Merge branch 'fix/g07' into fix/integrated

# Conflicts:
#	internal/ipc/api.go
#	internal/ipc/client.go
#	internal/llm/client.go

cmd/mavend/modelswap.go

@@ -58,6 +58,7 @@ func wireModelSwap(srv *ipc.Server, phr phraser.Phraser, cfg *config.Config) {
 			ModelPath:  res.ModelPath,
 			BaseURL:    res.BaseURL,
 			RolledBack: res.RolledBack,
+			NoBackend:  res.NoBackend,
 			TookMs:     res.Took.Milliseconds(),
 		}
 		if err != nil {
@@ -106,9 +107,15 @@ func wireModelSwap(srv *ipc.Server, phr phraser.Phraser, cfg *config.Config) {
 // the port of a server that no longer exists, and the daemon would degrade to
 // the classifier permanently after the first swap. The client is re-pointed, not
 // rebuilt, so nothing that holds it has to know a swap happened.
+// SetSwapGate is the other half, and on the deploy shape it is the load-bearing
+// one:
+// llama-server is relaunched on the same fixed port, so SetBaseURL is usually a
+// no-op, while the gate is what makes the swap's drain count these callers at
+// all. Without it a swap can kill the server mid-routing-decision.
 func llmClientFor(lp *phraser.LLMPhraser, timeout time.Duration) *llm.Client {
 	c := llm.New(lp.BaseURL(), timeout)
 	c.SetGate(residentGate, false)
+	c.SetSwapGate(lp)
 	lp.OnSwap(func(base string) { c.SetBaseURL(base) })
 	return c
 }
@@ -136,6 +143,7 @@ var residentGate = llm.NewGate(backgroundQuiet)
 func llmBackgroundClientFor(lp *phraser.LLMPhraser, timeout time.Duration) *llm.Client {
 	c := llm.New(lp.BaseURL(), timeout)
 	c.SetGate(residentGate, true)
+	c.SetSwapGate(lp)
 	lp.OnSwap(func(base string) { c.SetBaseURL(base) })
 	return c
 }