[Feature]: Resume task when provider fails

[jb825]

1. Why Do You NEED This Feature?

Some provider experiences failures on the server-side, and then forge stop its reflection.
Could you implement a resume "mode" when this failures hit.
(I mostly use Codex subscription)
Many thanks,

2. What Is NOT Possible Right Now?

NA

3. What WILL Be Possible With This Feature?

NA

Proposed Solution (User Experience)

NA

Alternatives Considered

NA

Use Cases

NA

Feature Category

Performance

Priority/Impact

High - Would significantly improve my workflow

Examples from Other Tools

No response

Implementation Ideas

No response

Contribution

• I'm willing to submit a PR to implement this feature
• I can help with testing
• I can help with documentation

Additional Context

No response

✅ Pre-submission Checklist

• I have clearly explained WHY I need this feature (not just that it would be nice)
• I have described what is NOT currently possible in detail
• I have explained what WILL be possible with concrete examples
• I have provided specific use cases and workflows
• I have searched existing issues to avoid duplicates

[tusharmath]

Have you tried :retry?

[bahirul]

Have you tried :retry?

Hi @tusharmath, yes we can do retry but it need manual intervention, i would suggest my PR #2566 to handle SSE error as retryable by default in codex, i look this behavior in bedrock provider so we can implement this in codex. After retryable fails then we can do manual :retry command.

I'm also often hit SSE error when using codex.

[tusharmath]

Fixed in #2566