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);
+  });
+});

tests/unit/agent-transcribe.test.ts

@@ -0,0 +1,23 @@
+import assert from "node:assert/strict";
+import { describe, it } from "node:test";
+import { transcribeAudioFile } from "../../src/lib/llm/transcribe";
+
+describe("transcribeAudioFile", () => {
+  it("returns mock text when llm base url is unset", async () => {
+    const original = process.env.LLM_BASE_URL;
+    const originalProvider = process.env.LLM_PROVIDER;
+    delete process.env.LLM_BASE_URL;
+    delete process.env.LLM_PROVIDER;
+
+    const text = await transcribeAudioFile(
+      new Blob(["audio"], { type: "audio/wav" }),
+      "recording.wav",
+    );
+    assert.match(text, /milk/i);
+
+    if (original === undefined) delete process.env.LLM_BASE_URL;
+    else process.env.LLM_BASE_URL = original;
+    if (originalProvider === undefined) delete process.env.LLM_PROVIDER;
+    else process.env.LLM_PROVIDER = originalProvider;
+  });
+});

tests/unit/assistant-chat-storage.test.ts

@@ -4,6 +4,7 @@ import {
   clearAssistantChat,
   loadAssistantChat,
   saveAssistantChat,
+  toClientChatMessage,
 } from "../../src/modules/agent/assistant-chat-storage";
 
 const storage = new Map<string, string>();
@@ -49,4 +50,15 @@ describe("assistant chat storage", () => {
     clearAssistantChat("user-a");
     assert.deepEqual(loadAssistantChat("user-a"), []);
   });
+
+  it("maps stored image messages to client attachments", () => {
+    const message = toClientChatMessage({
+      role: "user",
+      content: "read this",
+      imageUrl: "/api/uploads/assistant/home/photo.jpg",
+    });
+    assert.deepEqual(message.attachments, [
+      { type: "image", url: "/api/uploads/assistant/home/photo.jpg" },
+    ]);
+  });
 });

tests/unit/llm-content.test.ts

@@ -0,0 +1,27 @@
+import assert from "node:assert/strict";
+import { describe, it } from "node:test";
+import { buildVisionContentParts, textFromMessageContent } from "../../src/lib/llm/content";
+
+describe("llm content helpers", () => {
+  it("reads plain string content", () => {
+    assert.equal(textFromMessageContent("hello"), "hello");
+  });
+
+  it("joins text parts from multimodal content", () => {
+    assert.equal(
+      textFromMessageContent([
+        { type: "text", text: "first" },
+        { type: "image_url", image_url: { url: "data:image/png;base64,abc" } },
+        { type: "text", text: "second" },
+      ]),
+      "first\nsecond",
+    );
+  });
+
+  it("builds vision parts with fallback prompt when text is empty", () => {
+    const parts = buildVisionContentParts("", ["data:image/jpeg;base64,abc"]);
+    assert.equal(parts.length, 2);
+    assert.equal(parts[0]?.type, "text");
+    assert.equal(parts[1]?.type, "image_url");
+  });
+});