@ai-sdk/google 4.0.0-canary.80 → 4.0.0

package/CHANGELOG.md

@@ -1,5 +1,164 @@
 # @ai-sdk/google
 
+## 4.0.0
+
+### Major Changes
+
+- a3757d7: chore(provider/google): remove useless GenerativeAI affix from types and classes for consistency
+- f7d4f01: feat(provider): add support for `reasoning-file` type for files that are part of reasoning
+- ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only (`"type": "module"`). Consumers using `require()` must switch to ESM `import` syntax.
+- c29a26f: feat(provider): add support for provider references and uploading files as supported per provider
+- 3887c70: feat(provider): add new top-level reasoning parameter to spec and support it in `generateText` and `streamText`
+- 8359612: Start v7 pre-release
+- 04e9009: chore: make provider implementations code patterns more consistent, including renaming certain exported symbols
+
+  For all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.
+
+### Patch Changes
+
+- 7f04802: feat(provider/google): add support for managed agents in the Interactions API
+- 38fc777: Add AI Gateway hint to provider READMEs
+- b71c0d7: feat(provider/google): support Google search grounding when using `generateImage` with Gemini
+- 6190649: chore(provider/google): remove obsolete Google image model
+- 55db546: fix(provider/google): fix Gemini service tier enum after upstream update
+- 9a0a618: fix(google): fix `serviceTier` to be correctly formatted for Vertex API
+- 00a0f36: feat(google, google-vertex): added `gemini-embedding-2`, `deep-research-max-preview-04-2026` and `deep-research-preview-04-2026`
+- 9715ec7: feat(provider/google): add support for service tier parameter
+- 41da50c: fix(provider/google): support `functionCall.id` when returned by Gemini API and provide matching `functionResponse.id`
+- add4326: fix(provider/google): correct JSDoc for multimodal embedding content option
+- a8d70b6: fix(google): auto-inject `skip_thought_signature_validator` for Gemini 3 tool-call replays without a signature
+- 947cdab: Add Google realtime Live Translation provider options for `gemini-3.5-live-translate-preview`.
+- 4e825f3: feat(google): update Interactions API implementation to cater for upstream breaking changes coming May 26
+- b563707: feat(provider/google): add Gemini text-to-speech (speech) model support
+- a05109d: feat(provider/google): preserve per-modality token details in usage data
+- cfca634: fix(google): emit Vertex no-args streaming tool calls and preserve thoughtSignature
+
+  Vertex emits a no-args function call as a single chunk shaped `{ functionCall: { name: 'X' } }` with no `args`, no `partialArgs`, and no `willContinue`. The streaming parser had no branch for this shape, so the call was dropped along with any `thoughtSignature` it carried. For Gemini 3 thinking models this caused the next multi-turn step to 400 with `missing thought_signature`. The unary (`doGenerate`) path had the same drop.
+
+  Both paths now emit the call as a complete tool call with `'{}'` input and propagate `thoughtSignature` provider metadata.
+
+  Fixes #14847.
+
+- c9c4661: fix(provider/google): preserve groundingMetadata and urlContextMetadata when they arrive in a stream chunk before the finishReason chunk
+- 045d2e8: fix(google): read `serviceTier` from `usageMetadata.serviceTier` in both generate and stream paths
+
+  The previous implementation read `serviceTier` from the `x-gemini-service-tier`
+  response header, which is only populated on non-streaming responses. Gemini
+  streaming includes the value in `usageMetadata.serviceTier` on every chunk, so
+  `providerMetadata.google.serviceTier` was always `null` for streams. Read from
+  `usageMetadata` for both paths instead.
+
+- 19b95f9: fix(google): use VALIDATED function calling mode when any tool has strict:true
+- 2ce3c65: feat(provider/google-vertex): add Gemini text-to-speech (speech) model support
+- 5878b40: fix(google): prevent prototype pollution when streaming tool args
+- 46d1149: chore(provider-utils,google): fix grammar errors in error and warning messages
+- 6a26901: feat(google): add `fileData` support to embedding model
+- 01fa606: feat(provider/google): support combining built-in tools with function calling on Gemini 3
+- 5036db8: feat(google-vertex): add support for streaming tool arguments input
+- 9f0e36c: trigger release for all packages after provenance setup
+- a2609df: fix(google): fix streaming tool call args
+- ab43029: feat(provider/google): support multimodal content parts in embedding provider options
+- 82288b0: feat(provider/google): add `gemini-embedding-2-preview` and fix multimodal embedding support with `embedMany`
+- b04e23e: feat(provider/google): add support for the Gemini Interactions API
+- 58a2ad7: fix: more precise default message for tool execution denial
+- e59176c: chore(google): update v3 specs to v4
+- ebbb0f2: fix(provider/google): fix lack of image consistency when using Interactions API in stateless mode
+- aeda373: fix: only send provider credentials to same-origin response-supplied URLs
+
+  Several provider clients followed a URL taken from the provider's API response (a polling/status URL or a final media URL such as `polling_url`, `urls.get`, `result_url`, `result.sample`, or `video.uri`) and reused the authenticated headers — or appended `?key=<API_KEY>` — on that request. Because the host of the response-supplied URL was never validated, the long-lived API key was sent to whatever host the response named (a CDN in the benign case, or an attacker-chosen host if the provider response was tampered with), allowing credential exfiltration.
+
+  A new `isSameOrigin` helper is added to `@ai-sdk/provider-utils`, and the affected fetches in `@ai-sdk/black-forest-labs`, `@ai-sdk/fireworks`, `@ai-sdk/replicate`, `@ai-sdk/gladia`, `@ai-sdk/fal`, and `@ai-sdk/google` now attach credentials only when the followed URL is same-origin with the provider's configured API origin. Requests to a foreign origin are made without the credential.
+
+- 7fc6bd6: Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.
+- 0c4c275: trigger initial canary release
+- bdb9ea1: chore(google): remove now obsolete Interactions API `Api-Revision` header
+- db394ab: feat(provider/google): support cancelling long-running Interactions API agents via AbortSignal, and process their intermittent stream
+- ce769dd: feat(provider): add experimental Realtime API support for voice conversations
+
+  Adds first-class support for realtime (speech-to-speech) APIs:
+
+  - `Experimental_RealtimeModelV4` spec in `@ai-sdk/provider` with normalized event types and factory
+  - OpenAI, Google, and xAI realtime provider implementations
+  - `openai.experimental_realtime()` / `google.experimental_realtime()` / `xai.experimental_realtime()` work in both server and browser
+  - `.getToken()` static method on each provider for server-side ephemeral token creation
+  - `experimental_getRealtimeToolDefinitions` helper for provider session tool definitions
+  - `experimental_useRealtime` hook in `@ai-sdk/react` returning `UIMessage[]` (aligned with `useChat`), with `onToolCall` and `addToolOutput` for client-driven tool execution
+  - `inputAudioTranscription` session config for showing transcribed user audio messages when supported by the provider
+
+- 5b7e7c2: fix(google-vertex): don't send streamFunctionCallArguments for unary API calls and change default to false
+- 2edd14e: fix(provider/google): correctly mark reasoning files as such and fix related multi-turn errors
+- 9bd6512: feat(provider): change file part data property to be tagged with a type and remove the image part type
+- 258c093: chore: ensure consistent import handling and avoid import duplicates or cycles
+- 546cefe: feat(provider/google): add `gemini-3.5-flash`
+- 5463d0d: feat(provider): align tool result output content file part types with top-level message file part types
+- 55f0938: chore(provider/google): update available models
+- b8396f0: trigger initial beta release
+- 84f36e0: fix(google): omit passing includeServerSideToolInvocations for Vertex tool_config
+- 90e2d8a: chore: fix unused vars not being flagged by our lint tooling
+- 4dac142: feat(google): add new finishMessage field in providerMetadata
+- aeea161: feat(google): read `serviceTier` from `x-gemini-service-tier` response header in Gemini API and use PayGo for Vertex
+- 18c1970: feat(provider/google): Add multimodal tool-result support for Google function responses.
+
+  Tool results with `output.type = 'content'` now map media parts into
+  `functionResponse.parts` for Google models, including `image-data`,
+  `file-data`, and base64 `data:` URLs in URL-style content parts.
+  Remote HTTP(S) URLs in URL-style tool-result parts are not supported.
+
+- b3976a2: Add workflow serialization support to all provider models.
+
+  **`@ai-sdk/provider-utils`:** New `serializeModel()` helper that extracts only serializable properties from a model instance, filtering out functions and objects containing functions. Third-party provider authors can use this to add workflow support to their own models.
+
+  **All providers:** `headers` is now optional in provider config types. This is non-breaking — existing code that passes `headers` continues to work. Custom provider implementations that construct model configs manually can now omit `headers`, which is useful when models are deserialized from a workflow step boundary where auth is provided separately.
+
+  All provider model classes now include `WORKFLOW_SERIALIZE` and `WORKFLOW_DESERIALIZE` static methods, enabling them to cross workflow step boundaries without serialization errors.
+
+- ff5eba1: feat: roll `image-*` tool output types into their equivalent `file-*` types
+
+## 4.0.0-beta.85
+
+### Patch Changes
+
+- Updated dependencies [0416e3e]
+  - @ai-sdk/provider@4.0.0-beta.20
+  - @ai-sdk/provider-utils@5.0.0-beta.50
+
+## 4.0.0-beta.84
+
+### Patch Changes
+
+- 947cdab: Add Google realtime Live Translation provider options for `gemini-3.5-live-translate-preview`.
+
+## 4.0.0-beta.83
+
+### Patch Changes
+
+- bdb9ea1: chore(google): remove now obsolete Interactions API `Api-Revision` header
+
+## 4.0.0-beta.82
+
+### Patch Changes
+
+- b8396f0: trigger initial beta release
+- Updated dependencies [b8396f0]
+  - @ai-sdk/provider-utils@5.0.0-beta.49
+  - @ai-sdk/provider@4.0.0-beta.19
+
+## 4.0.0-canary.81
+
+### Patch Changes
+
+- 5878b40: fix(google): prevent prototype pollution when streaming tool args
+- aeda373: fix: only send provider credentials to same-origin response-supplied URLs
+
+  Several provider clients followed a URL taken from the provider's API response (a polling/status URL or a final media URL such as `polling_url`, `urls.get`, `result_url`, `result.sample`, or `video.uri`) and reused the authenticated headers — or appended `?key=<API_KEY>` — on that request. Because the host of the response-supplied URL was never validated, the long-lived API key was sent to whatever host the response named (a CDN in the benign case, or an attacker-chosen host if the provider response was tampered with), allowing credential exfiltration.
+
+  A new `isSameOrigin` helper is added to `@ai-sdk/provider-utils`, and the affected fetches in `@ai-sdk/black-forest-labs`, `@ai-sdk/fireworks`, `@ai-sdk/replicate`, `@ai-sdk/gladia`, `@ai-sdk/fal`, and `@ai-sdk/google` now attach credentials only when the followed URL is same-origin with the provider's configured API origin. Requests to a foreign origin are made without the credential.
+
+- Updated dependencies [aeda373]
+- Updated dependencies [375fdd7]
+- Updated dependencies [b4507d5]
+  - @ai-sdk/provider-utils@5.0.0-canary.48
+
 ## 4.0.0-canary.80
 
 ### Patch Changes

package/dist/index.d.ts

@@ -622,6 +622,28 @@ declare class GoogleRealtimeModel implements Experimental_RealtimeModelV4 {
     buildSessionConfig(config: Experimental_RealtimeModelV4SessionConfig): Record<string, unknown>;
 }
 
+type GoogleRealtimeModelId = string;
+type GoogleRealtimeModelOptions = {
+    /**
+     * Gemini Live Translation configuration.
+     *
+     * Required for `gemini-3.5-live-translate-preview` when translating speech
+     * to a target language.
+     */
+    translationConfig?: {
+        /**
+         * BCP-47 language code of the language to translate into.
+         * Defaults to `en` in the Gemini API.
+         */
+        targetLanguageCode?: string;
+        /**
+         * Whether input audio already in the target language should be echoed
+         * instead of producing silence.
+         */
+        echoTargetLanguage?: boolean;
+    };
+};
+
 declare const VERSION: string;
 
-export { GoogleRealtimeModel as Experimental_GoogleRealtimeModel, type GoogleRealtimeModelConfig as Experimental_GoogleRealtimeModelConfig, type GoogleEmbeddingModelOptions, type GoogleErrorData, type GoogleFilesUploadOptions, type GoogleEmbeddingModelOptions as GoogleGenerativeAIEmbeddingProviderOptions, type GoogleImageModelOptions as GoogleGenerativeAIImageProviderOptions, type GoogleProvider as GoogleGenerativeAIProvider, type GoogleProviderMetadata as GoogleGenerativeAIProviderMetadata, type GoogleLanguageModelOptions as GoogleGenerativeAIProviderOptions, type GoogleProviderSettings as GoogleGenerativeAIProviderSettings, type GoogleVideoModelId as GoogleGenerativeAIVideoModelId, type GoogleVideoModelOptions as GoogleGenerativeAIVideoProviderOptions, type GoogleImageModelOptions, type GoogleInteractionsAgentName, type GoogleInteractionsModelId, type GoogleInteractionsProviderMetadata, type GoogleLanguageModelInteractionsOptions, type GoogleLanguageModelOptions, type GoogleProvider, type GoogleProviderMetadata, type GoogleProviderSettings, type GoogleSpeechModelId, type GoogleSpeechModelOptions, type GoogleVideoModelId, type GoogleVideoModelOptions, VERSION, createGoogle, createGoogle as createGoogleGenerativeAI, google };
+export { GoogleRealtimeModel as Experimental_GoogleRealtimeModel, type GoogleRealtimeModelConfig as Experimental_GoogleRealtimeModelConfig, type GoogleRealtimeModelId as Experimental_GoogleRealtimeModelId, type GoogleRealtimeModelOptions as Experimental_GoogleRealtimeModelOptions, type GoogleEmbeddingModelOptions, type GoogleErrorData, type GoogleFilesUploadOptions, type GoogleEmbeddingModelOptions as GoogleGenerativeAIEmbeddingProviderOptions, type GoogleImageModelOptions as GoogleGenerativeAIImageProviderOptions, type GoogleProvider as GoogleGenerativeAIProvider, type GoogleProviderMetadata as GoogleGenerativeAIProviderMetadata, type GoogleLanguageModelOptions as GoogleGenerativeAIProviderOptions, type GoogleProviderSettings as GoogleGenerativeAIProviderSettings, type GoogleVideoModelId as GoogleGenerativeAIVideoModelId, type GoogleVideoModelOptions as GoogleGenerativeAIVideoProviderOptions, type GoogleImageModelOptions, type GoogleInteractionsAgentName, type GoogleInteractionsModelId, type GoogleInteractionsProviderMetadata, type GoogleLanguageModelInteractionsOptions, type GoogleLanguageModelOptions, type GoogleProvider, type GoogleProviderMetadata, type GoogleProviderSettings, type GoogleSpeechModelId, type GoogleSpeechModelOptions, type GoogleVideoModelId, type GoogleVideoModelOptions, VERSION, createGoogle, createGoogle as createGoogleGenerativeAI, google };

package/dist/index.js

@@ -7,7 +7,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "4.0.0-canary.80" : "0.0.0-test";
+var VERSION = true ? "4.0.0" : "0.0.0-test";
 
 // src/google-embedding-model.ts
 import {
@@ -1484,11 +1484,25 @@ function parsePath(rawPath) {
   }
   return segments;
 }
+var hasOwn = Object.prototype.hasOwnProperty;
+function hasOwnProperty(obj, key) {
+  return hasOwn.call(obj, key);
+}
+function defineOwnProperty(obj, key, value) {
+  Object.defineProperty(obj, key, {
+    value,
+    enumerable: true,
+    configurable: true,
+    writable: true
+  });
+}
 function getNestedValue(obj, segments) {
   let current = obj;
   for (const pathSegment of segments) {
     if (current == null || typeof current !== "object") return void 0;
-    current = current[pathSegment];
+    const currentRecord = current;
+    if (!hasOwnProperty(currentRecord, pathSegment)) return void 0;
+    current = currentRecord[pathSegment];
   }
   return current;
 }
@@ -1497,12 +1511,16 @@ function setNestedValue(obj, segments, value) {
   for (let i = 0; i < segments.length - 1; i++) {
     const pathSegment = segments[i];
     const nextSeg = segments[i + 1];
-    if (current[pathSegment] == null) {
-      current[pathSegment] = typeof nextSeg === "number" ? [] : {};
+    if (!hasOwnProperty(current, pathSegment) || current[pathSegment] == null) {
+      defineOwnProperty(
+        current,
+        pathSegment,
+        typeof nextSeg === "number" ? [] : {}
+      );
     }
     current = current[pathSegment];
   }
-  current[segments[segments.length - 1]] = value;
+  defineOwnProperty(current, segments[segments.length - 1], value);
 }
 function resolvePartialArgValue(arg) {
   var _a, _b;
@@ -3314,6 +3332,7 @@ import {
   createJsonResponseHandler as createJsonResponseHandler5,
   delay as delay2,
   getFromApi as getFromApi2,
+  isSameOrigin,
   parseProviderOptions as parseProviderOptions5,
   postJsonToApi as postJsonToApi4,
   resolve as resolve4
@@ -3519,7 +3538,7 @@ var GoogleVideoModel = class {
     const apiKey = resolvedHeaders == null ? void 0 : resolvedHeaders["x-goog-api-key"];
     for (const generatedSample of response.generateVideoResponse.generatedSamples) {
       if ((_h = generatedSample.video) == null ? void 0 : _h.uri) {
-        const urlWithAuth = apiKey ? `${generatedSample.video.uri}${generatedSample.video.uri.includes("?") ? "&" : "?"}key=${apiKey}` : generatedSample.video.uri;
+        const urlWithAuth = apiKey && isSameOrigin(generatedSample.video.uri, this.config.baseURL) ? `${generatedSample.video.uri}${generatedSample.video.uri.includes("?") ? "&" : "?"}key=${apiKey}` : generatedSample.video.uri;
         videos.push({
           type: "url",
           url: urlWithAuth,
@@ -6477,7 +6496,6 @@ var GoogleInteractionsLanguageModel = class _GoogleInteractionsLanguageModel {
     const { args, warnings, isAgent, pollingTimeoutMs } = await this.getArgs(options);
     const url = `${this.config.baseURL}/interactions`;
     const mergedHeaders = combineHeaders8(
-      INTERACTIONS_API_REVISION_HEADER,
       this.config.headers ? await resolve6(this.config.headers) : void 0,
       options.headers
     );
@@ -6558,7 +6576,6 @@ var GoogleInteractionsLanguageModel = class _GoogleInteractionsLanguageModel {
     const { args, warnings, isBackground, pollingTimeoutMs } = await this.getArgs(options);
     const url = `${this.config.baseURL}/interactions`;
     const mergedHeaders = combineHeaders8(
-      INTERACTIONS_API_REVISION_HEADER,
       this.config.headers ? await resolve6(this.config.headers) : void 0,
       options.headers
     );
@@ -6678,9 +6695,6 @@ var GoogleInteractionsLanguageModel = class _GoogleInteractionsLanguageModel {
     };
   }
 };
-var INTERACTIONS_API_REVISION_HEADER = {
-  "Api-Revision": "2026-05-20"
-};
 function pruneUndefined(obj) {
   const result = {};
   for (const [key, value] of Object.entries(obj)) {
@@ -6692,6 +6706,9 @@ function pruneUndefined(obj) {
 
 // src/realtime/google-realtime-event-mapper.ts
 import { safeParseJSON } from "@ai-sdk/provider-utils";
+function isRecord(value) {
+  return value != null && typeof value === "object" && !Array.isArray(value);
+}
 var GoogleRealtimeEventMapper = class {
   constructor() {
     this.turnCounter = 0;
@@ -6886,6 +6903,11 @@ var GoogleRealtimeEventMapper = class {
           }
         };
       case "input-audio-commit":
+        return {
+          realtimeInput: {
+            audioStreamEnd: true
+          }
+        };
       case "input-audio-clear":
       case "response-create":
       case "response-cancel":
@@ -6970,8 +6992,18 @@ function buildGoogleSessionConfig(config, modelId) {
   if ((config == null ? void 0 : config.outputAudioTranscription) != null) {
     setup.outputAudioTranscription = {};
   }
-  if ((config == null ? void 0 : config.providerOptions) != null) {
-    Object.assign(setup, config.providerOptions);
+  if ((config == null ? void 0 : config.providerOptions) == null) {
+    return setup;
+  }
+  const { google: google2, ...providerOptions } = config.providerOptions;
+  Object.assign(setup, providerOptions);
+  const googleOptions = isRecord(google2) ? google2 : void 0;
+  if ((googleOptions == null ? void 0 : googleOptions.translationConfig) != null) {
+    const target = isRecord(setup.generationConfig) ? setup.generationConfig : generationConfig;
+    setup.generationConfig = {
+      ...target,
+      translationConfig: googleOptions.translationConfig
+    };
   }
   return setup;
 }