RunErrorEvent

Defined in: packages/ai/src/types.ts:1396

Emitted when an error occurs during a run.

@ag-ui/core provides: message, code? Spec usage[] is provider/model token counts. Interrupt errors live in metadata.tanstack.interruptErrors.

Extends#

• Pick<AGUIRunErrorEvent, "message" | "code" | "timestamp" | "rawEvent">

Properties#

error?#

optional error?: object;

Defined in: packages/ai/src/types.ts:1409

Nested payload kept for in-process / durability consumers.

code?#

optional code?: string;

message#

message: string;

metadata?#

optional metadata?: object & Record<string, any>;

Defined in: packages/ai/src/types.ts:1416

Type Declaration#

tanstack?#

optional tanstack?: TanStackRunMetadata;

model?#

optional model?: string;

Defined in: packages/ai/src/types.ts:1407

Restored on the client from metadata.tanstack.

retryAfterMs?#

optional retryAfterMs?: number;

Defined in: packages/ai/src/types.ts:1415

How long the provider asks you to wait before a retry, in milliseconds. Adapters read it from the retry-after-ms or retry-after header. chat() moves it to metadata.tanstack.retryAfterMs.

runId?#

optional runId?: string;

Defined in: packages/ai/src/types.ts:1405

Restored on the client from metadata.tanstack.

threadId?#

optional threadId?: string;

Defined in: packages/ai/src/types.ts:1403

Restored on the client from metadata.tanstack.

type#

type: RUN_ERROR;

Defined in: packages/ai/src/types.ts:1400

usage?#

optional usage?: TokenUsage<ProviderUsageDetails> | TokenUsage[];

Defined in: packages/ai/src/types.ts:1401