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/index.ts

@@ -20,7 +20,7 @@ import {Ping} from "./commands/ping";
 import {RandomString} from "./commands/random-string";
 import {SystemInfo} from "./commands/system-info";
 import {Test} from "./commands/test";
-import {readData, readPrompts, retrieveAnswers} from "./db/database";
+import {readData, retrieveAnswers} from "./db/database";
 import {Uptime} from "./commands/uptime";
 import {WhatBetter} from "./commands/what-better";
 import {When} from "./commands/when";
@@ -183,7 +183,7 @@ export const callbackCommands: CallbackCommand[] = [
     new YtInfo()
 ];
 
-if (Environment.OLLAMA_ADDRESS && Environment.OLLAMA_MODEL && Environment.SYSTEM_PROMPT) {
+if (Environment.OLLAMA_ADDRESS && Environment.OLLAMA_MODEL) {
     commands.push(
         new OllamaChat(),
         new OllamaPrompt(),
@@ -252,10 +252,8 @@ async function shutdown(signal: NodeJS.Signals) {
 async function main() {
     const start = Date.now();
 
-    await readPrompts();
-
     console.log(Environment.SYSTEM_PROMPT);
-    
+
     console.log(
         `TEST_ENVIRONMENT: ${Environment.TEST_ENVIRONMENT}\n` +
         `DATA_PATH: ${Environment.DATA_PATH}\n` +