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.

tests/unit/agent-messages.test.ts

@@ -0,0 +1,28 @@
+import assert from "node:assert/strict";
+import { describe, it } from "node:test";
+import { clientChatInputSchema } from "../../src/modules/agent/messages";
+
+describe("clientChatInputSchema", () => {
+  it("accepts messages with image attachments", () => {
+    const parsed = clientChatInputSchema.safeParse({
+      stream: true,
+      messages: [
+        {
+          role: "user",
+          content: "Add this appointment to the calendar",
+          attachments: [{ type: "image", url: "/api/uploads/assistant/house-1/photo.jpg" }],
+        },
+      ],
+    });
+
+    assert.equal(parsed.success, true);
+  });
+
+  it("rejects empty message content", () => {
+    const parsed = clientChatInputSchema.safeParse({
+      messages: [{ role: "user", content: "   " }],
+    });
+
+    assert.equal(parsed.success, false);
+  });
+});