OpenAI server_is_overloaded stream errors are not retried

[johnwaldo]

Description

OpenAI-compatible streams can fail with a transient overload event instead of normal text:

{"type":"error","error":{"type":"service_unavailable_error","code":"server_is_overloaded","message":"Our servers are currently overloaded. Please try again later."}}

When that shape is surfaced as a stream error, it should enter the existing session retry flow instead of stopping the turn as a final error.

Plugins

None required to reproduce the underlying provider error shape.

OpenCode version

1.14.33

Steps to reproduce

1. Use an OpenAI-compatible model during a provider overload window.
2. The provider returns the stream error above.
3. The session stops instead of showing the existing retry countdown/status.

Screenshot and/or share link

N/A

Operating System

macOS

Terminal

Any

[github-actions]

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

• This issue appears to have been generated by an AI tool (aidevops.sh, as noted in the footer). AI-generated walls of text are not acceptable — please rewrite this in your own words, describing the actual problem you experienced and why you need this feature.
• Feature requests must start with [FEATURE]: in the title.

Please edit this issue to address the above within 2 hours, or it will be automatically closed.

---

This issue might be a duplicate of existing issues. Please check:

• Codex server_is_overloaded stream errors are not retried #25730: Codex server_is_overloaded stream errors are not retried
• 502 provider_unavailable errors from OpenRouter are not retried, causing subagent/session aborts #22448: 502 provider_unavailable errors from OpenRouter are not retried, causing subagent/session aborts
• Anthropic overloaded_error is not retried, halts session #20384: Anthropic overloaded_error is not retried, halts session
• Session retry loops forever — no max attempt cap or configurable limit #25733: Session retry loops forever — no max attempt cap or configurable limit

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

Thanks for updating the issue! It now meets the contributing guidelines and includes all the necessary information. We appreciate you taking the time to provide a clear description, reproduction steps, and system details.

[github-actions]

test

[johnwaldo]

Thanks for the automated guidance. I updated the issue and PR to match the repo templates and removed the generated footer/long-form wording.

I also checked the related work and saw #25728 covers the same server_is_overloaded stream shape from the Codex side. I pushed one small adjustment here so this branch also routes the stream error through parseStreamError, not just the later retry classifier.

If maintainers prefer #25728, I can close this PR as a duplicate. Otherwise this one is now the same narrow bug fix from the OpenAI-compatible stream angle.

[samiralibabic]

Please prioritise.