@google/genai 2.8.0 → 2.9.0

package/dist/vertex_internal/index.d.ts

@@ -157,7 +157,7 @@ declare interface ApiAuthApiKeyConfig {
  * WARNING: This is an internal API and may change without notice. Direct usage
  * is not supported and may break your application.
  */
-export declare class ApiClient implements GeminiNextGenAPIClientAdapter {
+export declare class ApiClient {
     readonly clientOptions: ApiClientInitOptions;
     private readonly customBaseUrl?;
     constructor(opts: ApiClientInitOptions);
@@ -322,9 +322,14 @@ declare interface AudioChunk {
 
 /** The audio transcription configuration in Setup. */
 declare interface AudioTranscriptionConfig {
-    /** The language codes of the audio. BCP-47 language code. If not set, the transcription will be in the language detected by the model. If set, the server will use the language code specified in the model config as a hint for the language of the audio
-     */
+    /** Deprecated: use LanguageAuto or LanguageHints instead. */
     languageCodes?: string[];
+    /** The model will detect the language automatically. Do not use together with LanguageHints. */
+    languageAuto?: LanguageAuto;
+    /** Specifies one or more languages in the audio. Do not use together with LanguageAuto. */
+    languageHints?: LanguageHints;
+    /** A list of phrases used for speech adaptation, which biases the ASR model to improve recognition of these specific terms. */
+    adaptationPhrases?: string[];
 }
 
 /**
@@ -2181,7 +2186,7 @@ declare interface Endpoint {
 /** End of speech sensitivity. */
 declare enum EndSensitivity {
     /**
-     * The default is END_SENSITIVITY_LOW.
+     * The default is END_SENSITIVITY_LOW for Gemini Enterprise Agent Platform and END_SENSITIVITY_HIGH for Gemini Live.
      */
     END_SENSITIVITY_UNSPECIFIED = "END_SENSITIVITY_UNSPECIFIED",
     /**
@@ -2675,18 +2680,6 @@ declare interface GcsSource {
     uris?: string[];
 }
 
-/**
- * @license
- * Copyright 2025 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-declare interface GeminiNextGenAPIClientAdapter {
-    isVertexAI: () => boolean;
-    getProject: () => string | undefined;
-    getLocation: () => string | undefined;
-    getAuthHeaders: () => Headers | Promise<Headers>;
-}
-
 /** Input example for preference optimization. This data type is not supported in Gemini API. */
 declare interface GeminiPreferenceExample {
     /** List of completions for a given prompt. */
@@ -4347,6 +4340,16 @@ declare enum Language {
     PYTHON = "PYTHON"
 }
 
+/** Indicates the language of the audio should be automatically detected. */
+declare interface LanguageAuto {
+}
+
+/** Provides hints to the model about possible languages present in the audio. */
+declare interface LanguageHints {
+    /** BCP-47 language codes. At least one must be specified. */
+    languageCodes?: string[];
+}
+
 /** An object that represents a latitude/longitude pair. This is expressed as a pair of doubles to represent degrees latitude and degrees longitude. Unless specified otherwise, this object must conform to the WGS84 standard. Values must be within normalized ranges. */
 declare interface LatLng {
     /** The latitude in degrees. It must be in the range [-90.0, +90.0]. */
@@ -5096,6 +5099,8 @@ declare interface LiveServerContent {
      it is waiting for more input from the user, e.g. because it expects the
      user to continue talking. */
     waitingForInput?: boolean;
+    /** Low latency transcription updated while the user is speaking. */
+    interimInputTranscription?: Transcription;
 }
 
 /** Server will not be able to service client soon. */
@@ -5279,30 +5284,30 @@ declare interface McpServer {
     streamableHttpTransport?: StreamableHttpTransport;
 }
 
-/** Server content modalities. */
+/** The modality that this token count applies to. */
 declare enum MediaModality {
     /**
-     * The modality is unspecified.
+     * When a modality is not specified, it is treated as `TEXT`.
      */
     MODALITY_UNSPECIFIED = "MODALITY_UNSPECIFIED",
     /**
-     * Plain text.
+     * The `Part` contains plain text.
      */
     TEXT = "TEXT",
     /**
-     * Images.
+     * The `Part` contains an image.
      */
     IMAGE = "IMAGE",
     /**
-     * Video.
+     * The `Part` contains a video.
      */
     VIDEO = "VIDEO",
     /**
-     * Audio.
+     * The `Part` contains audio.
      */
     AUDIO = "AUDIO",
     /**
-     * Document, e.g. PDF.
+     * The `Part` contains a document, such as a PDF.
      */
     DOCUMENT = "DOCUMENT"
 }
@@ -5351,9 +5356,9 @@ declare enum Modality {
     VIDEO = "VIDEO"
 }
 
-/** Represents token counting info for a single modality. */
+/** Represents a breakdown of token usage by modality. This message is used in CountTokensResponse and GenerateContentResponse.UsageMetadata to provide a detailed view of how many tokens are used by each modality (e.g., text, image, video) in a request. This is particularly useful for multimodal models, allowing you to track and manage token consumption for billing and quota purposes. */
 declare interface ModalityTokenCount {
-    /** The modality associated with this token count. */
+    /** The modality that this token count applies to. */
     modality?: MediaModality;
     /** The number of tokens counted for this modality. */
     tokenCount?: number;
@@ -6762,7 +6767,7 @@ declare type SpeechConfigUnion = SpeechConfig | string;
 /** Start of speech sensitivity. */
 declare enum StartSensitivity {
     /**
-     * The default is START_SENSITIVITY_LOW.
+     * The default is START_SENSITIVITY_LOW for Gemini Enterprise Agent Platform and START_SENSITIVITY_HIGH for Gemini Live.
      */
     START_SENSITIVITY_UNSPECIFIED = "START_SENSITIVITY_UNSPECIFIED",
     /**
@@ -7156,7 +7161,7 @@ declare enum TrafficType {
     PROVISIONED_THROUGHPUT = "PROVISIONED_THROUGHPUT"
 }
 
-/** Audio transcription in Server Conent. */
+/** Audio transcription in Server Content. */
 declare interface Transcription {
     /** Optional. Transcription text. */
     text?: string;
@@ -7657,9 +7662,10 @@ declare namespace types {
         UrlRetrievalStatus,
         BlockedReason,
         TrafficType,
-        Modality,
+        MediaModality,
         ModelStage,
         MediaResolution,
+        Modality,
         TuningMode,
         AdapterSize,
         JobState,
@@ -7670,10 +7676,10 @@ declare namespace types {
         TuningTask,
         VideoOrientation,
         DocumentState,
+        ServiceTier,
         PartMediaResolutionLevel,
         ToolType,
         ResourceScope,
-        ServiceTier,
         FeatureSelectionPreference,
         EmbeddingApiType,
         SafetyFilterLevel,
@@ -7694,7 +7700,6 @@ declare namespace types {
         FileState,
         FileSource,
         TurnCompleteReason,
-        MediaModality,
         VadSignalType,
         VoiceActivityType,
         StartSensitivity,
@@ -8093,6 +8098,8 @@ declare namespace types {
         SessionResumptionConfig,
         SlidingWindow,
         ContextWindowCompressionConfig,
+        LanguageAuto,
+        LanguageHints,
         AudioTranscriptionConfig,
         ProactivityConfig,
         CustomizedAvatar,
@@ -8447,29 +8454,30 @@ declare enum UrlRetrievalStatus {
 
 /** Usage metadata about response(s). */
 declare interface UsageMetadata {
-    /** Number of tokens in the prompt. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content. */
+    /** The total number of tokens in the prompt. This includes any text, images, or other media provided in the request. When `cached_content` is set, this also includes the number of tokens in the cached content. */
     promptTokenCount?: number;
-    /** Number of tokens in the cached part of the prompt (the cached content). */
+    /** Output only. The number of tokens in the cached content that was used for this request. */
     cachedContentTokenCount?: number;
     /** Total number of tokens across all the generated response candidates. */
     responseTokenCount?: number;
-    /** Number of tokens present in tool-use prompt(s). */
+    /** Output only. The number of tokens in the results from tool executions, which are provided back to the model as input, if applicable. */
     toolUsePromptTokenCount?: number;
-    /** Number of tokens of thoughts for thinking models. */
+    /** Output only. The number of tokens that were part of the model's generated "thoughts" output, if applicable. */
     thoughtsTokenCount?: number;
-    /** Total token count for prompt, response candidates, and tool-use prompts(if present). */
+    /** The total number of tokens for the entire request. This is the sum of `prompt_token_count`, `candidates_token_count`, `tool_use_prompt_token_count`, and `thoughts_token_count`. */
     totalTokenCount?: number;
-    /** List of modalities that were processed in the request input. */
+    /** Output only. A detailed breakdown of the token count for each modality in the prompt. */
     promptTokensDetails?: ModalityTokenCount[];
-    /** List of modalities that were processed in the cache input. */
+    /** Output only. A detailed breakdown of the token count for each modality in the cached content. */
     cacheTokensDetails?: ModalityTokenCount[];
     /** List of modalities that were returned in the response. */
     responseTokensDetails?: ModalityTokenCount[];
-    /** List of modalities that were processed in the tool-use prompt. */
+    /** Output only. A detailed breakdown by modality of the token counts from the results of tool executions, which are provided back to the model as input. */
     toolUsePromptTokensDetails?: ModalityTokenCount[];
-    /** Traffic type. This shows whether a request consumes Pay-As-You-Go
-     or Provisioned Throughput quota. */
+    /** Output only. The traffic type for this request. This field is not supported in Gemini API. */
     trafficType?: TrafficType;
+    /** Output only. Service tier of the request. This field is not supported in Vertex AI. */
+    serviceTier?: ServiceTier;
 }
 
 /** The type of the VAD signal. */
@@ -8745,6 +8753,8 @@ declare enum VideoOrientation {
 declare interface VoiceActivity {
     /** The type of the voice activity signal. */
     voiceActivityType?: VoiceActivityType;
+    /** The time voice activity detected in audio time, relative to the start of the audio stream. */
+    audioOffset?: string;
 }
 
 declare interface VoiceActivityDetectionSignal {

package/dist/vertex_internal/index.js

@@ -944,30 +944,34 @@ var TrafficType;
      */
     TrafficType["PROVISIONED_THROUGHPUT"] = "PROVISIONED_THROUGHPUT";
 })(TrafficType || (TrafficType = {}));
-/** Server content modalities. */
-var Modality;
-(function (Modality) {
+/** The modality that this token count applies to. */
+var MediaModality;
+(function (MediaModality) {
     /**
-     * The modality is unspecified.
+     * When a modality is not specified, it is treated as `TEXT`.
      */
-    Modality["MODALITY_UNSPECIFIED"] = "MODALITY_UNSPECIFIED";
+    MediaModality["MODALITY_UNSPECIFIED"] = "MODALITY_UNSPECIFIED";
     /**
-     * Indicates the model should return text
+     * The `Part` contains plain text.
      */
-    Modality["TEXT"] = "TEXT";
+    MediaModality["TEXT"] = "TEXT";
     /**
-     * Indicates the model should return images.
+     * The `Part` contains an image.
      */
-    Modality["IMAGE"] = "IMAGE";
+    MediaModality["IMAGE"] = "IMAGE";
     /**
-     * Indicates the model should return audio.
+     * The `Part` contains a video.
      */
-    Modality["AUDIO"] = "AUDIO";
+    MediaModality["VIDEO"] = "VIDEO";
     /**
-     * Indicates the model should return video.
+     * The `Part` contains audio.
      */
-    Modality["VIDEO"] = "VIDEO";
-})(Modality || (Modality = {}));
+    MediaModality["AUDIO"] = "AUDIO";
+    /**
+     * The `Part` contains a document, such as a PDF.
+     */
+    MediaModality["DOCUMENT"] = "DOCUMENT";
+})(MediaModality || (MediaModality = {}));
 /** The stage of the underlying model. This enum is not supported in Vertex AI. */
 var ModelStage;
 (function (ModelStage) {
@@ -1024,6 +1028,30 @@ var MediaResolution;
      */
     MediaResolution["MEDIA_RESOLUTION_HIGH"] = "MEDIA_RESOLUTION_HIGH";
 })(MediaResolution || (MediaResolution = {}));
+/** Server content modalities. */
+var Modality;
+(function (Modality) {
+    /**
+     * The modality is unspecified.
+     */
+    Modality["MODALITY_UNSPECIFIED"] = "MODALITY_UNSPECIFIED";
+    /**
+     * Indicates the model should return text
+     */
+    Modality["TEXT"] = "TEXT";
+    /**
+     * Indicates the model should return images.
+     */
+    Modality["IMAGE"] = "IMAGE";
+    /**
+     * Indicates the model should return audio.
+     */
+    Modality["AUDIO"] = "AUDIO";
+    /**
+     * Indicates the model should return video.
+     */
+    Modality["VIDEO"] = "VIDEO";
+})(Modality || (Modality = {}));
 /** Tuning mode. This enum is not supported in Gemini API. */
 var TuningMode;
 (function (TuningMode) {
@@ -1292,6 +1320,26 @@ var DocumentState;
      */
     DocumentState["STATE_FAILED"] = "STATE_FAILED";
 })(DocumentState || (DocumentState = {}));
+/** Pricing and performance service tier. */
+var ServiceTier;
+(function (ServiceTier) {
+    /**
+     * Default service tier, which is standard.
+     */
+    ServiceTier["UNSPECIFIED"] = "unspecified";
+    /**
+     * Flex service tier.
+     */
+    ServiceTier["FLEX"] = "flex";
+    /**
+     * Standard service tier.
+     */
+    ServiceTier["STANDARD"] = "standard";
+    /**
+     * Priority service tier.
+     */
+    ServiceTier["PRIORITY"] = "priority";
+})(ServiceTier || (ServiceTier = {}));
 /** The tokenization quality used for given media. */
 var PartMediaResolutionLevel;
 (function (PartMediaResolutionLevel) {
@@ -1356,26 +1404,6 @@ var ResourceScope;
      */
     ResourceScope["COLLECTION"] = "COLLECTION";
 })(ResourceScope || (ResourceScope = {}));
-/** Pricing and performance service tier. */
-var ServiceTier;
-(function (ServiceTier) {
-    /**
-     * Default service tier, which is standard.
-     */
-    ServiceTier["UNSPECIFIED"] = "unspecified";
-    /**
-     * Flex service tier.
-     */
-    ServiceTier["FLEX"] = "flex";
-    /**
-     * Standard service tier.
-     */
-    ServiceTier["STANDARD"] = "standard";
-    /**
-     * Priority service tier.
-     */
-    ServiceTier["PRIORITY"] = "priority";
-})(ServiceTier || (ServiceTier = {}));
 /** Options for feature selection preference. */
 var FeatureSelectionPreference;
 (function (FeatureSelectionPreference) {
@@ -1760,34 +1788,6 @@ var TurnCompleteReason;
      */
     TurnCompleteReason["MAX_REGENERATION_REACHED"] = "MAX_REGENERATION_REACHED";
 })(TurnCompleteReason || (TurnCompleteReason = {}));
-/** Server content modalities. */
-var MediaModality;
-(function (MediaModality) {
-    /**
-     * The modality is unspecified.
-     */
-    MediaModality["MODALITY_UNSPECIFIED"] = "MODALITY_UNSPECIFIED";
-    /**
-     * Plain text.
-     */
-    MediaModality["TEXT"] = "TEXT";
-    /**
-     * Images.
-     */
-    MediaModality["IMAGE"] = "IMAGE";
-    /**
-     * Video.
-     */
-    MediaModality["VIDEO"] = "VIDEO";
-    /**
-     * Audio.
-     */
-    MediaModality["AUDIO"] = "AUDIO";
-    /**
-     * Document, e.g. PDF.
-     */
-    MediaModality["DOCUMENT"] = "DOCUMENT";
-})(MediaModality || (MediaModality = {}));
 /** The type of the VAD signal. */
 var VadSignalType;
 (function (VadSignalType) {
@@ -1824,7 +1824,7 @@ var VoiceActivityType;
 var StartSensitivity;
 (function (StartSensitivity) {
     /**
-     * The default is START_SENSITIVITY_LOW.
+     * The default is START_SENSITIVITY_LOW for Gemini Enterprise Agent Platform and START_SENSITIVITY_HIGH for Gemini Live.
      */
     StartSensitivity["START_SENSITIVITY_UNSPECIFIED"] = "START_SENSITIVITY_UNSPECIFIED";
     /**
@@ -1840,7 +1840,7 @@ var StartSensitivity;
 var EndSensitivity;
 (function (EndSensitivity) {
     /**
-     * The default is END_SENSITIVITY_LOW.
+     * The default is END_SENSITIVITY_LOW for Gemini Enterprise Agent Platform and END_SENSITIVITY_HIGH for Gemini Live.
      */
     EndSensitivity["END_SENSITIVITY_UNSPECIFIED"] = "END_SENSITIVITY_UNSPECIFIED";
     /**
@@ -2146,7 +2146,7 @@ const CONTENT_TYPE_HEADER = 'Content-Type';
 const SERVER_TIMEOUT_HEADER = 'X-Server-Timeout';
 const USER_AGENT_HEADER = 'User-Agent';
 const GOOGLE_API_CLIENT_HEADER = 'x-goog-api-client';
-const SDK_VERSION = '2.8.0'; // x-release-please-version
+const SDK_VERSION = '2.9.0'; // x-release-please-version
 const LIBRARY_LABEL = `google-genai-sdk/${SDK_VERSION}`;
 const VERTEX_AI_API_DEFAULT_VERSION = 'v1beta1';
 const GOOGLE_AI_API_DEFAULT_VERSION = 'v1beta';