fix parse tools (#3975)

Author: Jintao-Huang

docs/source/Instruction/Agent支持.md

@@ -185,7 +185,7 @@ tools = [{
 
 ## loss_scale的使用
 
-loss_scale可以对模型输出部分的训练损失权重进行调节。例如在ReACT格式中，可以设置`--loss_scale react`（loss_scale配置文件书写在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/loss_scale/config/default_loss_scale_config.json)），该参数起到的作用是：
+loss_scale可以对模型输出部分的训练损失权重进行调节。例如在ReACT格式中，可以设置`--loss_scale react`（loss_scale配置文件书写在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/loss_scale/config/react.json)），该参数起到的作用是：
 
 'Thought:'和'Final Answer:'部分权重为1，'Action:'和'Action Input:'部分权重为2，'Observation:'字段本身权重为2，'Observation:'后面的工具调用结果权重为0。
 

docs/source_en/Instruction/Agent-support.md

@@ -190,7 +190,7 @@ tools = [{
 
 ## Usage of loss_scale
 
-`loss_scale` can be used to adjust the training loss weight for the model's output section. For example, in the ReACT format, you can set `--loss_scale react` (the loss_scale configuration file is written [here](https://github.com/modelscope/swift/blob/main/swift/plugin/loss_scale/config/default_loss_scale_config.json)). The role of this parameter is as follows:
+`loss_scale` can be used to adjust the training loss weight for the model's output section. For example, in the ReACT format, you can set `--loss_scale react` (the loss_scale configuration file is written [here](https://github.com/modelscope/swift/blob/main/swift/plugin/loss_scale/config/react.json)). The role of this parameter is as follows:
 
 - The weight for the 'Thought:' and 'Final Answer:' sections is 1.
 - The weight for the 'Action:' and 'Action Input:' sections is 2.

swift/llm/template/base.py

@@ -188,7 +188,14 @@ def _preprocess_function_call(self, inputs: StdTemplateInputs) -> None:
         agent_template = self.agent_template
         agent_template.template_meta = self.template_meta  # for hermes
         if inputs.tools:
-            inputs.tools = [agent_template._parse_json(tool) for tool in inputs.tools]
+            if isinstance(inputs.tools, str):
+                inputs.tools = agent_template._parse_json(inputs.tools)
+                if not isinstance(inputs.tools, (list, tuple)):
+                    inputs.tools = [inputs.tools]
+            elif isinstance(inputs.tools, (list, tuple)):
+                inputs.tools = [agent_template._parse_json(tool) for tool in inputs.tools]
+            else:
+                raise ValueError(f'inputs.tools: {inputs.tools}')
             for i, tool in enumerate(inputs.tools):
                 inputs.tools[i] = agent_template.wrap_tool(tool)
         i = 0