Add training and planning eval exports

src/agent_tools.py

@@ -34,6 +34,8 @@ from .data_agent_records import (
     confirm_generation_goal,
     confirm_generation_plan,
     export_dataset_records,
+    export_planning_eval_csv,
+    export_training_jsonl,
     get_generation_plan,
     normalize_dataset_draft,
     prepare_generation_goal,
@@ -1049,6 +1051,8 @@ def default_tool_registry() -> dict[str, AgentTool]:
             'data_agent_normalize_dataset_draft': _normalize_dataset_draft_tool,
             'data_agent_validate_dataset_records': _validate_dataset_records_tool,
             'data_agent_export_dataset_records': _export_dataset_records_tool,
+            'data_agent_export_training_jsonl': _export_training_jsonl_tool,
+            'data_agent_export_planning_eval_csv': _export_planning_eval_csv_tool,
         }),
     ]
     return {tool.name: tool for tool in tools}
@@ -1550,6 +1554,70 @@ def _export_dataset_records_tool(arguments: dict[str, Any], context: ToolExecuti
     return json.dumps(payload, ensure_ascii=False, indent=2)
 
 
+def _export_training_jsonl_tool(arguments: dict[str, Any], context: ToolExecutionContext) -> str:
+    require_validation_ok = arguments.get('require_validation_ok', True)
+    if not isinstance(require_validation_ok, bool):
+        raise ToolExecutionError('require_validation_ok must be a boolean')
+    overwrite = arguments.get('overwrite', True)
+    if not isinstance(overwrite, bool):
+        raise ToolExecutionError('overwrite must be a boolean')
+    system_prompt = arguments.get('system_prompt', '你是小爱同学，中文智能语音助手。')
+    if not isinstance(system_prompt, str):
+        raise ToolExecutionError('system_prompt must be a string')
+    try:
+        records = _records_from_arguments(arguments, context)
+        payload = export_training_jsonl(
+            records,
+            root=str(context.root),
+            output_path=_data_agent_output_path(
+                _optional_string(arguments, 'output_path') or 'output/training.jsonl',
+                context,
+                canonical_filename='training.jsonl',
+            ),
+            session_num=_coerce_int(arguments, 'session_num', 5),
+            session_time_minutes=_coerce_int(arguments, 'session_time_minutes', 5),
+            context_fields=_optional_string_list(arguments, 'context_fields'),
+            system_prompt=system_prompt,
+            require_validation_ok=require_validation_ok,
+            overwrite=overwrite,
+        )
+    except (DataRecordError, json.JSONDecodeError) as exc:
+        raise ToolExecutionError(str(exc)) from exc
+    return json.dumps(payload, ensure_ascii=False, indent=2)
+
+
+def _export_planning_eval_csv_tool(arguments: dict[str, Any], context: ToolExecutionContext) -> str:
+    require_validation_ok = arguments.get('require_validation_ok', True)
+    if not isinstance(require_validation_ok, bool):
+        raise ToolExecutionError('require_validation_ok must be a boolean')
+    overwrite = arguments.get('overwrite', True)
+    if not isinstance(overwrite, bool):
+        raise ToolExecutionError('overwrite must be a boolean')
+    complex_default = arguments.get('complex_default', False)
+    if not isinstance(complex_default, bool):
+        raise ToolExecutionError('complex_default must be a boolean')
+    try:
+        records = _records_from_arguments(arguments, context)
+        payload = export_planning_eval_csv(
+            records,
+            root=str(context.root),
+            output_path=_data_agent_output_path(
+                _optional_string(arguments, 'output_path') or 'output/eval_planning.csv',
+                context,
+                canonical_filename='eval_planning.csv',
+            ),
+            session_num=_coerce_int(arguments, 'session_num', 5),
+            session_time_minutes=_coerce_int(arguments, 'session_time_minutes', 5),
+            context_fields=_optional_string_list(arguments, 'context_fields'),
+            complex_default=complex_default,
+            require_validation_ok=require_validation_ok,
+            overwrite=overwrite,
+        )
+    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')