Stabilize product data export flow

src/agent_tools.py

@@ -1474,7 +1474,7 @@ def _data_agent_confirm_generation_plan_tool(arguments: dict[str, Any], context:
 
 
 def _normalize_dataset_draft_tool(arguments: dict[str, Any], _context: ToolExecutionContext) -> str:
-    draft_text = _require_string(arguments, 'draft_text')
+    draft_text = _draft_text_from_arguments(arguments, _context)
     batch_id = arguments.get('batch_id', 'aabbccdd')
     if not isinstance(batch_id, str) or not batch_id.strip():
         raise ToolExecutionError('batch_id must be a non-empty string')
@@ -1508,10 +1508,8 @@ def _normalize_dataset_draft_tool(arguments: dict[str, Any], _context: ToolExecu
 
 
 def _validate_dataset_records_tool(arguments: dict[str, Any], _context: ToolExecutionContext) -> str:
-    if 'records' not in arguments:
-        raise ToolExecutionError('records is required')
     try:
-        records = records_from_tool_argument(arguments['records'])
+        records = _records_from_arguments(arguments, _context)
         payload = validate_dataset_records(records)
     except (DataRecordError, json.JSONDecodeError) as exc:
         raise ToolExecutionError(str(exc)) from exc
@@ -1519,8 +1517,6 @@ def _validate_dataset_records_tool(arguments: dict[str, Any], _context: ToolExec
 
 
 def _export_dataset_records_tool(arguments: dict[str, Any], context: ToolExecutionContext) -> str:
-    if 'records' not in arguments:
-        raise ToolExecutionError('records is required')
     output_format = arguments.get('output_format', 'jsonl')
     if not isinstance(output_format, str):
         raise ToolExecutionError('output_format must be a string')
@@ -1530,8 +1526,11 @@ def _export_dataset_records_tool(arguments: dict[str, Any], context: ToolExecuti
     overwrite = arguments.get('overwrite', True)
     if not isinstance(overwrite, bool):
         raise ToolExecutionError('overwrite must be a boolean')
+    export_table = arguments.get('export_table', True)
+    if not isinstance(export_table, bool):
+        raise ToolExecutionError('export_table must be a boolean')
     try:
-        records = records_from_tool_argument(arguments['records'])
+        records = _records_from_arguments(arguments, context)
         canonical_filename = 'records.json' if output_format == 'json' else 'records.jsonl'
         payload = export_dataset_records(
             records,
@@ -1544,12 +1543,67 @@ def _export_dataset_records_tool(arguments: dict[str, Any], context: ToolExecuti
             output_format=output_format,
             require_validation_ok=require_validation_ok,
             overwrite=overwrite,
+            export_table=export_table,
         )
     except (DataRecordError, json.JSONDecodeError) as exc:
         raise ToolExecutionError(str(exc)) from exc
     return json.dumps(payload, ensure_ascii=False, indent=2)
 
 
+def _draft_text_from_arguments(arguments: dict[str, Any], context: ToolExecutionContext) -> str:
+    draft_text = arguments.get('draft_text')
+    draft_path = arguments.get('draft_path')
+    has_text = isinstance(draft_text, str) and bool(draft_text.strip())
+    has_path = isinstance(draft_path, str) and bool(draft_path.strip())
+    if has_text and has_path:
+        raise ToolExecutionError('provide only one of draft_text or draft_path')
+    if has_text:
+        return draft_text
+    if not has_path:
+        raise ToolExecutionError('draft_text or draft_path is required')
+    path = _resolve_path(draft_path, context, allow_missing=False, allow_outside_root=True)
+    if not path.is_file():
+        raise ToolExecutionError(f'draft_path is not a file: {path}')
+    return path.read_text(encoding='utf-8', errors='replace')
+
+
+def _records_from_arguments(arguments: dict[str, Any], context: ToolExecutionContext) -> list[dict[str, Any]]:
+    has_records = 'records' in arguments and arguments.get('records') is not None
+    records_path = arguments.get('records_path')
+    has_path = isinstance(records_path, str) and bool(records_path.strip())
+    if has_records and has_path:
+        raise ToolExecutionError('provide only one of records or records_path')
+    if has_records:
+        return records_from_tool_argument(arguments['records'])
+    if not has_path:
+        raise ToolExecutionError('records or records_path is required')
+    path = _resolve_path(records_path, context, allow_missing=False, allow_outside_root=True)
+    if not path.is_file():
+        raise ToolExecutionError(f'records_path is not a file: {path}')
+    return _records_from_file(path)
+
+
+def _records_from_file(path: Path) -> list[dict[str, Any]]:
+    text = path.read_text(encoding='utf-8', errors='replace').strip()
+    if not text:
+        raise DataRecordError('records_path is empty')
+    if path.suffix == '.jsonl':
+        records: list[dict[str, Any]] = []
+        for line_number, line in enumerate(text.splitlines(), start=1):
+            stripped = line.strip()
+            if not stripped:
+                continue
+            item = json.loads(stripped)
+            if not isinstance(item, dict):
+                raise DataRecordError(f'records_path line {line_number} must decode to an object')
+            records.append(item)
+        return records_from_tool_argument(records)
+    payload = json.loads(text)
+    if isinstance(payload, dict) and isinstance(payload.get('records'), list):
+        payload = payload['records']
+    return records_from_tool_argument(payload)
+
+
 def _data_agent_output_path(
     output_path: str,
     context: ToolExecutionContext,