CHANGELOG.md

Changelog

2.30.0 (2026-10-14)

Features

• interactions: add gemini-4-argon to Model enum (8a3c307)

Bug Fixes

• clear continuation state and preserve prompt feedback when continuation hop returns no candidates (e63d1f1)
• fix the grounding metadata merging for automatic continuation in generate content and generate content stream (6bfba87)
• make continuation streams retry dropped hops, stop on prompt_feedback, and keep real errors in generate_content (6bdc0d9)
• type GeminiNextGen signatures with public, importable names (ad3fb89)

2.29.1 (2026-10-13)

Bug Fixes

• concatenate output_text across multi-step model responses in a turn (567cc8a)

2.29.0 (2026-10-13)

Features

• accumulate streaming continuation usage metadata and expose initialPromptTokenCount (dbc961f)
• Add continuation_token to the Interactions interaction.status_update event. (a93776c)
• Add a CONTINUATION_REQUIRED Interaction status (754f71f)
• add billable token counts fields (839ffc2)
• Add startOffset/endOffset to Transcription and interimTranscriptTimestampEnabled to RealtimeInputConfig (bdbf156)
• Add usage in InteractionStatusUpdate events (8892aea)
• automatically consume the continuation token (98637d1)
• cli: update Speakeasy generator to v2.948.0, bump CLI to v0.4.2, and apply CLI overlay fixes (22d53ec)

Bug Fixes

• clear intermediate CONTINUATION finishReason in streaming continuation (22706af)
• do not record incomplete continuation stream turns in curated chat history (81c3c49)
• gemini-api-cli: remove unsupported 2.5 and 1.6 models from Interactions model options and CLI examples (1002720)
• js: do not set initial prompt token count for requests that do not use automatic consumption of continuation token (0885fb9)
• js: fix streaming continuation edge cases (stale token, AbortError, initialPromptTokenCount) (f3d10a6)
• Raise default HTTP timeouts so long-running requests aren't killed client-side (10e850c)
• resume streaming generation from the latest checkpoint continuation token on mid-stream errors or cutoffs (625ac2c)
• Update EnvironmentConfig.env schema to map keys to EnvVar or string. (8478e12)

2.28.0 (2026-10-07)

Features

• Support "allowlist": "disabled" in environment network config. (18bc392)
• update discovery doc (4e996fe)

2.27.0 (2026-10-02)

Features

• add lyria-3.5, gemini-omni-1.1-flash, and gemini-omni-flash-preview to Interactions Model enum (4ce63d1)
• support continuation_token in Interactions (a888ad7)

2.26.0 (2026-10-01)

Features

• support continuation_token in GenerateContent (ac628c5)

2.25.0 (2026-09-30)

Features

• add gcs_metrics_uri for exporting tuning job metrics. (bc085fb)
• Add Gemini 3.8 Flash TTS and Gemini 3.8 Flash Lite TTS models to SDKs (b12dad0)
• genai-sdk: Add environments dedicated module and from_environment support (4d7e80b)
• include labels for LiveClientSetup (d4bcdad)
• support labels for Gemini API GenerateContent (71c3997)

Bug Fixes

• use CreateAgentInteraction for Trigger.interaction and TriggerCreateParams.interaction (c4341e1)

2.24.0 (2026-09-22)

Features

• add sample_audio to Voice in GAOS SDK (d001d18)
• add Voices API resource to GAOS SDK (f97113f)
• expose SpeechMetadata, VoiceConfig.voice, and SpeechAnnotation in public GenAI SDKs (19b7858)
• support field.value_field syntax for map add_union_value annotations. (51d701a)
• update discovery doc (42f9716)
• wire voice into sdk (08b568e)

Bug Fixes

• sanitize path parameter descriptions in GAOS OpenAPI generation (1567962)

2.23.0 (2026-09-16)

Features

• add credential APIs resource to gaos. (0e6410b)
• Add RetrievalCallStep and RetrievalResultStep to interactions schema and SDKs. (d03d569)
• implement environments files upload and download across Python and TypeScript SDKs (3a4c512)
• support custom fetch in HttpOptions (01897b3)
• wire credential APIs resource to sdk. (280da75)

2.22.0 (2026-09-10)

Features

• Add from_environment support for environment copying (01ed17e)

Bug Fixes

• Add @ts-ignore before optional MCP imports in declaration files (7b5ef39)
• Remove unused field from FunctionResultDelta (aeb7453)
• Repair node fallback manifest and complete web entries (0f59bf8)

2.21.0 (2026-09-02)

Features

• Add Gemini 3.8 Flash model to SDKs and update Flash model descriptions (4a969fe)

2.20.0 (2026-08-31)

Features

• Add support for the audio/webm MIME type. (b0e3c5f)
• Add translation_config SDK support for GEAP. (3e1d923)
• add Video Understanding support to the Interactions API (6ddbeba)

Bug Fixes

• Don't set redundant Content-Length on file upload requests (2f5cc7a)
• Don't set redundant Content-Length on file upload requests (2f5cc7a), refs #1718
• expose ProcessingCallStep and ProcessingResultStep in Interactions SDK (b6f8db5)
• Quote setupComplete key in LiveClientMessage (4467faf)

2.19.0 (2026-08-25)

Features

• Add AudioTranscriptionConfigMode (c0a37de)
• add environment files support and scotty file download helper (0d6ee9d)
• Add TYPE_JPEG2000 to VideoContent.MimeType enum (41da204)

Performance Improvements

• Keep the Buffer in the Node tokenizer platform, ~2x faster model parse (11d804a)

2.18.0 (2026-08-19)

Features

• Add mode enum (VERBATIM, SMART) to AudioTranscriptionConfig and TranscriptionConfig. (4c5208b)
• Add enable_data_retention to ToolParallelAiSearch, Add step_count to ReinforcementTuningHyperParameters, Add BidiGenerateContentSetup (f52c208)
• Add IDLE state to live connection status enum and mark REQUIRES_ACTION as deprecated. (2f110f2)
• add video resolution and extension task parameters (39b2a2d)

Bug Fixes

• fix examples (3f631be)

2.17.1 (2026-08-13)

Bug Fixes

• Add gemini-3.7-flash (c495e82)

2.17.0 (2026-08-12)

Features

• Add interaction_status to LiveServerContent (4489991)
• api: make the deferred service tier publicly available on Vertex (9dafee9)
• Make speech_config a structured object. (9c90665)

2.16.0 (2026-08-06)

Features

• Add the Gemini Robotics ER 2 Preview model (5647ced)
• Add TOO_MANY_TOOL_CALLS to FinishReason enum. (a7fa568)
• Add top-level errors array to Interaction resource (iAPI) (b9dfd81)
• Make HttpOptions.timeout a per-attempt deadline in the JS GenAI SDK. (8268806)

Bug Fixes

• Add propertyOrdering auto-population for ResponseSchema and ResponseJsonSchema for Dotnet SDK (e26542f)

2.15.0 (2026-07-30)

Features

• add environment resource (2c911be)
• Support GoogleMaps Tool grounding_types places and routing (52655c1)
• Support per-request retryOptions in the JS GenAI SDK API Client (124b606)
• Wire environment service into genai sdk (70d7938)

2.14.0 (2026-07-28)

Features

• [GenerateContentConfig] Add GenerationConfig.audio_transcription_config and Part.audio_transcription. (4b2e67a)
• Add flat language_codes field to AudioTranscriptionConfig. (cc808eb)
• Allow api key + proj/location for enterprise mode (9c0540a)

Bug Fixes

• add deprecation warnings to Imagen generate_images, edit_images, generate_videos (if using prompt/text/image args), LiveConnectConfig.GenerationConfig which will be removed in the next major version (bb66101)

2.13.0 (2026-07-21)

Features

• A new field custom_vocabulary is added to message .google.cloud.aiplatform.v1beta1.BidiGenerateContentSetup (f32ec0a)
• add model selector (b5d70da)
• interaction-api: add queued status to interaction proto (1b7dd39)
• make ASR fields public in v1main and Interactions (08ef3eb)

2.12.0 (2026-07-15)

Features

• Add AntigravityAgentConfig to OpenAPI schema overlays and regenerate SDKs. (872aa26)
• Add history config. (8666bc2)
• Add support for preserve custom headers for gaos (f96662a)
• add trigger resource (43e0137)
• Add Triggers resource to GoogleGenAI client. (8d520cd)
• interactions: add CodeMenderAgentConfig (4469a85)
• Populate per-modality prompt token count in embedding responses for gemini-embedding-2 (163bf72)

2.11.0 (2026-07-09)

Features

• Add environment_id in network config (85fe0a5)
• Add response_format and Translation_config in GenerationConfig (3f3b7bc)
• add retrieval result step and new fields to maps and search results (ecfdc69)
• Add Tool.exa_ai_search for Gemini Enterprise API (3f3b7bc)
• support Function declarations during Agent Creation (824badf)
• voice consent signature types across all SDK languages. (5fb5354)

Bug Fixes

• interactions: accept both dict and list[dict] for transform (67d2f68)

Code Refactoring

• interactions: remove cached_content, presence_penalty, and frequency_penalty; expose safety_settings and labels (0f414be)

2.10.0 (2026-06-24)

Features

• [Interactions] Add ComputerUse.disabled_safety_policies (a2ca95c)
• [Models] Add ComputerUse.disabled_safety_policies (3618023)
• add usage fields for steps (048db9a)
• add video generation and response format parameters. (84e795c)

2.9.0 (2026-06-19)

Features

• Add audioOffset to VoiceActivity (3bc7d42)
• Add interimInputTranscription to LiveServerContent (3bc7d42)
• Add LanguageAuto, LanguageHints, and adaptationPhrases to AudioTranscriptionConfig (3bc7d42)
• Add ServiceTier to UsageMetadata (1f44b04)
• expose Computer Use API fields (da54ea4)
• interaction-api: Add presence_penalty, frequency_penalty, and cached_content to models.proto (2740a42)
• interaction-api: Rename usage to total_usage in StreamMetadata. (b72db47)
• introduce gaos sdk libs (bfac5d4)

Miscellaneous Chores

• Configure 2.9.0 as the next release (e9968c6)
• Configure a 2.9.0-rc.0 prerelease (ae612ec)

2.8.0 (2026-06-03)

Features

• Add Agent Platform MCP support to async generate_content (baeaeaa)
• Add transcription language code. (d2981d6)
• Add TranslationConfig for live translation. (8c44240)
• Support ReinforcementTuning in GenAI SDK including ValidateReward API method. (36f0bfb)

2.7.0 (2026-05-27)

Features

• Add Skill Registry ListSkills and DeleteSkill to SDK (d75582a)
• additional computer_use field support for vertex. (54a692b)
• interaction-api: Allow "text/csv" as a supported document mime type for Interaction API. (3cc830e)
• interaction-api: Enable BigQuery tool in Deep Research config. (58c8c7e)
• Support Reinforcement Tuning in GenAI SDK (418cc35)

2.6.0 (2026-05-21)

Features

• add enable_prompt_injection_detection for Computer Use feature for the Gemini API. (f780f3c)
• Add budget_exceeded status (1e97bd0)
• Add gemini-3.5-flash (1e97bd0)
• add new fields (b78eeee)

2.5.0 (2026-05-20)

Features

• Add Gemini 3.5 Flash model to options (fcf26e3)

2.4.0 (2026-05-17)

Features

• support Agent and Environment APIs. (b0d9d2b)

Bug Fixes

• output_text for turns that don't end with text. (1a3d94f)

2.3.0 (2026-05-15)

Features

• interaction.{output_text,output_image,output_audio,output_video} (0188233)

2.2.0 (2026-05-12)

Features

• Added missing FunctionCallResultDelta type and arguments field to the ArgumentDelta type (f76138b)

2.1.0 (2026-05-12)

Features

• Add gemini-3.1-flash-lite to model options (b0664e1)
• Add parameters to video response_format. (207c8f8)
• Introduce Server Side tools deltas (2e56d41)
• support Blocking FunctionCall in Live API in AgentPlatform (Vertex) (6bd8e7d)
• Add support for Vertex-lyria models lyria-3-pro-preview & lyria-3-clip-preview (f9af7410)

Bug Fixes

• Steps is not optional (6fb5386)

2.0.1 (2026-05-09)

Bug Fixes

• Update response_format field names to snake_case. (26af549)

2.0.0 (2026-05-07)

⚠ BREAKING CHANGES - Interactions Only

Note: The breaking changes are only in interactions. GenerateContent usage in unaffected. Refer to https://ai.google.dev/gemini-api/docs/interactions-breaking-changes-may-2026 for details

• Add steps for interactions (c0814c4)
• Deprecate legacy response_format and publish new polymorphic field. (68a6809)
• Rename SSE events to interaction.created and interaction.completed (d1b836b)

Bug Fixes

• timeout not functioning (850f680)

1.52.0 (2026-05-04)

Features

• [Python] Multimodal file search (e626bef)
• Multimodal file search (54caf6b)

1.51.0 (2026-04-29)

Features

• [Interactions] Add FileCitation.{custom_metadata,media_id,page_number} (9e08ba9)
• Add output_info to BatchJob (5327c60)
• Add gemini-3.1-flash-tts-preview model to options (35c941b)
• Add ImageResizeMode for GenerateVideos (faa1088)
• Add new Gemini Deep Research agent models (6f83a05)
• Add Vertex Dataset input and output options for batch jobs (6aa848e)
• interaction-api: Add grounding tool usage breakdown to Interaction Usage. (e1c31ad)
• introduce enterprise flag and GOOGLE_GENAI_USE_ENTERPRISE env var (cf7ad52)
• Replace the more ambiguous rate field with sample_rate. (6c80464)

1.50.1 (2026-04-14)

Bug Fixes

• Refactor Webhook types in GenAI SDKs for easier useage (5100abc)
• Rename webhooks.retrieve to webhooks.get. (db6e771)

1.50.0 (2026-04-13)

Features

• Add "eu" as a supported service location for Vertex AI platform. (2493f9c)
• Add DeepResearchAgentConfig fields (3615ca2)
• Add Live Avatar new fields (6a0ff96)
• Add support for new audio MIME types: opus, alaw, and mulaw (7137f13)
• add webhook and webhookConfig for js and python sdk (0f89605)
• Add webhook_config to batches.create() and models.generate_videos() (894bc93)
• Wire the webhook into python and js client. (b6c5d18)

1.49.0 (2026-04-08)

Features

• Introduce TYPE_L16 audio content and optional fields. (c62cb9a)

1.48.0 (2026-03-31)

Features

• Support dedicated TextAnnotationDelta for streaming tool responses (89552ba)

Bug Fixes

• Fix service_tier enums. (9bdc2ae)

1.47.0 (2026-03-27)

Features

• Add custom_metadata to FileSearchResult. (083a1e3)
• Add labels field to Veo configs (930c9c3)
• Add mime type for Audio content (1ad80c6)
• Add model_status to GenerateContentResponse (Gemini API only) (5e1110d)
• Add part_metadata in Part (Gemini API only) (5e1110d)
• Add service tier for interactions. (406de38)
• Add service tier to GenerateContent. (0bfe800)
• Add support for more image and audio MIME types in Interactions content (baadbfd)
• Add supported models to the ModelOptions (94642b6)
• genai: add TURN_INCLUDES_AUDIO_ACTIVITY_AND_ALL_VIDEO to TurnCoverage (fdacac2)
• support hyperparameters in distillation tuning (716e021)
• Support rendered_parts in GroundingSupport (5e1110d)

Bug Fixes

• support us region routing (d391cff)

1.46.0 (2026-03-17)

Breaking changes

• [Interactions] Breaking change to Interactions API to refactor TextContent annotations to use specific citation types (9fa8b1d)
• [Interactions] Breaking change for Interactions, rename ContentDelta unions. (917f24f)
• [Interactions] Breaking change to Interactions API to rename rendered_content to search_suggestions (cc6bd38)

Features

• [Interactions] Add and update 'signature' fields for tool call/result content types. (e73ca5b)
• [Interactions] Support Google Maps in Interactions (d0593e3)
• Support include_server_side_tool_invocations for genai. (c627d6f)

Bug Fixes

• Quote functionResponses key in LiveClientMessage (9740426)

1.45.0 (2026-03-12)

Features

• Add inference_generation_config to EvaluationConfig for Tuning (b4ac722)
• enable language code for audio transcription config in Live API for Vertex AI (67f39ec)

1.44.0 (2026-03-04)

Features

• Add gemini-3.1-flash-image-preview model (175603b)
• Support signature for all Interaction tool types (b79108f)
• Update data types from discovery doc. (249b15a)

1.43.0 (2026-02-26)

Features

• Add gemini-3.1-pro-preview to list of models in Interactions (14775fe)
• Add Image Grounding support to GoogleSearch tool (9187ca7)
• enable server side MCP and disable all other AFC when server side MCP is configured. (c7888c4)
• Support more image sizes and resolutions (54f4145)

Bug Fixes

• change interactions media mime type to enum (breaking change for experimental feature) (7c2d5b2)

1.42.0 (2026-02-18)

Features

• Support multimodal embedding for Gemini Embedding 2.0 and support MaaS models in Models.embed_content() (Vertex AI API) (944ae97)

1.41.0 (2026-02-10)

Features

• Add HTTP retry support to the SDK (37d4f2e)
• Add INCOMPLETE status to Interaction. (519f837)
• Pass retry options to the underlying Interactions client (086cf82)
• Support encryption_spec in tuning job creation configuration for GenAI SDK (e218add)

1.40.0 (2026-02-04)

Features

• Update data types from discovery doc. (bad81a7)

1.39.0 (2026-01-30)

Features

• Add include_input query parameter to Get Interaction endpoint. (84bc7f4)
• Add registerFiles for you can use gcs files with mldev. (7acf3e0)
• Support distillation tuning (c9a2e72)
• Support OSS Tuning in GenAI SDK (258f211)

Bug Fixes

• Add metadata in batch inlined response (0e95bb7)

1.38.0 (2026-01-20)

Features

• Add ModelArmorConfig support for prompt and response sanitization via the Model Armor service (be65c24)
• Allow custom endpoints for authentication with Vertex AI in Typescript (891e32d), closes #1137
• Update data types from discovery doc. (a16a180)
• Update data types from discovery doc. (a4eaa8c)

1.37.0 (2026-01-15)

Features

• Support 4:5 and 5:4 aspect ratio in Interactions (5294da2)

1.36.0 (2026-01-14)

Features

• Add FileSearchCallContent to Interactions (ccf11a4)
• Add ImageConfig to GenerationConfig for image generation in Interactions (f34b6fb)
• Support JS local tokenizer (bb429ad)
• voice activity support (3ad1011)

1.35.0 (2026-01-07)

Features

• [Python] add RegisterFiles so gcs files can be used with genai. (1bf555c)
• Add PersonGeneration to ImageConfig for Vertex Gempix (b0753d7)

1.34.0 (2025-12-16)

Features

• Add minimal and medium thinking levels. (19f8969)
• Add support for Struct in ToolResult Content. (750a4f7)
• Add ultra high resolution to the media resolution in Parts. (fa9a99e)
• Add ULTRA_HIGH MediaResolution and new ThinkingLevel enums (b8a7d8c)
• Define and use DocumentMimeType for DocumentContent (c2f118d)
• support multi speaker for Vertex AI (94d681b)

1.33.0 (2025-12-11)

Features

• Add IMAGE_RECITATION and IMAGE_OTHER enum values to FinishReason (ab87f51)
• Add voice activity detection signal. (bff9695)
• Make the Interactions API public. (a8dd67b)

1.32.0 (2025-12-09)

Features

• Add enableEnhancedCivicAnswers feature in GenerateContentConfig (b429389)
• Support ReplicatedVoiceConfig (7a56e35)

Bug Fixes

• Improve stream parsing performance (c9c1359)

1.31.0 (2025-12-03)

Features

• Add empty response for tunings.cancel() (5dc25bc)

1.30.0 (2025-11-18)

Features

• add display name to FunctionResponseBlob (81036ed)
• add display name to FunctionResponseFileData (564f718)
• Add generate_content_config.thinking_level (4e586df)
• Add image output options to ImageConfig for Vertex (fff5fb6)
• Add part.media_resolution (4e586df)
• support Function call argument streaming for all languages (b3b94f6)

1.29.1 (2025-11-12)

Bug Fixes

• Add missing fields to the model types (8937903)
• Don't generate warnings from response.text property because of thought_signature. (356b843)
• Fix base_steps parameter for recontext_image (946415f)

1.29.0 (2025-11-05)

Features

• add complete stats to BatchJob (3263514)
• Add FileSearch tool and associated FileSearchStore management APIs (05cff8c)
• Add FileSearch tool and associated FileSearchStore management APIs (25aa2a4)
• Add image_size to ImageConfig (Early Access Program) (e1e883a)
• Added phish filtering feature. (4b75e5d)
• update the build configs (97a2fac)

Bug Fixes

• disable AFC when there are AFC incompatible tool presented. (30c63b4)

1.28.0 (2025-10-29)

Features

• Add safety_filter_level and person_generation for Imagen upscaling (aaceb1b)
• Add support for preference optimization tuning in the SDK. (f74660e)
• Pass file name to the backend when uploading with a file path (7115726)
• support default global location when not using api key with vertexai backend (f8967b1)
• Update test-server-sdk dependency to ^0.2.9. (8d507bf)

Bug Fixes

• Fix downloader. With this change after you await the download, the file write is complete, and the data is fully readable. (127c9bf)

1.27.0 (2025-10-23)

Features

• Remove redundant calls to rollup/api-extractor, speeds up the TS SDK testing further by a factor of 2. (009b75f)

Bug Fixes

• google auth ADC error (f87611c)

1.26.0 (2025-10-21)

Features

• Add enable_enhanced_civic_answers in GenerationConfig (0e95d72)
• support jailbreak in HarmCategory and BlockedReason (cd79a83)

1.25.0 (2025-10-15)

Features

• Support video extension for Veo on Gemini Developer API (5d11d81)

1.24.0 (2025-10-10)

Features

• Enable Google Maps tool for Genai. (b671fe9)
• Support enableWidget feature in GoogleMaps (81ed6a3)
• Support Gemini batch inline request's metadata and add test coverage to safety setting (722562b)

1.23.0 (2025-10-08)

Features

• Add NO_IMAGE enum value to FinishReason (5305334)
• Add labels field to Imagen configs (1e9e96c)
• Add utility methods for creating FunctionResponsePart and creating FunctionResponse Part with FunctionResponseParts (5a0ce38)
• Enable Ingredients to Video and Advanced Controls for Veo on Gemini Developer API (Early Access Program) (d5bd0c1)

Bug Fixes

• support system_instruction and tools mapping via converter and cleanup handwritten mapping (54ec204)

1.22.0 (2025-10-02)

Features

• Add ImageConfig to GenerateContentConfig (c137172)
• Add thinking_config for live (decc090)
• rename ComputerUse tool (early access) (e4345f9)

1.21.0 (2025-09-25)

Features

• Add FunctionResponsePart & ToolComputerUse.excludedPredefinedFunctions (61620f6)
• Support Imagen 4 Ingredients on Vertex (56cccfc)

Bug Fixes

• #963 allow leading whitespace before data chunks (24f4153)
• Expose JOB_STATE_RUNNING and JOB_STATE_EXPIRED for Gemini Batches states (b513c69)
• initialization of pre_tuned_model_checkpoint_id from tuning config. (2e10e7f)

1.20.0 (2025-09-16)

Features

• Add 'turn_complete_reason' and 'waiting_for_input' fields. (cb54332)
• Add VideoGenerationMaskMode enum for Veo 2 Editing (3e850fd)

1.19.0 (2025-09-09)

Features

• Add labels to create tuning job config (220c4d6)
• Support Veo 2 Editing on Vertex (6e34fd0)

Bug Fixes

• Enable id field in FunctionCall for Vertex AI. (7c6e047)

1.18.0 (2025-09-09)

Features

• generate the function_call class's converters (e57a7bc)
• Implement embed content batches. (9cb8613)

1.17.0 (2025-09-02)

Features

• Add resolution field for Gemini Developer API Veo 3 generation (5ce467b)

1.16.0 (2025-08-27)

Features

• add sdkHttpResponse.headers to *Delete responses. (397c602)
• Add add_watermark field for recontext_image (Virtual Try-On, Product Recontext) (e182fe8)
• Add output_gcs_uri to Imagen upscale_image (8db102a)
• add outputSchema support for MCP (e2d4e50)
• Add VALIDATED mode into FunctionCallingConfigMode (af410e7)
• Add VideoGenerationReferenceType enum for generate_videos (eb17013)
• Support GenerateVideosSource for Veo GenerateVideos (2241749)
• support tunings.cancel in the genai SDK for Python, Java, JS, and Go (2d67d25)
• Update server test recordings to JSON. (dd0a033)

Bug Fixes

• js: empty env vars should be treated as undefined. (16a80c0)

1.15.0 (2025-08-18)

Features

• Support Imagen image segmentation on Vertex (6b86bae)
• Support Veo 2 Reference Images to Video Generation on Vertex (6bca6ad)

Bug Fixes

• chats: Drop the validation on part with empty text (d2602d2)
• Fix the bug to support Gemini Batch inlined requests system instruction (843c774)

1.14.0 (2025-08-13)

Features

• add an _exclude_fields characteristic in the config for unused values to avoid unnecessary and unused code in converter and type generation. (15a4504)
• enable continuous fine-tuning on a pre-tuned model in the SDK. (027f09d)
• support document name in grounding metadata (b801236)
• Support exclude_domains in Google Search and Enterprise Web Search (8ed49f1)

Bug Fixes

• Replace gemini-2.5-flash-preview-04-17 with gemini-2.5-flash. (d7f1c30)

1.13.0 (2025-08-06)

Features

• Add image_size field for Gemini Developer API Imagen 4 generation (9841ecb)
• Add Lyria enum for music generation mode for vocalization (b05821f)
• allow methods in batch to return headers in sdk_http_response by default (55a2be4)
• enable responseId for Gemini Developer API (40e3a58)
• Support image recontext on Vertex (e417867)
• Support new enum types for UrlRetrievalStatus (88b47e6)

1.12.0 (2025-07-30)

Features

• allow methods in models to return headers in sdk_http_response by default. (efdcb8a)
• allow methods in tuning to return headers in sdk_http_response by default (f81c16a)

Bug Fixes

• Correctly populated the Rai filter reasons on Video Generation (316cdb0)

1.11.0 (2025-07-23)

Features

• Add image_size field for Vertex Imagen 4 generation (b6cc23e)
• enable function calling for Callable Tool besides McpClient in generateContent. (90565bd)
• Introduced Operations.get() which is a generic function to handle all Operation types. (a6f85c1)
• return headers for list method in all modules. (e8591a3)
• Updates to codegen instructions to improve performance for TypeScript (9c97ec6)

1.10.0 (2025-07-17)

Features

• Add addWatermark parameter to the edit image configuration. (16bca99)
• Adding codegen instructions to guide LLMs to generate code with the Google GenAI SDK (7f74175)
• Update hasMcpToolUsage to set the MCP tool usage when it is detected by calling mcpToTool (a70f9c4)

Bug Fixes

• live: enhance security by moving api key from query parameters to header (f183b7d)
• live: Rollback commit f183b7d, breaks live in web env (be24e86)

1.9.0 (2025-07-09)

Features

• Add new languages for Imagen 4 prompt language (65be769)

Bug Fixes

• add unref() for request timeouts (6b76c4b)

1.8.0 (2025-07-01)

Features

• Enable Vertex Multimodal Dataset as input to supervised fine-tuning. (055b435)
• Support Batches delete (6cd9174)
• Support different media input in Vertex Live API (305952e)

1.7.0 (2025-06-25)

Features

• Add compressionQuality enum for generate_videos (4325773)
• Add enhance_input_image and image_preservation_factor fields for upscale_image (13eedda)
• Batches support in TS (dd7355e)
• expose the responseJsonSchema in GenerateContentConfig (db54a5f)

Bug Fixes

• live: support ArrayBuffer in WebSocket messages (5a8aeac), closes #714

1.6.0 (2025-06-21)

Features

• allow users to access headers for generateContent method and generateContentStream (f5f0e02)
• enable json schema for controlled output and function declaration. (7d53d57)
• Include status code and export HTTP errors (bcabcb6)
• support extra_body in HttpOptions (1d48b6e)

Bug Fixes

• Fix build errors when the mcp package is not installed. (5b7e695)

1.5.1 (2025-06-13)

Bug Fixes

• Update MCP dependencies to be type-only (648019b)

1.5.0 (2025-06-11)

Features

• add a timeout parameter to CallableToolConfig (06f31fd)
• Add datastore_spec field for VertexAISearch (1b18a52)
• Add support for Veo frame interpolation and video extension (53f22e6)
• Make the MCP SDK an optional peer dependency. (2472fd3)
• RAG - Introducing context storing for Gemini Live API. (bdc2355)

Bug Fixes

• Prioritize credentials over implicit api key (from env) for node client using Vertex AI (d82aba2), closes #616

1.4.0 (2025-06-04)

Features

• Add enhance_prompt field for Gemini Developer API generate_videos (ea3cc8e)
• Enable url_context for Vertex (e377f58)
• js: Support GEMINI_API_KEY as environment variable for setting API key. (97850ad)

Bug Fixes

• defined Type becomes TYPE_UNSPECIFIED when obfuscation is enabled (1ddf4f5)
• Update live SDK sample to address choppy audio quality (319bcbb)
• use Enum's value instead of keys for obfuscation. (132bd04)

1.3.0 (2025-05-30)

Features

• Adding thought_signature field to the Part to store the signature for thoughts. (20815b2)
• include UNEXPECTED_TOOL_CALL enum value to FinishReason for Vertex AI APIs. (bd5a2bf)
• Support ephemeral auth tokens as API keys for live connections in TS. (507bfb5)
• Support ephemeral token creation in TS (425cfe6)

Bug Fixes

• Rename LiveEphemeralParameters to LiveConnectConstraints. (86e9652)

1.2.0 (2025-05-28)

⚠ BREAKING CHANGES TO EXPERIMENTAL FEATURES

• Remove unsupported Lyria enum for music generation mode

Features

• Add generate_audio field for private testing of video generation (37e14c5)

Documentation

• fix README typo (04259ad)

Miscellaneous Chores

• Remove unsupported Lyria enum for music generation mode (0b935cd)

1.1.0 (2025-05-26)

Features

• Add CommonJS modules (f40c47c)
• support new fields in FileData, GenerationConfig, GroundingChunkRetrievedContext, RetrievalConfig, Schema, TuningJob, VertexAISearch, (cd04548)

1.0.1 (2025-05-22)

Note

This version drops support for end-of-life Node.js v18.

Bug Fixes

• After an error on sendMessage, all subsequent calls fail with the same error (778abcc)
• Fixed sendMessage subsequent calls test to follow the arrange-act-assert pattern (778abcc)
• Unbreak direct requires from node. (023efd5)

1.0.0 (2025-05-19)

⚠ BREAKING CHANGES

• Fix Lyria method name for JS, update parameters type

Features

• Support ephemeral token creation in Python (8e12730)
• Support using ephemeral token in Live session connection in Python (8e12730)

Bug Fixes

• allow McpClient to be passed in with AFC disabled. (b13f1f8)
• Blob handling in realtime music (f760755)
• Prevent MCP label from being appended multiple times if they already exist (c59ffe7)

Documentation

• No longer preview. (5e137d4)

Miscellaneous Chores

• Fix Lyria method name for JS, update parameters type (99dba6e)

0.15.0 (2025-05-19)

Features

• add time range filter to Google Search Tool (a938111)
• Add basic support for async function calling. (8e2f357)
• Add CallableToolConfig to specify behavior for FunctionDeclarations (c4148d0)
• add configurations for afc. (ce7855b)
• add live proactivity_audio and enable_affective_dialog (20e3892)
• Add Lyria Realtime music generation support for JS (aefcaa5)
• Add Lyria Realtime Music Types (99255d8)
• Add MCP telemetry usage to TS SDK. (09a83e9)
• add multi-speaker voice config (6fe6074)
• Add support for lat/long in search. (4cd79f6)
• Add support for MCP in TS SDK. (921a4be)
• add support for propertyOrdering field. (a77822b)
• Add Video FPS, and enable start/end_offset for MLDev (19f20e9)
• Enable AFC on Generate content stream (ff2ce35)
• export the createJsonSchemaValidator methods to be available for other library. (b3359a1)
• List all mcp tools to max and mcpToTool taking a spread. (44cd9c9)
• MCP: Add a new interface for automatic function calling (dc49ffc)
• MCP: Add mcpToTool to pass MCP clients for automatic function calling (825f385)
• Remove MCP Tool and MCP Client from ToolUnion (d35e16d)
• support customer-managed encryption key in cached content (3e7437a)
• Support Url Context Retrieval tool (aaaf9a9)

Bug Fixes

• Add an ES module for node environments. (ff4bbd1)
• Add default headers to model calls when MCP is enabled (9442eea)
• Allow contents with no-text thoughts in chat history (4112d1c)
• chats: Enforce internal management of chat history (abe592f)
• chats: Relax the constraint on chat turns (68115a8)
• make the system-test build. (dd7154c)
• move test-server-sdk from dependencies to devDependencies (233a909)
• Move test-server-sdk to devDependencies (#574) (b64deeb)
• Run tests against Node 24 (28a56ac)
• Skip MCP tool call when function name not present in the tool (9f3d360)

0.14.1 (2025-05-15)

Bug Fixes

• Move test-server-sdk to devDependencies (#574) (5913e59)

0.14.0 (2025-05-13)

Features

• Add Imagen edit_image support in JS SDK (6c99936)
• Add Imagen upscale_image support for JS (6fe1a68)
• add support for audio, video, text and session resumption in java. (e5542c6)
• support display_name for Blob class when calling Vertex AI (fc35f51)
• Support tuning checkpoints (6bd9c9e)

0.13.0 (2025-05-07)

Features

• Add text and data accessors to LiveServerMessage (a3c4201)
• Add Tool.enterprise_web_search field (29b097d)
• Add a models.list function to list available models. (477d9ec)
• Add Files.download method. (8f44c99)
• Add support for Grounding with Google Maps (41f0cc2)
• enable input transcription for Gemini API. (767c5d5)
• Support global location (fixes #502) (ff906fb)

Bug Fixes

• add retry logic for missing X-Goog-Upload-Status header for js (8cf039e)

0.12.0 (2025-04-30)

Features

• add support for live grounding metadata (f5ed429)

0.11.0 (2025-04-30)

Features

• add models.delete and models.update to manage tuned models (0766718)
• Added support for Tuning operations (d5a035f)
• make min_property, max_property, min_length, max_length, example, patter fields available for Schema class when calling Gemini API (5f91ee7)

Bug Fixes

• Apply converters to list items when the API value isn't an array (249769f)
• chats: Properly handle streaming errors to not throw an error that couldn't be caught, which might result in crash in web. Fixes #487 (0b62e15)
• CI: Fix docs generation for release event (899969e)
• Clean the CHANGELOG to remove the changes not included in the bundle. (89b1d66)
• do not raise error for default field in Schema for Gemini API calls (6f72396)
• Don't transform lists twice (249769f)

0.10.0 (2025-04-23)

Features

• add additional realtime input fields (2150416)
• Add helper function GenerateContentResponse.data to return concatenation of all inline data parts. (97b59a2)
• Allow users to set AbortSignal inside per request config to cancel http request (c44f48d)
• support default field in Schema when users call Gemini API (2e61cce)
• Support setting the default base URL in clients via setDefaultBaseUrls() (df978b8)
• Use ws:// for websockets established over http base URLs. (774505b)

Bug Fixes

• Return actual error text from streaming response (808e0b5), closes #346
• Update _api_client to parse and throw errors during processing stream responses (fixes #461) (1932f1d)

0.9.0 (2025-04-17)

⚠ BREAKING CHANGES

• Simplified the types allowed on the generateContent contents parameter.

Features

• add a helper module to process zod objecsts. (fad2789)
• add support for model_selection_config to GenerateContentConfig (37a9cae)
• Expose transcription configurations for audio in TS, and move generationConfig to the top level LiveConnectConfig (d3a841d)
• Simplified the types allowed on the generateContent contents parameter. (324d158)
• Support audio transcription in Vertex Live API (8d11c04)
• Support RealtimeInputConfig, and language_code in SpeechConfig in python (004ff6a)
• Update VertexRagStore (043d06c)

Bug Fixes

• CI: Fix stable docs generation with release event (89c61b9)

0.8.0 (2025-04-09)

Features

• Add domain to Web GroundingChunk (dc56670)
• Add generationComplete notification to LiveServerContent (4d9811b)
• add session resumption to live module (b5c6975)
• add session resumption. (fff2b66)
• Add thinking_budget to ThinkingConfig for Gemini Thinking Models (76e0e18)
• Add traffic type to GenerateContentResponseUsageMetadata (d84156e)
• Add types for configurable speech detection (fc861bc)
• Add types to support continuous sessions with a sliding window (0fd8256)
• Add UsageMetadata to LiveServerMessage (67b34f7)
• expose generation_complete, input/output_transcription & input/output_audio_transcription to SDK for Vertex Live API (1e8be50)
• merge GenerationConfig into LiveConnectConfig (d25d77d)
• Populate X-Server-Timeout header when a request timeout is set. (6f00495)
• support media resolution (9ebd58b)
• Support models.get() for getting model information (fc62381)
• Update Live converters to pass along configurable speech detection parameters (8301fa2)
• Update Live converters to pass along params to support continuous sessions with a sliding window (3814d92)

Bug Fixes

• Use authentication headers as provided by google-auth-library (94b11a1)

0.7.0 (2025-03-27)

⚠ BREAKING CHANGES

• Change File.sizeBytes from number type to string type

Features

• Add experimental generate_video support (0fa1f05)
• add MediaModalities for ModalityTokenCount (9869098)

Bug Fixes

• Change File.sizeBytes from number type to string type (184c7db)
• Update tLiveClienttToolResponse() to accept FunctionResponse[] (4cab8bf)

0.6.1 (2025-03-25)

Features

• Add engine to VertexAISearch (69dfbaf)
• allow title property to be sent to Gemini API. Gemini API now supports the title property, so it's ok to pass this onto both Vertex and Gemini API. (c5855a3)
• implement files.delete for JS client SDK. (4ac44de)
• Save prompt safety attributes in dedicated field for generate_images (1a774fa)

Bug Fixes

• schema transformer logic fix. (6311f60)

0.6.0 (2025-03-20)

⚠ BREAKING CHANGES

• Unexport Content converter functions

Features

• add IMAGE_SAFTY enum value to FinishReason (81ae907)

Code Refactoring

• Separate converter functions to dedicated _{module}_converters.ts file for readability (bb9ba98)

0.5.0 (2025-03-20)

⚠ BREAKING CHANGES

• Make "turnComplete:true" the default.

Features

• Add sendClientContent, sendRealtimeInput, sendToolResponse to live session (e7ec3c0)
• Make "turnComplete:true" the default. (5f77e3e)
• Support Google Cloud Express for Vertex AI (e15c7f3)
• support new UsageMetadata fields (fe000ed)
• Support Vertex AI on browser runtimes (e15c7f3)
• Upgrade the SDK launch stage to preview. (da38b6d)

0.4.0 (2025-03-14)

⚠ BREAKING CHANGES

• remove the createPartFromVideoMetadata usability function.

Features

• enable union type for Schema when calling Gemini API. (180983c)
• Provide a better error message when trying to use VertexAI in browsers. (1ab1402)
• Support returned safety attributes for generate_images (a0e0fcf)
• throw exception when given method is not supported in Gemini API or Vertex AI (96ccb6f)

Bug Fixes

• remove the createPartFromVideoMetadata usability function. (d660a7f)

0.3.1 (2025-03-11)

0.3.0 (2025-03-11)

⚠ BREAKING CHANGES

• Make file.upload use named parameters.

Features

• Enable Live for Vertex AI. (2bda9d4)

Bug Fixes

• Set web as the browser entry points for bundlers that don't support the exports key (18cb728)

Miscellaneous Chores

• Make file.upload use named parameters. (60433f4)