feat(ai): improve runtime capability reporting and context settings

Add explicit chat capability tracking, expose formatted runtime capabilities
in the info command, and support a max context size option for user AI settings.

Also update Ollama base URL resolution to use OLLAMA_ADDRESS and simplify
provider chat command execution.

src/util/utils.ts

@@ -90,7 +90,8 @@ export function searchChatCommand(
     botUsername: string | undefined = botUser.username
 ): Command | null {
     for (const command of commands) {
-        const match = command.finalRegexp.exec(text);
+        const finalRegexp = command.finalRegexp;
+        const match = finalRegexp.exec(text);
         if (!match) continue;
 
         const mentioned = match[2]?.toLowerCase();
@@ -2089,19 +2090,6 @@ export function photoPathByUniqueId(uniqueId: string): string {
     return path.join(photoDir, uniqueId + ".jpg");
 }
 
-export function getCurrentModel(): string | undefined {
-    switch (Environment.DEFAULT_AI_PROVIDER) {
-        case AiProvider.OLLAMA:
-            return Environment.OLLAMA_CHAT_MODEL;
-        case AiProvider.GEMINI:
-            return Environment.GEMINI_MODEL;
-        case AiProvider.MISTRAL:
-            return Environment.MISTRAL_MODEL;
-        case AiProvider.OPENAI:
-            return Environment.OPENAI_MODEL;
-    }
-}
-
 export async function processMyChatMember(u: ChatMemberUpdated): Promise<void> {
     console.log("my_chat_member", u);
 }