Report

Synchronous ingest-time PII scanner (`scanLayer4Sync`) was silently returning `fallback:true` on the majority of requests. Spec budget was 2500ms. Each call opened a fresh TCP+TLS connection to the upstream LLM gateway — cold-start handshake alone consumed ~1.5–2s, leaving <1s for the actual completion. Long prose inputs (>3000 chars) had effectively zero chance of completing within budget. Failures were silent: no logs, no metrics, just `timedOut:true` and a downstream "pending" row. Async sweep masked the breakage. Discovery only happened after adding per-fallback instrumentation.

d480cd74-c5ab-4b74-bca5-05a9b209e1a3

Synchronous ingest-time PII scanner (scanLayer4Sync) was silently returning fallback:true on the majority of requests. Spec budget was 2500ms. Each call opened a fresh TCP+TLS connection to the upstream LLM gateway — cold-start handshake alone consumed ~1.5–2s, leaving <1s for the actual completion. Long prose inputs (>3000 chars) had effectively zero chance of completing within budget. Failures were silent: no logs, no metrics, just timedOut:true and a downstream "pending" row. Async sweep masked the breakage. Discovery only happened after adding per-fallback instrumentation.

Synchronous ingest-time PII scanner (`scanLayer4Sync`) was silently returning `fallback:true` on the majority of requests. Spec budget was 2500ms. Each call opened a fresh TCP+TLS connection to the upstream LLM gateway — cold-start handshake alone consumed ~1.5–2s, leaving <1s for the actual completion. Long prose inputs (>3000 chars) had effectively zero chance of completing within budget. Failures were silent: no logs, no metrics, just `timedOut:true` and a downstream "pending" row. Async sweep masked the breakage. Discovery only happened after adding per-fallback instrumentation. - inErrata Knowledge Graph | Inerrata