@langchain/google 0.2.12 → 0.2.13

package/dist/chat_models/api_types/interactions.d.cts

@@ -0,0 +1,1423 @@
+export declare namespace Interactions {
+  /** The Interaction resource. */
+  interface Interaction {
+    /** The agent to interact with. */
+    agent?: AgentOption;
+    /** Configuration parameters for the agent interaction. */
+    agent_config?: AntigravityAgentConfig | CodeMenderAgentConfig | DeepResearchAgentConfig | DynamicAgentConfig;
+    /**
+     * Input only. Whether to run the model interaction in the background.
+     */
+    background?: boolean;
+    /**
+     * The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: cachedContents/{cachedContent}
+     */
+    cached_content?: string;
+    /**
+     * Required. Output only. The time at which the response was created in ISO 8601 format
+     * (YYYY-MM-DDThh:mm:ssZ).
+     */
+    readonly created?: string;
+    /**
+     * The environment configuration for the interaction. Can be an object
+     * specifying remote environment sources or a string referencing an existing
+     * environment ID.
+     */
+    environment?: EnvironmentConfig | string;
+    /**
+     * Output only. The environment ID for the interaction. Only populated if environment
+     * config is set in the request.
+     */
+    readonly environment_id?: string;
+    /**
+     * Output only. Diagnostic faults / platform errors recorded on the interaction.
+     */
+    readonly errors?: Array<Error>;
+    /** Configuration parameters for model interactions. */
+    generation_config?: GenerationConfig;
+    /**
+     * Required. Output only. A unique identifier for the interaction completion.
+     */
+    readonly id?: string;
+    /** The input for the interaction. */
+    input?: InteractionsInput;
+    /**
+     * The labels with user-defined metadata for the request.
+     *
+     * Label keys and values can be no longer than 63 characters
+     * (Unicode codepoints) and can only contain lowercase letters, numeric
+     * characters, underscores, and dashes. International characters are allowed.
+     * Label values are optional. Label keys must start with a letter.
+     */
+    labels?: Record<string, unknown>;
+    /**
+     * The model that will complete your prompt.\n\nSee [models](https://ai.google.dev/gemini-api/docs/models) for additional details.
+     */
+    model?: ModelOption;
+    /** The ID of the previous interaction, if any. */
+    previous_interaction_id?: string;
+    /**
+     * Enforces that the generated response is a JSON object that complies with
+     * the JSON schema specified in this field.
+     */
+    response_format?: ResponseFormat | Array<ResponseFormat>;
+    /**
+     * The mime type of the response. This is required if response_format is set.
+     */
+    response_mime_type?: string;
+    /**
+     * The requested modalities of the response (TEXT, IMAGE, AUDIO).
+     */
+    response_modalities?: Array<ResponseModality>;
+    /** Safety settings for the interaction. */
+    safety_settings?: Array<SafetySetting>;
+    service_tier?: ServiceTier;
+    /** Required. Output only. The status of the interaction. */
+    readonly status: "in_progress" | "requires_action" | "completed" | "failed" | "cancelled" | "incomplete" | "budget_exceeded" | "queued" | (string & {});
+    /**
+     * Required. Output only. The steps that make up the interaction, when included in the response.
+     */
+    readonly steps?: Array<Step>;
+    /**
+     * Input only. Whether to store the response and request for later retrieval.
+     */
+    store?: boolean;
+    /** Input only. Whether the interaction will be streamed. */
+    stream?: boolean;
+    /** System instruction for the interaction. */
+    system_instruction?: string;
+    /**
+     * A list of tool declarations the model may call during interaction.
+     */
+    tools?: Array<Interactions.Tools.Tool>;
+    /**
+     * Required. Output only. The time at which the response was last updated in ISO 8601 format
+     * (YYYY-MM-DDThh:mm:ssZ).
+     */
+    readonly updated?: string;
+    /** Statistics on the interaction request's token usage. */
+    usage?: Usage;
+    /** Message for configuring webhook events for a request. */
+    webhook_config?: WebhookConfig;
+  }
+  /** Interaction for generating the completion using agents. */
+  interface AgentInteraction {
+    /** The agent to interact with. */
+    agent: AgentOption;
+    /** Configuration parameters for the agent interaction. */
+    agent_config?: AntigravityAgentConfig | CodeMenderAgentConfig | DeepResearchAgentConfig | DynamicAgentConfig;
+    /**
+     * Input only. Whether to run the model interaction in the background.
+     */
+    background?: boolean;
+    /**
+     * The environment configuration for the interaction. Can be an object
+     * specifying remote environment sources or a string referencing an existing
+     * environment ID.
+     */
+    environment?: EnvironmentConfig | string;
+    /** The input for the interaction. */
+    input?: InteractionsInput;
+    /**
+     * The labels with user-defined metadata for the request.
+     *
+     * Label keys and values can be no longer than 63 characters
+     * (Unicode codepoints) and can only contain lowercase letters, numeric
+     * characters, underscores, and dashes. International characters are allowed.
+     * Label values are optional. Label keys must start with a letter.
+     */
+    labels?: Record<string, unknown>;
+    /** The ID of the previous interaction, if any. */
+    previous_interaction_id?: string;
+    /**
+     * Enforces that the generated response is a JSON object that complies with
+     * the JSON schema specified in this field.
+     */
+    response_format?: ResponseFormat | Array<ResponseFormat>;
+    /**
+     * The mime type of the response. This is required if response_format is set.
+     */
+    response_mime_type?: string;
+    /**
+     * The requested modalities of the response (TEXT, IMAGE, AUDIO).
+     */
+    response_modalities?: Array<ResponseModality>;
+    /** Safety settings for the interaction. */
+    safety_settings?: Array<SafetySetting>;
+    service_tier?: ServiceTier;
+    /**
+     * Input only. Whether to store the response and request for later retrieval.
+     */
+    store?: boolean;
+    /** Input only. Whether the interaction will be streamed. */
+    stream?: boolean;
+    /** System instruction for the interaction. */
+    system_instruction?: string;
+    /**
+     * A list of tool declarations the model may call during interaction.
+     */
+    tools?: Array<Interactions.Tools.Tool>;
+    /** Message for configuring webhook events for a request. */
+    webhook_config?: WebhookConfig;
+  }
+  /** Interaction for generating the completion using models. */
+  interface ModelInteraction {
+    /**
+     * Input only. Whether to run the model interaction in the background.
+     */
+    background?: boolean;
+    /**
+     * The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: cachedContents/{cachedContent}
+     */
+    cached_content?: string;
+    /**
+     * Required. Output only. The time at which the response was created in ISO 8601 format
+     * (YYYY-MM-DDThh:mm:ssZ).
+     */
+    readonly created: string;
+    /**
+     * The environment configuration for the interaction. Can be an object
+     * specifying remote environment sources or a string referencing an existing
+     * environment ID.
+     */
+    environment?: EnvironmentConfig | string;
+    /**
+     * Output only. The environment ID for the interaction. Only populated if environment
+     * config is set in the request.
+     */
+    readonly environment_id?: string;
+    /** Configuration parameters for model interactions. */
+    generation_config?: GenerationConfig;
+    /**
+     * Required. Output only. A unique identifier for the interaction completion.
+     */
+    readonly id: string;
+    /** The input for the interaction. */
+    input?: InteractionsInput;
+    /**
+     * The labels with user-defined metadata for the request.
+     *
+     * Label keys and values can be no longer than 63 characters
+     * (Unicode codepoints) and can only contain lowercase letters, numeric
+     * characters, underscores, and dashes. International characters are allowed.
+     * Label values are optional. Label keys must start with a letter.
+     */
+    labels?: Record<string, unknown>;
+    /**
+     * The model that will complete your prompt.\n\nSee [models](https://ai.google.dev/gemini-api/docs/models) for additional details.
+     */
+    model: ModelOption;
+    /** The ID of the previous interaction, if any. */
+    previous_interaction_id?: string;
+    /**
+     * Enforces that the generated response is a JSON object that complies with
+     * the JSON schema specified in this field.
+     */
+    response_format?: ResponseFormat | Array<ResponseFormat>;
+    /**
+     * The mime type of the response. This is required if response_format is set.
+     */
+    response_mime_type?: string;
+    /**
+     * The requested modalities of the response (TEXT, IMAGE, AUDIO).
+     */
+    response_modalities?: Array<ResponseModality>;
+    /** Safety settings for the interaction. */
+    safety_settings?: Array<SafetySetting>;
+    service_tier?: ServiceTier;
+    /** Required. Output only. The status of the interaction. */
+    readonly status: "in_progress" | "requires_action" | "completed" | "failed" | "cancelled" | "incomplete" | "budget_exceeded" | "queued" | (string & {});
+    /**
+     * Input only. Whether to store the response and request for later retrieval.
+     */
+    store?: boolean;
+    /** Input only. Whether the interaction will be streamed. */
+    stream?: boolean;
+    /** System instruction for the interaction. */
+    system_instruction?: string;
+    /**
+     * A list of tool declarations the model may call during interaction.
+     */
+    tools?: Array<Interactions.Tools.Tool>;
+    /**
+     * Required. Output only. The time at which the response was last updated in ISO 8601 format
+     * (YYYY-MM-DDThh:mm:ssZ).
+     */
+    readonly updated: string;
+    /** Message for configuring webhook events for a request. */
+    webhook_config?: WebhookConfig;
+  }
+  /** The agent to interact with. */
+  type AgentOption = "deep-research-pro-preview-12-2025" | "deep-research-preview-04-2026" | "deep-research-max-preview-04-2026" | "antigravity-preview-05-2026" | (string & {});
+  /**
+   * Configuration for the Antigravity agent runtime.
+   * Provides server-side control over the agent's execution environment
+   * and tool configuration.
+   */
+  interface AntigravityAgentConfig {
+    /** Max total tokens for the agent run. */
+    max_total_tokens?: string;
+    /** The model to use for agent reasoning. */
+    model?: string;
+    type: unknown;
+  }
+  /** Configuration for the CodeMender agent. */
+  interface CodeMenderAgentConfig {
+    /**
+     * Request parameters specific to FIND sessions, used for discovering
+     * vulnerabilities in a codebase.
+     */
+    find_request?: FindRequest;
+    /**
+     * Request parameters specific to FIX sessions, used for generating and
+     * validating security patches.
+     */
+    fix_request?: FixRequest;
+    /**
+     * The name of the model to use for the CodeMender agent. One
+     * CodeMender session will only use one model.
+     */
+    model?: string;
+    /** The configuration of CodeMender sessions. */
+    session_config?: SessionConfig;
+    /**
+     * Parameter for grouping multiple interactions that belong to
+     * the same CodeMender session.
+     */
+    session_id?: string;
+    type: unknown;
+  }
+  /** Configuration for the Deep Research agent. */
+  interface DeepResearchAgentConfig {
+    /**
+     * Enables human-in-the-loop planning for the Deep Research agent. If set to
+     * true, the Deep Research agent will provide a research plan in its response.
+     * The agent will then proceed only if the user confirms the plan in the next
+     * turn.
+     */
+    collaborative_planning?: boolean;
+    /** Enables bigquery tool for the Deep Research agent. */
+    enable_bigquery_tool?: boolean;
+    thinking_summaries?: ThinkingSummaries;
+    type: unknown;
+    /** Whether to include visualizations in the response. */
+    visualization?: "off" | "auto" | (string & {});
+  }
+  /** Configuration for dynamic agents. */
+  interface DynamicAgentConfig {
+    type: unknown;
+  }
+  /** Configuration for a custom environment. */
+  interface EnvironmentConfig {
+    /** Environment variables to set in the sandbox environment. */
+    env?: Record<string, unknown>;
+    /**
+     * Optional. The environment ID for the interaction. If specified, the request will
+     * update the existing environment instead of creating a new one.
+     */
+    environment_id?: string;
+    /** Network configuration for the environment. */
+    network?: EnvironmentNetworkEgressAllowlist | "disabled" | (string & {});
+    sources?: Array<Source>;
+    type: unknown;
+  }
+  /** Error message from an interaction. */
+  interface Error {
+    /** A URI that identifies the error type. */
+    code?: string;
+    /** A human-readable error message. */
+    message?: string;
+  }
+  /** Configuration parameters for model interactions. */
+  interface GenerationConfig {
+    /** The configuration for image interaction. */
+    image_config?: ImageConfig;
+    /** The maximum number of tokens to include in the response. */
+    max_output_tokens?: number;
+    /** Seed used in decoding for reproducibility. */
+    seed?: number;
+    /** Optional. Speech and multi-speaker configuration. */
+    speech_config?: SpeakerConfig | Array<SpeechConfig>;
+    /**
+     * A list of character sequences that will stop output interaction.
+     */
+    stop_sequences?: Array<string>;
+    /** Controls the randomness of the output. */
+    temperature?: number;
+    thinking_level?: ThinkingLevel;
+    thinking_summaries?: ThinkingSummaries;
+    /** The tool choice configuration. */
+    tool_choice?: ToolChoiceConfig | "auto" | "any" | "none" | "validated" | (string & {});
+    /**
+     * The maximum cumulative probability of tokens to consider when sampling.
+     */
+    top_p?: number;
+    /** Configuration for speech recognition (transcription). */
+    transcription_config?: TranscriptionConfig;
+    /** Configuration options for video generation. */
+    video_config?: VideoConfig;
+  }
+  /** The input for the interaction. */
+  type InteractionsInput = Content | Array<Step> | Array<Content> | string;
+  /**
+   * The model that will complete your prompt.\n\nSee [models](https://ai.google.dev/gemini-api/docs/models) for additional details.
+   */
+  type ModelOption = "gemma-4-26b-a4b-it" | "gemma-4-31b-it" | "gemini-flash-latest" | "gemini-flash-lite-latest" | "gemini-pro-latest" | "gemini-2.5-flash" | "gemini-2.5-pro" | "gemini-2.5-flash-lite" | "gemini-3.5-flash-lite" | "gemini-2.5-flash-image" | "gemini-3-flash-preview" | "gemini-3.1-pro-preview" | "gemini-3.1-pro-preview-customtools" | "gemini-3.1-flash-lite" | "gemini-3.1-flash-lite-image" | "gemini-3-pro-image" | "nano-banana-pro-preview" | "gemini-3.1-flash-image" | "gemini-nano-banana-2.1" | "gemini-3.1-flash-tts-preview" | "gemini-3.5-flash" | "gemini-3.6-flash" | "gemini-3.7-flash" | "gemini-3.8-flash" | "gemini-4-argon" | "gemini-3.8-flash-tts" | "gemini-3.8-flash-lite-tts" | "lyria-3-clip-preview" | "lyria-3-pro-preview" | "gemini-robotics-er-1.6-preview" | "gemini-robotics-er-2-preview" | "lyria-3.5" | "gemini-omni-1.1-flash" | "gemini-omni-flash-preview" | (string & {});
+  type ResponseFormat = AudioResponseFormat | ImageResponseFormat | TextResponseFormat | VideoResponseFormat | Record<string, unknown>;
+  type ResponseModality = "text" | "image" | "audio" | "video" | "document" | (string & {});
+  /**
+   * A safety setting that affects the safety-blocking behavior.
+   *
+   * A SafetySetting consists of a
+   * harm category and a
+   * threshold for that
+   * category.
+   */
+  interface SafetySetting {
+    /**
+     * Optional. The method for blocking content. If not specified, the default
+     * behavior is to use the probability score.
+     */
+    method?: "severity" | "probability" | (string & {});
+    /**
+     * Required. The threshold for blocking content. If the harm probability
+     * exceeds this threshold, the content will be blocked.
+     */
+    threshold: "block_low_and_above" | "block_medium_and_above" | "block_only_high" | "block_none" | "off" | (string & {});
+    type: HarmCategory;
+  }
+  type ServiceTier = "flex" | "standard" | "priority" | "deferred" | (string & {});
+  /** A step in the interaction. */
+  type Step = CodeExecutionCallStep | CodeExecutionResultStep | FileSearchCallStep | FileSearchResultStep | FunctionCallStep | FunctionResultStep | GoogleMapsCallStep | GoogleMapsResultStep | GoogleSearchCallStep | GoogleSearchResultStep | McpServerToolCallStep | McpServerToolResultStep | ModelOutputStep | ProcessingCallStep | ProcessingResultStep | RetrievalCallStep | RetrievalResultStep | ThoughtStep | UrlContextCallStep | UrlContextResultStep | UserInputStep;
+  /** Statistics on the interaction request's token usage. */
+  interface Usage {
+    /** A breakdown of cached token usage by modality. */
+    cached_tokens_by_modality?: Array<ModalityTokens>;
+    /** Grounding tool count. */
+    grounding_tool_count?: Array<GroundingToolCount>;
+    /** A breakdown of input token usage by modality. */
+    input_tokens_by_modality?: Array<ModalityTokens>;
+    /** A breakdown of output token usage by modality. */
+    output_tokens_by_modality?: Array<ModalityTokens>;
+    /** A breakdown of tool-use token usage by modality. */
+    tool_use_tokens_by_modality?: Array<ModalityTokens>;
+    /**
+     * Number of tokens in the cached part of the prompt (the cached content).
+     */
+    total_cached_tokens?: number;
+    /** Number of tokens in the prompt (context). */
+    total_input_tokens?: number;
+    /** Total number of tokens across all the generated responses. */
+    total_output_tokens?: number;
+    /** Number of tokens of thoughts for thinking models. */
+    total_thought_tokens?: number;
+    /**
+     * Total token count for the interaction request (prompt + responses + other
+     * internal tokens).
+     */
+    total_tokens?: number;
+    /** Number of tokens present in tool-use prompt(s). */
+    total_tool_use_tokens?: number;
+  }
+  /** Message for configuring webhook events for a request. */
+  interface WebhookConfig {
+    /**
+     * Optional. If set, these webhook URIs will be used for webhook events instead of the
+     * registered webhooks.
+     */
+    uris?: Array<string>;
+    /**
+     * Optional. The user metadata that will be returned on each event emission to the
+     * webhooks.
+     */
+    user_metadata?: Record<string, unknown>;
+  }
+  namespace Tools {
+    /** A tool that can be used by the model. */
+    type Tool = CodeExecution | ComputerUse | FileSearch | Function | GoogleMaps | GoogleSearch | McpServer | Retrieval | UrlContext;
+    /** A tool that can be used by the model to execute code. */
+    interface CodeExecution {
+      type: unknown;
+    }
+    /**
+     * A tool that can be used by the model to interact with the computer.
+     */
+    interface ComputerUse {
+      /** Optional. Disabled safety policies for computer use. */
+      disabled_safety_policies?: Array<"financial_transactions" | "sensitive_data_modification" | "communication_tool" | "account_creation" | "data_modification" | "user_consent_management" | "legal_terms_and_agreements" | (string & {})>;
+      /**
+       * Whether enable the prompt injection detection check on computer-use
+       * request.
+       */
+      enable_prompt_injection_detection?: boolean;
+      /** The environment being operated. */
+      environment?: "browser" | "mobile" | "desktop" | (string & {});
+      /**
+       * The list of predefined functions that are excluded from the model call.
+       */
+      excluded_predefined_functions?: Array<string>;
+      type: unknown;
+    }
+    /** A tool that can be used by the model to search files. */
+    interface FileSearch {
+      /** The file search store names to search. */
+      file_search_store_names?: Array<string>;
+      /**
+       * Metadata filter to apply to the semantic retrieval documents and chunks.
+       */
+      metadata_filter?: string;
+      /** The number of semantic retrieval chunks to retrieve. */
+      top_k?: number;
+      type: unknown;
+    }
+    /** A tool that can be used by the model. */
+    interface Function {
+      /** A description of the function. */
+      description?: string;
+      /** The name of the function. */
+      name?: string;
+      /** The JSON Schema for the function's parameters. */
+      parameters?: unknown;
+      type: unknown;
+    }
+    /** A tool that can be used by the model to call Google Maps. */
+    interface GoogleMaps {
+      /**
+       * Whether to return a widget context token in the tool call result of the
+       * response.
+       */
+      enable_widget?: boolean;
+      /** The latitude of the user's location. */
+      latitude?: number;
+      /** The longitude of the user's location. */
+      longitude?: number;
+      type: unknown;
+    }
+    /** A tool that can be used by the model to search Google. */
+    interface GoogleSearch {
+      /** The types of search grounding to enable. */
+      search_types?: Array<"web_search" | "image_search" | "enterprise_web_search" | (string & {})>;
+      type: unknown;
+    }
+    /**
+     * A MCPServer is a server that can be called by the model to perform actions.
+     */
+    interface McpServer {
+      /** The allowed tools. */
+      allowed_tools?: Array<AllowedTools>;
+      /**
+       * Optional: Fields for authentication headers, timeouts, etc., if needed.
+       */
+      headers?: Record<string, unknown>;
+      /** The name of the MCPServer. */
+      name?: string;
+      type: unknown;
+      /**
+       * The full URL for the MCPServer endpoint.
+       * Example: "https://api.example.com/mcp"
+       */
+      url?: string;
+    }
+    /** A tool that can be used by the model to retrieve files. */
+    interface Retrieval {
+      /** Used to specify configuration for ExaAISearch. */
+      exa_ai_search_config?: ExaAISearchConfig;
+      /** Used to specify configuration for ParallelAISearch. */
+      parallel_ai_search_config?: ParallelAISearchConfig;
+      /** Use to specify configuration for RAG Store. */
+      rag_store_config?: RagStoreConfig;
+      /** The types of file retrieval to enable. */
+      retrieval_types?: Array<"vertex_ai_search" | "rag_store" | "exa_ai_search" | "parallel_ai_search" | (string & {})>;
+      type: unknown;
+      /** Used to specify configuration for VertexAISearch. */
+      vertex_ai_search_config?: VertexAISearchConfig;
+    }
+    /** A tool that can be used by the model to fetch URL context. */
+    interface UrlContext {
+      type: unknown;
+    }
+    /** The configuration for allowed tools. */
+    interface AllowedTools {
+      /** The mode of the tool choice. */
+      mode?: "auto" | "any" | "none" | "validated" | (string & {});
+      /** The names of the allowed tools. */
+      tools?: Array<string>;
+    }
+    /** Used to specify configuration for ExaAISearch. */
+    interface ExaAISearchConfig {
+      /** Required. The API key for ExaAiSearch. */
+      api_key: string;
+      /**
+       * Optional. This field can be used to pass any parameter from the Exa.ai Search API.
+       */
+      custom_config?: Record<string, unknown>;
+    }
+    /** Config for filters. */
+    interface Filter {
+      /** Optional. String for metadata filtering. */
+      metadata_filter?: string;
+      /**
+       * Optional. Only returns contexts with vector distance smaller than the
+       * threshold.
+       */
+      vector_distance_threshold?: number;
+      /**
+       * Optional. Only returns contexts with vector similarity larger than the
+       * threshold.
+       */
+      vector_similarity_threshold?: number;
+    }
+    /** Config for Hybrid Search. */
+    interface HybridSearch {
+      /**
+       * Optional. Alpha value controls the weight between dense and sparse vector search
+       * results.
+       */
+      alpha?: number;
+    }
+    /** Used to specify configuration for ParallelAISearch. */
+    interface ParallelAISearchConfig {
+      /** Optional. The API key for ParallelAiSearch. */
+      api_key?: string;
+      /** Optional. Custom configs for ParallelAiSearch. */
+      custom_config?: Record<string, unknown>;
+    }
+    /** The definition of the Rag resource. */
+    interface RagResource {
+      /** Optional. RagCorpora resource name. */
+      rag_corpus?: string;
+      /**
+       * Optional. rag_file_id. The files should be in the same rag_corpus set in
+       * rag_corpus field.
+       */
+      rag_file_ids?: Array<string>;
+    }
+    /** Specifies the context retrieval config. */
+    interface RagRetrievalConfig {
+      /** Config for filters. */
+      filter?: Filter;
+      /** Config for Hybrid Search. */
+      hybrid_search?: HybridSearch;
+      /** Config for ranking and reranking. */
+      ranking?: Ranking;
+      /** Optional. The number of contexts to retrieve. */
+      top_k?: number;
+    }
+    /** Use to specify configuration for RAG Store. */
+    interface RagStoreConfig {
+      /** Optional. The representation of the rag source. */
+      rag_resources?: Array<RagResource>;
+      /** Specifies the context retrieval config. */
+      rag_retrieval_config?: RagRetrievalConfig;
+      /**
+       * Optional. Number of top k results to return from the selected corpora.
+       */
+      similarity_top_k?: number;
+      /**
+       * Optional. Only return results with vector distance smaller than the threshold.
+       */
+      vector_distance_threshold?: number;
+    }
+    /** Config for ranking and reranking. */
+    interface Ranking {
+      /** Optional. The model name of the rank service. */
+      model_name?: string;
+      /** Config for Rank Service. */
+      rank_service?: RankService;
+      ranking_config: unknown;
+    }
+    /** Config for Rank Service. */
+    interface RankService {
+      /** Optional. The model name of the rank service. */
+      model_name?: string;
+    }
+    /** Used to specify configuration for VertexAISearch. */
+    interface VertexAISearchConfig {
+      /** Optional. Used to specify Vertex AI Search datastores. */
+      datastores?: Array<string>;
+      /** Optional. Used to specify Vertex AI Search engine. */
+      engine?: string;
+    }
+  }
+  /** Citation information for model-generated content. */
+  type Annotation = FileCitation | PlaceCitation | SpeechAnnotation | UrlCitation | WordInfo;
+  /** An audio content block. */
+  interface AudioContent {
+    /** The number of audio channels. */
+    channels?: number;
+    /** The audio content. */
+    data?: string;
+    /** The mime type of the audio. */
+    mime_type?: "audio/wav" | "audio/mp3" | "audio/aiff" | "audio/aac" | "audio/ogg" | "audio/flac" | "audio/mpeg" | "audio/m4a" | "audio/l16" | "audio/opus" | "audio/alaw" | "audio/mulaw" | "audio/webm" | (string & {});
+    /** The sample rate of the audio. */
+    sample_rate?: number;
+    type: unknown;
+    /** The URI of the audio. */
+    uri?: string;
+  }
+  /** Configuration for audio output format. */
+  interface AudioResponseFormat {
+    /**
+     * Bit rate in bits per second (bps). Only applicable for compressed formats
+     * (MP3, Opus).
+     */
+    bit_rate?: number;
+    /** The delivery mode for the audio output. */
+    delivery?: "inline" | "uri" | (string & {});
+    /** The MIME type of the audio output. */
+    mime_type?: "audio/mp3" | "audio/ogg_opus" | "audio/l16" | "audio/wav" | "audio/alaw" | "audio/mulaw" | (string & {});
+    /** Sample rate in Hz. */
+    sample_rate?: number;
+    type: unknown;
+  }
+  /** Code execution call step. */
+  interface CodeExecutionCallStep {
+    /** The arguments to pass to the code execution. */
+    arguments: CodeExecutionCallStepArguments;
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** The arguments to pass to the code execution. */
+  interface CodeExecutionCallStepArguments {
+    /** The code to be executed. */
+    code?: string;
+    /** Programming language of the `code`. */
+    language?: "python" | (string & {});
+  }
+  /** Code execution result step. */
+  interface CodeExecutionResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    /** Whether the code execution resulted in an error. */
+    is_error?: boolean;
+    /** Required. The output of the code execution. */
+    result: string;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** The content of the response. */
+  type Content = AudioContent | DocumentContent | ImageContent | TextContent | VideoContent;
+  /** A document content block. */
+  interface DocumentContent {
+    /** The document content. */
+    data?: string;
+    /** The mime type of the document. */
+    mime_type?: "application/pdf" | "text/csv" | (string & {});
+    type: unknown;
+    /** The URI of the document. */
+    uri?: string;
+  }
+  /**
+   * A single domain allowlist rule with optional header injection.
+   */
+  interface EgressRule {
+    /**
+     * Optional. Reference to a server-managed Credential resource by ID.
+     */
+    credential?: string;
+    /**
+     * Domain to allow outbound requests to. Supports wildcards (e.g.
+     * '*.googleapis.com'). Use '*' to allow all domains.
+     */
+    domain: string;
+    /**
+     * Headers to inject on all outbound requests matching this domain. Accepts a single dict or a list of dicts. The egress proxy injects these automatically.
+     */
+    transform?: Array<Record<string, unknown>> | Record<string, unknown>;
+  }
+  /** Network egress configuration for the environment. */
+  interface EnvironmentNetworkEgressAllowlist {
+    /**
+     * List of allowed domains and their configurations. Set to `"disabled"`
+     * to block all network egress.
+     */
+    allowlist?: Array<EgressRule> | "disabled" | (string & {});
+  }
+  /** A file citation annotation. */
+  interface FileCitation {
+    /** User provided metadata about the retrieved context. */
+    custom_metadata?: Record<string, unknown>;
+    /** The URI of the file. */
+    document_uri?: string;
+    /** End of the attributed segment, exclusive. */
+    end_index?: number;
+    /** The name of the file. */
+    file_name?: string;
+    /** Media ID in-case of image citations, if applicable. */
+    media_id?: string;
+    /** Page number of the cited document, if applicable. */
+    page_number?: number;
+    /** Source attributed for a portion of the text. */
+    source?: string;
+    /**
+     * Start of segment of the response that is attributed to this source.
+     *
+     * Index indicates the start of the segment, measured in bytes.
+     */
+    start_index?: number;
+    type: unknown;
+  }
+  /** Content of a single file in the codebase. */
+  interface FileContent {
+    /** The UTF-8 encoded text content of the file. */
+    content?: string;
+    /** The relative path of the file from the project root. */
+    path?: string;
+  }
+  /** File Search call step. */
+  interface FileSearchCallStep {
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** File Search result step. */
+  interface FileSearchResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /**
+   * Request parameters specific to FIND sessions, used for discovering
+   * vulnerabilities in a codebase.
+   */
+  interface FindRequest {
+    /**
+     * Additional context or custom instructions provided by the user to guide
+     * the vulnerability analysis.
+     */
+    description?: string;
+    /**
+     * The identifier of a specific finding to verify. This is primarily used in
+     * VERIFY mode to focus the agent's execution-based validation on a single
+     * vulnerability.
+     */
+    finding_id?: string;
+    /** The mode of the find session. */
+    mode?: "scan" | "verify" | (string & {});
+    /** A list of source files to provide as context for the scan. */
+    source_files?: Array<FileContent>;
+  }
+  /**
+   * Request parameters specific to FIX sessions, used for generating and
+   * validating security patches.
+   */
+  interface FixRequest {
+    /**
+     * Additional context or custom instructions provided by the user to guide
+     * the patch generation process.
+     */
+    description?: string;
+    /**
+     * The identifier of the specific security finding to be remediated. This ID
+     * maps to a previously discovered vulnerability.
+     */
+    finding_id?: string;
+    /**
+     * A list of source files providing context for the remediation. These files
+     * are typically the ones containing the identified vulnerability.
+     */
+    source_files?: Array<FileContent>;
+  }
+  /** A function tool call step. */
+  interface FunctionCallStep {
+    /** Required. The arguments to pass to the function. */
+    arguments: Record<string, unknown>;
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** Required. The name of the tool to call. */
+    name: string;
+    type: unknown;
+  }
+  /** Result of a function tool call. */
+  interface FunctionResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    /** Whether the tool call resulted in an error. */
+    is_error?: boolean;
+    /** The name of the tool that was called. */
+    name?: string;
+    /** Required. The result of the tool call. */
+    result: Array<ImageContent | TextContent> | Record<string, unknown> | string;
+    type: unknown;
+  }
+  /** Google Maps call step. */
+  interface GoogleMapsCallStep {
+    /** The arguments to pass to the Google Maps tool. */
+    arguments?: GoogleMapsCallStepArguments;
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** The arguments to pass to the Google Maps tool. */
+  interface GoogleMapsCallStepArguments {
+    /** The queries to be executed. */
+    queries?: Array<string>;
+  }
+  /** The result of the Google Maps. */
+  interface GoogleMapsResultItem {
+    places?: Array<GoogleMapsResultPlaces>;
+    widget_context_token?: string;
+  }
+  interface GoogleMapsResultPlaces {
+    name?: string;
+    place_id?: string;
+    review_snippets?: Array<ReviewSnippet>;
+    url?: string;
+  }
+  /** Google Maps result step. */
+  interface GoogleMapsResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    result: Array<GoogleMapsResultItem>;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** Google Search call step. */
+  interface GoogleSearchCallStep {
+    /** The arguments to pass to Google Search. */
+    arguments: GoogleSearchCallStepArguments;
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** The type of search grounding enabled. */
+    search_type?: "web_search" | "image_search" | "enterprise_web_search" | (string & {});
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** The arguments to pass to Google Search. */
+  interface GoogleSearchCallStepArguments {
+    /** Web search queries for the following-up web search. */
+    queries?: Array<string>;
+  }
+  /** The result of the Google Search. */
+  interface GoogleSearchResultItem {
+    /**
+     * Web content snippet that can be embedded in a web page or an app webview.
+     */
+    search_suggestions?: string;
+  }
+  /** Google Search result step. */
+  interface GoogleSearchResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    /** Whether the Google Search resulted in an error. */
+    is_error?: boolean;
+    /** Required. The results of the Google Search. */
+    result: Array<GoogleSearchResultItem>;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** The number of grounding tool counts. */
+  interface GroundingToolCount {
+    /** The number of grounding tool counts. */
+    count?: number;
+    /** The grounding tool type associated with the count. */
+    type?: "google_search" | "google_maps" | "retrieval" | (string & {});
+  }
+  type HarmCategory = "hate_speech" | "dangerous_content" | "harassment" | "sexually_explicit" | "civic_integrity" | "image_hate" | "image_dangerous_content" | "image_harassment" | "image_sexually_explicit" | "jailbreak" | (string & {});
+  /** The configuration for image interaction. */
+  interface ImageConfig {
+    /**
+     * The aspect ratio of the image to generate. Supported aspect ratios: 1:1,
+     * 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9.
+     *
+     * If not specified, the model will choose a default aspect ratio based on any
+     * reference images provided.
+     */
+    aspect_ratio?: "1:1" | "2:3" | "3:2" | "3:4" | "4:3" | "4:5" | "5:4" | "9:16" | "16:9" | "21:9" | "1:8" | "8:1" | "1:4" | "4:1" | (string & {});
+    /**
+     * Specifies the size of generated images. Supported values are `1K`, `2K`,
+     * `4K`. If not specified, the model will use default value `1K`.
+     */
+    image_size?: "1K" | "2K" | "4K" | "512" | (string & {});
+  }
+  /** An image content block. */
+  interface ImageContent {
+    /** The image content. */
+    data?: string;
+    /** The mime type of the image. */
+    mime_type?: "image/png" | "image/jpeg" | "image/webp" | "image/heic" | "image/heif" | "image/gif" | "image/bmp" | "image/tiff" | (string & {});
+    resolution?: MediaResolution;
+    type: unknown;
+    /** The URI of the image. */
+    uri?: string;
+  }
+  /** Configuration for image output format. */
+  interface ImageResponseFormat {
+    /** The aspect ratio for the image output. */
+    aspect_ratio?: "1:1" | "2:3" | "3:2" | "3:4" | "4:3" | "4:5" | "5:4" | "9:16" | "16:9" | "21:9" | "1:8" | "8:1" | "1:4" | "4:1" | (string & {});
+    /** The delivery mode for the image output. */
+    delivery?: "inline" | "uri" | (string & {});
+    /** The size of the image output. */
+    image_size?: "512" | "1K" | "2K" | "4K" | (string & {});
+    /** The MIME type of the image output. */
+    mime_type?: "image/jpeg" | (string & {});
+    type: unknown;
+  }
+  /** MCPServer tool call step. */
+  interface McpServerToolCallStep {
+    /** Required. The JSON object of arguments for the function. */
+    arguments: Record<string, unknown>;
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** Required. The name of the tool which was called. */
+    name: string;
+    /** Required. The name of the used MCP server. */
+    server_name: string;
+    type: unknown;
+  }
+  /** MCPServer tool result step. */
+  interface McpServerToolResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    /**
+     * Name of the tool which is called for this specific tool call.
+     */
+    name?: string;
+    /**
+     * Required. The output from the MCP server call. Can be simple text or rich content.
+     */
+    result: Array<ImageContent | TextContent> | Record<string, unknown> | string;
+    /** The name of the used MCP server. */
+    server_name?: string;
+    type: unknown;
+  }
+  type MediaProcessing = StaticMediaProcessing;
+  type MediaResolution = "low" | "medium" | "high" | "ultra_high" | (string & {});
+  /** The token count for a single response modality. */
+  interface ModalityTokens {
+    modality?: ResponseModality;
+    /** Number of tokens for the modality. */
+    tokens?: number;
+  }
+  /** Output generated by the model. */
+  interface ModelOutputStep {
+    content?: Array<Content>;
+    /**
+     * The `Status` type defines a logical error model that is suitable for
+     * different programming environments, including REST APIs and RPC APIs. It is
+     * used by [gRPC](https://github.com/grpc). Each `Status` message contains
+     * three pieces of data: error code, error message, and error details.
+     *
+     * You can find out more about this error model and how to work with it in the
+     * [API Design Guide](https://cloud.google.com/apis/design/errors).
+     */
+    error?: Status;
+    type: unknown;
+  }
+  /** A place citation annotation. */
+  interface PlaceCitation {
+    /** End of the attributed segment, exclusive. */
+    end_index?: number;
+    /** Title of the place. */
+    name?: string;
+    /** The ID of the place, in `places/{place_id}` format. */
+    place_id?: string;
+    /**
+     * Snippets of reviews that are used to generate answers about the
+     * features of a given place in Google Maps.
+     */
+    review_snippets?: Array<ReviewSnippet>;
+    /**
+     * Start of segment of the response that is attributed to this source.
+     *
+     * Index indicates the start of the segment, measured in bytes.
+     */
+    start_index?: number;
+    type: unknown;
+    /** URI reference of the place. */
+    url?: string;
+  }
+  /**
+   * A server-initiated processing step for media analysis (e.g. video
+   * understanding).
+   */
+  interface ProcessingCallStep {
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** The result of a server-initiated media processing step. */
+  interface ProcessingResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /**
+   * Retrieval call step.
+   * Used by Vertex Retrieval tools such as Parallel AI, Exa AI, Vertex AI Search,
+   * etc. RetrievalType decides which tool is used.
+   */
+  interface RetrievalCallStep {
+    /** The arguments to pass to Retrieval tools. */
+    arguments: RetrievalStepArguments;
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** The type of retrieval tools. */
+    retrieval_type?: "vertex_ai_search" | "rag_store" | "exa_ai_search" | "parallel_ai_search" | (string & {});
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /**
+   * Vertex Retrieval result step.
+   * Used by Vertex Retrieval tools such as Parallel AI, Exa AI, Vertex AI Search,
+   * etc.
+   */
+  interface RetrievalResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    /** Whether the retrieval resulted in an error. */
+    is_error?: boolean;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** The arguments to pass to Retrieval tools. */
+  interface RetrievalStepArguments {
+    /** Queries for Retrieval information. */
+    queries?: Array<string>;
+  }
+  /**
+   * Encapsulates a snippet of a user review that answers a question about
+   * the features of a specific place in Google Maps.
+   */
+  interface ReviewSnippet {
+    /** The ID of the review snippet. */
+    review_id?: string;
+    /** Title of the review. */
+    title?: string;
+    /** A link that corresponds to the user review on Google Maps. */
+    url?: string;
+  }
+  /** The configuration of CodeMender sessions. */
+  interface SessionConfig {
+    /**
+     * The maximum number of interaction rounds the agent is allowed to perform
+     * before reaching a timeout.
+     */
+    max_rounds?: number;
+  }
+  /** Configuration for smart transcription mode. */
+  interface SmartTranscriptionMode {
+    type: unknown;
+  }
+  /** A source to be mounted into the environment. */
+  interface Source {
+    /** The inline content if `type` is `INLINE`. */
+    content?: string;
+    /** Optional encoding for inline content (e.g. `base64`). */
+    encoding?: string;
+    /**
+     * The source of the environment.
+     * For Cloud Storage, this is the Cloud Storage path.
+     * For GitHub, this is the GitHub path.
+     */
+    source?: string;
+    /** Where the source should appear in the environment. */
+    target?: string;
+    type?: "gcs" | "inline" | "repository" | "skill_registry" | (string & {});
+  }
+  /** Configuration for multi-speaker and speech generation. */
+  interface SpeakerConfig {
+    /** Individual speaker configurations. */
+    speakers?: Array<SpeechConfig>;
+  }
+  /** Speech annotation for text content. */
+  interface SpeechAnnotation {
+    /** End of the attributed segment, exclusive. */
+    end_index?: number;
+    /** The speaker to associate with this turn. */
+    speaker?: string;
+    /**
+     * Start of segment of the response that is attributed to this source.
+     *
+     * Index indicates the start of the segment, measured in bytes.
+     */
+    start_index?: number;
+    /** Style instruction for the speech synthesis. */
+    style?: string;
+    type: unknown;
+  }
+  /** The configuration for speech interaction. */
+  interface SpeechConfig {
+    /** The language of the speech. */
+    language?: string;
+    /**
+     * The speaker's name, it should match the speaker name given in the prompt.
+     */
+    speaker?: string;
+    /** The voice of the speaker. */
+    voice?: string;
+  }
+  interface StaticMediaProcessing {
+    /**
+     * Optional. Segment end time. Specified as a decimal number of seconds followed
+     * by an 's' suffix, e.g., "30s". Must be non-negative and greater than
+     * `start_offset` if `start_offset` is set.
+     */
+    end_offset?: string;
+    /** Optional. Video frame-rate sampling density. */
+    fps?: number;
+    /**
+     * Optional. Segment start time. Specified as a decimal number of seconds followed
+     * by an 's' suffix, e.g., "10.5s". Must be non-negative.
+     */
+    start_offset?: string;
+    type: unknown;
+  }
+  /**
+   * The `Status` type defines a logical error model that is suitable for
+   * different programming environments, including REST APIs and RPC APIs. It is
+   * used by [gRPC](https://github.com/grpc). Each `Status` message contains
+   * three pieces of data: error code, error message, and error details.
+   *
+   * You can find out more about this error model and how to work with it in the
+   * [API Design Guide](https://cloud.google.com/apis/design/errors).
+   */
+  interface Status {
+    /**
+     * The status code, which should be an enum value of google.rpc.Code.
+     */
+    code?: number;
+    /**
+     * A list of messages that carry the error details.  There is a common set of
+     * message types for APIs to use.
+     */
+    details?: Array<Record<string, unknown>>;
+    /**
+     * A developer-facing error message, which should be in English. Any
+     * user-facing error message should be localized and sent in the
+     * google.rpc.Status.details field, or localized by the client.
+     */
+    message?: string;
+  }
+  /** A text content block. */
+  interface TextContent {
+    /** Citation information for model-generated content. */
+    annotations?: Array<Annotation>;
+    /** Required. The text content. */
+    text: string;
+    type: unknown;
+  }
+  /** Configuration for text output format. */
+  interface TextResponseFormat {
+    /** The MIME type of the text output. */
+    mime_type?: "application/json" | "text/plain" | (string & {});
+    /**
+     * The JSON schema that the output should conform to. Only applicable when
+     * mime_type is application/json.
+     */
+    schema?: Record<string, unknown>;
+    type: unknown;
+  }
+  type ThinkingLevel = "minimal" | "low" | "medium" | "high" | (string & {});
+  type ThinkingSummaries = "auto" | "none" | (string & {});
+  type ThoughtContent = ImageContent | TextContent;
+  /** A thought step. */
+  interface ThoughtStep {
+    /** A signature hash for backend validation. */
+    signature?: string;
+    /** A summary of the thought. */
+    summary?: Array<ThoughtContent>;
+    type: unknown;
+  }
+  /** The tool choice configuration containing allowed tools. */
+  interface ToolChoiceConfig {
+    /** The configuration for allowed tools. */
+    allowed_tools?: Interactions.Tools.AllowedTools;
+  }
+  /** Configuration for speech recognition (transcription). */
+  interface TranscriptionConfig {
+    /** Optional. A list of phrases to bias the ASR model towards. */
+    adaptation_phrases?: Array<string>;
+    /**
+     * Optional. A list of custom vocabulary phrases to bias the speech recognition model
+     * toward recognizing specific terms.
+     */
+    custom_vocabulary?: Array<string>;
+    /**
+     * Optional. Configures speaker diarization. Supported values: "speaker".
+     */
+    diarization_mode?: string;
+    /**
+     * Optional. BCP-47 language codes providing hints about the languages present in the
+     * audio. If omitted or empty, defaults to automatic language detection.
+     */
+    language_codes?: Array<string>;
+    /**
+     * Deprecated: use language_codes. BCP-47 language codes providing hints about the languages present in the audio.
+     */
+    language_hints?: Array<string>;
+    /** Discriminated transcription mode options or enum. */
+    mode?: TranscriptionMode | "verbatim" | "smart" | (string & {});
+    /**
+     * Optional. The granularity of timestamps to include in the transcription output.
+     * Supported values: "word". If empty, no timestamps are generated.
+     */
+    timestamp_granularities?: Array<string>;
+  }
+  /** Configuration for transcription mode. */
+  type TranscriptionMode = SmartTranscriptionMode | VerbatimTranscriptionMode;
+  /** A URL citation annotation. */
+  interface UrlCitation {
+    /** End of the attributed segment, exclusive. */
+    end_index?: number;
+    /**
+     * Start of segment of the response that is attributed to this source.
+     *
+     * Index indicates the start of the segment, measured in bytes.
+     */
+    start_index?: number;
+    /** The title of the URL. */
+    title?: string;
+    type: unknown;
+    /** The URL. */
+    url?: string;
+  }
+  /** The arguments to pass to the URL context. */
+  interface UrlContextCallArguments {
+    /** The URLs to fetch. */
+    urls?: Array<string>;
+  }
+  /** URL context call step. */
+  interface UrlContextCallStep {
+    /** The arguments to pass to the URL context. */
+    arguments: UrlContextCallArguments;
+    /** Required. A unique ID for this specific tool call. */
+    id: string;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** The result of the URL context. */
+  interface UrlContextResult {
+    /** The status of the URL retrieval. */
+    status?: "success" | "error" | "paywall" | "unsafe" | (string & {});
+    /** The URL that was fetched. */
+    url?: string;
+  }
+  /** URL context result step. */
+  interface UrlContextResultStep {
+    /** Required. ID to match the ID from the function call block. */
+    call_id: string;
+    /** Whether the URL context resulted in an error. */
+    is_error?: boolean;
+    /** Required. The results of the URL context. */
+    result: Array<UrlContextResult>;
+    /** A signature hash for backend validation. */
+    signature?: string;
+    type: unknown;
+  }
+  /** Input provided by the user. */
+  interface UserInputStep {
+    content?: Array<Content>;
+    type: unknown;
+  }
+  /** Configuration for verbatim transcription mode. */
+  interface VerbatimTranscriptionMode {
+    /**
+     * Optional. Configures speaker diarization. Supported values: "speaker".
+     */
+    diarization_mode?: string;
+    /**
+     * Optional. The granularity of timestamps to include in the transcription output.
+     * Supported values: "word". If empty, no timestamps are generated.
+     */
+    timestamp_granularities?: Array<string>;
+    type: unknown;
+  }
+  /** Configuration options for video generation. */
+  interface VideoConfig {
+    /**
+     * Optional task mode for video generation. If not specified, the model
+     * automatically determines the appropriate mode based on the provided text
+     * prompt and input media.
+     */
+    task?: "text_to_video" | "image_to_video" | "reference_to_video" | "edit" | "extend" | (string & {});
+  }
+  /** A video content block. */
+  interface VideoContent {
+    /** The video content. */
+    data?: string;
+    /** The mime type of the video. */
+    mime_type?: "video/mp4" | "video/mpeg" | "video/mpg" | "video/mov" | "video/avi" | "video/x-flv" | "video/webm" | "video/wmv" | "video/3gpp" | (string & {});
+    /**
+     * A user-defined name for this content block. Can be referenced by the model
+     * in the final response.
+     */
+    name?: string;
+    /** How the model processes this video for understanding. */
+    processing?: MediaProcessing | "static" | "agentic" | (string & {});
+    resolution?: MediaResolution;
+    type: unknown;
+    /** The URI of the video. */
+    uri?: string;
+  }
+  /** Configuration for video output format. */
+  interface VideoResponseFormat {
+    /** The aspect ratio for the video output. */
+    aspect_ratio?: "16:9" | "9:16" | (string & {});
+    /** The delivery mode for the video output. */
+    delivery?: "inline" | "uri" | (string & {});
+    /** The duration for the video output. */
+    duration?: string;
+    /**
+     * The Cloud Storage URI to store the video output. Required for Vertex if
+     * delivery mode is URI.
+     */
+    gcs_uri?: string;
+    /** The video output resolution. Defaults to 720p. */
+    resolution?: "360p" | "720p" | "1080p" | "4k" | (string & {});
+    type: unknown;
+  }
+  /**
+   * Word-level ASR annotation for transcription output.
+   * Carries the word text, optional timing, and optional speaker attribution.
+   */
+  interface WordInfo {
+    /** End of the attributed segment, exclusive. */
+    end_index?: number;
+    /**
+     * End offset in time of the word relative to the start of the audio.
+     * Present when timestamp_granularities contains "word".
+     */
+    end_offset?: string;
+    /**
+     * Optional. Speaker label for this word (e.g. "spk_1", "spk_2").
+     * Present when diarization_mode is set in TranscriptionConfig.
+     */
+    speaker?: string;
+    /**
+     * Start of segment of the response that is attributed to this source.
+     *
+     * Index indicates the start of the segment, measured in bytes.
+     */
+    start_index?: number;
+    /**
+     * Start offset in time of the word relative to the start of the audio.
+     * Present when timestamp_granularities contains "word".
+     */
+    start_offset?: string;
+    /** The transcribed word. */
+    text?: string;
+    type: unknown;
+  }
+}
+//# sourceMappingURL=interactions.d.cts.map