Python: [Bug]: Multi-turn tool calls fail with both Responses API and Chat Completions API when used via agent-framework-ag-ui (Foundry project endpoint)

Description

Summary

Using agent-framework-ag-ui from Python with a Microsoft Foundry project inference endpoint, the first turn of a tool-calling chat works correctly, but any second or later turn that follows a tool call fails with a 400 from the upstream OpenAI API.

The failure mode differs by client type but both surface a consistent root cause: when AG-UI replays conversation history on subsequent turns, the messages produced by the prior tool-calling turn are not paired correctly with their tool results before being sent back to the LLM.

This affects all four AG-UI features we tested (Agentic Chat, Human-in-the-Loop, Shared State, Agentic Generative UI) as soon as the agent has invoked any tool at least once.

Code Sample

## Reproduction

Minimal server (full repo: <will-be-linked>):


import os
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIChatClient  # or OpenAIChatCompletionClient — both fail
from agent_framework_ag_ui import add_agent_framework_fastapi_endpoint
from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from dotenv import load_dotenv

load_dotenv()

@tool
def search_cars(car_class: str | None = None) -> list[dict]:
    return [{"car_id": "SUV-001", "class": "suv", "daily_jpy": 12800}]

client = OpenAIChatClient(  # also tried OpenAIChatCompletionClient — same outcome, different error
    model=os.environ["FOUNDRY_MODEL"],
    base_url=os.environ["FOUNDRY_BASE_URL"],  # ".../openai/v1"
    api_key=os.environ["FOUNDRY_API_KEY"],
)

agent = Agent(
    name="ShirokumaChat",
    instructions="You are a car rental booking assistant.",
    client=client,
    tools=[search_cars],
)

app = FastAPI()
app.add_middleware(CORSMiddleware, allow_origins=["*"], allow_methods=["*"], allow_headers=["*"])
add_agent_framework_fastapi_endpoint(app, agent, "/agentic_chat")


Steps:

1. Start the server on `localhost:8888`.
2. In AG-UI Dojo (running locally), open the Agentic Chat tab for `Microsoft Agent Framework (Python)`.
3. Send turn 1: "Show me your SUV cars" → tool is called, response streams correctly. ✅
4. Send turn 2 in the **same** chat session (anything, e.g. "What's the price?") → server returns 200 but the stream contains a `RUN_ERROR` and no text response. ❌

Error Messages / Stack Traces

## Expected behavior

Subsequent turns should continue the conversation, with the agent having access to the tool result from the previous turn.

## Actual behavior

### With `OpenAIChatClient` (Responses API)


openai.BadRequestError: Error code: 400 - {
  'error': {
    'message': 'No tool output found for function call call_cLJJ7tsAQL9j7ZK3J1g8ca30.',
    'type': 'invalid_request_error',
    'param': 'input',
    'code': None
  }
}


Full traceback (abridged):


File ".venv/Lib/site-packages/agent_framework_openai/_chat_client.py", line 647, in _stream
    async for chunk in await client.responses.create(stream=True, **run_options):
File ".venv/Lib/site-packages/openai/resources/responses/responses.py", line 2626, in create
    return await self._post(...)
agent_framework.exceptions.ChatClientException: OpenAIChatClient service failed to complete the prompt: 400 - No tool output found for function call call_cLJJ7tsAQL9j7ZK3J1g8ca30.


### With `OpenAIChatCompletionClient` (Chat Completions API)


openai.BadRequestError: Error code: 400 - {
  'error': {
    'message': "An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'. The following tool_call_ids did not have response messages: call_7jOeA41CWTxLIyheCJnxqr6G, call_cWxiZjHImVV1KTq6ajOqTbnB",
    'type': 'invalid_request_error',
    'param': 'messages.[3].role',
    'code': None
  }
}


Full traceback (abridged):


File ".venv/Lib/site-packages/agent_framework_openai/_chat_completion_client.py", line 522, in _stream
    async for chunk in await client.chat.completions.create(stream=True, **options_dict):
agent_framework.exceptions.ChatClientException: OpenAIChatCompletionClient service failed to complete the prompt:
  An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'.

Package Versions

agent-framework-core 1.4.0, agent-framework-ag-ui 1.0.0rc1, agent-framework-openai 1.4.0, ag-ui-protocol 0.1.18, openai 2.37.0, fastapi 0.133.0, pydantic 2.13.4

Python Version

3.12.11

Additional Context

Frontend: AG-UI Dojo (apps/dojo in ag-ui-protocol/ag-ui, latest main), integration = Microsoft Agent Framework (Python), pointed at our local server via AGENT_FRAMEWORK_PYTHON_URL=http://localhost:8888.

Backend endpoint: Microsoft Foundry project inference URL of the form
https://<resource>.services.ai.azure.com/api/projects/<project>/openai/v1
authenticated with an API key.

Why both APIs fail (analysis)

Both errors point at the same root cause from different angles:

Chat Completions strictly requires (assistant{tool_calls}, tool{tool_call_id}) pairs to be interleaved in the messages array. The 400 says the tool role messages are missing from the replayed history.
Responses API expects function call results to be presented as function_call_output items in input. The 400 says the output for a specific call_id is missing.

In both cases, AG-UI's HttpAgent (or whatever produces the replayed history sent to the Python backend) is dropping or mis-pairing the tool result messages from the previous turn. The server-side agent-framework-ag-ui pipeline appears to pass this incomplete history through to the chat client without reconstructing the missing pairs.

Related issues

Python: [Bug]: Tool calling not working with Responses API #3304 — Python: Tool calling not working with Responses API (matches our Responses-API error exactly)
.NET: AG-UI: Multi-turn tool calls replay produces invalid OpenAI tool_call history #2699 — .NET: AG-UI: Multi-turn tool calls replay produces invalid OpenAI tool_call history (.NET equivalent of our Chat Completions error)
Python: AG-UI, Tool calls suppress shared state message injection #3010 — Python: AG-UI shared state breaks after first tool call
Python: [Bug]: MCP Tool Calls + Reasoning Not Emitted as AG-UI Events (Foundry) #4213 — Python: MCP tool calls + reasoning not emitted as AG-UI events (Foundry)
Python: [AG-UI] Error occurs when using with_plan_review in Magentic workflow #3331 — Python: with_plan_review in Magentic workflow + AG-UI
AG-UI: tool result messages missing from conversation history on subsequent turns (causes LLM 400) CopilotKit/CopilotKit#3884 — AG-UI: tool result messages missing from conversation history on subsequent turns (client-side cause), proposes PR .NET: AF version bump 12-feb #3885

This issue intentionally reports the end-to-end symptom on Python + Foundry with both client types, because the existing issues are scattered (per-API, per-platform, per-feature) and the impression from a user's perspective is that AG-UI is currently unusable for any multi-turn tool-calling scenario in Python — which is not made visible in the AG-UI integration docs or the Microsoft Community Hub announcement post.

Requests

Confirm whether the root cause is server-side (agent-framework-ag-ui history reconstruction) or client-side (AG-UI Dojo / HttpAgent not sending tool results back) — or both.
Add a documentation note about the current limitation on the AG-UI integration page until fixed.
Coordinate with CopilotKit#3884 / PR .NET: AF version bump 12-feb #3885 if the fix needs to land on both sides.

Workaround tried

We are evaluating the workaround suggested in CopilotKit#3884: subclass AgentFrameworkAgent to scan input messages and inject synthetic tool (or function_call_output) entries for any tool_call_id that lacks a matching result before handing off to the chat client. Will follow up here with results.

I am encountering related error not from AgentFramework, but from Agent Service. However, it's intermittent in nature. I am creating PromptAgentDefinition Agent with local functions (FunctionTool) and the conversation is maintained using conversation_id:

---------------------------------------------------------------------------
BadRequestError                           Traceback (most recent call last)
Cell In[66], line 1
----> 1 response = invoke_agent_stream(
      2     ".........",
      3     conversation_id=conversation.id,
      4     openai_client=openai_client,
      5 )
      6 response.id

Cell In[64], line 38, in invoke_agent_stream(prompt, conversation_id, max_hops, openai_client)
     35 if conversation_id is not None:
     36     print(f"[agent] Using conversation_id={conversation_id}")
---> 38 stream = openai_client.responses.create(**request)
     40 response = None
     41 printed = False

File ~/<PROJECT_HOME>/venv/lib/python3.12/site-packages/openai/resources/responses/responses.py:898, in Responses.create(self, background, context_management, conversation, include, input, instructions, max_output_tokens, max_tool_calls, metadata, model, parallel_tool_calls, previous_response_id, prompt, prompt_cache_key, prompt_cache_retention, reasoning, safety_identifier, service_tier, store, stream, stream_options, temperature, text, tool_choice, tools, top_logprobs, top_p, truncation, user, extra_headers, extra_query, extra_body, timeout)
    859 def create(
    860     self,
    861     *,
   (...)    896     timeout: float | httpx.Timeout | None | NotGiven = not_given,
    897 ) -> Response | Stream[ResponseStreamEvent]:
--> 898     return self._post(
    899         "/responses",
    900         body=maybe_transform(
    901             {
    902                 "background": background,
    903                 "context_management": context_management,
    904                 "conversation": conversation,
    905                 "include": include,
    906                 "input": input,
    907                 "instructions": instructions,
    908                 "max_output_tokens": max_output_tokens,
    909                 "max_tool_calls": max_tool_calls,
    910                 "metadata": metadata,
    911                 "model": model,
    912                 "parallel_tool_calls": parallel_tool_calls,
    913                 "previous_response_id": previous_response_id,
    914                 "prompt": prompt,
    915                 "prompt_cache_key": prompt_cache_key,
    916                 "prompt_cache_retention": prompt_cache_retention,
    917                 "reasoning": reasoning,
    918                 "safety_identifier": safety_identifier,
    919                 "service_tier": service_tier,
    920                 "store": store,
    921                 "stream": stream,
    922                 "stream_options": stream_options,
    923                 "temperature": temperature,
    924                 "text": text,
    925                 "tool_choice": tool_choice,
    926                 "tools": tools,
    927                 "top_logprobs": top_logprobs,
    928                 "top_p": top_p,
    929                 "truncation": truncation,
    930                 "user": user,
    931             },
    932             response_create_params.ResponseCreateParamsStreaming
    933             if stream
    934             else response_create_params.ResponseCreateParamsNonStreaming,
    935         ),
    936         options=make_request_options(
    937             extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
    938         ),
    939         cast_to=Response,
    940         stream=stream or False,
    941         stream_cls=Stream[ResponseStreamEvent],
    942     )

File ~/vssexclude/ai_cortix/foundryiq_poc/cortix-reco-qa-gen-poc/venv/lib/python3.12/site-packages/openai/_base_client.py:1297, in SyncAPIClient.post(self, path, cast_to, body, content, options, files, stream, stream_cls)
   1288     warnings.warn(
   1289         "Passing raw bytes as `body` is deprecated and will be removed in a future version. "
   1290         "Please pass raw bytes via the `content` parameter instead.",
   1291         DeprecationWarning,
   1292         stacklevel=2,
   1293     )
   1294 opts = FinalRequestOptions.construct(
   1295     method="post", url=path, json_data=body, content=content, files=to_httpx_files(files), **options
   1296 )
-> 1297 return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))

File ~/vssexclude/ai_cortix/foundryiq_poc/cortix-reco-qa-gen-poc/venv/lib/python3.12/site-packages/openai/_base_client.py:1070, in SyncAPIClient.request(self, cast_to, options, stream, stream_cls)
   1067             err.response.read()
   1069         log.debug("Re-raising status error")
-> 1070         raise self._make_status_error_from_response(err.response) from None
   1072     break
   1074 assert response is not None, "could not resolve response (should never happen)"

BadRequestError: Error code: 400 - {'error': {'message': 'No tool output found for function call call_SaZJpeD4Xp4R2L6nE9OyxCWM.', 'type': 'invalid_request_error', 'param': 'input', 'code': None}}

shirokuma (@nomhiro)

👋 Hi shirokuma (@nomhiro) — thanks for the report!

Your error messages ('No tool output found for function call_cLJJ7tsAQL9j7ZK3J1g8ca30' and 'tool_call_ids did not have response messages') match a confirmed bug in _sanitize_tool_history within agent-framework-ag-ui where the history sanitizer silently dropped pending tool call state when a second assistant message arrived. This was fixed in PR #6581 (commit 5145d50, merged 2026-06-19). Since you reported running agent-framework-ag-ui 1.0.0rc1, upgrading to 1.0.0rc7 or later should resolve the multi-turn tool-calling failures you observed with both the Responses API and Chat Completions API.

You reported using: agent-framework-ag-ui 1.0.0rc1
Latest version: 1.0.0rc7
Likely fix: 5145d50be803

If upgrading to the latest release doesn't fix it, please reopen and we'll take another look. 🙏

Navigation Menu

Repository navigation

Python: [Bug]: Multi-turn tool calls fail with both Responses API and Chat Completions API when used via `agent-framework-ag-ui` (Foundry project endpoint) #5941

Description

Summary

Code Sample

Error Messages / Stack Traces

Package Versions

Python Version

Additional Context

Why both APIs fail (analysis)

Related issues

Requests

Workaround tried

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Python: [Bug]: Multi-turn tool calls fail with both Responses API and Chat Completions API when used via agent-framework-ag-ui (Foundry project endpoint) #5941

Description

Description

Summary

Code Sample

Error Messages / Stack Traces

Package Versions

Python Version

Additional Context

Why both APIs fail (analysis)

Related issues

Requests

Workaround tried

Activity

arnabbiswas1 commented on May 27, 2026

github-actions commented on Jul 7, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions

Python: [Bug]: Multi-turn tool calls fail with both Responses API and Chat Completions API when used via `agent-framework-ag-ui` (Foundry project endpoint) #5941