microsoft/autogen · error · ArgumentException

Invalid message type

Error message

Invalid message type

What it means

ArgumentException thrown by OpenAIChatAgent.CreateChatMessages: this agent only accepts messages that are IMessage<ChatMessage> envelopes (the official OpenAI SDK ChatMessage type). It performs no conversion of TextMessage or other AutoGen types itself — that is the job of the OpenAIChatRequestMessageConnector middleware.

Source

Thrown at dotnet/src/AutoGen.OpenAI/Agent/OpenAIChatAgent.cs:123

        var settings = this.CreateChatCompletionsOptions(options);
        var response = this.chatClient.CompleteChatStreamingAsync(chatHistory, settings, cancellationToken);
        await foreach (var update in response.WithCancellation(cancellationToken))
        {
            if (update.ContentUpdate.Count > 1)
            {
                throw new InvalidOperationException("Only one choice is supported in streaming response");
            }

            yield return new MessageEnvelope<StreamingChatCompletionUpdate>(update, from: this.Name);
        }
    }

    private IEnumerable<ChatMessage> CreateChatMessages(IEnumerable<IMessage> messages)
    {
        var oaiMessages = messages.Select(m => m switch
        {
            IMessage<ChatMessage> chatMessage => chatMessage.Content,
            _ => throw new ArgumentException("Invalid message type")
        });

        // add system message if there's no system message in messages
        if (!oaiMessages.Any(m => m is SystemChatMessage) && systemMessage is not null)
        {
            oaiMessages = new[] { new SystemChatMessage(systemMessage) }.Concat(oaiMessages);
        }

        return oaiMessages;
    }

    private ChatCompletionOptions CreateChatCompletionsOptions(GenerateReplyOptions? options)
    {
        var option = new ChatCompletionOptions()
        {
            Seed = this.options.Seed,
            Temperature = options?.Temperature ?? this.options.Temperature,
            MaxOutputTokenCount = options?.MaxToken ?? this.options.MaxOutputTokenCount,

View on GitHub (pinned to 027ecf0a37)

Solutions

1. Register the message connector: agent.RegisterMessageConnector() wraps the agent with OpenAIChatRequestMessageConnector which converts TextMessage et al. to ChatMessage
2. Or convert messages yourself to MessageEnvelope.Create(new UserChatMessage("...")) before sending
3. Verify no middleware is stripping ChatMessage envelopes back into plain messages

Example fix

// before
var agent = new OpenAIChatAgent(chatClient, name: "assistant");
await agent.SendAsync("hi"); // ArgumentException: Invalid message type

// after
var agent = new OpenAIChatAgent(chatClient, name: "assistant")
    .RegisterMessageConnector();
await agent.SendAsync("hi");

// ensure every message is a ChatMessage envelope before calling a bare OpenAIChatAgent
bool ok = messages.All(m => m is IMessage<ChatMessage>);

static bool IsChatMessageEnvelope(IMessage m) => m is IMessage<ChatMessage>;

catch (ArgumentException ex) when (ex.Message == "Invalid message type") { /* register message connector and retry */ }

When it happens

Trigger: Calling GenerateReplyAsync/GenerateStreamingReplyAsync on a bare OpenAIChatAgent with TextMessage, IMessage<string>, or any non-MessageEnvelope<ChatMessage> input.

Common situations: Using OpenAIChatAgent directly without calling RegisterMessageConnector(); migrating code from AutoGen.OpenAI.V1 where types differ; assuming the agent does its own message translation.

Related errors

• Invalid return message type {message.GetType().Name}
• Please set OPENAI_API_KEY environment variable.
• Please set OPENAI_API_KEY environment variable.
• Please set OPENAI_API_KEY environment variable.
• Please set OPENAI_API_KEY environment variable.

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/b959eae8c2adabf0. Report an issue: GitHub.