mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
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 |
||
|---|---|---|
| .. | ||
| create_dashboard_summary.sql | ||
| create_proxy_telemetry_v2.sql | ||
| upgrade_dashboard_v2.sql | ||
| upgrade_telemetry_cache_bust.sql | ||