You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on May 24, 2026. It is now read-only.
Context
SDK v0.2.2 added
ModelCapabilitiesOverridetoModelApi.SwitchToAsync(). Currently we passnull(PR #641).Opportunity
When switching to a vision-capable model (e.g., GPT-4o, Claude with vision), we could pass
ModelCapabilitiesOverridewith:Limits.Vision.SupportedMediaTypes— MIME types the model acceptsLimits.Vision.MaxPromptImages— image count limitLimits.Vision.MaxPromptImageSize— size limit per imageLimits.MaxContextWindowTokens— context window for the specific modelThis would enable the CLI to enforce proper image limits and token budgets per model rather than using server defaults.
Current State
Priority
Low — only relevant if custom model limits are needed. Server defaults work fine for now.