microsoft-foundry / microsoft-foundry/foundry-samples
/responses endpoint returns "conversation": null, causing AgentThreadAndHITL flow to fail.
@dooriya is already working on this.
Since Aug 13, 2026.
- Dominant language
- Bicep
- Stars
- 445
- Forks
- 494
- Avg merge
- 11h 35m
- Merged PRs (30d)
- 38
Description
I tried to interact with the agent workflow at https://github.com/microsoft-foundry/foundry-samples/tree/main/samples/csharp/hosted-agents/AgentFramework/AgentThreadAndHITL using:
- The
test_requests.pyfile to test and prompt the agent - Any OpenAI Responses compatible client by sending requests to
http://localhost:8080/
The response contains:
"conversation": null
response output example snippet:
{ "status": "completed", "output": [ { "type": "function_call", "id": "msg_ffzNgCBMBDvnEoUmpy04qiQX11DcfTCuani6MPi5O51kZ6oHV9", "created_by": { "response_id": "resp_ffzNgCBMBDvnEoUmpyN6826hrdV3g4ojGJsYh0R4BwzM5MhwJf" }, "status": "in_progress", "call_id": "call_O6udgoGJXxoaHjAJhoLADgvG", "name": "__hosted_agent_adapter_hitl__", } ], "conversation": null, "agent": { "type": "agent_reference", "name": "local_agent", }, }
Since "conversation" is null:
conversation_idcannot be extracted- Follow-up request with function_call_output cannot be tied to a conversation
- HITL flow cannot continue
Because of this, it is not possible to extract a conversation_id and continue the HITL workflow by sending function call output in a follow-up request.
Contributor 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.
Assessment
This issue has not been assessed yet.