Skip to content

Proxy resilience: rate limiting and concurrency controls #67

@chindris-mihai-alexandru

Description

Tasks:

  • Add request queue or per-model concurrency limits in OpenAI proxy.
  • Optional rate limiting to prevent burst overload.

Acceptance:

  • Proxy stays stable under spikes; limits configurable.

Metadata

Metadata

Assignees

No one assigned

    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