Stabilize product data export flow

src/data_agent_records.py

@@ -7,9 +7,11 @@ Skill 应该先让模型生成紧凑、便于人工 review 的 dataset draft tex
 再由这里的逻辑解析并补齐为 canonical records，供后续校验和导出使用。
 """
 
+import csv
 import json
 import re
 import time
+from io import StringIO
 from pathlib import Path
 from typing import Any
 
@@ -461,6 +463,7 @@ def export_dataset_records(
     output_format: str = 'jsonl',
     require_validation_ok: bool = True,
     overwrite: bool = True,
+    export_table: bool = True,
 ) -> dict[str, Any]:
     """校验并导出 canonical records。
 
@@ -480,8 +483,11 @@ def export_dataset_records(
         )
 
     path = _resolve_output_path(root, output_path)
+    table_path = path.with_name('records.csv')
     if path.exists() and not overwrite:
         raise DataRecordError(f'output_path already exists: {output_path}')
+    if export_table and table_path.exists() and not overwrite:
+        raise DataRecordError('table output_path already exists: records.csv')
     path.parent.mkdir(parents=True, exist_ok=True)
 
     if output_format == 'jsonl':
@@ -494,13 +500,83 @@ def export_dataset_records(
 
     path.write_text(content, encoding='utf-8')
     rel_path = str(path.relative_to(Path(root).resolve()))
-    return {
+    payload = {
         'output_path': rel_path,
         'output_format': output_format,
         'record_count': len(records),
         'bytes_written': len(content.encode('utf-8')),
         'validation': validation,
     }
+    if export_table:
+        table_content = render_dataset_records_table_csv(records)
+        table_path.write_text(table_content, encoding='utf-8-sig')
+        payload.update(
+            {
+                'table_output_path': str(table_path.relative_to(Path(root).resolve())),
+                'table_output_format': 'csv',
+                'table_bytes_written': len(table_content.encode('utf-8-sig')),
+            }
+        )
+    return payload
+
+
+def render_dataset_records_table_csv(records: list[dict[str, Any]]) -> str:
+    """把 canonical records 转成同事流转用的表格 CSV。"""
+
+    output = StringIO()
+    writer = csv.DictWriter(output, fieldnames=_dataset_table_columns(), lineterminator='\n')
+    writer.writeheader()
+    for record in records:
+        writer.writerow(_dataset_record_table_row(record))
+    return output.getvalue()
+
+
+def _dataset_table_columns() -> list[str]:
+    return [
+        'request_id',
+        'timestamp',
+        'query',
+        'prev_session',
+        'context',
+        'label',
+        '是否迁移Function',
+        'function',
+    ]
+
+
+def _dataset_record_table_row(record: dict[str, Any]) -> dict[str, str]:
+    source = record.get('source') if isinstance(record.get('source'), dict) else {}
+    turn = record.get('turn') if isinstance(record.get('turn'), dict) else {}
+    label = record.get('label') if isinstance(record.get('label'), dict) else {}
+    context = record.get('context') if isinstance(record.get('context'), dict) else {}
+    prev_session = record.get('prev_session')
+    if not isinstance(prev_session, list):
+        prev_session = []
+    return {
+        'request_id': str(source.get('request_id') or ''),
+        'timestamp': str(source.get('timestamp') or turn.get('timestamp') or ''),
+        'query': str(turn.get('query') or ''),
+        'prev_session': json.dumps(_table_prev_session(prev_session), ensure_ascii=False, separators=(',', ':')),
+        'context': json.dumps(context, ensure_ascii=False, separators=(',', ':')),
+        'label': str(label.get('dataset_label') or ''),
+        '是否迁移Function': '',
+        'function': str(label.get('target') or ''),
+    }
+
+
+def _table_prev_session(prev_session: list[Any]) -> list[dict[str, str]]:
+    rows: list[dict[str, str]] = []
+    for item in prev_session[-10:]:
+        if not isinstance(item, dict):
+            continue
+        rows.append(
+            {
+                'query': str(item.get('query') or ''),
+                'tts': str(item.get('tts') or ''),
+                'timestamp': str(item.get('timestamp') or ''),
+            }
+        )
+    return rows
 
 
 def _parse_draft_text(draft_text: str) -> dict[str, Any]:
@@ -797,7 +873,7 @@ def _case_to_record(
     if not current_query:
         raise DataRecordError(f'case {index} current 用户 line must be non-empty')
 
-    target = str(case.get('target') or '').strip()
+    target = _canonical_target(str(case.get('target') or '').strip())
     if not target:
         raise DataRecordError(f'case {index} target is required')
 
@@ -866,6 +942,17 @@ def _target_type(target: str) -> str:
     return 'unknown'
 
 
+def _canonical_target(target: str) -> str:
+    """规范常见 Agent 标签写法，允许草稿里用单引号降低 JSON 转义风险。"""
+
+    match = re.fullmatch(r'Agent\s*\(\s*tag\s*=\s*([\'"])(.+?)\1\s*\)', target)
+    if not match:
+        return target
+    tag = match.group(2).strip()
+    escaped = tag.replace('\\', '\\\\').replace('"', '\\"')
+    return f'Agent(tag="{escaped}")'
+
+
 def _record_id(*, source_type: str, batch_id: str, request_id: str, index: int) -> str:
     if source_type == 'generated':
         return f'gen_{_safe_token(batch_id)}_{index:06d}'