AxAgentPlaybookConfig

TypeScript

type AxAgentPlaybookConfig = object & Pick<AxPlaybookOptions, 
  | "maxReflectorRounds"
  | "maxSectionSize"
  | "allowDynamicSections"
  | "seed"
| "verbose">;

Defined in: https://github.com/ax-llm/ax/blob/3ac75e381dcefb739712993c304c34295567283a/src/ax/agent/playbookConfig.ts#L53

Type declaration

Name	Type	Description
`apply?`	`boolean`	Render the playbook into the live stage prompt. Default true.
`learn?`	\| `boolean` \| `AxAgentPlaybookLearnOptions`	Run-end failure learning — ON by default (the config block itself is the opt-in). After each completed run that produced failure signals (error turns, repeated dead-ends, tool errors), one bounded playbook update (default: 1 reflector + 1 curator call) curates avoidance rules into the `failures_to_avoid` section. Clean runs cost zero extra calls. Pass an object to tune gating, or `false` for a render-only playbook.
`onUpdate()?`	(`result`: `AxAgentPlaybookUpdateResult`) => `void` \| `Promise`<`void`>	Persistence hook — fires after a run-end update actually ran (`status !== 'skipped'`). Failures in the hook are swallowed; playbook upkeep never breaks the completed user-facing run.
`playbook?`	\| `AxPlaybookSnapshot` \| `AxACEPlaybook`	Seed content: a persisted AxPlaybookSnapshot (from `onUpdate` / `handle.getState()`) or a bare playbook object.
`studentAI?`	`Readonly`<`AxAIService`>	AI running reflection/curation. Defaults to the agent’s `ai`.
`target?`	`"actor"` \| `"responder"`	Stage whose live prompt receives the rendered playbook. Default ‘actor’.
`teacherAI?`	`Readonly`<`AxAIService`>	Stronger model for reflection/curation. Defaults to the agent’s `judgeAI`.