feat(agent): add voice input and photo attachments to assistant

Wire mic through Whisper-compatible transcriptions on LLM_BASE_URL.

Photos upload to MinIO and reach the vision model as base64 image_url parts.

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

@@ -1,24 +1,11 @@
-import { z } from "zod";
 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 { clientChatInputSchema } from "@/modules/agent/messages";
 import { encodeSseEvent } from "@/modules/agent/server/progress";
 import { runAgentChat } from "@/modules/agent/server/run";
 
-const chatInput = z.object({
-  stream: z.boolean().optional(),
-  messages: z
-    .array(
-      z.object({
-        role: z.enum(["user", "assistant"]),
-        content: z.string().trim().min(1).max(8000),
-      }),
-    )
-    .min(1)
-    .max(40),
-});
-
 export async function POST(request: Request) {
   const auth = await resolveApiAuth(request);
   if (!auth?.userId) {
@@ -39,7 +26,7 @@ export async function POST(request: Request) {
     return apiError("Invalid JSON body", 400);
   }
 
-  const parsed = chatInput.safeParse(body);
+  const parsed = clientChatInputSchema.safeParse(body);
   if (!parsed.success) {
     return apiError(parsed.error.issues[0]?.message ?? "Validation error", 400);
   }