feat(agent): route chat through selected model

src/app/api/agent/chat/route.ts

@@ -2,6 +2,7 @@ import { apiError, apiJson } from "@/lib/api-handler";
 import { resolveApiAuth } from "@/lib/api-auth";
 import { getAssistantPreferences, resolveAssistantSystemPrompt } from "@/lib/assistant-preference";
 import { isLlmConfigured } from "@/lib/llm";
+import { listLlmModels, resolveAssistantModel } from "@/lib/llm/models";
 import { clientChatInputSchema } from "@/modules/agent/messages";
 import { encodeSseEvent } from "@/modules/agent/server/progress";
 import { runAgentChat } from "@/modules/agent/server/run";
@@ -31,6 +32,18 @@ export async function POST(request: Request) {
     return apiError(parsed.error.issues[0]?.message ?? "Validation error", 400);
   }
 
+  const modelList = await listLlmModels();
+  const modelResolution = resolveAssistantModel({
+    requestedModel: parsed.data.model,
+    savedModel: assistant.model,
+    fallbackModel: modelList.fallbackModel,
+    models: modelList.models,
+  });
+
+  if (!modelResolution.ok) {
+    return apiError(modelResolution.error, 400);
+  }
+
   if (parsed.data.stream) {
     const stream = new ReadableStream<Uint8Array>({
       async start(controller) {
@@ -44,6 +57,7 @@ export async function POST(request: Request) {
             messages: parsed.data.messages,
             request,
             systemPrompt,
+            model: modelResolution.model,
             onProgress: send,
           });
 
@@ -78,6 +92,7 @@ export async function POST(request: Request) {
       messages: parsed.data.messages,
       request,
       systemPrompt,
+      model: modelResolution.model,
     });
 
     return apiJson({

src/lib/llm/index.ts

@@ -13,8 +13,8 @@ export type {
 export { getLlmConfig, isLlmConfigured } from "./config";
 export { createMockLlmClient } from "./mock";
 
-export function createLlmClient(override?: LlmClient): LlmClient {
-  if (override) return override;
+export function createLlmClient(options?: { model?: string; override?: LlmClient }): LlmClient {
+  if (options?.override) return options.override;
 
   const config = getLlmConfig();
   if (config.provider === "mock" || !config.baseUrl) {
@@ -24,6 +24,6 @@ export function createLlmClient(override?: LlmClient): LlmClient {
   return createOpenAiCompatibleClient({
     baseUrl: config.baseUrl,
     apiKey: config.apiKey,
-    model: config.model,
+    model: options?.model ?? config.model,
   });
 }

src/modules/agent/messages.ts

@@ -1,4 +1,5 @@
 import { z } from "zod";
+import { isValidLlmModelId } from "@/lib/llm/models";
 
 export const clientChatAttachmentSchema = z.object({
   type: z.literal("image"),
@@ -11,8 +12,14 @@ export const clientChatMessageSchema = z.object({
   attachments: z.array(clientChatAttachmentSchema).max(3).optional(),
 });
 
+export const clientChatModelSchema = z
+  .string()
+  .trim()
+  .refine((value) => isValidLlmModelId(value), "Invalid assistant model");
+
 export const clientChatInputSchema = z.object({
   stream: z.boolean().optional(),
+  model: clientChatModelSchema.optional(),
   messages: z.array(clientChatMessageSchema).min(1).max(40),
 });
 

src/modules/agent/server/run.ts

@@ -45,11 +45,12 @@ export async function runAgentChat(options: {
   messages: ClientChatMessage[];
   request: Request;
   systemPrompt?: string;
+  model?: string;
   llm?: LlmClient;
   executeTool?: ToolExecutor;
   onProgress?: AgentProgressHandler;
 }): Promise<AgentChatResult> {
-  const llm = options.llm ?? createLlmClient();
+  const llm = options.llm ?? createLlmClient({ model: options.model });
   const executeTool = options.executeTool ?? createApiToolExecutor(options.request);
   const onProgress = options.onProgress;
   const systemPrompt = options.systemPrompt ?? AGENT_SYSTEM_PROMPT;