@code-yeongyu/senpi 2026.9.11 → 2026.9.12-3

package/node_modules/@google/genai/dist/vertex_internal/index.d.ts

@@ -414,6 +414,24 @@ declare interface AudioTranscriptionConfig {
     /** Configures speaker diarization.
      */
     diarization?: boolean;
+    /** Optional. Configures transcription mode. Supported values: `VERBATIM`, `SMART`. If unspecified, defaults to `VERBATIM` transcription. In `SMART` mode, the model performs disfluency removal (eliminating filler words, repetitions, and false starts), light grammatical cleanup, automatic formatting (paragraphs, bullet points, numbered lists), and minor user edits (inline self-corrections). Timestamps and diarization are incompatible with mode `SMART`. */
+    mode?: AudioTranscriptionConfigMode;
+}
+
+/** Transcription mode. */
+declare enum AudioTranscriptionConfigMode {
+    /**
+     * Unspecified transcription mode.
+     */
+    MODE_UNSPECIFIED = "MODE_UNSPECIFIED",
+    /**
+     * Verbatim transcription mode.
+     */
+    VERBATIM = "VERBATIM",
+    /**
+     * Smart transcription mode.
+     */
+    SMART = "SMART"
 }
 
 /**
@@ -1365,12 +1383,6 @@ declare interface CreateChatParameters {
      docs to find the available models.
      */
     model: string;
-    /** Config for the entire chat session.
-
-     This config applies to all requests within the session
-     unless overridden by a per-request `config` in `SendMessageParameters`.
-     */
-    config?: GenerateContentConfig;
     /** The initial conversation history for the chat session.
 
      This allows you to start the chat with a pre-existing history. The history
@@ -1378,6 +1390,12 @@ declare interface CreateChatParameters {
      It should start with a 'user' message.
      */
     history?: Content[];
+    /** Config for the entire chat session.
+
+     This config applies to all requests within the session
+     unless overridden by a per-request `config` in `SendMessageParameters`.
+     */
+    config?: GenerateContentConfig;
 }
 
 /** Config for optional parameters. */
@@ -5544,6 +5562,22 @@ declare enum MediaModality {
     DOCUMENT = "DOCUMENT"
 }
 
+/** How the model processes input media for understanding. */
+declare enum MediaProcessing {
+    /**
+     * Default. Uses model-specific processing
+     */
+    MEDIA_PROCESSING_UNSPECIFIED = "MEDIA_PROCESSING_UNSPECIFIED",
+    /**
+     * Fixed-rate frame extraction. All frames placed in context.
+     */
+    STATIC = "STATIC",
+    /**
+     * Model-driven dynamic navigation. Recommended for most use cases.
+     */
+    AGENTIC = "AGENTIC"
+}
+
 /** The media resolution to use. */
 declare enum MediaResolution {
     /**
@@ -5923,6 +5957,8 @@ declare interface Part {
     videoMetadata?: VideoMetadata;
     /** Custom metadata associated with the Part. Agents using genai.Part as content representation may need to keep track of the additional information. For example it can be name of a file/source from which the Part originates or a way to multiplex multiple Part streams. This field is not supported in Vertex AI. */
     partMetadata?: Record<string, unknown>;
+    /** How the model processes this part's media for understanding. */
+    mediaProcessing?: MediaProcessing;
 }
 
 /** Partial argument value of the function call. This data type is not supported in Gemini API. */
@@ -7456,7 +7492,11 @@ declare enum ToolType {
     /**
      * File search tool, maps to Tool.file_search.
      */
-    FILE_SEARCH = "FILE_SEARCH"
+    FILE_SEARCH = "FILE_SEARCH",
+    /**
+     * Media processing tool.
+     */
+    MEDIA_PROCESSING = "MEDIA_PROCESSING"
 }
 
 declare type ToolUnion = Tool | CallableTool;
@@ -7503,9 +7543,9 @@ declare interface Transcription {
 
 /** 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. */
+    /** 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"). */
+    /** The target language for translation. Supported values are BCP-47 language codes (e.g. "en", "es", "fr"). */
     targetLanguageCode?: string;
 }
 
@@ -8014,6 +8054,7 @@ declare namespace types {
         TuningTask,
         DocumentState,
         ServiceTier,
+        MediaProcessing,
         PartMediaResolutionLevel,
         ToolType,
         ResourceScope,
@@ -8041,6 +8082,7 @@ declare namespace types {
         EndSensitivity,
         ActivityHandling,
         TurnCoverage,
+        AudioTranscriptionConfigMode,
         Scale,
         MusicGenerationMode,
         LiveMusicPlaybackControl,

package/node_modules/@google/genai/dist/vertex_internal/index.js

@@ -1536,6 +1536,22 @@ var ServiceTier;
      */
     ServiceTier["PRIORITY"] = "priority";
 })(ServiceTier || (ServiceTier = {}));
+/** How the model processes input media for understanding. */
+var MediaProcessing;
+(function (MediaProcessing) {
+    /**
+     * Default. Uses model-specific processing
+     */
+    MediaProcessing["MEDIA_PROCESSING_UNSPECIFIED"] = "MEDIA_PROCESSING_UNSPECIFIED";
+    /**
+     * Fixed-rate frame extraction. All frames placed in context.
+     */
+    MediaProcessing["STATIC"] = "STATIC";
+    /**
+     * Model-driven dynamic navigation. Recommended for most use cases.
+     */
+    MediaProcessing["AGENTIC"] = "AGENTIC";
+})(MediaProcessing || (MediaProcessing = {}));
 /** The tokenization quality used for given media. */
 var PartMediaResolutionLevel;
 (function (PartMediaResolutionLevel) {
@@ -1587,6 +1603,10 @@ var ToolType;
      * File search tool, maps to Tool.file_search.
      */
     ToolType["FILE_SEARCH"] = "FILE_SEARCH";
+    /**
+     * Media processing tool.
+     */
+    ToolType["MEDIA_PROCESSING"] = "MEDIA_PROCESSING";
 })(ToolType || (ToolType = {}));
 /** Resource scope. */
 var ResourceScope;
@@ -2052,6 +2072,22 @@ var TurnCoverage;
      */
     TurnCoverage["TURN_INCLUDES_AUDIO_ACTIVITY_AND_ALL_VIDEO"] = "TURN_INCLUDES_AUDIO_ACTIVITY_AND_ALL_VIDEO";
 })(TurnCoverage || (TurnCoverage = {}));
+/** Transcription mode. */
+var AudioTranscriptionConfigMode;
+(function (AudioTranscriptionConfigMode) {
+    /**
+     * Unspecified transcription mode.
+     */
+    AudioTranscriptionConfigMode["MODE_UNSPECIFIED"] = "MODE_UNSPECIFIED";
+    /**
+     * Verbatim transcription mode.
+     */
+    AudioTranscriptionConfigMode["VERBATIM"] = "VERBATIM";
+    /**
+     * Smart transcription mode.
+     */
+    AudioTranscriptionConfigMode["SMART"] = "SMART";
+})(AudioTranscriptionConfigMode || (AudioTranscriptionConfigMode = {}));
 /** Scale of the generated music. */
 var Scale;
 (function (Scale) {
@@ -2310,7 +2346,7 @@ 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 = '2.18.0'; // x-release-please-version
+const SDK_VERSION = '2.21.0'; // 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';
@@ -3259,7 +3295,7 @@ async function uploadBlobInternal(file, uploadUrl, apiClient, httpOptions) {
         let retryCount = 0;
         let currentDelayMs = INITIAL_RETRY_DELAY_MS;
         while (retryCount < MAX_RETRY_COUNT) {
-            const mergedHeaders = Object.assign(Object.assign({}, ((httpOptions === null || httpOptions === void 0 ? void 0 : httpOptions.headers) || {})), { 'X-Goog-Upload-Command': uploadCommand, 'X-Goog-Upload-Offset': String(offset), 'Content-Length': String(chunkSize) });
+            const mergedHeaders = Object.assign(Object.assign({}, ((httpOptions === null || httpOptions === void 0 ? void 0 : httpOptions.headers) || {})), { 'X-Goog-Upload-Command': uploadCommand, 'X-Goog-Upload-Offset': String(offset) });
             response = await apiClient.request({
                 path: '',
                 body: chunk,
@@ -3478,7 +3514,7 @@ class NodeUploader {
                 let retryCount = 0;
                 let currentDelayMs = INITIAL_RETRY_DELAY_MS;
                 while (retryCount < MAX_RETRY_COUNT) {
-                    const mergedHeaders = Object.assign(Object.assign({}, ((httpOptions === null || httpOptions === void 0 ? void 0 : httpOptions.headers) || {})), { 'X-Goog-Upload-Command': uploadCommand, 'X-Goog-Upload-Offset': String(offset), 'Content-Length': String(bytesRead), 'X-Goog-Upload-File-Name': fileName });
+                    const mergedHeaders = Object.assign(Object.assign({}, ((httpOptions === null || httpOptions === void 0 ? void 0 : httpOptions.headers) || {})), { 'X-Goog-Upload-Command': uploadCommand, 'X-Goog-Upload-Offset': String(offset), 'X-Goog-Upload-File-Name': fileName });
                     response = await apiClient.request({
                         path: '',
                         body: chunk,