pause queue sends on exhaustion#21634
Conversation
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Codex <noreply@openai.com>
|
All contributors have signed the CLA ✍️ ✅ |
|
I have read the CLA Document and I hereby sign the CLA |
|
recheck |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: accab93797
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| usage_limit_reached = ts.usage_limit_reached(); | ||
| } | ||
| if !pending_input.is_empty() { | ||
| if !usage_limit_reached && !pending_input.is_empty() { |
There was a problem hiding this comment.
This branch drops any pending_input that was accepted during the active turn once a usage limit is reached: take_pending_input() already drained it, and the new guard skips recording or re-queuing it. Clients that do not keep a duplicate TUI queue lose the user's steer/follow-up instead of pausing it for a later decision.
Useful? React with 👍 / 👎.
Keep the usage-limit safety behavior while removing the queued-input review and management flow added on top of it. Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Codex <noreply@openai.com>
1 participant
after a user hits exhaustion of their available usage, rather than immediately sending messages which will all hit that same limit, pause and give the user time to decide what to do.