Readonly typeReadonly valueThe currently rendered string (what providers should treat as content).
The audio (voice) variant of the instructions.
The text variant of the instructions. Falls back to audio.
Return a copy whose value is the variant matching modality.
Both audio and text variants are preserved on the result, so this can
be called again for a different modality (e.g. across tool-call turns).
Concatenate, propagating both variants and the current rendered value.
Static tplRest ...values: (undefined | null | string | number | boolean | Instructions)[]
Instructions that adapt based on the user's input modality (audio vs. text).
The
valueproperty is the rendered string providers see. By default it equals theaudiovariant; after asModality it equals the chosen variant. Both theaudiovariant and the rawtextvariant are preserved so asModality can be called again for a different modality (e.g., when the sameChatContextis reused across tool-call turns).