I have a fairly lengthy system message and output json_schema and when I start a responses conversation it works great until the model (gpt-4o-mini) decides it needs to search for something. If it’s not found it just slightly re-words the search criteria over and over again until it runs out of some…

Responses seems to get stuck in a loop with vector stores

rahman.abdirashov April 8, 2025, 8:39am 4

It works now in the OpenAI playground. The issue seems fixed.

Topic		Replies	Views
GPT-4o Cannot continue a conversation Bugs	1	315	September 24, 2024
Gpt4o-mini retrieval doesn't work as expected? API assistants-api , vector-store , gpt-4o-mini	9	946	February 18, 2025
Realtime Audio API Looping Constantly Bug Bugs realtime	9	375	April 24, 2025
API to gpt-3.5-turbo-16k getting stuck in a loop until it reaches max tokens API	7	1250	November 21, 2023
Assistant starts to ignore user prompts after a few Create Run API calls API gpt-4 , assistants-api	2	503	June 13, 2024