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-c2-core/app/internal/replay.py

@@ -58,9 +58,9 @@ PREFETCH = 6
 # Estimates, not a bill — nothing in DRB reads a real invoice (server-26#45).
 USD_WHISPER_PER_MIN    = 0.006
 USD_PER_EXTRACTION     = 0.0005   # gpt-4o-mini scene extraction + embedding
-USD_PER_CORRECTION     = 0.0003   # Gemini flash transcript correction
+USD_PER_CORRECTION     = 0.0004   # gpt-4o-mini transcript correction (~1.5k in / 300 out tokens)
 USD_PER_GEOCODE        = 0.005    # Google geocode, roughly one per located scene
-USD_PER_LLM_CORRELATE  = 0.0005   # one Gemini flash correlation decision (ambiguous scenes only)
+USD_PER_LLM_CORRELATE  = 0.0004   # one gpt-4o-mini correlation decision (~2k in / 100 out; ambiguous scenes only)
 _LLM_CONSENSUS = ("llm", "rules_guard", "agreed", "tiebreak", "llm_orphan_gate")
 
 # Fields the pipeline writes onto a call doc. Stripped when a call is copied
@@ -569,7 +569,7 @@ async def _run(run_id: str, org_id: str, calls: list[dict], mode: str,
         metrics = compute_metrics(incidents, sb_calls)
         metrics["est_cost_usd"] = _running_cost(progress, metrics, mode)
         metrics["ai_failures"] = dict(Counter(f"{f['tier']}: {f['problem']}" for f in ai_failures))
-        metrics["gemini_usage"] = usage
+        metrics["llm_usage"] = usage
     except Exception as e:
         status = "failed"
         errors.append(f"run: {type(e).__name__}: {e}"[:300])