v1.133.0

Compare Source

Features

• Deprecate tuning public preview SDK in favor of tuning SDK (35d362c)
• GenAI SDK client - Enabling Few-shot Prompt Optimization by passing either "OPTIMIZATION_TARGET_FEW_SHOT_RUBRICS" or "OPTIMIZATION_TARGET_FEW_SHOT_TARGET_RESPONSE" to the optimize_prompt method (715cc5b)
• GenAI SDK client(memory): Add enable_third_person_memories (65717fa)
• Support Developer Connect in AE (04f1771)

Bug Fixes

• Add None check for agent_info in evals.py (c8c0f0f)
• GenAI client(evals) - Fix TypeError in _build_generate_content_config (be2eaaa)
• Make project_number to project_id mapping fail-open. (f1c8458)
• Replace asyncio.run with create_task in ADK async thread mains. (83f4076)
• Replace asyncio.run with create_task in ADK async thread mains. (8c876ef)
• Require uri or staging bucket configuration for saving model to Vertex Experiment. (5448f06)
• Return embedding metadata if available (d9c6eb1)
• Update examples_dataframe type to PandasDataFrame in Prompt Optimizer. (a2564cc)

v1.132.0

Compare Source

Features

• Add Lustre support to the Vertex Training Custom Job API (71747e8)
• Add Lustre support to the Vertex Training Custom Job API (71747e8)

Documentation

• A comment for field restart_job_on_worker_restart in message .google.cloud.aiplatform.v1beta1.Scheduling is changed (71747e8)
• A comment for field timeout in message .google.cloud.aiplatform.v1beta1.Scheduling is changed (71747e8)

v1.131.0

Compare Source

Features

• Allow list of events to be passed to AdkApp.async_stream_query (dd8840a)
• GenAI Client(evals) - Support CustomCodeExecution metric in Vertex Gen AI Eval Service (4114728)
• Updates the ADK template to direct structured JSON logs to standard output. (a65ec29)

Bug Fixes

• Fix RagManagedVertexVectorSearch when using backend_config (df0976e)
• GenAI Client(evals) - patch for vulnerability in visualization (8a00d43)

v1.130.0

Compare Source

Features

• A new field min_gpu_driver_version is added to message .google.cloud.aiplatform.v1beta1.MachineSpec (26dfdfe)
• Adding RagManagedVertexVectorSearch Vector DB option for RAG corpuses to SDK (da79e21)
• Expose FullFineTunedResources for full fine tuned deployments (26dfdfe)
• Expose zone when creating a FeatureOnlineStore (26dfdfe)
• GenAI Client(evals) - Add support to local agent run for agent eval (30e41d0)
• GenAI SDK client(memory): Add PurgeMemories (95eb10f)
• Introduce RagManagedVertexVectorSearch as a new vector db option (26dfdfe)

Documentation

• Update ReplicatedVoiceConfig.mime_type comment (26dfdfe)
• Update ReplicatedVoiceConfig.mime_type comment (26dfdfe)

v1.129.0

Compare Source

⚠ BREAKING CHANGES

• An existing field transfer_to_agent is removed from message .google.cloud.aiplatform.v1beta1.EventActions
• updating bigtable_metadata field name in FeatureOnlineStore
• updating enableDirectBigtableAccess field name in FeatureOnlineStore`
• updating bigtable_metadata field name in FeatureView

Features

• Add gpu_partition_size in machine_spec v1 api (e0bc3d8)
• Add ReplicatedVoiceConfig to VoiceConfig to enable Gemini TTS voice replication (e0bc3d8)
• Add ReplicatedVoiceConfig to VoiceConfig to enable Gemini TTS voice replication (e0bc3d8)
• Add EmbedContent method v1 (e0bc3d8)
• Add EmbedContent method v1beta1 (e0bc3d8)
• Add FunctionResponsePart and excluded_predefined_functions in ComputerUse (e0bc3d8)
• Add FunctionResponsePart and excluded_predefined_functions in ComputerUse (e0bc3d8)
• Add new fields SUCCESSFULLY_DEPLOYED and FAILED_TO_DEPLOY to DeploymentStage (e0bc3d8)
• Add new fields SUCCESSFULLY_DEPLOYED and FAILED_TO_DEPLOY to DeploymentStage (e0bc3d8)
• Add order_by to list_events (e0bc3d8)
• Add support for developer connect based deployment (e0bc3d8)
• Add support for developer connect based deployment (e0bc3d8)
• Continuous Tuning (e0bc3d8)
• Enable Vertex Model Garden Managed OSS Fine Tuning. (26b7e51)
• GenAI Client(evals) - Add location override parameter to run_inference and evaluate methods (b867043)
• GenAI Client(evals) - support setting autorater generation config for predefined rubric metrics (9304f15)
• GenAI SDK client(multimodal) - Support Assess Tuning Resource for multimodal dataset. (bc26160)
• GenAI SDK client(sessions): Add label to Sessions (837c8ea)

Bug Fixes

• Add OTel cloud.provider attribute to AdkTemplate (7d3bcdd)
• Add support for app in _init_session (d9f6c58)
• An existing field transfer_to_agent is removed from message .google.cloud.aiplatform.v1beta1.EventActions (e0bc3d8)
• Correlate traces with logs in Cloud Trace panel on adk deploy agent_engine (9301551)
• Enable from vertexai.types import TypeName without needing to run from vertexai import types first (46285bf)
• Enable from vertexai.types import TypeName without needing to run from vertexai import types first (f4a6cbe)
• Gen AI SDK client - Fix bug in GCS bucket creation for new agent engines. (8d4ce38)
• GenAI SDK client(eval) - Reorder the params to put the Config param at the last place. (e8b12cb)
• Save artifact in init_session (2a43e9b)
• Update default input and output modes in create_agent_card (7ca4226)
• Updating bigtable_metadata field name in FeatureOnlineStore (e0bc3d8)
• Updating bigtable_metadata field name in FeatureView (e0bc3d8)
• Updating enableDirectBigtableAccess field name in FeatureOnlineStore` (e0bc3d8)

Documentation

• A comment for field filter in message .google.cloud.aiplatform.v1beta1.ListSessionsRequest is changed (e0bc3d8)
• A comment for field package_spec in message .google.cloud.aiplatform.v1.ReasoningEngineSpec is changed (e0bc3d8)
• A comment for field package_spec in message .google.cloud.aiplatform.v1beta1.ReasoningEngineSpec is changed (e0bc3d8)
• A comment for message ReasoningEngineSpec is changed (e0bc3d8)
• A comment for message ReasoningEngineSpec is changed (e0bc3d8)
• Fix idle_scaledown_period minimum from 3600 to 300 (5 minutes) (e0bc3d8)
• Remove comments for a non public feature (e0bc3d8)

Miscellaneous Chores

• Release 1.129.0 (89db338)

v1.128.0

Compare Source

Features

• GenAI Client(evals) - Add pass_rate to AggregatedMetricResult and calculate it for adaptive rubric metrics. (1f1f67e)
• GenAI SDK client - Support build options in Agent Engine GCS Deployment. (28499a9)
• GenAI SDK client - Support build options in Agent Engine source-based Deployment. (f7e718f)
• GenAI SDK client(multimodal) - Support Assemble feature on the multimodal datasets. (2195411)

Bug Fixes

• Fix the change runner behavior back to sync function in streaming_agent_run_with_events (e9d9c31)
• GenAI Client(evals) - fix eval visualizations in Vertex Workbench (c3abe51)
• GenAI Client(evals) - Reformat codebase 1. Remove duplicated code in _evals_utils and _evals_metric_loader 2. Keep metric utils in _evals_metric_loader and data util in _evals_utils (5f3c655)

v1.127.0

Compare Source

Features

• Reenable VertexAiSession for streaming_agent_run_with_events (d3b12d5)

Bug Fixes

• Forward reference resolution in Pydantic schema generation. (0013865)
• GenAI Client(evals): Long traces do not scroll (3a99664)

Documentation

• Add vertexai.types module to generated docs (fc83569)

v1.126.1

Compare Source

Bug Fixes

• Add telemetry enablement env for agent engines deployed using module (e64ff28)

v1.126.0

Compare Source

Features

• Default to "unspecified" for telemetry enablement (3ca65cb)
• GenAI Client(evals) - Add loading agent info util function (acb6cab)
• GenAI Client(evals): Add warning message when tool usage is empty for tool_use_quality (531d223)

Bug Fixes

• Populate missing auth_id for _init_session into adk session.state (37fa3ce)

v1.125.0

Compare Source

⚠ BREAKING CHANGES

• Switch tracing APIs in preview AdkApp.
• Switch cloudtrace.googleapis.com to telemetry.googleapis.com for tracing API.

Features

• Add reservation affinity support to preview BatchPredictionJob (c8f38a0)
• Add support for Vertex Express Mode API key in AdkApp (05834cb)
• Add the identity type option for the agent engine and add effective identity to the resource (bf1851e)
• Alow VertexAiSession for streaming_agent_run_with_events (13faa27)
• GenAI Client(evals) - Add retry to predefine metric (9a46e67)

Bug Fixes

• GenAI Client(evals) - Change dataset visualization table to fixed to prevent horizontal expansion. (7a5a066)
• GenAI Client(evals) - Remove requirement for agent_info.agent in create_evaluation_run in Vertex AI GenAI SDK evals. (d02a7da)
• GenAI Client(evals) - Support direct pandas DataFrame dataset in evaluate() (a917122)
• Revert: Alow VertexAiSession for streaming_agent_run_with_events (7c8c218)

Miscellaneous Chores

• Release 1.125.0 (d344858)
• Switch cloudtrace.googleapis.com to telemetry.googleapis.com for tracing API. (c81f912)
• Switch tracing APIs in preview AdkApp. (27ef56b)

v1.124.0

Compare Source

⚠ BREAKING CHANGES

• GenAI SDK client - Enabling new data driven prompt optimization for prompts from Android API by passing

Features

• GenAI SDK client - Enabling new data driven prompt optimization for prompts from Android API by passing (4216790)

Bug Fixes

• GenAI Client(evals) - Apply sync function for agent run (8a20349)
• GenAI Client(evals) - Support EvaluationDataset output from run_inference as input dataset in create_evaluation_run in Vertex AI GenAI SDK evals (741c6ad)
• GenAI Client(evals) - Update send online eval service request default value and avoid None value (09bf9a9)

Miscellaneous Chores

• Release 1.124.0 (35ac4c5)

v1.123.0

Compare Source

Features

• Add initial support for Python v3.14 (4618729)
• Add more attributes to OTel resource for ADK tracing (5aaa60e)
• Add Python 3.13 Kokoro run config (57d2709)
• Add support for app input in AdkApp template (10ca56f)
• Add support of google-cloud-storage v3 dependency (85cbb75)
• Disable prompt/response content in ADK spans if telemetry env is set (be5d1f5)
• GenAI Client(evals) - Add agent data to EvaluationRun show in Vertex AI GenAI SDK evals (d62afc3)
• GenAI SDK client - add context management to AsyncClient (8075e60)
• GenAI SDK client - Enabling zero-shot prompt optimization for prompts from Android API by passing optimization_target=vertexai.types.OptimizeTarget.OPTIMIZATION_TARGET_GEMINI_NANO in the config (92d8b2a)
• GenAI SDK client (Multimodal Dataset) - Create a multimodal dataset from Big Query. (d4e211d)
• GenAI SDK client(memory): Add extracted memories to MemoryRevision resources (2267d58)
• GenAI SDK client(memory): Add filter to RetrieveMemories (2267d58)
• GenAI SDK client(memory): Add Memory Topic labels to Memory (de941a6)
• GenAI SDK client(multimodal) - Add get/update/list/delete to multimodal datasets. (34996a2)
• GenAI SDK client(multimodal) - Add public get/update/delete methods to multimodal datasets. (6737a70)
• Support Inline Source Deployment in Agent Engine (9ae5f35)

Bug Fixes

• Allow both camelCase and snake_case in _StreamRunRequest (6a6674d)
• Clone agent_framework attribute in ModuleAgent.clone() (81f8c40)
• GenAI Client(evals) - fix hallucination visualization (a52da0b)
• GenAI Client(evals) - fix visualization (67f9099)
• GenAI SDK client - Fix log showing how to get an Agent Engine. Positional arguments are not allowed. (0fc74de)
• Remove unnecessary pandas import from multimodal datasets preview module. (5dd51a2)

Documentation

• Add docstring for classes and fields that are not supported in Gemini or Vertex API (cd99635)
• Add docstring for enum classes that are not supported in Gemini or Vertex API (db364ab)

v1.122.0

Compare Source

Features

• Add STZ support for Endpoint.deploy and Model.deploy (preview). (7dd2629)
• Add support for Python v3.13 (db286c4)
• Add support for telemetry env enablement and logging setup in default instrumentor. (a26171c)
• Allow Memory Revisions to be disabled (cf0948f)
• Disable request/response content in custom ADK spans on Agent Engine in case there's no explicit consent (dc5dcc7)
• GenAI Client(evals) - Add create_evaluation_set and create_evaluation_item methods to Vertex AI GenAI SDK evals (83553a9)
• GenAI Client(evals) - Add evaluation_df input support to create_evaluation_run method in Vertex AI GenAI SDK evals (7a1262b)
• GenAI Client(evals) - Add inference_configs to create_evaluation_run method in Vertex AI GenAI SDK evals (5b5e6bd)
• GenAI Client(evals) - Add labels to EvaluationRun in Vertex AI GenAI SDK evals (67cf80b)
• GenAI Client(evals) - Add metrics to create_evaluation_run method in Vertex AI GenAI SDK evals (ce35218)
• GenAI Client(evals) - Add agent eval data converter evals (cd61c86)
• GenAI Client(evals) - Add Detailed View to show method for EvaluationRun for Vertex AI GenAI SDK evals (dc16065)
• GenAI Client(evals) - Register hallucination and tool_usage_quality metrics for agent eval (7ae013e)
• GenAI Client(evals) - Update agent eval evaluation report dashboard (e2aa3eb)
• GenAI SDK client - Add TTL support for Agent Engine Code Execution (9d139eb)
• GenAI SDK client: Add async Memory and Memory Revisions methods (55b7c23)
• GenAI SDK client(evals) - Add agent run in run_inference (8b9ed04)
• GenAI SDK client(evals) - Add predefined metrics for Gecko text-to-image and text-to-video evaluations (b05e5b3)
• GenAI SDK client(evals) - Update evaluate function to enable agent_info (d13b230)
• GenAI SDK client(evals) Send agent eval request to EvaluateInstance (87ea594)
• Support TTL (per Memory Bank and per-request) for Memory Revisions (cf0948f)

Bug Fixes

• GenAI Client(evals) - Support multiple metrics in Detailed View show method for EvaluationRun for Vertex AI GenAI SDK evals (3ac82ea)
• GenAI SDK (prompts) - Fix bug where passing encryption_spec to prompts.create raised an error (f0a4a00)

v1.121.0

Compare Source

⚠ BREAKING CHANGES

• remove deprecated transfer_to_agent parameter

Features

• A new message ScaleToZeroSpec is added (62ea30a)
• Add additional proto fields and GenerateFetchAccessToken API (62ea30a)
• Add aspect_ratio and image_config for v1 version (62ea30a)
• Add aspect_ratio and image_config for v1beta1 version (62ea30a)
• Add async methods for Sessions and Session Events (ac6e0b4)
• Add JAILBREAK as a new Prompt block reason in PredictionService (62ea30a)
• Add JAILBREAK category to SafetySettings for prediction service (62ea30a)
• Add JAILBREAK category to SafetySettings for prediction service (62ea30a)
• Add labels field for Predict API for Imagen use case (v1beta and v1) (62ea30a)
• Add ListOperations partial success flag (62ea30a)
• Add ListOperations unreachable resources (62ea30a)
• Add matching engine deployment tier parameter and new shard size (ffe9cde)
• Add resource attributes and GenAI instrumentation to default instrumentator in ADK VAE template (f0dc877)
• Add support for Inline source based deployment (62ea30a)
• Add support for Inline source based deployment (62ea30a)
• Add support for Python 3.14 (62ea30a)
• GenAI SDK client - Update input handling inside code execution sandbox (9a452cc)
• GenAI SDK client(evals) Update data model for agent evaluation (4ca9fcc)
• Initial implementation of the SDK for Memory Revisions (b91b63c)
• Support for explicitly providing class_methods in Agent Engine config. (af8c898)
• Updated Observability GenAI data format converter for JSONL (00e57de)

Bug Fixes

• Adding google internal import rule for vertex service to adk app (0d1240e)

Miscellaneous Chores

• Release 1.121.0 (8b2eed8)
• Remove deprecated transfer_to_agent parameter (71a7832)

v1.120.0

Compare Source

Features

• Add ability to use existing sessions for streaming_agent_run_with_events calls. (0a369ea)
• Add DeploymentTier enum to DeployedIndex (89a26c1)
• Add labels field for Predict API for Imagen use case (v1beta) (89a26c1)
• Auto-generated CL for //google/cloud/aiplatform:aiplatform_v1_public_proto_gen (89a26c1)
• Expose PSC for CustomModel (d02099c)
• GenAI Client(evals) - Add get_evaluation_set and get_evaluation_item methods to Vertex AI GenAI SDK evals (7757886)
• GenAI Client(evals) - Add show method for EvaluationRun class in Vertex AI GenAI SDK evals (0c932b9)
• Migrate vertex ai session service to use agent engine sdk (b72df1c)
• Migrate vertex_ai_session_service to use Agent Engine SDK (55b54a2)
• Migrate vertex_ai_session_service to use Agent Engine SDK (03772e2)

Bug Fixes

• GenAI Client(evals) - Parse user defined rubrics correctly to LLM metric (64b0665)

Documentation

• Fix Sessions SDK docstrings (0077bde)

v1.119.0

Compare Source

Features

• GenAI Client(evals) - Add EvaluationResults to get_evaluation_run method response in Vertex AI GenAI SDK evals (f07ecc3)
• GenAI SDK client (prompt management): Release Prompts module to GA (3394028)

v1.118.0

Compare Source

⚠ BREAKING CHANGES

• GenAI SDK client (prompt management) - Split create into two methods, create() and create_version()
• GenAI SDK client (prompt management) - Split get into two methods, get() and get_version()
• GenAI SDK client (prompt management) - Rename list methods to list() and list_versions()
• GenAI SDK client (prompt management) - Rename delete methods to delete() and delete_version()
• GenAI SDK client (prompt management) - Rename prompt_management module to prompts

Features

• Add enable_widget option in Google Maps and additional grounding information (0722687)
• Add filter option for deploy configuration in Model Garden deploy SDK (ac33e87)
• Add Model Garden deploy SDK select verified config guide. (36a5bbc)
• Add private_model_server_enabled to in Endpoint.proto (0722687)
• Add Validation mode in FunctionCallingConfig (0722687)
• Add Validation mode in FunctionCallingConfig (0722687)
• GenAI Client(evals) - Add create_evaluation_run method to Vertex AI GenAI SDK evals (7db9b4f)
• GenAI Client(evals) - Add get_evaluation_run method to Vertex AI GenAI SDK evals (bbbadbc)
• GenAI SDK client (prompt management) - Rename delete methods to delete() and delete_version() (d52ed42)
• GenAI SDK client (prompt management) - Rename list methods to list() and list_versions() (d52ed42)
• GenAI SDK client (prompt management) - Rename prompt_management module to prompts (d52ed42)
• GenAI SDK client (prompt management) - Split create into two methods, create() and create_version() (d52ed42)
• GenAI SDK client (prompt management) - Split get into two methods, get() and get_version() (d52ed42)
• GenAI SDK client(evals) Add data model for agent evaluation (d3ef487)
• PSC support for custom weights deploy (0722687)
• Tuning PreTunedModel API field (0722687)

Bug Fixes

• Mitigate breaking change in GenAI SDK for ADK on AgentEngine (9fa50aa)
• Relax the type annotations to avoid issues with pydantic when deploying (7a6a2f5)
• Remove the upperbound on google-genai for AgentEngine (74726f3)

Documentation

• A comment for field dedicated_endpoint_disabled in message .google.cloud.aiplatform.v1beta1.DeployRequest is changed (0722687)
• Remove legacy internal lint directives (0722687)
• Update the comment for ANY mode in FunctionCallingConfig. (0722687)
• Update the comment for ANY mode in FunctionCallingConfig. (0722687)

Miscellaneous Chores

• Release 1.118.0 (a67a795)

v1.117.0

Compare Source

Features

• Expose user reservation for CustomModel (f796e74)
• Gen AI SDK client - add experimental restore_version method to Prompt Management (820e0b6)

Documentation

• Add generated docs for Gen AI Modules (c3c2f7f)

v1.116.0

Compare Source

Features

• Add experimental async list_prompts and list_version methods to prompt management (13a626b)
• GenAI SDK client - add experimental async delete_prompt and delete_version method to Prompt Management (45e616a)
• Update gapic utils to allows creating RAG clients with api_override (9851905)

Bug Fixes

• GenAI Client(evals) - Add support for context in Grounding metric (e75d91f)
• Pass plugins to the Runner in ADK template. (b43b7b4)

Documentation

• Update AgentEngine with ADK template to the version in GA (0d600fd)

v1.115.0

Compare Source

⚠ BREAKING CHANGES

• The optimize_prompt method no longer returns the parsed response directly. Code must be updated to access the .raw_text_response or .parsed_response attribute on the new return object.

Features

• Add has_template_config to MultimodalDataset. (97a6e71)
• GenAI SDK client - add experimental async create_version and get methods to prompt management (d8de037)
• GenAI SDK client - Add experimental delete_prompt() and delete_version() methods to Prompt Management (3f7f976)
• GenAI SDK client - Modify optimize_prompt to return raw and parsed responses. (415cf26)
• GenAI SDK client -- add support for user defined labels for ReasoningEngine (002b441)
• Update list_deploy_options api for Vertex AI Model Garden custom model to support filtering by machines that user has quota for. (540e9e0)

Bug Fixes

• GenAI Client(evals) - Improve LiteLLM model completion response parsing (ff55a48)
• Update definition of async_add_session_to_memory to not depend on Session (dc9a5da)

Documentation

• Add Agent Engine with ADK examples to README. (c74305b)
• Streamline installation section in README and add uv package installation command (bf91a55)

Miscellaneous Chores

• Release 1.115.0 (bcf9ce0)

v1.114.0

Compare Source

Features

• GenAI SDK client - Add experimental list_prompts() and list_versions() methods to Prompt Management (18a5559)

Bug Fixes

• GenAI SDK client - Add agent_server_mode arg to AgentEngineConfig and pass it to API request if present. (1f821fd)

v1.113.0

Compare Source

Features

• GenAI - Added GPT, Qwen, and DeepSeek models support in GenAI batch prediction (cdd73d2)
• GenAI Client(evals) - Add support for Vertex Model Garden MaaS models. (751cb18)

Bug Fixes

• GenAI Client(evals) - Update data handling for adaptive rubric multi-turn evaluation metrics (c511490)

v1.112.0

Compare Source

Features

• G