Normalize product data prompt formatting

skills/model-labeling/scripts/batch_label_model.py

@@ -397,6 +397,8 @@ def build_planning_prompt(
 
 
 def wrap_chat_prompt(system_prompt: str, instruction: str) -> str:
+    system_prompt = prompt_section_without_trailing_newline(system_prompt)
+    instruction = prompt_section_with_one_trailing_newline(instruction)
     return (
         f"<|im_start|>system\n{system_prompt}<|im_end|>\n"
         f"<|im_start|>user\n{instruction}<|im_end|>\n"
@@ -404,6 +406,14 @@ def wrap_chat_prompt(system_prompt: str, instruction: str) -> str:
     )
 
 
+def prompt_section_without_trailing_newline(text: str) -> str:
+    return str(text or "").rstrip("\n")
+
+
+def prompt_section_with_one_trailing_newline(text: str) -> str:
+    return prompt_section_without_trailing_newline(text) + "\n"
+
+
 def build_training_instruction(record: dict[str, Any], session_num: int, session_time_minutes: int) -> str:
     turn = record.get("turn") if isinstance(record.get("turn"), dict) else {}
     query = str(turn.get("query") or "")
@@ -414,7 +424,7 @@ def build_training_instruction(record: dict[str, Any], session_num: int, session
     return (
         "请参考用户的[当前query]、[对话历史]、[知识注入]、[系统状态]识别出[当前query]的[function]结果，[function]是python的code形式。\n"
         "[知识注入]\n"
-        f"{json.dumps({'location': str(context.get('location') or ''), 'rag': str(context.get('rag') or '')}, ensure_ascii=False, indent=0)}\n"
+        f"{context_prompt_block(context)}\n"
         "[系统状态]\n"
         "{}\n"
         "[对话历史]\n"
@@ -425,6 +435,17 @@ def build_training_instruction(record: dict[str, Any], session_num: int, session
     )
 
 
+def context_prompt_block(context: dict[str, Any]) -> str:
+    fields = ("location", "rag")
+    lines = ["{"]
+    for index, field in enumerate(fields):
+        comma = "," if index < len(fields) - 1 else ""
+        value = str(context.get(field) or "")
+        lines.append(f'"{field}": {json.dumps(value, ensure_ascii=False)}{comma}')
+    lines.append("}")
+    return "\n".join(lines)
+
+
 def render_history(prev_session: list[Any], current_ts: int | None, session_num: int, session_time_minutes: int) -> str:
     usable: list[dict[str, Any]] = []
     for item in prev_session[-session_num:]: