AxContextPolicyConfig Generated TypeScript API reference. typescript api api/reference build/apidocs/Interface.AxContextPolicyConfig.md interface AxContextPolicyConfig

AxContextPolicyConfig

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/agent/rlm.ts#L448

Public context policy for the Actor loop. Users choose replay style via preset and overall prompt budget via budget.

Properties

PropertyTypeDescription
budget?AxContextPolicyBudgetOverall prompt budget and compression aggressiveness.
preset?AxContextPolicyPresetOpinionated preset for how the agent should replay and compress context. - full: prefer raw replay of earlier actions - adaptive: balance replay detail with checkpoint compression while keeping more recent evidence visible - lean: prefer live state + compact summaries over raw replay detail - checkpointed: keep full replay until the rendered actor prompt grows beyond the selected budget, then replace older successful turns with a checkpoint summary
Docs