headroom/sql
chopratejas 14d00c6c74 Token-level cache hit rate, compression-vs-cache tracking, dashboard SQL, security plan
Cache stats:
- hit_rate is now token-level (cache_read / total_input) not request-level
- Track uncached_input_tokens per provider in metrics
- Preserve request_hit_rate as secondary metric

Compression-vs-cache:
- Detect when compression busts the prefix cache (expected_cached - actual_read)
- Two simple session-level numbers: tokens_saved vs cache_bust_tokens
- Log CACHE-BUST per request, aggregate in /stats and telemetry beacon
- Single new column in proxy_telemetry_v2: cache_bust_tokens

Dashboard infra:
- SQL for dashboard_summary table + pg_cron hourly refresh
- Hourly + daily aggregation from proxy_telemetry_v2
- Upgrade scripts for adding hourly_stats and cache bust columns
2026-04-06 18:10:29 -07:00
..
create_dashboard_summary.sql Token-level cache hit rate, compression-vs-cache tracking, dashboard SQL, security plan 2026-04-06 18:10:29 -07:00
create_proxy_telemetry_v2.sql Switch telemetry to proxy_telemetry_v2 table, bump to 0.5.12 2026-03-30 10:55:45 -07:00
upgrade_dashboard_v2.sql Token-level cache hit rate, compression-vs-cache tracking, dashboard SQL, security plan 2026-04-06 18:10:29 -07:00
upgrade_telemetry_cache_bust.sql Token-level cache hit rate, compression-vs-cache tracking, dashboard SQL, security plan 2026-04-06 18:10:29 -07:00