Adds two orthogonal identity fields to the anonymous telemetry beacon so we
can segment usage by integration surface and deployment shape:
- headroom_stack: how Headroom is invoked (proxy, wrap_claude, wrap_codex,
adapter_ts_openai, adapter_ts_anthropic, etc.). Resolved from HEADROOM_STACK
env, HEADROOM_AGENT_TYPE fallback, or aggregated request-header counts.
- install_mode: how the proxy is deployed (wrapped / persistent / on_demand).
Detected from HEADROOM_AGENT_TYPE plus DeploymentManifest lookup.
TS SDK adapters now tag every request with X-Headroom-Stack; a FastAPI
middleware buckets the counts and surfaces them via /stats so the beacon can
report requests_by_stack for mixed-integration sessions.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
