Replay: fail fast on a dead AI account; extraction reports to ai_health

First replay (290 calls, 09-22 10:00-12:00 ET) produced 0 incidents and
no errors: every gpt-4o-mini extraction failed and _sync_extract
swallowed it as "no scenes". Same shape as #169 — and the live extraction
tier in /health/ai had no reporter at all, so this has been invisible in
production too.

- intelligence: API failures propagate out of _sync_extract; extract_scenes
  reports them to ai_health ("extraction" tier, billing/dead-model
  classified) and still returns [] so the pipeline degrades as before.
- ai_health: inside a replay sandbox, failures go to the run's own sink
  instead of being dropped.
- replay: aborts after 5 permanent failures on a tier, naming the cause;
  run metrics carry ai_failures; UI shows them.
- replay estimate: audio minutes from started_at/ended_at (no duration
  field exists on call docs).
- ReplayTab exposes the loaded run on window.__drbReplay for in-page
  analysis.

c2-core: 458 pass.

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

drb-frontend/lib/types.ts

@@ -339,6 +339,7 @@ export interface ReplayMetrics {
   corr_consensus: Record<string, number>;
   llm_decisions: number;
   est_cost_usd: number;
+  ai_failures?: Record<string, number>;
 }
 
 export interface ReplayRun {