Skip to content
Kuralle

AgentConfig

Properties

Section titled “Properties”

agents?

Section titled “agents?”
optional agents?: AgentConfig[];

controlModel?

Section titled “controlModel?”
optional controlModel?: LanguageModel;

Optional model for the control path (routing, decide, extraction), run at temperature 0 for determinism. Defaults to model (the speaker) when unset. Set this to pin control to a reliable provider independent of the speaker.

description?

Section titled “description?”
optional description?: string;

experimental?

Section titled “experimental?”
optional experimental?: object;
Name Type Description

outOfBandControl?

boolean

Flow reply nodes: silo flow-transition control tools + deterministic evaluator (ADR 0003 H1). Default OFF.

flows?

Section titled “flows?”
optional flows?: Flow[];

globalTools?

Section titled “globalTools?”
optional globalTools?: Record<string, AnyTool>;

Safe, always-available tools made model-visible in EVERY speaking node turn (the agent “base layer”, ADR 0001) — e.g. a returns/FAQ knowledge-base lookup the user might ask for mid-flow. This is an explicit allow-list: NEVER put consequential/mutating tools here (they must stay flow-gated), and they are not exposed during non-speaking collect extraction.

guardrails?

Section titled “guardrails?”
optional guardrails?: Guardrails;

handoffs?

Section titled “handoffs?”
optional handoffs?: string[];

id

Section titled “id”
id: string;

instructions?

Section titled “instructions?”
optional instructions?: Instructions;

knowledge?

Section titled “knowledge?”
optional knowledge?: AgentKnowledge;

limits?

Section titled “limits?”
optional limits?: Limits;

memory?

Section titled “memory?”
optional memory?: AgentMemory;

model?

Section titled “model?”
optional model?: LanguageModel;

name?

Section titled “name?”
optional name?: string;

refine?

Section titled “refine?”
optional refine?: RefinementCapability[];

Pre-turn refinement policies. Default: none.

routes?

Section titled “routes?”
optional routes?: Route[];

routing?

Section titled “routing?”
optional routing?: RoutingPolicy;

skills?

Section titled “skills?”
optional skills?: SkillSource;

Bundled procedural skills (Anthropic Agent Skill model): Level-1 name+description in prompt, body via load_skill, resources via read_skill_resource. Scripts = allowedTools only.

tools?

Section titled “tools?”
optional tools?: Record<string, AnyTool>;

Durable, model-callable effect tools (exactly-once on replay). Wrap raw AI SDK tools with wrapAiSdkTool().

validate?

Section titled “validate?”
optional validate?: ValidationCapability[];

Post-turn validation policies (grounding/confidence gate). Default: none.

workspace?

Section titled “workspace?”
optional workspace?: AgentWorkspaceConfig;

Portable workspace filesystem; auto-registers the durable workspace tool when set. Defaults to read-only; pass { fs, readOnly: false } for write/edit. Read-only workspaces are exposed in globalTools (ADR 0001); read-write ones are executor-only.