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/commands/ollama-chat.ts

@@ -16,10 +16,12 @@ export class OllamaChat extends ChatCommand {
     description = Environment.commandDescriptions.ollamaChat;
 
     async execute(msg: Message, match?: RegExpExecArray): Promise<void> {
-        return this.executeOllama(msg, match?.[3] || "", match?.[1]?.toLowerCase()?.startsWith("think"));
-    }
-
-    async executeOllama(msg: Message, text: string, think: boolean = false): Promise<void> {
-        await runUnifiedAi({provider: AiProvider.OLLAMA, msg, text, stream: true, think: think});
+        await runUnifiedAi({
+            provider: AiProvider.OLLAMA,
+            msg: msg,
+            text: match?.[3] ?? "",
+            stream: true,
+            think: match?.[1]?.toLowerCase()?.startsWith("think")
+        });
     }
 }