drop restored upstream comments

They're upstream opencode comments, not kilo changes, so they
shouldn't live inside kilocode_change markers — and outside the
markers they add noise to this PR's diff. Drop them.

packages/opencode/src/provider/transform.ts

@@ -987,9 +987,6 @@ export function options(input: {
   if (input.model.api.id.includes("gpt-5") && !input.model.api.id.includes("gpt-5-chat")) {
     if (!input.model.api.id.includes("gpt-5-pro")) {
       result["reasoningEffort"] = "medium"
-      // Only inject reasoningSummary for providers that support it natively.
-      // @ai-sdk/openai-compatible proxies (e.g. LiteLLM) do not understand this
-      // parameter and return "Unknown parameter: 'reasoningSummary'".
       if (
         input.model.api.npm === "@ai-sdk/openai" ||
         input.model.api.npm === "@ai-sdk/azure" ||
@@ -1001,8 +998,6 @@ export function options(input: {
       }
     }
 
-    // Only set textVerbosity for non-chat gpt-5.x models
-    // Chat models (e.g. gpt-5.2-chat-latest) only support "medium" verbosity
     if (
       // kilocode_change start - gate textVerbosity to Responses-API providers
       (input.model.api.npm === "@ai-sdk/openai" ||