Exception has occurred: ValidationError
1 validation error for ChatCompletions
choices.0.message.tool_calls.1
Input should be a valid dictionary or instance of ChatCompletionMessageToolCall [type=model_type, input_value=None, input_type=NoneType]
For further information visit https://errors.pydantic.dev/2.10/v/model_type
File "C:\Users\shreyas\Music\Cenzex\CityInsider\proto_agent_portkey.py", line 301, in trigger
response: ChatCompletion = await self.async_client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\shreyas\Music\Cenzex\CityInsider\proto_agent_portkey.py", line 420, in ask_question
return await self.trigger()
File "C:\Users\shreyas\Music\Cenzex\CityInsider\interface.py", line 80, in websocket_endpoint
response = await instance.ask_question(message["data"])
File "C:\Users\shreyas\Music\Cenzex\CityInsider\main.py", line 8, in <module>
uvicorn.run(app, port=7005, factory=False)
pydantic_core._pydantic_core.ValidationError: 1 validation error for ChatCompletions
choices.0.message.tool_calls.1
Input should be a valid dictionary or instance of ChatCompletionMessageToolCall [type=model_type, input_value=None, input_type=NoneType]
For further information visit https://errors.pydantic.dev/2.10/v/model_type ...

he has a fair point though, gemini, anthropic and all others support tool responses being images and so on, how do we accomodate for that at the gatewat level

[
{
"role": "system",
"content": "My System Prompt"
},
{
"role": "user",
"content": [
{
"type": "text",
"text": "when does the flight from baroda to bangalore land tomorrow, what time, what is its flight number, and what is its baggage belt?"
}
]
},
{
"role": "assistant",
"content": [
{
"type": "tool_use",
"id": "toolu_018fPMpEdPiCjkK8AkfCXgLh",
"name": "send_message_to_agent",
"input": {
"agent_name": "aggreg-agent",
"message": "WHAT: flight information from Baroda to Bangalore for tomorrow\nWHEN: tomorrow\nWHERE: Baroda to Bangalore"
}
}
]
},
{
"role": "user",
"content": [
{
"content": "tool call successful",
"type": "tool_result",
"tool_use_id": "toolu_018fPMpEdPiCjkK8AkfCXgLh"
}
]
}
]

One interesting question
how can i use google context caching feature with this

to use prompt caching by anthropic, do we just include the promptcaching cache type ephemeral as they have specified??

Not able to create virtual Keys