Please read this first

• Have you read the docs? Agents SDK docs
  • Yes
• Have you searched for related issues? Others may have faced similar issues.
  • Yes

Describe the bug

When adding previous_response_id to Runner.run, I receive this error:

Error getting response: Error code: 400 - {'error': {'message': 'No tool output found for function call call_***.', 'type': 'invalid_request_error', 'param': 'input', 'code': None}}. (request_id: req_***)

Here's the code of the runner, previous_response_id is definitely correct, when I throw in a random string there I get a different error stating it's invalid.

result = await Runner.run(
    starting_agent=orchestrator_agent,
    input=prompt,
    context=context,
    previous_response_id=req.message.previous_response_id, # <- Added here
)

Orchestrator calls other agents which themselves have access to various tools/functions. All works fine until I add previous_response_id.

Debug information

• Agents SDK version: v0.0.14
• Python version 3.12