Skip to content

AI_RetryError: Failed after 4 attempts. Last error: Too Many Requests #2398

Closed

Description

@andreluisos

I've searched around and this seems to be related to provider. Anyone else? #2018 #2116

Activity

  1. github-actions commented on Sep 3, 2025

    @github-actions
    Contributor

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

    Feel free to ignore if none of these address your specific case.

  2. rekram1-node commented on Sep 3, 2025

    @rekram1-node
    Contributor

    What provider are you using?

  3. andreluisos commented on Sep 3, 2025

    @andreluisos
    Author

    What provider are you using?

    Copilot and claude.

    Nevermind... Only copilot is having the issue. Probaly provider issue.

  4. rekram1-node commented on Sep 3, 2025

    @rekram1-node
    Contributor

    You may be getting rate limited? 2 things:

    • check your copilot dashboard
    • you can try opencode auth logout and log back in again
  5. rekram1-node commented on Sep 3, 2025

    @rekram1-node
    Contributor

    we can also try looking at your logs

  6. thoroc commented on Sep 17, 2025

    @thoroc

    @andreluisos can you confirm this is still happening? I recall seeing something similar, but it was a while ago, and nothing since the (subsequent) latest update.

  7. taqtiqa-mark commented on Dec 2, 2025

    @taqtiqa-mark

    I now (v1.0.126) experience OC (apparently) spamming X.ai to the point where I see the red error message "Too many requests..."

    Trying to divine what is happening from the logs is either neigh impossible... or I'm holding the wrong chicken and standing on the wrong leg - @rekram1-node any hints on where in the logs we can find what is happening?

  8. rekram1-node commented on Dec 2, 2025

    @rekram1-node
    Contributor

    @taqtiqa-mark what kind of logs are you looking for exactly? when you get 429s we continue to retry but with a backoff that respects the retry-after ratelimiting headers

    The retry message you see is taken directly from the response from the server, or it should be

  9. taqtiqa-mark commented on Dec 2, 2025

    @taqtiqa-mark

    @taqtiqa-mark what kind of logs are you looking for exactly?

    Ideally the full transcript of the API (pre-encryption/HTTPS) messages sent/received.
    There is no way my message submissions triggered a rate limit violation, 10-20 messages tops across a couple of new sessions.

    I also have a sneeking suspicion about what happens when OC chokes on the the XML parsing (mentioned in other issues), so it'd be nice to see the logs of that too.

  10. taqtiqa-mark commented on Dec 2, 2025

    @taqtiqa-mark

    @taqtiqa-mark what kind of logs are you looking for exactly?

    @rekram1-node progress is probably blocked by issue #4999 ?

  11. taqtiqa-mark commented on Feb 6, 2026

    @taqtiqa-mark

    In the spirit of calling out excellent engineering and design....

    I've found that the Pi Coding Agent is more robust and, for me has none of the issues that I've encountered in OC, or has an elegant way to resolve them.... I'm dropping out of OC issues:

  12. github-actions commented on Apr 7, 2026

    @github-actions
    Contributor

    To stay organized issues are automatically closed after 90 days of no activity. If the issue is still relevant please open a new one.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions