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:204

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:211

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:218

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:223

Array of sequences that will stop generation when encountered.

cacheConfig?

optional cacheConfig?: CacheConfig;

Defined in: src/models/bedrock.ts:230

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:235

Additional fields to include in the Bedrock request.

additionalResponseFieldPaths?

optional additionalResponseFieldPaths?: string[];

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

Additional response field paths to extract from the Bedrock response.

additionalArgs?

optional additionalArgs?: JSONValue;

Defined in: src/models/bedrock.ts:246

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:256

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:264

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:270

Guardrail configuration for content filtering and safety controls.

See

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

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