Measured baseline: 877ms TTFP cold, 334ms warm, with CPU throttling confirmed (500m limit, 10-12 throttle events per streaming request). Plan covers: CPU limit bump, frontend waterfall elimination, adaptive first batch, deferred decision filtering, POI decoupling, and Server-Timing headers. |
||
|---|---|---|
| .. | ||
| plans | ||
| BACKEND.md | ||