--- url: >- https://adk.nht.io/api/@nhtio/adk/dispatch_runner/interfaces/GenerationStatsEvent.md description: >- Payload fired on the observability `generationStats` hook for every record emitted via [`DispatchExecutorHelpers.reportGenerationStats`](https://adk.nht.io/api/@nhtio/adk/dispatch_runner/interfaces/DispatchExecutorHelpers#reportgenerationstats). --- # Interface: GenerationStatsEvent Defined in: [lib/types/dispatch\_runner.ts:285](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L285) Payload fired on the observability `generationStats` hook for every record emitted via [DispatchExecutorHelpers.reportGenerationStats](DispatchExecutorHelpers.md#reportgenerationstats). ## Remarks The runner enriches the executor-supplied [GenerationStats](GenerationStats.md) with the active `dispatchId` and 0-based `iteration` index (and an `emittedAt` timestamp) so subscribers can correlate stats across multiple in-flight dispatches without threading extra context — exactly as [LogEvent](LogEvent.md) does for the `log` channel. ## Extends * [`GenerationStats`](GenerationStats.md) ## Properties | Property | Type | Description | Inherited from | Defined in | | ------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------- | | `completionTokens?` | `number` | Tokens in the completion / output (OpenAI `usage.completion_tokens`, Ollama `eval_count`). | [`GenerationStats`](GenerationStats.md).[`completionTokens`](GenerationStats.md#property-completiontokens) | [lib/types/dispatch\_runner.ts:254](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L254) | | `dispatchId` | `string` | Stable identifier for the dispatch that produced the event. | - | [lib/types/dispatch\_runner.ts:287](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L287) | | `emittedAt` | `DateTime` | When the event was emitted. | - | [lib/types/dispatch\_runner.ts:291](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L291) | | `evalDurationNs?` | `number` | Time spent generating the response in nanoseconds (Ollama `eval_duration`). | [`GenerationStats`](GenerationStats.md).[`evalDurationNs`](GenerationStats.md#property-evaldurationns) | [lib/types/dispatch\_runner.ts:264](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L264) | | `finishReason?` | `string` | Why generation stopped (Ollama `done_reason`, OpenAI `finish_reason`). | [`GenerationStats`](GenerationStats.md).[`finishReason`](GenerationStats.md#property-finishreason) | [lib/types/dispatch\_runner.ts:266](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L266) | | `iteration` | `number` | 0-based iteration index within the dispatch. | - | [lib/types/dispatch\_runner.ts:289](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L289) | | `loadDurationNs?` | `number` | Time spent loading the model in nanoseconds (Ollama `load_duration`). | [`GenerationStats`](GenerationStats.md).[`loadDurationNs`](GenerationStats.md#property-loaddurationns) | [lib/types/dispatch\_runner.ts:260](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L260) | | `model?` | `string` | Model identifier the provider echoed back. | [`GenerationStats`](GenerationStats.md).[`model`](GenerationStats.md#property-model) | [lib/types/dispatch\_runner.ts:268](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L268) | | `promptEvalDurationNs?` | `number` | Time spent evaluating the prompt in nanoseconds (Ollama `prompt_eval_duration`). | [`GenerationStats`](GenerationStats.md).[`promptEvalDurationNs`](GenerationStats.md#property-promptevaldurationns) | [lib/types/dispatch\_runner.ts:262](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L262) | | `promptTokens?` | `number` | Tokens in the prompt / input (OpenAI `usage.prompt_tokens`, Ollama `prompt_eval_count`). | [`GenerationStats`](GenerationStats.md).[`promptTokens`](GenerationStats.md#property-prompttokens) | [lib/types/dispatch\_runner.ts:252](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L252) | | `provider?` | `string` | Stable provider discriminator (e.g. `'ollama'`, `'openai_chat_completions'`). | [`GenerationStats`](GenerationStats.md).[`provider`](GenerationStats.md#property-provider) | [lib/types/dispatch\_runner.ts:270](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L270) | | `raw?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `unknown`> | Full provider-native stats object, verbatim, for forward-compatibility. | [`GenerationStats`](GenerationStats.md).[`raw`](GenerationStats.md#property-raw) | [lib/types/dispatch\_runner.ts:272](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L272) | | `totalDurationNs?` | `number` | Total wall-clock generation time in nanoseconds (Ollama `total_duration`). | [`GenerationStats`](GenerationStats.md).[`totalDurationNs`](GenerationStats.md#property-totaldurationns) | [lib/types/dispatch\_runner.ts:258](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L258) | | `totalTokens?` | `number` | Total tokens, when the provider reports a combined figure. | [`GenerationStats`](GenerationStats.md).[`totalTokens`](GenerationStats.md#property-totaltokens) | [lib/types/dispatch\_runner.ts:256](https://github.com/NHTIO/ADK/blob/v1.20260609.0/src/lib/types/dispatch_runner.ts#L256) |