I have been getting frequent ClientResponseError coming back from Tool requests from a custom GPT the last two days. My APIs are alive and operational. The problem seems to come and go. Anybody else experiencing this?
Thanks for flagging this - that definitely sounds frustrating, especially if everything on your end looks healthy.
Would you mind creating a support ticket for this? That’ll help our team take a closer look at what’s happening under the hood and investigate any intermittent issues like the one you’re describing.
Once the ticket is created, please share the case ID here so I can take a look at it internally and help move things along.
I know there have been many recent changes and commits in Codex related to tools. I am not sure whether the API and Codex are connected in this case, but if they are, this example of a commit may shed some light on the issue:
A similar pattern happened a few days ago when users were reporting MCP problems around the same time there were Codex commits related to MCP.
Again, this is only a guess, but there are at least a few facts that seem to correlate.
Hi. If anyone can find a solution to this problem please let us know here. The issue is very frustrating since we can’t do anything about it. And as mentioned it is flaky. I managed to work only once after several tries and no more luck after that. Thanks to those who is dedicatedly working on this. But please update us for any potential solutions or workaround that is available. Right now no call is working. Custom GPT lost a lot of viability for this issue.