--- url: >- https://adk.nht.io/api/@nhtio/adk/batteries/llm/openai_chat_completions/types/interfaces/OpenAIChatCompletionsAdapterOptions.md description: Configuration options for the OpenAI Chat Completions adapter. --- # Interface: OpenAIChatCompletionsAdapterOptions Defined in: [src/batteries/llm/openai\_chat\_completions/types.ts:486](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L486) Configuration options for the OpenAI Chat Completions adapter. ## Properties | Property | Type | Default value | Description | Defined in | | -------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `apiKey?` | `string` | `undefined` | API key for authenticating requests to the OpenAI-compatible service. | [src/batteries/llm/openai\_chat\_completions/types.ts:489](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L489) | | `audio?` | { `format`: `"wav"` | `"mp3"` | `"flac"` | `"opus"` | `"pcm16"`; `voice`: `string`; } | `undefined` | Parameters for audio output if requested. | [src/batteries/llm/openai\_chat\_completions/types.ts:614](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L614) | | `audio.format` | `"wav"` | `"mp3"` | `"flac"` | `"opus"` | `"pcm16"` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:614](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L614) | | `audio.voice` | `string` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:614](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L614) | | `autoAck?` | `boolean` | `false` | Whether the executor should call [ctx.ack()](../../../../../types/interfaces/DispatchContext.md#ack) itself when a generation completes with no tool calls (a terminal text answer). **Remarks** `ack()` is terminal and one-shot: once called, the dispatch loop exits after the current iteration. When the executor acks automatically, it seizes turn-completion control from the implementor — a `dispatchOutputPipeline` quality gate can never run, because the signal is already set before the output pipeline executes. This option therefore defaults to **`false`** (opt-in). With `autoAck: false`, a tool-call-free response leaves the context unsignalled and the executor returns; the implementor's output pipeline (or a later iteration) is responsible for calling `ctx.ack()` / `ctx.nack()`. This is the seam that makes output-side quality gates (citation enforcement, schema validation, regenerate-on-reject) possible. Set `autoAck: true` to restore single-shot behavior: the executor acks the moment a tool-call-free answer finishes, terminating the turn without giving the output pipeline a vote. The tool-call path is unaffected by this flag — it always withholds ack so the runner can iterate and execute the calls. Error paths always [nack](../../../../../types/interfaces/DispatchContext.md#nack) regardless of this flag. | [src/batteries/llm/openai\_chat\_completions/types.ts:608](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L608) | | `baseURL?` | `string` | `undefined` | Base URL for the OpenAI-compatible API endpoint. | [src/batteries/llm/openai\_chat\_completions/types.ts:491](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L491) | | `bucketOrder?` | [`ChatCompletionsBucketOrder`](../../../../type-aliases/ChatCompletionsBucketOrder.md) | `undefined` | Determines order of memory and retrievable buckets in history assembly. | [src/batteries/llm/openai\_chat\_completions/types.ts:505](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L505) | | `contextWindow?` | `number` | `undefined` | Size of the model's token context window. | [src/batteries/llm/openai\_chat\_completions/types.ts:507](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L507) | | `fetch?` | { (`input`: `URL` | `RequestInfo`, `init?`: `RequestInit`): `Promise`<`Response`>; (`input`: `string` | `URL` | `Request`, `init?`: `RequestInit`): `Promise`<`Response`>; } | `undefined` | Custom fetch implementation to use for HTTP requests. | [src/batteries/llm/openai\_chat\_completions/types.ts:503](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L503) | | `forgeToolsFilter?` | (`forged`: [`ToolRegistry`](../../../../../forge/classes/ToolRegistry.md), `ctx`: [`DispatchContext`](../../../../../types/interfaces/DispatchContext.md)) => [`ToolRegistry`](../../../../../forge/classes/ToolRegistry.md) | `undefined` | OPTIONAL hook to SHAPE the artifact-query tools forged from prior-turn SpooledArtifact results, before they merge into the visible tool set. Receives the merged forged registry + dispatch context; returns a (possibly narrowed) registry, applied BEFORE the merge with `ctx.tools`. Lets the assembler keep only the core readers on a tight window (the rest reachable via tool\_catalog/call\_a\_tool). Default absent = identity (all forged tools) = backward-compatible. The battery stays budget-agnostic (per the CONTRIBUTING size-threshold rule) — it applies the supplied filter without measuring context; budget logic lives in the caller's filter. | [src/batteries/llm/openai\_chat\_completions/types.ts:763](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L763) | | `frequency_penalty?` | `number` | `undefined` | Frequency penalty wire field to discourage repeating words. | [src/batteries/llm/openai\_chat\_completions/types.ts:616](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L616) | | `function_call?` | | `"auto"` | `"none"` | { `name`: `string`; } | `undefined` | Deprecated wire field to control which function is called. | [src/batteries/llm/openai\_chat\_completions/types.ts:618](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L618) | | `functions?` | { `description?`: `string`; `name`: `string`; `parameters?`: [`JsonSchema`](../../../../interfaces/JsonSchema.md); }\[] | `undefined` | Deprecated list of functions available to the model. | [src/batteries/llm/openai\_chat\_completions/types.ts:620](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L620) | | `headers?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `string`> | `undefined` | Extra HTTP headers to include with each request. | [src/batteries/llm/openai\_chat\_completions/types.ts:493](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L493) | | `helpers?` | [`Partial`](https://www.typescriptlang.org/docs/handbook/utility-types.html#partialtype)<[`ChatCompletionsHelpers`](ChatCompletionsHelpers.md)> | `undefined` | Optional overrides for OpenAI chat completions helpers. | [src/batteries/llm/openai\_chat\_completions/types.ts:536](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L536) | | `localToolCallParser?` | | [`ToolCallParserName`](../../../transformers_js/helpers/type-aliases/ToolCallParserName.md) | [`ToolCallParserFn`](../../../transformers_js/helpers/type-aliases/ToolCallParserFn.md) | `undefined` | OPTIONAL fallback parser for tool calls the provider did NOT return structurally. **Remarks** The Chat Completions `message.tool_calls` array is authoritative: when the provider returns tool calls, those are used and this option is never consulted. But some models — especially small local ones served through an OpenAI-compatible endpoint — emit a tool call in a surface form the endpoint does not lift into `tool_calls`: ``, or bare `name\nkey: value`. Those land as plain assistant `content`with`tool_calls`empty, silently dropping the call. This is a cross-model, cross-weight reality, not a single-endpoint quirk. Set this to a parser family name (e.g.`'gemma'`), `'auto'`(try every bundled parser in priority order), or a custom [ToolCallParserFn](../../../transformers_js/helpers/type-aliases/ToolCallParserFn.md) to recover such calls from`content`ONLY when the provider returned none. Recovered calls execute exactly like native ones. Default absent = disabled = today's native-only behaviour (fully backward-compatible). Mirrors the on-device batteries'`toolCallParser`, which parse from text unconditionally because those runtimes never return structured calls. | [src/batteries/llm/openai\_chat\_completions/types.ts:751](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L751) | | `logit_bias?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `number`> | `undefined` | Bias logits to control token generation likelihood. | [src/batteries/llm/openai\_chat\_completions/types.ts:622](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L622) | | `logprobs?` | `boolean` | `undefined` | Request log probabilities for generated tokens. | [src/batteries/llm/openai\_chat\_completions/types.ts:624](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L624) | | `max_completion_tokens?` | `number` | `undefined` | Hard limit on token count for model reasoning/completion. | [src/batteries/llm/openai\_chat\_completions/types.ts:626](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L626) | | `max_tokens?` | `number` | `undefined` | Maximum number of generated tokens. | [src/batteries/llm/openai\_chat\_completions/types.ts:628](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L628) | | `metadata?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `string`> | `undefined` | Metadata key-value pairs forwarded to the provider. | [src/batteries/llm/openai\_chat\_completions/types.ts:630](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L630) | | `modalities?` | (`"text"` | `"audio"`)\[] | `undefined` | Desired modalities for model output, such as text and audio. | [src/batteries/llm/openai\_chat\_completions/types.ts:632](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L632) | | `model` | `string` | `undefined` | Name of the model to use for completion. | [src/batteries/llm/openai\_chat\_completions/types.ts:612](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L612) | | `n?` | `number` | `undefined` | Number of completions to generate for each request. | [src/batteries/llm/openai\_chat\_completions/types.ts:634](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L634) | | `onPromptAssembled?` | [`PromptAssembledObserverFn`](../../../../type-aliases/PromptAssembledObserverFn.md) | `undefined` | Observe the fully-assembled request this battery is about to POST TO the provider — fired once per terminal generation, the instant the body is built and BEFORE the fetch, with the wire `messages`, `tools`, and the complete `requestBody`. The mirror of [onRawGeneration](#property-onrawgeneration). Purely observational (return value ignored, errors swallowed). Default absent. An ADK-control key — stripped from the wire request body, never sent to the provider. The request is handed back AS-IS — no redaction — so treat it as potentially sensitive (it may contain auth material that rode the body) if you persist it. See [PromptAssembledObserverFn](../../../../type-aliases/PromptAssembledObserverFn.md). | [src/batteries/llm/openai\_chat\_completions/types.ts:732](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L732) | | `onRawGeneration?` | [`RawGenerationObserverFn`](../../../../type-aliases/RawGenerationObserverFn.md) | `undefined` | Observe the model's RAW response for each completed generation — fired once per terminal generation, after the provider's reply is parsed but before the result is persisted, with the returned assistant content (`rawText`), the residual `cleanedText`, and the extracted `reasoning` / `toolCalls`. Purely observational (return value ignored, errors swallowed). Default absent. An ADK-control key — stripped from the wire request body, never sent to the provider. See [RawGenerationObserverFn](../../../../type-aliases/RawGenerationObserverFn.md). | [src/batteries/llm/openai\_chat\_completions/types.ts:722](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L722) | | `parallel_tool_calls?` | `boolean` | `undefined` | Allow the model to emit multiple tool calls in one turn. | [src/batteries/llm/openai\_chat\_completions/types.ts:636](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L636) | | `prediction?` | { `content`: | `string` | { `text`: `string`; `type`: `"text"`; }\[]; `type`: `"content"`; } | `undefined` | Prediction helper to accelerate latency of known content. | [src/batteries/llm/openai\_chat\_completions/types.ts:638](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L638) | | `prediction.content` | | `string` | { `text`: `string`; `type`: `"text"`; }\[] | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:640](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L640) | | `prediction.type` | `"content"` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:639](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L639) | | `presence_penalty?` | `number` | `undefined` | Presence penalty wire field to encourage new topics. | [src/batteries/llm/openai\_chat\_completions/types.ts:643](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L643) | | `prompt_cache_key?` | `string` | `undefined` | Vendor cache key for caching system prompts. | [src/batteries/llm/openai\_chat\_completions/types.ts:645](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L645) | | `prompt_cache_retention?` | `"in_memory"` | `"24h"` | `undefined` | Cache retention strategy for cached system prompts. | [src/batteries/llm/openai\_chat\_completions/types.ts:647](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L647) | | `reasoning_effort?` | `"none"` | `"minimal"` | `"low"` | `"medium"` | `"high"` | `undefined` | Target reasoning depth/effort for reasoning models. | [src/batteries/llm/openai\_chat\_completions/types.ts:649](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L649) | | `reasoningFieldPrecedence?` | [`ReasoningFieldPrecedence`](../type-aliases/ReasoningFieldPrecedence.md) | `['reasoning', 'reasoning_content']` | Ordered precedence of the wire fields the adapter reads for model reasoning/thinking output. **Remarks** Reasoning is not part of OpenAI's official Chat Completions spec, so OpenAI-compatible providers disagree on the field name: Ollama's `/v1` and current vLLM emit `reasoning`, while legacy vLLM (≤0.8) and the DeepSeek API emit `reasoning_content`. The adapter reads every field in this list that is present on the response. Precedence governs two things. When more than one listed field is present with **identical** content (or only one is present), the adapter emits a single thought attributed to the highest-precedence field. When listed fields are present with **divergent** content, each surfaces as its own thought (ordered by precedence) rather than silently dropping one — a thought stream is the wrong place to lose data. | [src/batteries/llm/openai\_chat\_completions/types.ts:534](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L534) | | `replayCompatibility?` | readonly `string`\[] | `undefined` | List of replay labels supported by the assistant. | [src/batteries/llm/openai\_chat\_completions/types.ts:515](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L515) | | `requestTimeoutMs?` | `number` | `undefined` | Request timeout in milliseconds for API calls. | [src/batteries/llm/openai\_chat\_completions/types.ts:499](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L499) | | `response_format?` | | { `type`: `"text"`; } | { `type`: `"json_object"`; } | { `json_schema`: { `description?`: `string`; `name`: `string`; `schema`: [`JsonSchema`](../../../../interfaces/JsonSchema.md); `strict?`: `boolean`; }; `type`: `"json_schema"`; } | `undefined` | Enforces a specific output format, e.g. JSON schema. | [src/batteries/llm/openai\_chat\_completions/types.ts:651](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L651) | | `retry?` | [`ChatCompletionsRetryConfig`](../../../../interfaces/ChatCompletionsRetryConfig.md) | `undefined` | Configures request retry behavior. | [src/batteries/llm/openai\_chat\_completions/types.ts:501](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L501) | | `safety_identifier?` | `string` | `undefined` | Unique safety system identifier or configuration ID. | [src/batteries/llm/openai\_chat\_completions/types.ts:664](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L664) | | `seed?` | `number` | `undefined` | Deterministic random seed for generation. | [src/batteries/llm/openai\_chat\_completions/types.ts:666](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L666) | | `selfIdentity?` | `string` | `undefined` | Unique identity label for the assistant instance. | [src/batteries/llm/openai\_chat\_completions/types.ts:509](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L509) | | `service_tier?` | `"default"` | `"auto"` | `"flex"` | `"scale"` | `"priority"` | `undefined` | Service reliability tier for processing the request. | [src/batteries/llm/openai\_chat\_completions/types.ts:668](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L668) | | `spoolStore?` | [`SpoolStore`](../../../../../common/type-aliases/SpoolStore.md) | a new `InMemorySpoolStore` per dispatch | Backing store for `string` / `Uint8Array` tool returns. Tool output bytes are written under the tool call's id; the resulting [@nhtio/adk!SpooledArtifact](../../../../../spooled_artifact/classes/SpooledArtifact.md) (or the tool's configured subclass) is the model-visible handle for the rest of the turn. **Remarks** Defaults to a fresh, ephemeral per-dispatch [@nhtio/adk/batteries/storage/in\_memory!InMemorySpoolStore](../../../../storage/in_memory/classes/InMemorySpoolStore.md). Inject an [@nhtio/adk/batteries/storage/opfs!OpfsSpoolStore](../../../../storage/opfs/classes/OpfsSpoolStore.md) or a Flydrive-backed store to persist artifacts to durable storage (and to stream large/binary tool output to disk rather than buffering it in memory). **Lifetime / namespacing:** the default store is per-dispatch, so tool-call ids only need to be unique within a dispatch. An injected durable store persists across turns and dispatches, so the tool-call ids used as keys must be globally unique for that store (or the store must apply its own `keyPrefix`); the adapter does not namespace keys for you, and it does not delete entries — lifetime and cleanup of an injected store are the consumer's responsibility. | [src/batteries/llm/openai\_chat\_completions/types.ts:557](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L557) | | `stop?` | `string` | `string`\[] | `undefined` | Custom stop sequence strings. | [src/batteries/llm/openai\_chat\_completions/types.ts:670](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L670) | | `store?` | `boolean` | `undefined` | Request the provider to store the completed trace. | [src/batteries/llm/openai\_chat\_completions/types.ts:672](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L672) | | `stream?` | `boolean` | `undefined` | Whether to stream the completion response chunk by chunk. | [src/batteries/llm/openai\_chat\_completions/types.ts:495](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L495) | | `stream_options?` | { `include_obfuscation?`: `boolean`; `include_usage?`: `boolean`; } | `undefined` | Configuration options for response streaming. | [src/batteries/llm/openai\_chat\_completions/types.ts:674](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L674) | | `stream_options.include_obfuscation?` | `boolean` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:674](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L674) | | `stream_options.include_usage?` | `boolean` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:674](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L674) | | `streamIdleTimeoutMs?` | `number` | `undefined` | Idle timeout in milliseconds for the stream before aborting. | [src/batteries/llm/openai\_chat\_completions/types.ts:497](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L497) | | `strictToolChoice?` | `boolean` | `false` | When `tool_choice` (or the `allowed_tools` variant) forces the model onto a specific tool name, and that name resolves to an ephemeral, forged artifact-query tool (one produced by `.forgeTools(ctx)` — i.e. `tool.ephemeral === true`), this flag controls how the adapter reacts: - `false` (default): emit a single `helpers.log.warn({ kind: 'tool-choice-forged-artifact', ... })` record and continue. Forging an artifact-query tool by name is almost always a misconfiguration — the tool may not exist in the next iteration once the artifact ages out — but the call still goes through. - `true`: hard-fail with `E_INVALID_OPENAI_CHAT_COMPLETIONS_OPTIONS`. Use this in production deployments where forcing a forged tool indicates a real bug. | [src/batteries/llm/openai\_chat\_completions/types.ts:573](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L573) | | `temperature?` | `number` | `undefined` | Sampling temperature control. | [src/batteries/llm/openai\_chat\_completions/types.ts:676](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L676) | | `thoughtSurfacing?` | `"all"` | `"all-self"` | `"latest-self"` | `undefined` | Determines which thoughts are surfaced back to the model. | [src/batteries/llm/openai\_chat\_completions/types.ts:511](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L511) | | `tokenEncoding?` | | [`TokenEncodingId`](../../../../../type-aliases/TokenEncodingId.md) | `null` | `undefined` | Tokenizer encoding configuration for token counting. | [src/batteries/llm/openai\_chat\_completions/types.ts:513](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L513) | | `tool_choice?` | | `"required"` | `"auto"` | `"none"` | { `function`: { `name`: `string`; }; `type`: `"function"`; } | { `custom`: { `name`: `string`; }; `type`: `"custom"`; } | { `allowed_tools`: { `mode`: `"required"` | `"auto"`; `tools`: ( | { `function`: { `name`: `string`; }; `type`: `"function"`; } | { `custom`: { `name`: `string`; }; `type`: `"custom"`; })\[]; }; `type`: `"allowed_tools"`; } | `undefined` | Enforce or disable tool execution selection. | [src/batteries/llm/openai\_chat\_completions/types.ts:678](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L678) | | `toolCallIdFilter?` | [`ToolCallIdFilterFn`](../../../../type-aliases/ToolCallIdFilterFn.md) | `undefined` | Optional ingress hook for adapting provider tool-call ids; absent preserves the vendor id. | [src/batteries/llm/openai\_chat\_completions/types.ts:753](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L753) | | `top_logprobs?` | `number` | `undefined` | Top log probability tokens limit. | [src/batteries/llm/openai\_chat\_completions/types.ts:695](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L695) | | `top_p?` | `number` | `undefined` | Nucleus sampling probability threshold. | [src/batteries/llm/openai\_chat\_completions/types.ts:697](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L697) | | `unsupportedMediaPolicy?` | [`UnsupportedMediaPolicy`](../../../transformers_js/type-aliases/UnsupportedMediaPolicy.md) | `'throw'` | Policy for how the adapter handles a [@nhtio/adk!Media](../../../../../common/classes/Media.md) instance whose modality the OpenAI Chat Completions wire format does not natively support (today: video). See [UnsupportedMediaPolicy](../../../transformers_js/type-aliases/UnsupportedMediaPolicy.md). | [src/batteries/llm/openai\_chat\_completions/types.ts:582](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L582) | | `user?` | `string` | `undefined` | End-user identifier for abuse monitoring. | [src/batteries/llm/openai\_chat\_completions/types.ts:699](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L699) | | `verbosity?` | `"low"` | `"medium"` | `"high"` | `undefined` | Diagnostics verbosity level. | [src/batteries/llm/openai\_chat\_completions/types.ts:701](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L701) | | `web_search_options?` | { `search_context_size?`: `"low"` | `"medium"` | `"high"`; `user_location?`: { `approximate`: { `city?`: `string`; `country?`: `string`; `region?`: `string`; `timezone?`: `string`; }; `type`: `"approximate"`; }; } | `undefined` | Configuration for built-in web search. | [src/batteries/llm/openai\_chat\_completions/types.ts:703](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L703) | | `web_search_options.search_context_size?` | `"low"` | `"medium"` | `"high"` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:704](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L704) | | `web_search_options.user_location?` | { `approximate`: { `city?`: `string`; `country?`: `string`; `region?`: `string`; `timezone?`: `string`; }; `type`: `"approximate"`; } | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:705](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L705) | | `web_search_options.user_location.approximate` | { `city?`: `string`; `country?`: `string`; `region?`: `string`; `timezone?`: `string`; } | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:707](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L707) | | `web_search_options.user_location.approximate.city?` | `string` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:708](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L708) | | `web_search_options.user_location.approximate.country?` | `string` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:709](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L709) | | `web_search_options.user_location.approximate.region?` | `string` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:710](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L710) | | `web_search_options.user_location.approximate.timezone?` | `string` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:711](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L711) | | `web_search_options.user_location.type` | `"approximate"` | `undefined` | - | [src/batteries/llm/openai\_chat\_completions/types.ts:706](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_chat_completions/types.ts#L706) |