assistant: pick the chat's model, local or cloud, from the header

The canvas keeps the chat's model from the daemon (hello.chat_model,
conversation.model), falls back to the preferred one (set from shell.qml
later), and sends it as model with every ask, typed or spoken. The To .md
write stays without one: the daemon always writes with the local model.

Models.qml lists the daemon's models event, router models then cloud
ones, in a panel like History. It opens from the header label in chat,
from a Model button next to History outside chat, and with Ctrl+M. The
models are asked for on hello too, so the cloud marker is right before
the panel was ever opened. Moving a chat with turns to a cloud model
says once that its history goes to that provider.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

1 files changed, 42 insertions, 4 deletions

diff --git a/desktop/assistant/Assistant.qml b/desktop/assistant/Assistant.qml
index 2641a5e..0b7026d 100644
--- a/desktop/assistant/Assistant.qml
+++ b/desktop/assistant/Assistant.qml
@@ -66,6 +66,18 @@ Scope {
     // The preferred model being loaded on open, shown in the header until
     // the router reports it loaded. Set from shell.qml.
     property string swapping: ""
+    // The model this chat is asked with: its stored pick (hello.chat_model,
+    // conversation.model), "" for none, then the preferred one (set from
+    // shell.qml). "" for both: the daemon uses whatever the router has
+    // loaded. Spec: desktop-assistant,
+    // docs/superpowers/specs/2026-10-23-cloud-models-design.md.
+    property string chatModel: ""
+    property string preferred: ""
+    readonly property string wanted: root.chatModel || root.preferred
+    // The daemon's models event: [{id, status, cloud: false} | {id, provider, cloud: true}].
+    property var models: []
+    readonly property bool cloud: root.models.some(m => m.cloud && m.id === root.wanted)
+    property bool modelsOpen: false
     property int ctxUsed: 0
     property int ctxMax: 0
     property var convId: null
@@ -113,11 +125,12 @@ Scope {
 
     function close() {
         root.endRecording(false);
-        root.open = false; root.historyOpen = false; root.pickerOpen = false;
+        root.open = false; root.historyOpen = false; root.pickerOpen = false; root.modelsOpen = false;
     }
     // Escape: a recording, the picker, then the history panel, then the card.
     function back() {
         if (root.recording) root.endRecording(false);
+        else if (root.modelsOpen) root.modelsOpen = false;
         else if (root.pickerOpen) root.pickerOpen = false;
         else if (root.historyOpen) root.historyOpen = false;
         else root.close();
@@ -258,8 +271,8 @@ Scope {
                     root.notice = "recording failed";
                 } else if (rec.send && root.connected) {
                     root.chatting = true;
-                    root.send({ type: "ask", text: "", audio: root.micPath,
-                                files: root.staged.map(f => f.path) });
+                    root.send(root.withModel({ type: "ask", text: "", audio: root.micPath,
+                                               files: root.staged.map(f => f.path) }));
                 }
                 rec.destroy();
             }
@@ -325,16 +338,37 @@ Scope {
             || (text.trim() === "" && !root.staged.length)) return false;
         root.notice = "";
         root.chatting = true;
-        root.send({ type: "ask", text: text, files: root.staged.map(f => f.path) });
+        root.send(root.withModel({ type: "ask", text: text, files: root.staged.map(f => f.path) }));
         return true;
     }
 
     function showHistory() {
         root.pickerOpen = false;
+        root.modelsOpen = false;
         root.historyOpen = true;
         root.send({ type: "list" });
     }
 
+    function showModels() {
+        root.historyOpen = root.pickerOpen = false;
+        root.modelsOpen = true;
+        root.send({ type: "models" });
+    }
+    // Applies from the next ask; the daemon stores it with the chat then.
+    // Moving a chat with turns to the cloud sends its history there, so
+    // that is said once, on the switch.
+    function pickModel(id) {
+        const m = root.models.find(x => x.id === id);
+        if (m && m.cloud && !root.cloud && turns.count)
+            root.notice = `History in this chat goes to ${m.provider}.`;
+        root.chatModel = id;
+        root.modelsOpen = false;
+    }
+    function withModel(cmd) {
+        if (root.wanted) cmd.model = root.wanted;
+        return cmd;
+    }
+
     function row(t, live) {
         return { user: t.user ?? "", reply: t.reply ?? "", think: t.think ?? "",
                  tools: (t.tools ?? []).join(","), error: "", live: live,
@@ -371,15 +405,18 @@ Scope {
             root.state = e.state;
             root.runningTool = e.state === "tool" ? e.tool : "";
             root.model = e.model ?? "";
+            root.chatModel = e.chat_model ?? "";
             root.ctxUsed = e.ctx_used;
             root.ctxMax = e.ctx_max;
             root.load(e.id, e.turns, e.pending);
             // A restart or reload counts as active: the conversation it
             // reconnects to is not stale just because this process is new.
             if (e.pending || e.turns.length) root.lastActive = Date.now();
+            root.send({ type: "models" });
             break;
         case "conversation":
             root.load(e.id, e.turns, null);
+            root.chatModel = e.model ?? "";
             // Opened from History on purpose: it counts as active now.
             if (e.turns.length) root.lastActive = Date.now();
             // Emptied (New, or the current one deleted) with nothing staged:
@@ -445,6 +482,7 @@ Scope {
         case "ctx": root.ctxUsed = e.used; root.ctxMax = e.max; if (e.model) root.model = e.model; break;
         case "conversations": root.convs = e.items; break;
         case "results": root.results = e.items; break;
+        case "models": root.models = e.items; break;
         }
     }