MistralLLM

Defined in: src/providers/llm/mistral/MistralLLM.ts:114

Mistral LLM provider.

Remarks

A thin subclass of OpenAICompatibleLLM that configures defaults for Mistral’s API. All generation logic (streaming, non-streaming, abort handling, proxy support) is inherited from the base class.

Mistral models are known for strong performance-per-parameter and excellent multilingual support. The mistral-small-latest model (default) provides a good balance of speed and quality for voice assistant use cases.

Example

import { MistralLLM } from 'composite-voice';

const llm = new MistralLLM({
  mistralApiKey: process.env.MISTRAL_API_KEY,
  model: 'mistral-small-latest',
  systemPrompt: 'You are a helpful multilingual voice assistant.',
});
await llm.initialize();

const stream = await llm.generate('Explain the water cycle.');
for await (const chunk of stream) {
  process.stdout.write(chunk);
}

await llm.dispose();

See

• MistralLLMConfig for configuration options.
• OpenAICompatibleLLM for the base class.
• OpenAILLM for the OpenAI alternative.

Extends

• OpenAICompatibleLLM

Constructors

Constructor

new MistralLLM(config, logger?): MistralLLM;

Defined in: src/providers/llm/mistral/MistralLLM.ts:129

Creates a new Mistral LLM provider instance.

Parameters

Returns

MistralLLM

Remarks

The constructor resolves the API key (preferring mistralApiKey over apiKey) and applies Mistral-specific defaults for baseURL and model.

Overrides

OpenAICompatibleLLM.constructor

Properties

Accessors

isProxyMode

Get Signature

get protected isProxyMode(): boolean;

Defined in: src/providers/base/BaseProvider.ts:286

Whether the provider is in proxy mode.

Returns

boolean

true when proxyUrl is set.

Inherited from

OpenAICompatibleLLM.isProxyMode

Methods

assertAuth()

protected assertAuth(): void;

Defined in: src/providers/base/BaseProvider.ts:272

Validate that auth is configured (either apiKey or proxyUrl).

Returns

void

Remarks

Call this in onInitialize() for any provider that requires external authentication. Native providers (NativeSTT, NativeTTS) and in-browser providers (WebLLM) should NOT call this method.

Throws

ProviderInitializationError Thrown when neither apiKey nor proxyUrl is set.

Inherited from

OpenAICompatibleLLM.assertAuth

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

OpenAICompatibleLLM.assertReady

buildClientOptions()

protected buildClientOptions(): Record<string, unknown>;

Defined in: src/providers/llm/openai-compatible/OpenAICompatibleLLM.ts:187

Build the options object passed to new OpenAI(...).

Returns

Record<string, unknown>

An object of additional options to pass to the OpenAI SDK constructor.

Remarks

Override in subclasses to inject provider-specific SDK constructor options. The returned object is spread into the OpenAI client constructor after the base options (apiKey, baseURL, maxRetries, timeout, dangerouslyAllowBrowser).

Example

// In a subclass (e.g., OpenAILLM):
protected override buildClientOptions(): Record<string, unknown> {
  return { organization: this.config.organizationId };
}

Inherited from

OpenAICompatibleLLM.buildClientOptions

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.

Inherited from

OpenAICompatibleLLM.dispose

generate()

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

Defined in: src/providers/llm/openai-compatible/OpenAICompatibleLLM.ts:282

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.

Example

const provider = new OpenAICompatibleLLM({ apiKey: 'sk-...', model: 'gpt-4' });
await provider.initialize();

const stream = await provider.generate('Explain quantum computing briefly.');
for await (const chunk of stream) {
  process.stdout.write(chunk);
}

Inherited from

OpenAICompatibleLLM.generate

generateFromMessages()

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

Defined in: src/providers/llm/openai-compatible/OpenAICompatibleLLM.ts:342

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; otherwise, a single chunk containing the full response is yielded.

Remarks

This is the primary generation method. It merges per-call options with the provider config defaults, converts the messages to OpenAI’s ChatCompletionMessageParam format, and dispatches to either the streaming or non-streaming code path based on config.stream.

The returned async iterable respects the options.signal abort signal. When aborted, iteration stops and an AbortError is thrown. This is used by the CompositeVoice eager/preflight pipeline to cancel speculative generations.

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 provider = new OpenAICompatibleLLM({ apiKey: 'sk-...', model: 'gpt-4' });
await provider.initialize();

const messages: LLMMessage[] = [
  { role: 'system', content: 'You are a helpful assistant.' },
  { role: 'user', content: 'What is the capital of France?' },
];

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

Inherited from

OpenAICompatibleLLM.generateFromMessages

getConfig()

getConfig(): LLMProviderConfig;

Defined in: src/providers/base/BaseLLMProvider.ts:246

Get a shallow copy of the current LLM configuration.

Returns

LLMProviderConfig

A new LLMProviderConfig object.

Inherited from

OpenAICompatibleLLM.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.

Inherited from

OpenAICompatibleLLM.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.

Inherited from

OpenAICompatibleLLM.isReady

isToolCall()

isToolCall(_chunk): boolean;

Defined in: src/providers/base/BaseLLMProvider.ts:179

Check whether a response chunk represents a tool call.

Parameters

Returns

boolean

true when the chunk represents a tool call.

Remarks

The default implementation returns false. Tool-aware providers override this to detect tool invocations in the response stream.

Inherited from

OpenAICompatibleLLM.isToolCall

mergeOptions()

protected mergeOptions(options?): LLMGenerationOptions;

Defined in: src/providers/base/BaseLLMProvider.ts:224

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

OpenAICompatibleLLM.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

OpenAICompatibleLLM.onConfigUpdate

onDispose()

protected onDispose(): Promise<void>;

Defined in: src/providers/llm/openai-compatible/OpenAICompatibleLLM.ts:246

Dispose of the OpenAI client and release resources.

Returns

Promise<void>

Remarks

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

Inherited from

OpenAICompatibleLLM.onDispose

onInitialize()

protected onInitialize(): Promise<void>;

Defined in: src/providers/llm/openai-compatible/OpenAICompatibleLLM.ts:203

Initialize the OpenAI-compatible client.

Returns

Promise<void>

Remarks

Dynamically imports the openai 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 openai package cannot be found (peer dependency not installed).

Inherited from

OpenAICompatibleLLM.onInitialize

processMessages()

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

Defined in: src/providers/llm/openai-compatible/OpenAICompatibleLLM.ts:293

Implement the abstract BaseLLMProvider.processMessages method.

Parameters

Returns

Promise<AsyncIterable<string, any, any>>

Remarks

Delegates to generateFromMessages.

Inherited from

OpenAICompatibleLLM.processMessages

processText()

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

Defined in: src/providers/base/BaseLLMProvider.ts:163

Process a single text prompt (convenience wrapper).

Parameters

Returns

Promise<AsyncIterable<string, any, any>>

An AsyncIterable that yields text chunks as they arrive.

Remarks

Converts the prompt to a messages array (optionally prepending a system message from config) and delegates to processMessages.

Inherited from

OpenAICompatibleLLM.processText

promptToMessages()

protected promptToMessages(prompt): LLMMessage[];

Defined in: src/providers/base/BaseLLMProvider.ts:195

Convert a plain-text prompt into an LLMMessage array.

Parameters

Returns

LLMMessage[]

A messages array suitable for processMessages.

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

OpenAICompatibleLLM.promptToMessages

resolveApiKey()

protected resolveApiKey(): string;

Defined in: src/providers/base/BaseProvider.ts:325

Resolve the API key for this provider.

Returns

string

The configured API key, or 'proxy' in proxy mode.

Remarks

Returns 'proxy' in proxy mode so that SDK clients (which require a non-empty API key string) can be instantiated without the real key.

Inherited from

OpenAICompatibleLLM.resolveApiKey

resolveAuthHeader()

protected resolveAuthHeader(defaultAuthType?): string | undefined;

Defined in: src/providers/base/BaseProvider.ts:364

Resolve Authorization header value for the configured auth type.

Parameters

Returns

string | undefined

The Authorization header value, or undefined in proxy mode.

Remarks

Returns the header value for REST or server-side WebSocket connections:

• 'token' → 'Token <apiKey>'
• 'bearer' → 'Bearer <apiKey>'

Returns undefined in proxy mode.

Inherited from

OpenAICompatibleLLM.resolveAuthHeader

resolveBaseUrl()

protected resolveBaseUrl(defaultUrl?): string | undefined;

Defined in: src/providers/base/BaseProvider.ts:307

Resolve the base URL for this provider.

Parameters

Returns

string | undefined

The resolved URL, or undefined when all sources are unset.

Remarks

Priority: proxyUrl > endpoint > defaultUrl.

For WebSocket providers (this.type === 'websocket'), the proxy URL’s http(s) scheme is automatically converted to ws(s).

When no URL is configured and defaultUrl is undefined, the return value is undefined — this lets SDK-based providers (Anthropic, OpenAI) fall back to their own built-in defaults.

Inherited from

OpenAICompatibleLLM.resolveBaseUrl

resolveWsProtocols()

protected resolveWsProtocols(defaultAuthType?): string[] | undefined;

Defined in: src/providers/base/BaseProvider.ts:343

Resolve WebSocket subprotocol for authentication.

Parameters

Returns

string[] | undefined

Subprotocol array for new WebSocket(url, protocols), or undefined.

Remarks

Returns the subprotocol array for direct mode based on authType:

• 'token' → ['token', apiKey] (Deepgram default)
• 'bearer' → ['bearer', apiKey] (OAuth/Bearer tokens)

Returns undefined in proxy mode (no client-side auth needed).

Inherited from

OpenAICompatibleLLM.resolveWsProtocols

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

OpenAICompatibleLLM.updateConfig