default_section
+
    return rule