ui : resolve a conversation's backend before sending

Assisted-by: pi:llama.cpp/DeepSeek-V4.1-Flash

tools/ui/src/lib/stores/chat/index.svelte.ts

@@ -809,6 +809,15 @@ class ChatStore implements ChatStreamHost, ChatFlowsHost {
 		modelOverride?: string | null,
 		firstUserMessageContent?: string
 	): Promise<void> {
+		// a conversation keeps the model that generated it, which can belong to
+		// another backend; make that backend active so the request is not sent to
+		// a server that does not serve the model
+		const requestedModel = modelOverride ?? getConversationModel(allMessages);
+
+		if (requestedModel) {
+			await modelsStore.ensureModelBackend(requestedModel);
+		}
+
 		// the ::model suffix in the stream identity is only for router mode, where it routes to the
 		// owning child. in single-model mode the identity stays the bare conv id so that attach, stop
 		// and reattach all agree, regardless of fresh send vs regenerate passing a resolved model

tools/ui/src/lib/stores/models/index.svelte.ts

@@ -222,6 +222,19 @@ class ModelsStore implements ModelPropsHost, ModelStatusHost {
 		await this.selectModelById(availableModels[0].id);
 	}
 
+	/**
+	 * Make the backend serving `modelName` active when it is not already.
+	 * A conversation keeps the model that generated it, which can belong to a
+	 * backend other than the active one.
+	 */
+	async ensureModelBackend(modelName: string): Promise<void> {
+		const option = this.models.find((model) => model.model === modelName);
+
+		if (!option?.backendId || option.backendId === backendsStore.active.id) return;
+
+		await this.selectModelById(option.id);
+	}
+
 	/**
 	 * Fetch list of models from server and detect server role.
 	 * Also fetches modalities for MODEL mode (single model).