Skip to content

feat: add server_error, rate_limit, and no_kv_space retry logic to accommodate Foundry API issues #5527

Merged
rekram1-node merged 3 commits intoanomalyco:devfrom
seIIers:feat/azure-foundry-retry
Dec 14, 2025
Merged

feat: add server_error, rate_limit, and no_kv_space retry logic to accommodate Foundry API issues #5527
rekram1-node merged 3 commits intoanomalyco:devfrom
seIIers:feat/azure-foundry-retry

Conversation

@seIIers
Copy link
Copy Markdown
Contributor

@seIIers seIIers commented Dec 14, 2025

Adds more granular error handling to session retry logic:

  • Rate limit errors - returns "Rate Limited"
  • KV cache full errors - returns "KV Cache Full"
  • Server errors - returns "Server Error"

Not sure if this would have side effects for other providers

Closes #5526

@rekram1-node rekram1-node merged commit 92948ed into anomalyco:dev Dec 14, 2025
nalin-singh pushed a commit to nalin-singh/opencode that referenced this pull request Dec 17, 2025
rekram1-node added a commit that referenced this pull request Dec 27, 2025
…commodate Foundry API issues (#5527)

Co-authored-by: Aiden Cline <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

GPT 5.2 on Azure rate_limit_exceeded & no_kv_space issues

2 participants