Merge branch 'fix/g06' into fix/integrated

# Conflicts:
#	cmd/mavend/memoryeval.go

cmd/mavend/memoryeval.go

@@ -25,11 +25,14 @@ import (
 //
 // It used to be five minutes, on the grounds that nobody waits for the answer.
 // Nobody waits for the evaluation, but there is ONE resident model behind one
-// llama-server, so a voice turn that arrives mid-evaluation waits behind it:
-// five minutes of evaluation is five minutes of a mute assistant. Sixty seconds
-// is long enough for a Thinking model on this prompt and short enough that the
-// worst collision is one turn answered late rather than a turn abandoned. An
-// evaluation cut off here costs nothing: it is retried at the next interval.
+// llama-server, so a voice turn arriving mid-evaluation waited behind it: five
+// minutes of evaluation was five minutes of a mute assistant.
+//
+// The background client now yields the slot while a turn is in flight, so the
+// collision is handled where it belongs and this is a prompt budget again.
+// Sixty seconds is long enough for a Thinking model here, and an evaluation cut
+// off costs nothing, because it is retried at the next interval. Raise it if
+// observations start truncating.
 const memoryEvalTimeout = 60 * time.Second
 
 // memoryEvalWorker — ticker + evaluator.
@@ -58,7 +61,9 @@ func newMemoryEvalWorker(st *store.Store, phr phraser.Phraser, cfg *config.Confi
 	if interval <= 0 {
 		interval = config.DefaultMemoryEvalInterval
 	}
-	client := llmClientFor(lp, memoryEvalTimeout)
+	// Background: nobody is waiting on an observation, and it must not sit in
+	// front of a voice turn on the single llama-server slot.
+	client := llmBackgroundClientFor(lp, memoryEvalTimeout)
 	ev := memeval.NewEvaluator(st, st, client, memeval.Config{
 		MaxItems:      cfg.MemoryEval.MaxItems,
 		MinConfidence: cfg.MemoryEval.MinConfidence,