Skip to content

BedrockModel

Defined in: src/models/bedrock.ts:438

AWS Bedrock model provider implementation.

Implements the Model interface for AWS Bedrock using the Converse Stream API. Supports streaming responses, tool use, prompt caching, and comprehensive error handling.

const provider = new BedrockModel({
modelConfig: {
modelId: 'global.anthropic.claude-sonnet-4-6',
maxTokens: 1024,
temperature: 0.7
},
clientConfig: {
region: 'us-west-2'
}
})
const messages: Message[] = [
{ type: 'message', role: 'user', content: [{ type: 'textBlock', text: 'Hello!' }] }
]
for await (const event of provider.stream(messages)) {
if (event.type === 'modelContentBlockDeltaEvent' && event.delta.type === 'textDelta') {
process.stdout.write(event.delta.text)
}
}
new BedrockModel(options?): BedrockModel;

Defined in: src/models/bedrock.ts:483

Creates a new BedrockModel instance.

ParameterTypeDescription
options?BedrockModelOptionsOptional configuration for model and client

BedrockModel

// Minimal configuration with defaults
const provider = new BedrockModel({
region: 'us-west-2'
})
// With model configuration
const provider = new BedrockModel({
region: 'us-west-2',
modelId: 'global.anthropic.claude-sonnet-4-6',
maxTokens: 2048,
temperature: 0.8,
cacheConfig: { strategy: 'auto' }
})
// With client configuration
const provider = new BedrockModel({
region: 'us-east-1',
clientConfig: {
credentials: myCredentials
}
})

Model.constructor

get modelInfo(): ModelInfo;

Defined in: src/models/bedrock.ts:535

Turns serverSideSummary off, and reports OpenAI models as implicitly cached; a modelInfo override still wins over both. The shared model info lists cache points for their OpenAI-compatible APIs, but Converse caches them implicitly and rejects cache points.

ModelInfo

Model.modelInfo


get modelId(): string;

Defined in: src/models/model.ts:398

The model ID from the current configuration, if configured.

string

Model.modelId


get stateful(): boolean;

Defined in: src/models/model.ts:414

Whether this model manages conversation state server-side.

When true, the server tracks conversation context across turns, so the SDK sends only the latest message instead of the full history. After each invocation, the agent’s local message history is cleared automatically.

Reads modelInfo.capabilities.stateful, so a provider that keeps state server-side sets it there (see modelInfo) and a modelInfo config override can change it.

boolean

false when unknown

Model.stateful

updateConfig(modelConfig): void;

Defined in: src/models/bedrock.ts:659

Updates the model configuration. Merges the provided configuration with existing settings.

ParameterTypeDescription
modelConfigBedrockModelConfigConfiguration object with model-specific settings to update

void

// Update temperature and maxTokens
provider.updateConfig({
temperature: 0.9,
maxTokens: 2048
})

Model.updateConfig


getConfig(): BedrockModelConfig;

Defined in: src/models/bedrock.ts:674

Retrieves the current model configuration.

BedrockModelConfig

The current configuration object

const config = provider.getConfig()
console.log(config.modelId)

Model.getConfig


countTokens(messages, options?): Promise<number>;

Defined in: src/models/bedrock.ts:691

Count tokens using Bedrock’s native CountTokens API.

Uses the same message format as the Converse API to get accurate token counts directly from the Bedrock service. Falls back to the base class heuristic on failure.

ParameterTypeDescription
messagesMessage[]Array of conversation messages to count tokens for
options?CountTokensOptionsOptional options containing system prompt and tool specs

Promise<number>

Total input token count

Model.countTokens


stream(messages, options?): AsyncIterable<ModelStreamEvent>;

Defined in: src/models/bedrock.ts:772

Streams a conversation with the Bedrock model. Returns an async iterable that yields streaming events as they occur.

ParameterTypeDescription
messagesMessage[]Array of conversation messages
options?StreamOptionsOptional streaming configuration

AsyncIterable<ModelStreamEvent>

Async iterable of streaming events

{ContextWindowOverflowError} When input exceeds the model’s context window

{ModelThrottledError} When Bedrock service throttles requests

const messages: Message[] = [
{ type: 'message', role: $1, content: [{ type: 'textBlock', text: 'What is 2+2?' }] }
]
const options: StreamOptions = {
systemPrompt: 'You are a helpful math assistant.',
toolSpecs: [calculatorTool]
}
for await (const event of provider.stream(messages, options)) {
if (event.type === 'modelContentBlockDeltaEvent') {
console.log(event.delta)
}
}

Model.stream


summarize(messages, options?): Promise<SummarizeResult>;

Defined in: src/models/model.ts:490

Summarizes messages.

messages is a request as the caller would send it to stream(), along with its tool specs and system prompt. The base implementation sends that request closed by an instruction not to act on it or call tools, followed by instructions (or default ones), and otherwise as given, so a caller that replays its own conversation can share its prompt cache. The summary is the reply’s text, including a reply cut off at the output limit or a stop sequence. A reply that ends for another reason, such as a tool call, a cancellation or a guardrail, or that holds no text, gives an empty result.

Every summary is a summaryBlock. The base implementation leaves its provider unset. A provider that reports modelInfo.capabilities.serverSideSummary as true overrides this method to summarize server-side and sets provider to its own name, using the base implementation when the capability is off or the server-side summary fails, as AnthropicModel does. A summary with a provider can stand in for the messages it summarized only when they start at the conversation’s first message; a caller that summarizes anything else uses only its text.

ParameterTypeDescription
messagesMessage[]The request to summarize, left unmodified
options?SummarizeOptionsThe request’s system prompt and tools, summarization instructions, cancel signal and agent metadata

Promise<SummarizeResult>

The summary and the token usage of the calls made for it

Model.summarize


estimateUtilization(inputTokens): number;

Defined in: src/models/model.ts:503

Estimate the fraction of the model’s context window consumed by the given input token count.

Resolves the model’s context window limit (falling back to DEFAULT_CONTEXT_WINDOW_LIMIT with a warning when not configured) and returns inputTokens / contextWindowLimit.

ParameterTypeDescription
inputTokensnumberTotal input token count (e.g. from a model event’s projectedInputTokens)

number

Token usage ratio (0–1+; above 1.0 means overflow)

Model.estimateUtilization


streamAggregated(messages, options?): AsyncGenerator<
| ContentBlock
| ModelStreamEvent, StreamAggregatedResult, undefined>;

Defined in: src/models/model.ts:570

Streams a conversation with aggregated content blocks and messages. Returns an async generator that yields streaming events and content blocks, and returns the final message with stop reason and optional metadata.

This method enhances the basic stream() by collecting streaming events into complete ContentBlock and Message objects, which are needed by the agentic loop for tool execution and conversation management.

The method yields:

  • ModelStreamEvent - Original streaming events (passed through)
  • ContentBlock - Complete content block (emitted when block completes)

The method returns:

  • StreamAggregatedResult containing the complete message, stop reason, and optional metadata

All exceptions thrown from this method are wrapped in ModelError to provide a consistent error type for model-related errors. Specific error subtypes like ContextWindowOverflowError, ModelThrottledError, and MaxTokensError are preserved.

ParameterTypeDescription
messagesMessage[]Array of conversation messages
options?StreamOptionsOptional streaming configuration

AsyncGenerator< | ContentBlock | ModelStreamEvent, StreamAggregatedResult, undefined>

Async generator yielding ModelStreamEvent | ContentBlock and returning a StreamAggregatedResult

ModelError - Base class for all model-related errors

ContextWindowOverflowError - When input exceeds the model’s context window

ModelThrottledError - When the model provider throttles requests

MaxTokensError - When the model reaches its maximum token limit

Model.streamAggregated