Interface: TextAdapter<TModel, TProviderOptions, TInputModalities, TMessageMetadataByModality, TToolCapabilities, TToolCallMetadata>#

Defined in: packages/typescript/ai/src/activities/chat/adapter.ts:59

Text adapter interface with pre-resolved generics.

An adapter is created by a provider function: provider('model') → adapter All type resolution happens at the provider call site, not in this interface.

Generic parameters:

• TModel: The specific model name (e.g., 'gpt-4o')
• TProviderOptions: Provider-specific options for this model (already resolved)
• TInputModalities: Supported input modalities for this model (already resolved)
• TMessageMetadata: Metadata types for content parts (already resolved)
• TToolCapabilities: Tuple of tool-kind strings supported by this model, resolved from supports.tools
• TToolCallMetadata: Metadata type that round-trips with tool calls (e.g. Gemini's thoughtSignature)

Type Parameters#

TModel#

TModel extends string

TProviderOptions#

TProviderOptions extends Record<string, any>

TInputModalities#

TInputModalities extends ReadonlyArray<Modality>

TMessageMetadataByModality#

TMessageMetadataByModality extends DefaultMessageMetadataByModality

TToolCapabilities#

TToolCapabilities extends ReadonlyArray<string> = ReadonlyArray<string>

TToolCallMetadata#

TToolCallMetadata = unknown

Properties#

~types#

~types: object;

~types: object;

Defined in: packages/typescript/ai/src/activities/chat/adapter.ts:77

Internal

Type-only properties for inference. Not assigned at runtime.

inputModalities#

inputModalities: TInputModalities;

inputModalities: TInputModalities;

messageMetadataByModality#

messageMetadataByModality: TMessageMetadataByModality;

messageMetadataByModality: TMessageMetadataByModality;

providerOptions#

providerOptions: TProviderOptions;

providerOptions: TProviderOptions;

toolCallMetadata#

toolCallMetadata: TToolCallMetadata;

toolCallMetadata: TToolCallMetadata;

toolCapabilities#

toolCapabilities: TToolCapabilities;

toolCapabilities: TToolCapabilities;

chatStream()#

chatStream: (options) => AsyncIterable<AGUIEvent>;

chatStream: (options) => AsyncIterable<AGUIEvent>;

Defined in: packages/typescript/ai/src/activities/chat/adapter.ts:88

Stream text completions from the model

Parameters#

options#

TextOptions<TProviderOptions>

Returns#

AsyncIterable<AGUIEvent>

kind#

readonly kind: "text";

readonly kind: "text";

Defined in: packages/typescript/ai/src/activities/chat/adapter.ts:68

Discriminator for adapter kind

model#

readonly model: TModel;

readonly model: TModel;

Defined in: packages/typescript/ai/src/activities/chat/adapter.ts:72

The model this adapter is configured for

name#

readonly name: string;

readonly name: string;

Defined in: packages/typescript/ai/src/activities/chat/adapter.ts:70

Provider name identifier (e.g., 'openai', 'anthropic')

structuredOutput()#

structuredOutput: (options) => Promise<StructuredOutputResult<unknown>>;

structuredOutput: (options) => Promise<StructuredOutputResult<unknown>>;

Defined in: packages/typescript/ai/src/activities/chat/adapter.ts:100

Generate structured output using the provider's native structured output API. This method uses stream: false and sends the JSON schema to the provider to ensure the response conforms to the expected structure.

Parameters#

options#

StructuredOutputOptions<TProviderOptions>

Structured output options containing chat options and JSON schema

Returns#

Promise<StructuredOutputResult<unknown>>

Promise with the raw data (validation is done in the chat function)

structuredOutputStream()?#

optional structuredOutputStream: (options) => AsyncIterable<AGUIEvent>;

optional structuredOutputStream: (options) => AsyncIterable<AGUIEvent>;

Defined in: packages/typescript/ai/src/activities/chat/adapter.ts:117

Stream structured output using the provider's native streaming structured output API (stream + response_format json_schema in a single request).

Optional — adapters without native streaming JSON omit this method and the activity layer synthesizes a stream around the non-streaming structuredOutput call.

Implementations must emit standard AG-UI lifecycle events (RUN_STARTED, TEXT_MESSAGE_*, RUN_FINISHED) carrying raw JSON text deltas, plus a final CUSTOM event named structured-output.complete whose value is { object, raw, reasoning? }.

Parameters#

options#

StructuredOutputOptions<TProviderOptions>

Returns#

AsyncIterable<AGUIEvent>