{loadError}
{/if} {#if settings === null && !loadError}Loading vision settings…
{:else if settings !== null}
Current: {limitLabel}
Max native images per turn before the oldest are transcribed to text.
0 disables compaction. Default is {DEFAULT_IMAGE_LIMIT}.
{imageLimitError}
{:else if imageLimitSaved}Saved.
{/if}Saving…
{/if}The vision-capable model that transcribes old images to text. "Auto" lets the server choose.
{#if compactionError}{compactionError}
{:else if compactionSaved}Saved.
{/if}