Class LLM

Hierarchy (view full)

llm.LLM
- LLM

Index

Constructors

Accessors

Methods

aclose chat close label prewarm

Constructors

constructor

new LLM(opts?): responses.LLM
Create a new instance of OpenAI Responses LLM.
Parameters
- opts: Partial<responses.LLMOptions> = defaultLLMOptions
Returns responses.LLM
Remarks
apiKey must be set to your OpenAI API key, either using the argument or by setting the OPENAI_API_KEY environment variable.
Overrides LLM.constructor
- Defined in plugins/openai/src/responses/llm.ts:386

Accessors

model

get model(): string
Get the model name/identifier for this LLM instance.

Returns string
The model name if available, "unknown" otherwise.

Remarks
Plugins should override this property to provide their model information.
Overrides llm.LLM.model
- Defined in plugins/openai/src/responses/llm.ts:413

provider

get provider(): string
Get the provider name for this LLM instance.

Returns string
The provider name if available, "unknown" otherwise.

Remarks
Plugins should override this property to provide their provider information.
Inherited from llm.LLM.provider
- Defined in agents/dist/llm/llm.d.ts:69

Methods

aclose

aclose(): Promise<void>
Returns Promise<void>
Overrides LLM.aclose
- Defined in plugins/openai/src/responses/llm.ts:421

chat

chat(__namedParameters): llm.LLMStream
Returns a LLMStream that can be used to push text and receive LLM responses.
Parameters
- __namedParameters: {
      chatCtx: ChatContext;
      connOptions?: APIConnectOptions;
      extraKwargs?: Record<string, unknown>;
      parallelToolCalls?: boolean;
      toolChoice?: llm.ToolChoice;
      toolCtx?: ToolContextLike;
  }
  - chatCtx: ChatContext
  - Optional connOptions?: APIConnectOptions
  - Optional extraKwargs?: Record<string, unknown>
  - Optional parallelToolCalls?: boolean
  - Optional toolChoice?: llm.ToolChoice
  - Optional toolCtx?: ToolContextLike
Returns llm.LLMStream
Overrides LLM.chat
- Defined in plugins/openai/src/responses/llm.ts:429

close

close(): Promise<void>
Returns Promise<void>
- Defined in plugins/openai/src/responses/llm.ts:425

label

label(): string
Returns string
Overrides LLM.label
- Defined in plugins/openai/src/responses/llm.ts:409

prewarm

prewarm(): void
Pre-warm connection to the LLM service.

Establishes DNS resolution and the TLS connection to the provider before the first inference request, reducing time-to-first-token on the initial reply. Non-blocking (fire-and-forget) and idempotent; calls made after aclose are ignored. Providers enable it by overriding _prewarmImpl.

Returns void
Overrides LLM.prewarm
- Defined in plugins/openai/src/responses/llm.ts:417