Commit Graph

3 Commits

Author SHA1 Message Date
iomgaa d8e8fd8124 refactor: route TPM reservation and settlement through the derived value
Five call sites (QuotaGate entry, RetryMW/EmbeddingClient success and
transient-failure settlement) now read effective_est_tokens() instead of
est_tokens. Success paths gain an unavailable branch that keeps delta at
zero once usage frames may be missing; it has no producer yet, so
behaviour is unchanged while the tpm>0 => est_tokens>0 gate still holds.
2026-07-30 10:15:52 -04:00
iomgaa 0e22fcf433 feat: add dual-condition stall detection and quiet accounting degradation 2026-07-21 00:43:39 -04:00
iomgaa c3d5079d39 feat: add retry middleware with per-attempt governance orchestration 2026-07-20 07:05:42 -04:00