_get_tools in ChatTemplateStrategy : function "parameters" can be dict or string (#3238)

* When training of function calls, "tools" elements of a dataset can contain same parameter name but with different types. Datasets fails to load such training set. This fix allows "parameters" element of function call to be string( by running "json.dumps" in preparation of training data set). The _get_tools function will iterate over tool definitions, if "parameters" element is dict, it will keep that way, if it is a string, it will be converted to dict by invoking "json.loads" on string value.

* feat: add doc on tool parameters json loading

* feat: add tests for parameters json string

---------

Co-authored-by: ezlotnik <eduard_zlotnik@intuit.com>
Co-authored-by: NanoCode012 <nano@axolotl.ai>

src/axolotl/prompt_strategies/chat_template.py

@@ -823,6 +823,23 @@ class ChatTemplateStrategy(PromptTokenizingStrategy):
             return None
 
         if isinstance(tools, list):
+            # Process each tool to handle JSON string parameters
+            for tool in tools:
+                if isinstance(tool, dict) and "function" in tool:
+                    function = tool["function"]
+                    if "parameters" in function:
+                        params = function["parameters"]
+                        if isinstance(params, str):
+                            try:
+                                function["parameters"] = json.loads(params)
+                            except json.JSONDecodeError as e:
+                                LOG.error(
+                                    f"Error parsing tool parameters as JSON. "
+                                    f"Function: {function.get('name', 'unknown')}, "
+                                    f"Parameters string: {params!r}, "
+                                    f"Error: {e}"
+                                )
+                                raise
             return tools
 
         raise ValueError(