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/lib/llm/mock.ts

@@ -1,14 +1,5 @@
 import type { ChatCompletionRequest, ChatCompletionResult, LlmClient } from "./types";
-
-function lastUserText(messages: ChatCompletionRequest["messages"]): string {
-  for (let i = messages.length - 1; i >= 0; i -= 1) {
-    const message = messages[i];
-    if (message?.role === "user" && message.content) {
-      return message.content.toLowerCase();
-    }
-  }
-  return "";
-}
+import { textFromMessageContent } from "./content";
 
 function hadToolResults(messages: ChatCompletionRequest["messages"]): boolean {
   return messages.some((message) => message.role === "tool");
@@ -17,7 +8,9 @@ function hadToolResults(messages: ChatCompletionRequest["messages"]): boolean {
 export function createMockLlmClient(): LlmClient {
   return {
     async chatCompletion(request: ChatCompletionRequest): Promise<ChatCompletionResult> {
-      const userText = lastUserText(request.messages);
+      const userText = textFromMessageContent(
+        [...request.messages].reverse().find((message) => message.role === "user")?.content ?? "",
+      ).toLowerCase();
 
       if (hadToolResults(request.messages)) {
         return {