BedrockModelConfig

Configuration interface for AWS Bedrock model provider.

Extends BaseModelConfig with Bedrock-specific configuration options for model parameters, caching, and additional request/response fields.

Example

const config: BedrockModelConfig = {
  modelId: 'global.anthropic.claude-sonnet-4-6',
  maxTokens: 1024,
  temperature: 0.7,
  cacheConfig: { strategy: 'auto' }
}

Extends

BaseModelConfig

Extended by

BedrockModelOptions

Properties

maxTokens?

optional maxTokens?: number;

Defined in: src/models/bedrock.ts:214

Maximum number of tokens to generate in the response.

See

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

Overrides

BaseModelConfig.maxTokens

temperature?

optional temperature?: number;

Defined in: src/models/bedrock.ts:221

Controls randomness in generation.

See

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

Overrides

BaseModelConfig.temperature

topP?

optional topP?: number;

Defined in: src/models/bedrock.ts:228

Controls diversity via nucleus sampling.

See

https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InferenceConfiguration.html

Overrides

BaseModelConfig.topP

stopSequences?

optional stopSequences?: string[];

Defined in: src/models/bedrock.ts:233

Array of sequences that will stop generation when encountered.

cacheConfig?

optional cacheConfig?: CacheConfig;

Defined in: src/models/bedrock.ts:240

Configuration for prompt caching.

See

https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html

additionalRequestFields?

optional additionalRequestFields?: JSONValue;

Defined in: src/models/bedrock.ts:245

Additional fields to include in the Bedrock request.

additionalResponseFieldPaths?

optional additionalResponseFieldPaths?: string[];

Defined in: src/models/bedrock.ts:250

Additional response field paths to extract from the Bedrock response.

additionalArgs?

optional additionalArgs?: JSONValue;

Defined in: src/models/bedrock.ts:256

Additional arguments to pass through to the Bedrock Converse API.

See

https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/bedrock-runtime/command/ConverseStreamCommand/

stream?

optional stream?: boolean;

Defined in: src/models/bedrock.ts:266

Whether or not to stream responses from the model.

This will use the ConverseStream API instead of the Converse API.

See

includeToolResultStatus?

optional includeToolResultStatus?: boolean | "auto";

Defined in: src/models/bedrock.ts:274

Flag to include status field in tool results.

true: Always include status field
false: Never include status field
'auto': Automatically determine based on model ID (default)

guardrailConfig?

optional guardrailConfig?: BedrockGuardrailConfig;

Defined in: src/models/bedrock.ts:280

Guardrail configuration for content filtering and safety controls.

See

https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html

useNativeTokenCount?

optional useNativeTokenCount?: boolean;

Defined in: src/models/bedrock.ts:289

Whether to use the native Bedrock CountTokens API.

When true (default), countTokens() calls the Bedrock CountTokens API for accurate counts. When false, skips the API call and uses the character-based heuristic estimator.

modelId?

optional modelId?: string;

Defined in: src/models/model.ts:91

The model identifier. This typically specifies which model to use from the provider’s catalog.

Inherited from

BaseModelConfig.modelId

contextWindowLimit?

optional contextWindowLimit?: number;

Defined in: src/models/model.ts:124

Maximum context window size in tokens for the model.

This value represents the total token capacity shared between input and output. When not provided, it is automatically resolved from a built-in lookup table based on the configured model ID. An explicit value always takes precedence.

When modelId is changed via updateConfig(), this value is automatically re-resolved if it was initially auto-populated. Explicitly set values are preserved.

Inherited from

BaseModelConfig.contextWindowLimit