Store and describe images through a shared media intake (#252)

Vision needs a second model this box does not have, so the shipped half is
the part that works without one: an image arrives, is sniffed, is stored
content-addressed, and is prepared for inference. The describing half is
written and tested against a fake server, and refuses any endpoint that is
not on this box.

internal/media is the intake all three senses share — hearing and speaker
recognition store their audio in the same place under the same retention.
Blobs stay out of the sqlite store; only the derived text becomes a note,
and only when the caller asks. Retention is enforced by an hourly prune
loop rather than by a comment.

The plan's RemoteProvider step is refused: no cloud model, inference stays
on the box, and vision.NewLocal validates that at construction.

internal/ipc/wire.go

@@ -54,6 +54,7 @@ const (
 	MethodIngestMail             Method = "ingest_mail"
 	MethodSwapModel              Method = "swap_model"
 	MethodModelStatus            Method = "model_status"
+	MethodDescribeImage          Method = "describe_image"
 )
 
 // Request — one frame from module to core. Params is the JSON-encoded argument