AI providers: review follow-ups to 0060ccd

Replay usage key gemini_usage -> llm_usage (backend + ReplayTab), re-price the
correction/correlation estimates for gpt-4o-mini, no temperature for o-series
or gpt-5 models, and refresh comments still naming Gemini.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

drb-frontend/components/admin/ReplayTab.tsx

@@ -361,10 +361,10 @@ function RunDetail({ run }: { run: ReplayRun }) {
           paths: {Object.entries(m.corr_path).map(([k, v]) => `${k} ${v}`).join(" · ")}
         </p>
       )}
-      {m?.gemini_usage && Object.keys(m.gemini_usage).length > 0 && (
+      {m?.llm_usage && Object.keys(m.llm_usage).length > 0 && (
         <p className="text-xs font-mono text-ink-muted">
           Gemini tokens:{" "}
-          {Object.entries(m.gemini_usage)
+          {Object.entries(m.llm_usage)
             .map(([k, u]) => `${k} ${u.calls} calls, in ${u.in.toLocaleString()} / out ${u.out.toLocaleString()} / thinking ${u.thinking.toLocaleString()}`)
             .join(" · ")}
         </p>