AnthropicLLM

Defined in: src/providers/llm/anthropic/AnthropicLLM.ts:191

Anthropic LLM provider for Claude models.

Remarks

Uses the official @anthropic-ai/sdk for the Messages API with full support for streaming (messages.stream) and non-streaming (messages.create) responses. The provider handles the Anthropic-specific message format automatically:

• System messages are extracted from the message array and passed as the top-level system parameter (Anthropic does not accept role: 'system' in the messages array).
• Streaming yields text from content_block_delta events with type: 'text_delta'.
• Abort support is provided via the options.signal parameter, which is forwarded to the Anthropic SDK to cancel in-flight HTTP requests.

Examples

import { AnthropicLLM } from 'composite-voice';

const llm = new AnthropicLLM({
  apiKey: process.env.ANTHROPIC_API_KEY,
  model: 'claude-haiku-4-5',
  maxTokens: 512,
  systemPrompt: 'You are a concise voice assistant.',
});
await llm.initialize();

const stream = await llm.generate('What is the speed of light?');
for await (const chunk of stream) {
  process.stdout.write(chunk);
}

await llm.dispose();

import { AnthropicLLM } from 'composite-voice';

const llm = new AnthropicLLM({
  proxyUrl: 'http://localhost:3000/api/proxy/anthropic',
  model: 'claude-sonnet-4-6',
});
await llm.initialize();

const stream = await llm.generate('Tell me a joke.');
for await (const chunk of stream) {
  document.getElementById('output')!.textContent += chunk;
}

See

• AnthropicLLMConfig for configuration options.
• BaseLLMProvider for the abstract base class.
• OpenAILLM for the OpenAI alternative.

Extends

• BaseLLMProvider

Implements

• ToolAwareLLMProvider

Constructors

Constructor

new AnthropicLLM(config, logger?): AnthropicLLM;

Defined in: src/providers/llm/anthropic/AnthropicLLM.ts:208

Creates a new Anthropic LLM provider instance.

Parameters

Returns

AnthropicLLM

Remarks

The constructor normalizes the configuration by applying defaults: maxTokens defaults to 1024, stream defaults to true, and model defaults to 'claude-haiku-4-5'.

Overrides

BaseLLMProvider.constructor

Properties

Methods

assertReady()

protected assertReady(): void;

Defined in: src/providers/base/BaseProvider.ts:255

Guard that throws if the provider has not been initialized.

Returns

void

Remarks

Call at the start of any method that requires the provider to be ready.

Throws

Error Thrown with a descriptive message when initialized is false.

Inherited from

BaseLLMProvider.assertReady

dispose()

dispose(): Promise<void>;

Defined in: src/providers/base/BaseProvider.ts:154

Clean up resources and dispose of the provider.

Returns

Promise<void>

Remarks

Delegates to the subclass hook onDispose and resets the initialized flag. If the provider is not initialized, the call is a no-op.

Throws

Re-throws any error raised by onDispose.

Implementation of

ToolAwareLLMProvider.dispose

Inherited from

BaseLLMProvider.dispose

generate()

generate(prompt, options?): Promise<AsyncIterable<string, any, any>>;

Defined in: src/providers/llm/anthropic/AnthropicLLM.ts:307

Generate an LLM response from a single text prompt.

Parameters

Returns

Promise<AsyncIterable<string, any, any>>

An async iterable that yields text chunks. When streaming is enabled (the default), chunks arrive incrementally; otherwise, a single chunk containing the full response is yielded.

Remarks

Convenience wrapper that converts the prompt to a message array (prepending the system prompt if configured) and delegates to generateFromMessages.

Throws

Error Thrown if the provider has not been initialized or the client is unavailable.

Throws

AbortError Thrown if the provided options.signal is aborted before or during generation.

Implementation of

ToolAwareLLMProvider.generate

Overrides

BaseLLMProvider.generate

generateFromMessages()

generateFromMessages(messages, options?): Promise<AsyncIterable<string, any, any>>;

Defined in: src/providers/llm/anthropic/AnthropicLLM.ts:351

Generate an LLM response from a multi-turn conversation.

Parameters

Returns

Promise<AsyncIterable<string, any, any>>

An async iterable that yields text chunks. When streaming is enabled (the default), chunks arrive incrementally from content_block_delta events; otherwise, a single chunk containing the full response is yielded.

Remarks

This is the primary generation method. It extracts system messages from the array and passes them as Anthropic’s top-level system parameter (since Anthropic does not accept role: 'system' inline). Remaining messages are converted to the Anthropic MessageParam format.

Dispatches to either the streaming (messages.stream) or non-streaming (messages.create) code path based on config.stream.

Throws

Error Thrown if the provider has not been initialized or the client is unavailable.

Throws

AbortError Thrown if the provided options.signal is aborted before or during generation.

Example

const messages: LLMMessage[] = [
  { role: 'system', content: 'You are a helpful assistant.' },
  { role: 'user', content: 'Summarize the theory of relativity.' },
];

const stream = await anthropicLLM.generateFromMessages(messages);
for await (const chunk of stream) {
  process.stdout.write(chunk);
}

Implementation of

ToolAwareLLMProvider.generateFromMessages

Overrides

BaseLLMProvider.generateFromMessages

generateWithTools()

generateWithTools(messages, options?): Promise<AsyncIterable<LLMStreamChunk, any, any>>;

Defined in: src/providers/llm/anthropic/AnthropicLLM.ts:556

Generate a response with tool use support.

Parameters

Returns

Promise<AsyncIterable<LLMStreamChunk, any, any>>

Remarks

Returns an async iterable of LLMStreamChunk — text chunks go to TTS, tool_call chunks go to the tool executor. The done chunk signals the stop reason so the caller knows whether to send tool results and re-call.

Implementation of

ToolAwareLLMProvider.generateWithTools

getConfig()

getConfig(): LLMProviderConfig;

Defined in: src/providers/base/BaseLLMProvider.ts:192

Get a shallow copy of the current LLM configuration.

Returns

LLMProviderConfig

A new LLMProviderConfig object.

Inherited from

BaseLLMProvider.getConfig

initialize()

initialize(): Promise<void>;

Defined in: src/providers/base/BaseProvider.ts:127

Initialize the provider, making it ready for use.

Returns

Promise<void>

Remarks

Calls the subclass hook onInitialize. If the provider has already been initialized the call is a no-op.

Throws

ProviderInitializationError Thrown when onInitialize rejects. The original error is wrapped with the provider class name for diagnostics.

Implementation of

ToolAwareLLMProvider.initialize

Inherited from

BaseLLMProvider.initialize

isReady()

isReady(): boolean;

Defined in: src/providers/base/BaseProvider.ts:178

Check whether the provider has been initialized and is ready.

Returns

boolean

true when initialize has completed successfully and dispose has not yet been called.

Implementation of

ToolAwareLLMProvider.isReady

Inherited from

BaseLLMProvider.isReady

mergeOptions()

protected mergeOptions(options?): LLMGenerationOptions;

Defined in: src/providers/base/BaseLLMProvider.ts:170

Merge per-call generation options with the provider’s config defaults.

Parameters

Returns

LLMGenerationOptions

A merged LLMGenerationOptions object.

Remarks

Values supplied in options take precedence over values in config. Only defined values are included in the result, allowing providers to distinguish “not set” from explicit values.

Inherited from

BaseLLMProvider.mergeOptions

onConfigUpdate()

protected onConfigUpdate(_config): void;

Defined in: src/providers/base/BaseProvider.ts:242

Hook called after updateConfig merges new values.

Parameters

Returns

void

Remarks

The default implementation is a no-op. Override in subclasses to react to runtime configuration changes (e.g. reconnect with a new API key).

Inherited from

BaseLLMProvider.onConfigUpdate

onDispose()

protected onDispose(): Promise<void>;

Defined in: src/providers/llm/anthropic/AnthropicLLM.ts:282

Dispose of the Anthropic client and release resources.

Returns

Promise<void>

Remarks

Nullifies the client reference so that it can be garbage-collected. Called automatically by BaseLLMProvider.dispose.

Overrides

BaseLLMProvider.onDispose

onInitialize()

protected onInitialize(): Promise<void>;

Defined in: src/providers/llm/anthropic/AnthropicLLM.ts:230

Initialize the Anthropic client.

Returns

Promise<void>

Remarks

Dynamically imports the @anthropic-ai/sdk peer dependency, resolves the base URL (preferring proxyUrl over baseURL), and creates the SDK client instance. Called automatically by BaseLLMProvider.initialize.

Throws

ProviderInitializationError Thrown if neither apiKey nor proxyUrl is configured, or if the @anthropic-ai/sdk package cannot be found (peer dependency not installed).

Overrides

BaseLLMProvider.onInitialize

promptToMessages()

protected promptToMessages(prompt): LLMMessage[];

Defined in: src/providers/base/BaseLLMProvider.ts:141

Convert a plain-text prompt into an LLMMessage array.

Parameters

Returns

LLMMessage[]

A messages array suitable for generateFromMessages.

Remarks

If the provider’s config includes a systemPrompt, it is prepended as a system message. The prompt itself becomes a user message.

Inherited from

BaseLLMProvider.promptToMessages

updateConfig()

updateConfig(config): void;

Defined in: src/providers/base/BaseProvider.ts:201

Merge partial configuration updates into the current config.

Parameters

Returns

void

Remarks

After merging, the subclass hook onConfigUpdate is called so providers can react to changed values at runtime.

Inherited from

BaseLLMProvider.updateConfig