Warm Session • AI Agent SDK
WarmSession: A warm per-session agent cache eligible for memory-pressure eviction.
WarmSession
Defined in the protocols module.
AI Agent
A warm per-session agent cache eligible for memory-pressure eviction.
A pure, import-free fact carried from the running gateway to :func:plan_pressure_evictions. Attributes:
- `
session_id`: the cache key to soft-evict. - `
last_activity`: monotonic/epoch seconds of the session’s last turn; - the planner evicts the coldest (smallest `
last_activity`) first. - `
in_flight:True` while a turn is executing — never evicted (would - abort live work).
- `
flushed:True` when the transcript is durably persisted — only a - flushed cache is rebuildable, so an unflushed one is never evicted
- (would lose data).
Properties
ResponseField
strNo description available.
ResponseField
floatNo description available.
ResponseField
boolNo description available.
ResponseField
boolNo description available.
Source
View on GitHubpraisonaiagents/gateway/protocols.py at line 4906