Hi,

We’ve noticed what appears to be a regression in how GPT Apps behave on desktop.

Previously, once an app had been invoked in a conversation (for example using @appname), it remained active for the rest of that conversation. There was no need to invoke it again for every subsequent message.

Now, on both:

• ChatGPT in the browser (desktop)
• ChatGPT Desktop app

the app seems to lose context after every prompt. Unless the app is explicitly invoked again on each message, ChatGPT falls back to either:

• a regular web search, or
• its base model knowledge/training.

This significantly degrades the user experience, especially for apps designed to support a continuous conversation.

Interestingly, this behavior does not seem to occur on the mobile app, where the app appears to remain active across the conversation as before.

Expected behavior

• Invoke the app once in a conversation.
• All subsequent messages continue using that app until the user explicitly switches away.

Current behavior (Desktop)

• The app must be invoked before every single prompt.
• Otherwise ChatGPT ignores the app and responds using web search or its default knowledge.

Is anyone else seeing the same behavior? Is this an intentional change or a regression?

Thanks!

We have a similar report from a month ago.
From your perspective, is this the same issue?

Wanted to check if anyone else is seeing this. Expected behavior: When a user mentions the name of the app in their prompt, ChatGPT should recognize the app, pick the right tool, and invoke it automatically, without the user needing to select the app from the picker first. This used to work reliably for us. What we’re seeing now: ChatGPT does recognize the app, the chat trace shows “Looked for available tools” and “Thought for Ns”, but no tool actually fires. Instead, the model responds in pla…

Thanks for the pointer! I don’t think it’s the same issue.

In our case, the app is invoked correctly on the first message and tool calls work as expected. The issue is that the app is no longer kept active for subsequent messages on Desktop, so we have to invoke it again before every prompt.

I believe the issue you’re referring to is more likely the one discussed here:

Thanks for the update! Based on our initial testing, things look much better. The broken behavior still seems to occur occasionally, but very rarely and we haven’t been able to identify a reproduction pattern yet. Thanks for the fix — if we manage to spot anything that could explain why it still happens from time to time, we’ll report back here. Encouraging progress nonetheless!

As far as I know, that regression has already been fixed. Our issue seems to be a different regression related to app persistence within a conversation.

To help investigate the issue I reported earlier, here is a conversation ID that consistently reproduces the problem:

Conversation ID: 6a423a10-9b20-83eb-8600-6e03bb2ae9e3

What happens:

1. First prompt
   • The GPT App is explicitly invoked.
   • The app’s tools are correctly called.
   • The response is based on the tool results, as expected.
2. Second prompt
   • Previously, ChatGPT would keep using the same app, call its tools again if needed, refine the search, and provide updated results.
   • Now, no tool lookup or tool invocation happens at all.
   • Instead, ChatGPT answers using its own knowledge (or web search), as if the app was no longer active.

This behavior is reproducible on both the desktop web interface and the ChatGPT Desktop app, but it does not appear to happen on the mobile app.

I hope this conversation ID helps identify where the regression occurred.