document Redis session cache backend for model affinity

This commit is contained in:
Spherrrical 2026-04-13 16:14:08 -07:00
parent e9e6e1765a
commit 5ae18b4623
2 changed files with 53 additions and 0 deletions

View file

@ -178,6 +178,13 @@ overrides:
routing:
session_ttl_seconds: 600 # How long a pinned session lasts (default: 600s / 10 min)
session_max_entries: 10000 # Max cached sessions before eviction (upper limit: 10000)
# session_cache controls the backend used to store affinity state.
# "memory" (default) is in-process and works for single-instance deployments.
# "redis" shares state across replicas — required for multi-replica / Kubernetes setups.
session_cache:
type: memory # "memory" (default) or "redis"
# url is required when type is "redis". Supports redis:// and rediss:// (TLS).
# url: redis://localhost:6379
# State storage for multi-turn conversation history
state_storage: