Interface: ToolDurability<TInput, TOutput>
Defined in: packages/core/src/utils/tools.ts:98
What a tool declares about how a durable run treats its calls: whether one
may run again after a crash, how long one may run, and whether it runs a
child loop. Usually nothing: resolveToolReplay() reads requiresApproval
and MCP annotations too, and an undeclared tool is unsafe, so a durable
run suspends instead of repeating its effect.
Every member is a plain enumerable property, so a host that wraps a tool as
{ ...tool, execute } keeps what it declared.
Extended by
Type Parameters
TInput
TInput = unknown
TOutput
TOutput = unknown
Properties
childRun?
optionalchildRun?:boolean
Defined in: packages/core/src/utils/tools.ts:119
The tool runs a child loop (a subagent) inside its call. Its own loop has
its own limits, so the call gets no tool limit unless it declares
timeoutMs, and the parent's loop needs the place's childRecovery.
A Processable tool runs one without declaring it. See declareChildRun().
reconcile?
optionalreconcile?: (toolCallId,input) =>Promise<EffectReconciliation<TOutput>>
Defined in: packages/core/src/utils/tools.ts:102
What an interrupted call did, looked up by its toolCallId.
Parameters
toolCallId
string
input
TInput
Returns
Promise<EffectReconciliation<TOutput>>
replay?
optionalreplay?:ToolReplay
Defined in: packages/core/src/utils/tools.ts:100
'safe': may run again with the same toolCallId. 'unsafe': never runs again without reconciling.
timeoutMs?
optionaltimeoutMs?:number|false
Defined in: packages/core/src/utils/tools.ts:112
This tool's limit per call in a checkpointed durable loop, in milliseconds
from the call's start (AI SDK timeout.tools): past it the call's
abortSignal aborts and the call ends as a tool error. false: no limit.
Unset: the run's RunPolicy.toolTimeoutMs, else its stepIdleTimeoutMs.
Wins over childRun, so a host can bound a child loop too.
version?
optionalversion?:string
Defined in: packages/core/src/utils/tools.ts:104
Semantic version. Required only for strict durability.