feat: add Ollama audio transcription and runtime config reload

- add audio capability reporting for Ollama models
- support Telegram voice messages via ffmpeg conversion and Ollama transcription
- add USE_SYSTEM_PROMPT toggle and runtime reloading of .env/system prompt settings
- support ollama_options.json for custom Ollama request options
- improve Telegram MarkdownV2 escaping and formatting preservation
- add environment setters for AI provider credentials and models
- show audio capability in info/model commands

src/db/database.ts

@@ -2,7 +2,6 @@ import * as fs from "fs";
 import {Environment} from "../common/environment";
 import {logError} from "../util/utils";
 import {Answers} from "../model/answers";
-import path from "node:path";
 
 type DataJsonFile = {
     admins: number[]
@@ -28,19 +27,6 @@ export async function readData(): Promise<void> {
     }
 }
 
-export async function readPrompts(): Promise<void> {
-    try {
-        const prompt = fs.readFileSync(path.join(Environment.DATA_PATH, "system_prompt.txt")).toString().trim();
-        if (prompt.length) {
-            Environment.setSystemPrompt(prompt);
-        }
-    } catch (e) {
-        logError(e);
-    }
-
-    return Promise.resolve();
-}
-
 export async function saveData(): Promise<void> {
     const adminIds: number[] = [];
     Environment.ADMIN_IDS.forEach(id => adminIds.push(id));