Merge the seam log line (V-483)

internal/llm/remote.go

@@ -159,21 +159,28 @@ func (p *Pair) set(up bool) {
 // admission answer is a cache and can be one interval out of date, so an error
 // here is expected rather than exceptional.
 //
-// This is the silent half of the degradation rule. It must be indistinguishable
+// This is the silent half of the degradation rule: he is not told which model
-// from today's behaviour when the workstation is down.
+// phrased his reply. The log is told, one line per call, because the seam was
+// otherwise unreadable after the fact — the transition lines say the card was
+// free at 11:27, not which side answered the turn at 13:24. QA had no way to
+// tell an offloaded turn from a floor one.
 func (p *Pair) Complete(ctx context.Context, r Req) (string, error) {
 	if p.floor == nil {
 		return "", ErrNoFloor
 	}
+	why := "workstation down"
 	if p.Available() {
 		out, err := p.remote.Complete(ctx, r)
 		if err == nil {
+			log.Print("llm: served by the workstation model")
 			return out, nil
 		}
 		// The cached answer was wrong. Correct it now rather than sending the
 		// next request into the same hole, then fall back.
 		p.set(false)
+		why = "workstation failed mid-request"
 	}
+	log.Printf("llm: served by the resident model (%s)", why)
 	return p.floor.Complete(ctx, r)
 }
 
@@ -189,5 +196,6 @@ func (p *Pair) CompleteRemote(ctx context.Context, r Req) (string, error) {
 		p.set(false)
 		return "", errors.Join(ErrRemoteUnavailable, err)
 	}
+	log.Print("llm: served by the workstation model, no floor for this caller")
 	return out, nil
 }