Merge branch 'fix/g07' into fix/integrated

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

cmd/mavweb/main.go

@@ -364,6 +364,11 @@ func main() {
 	flag.Parse()
 
 	var core ipc.CoreAPI
+	// swapConn — a second connection, for /models and nothing else. A model swap
+	// is a multi-minute IPC call and ipc.Client serialises everything on one
+	// mutex, so sharing the connection would freeze every other page for the
+	// length of the load. See handleModels.
+	var swapConn modelController
 	if *coreSock != "" {
 		c, err := ipc.DialWait(*coreSock, 60*time.Second)
 		if err != nil {
@@ -371,6 +376,12 @@ func main() {
 		}
 		defer c.Close()
 		core = c
+		if sc, err := ipc.Dial(*coreSock); err != nil {
+			log.Printf("models: second core connection failed (%v) — /models will share the main one and a swap will block the other pages", err)
+		} else {
+			defer sc.Close()
+			swapConn = sc
+		}
 	}
 
 	mux := http.NewServeMux()
@@ -516,13 +527,14 @@ func main() {
 	// /tools, and for a comparable reason: which model is loaded decides how every
 	// utterance is routed and how every reply is worded. GET is read-only.
 	mux.HandleFunc("/models", func(w http.ResponseWriter, r *http.Request) {
-		handleModels(w, r, core, stepUpSession, *requireStepUp)
+		handleModels(w, r, core, swapConn, stepUpSession, *requireStepUp)
 	})
 
 	// State-changing routes on this server, and their gate (Vikunja #317):
 	//
 	//   POST /tools      step-up  — defines argv that internal/tool executes
 	//   POST /routines   step-up  — accepting schedules recurring firing
+	//   POST /models     step-up  — replaces the model that routes and phrases
 	//   POST /api/revert step-up  — voids the latest fact for a key
 	//   POST /api/chat   step-up  — reaches the router, LLM and the act path
 	//   POST /api/ptt    step-up  — audio into runTurn, so the same router,