[MEAI.OpenAI] OpenAIResponsesChatClient streams reasoning and non-message items with Role=null, merging them into preceding Tool messages ```
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 78/100
Research direction
Start in src/Libraries/Microsoft.Extensions.AI.OpenAI/OpenAIResponsesChatClient.cs, focusing on how lastRole is set for reasoning and other output items before the first message or function call. Compare that with the existing FunctionCallOutputResponseItem handling, then inspect ChatResponseExtensions.ProcessUpdate to understand how role-less updates are combined. Done means the reproduction places the second turn's reasoning and other output items in an assistant message, leaving the tool message with only its function result.
Written by the indexing model from the issue text.
Description
Description
In OpenAIResponsesChatClient.GetStreamingResponseAsync, lastRole and lastMessageId are initialized to null at the start of each model call and are only assigned when a MessageResponseItem or FunctionCallResponseItem is added.
Because OpenAI's /v1/responses streaming API emits reasoning items (and default output items such as compaction) before any message or function_call item, those ChatResponseUpdate instances are yielded with Role = null and MessageId = null.
When OpenAIResponsesChatClient runs inside a multi-turn tool loop (such as FunctionInvokingChatClient or Microsoft.Agents.AI agents) and updates are combined via ToChatResponse() / ToChatResponseAsync() — including inside OpenTelemetryChatClient when serializing gen_ai.output.messages — ChatResponseExtensions.ProcessUpdate treats Role == null && MessageId == null as a continuation of the previous message and appends the next model call's TextReasoningContent (and AIContent items) onto the preceding ChatRole.Tool message.
Reproduction Steps
Create a .NET 10.0 console project with Microsoft.Extensions.AI 11.0.0 and Microsoft.Extensions.AI.OpenAI 11.0.0 (no API key or network access needed) and run dotnet run:
<!-- Repro.csproj -->
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFramework>net10.0</TargetFramework>
<ImplicitUsings>enable</ImplicitUsings>
<Nullable>enable</Nullable>
<NoWarn>OPENAI001</NoWarn>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Microsoft.Extensions.AI" Version="11.0.0" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="11.0.0" />
</ItemGroup>
</Project>
// Program.cs
using System.ClientModel;
using System.ClientModel.Primitives;
using System.Net;
using System.Text;
using Microsoft.Extensions.AI;
using OpenAI;
using OpenAI.Responses;
const string Turn1Sse = """
event: response.created
data: {"type":"response.created","sequence_number":0,"response":{"id":"resp_1","object":"response","created_at":1700000000,"status":"in_progress","model":"gpt-5","output":[]}}
event: response.output_item.added
data: {"type":"response.output_item.added","sequence_number":1,"output_index":0,"item":{"id":"fc_1","type":"function_call","status":"in_progress","call_id":"call_1","name":"get_menu","arguments":""}}
event: response.function_call_arguments.delta
data: {"type":"response.function_call_arguments.delta","sequence_number":2,"item_id":"fc_1","output_index":0,"delta":"{}"}
event: response.output_item.done
data: {"type":"response.output_item.done","sequence_number":3,"output_index":0,"item":{"id":"fc_1","type":"function_call","status":"completed","call_id":"call_1","name":"get_menu","arguments":"{}"}}
event: response.completed
data: {"type":"response.completed","sequence_number":4,"response":{"id":"resp_1","object":"response","created_at":1700000000,"status":"completed","model":"gpt-5","output":[{"id":"fc_1","type":"function_call","status":"completed","call_id":"call_1","name":"get_menu","arguments":"{}"}]}}
""";
const string Turn2Sse = """
event: response.created
data: {"type":"response.created","sequence_number":0,"response":{"id":"resp_2","object":"response","created_at":1700000001,"status":"in_progress","model":"gpt-5","output":[]}}
event: response.output_item.added
data: {"type":"response.output_item.added","sequence_number":1,"output_index":0,"item":{"id":"rs_1","type":"reasoning","summary":[]}}
event: response.reasoning_summary_text.delta
data: {"type":"response.reasoning_summary_text.delta","sequence_number":2,"item_id":"rs_1","output_index":0,"summary_index":0,"delta":"Thinking about the menu..."}
event: response.output_item.done
data: {"type":"response.output_item.done","sequence_number":3,"output_index":0,"item":{"id":"rs_1","type":"reasoning","summary":[{"type":"summary_text","text":"Thinking about the menu..."}]}}
event: response.output_item.added
data: {"type":"response.output_item.added","sequence_number":4,"output_index":1,"item":{"id":"msg_1","type":"message","status":"in_progress","role":"assistant","content":[]}}
event: response.output_text.delta
data: {"type":"response.output_text.delta","sequence_number":5,"item_id":"msg_1","output_index":1,"content_index":0,"delta":"Burger is $10."}
event: response.output_item.done
data: {"type":"response.output_item.done","sequence_number":6,"output_index":1,"item":{"id":"msg_1","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Burger is $10.","annotations":[]}]}}
event: response.completed
data: {"type":"response.completed","sequence_number":7,"response":{"id":"resp_2","object":"response","created_at":1700000001,"status":"completed","model":"gpt-5","output":[{"id":"rs_1","type":"reasoning","summary":[{"type":"summary_text","text":"Thinking about the menu..."}]},{"id":"msg_1","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Burger is $10.","annotations":[]}]}]}}
""";
int call = 0;
using var httpClient = new HttpClient(new FakeSseHandler(() => ++call == 1 ? Turn1Sse : Turn2Sse));
var openAiOptions = new OpenAIClientOptions { Transport = new HttpClientPipelineTransport(httpClient) };
IChatClient client = new OpenAIClient(new ApiKeyCredential("fake"), openAiOptions)
.GetResponsesClient()
.AsIChatClient("gpt-5")
.AsBuilder()
.UseFunctionInvocation()
.Build();
var options = new ChatOptions { Tools = [AIFunctionFactory.Create(() => "Burger $10", "get_menu")] };
ChatResponse response = await client.GetStreamingResponseAsync("What is on the menu?", options).ToChatResponseAsync();
for (int i = 0; i < response.Messages.Count; i++)
{
var m = response.Messages[i];
Console.WriteLine($"Message[{i}] Role={m.Role}: [{string.Join(", ", m.Contents.Select(c => c.GetType().Name))}]");
}
sealed class FakeSseHandler(Func<string> nextSse) : HttpMessageHandler
{
protected override Task<HttpResponseMessage> SendAsync(HttpRequestMessage request, CancellationToken cancellationToken) =>
Task.FromResult(new HttpResponseMessage(HttpStatusCode.OK)
{
Content = new StringContent(nextSse(), Encoding.UTF8, "text/event-stream")
});
}
Expected behavior
Message[1] (Role=tool) contains only FunctionResultContent, and the second turn's TextReasoningContent (and any AIContent output items) are placed in an assistant message:
Message[0] Role=assistant: [FunctionCallContent]
Message[1] Role=tool: [FunctionResultContent]
Message[2] Role=assistant: [TextReasoningContent, TextContent]
Actual behavior
TextReasoningContent (and any default AIContent items such as Responses compaction items) from the second model call are merged into Message[1] (Role=tool):
Message[0] Role=assistant: [FunctionCallContent]
Message[1] Role=tool: [FunctionResultContent, TextReasoningContent]
Message[2] Role=assistant: [TextContent]
When OpenTelemetryChatClient wraps a multi-turn tool or agent loop (for example via UseOpenTelemetry() above UseFunctionInvocation(), or Microsoft.Agents.AI's OpenTelemetryAgent), gen_ai.output.messages records model reasoning and compaction items inside role: "tool" messages.
Regression?
No — present in Microsoft.Extensions.AI.OpenAI 10.0.0 through 11.0.0.
Known Workarounds
Wrap the inner OpenAIResponsesChatClient in a DelegatingChatClient that defaults update.Role ??= ChatRole.Assistant; on each ChatResponseUpdate yielded from GetStreamingResponseAsync.
Configuration
Microsoft.Extensions.AI:11.0.0Microsoft.Extensions.AI.OpenAI:11.0.0- .NET SDK / Runtime:
.NET 10.0(OS-independent; reproduced on Linux and Windows)
Other information
Root cause in OpenAIResponsesChatClient (v11.0.0):
lastRoleandlastMessageIdstart asnullper call, andCreateUpdateconstructs every update withnew(lastRole, ...):OpenAIResponsesChatClient.cs#L371-L386(v11.0.0)lastRoleis assigned only when aMessageResponseItemorFunctionCallResponseItemis added:OpenAIResponsesChatClient.cs#L459-L471(v11.0.0)- Reasoning deltas, encrypted reasoning items, and
defaultitems (such as compaction) arrive before any message/function-call item and are yielded withRole = null: FunctionCallOutputResponseItemin the same method already setslastRole ??= ChatRole.Assistant;:OpenAIResponsesChatClient.cs#L558-L561(v11.0.0). SettinglastRole ??= ChatRole.Assistant;for reasoning and other model output items (or initializinglastRole = ChatRole.Assistant) ensuresChatResponseExtensions.ProcessUpdate(ChatResponseExtensions.cs#L538-L562(v11.0.0)) starts a newassistantmessage after atoolmessage, including inOpenTelemetryChatClient(OpenTelemetryChatClient.cs#L267(v11.0.0)).
- Dominant language
- C#
- Stars
- 3.3k
- Forks
- 919
- Avg merge
- 2d 2h
- Merged PRs (30d)
- 35
Getting set up
Starts the project's dev container in your browser, under your own GitHub account.
- No Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from dotnet/extensions
-
area-ai untriaged
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
dotnet/extensions#7956 ·
Maintainers usually reply within 1 day
-
ServiceEndpointWatcher logs normal cancellation as an errorPossibly taken @seragAhmed claimed this 5 days ago. Openbug untriaged
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
dotnet/extensions#7940 · 1 comment ·
Maintainers usually reply within 1 day
-
OpenAISpeechToTextClient sends Ogg MemoryStream audio with an .mp3 filenamePossibly taken @Manish-1kumar claimed this 17 days ago. Openarea-ai untriaged
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
dotnet/extensions#7900 · 1 comment ·
Maintainers usually reply within 1 day
-
Unable to obtain the UsageContent and FinishReason of response.incompletePossibly taken @jaeminbird claimed this 20 days ago. Openarea-ai bug untriaged
Difficulty 2/5 1-3 hours Newbie friendliness 67/100
dotnet/extensions#7893 ·
Maintainers usually reply within 1 day
-
AI Chat Web template: scaffolded Identity pages are inaccessible because App.razor applies an interactive render mode unconditionallyPossibly taken @valkiara claimed this 20 days ago. Openarea-ai-templates untriaged
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
dotnet/extensions#7889 · 1 comment ·
Maintainers usually reply within 1 day
All issues in dotnet/extensions
Similar issues
-
documentation
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
-
area/backend type/bug
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
umbraco/Umbraco-CMS#24668 · 1 comment ·
Maintainers usually reply within 1 day
-
Pri3
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
MicrosoftDocs/windows-dev-docs#6205 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
Maintainers usually reply within 1 day