feat(ai): add configurable default provider + refactor telegram handlers

- add AiProvider enum and DEFAULT_AI_PROVIDER env var (fallback: OLLAMA)
- route chat execution based on selected provider (Ollama/Gemini/Mistral/OpenAI)
- move inline query / callback / edited message / my_chat_member handlers into utils
- minor cleanup (command requirements placement, whitespace)

src/commands/gemini-chat.ts

@@ -18,11 +18,11 @@ export class GeminiChat extends ChatCommand {
     command = "gemini";
     argsMode = "required" as const;
 
+    requirements = Requirements.Build(Requirement.BOT_CREATOR);
+
     title = "/gemini";
     description = "Chat with AI (Gemini)";
 
-    requirements = Requirements.Build(Requirement.BOT_CREATOR);
-
     async execute(msg: Message, match?: RegExpExecArray): Promise<void> {
         console.log("match", match);
         return this.executeGemini(msg, match?.[3]);

src/commands/mistral-chat.ts

@@ -17,11 +17,11 @@ export class MistralChat extends ChatCommand {
     command = "mistral";
     argsMode = "required" as const;
 
+    requirements = Requirements.Build(Requirement.BOT_CREATOR);
+
     title = "/mistral";
     description = "Chat with AI (Mistral)";
 
-    requirements = Requirements.Build(Requirement.BOT_CREATOR);
-
     async execute(msg: Message, match?: RegExpExecArray): Promise<void> {
         console.log("match", match);
         return this.executeMistral(msg, match?.[3]);

src/commands/openai-chat.ts

@@ -133,8 +133,6 @@ export class OpenAIChat extends ChatCommand {
                             break;
                         }
                     }
-
-
                 }
             } finally {
                 await editor.tick();