List session runs

Per-turn run observability (Gate 5 §5.5, OS-D08 aggregate/redacted-only): for each processed turn — model-call count, cost (credits), total latency, an error flag, the per-turn cache-read token share, a provider-fallback flag, and the public model classes used — so a developer can self-diagnose "why is this turn slow / what did it cost / did it error / did it hit cache / did it fall back" WITHOUT any internal prompt, role, raw model id, or world-model detail. App-scoped.