Selected model is at capacity. Please try a different model.
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.4k
- PR merge metrics
- PR metrics pending
Description
What issue are you seeing?
Package: Pro 20x
Platform: ChatGPT desktop client for macOS, Codex mode
MacOS version: 26.6.2
Application release: 26.901.51231 (from application logs)
Symptom:
Terra, Luna, Sol, and Astra all continue to prompt:
Selected model is at capacity. Please try a different model.
Confirmed:
- Switching models is invalid.
- Creating a new session also failed.
- The usage page shows that there is still about 80% remaining.
- In the main session log, four consecutive task_completes are clearly recorded:
codex_error_info = server_overloaded - The snapshot of the same period limit shows:
plan_type = pro
primary.used_percent = 20.0
rate_limit_reached_type = null
What steps can reproduce the bug?
No steps are required, any task yields the same result
What is the expected behavior?
No response
Additional information
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the main session log entries showing codex_error_info = server_overloaded and compare them with the period-limit snapshot showing 20% usage and no rate-limit type. Determine whether the desktop client has an actionable discrepancy to reproduce; done means identifying a client-side cause or confirming that the failure is external server capacity.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- macos, rust
- Domain
- desktop
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100