We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
If requests fail because of invalid OpenAI API keys (e.g #109) we ensure a clear actionable message is surfaced to the user. See also #82
The text was updated successfully, but these errors were encountered:
This doesn't appear to be an issue with HashiCorp's retryable errors swallowing the errors. If the APIKey is invalid OpenAI returns status code status code: 401. https://platform.openai.com/docs/guides/error-codes/api-errors
It looks like HashiCorp's base retry polies retries on StatusTooManyRequests - 429 StatusServiceUnavailable - 500 errors with the exception of NotImplemented https://github.com/hashicorp/go-retryablehttp/blob/86e852df43aa0d94150c4629d74e5116d1ff3348/client.go#L495
One problem is that in the server in Agent we don't log the error if there is one for generate
foyle/app/pkg/agent/agent.go
Line 93 in 3ab5177
Sorry, something went wrong.
Improve logging of OpenAI errors (#117)
9e149f3
* Log Agent.Generate errors so we have clear error messages in the event the OpenAI request fails. Fix #112
Successfully merging a pull request may close this issue.
If requests fail because of invalid OpenAI API keys (e.g #109) we ensure a clear actionable message is surfaced to the user.
See also #82
The text was updated successfully, but these errors were encountered: