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/commands/info.ts

@@ -36,7 +36,8 @@ export class Info extends Command {
             `vision${aiModelCapabilities.vision?.external ? "(ext)" : ""}: ${boolToEmoji(aiModelCapabilities.vision?.supported)}\n` +
             `ocr${aiModelCapabilities.ocr?.external ? "(ext)" : ""}: ${boolToEmoji(aiModelCapabilities.ocr?.supported)}\n` +
             `thinking${aiModelCapabilities.thinking?.external ? "(ext)" : ""}: ${boolToEmoji(aiModelCapabilities.thinking?.supported)}\n` +
-            `tools${aiModelCapabilities.tools?.external ? "(ext)" : ""}: ${boolToEmoji(aiModelCapabilities.tools?.supported)}` +
+            `tools${aiModelCapabilities.tools?.external ? "(ext)" : ""}: ${boolToEmoji(aiModelCapabilities.tools?.supported)}\n` +
+            `audio${aiModelCapabilities.audio?.external ? "(ext)": ""}: ${boolToEmoji(aiModelCapabilities.audio?.supported)}` +
             "```";
 
         const cmds = commands.filter(c => !(c instanceof ChatCommand));