Improve online mining record conversion

skills/online-mining-v2/scripts/build_dataset_draft.py

@@ -35,6 +35,69 @@ def case_value(case: dict, key: str):
     return case.get(key) or pre.get(key) or main.get(key)
 
 
+def build_dataset_draft_text(
+    *,
+    dataset_label: str,
+    target: str,
+    complex_value: bool,
+    cases: list[dict],
+) -> str:
+    """把 review 后的线上 case 转成 product-data dataset draft text。
+
+    这个 draft 是中间格式，不是最终数据。后续必须再经过
+    product-data 的 normalize/validate/export。
+    """
+
+    lines = [f"# dataset_label: {dataset_label}", ""]
+    for index, case in enumerate(cases, start=1):
+        query = str(case_value(case, "query") or "").strip()
+        if not query:
+            continue
+        request_id = str(case_value(case, "request_id") or "").strip()
+        timestamp = case_value(case, "timestamp")
+        tts = str(case_value(case, "tts") or "").strip()
+        planning_result = str(case_value(case, "planning_result") or "").strip()
+        case_target = str(case_value(case, "target") or target).strip()
+        case_complex = case_value(case, "complex")
+        if isinstance(case_complex, str):
+            case_complex_text = case_complex.strip().lower()
+            item_complex = case_complex_text in {"true", "1", "yes", "y", "是", "复杂", "complex"}
+        elif isinstance(case_complex, bool):
+            item_complex = case_complex
+        else:
+            item_complex = complex_value
+        notes = []
+        if planning_result:
+            notes.append(f"线上模型输出: {planning_result}")
+        main_domain = case_value(case, "domain") or case.get("main_domain")
+        if main_domain:
+            notes.append(f"线上 domain: {main_domain}")
+        lines.append(f"### case: online_{index:04d}")
+        prev_session = case_value(case, "prev_session")
+        if isinstance(prev_session, list):
+            for item in prev_session[-10:]:
+                if not isinstance(item, dict):
+                    continue
+                prev_query = str(item.get("query") or "").strip()
+                prev_tts = str(item.get("tts") or "").strip()
+                if prev_query and prev_tts:
+                    lines.append(f"用户: {prev_query}")
+                    lines.append(f"小爱: {prev_tts}")
+        lines.append(f"用户: {query}")
+        lines.append(f"complex: {'true' if item_complex else 'false'}")
+        lines.append(f"target: {case_target}")
+        if request_id:
+            lines.append(f"request_id: {request_id}")
+        if timestamp:
+            lines.append(f"timestamp: {timestamp}")
+        if tts:
+            lines.append(f"notes: tts={tts}" + (f"；{'；'.join(notes)}" if notes else ""))
+        elif notes:
+            lines.append(f"notes: {'；'.join(notes)}")
+        lines.append("")
+    return "\n".join(lines).strip() + "\n"
+
+
 def main() -> int:
     try:
         payload = load_json_payload()
@@ -49,36 +112,12 @@ def main() -> int:
         if not cases:
             raise ValueError("cases must not be empty")
 
-        lines = [f"# dataset_label: {dataset_label}", ""]
-        for index, case in enumerate(cases, start=1):
-            query = str(case_value(case, "query") or "").strip()
-            if not query:
-                continue
-            request_id = str(case_value(case, "request_id") or "").strip()
-            timestamp = case_value(case, "timestamp")
-            tts = str(case_value(case, "tts") or "").strip()
-            planning_result = str(case_value(case, "planning_result") or "").strip()
-            notes = []
-            if planning_result:
-                notes.append(f"线上模型输出: {planning_result}")
-            main_domain = case_value(case, "domain") or case.get("main_domain")
-            if main_domain:
-                notes.append(f"线上 domain: {main_domain}")
-            lines.append(f"### case: online_{index:04d}")
-            lines.append(f"用户: {query}")
-            lines.append(f"complex: {'true' if complex_value else 'false'}")
-            lines.append(f"target: {target}")
-            if request_id:
-                lines.append(f"request_id: {request_id}")
-            if timestamp:
-                lines.append(f"timestamp: {timestamp}")
-            if tts:
-                lines.append(f"notes: tts={tts}" + (f"；{'；'.join(notes)}" if notes else ""))
-            elif notes:
-                lines.append(f"notes: {'；'.join(notes)}")
-            lines.append("")
-
-        draft_text = "\n".join(lines).strip() + "\n"
+        draft_text = build_dataset_draft_text(
+            dataset_label=dataset_label,
+            target=target,
+            complex_value=complex_value,
+            cases=cases,
+        )
         output_path = None
         if payload.get("output_path"):
             output = resolve_portable_path(str(payload["output_path"]))
@@ -94,4 +133,3 @@ def main() -> int:
 
 if __name__ == "__main__":
     raise SystemExit(main())
-