@google/genai 2.9.0 → 2.11.0

package/dist/tokenizer/node.d.ts

@@ -40,6 +40,82 @@ declare enum ApiSpec {
     ELASTIC_SEARCH = "ELASTIC_SEARCH"
 }
 
+/** The aspect ratio for the image output. */
+declare enum AspectRatio {
+    /**
+     * Default value. This value is unused.
+     */
+    ASPECT_RATIO_UNSPECIFIED = "ASPECT_RATIO_UNSPECIFIED",
+    /**
+     * 1:1 aspect ratio.
+     */
+    ASPECT_RATIO_ONE_BY_ONE = "ASPECT_RATIO_ONE_BY_ONE",
+    /**
+     * 2:3 aspect ratio.
+     */
+    ASPECT_RATIO_TWO_BY_THREE = "ASPECT_RATIO_TWO_BY_THREE",
+    /**
+     * 3:2 aspect ratio.
+     */
+    ASPECT_RATIO_THREE_BY_TWO = "ASPECT_RATIO_THREE_BY_TWO",
+    /**
+     * 3:4 aspect ratio.
+     */
+    ASPECT_RATIO_THREE_BY_FOUR = "ASPECT_RATIO_THREE_BY_FOUR",
+    /**
+     * 4:3 aspect ratio.
+     */
+    ASPECT_RATIO_FOUR_BY_THREE = "ASPECT_RATIO_FOUR_BY_THREE",
+    /**
+     * 4:5 aspect ratio.
+     */
+    ASPECT_RATIO_FOUR_BY_FIVE = "ASPECT_RATIO_FOUR_BY_FIVE",
+    /**
+     * 5:4 aspect ratio.
+     */
+    ASPECT_RATIO_FIVE_BY_FOUR = "ASPECT_RATIO_FIVE_BY_FOUR",
+    /**
+     * 9:16 aspect ratio.
+     */
+    ASPECT_RATIO_NINE_BY_SIXTEEN = "ASPECT_RATIO_NINE_BY_SIXTEEN",
+    /**
+     * 16:9 aspect ratio.
+     */
+    ASPECT_RATIO_SIXTEEN_BY_NINE = "ASPECT_RATIO_SIXTEEN_BY_NINE",
+    /**
+     * 21:9 aspect ratio.
+     */
+    ASPECT_RATIO_TWENTY_ONE_BY_NINE = "ASPECT_RATIO_TWENTY_ONE_BY_NINE",
+    /**
+     * 1:8 aspect ratio.
+     */
+    ASPECT_RATIO_ONE_BY_EIGHT = "ASPECT_RATIO_ONE_BY_EIGHT",
+    /**
+     * 8:1 aspect ratio.
+     */
+    ASPECT_RATIO_EIGHT_BY_ONE = "ASPECT_RATIO_EIGHT_BY_ONE",
+    /**
+     * 1:4 aspect ratio.
+     */
+    ASPECT_RATIO_ONE_BY_FOUR = "ASPECT_RATIO_ONE_BY_FOUR",
+    /**
+     * 4:1 aspect ratio.
+     */
+    ASPECT_RATIO_FOUR_BY_ONE = "ASPECT_RATIO_FOUR_BY_ONE"
+}
+
+/** Configuration for audio-specific output formatting. */
+declare class AudioResponseFormat {
+    /** Optional. Bit rate in bits per second (bps). Only applicable for compressed formats (MP3, Opus). */
+    bitRate?: number;
+    /** Optional. Delivery mode for the generated content. */
+    delivery?: Delivery;
+    /** Optional. The MIME type of the audio output. */
+    mimeType?: string;
+    /** Optional. Sample rate for the generated audio in Hertz. */
+    sampleRate?: number;
+}
+
 /** The authentication config to access the API. */
 declare interface AuthConfig {
     /** The authentication config to access the API. Only API key is supported. This field is not supported in Gemini API. */
@@ -115,7 +191,7 @@ declare enum AuthType {
     OIDC_AUTH = "OIDC_AUTH"
 }
 
-/** Specifies the function Behavior. Currently only non-blocking functions are supported. If not specified, the system keeps the current function call behavior. This field is currently only supported by the BidiGenerateContent method. */
+/** Specifies the function Behavior. If not specified, the system keeps the current function call behavior. This field is currently only supported by the BidiGenerateContent method. */
 declare enum Behavior {
     /**
      * This value is unspecified.
@@ -156,15 +232,12 @@ declare interface CodeExecutionResult {
 declare interface ComputerUse {
     /** Required. The environment being operated. */
     environment?: Environment;
-    /** By default, predefined functions are included in the final model call.
-     Some of them can be explicitly excluded from being automatically included.
-     This can serve two purposes:
-     1. Using a more restricted / different action space.
-     2. Improving the definitions / instructions of predefined functions. */
+    /** Optional. By default, [predefined functions](https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use#supported-actions) are included in the final model call. Some of them can be explicitly excluded from being automatically included. This can serve two purposes: 1. Using a more restricted / different action space. 2. Improving the definitions / instructions of predefined functions. */
     excludedPredefinedFunctions?: string[];
-    /** Optional. Whether enable the prompt injection detection check on computer-use request.
-     */
+    /** Optional. Enables the prompt injection detection check on computer-use request. */
     enablePromptInjectionDetection?: boolean;
+    /** Optional. Disabled safety policies for computer use. This field is not supported in Vertex AI. */
+    disabledSafetyPolicies?: SafetyPolicy[];
 }
 
 /** Local tokenizer compute tokens result. */
@@ -216,6 +289,22 @@ export declare interface CountTokensResult {
     totalTokens?: number;
 }
 
+/** Delivery mode for the generated content. */
+declare enum Delivery {
+    /**
+     * Default value. This value is unused.
+     */
+    DELIVERY_UNSPECIFIED = "DELIVERY_UNSPECIFIED",
+    /**
+     * Generated bytes are returned inline in the response.
+     */
+    INLINE = "INLINE",
+    /**
+     * Generated content is stored and a URI is returned.
+     */
+    URI = "URI"
+}
+
 /** Describes the options to customize dynamic retrieval. */
 declare interface DynamicRetrievalConfig {
     /** Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used. */
@@ -360,7 +449,7 @@ declare interface FunctionDeclaration {
     response?: Schema;
     /** Optional. Describes the output from this function in JSON Schema format. The value specified by the schema is the response value of the function. This field is mutually exclusive with `response`. */
     responseJsonSchema?: unknown;
-    /** Optional. Specifies the function Behavior. Currently only non-blocking functions are supported. If not specified, the system keeps the current function call behavior. This field is currently only supported by the BidiGenerateContent method. */
+    /** Optional. Specifies the function Behavior. If not specified, the system keeps the current function call behavior. This field is currently only supported by the BidiGenerateContent method. */
     behavior?: Behavior;
 }
 
@@ -455,11 +544,11 @@ declare interface GenerationConfig {
     presencePenalty?: number;
     /** Optional. If set to true, the log probabilities of the output tokens are returned. Log probabilities are the logarithm of the probability of a token appearing in the output. A higher log probability means the token is more likely to be generated. This can be useful for analyzing the model's confidence in its own output and for debugging. */
     responseLogprobs?: boolean;
-    /** Optional. The IANA standard MIME type of the response. The model will generate output that conforms to this MIME type. Supported values include 'text/plain' (default) and 'application/json'. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. */
+    /** Optional. The IANA standard MIME type of the response. The model will generate output that conforms to this MIME type. Supported values include 'text/plain' (default) and 'application/json'. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. Deprecated: Use `response_format` instead. */
     responseMimeType?: string;
     /** Optional. The modalities of the response. The model will generate a response that includes all the specified modalities. For example, if this is set to `[TEXT, IMAGE]`, the response will include both text and an image. */
     responseModalities?: Modality[];
-    /** Optional. Lets you to specify a schema for the model's response, ensuring that the output conforms to a particular structure. This is useful for generating structured data such as JSON. The schema is a subset of the [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema) object. When this field is set, you must also set the `response_mime_type` to `application/json`. */
+    /** Optional. Lets you to specify a schema for the model's response, ensuring that the output conforms to a particular structure. This is useful for generating structured data such as JSON. The schema is a subset of the [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema) object. When this field is set, you must also set the `response_mime_type` to `application/json`. Deprecated: Use `response_format` instead. */
     responseSchema?: Schema;
     /** Optional. Routing configuration. This field is not supported in Gemini API. */
     routingConfig?: GenerationConfigRoutingConfig;
@@ -479,6 +568,10 @@ declare interface GenerationConfig {
     topP?: number;
     /** Optional. Enables enhanced civic answers. It may not be available for all models. This field is not supported in Vertex AI. */
     enableEnhancedCivicAnswers?: boolean;
+    /** Optional. New response format field for the model to configure output formatting and delivery. */
+    responseFormat?: ResponseFormat[];
+    /** Optional. Config for translation. This field is not supported in Vertex AI. */
+    translationConfig?: TranslationConfig;
 }
 
 /** The configuration for routing the request to a specific model. This can be used to control which model is used for the generation, either automatically or by specifying a model name. This data type is not supported in Gemini API. */
@@ -580,10 +673,46 @@ declare interface HttpRetryOptions {
     attempts?: number;
 }
 
+/** Configuration for image-specific output formatting. */
+declare class ImageResponseFormat {
+    /** Optional. The aspect ratio for the image output. */
+    aspectRatio?: AspectRatio;
+    /** Optional. Delivery mode for the generated content. */
+    delivery?: Delivery;
+    /** Optional. The size of the image output. */
+    imageSize?: ImageSize;
+    /** Optional. The MIME type of the image output. */
+    mimeType?: string;
+}
+
 /** Image search for grounding and related configurations. */
 declare interface ImageSearch {
 }
 
+/** The size of the image output. */
+declare enum ImageSize {
+    /**
+     * Default value. This value is unused.
+     */
+    IMAGE_SIZE_UNSPECIFIED = "IMAGE_SIZE_UNSPECIFIED",
+    /**
+     * 512px image size.
+     */
+    IMAGE_SIZE_FIVE_TWELVE = "IMAGE_SIZE_FIVE_TWELVE",
+    /**
+     * 1K image size.
+     */
+    IMAGE_SIZE_ONE_K = "IMAGE_SIZE_ONE_K",
+    /**
+     * 2K image size.
+     */
+    IMAGE_SIZE_TWO_K = "IMAGE_SIZE_TWO_K",
+    /**
+     * 4K image size.
+     */
+    IMAGE_SIZE_FOUR_K = "IMAGE_SIZE_FOUR_K"
+}
+
 /** Represents a time interval, encoded as a Timestamp start (inclusive) and a Timestamp end (exclusive). The start must be less than or equal to the end. When the start equals the end, the interval is empty (matches no time). When both start and end are unspecified, the interval matches any time. */
 declare interface Interval {
     /** Optional. Exclusive end of the interval. If specified, a Timestamp matching this interval will have to be before the end. */
@@ -917,6 +1046,17 @@ declare interface ReplicatedVoiceConfig {
 
      * @remarks Encoded as base64 string. */
     voiceSampleAudio?: string;
+    /** Recorded consent verifying ownership of the voice. This
+     represents 16-bit signed little-endian wav data, with a 24kHz sampling
+     rate.
+     * @remarks Encoded as base64 string. */
+    consentAudio?: string;
+    /** Signature of a previously verified consent audio. This should be
+     populated with a signature generated by the server for a previous
+     request containing the consent_audio field. When provided, the
+     signature is verified instead of the consent_audio field to reduce
+     latency. Requests will fail if the signature is invalid or expired. */
+    voiceConsentSignature?: VoiceConsentSignature;
 }
 
 /** Resource scope. */
@@ -931,6 +1071,18 @@ declare enum ResourceScope {
     COLLECTION = "COLLECTION"
 }
 
+/** Configuration for the model to configure output formatting and delivery. This data type is not supported in Gemini API. */
+declare class ResponseFormat {
+    /** Audio output format. */
+    audio?: AudioResponseFormat;
+    /** Image output format. */
+    image?: ImageResponseFormat;
+    /** Text output format. */
+    text?: TextResponseFormat;
+    /** Video output format. */
+    video?: VideoResponseFormat;
+}
+
 /** Defines a retrieval tool that model can call to access external knowledge. This data type is not supported in Gemini API. */
 declare interface Retrieval {
     /** Optional. Deprecated. This option is no longer supported. */
@@ -943,6 +1095,42 @@ declare interface Retrieval {
     vertexRagStore?: VertexRagStore;
 }
 
+/** SafetyPolicy */
+declare enum SafetyPolicy {
+    /**
+     * Unspecified safety policy.
+     */
+    SAFETY_POLICY_UNSPECIFIED = "SAFETY_POLICY_UNSPECIFIED",
+    /**
+     * Safety policy for financial transactions.
+     */
+    FINANCIAL_TRANSACTIONS = "FINANCIAL_TRANSACTIONS",
+    /**
+     * Safety policy for sensitive data modification.
+     */
+    SENSITIVE_DATA_MODIFICATION = "SENSITIVE_DATA_MODIFICATION",
+    /**
+     * Safety policy for communication tools (e.g. Gmail, Chat, Meet).
+     */
+    COMMUNICATION_TOOL = "COMMUNICATION_TOOL",
+    /**
+     * Safety policy for account creation.
+     */
+    ACCOUNT_CREATION = "ACCOUNT_CREATION",
+    /**
+     * Safety policy for data modification.
+     */
+    DATA_MODIFICATION = "DATA_MODIFICATION",
+    /**
+     * Safety policy for user consent management.
+     */
+    USER_CONSENT_MANAGEMENT = "USER_CONSENT_MANAGEMENT",
+    /**
+     * Safety policy for legal terms and agreements.
+     */
+    LEGAL_TERMS_AND_AGREEMENTS = "LEGAL_TERMS_AND_AGREEMENTS"
+}
+
 /** Schema is used to define the format of input/output data.
 
  Represents a select subset of an [OpenAPI 3.0 schema
@@ -1035,6 +1223,14 @@ declare interface StreamableHttpTransport {
     url?: string;
 }
 
+/** Configuration for text-specific output formatting. */
+declare class TextResponseFormat {
+    /** Optional. The IANA standard MIME type of the response. */
+    mimeType?: string;
+    /** Optional. The JSON schema that the output should conform to. Only applicable when mime_type is APPLICATION_JSON. */
+    schema?: unknown;
+}
+
 /** The thinking features configuration. */
 declare interface ThinkingConfig {
     /** Indicates whether to include thoughts in the response. If true, thoughts are returned only if the model supports thought and thoughts are available.
@@ -1086,9 +1282,7 @@ export declare interface TokensInfo {
 declare interface Tool {
     /** Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. This field is not supported in Gemini API. */
     retrieval?: Retrieval;
-    /** Optional. Tool to support the model interacting directly with the
-     computer. If enabled, it automatically populates computer-use specific
-     Function Declarations. */
+    /** Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. */
     computerUse?: ComputerUse;
     /** Optional. FileSearch tool type. Tool to retrieve knowledge from Semantic Retrieval corpora. This field is not supported in Vertex AI. */
     fileSearch?: FileSearch;
@@ -1111,6 +1305,8 @@ declare interface Tool {
     urlContext?: UrlContext;
     /** Optional. MCP Servers to connect to. This field is not supported in Vertex AI. */
     mcpServers?: McpServer[];
+    /** Optional. Uses Exa.ai to search for information to answer user queries. The search results will be grounded on Exa.ai and presented to the model for response generation. This field is not supported in Gemini API. */
+    exaAiSearch?: ToolExaAiSearch;
 }
 
 /** A predicted server-side `ToolCall` returned from the model.
@@ -1132,6 +1328,14 @@ declare interface ToolCall {
 declare interface ToolCodeExecution {
 }
 
+/** ExaAiSearch tool type. A tool that uses the Exa.ai search engine for grounding. This data type is not supported in Gemini API. */
+declare interface ToolExaAiSearch {
+    /** Required. The API key for ExaAiSearch. */
+    apiKey?: string;
+    /** Optional. This field can be used to pass any parameter from the Exa.ai Search API. */
+    customConfigs?: Record<string, unknown>;
+}
+
 /** ParallelAiSearch tool type. A tool that uses the Parallel.ai search engine for grounding. This data type is not supported in Gemini API. */
 declare interface ToolParallelAiSearch {
     /** Optional. The API key for ParallelAiSearch. If an API key is not provided, the system will attempt to verify access by checking for an active Parallel.ai subscription through the Google Cloud Marketplace. See https://docs.parallel.ai/search/search-quickstart for more details. */
@@ -1183,6 +1387,14 @@ declare enum ToolType {
     FILE_SEARCH = "FILE_SEARCH"
 }
 
+/** Config for stream translation. */
+declare interface TranslationConfig {
+    /** Optional. If true, the model will generate audio when the target language is spoken, essentially it will parrot the input. If false, we will not produce audio for the target language. */
+    echoTargetLanguage?: boolean;
+    /** Required. The target language for translation. Supported values are BCP-47 language codes (e.g. "en", "es", "fr"). */
+    targetLanguageCode?: string;
+}
+
 /** Data type of the schema field. */
 declare enum Type {
     /**
@@ -1279,6 +1491,18 @@ declare interface VideoMetadata {
     startOffset?: string;
 }
 
+/** Configuration for video-specific output formatting. This data type is not supported in Gemini API. */
+declare class VideoResponseFormat {
+    /** The aspect ratio for the video output. */
+    aspectRatio?: AspectRatio;
+    /** Optional. Delivery mode for the generated content. */
+    delivery?: Delivery;
+    /** Optional. The duration for the video output. */
+    duration?: string;
+    /** Optional. The Google Cloud Storage URI to store the video output. Required for Vertex if delivery is URI. */
+    gcsUri?: string;
+}
+
 /** The configuration for the voice to use. */
 declare interface VoiceConfig {
     /** The configuration for a replicated voice, which is a clone of a
@@ -1289,6 +1513,13 @@ declare interface VoiceConfig {
     prebuiltVoiceConfig?: PrebuiltVoiceConfig;
 }
 
+/** The signature of the voice consent check. */
+declare interface VoiceConsentSignature {
+    /** The signature string.
+     */
+    signature?: string;
+}
+
 /** Standard web search for grounding and related configurations. Only text results are returned. */
 declare interface WebSearch {
 }