.NET: [Bug]: HostedImageGenerationTool throws NullReferenceException

[marcominerva]

Description

When I add the HostedImageGenerationTool, I get a NullReferenceException.

Code Sample

#!/usr/bin/env dotnet

#:sdk Microsoft.NET.Sdk

#:property OutputType=Exe
#:property TargetFramework=net10.0
#:property ImplicitUsings=enable
#:property Nullable=enable
#:property NoWarn=$(NoWarn);MEAI001;OPENAI001;MAAI001
#:property PublishAot=false

#:package Microsoft.Agents.AI.OpenAI@1.3.0

using System.ClientModel;
using System.ClientModel.Primitives;
using System.ComponentModel;
using System.Diagnostics;
using System.Text.Encodings.Web;
using System.Text.Json;
using AgentSample;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI;
using OpenAI.Responses;

var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var apiKey = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY") ?? throw new InvalidOperationException("AZURE_OPENAI_API_KEY is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.5";

var openAIClient = new OpenAIClient(new ApiKeyCredential(Constants.ApiKey), new()
{
    Endpoint = new(Constants.Endpoint)
});

var chatClient = openAIClient.GetResponsesClient()
    .AsIChatClientWithStoredOutputDisabled(Constants.DeploymentName);

var agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
    Name = "ResponseAgent",
    ChatOptions = new()
    {
        Instructions = "You are a helpful assistant that provides concise and accurate answers to questions.",
        Reasoning = new()
        {
            Effort = ReasoningEffort.Medium,
            Output = ReasoningOutput.Summary
        },
        Tools = [new HostedImageGenerationTool()],
    }
});


var session = await agent.CreateSessionAsync();

while (true)
{
    Console.Write("Question: ");
    var question = Console.ReadLine()!;

    var response = await agent.RunAsync(question, session);
    Console.WriteLine(response);

    Console.WriteLine();
}

Error Messages / Stack Traces

System.ArgumentNullException: 'Value cannot be null. (Parameter 'value')'
   at OpenAI.Argument.AssertNotNull[T](T value, String name)
   at OpenAI.Responses.ImageGenerationToolOutputFileFormat..ctor(String value)
   at OpenAI.Responses.ImageGenerationToolOutputFileFormat.op_Implicit(String value)
   at Microsoft.Extensions.AI.OpenAIResponsesChatClient.ToResponseTool(AITool tool, ChatOptions options)
   at Microsoft.Extensions.AI.OpenAIResponsesChatClient.AsCreateResponseOptions(ChatOptions options, String& openAIConversationId)
   at Microsoft.Extensions.AI.OpenAIResponsesChatClient.GetResponseAsync(IEnumerable`1 messages, ChatOptions options, CancellationToken cancellationToken)
   at Microsoft.Extensions.AI.ConfigureOptionsChatClient.GetResponseAsync(IEnumerable`1 messages, ChatOptions options, CancellationToken cancellationToken)
   at Microsoft.Extensions.AI.FunctionInvokingChatClient.GetResponseAsync(IEnumerable`1 messages, ChatOptions options, CancellationToken cancellationToken)
   at Microsoft.Agents.AI.ChatClientAgent.RunCoreAsync(IEnumerable`1 messages, AgentSession session, AgentRunOptions options, CancellationToken cancellationToken)
   at Microsoft.Agents.AI.ChatClientAgent.RunCoreAsync(IEnumerable`1 messages, AgentSession session, AgentRunOptions options, CancellationToken cancellationToken)
   at Program.<Main>$(String[] args) in C:\Temp\AgentSample\AgentSample\Program.cs:line 108

Package Versions

Microsoft.Agents.AI.OpenAI: 1.3.0

.NET Version

.NET 10.0.7

[rogeriorfp]

@marcominerva Apparently, no default value is defined for the output format. You can explicitly set it as follows:

Tools = [
    new HostedImageGenerationTool()
    {
        Options = new()
        {
            MediaType = MediaTypeNames.Image.Png
        }
    }
],

You can also use MediaTypeNames.Image.Jpeg or MediaTypeNames.Image.Webp. Alternatively, you may use the string literals "image/png", "image/jpeg", or "image/webp".

Note: MediaTypeNames belongs to the System.Net.Mime namespace.

[marcominerva]

Thanks for your answer @rogeriorfp. I have tried your suggestion, but now I keep getting this exception:

 System.ClientModel.ClientResultException: 'HTTP 400 (invalid_request_error: )

There was an issue with your request. Please check your inputs and try again'

Here it is the raw HTTP messages of request and response:

Raw Request (https://commonservice-eastus2.openai.azure.com/openai/v1/responses)
{
  "model": "gpt-5.5",
  "reasoning": {
    "effort": "medium",
    "summary": "concise"
  },
  "tools": [
    {
      "type": "image_generation",
      "output_format": "jpeg"
    }
  ],
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "draw a tree"
        }
      ]
    }
  ],
  "include": [
    "reasoning.encrypted_content"
  ],
  "store": false,
  "instructions": "You are a helpful assistant that provides concise and accurate answers to questions."
}
--------------------------------------------------
Raw Response
{
  "error": {
    "message": "There was an issue with your request. Please check your inputs and try again",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

Interestingly, If I add other hosted tools like

Tools = [new HostedWebSearchTool(), new HostedCodeInterpreterTool(), new HostedImageGenerationTool()
    {
        Options = new()
        {
            MediaType = MediaTypeNames.Image.Jpeg
        }
    }
],

I get another error response (500):

Raw Request (https://commonservice-eastus2.openai.azure.com/openai/v1/responses)
{
  "model": "gpt-5.5",
  "reasoning": {
    "effort": "medium",
    "summary": "concise"
  },
  "tools": [
    {
      "type": "web_search"
    },
    {
      "type": "code_interpreter",
      "container": {
        "type": "auto"
      }
    },
    {
      "type": "image_generation",
      "output_format": "jpeg"
    }
  ],
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "draw a tree"
        }
      ]
    }
  ],
  "include": [
    "reasoning.encrypted_content"
  ],
  "store": false,
  "instructions": "You are a helpful assistant that provides concise and accurate answers to questions."
}
--------------------------------------------------
Raw Response
{
  "error": {
    "message": "The server had an error processing your request. Sorry about that! You can retry your request, or contact us through an Azure support request at: https://go.microsoft.com/fwlink/?linkid=2213926 if you keep seeing this error. (Please include the request ID 0d218528-7c85-4d8a-b64a-641ea4a95841 in your email.)",
    "type": "server_error",
    "param": null,
    "code": "server_error"
  }
}