SpendBudgetPolicyProtocol
Defined in the protocols module.AI Agent Protocol for gateway cumulative-spend admission decisions. Pure, import-free decision contract symmetric with :class:
RateLimitPolicyProtocol. The wrapper supplies typed facts — the
caller identity, the scope (channel / tenant token), the amount
already spent_usd for that identity+scope in the current window, the
current now timestamp, and (optionally) the pending_usd estimated
cost of the turn being admitted and the oldest_spend_ts of the spend in
the window — and the policy decides whether the turn is allowed or
rejected/throttled with a retry_after_seconds hint. Storage of the
spend ledger lives in a
:class:~praisonaiagents.telemetry.protocols.TokenUsageSinkProtocol; this
contract keeps only the decision injectable and provable in isolation.
A config-driven default (:class:WindowedSpendBudgetPolicy) is provided
for the common “cap $X per identity per rolling window” case.
Methods
check()
Return a :class:
RateLimitDecision for the supplied facts.Source
View on GitHub
praisonaiagents/gateway/protocols.py at line 4336