v1.158.0

1.158.0 (2026-06-16)

Features

• Add ReasoningEngineRuntimeRevisionService and update related fields in ReasoningEngine (b51f0f6)
• GenAI client - Add update_corpus and update_config methods to the RAG module (237c562)
• GenAI SDK client - Add import_files method to RAG client (a5c6095)
• Release ReasoningEngineExecutionService.CancelAsyncQueryReasoningEngine v1 API (b51f0f6)
• Release ReasoningEngineExecutionService.CancelAsyncQueryReasoningEngine v1beta1 API (b51f0f6)

Bug Fixes

• GenAI client - Make vertex_rag_store a required arg for client.rag.retrieve_contexts and make the tools arg in ask_contexts part of config (60b0f84)
• GenAI Client(evals) - Strip ADK-injected params from plain callable tools (551c5bd)
• Keeping the non-default version of the model resource (14a2265)

v1.157.0

1.157.0 (2026-06-09)

Features

• GenAI client - Add delete_file and delete_corpus methods to RAG module (4a594dd)
• GenAI SDK client(multimodal) - Add to_batch_job_source and get_batch_job_destination to MultimodalDataset (116b71c)
• GenAI SDK client(multimodal) - Implement create_from_gemini_request_jsonl in Datasets and AsyncDatasets classes. (6e51cdf)

Bug Fixes

• Mark async test properly (a35f155)
• Remove authorization handling from ADK preview template (cb12436)
• Verify dedicated endpoint predict_async TLS against the certifi CA bundle (3b3471a)

v1.156.0

1.156.0 (2026-06-03)

Features

• GenAI SDK client - add rag.create_corpus() method (a76a4b6)

Bug Fixes

• Update agent engine utils in vertex_ai and agentplatform to support python-a2a sdk 1.0 (2faf725)

v1.155.0

1.155.0 (2026-06-02)

Features

• Add Skill Registry GetSkillRevision and ListSkillRevisions to SDK (94cd20c)
• Add Skill Registry ListSkills and DeleteSkill to SDK (57097a3)
• Forward per-call http_options from AgentEngine.query family of methods. (e6818d3)
• GenAI client - Add retrieve_contexts and ask_contexts methods to RAG module (b90e084)
• GenAI SDK client - Add RAG module with list_corpora, get_corpus, get_file, list_files, and get_config methods (3bc2f58)

Bug Fixes

• Job state name print (be945df)
• Route Endpoint.predict_async via dedicated DNS when the endpoint is dedicated (b6a9652)
• Update authorization for streaming_agent_run_with_events (ae54eb5)
• Using location and project parsed from resource name if not provided (caa416a)

Documentation

• Add a warning that the autorater config is not applicable for predefined metrics in SDK (ad4284b)
• Corrected resource name format in docstrings for list sandbox methods. (1f32406)

v1.154.0

1.154.0 (2026-05-27)

Features

• Add new fields (027acc8)
• Add Skill Registry module to Vertex AI client - Get Skill method (df50ac0)
• Make skill_id a required parameter in skills.create (bc4be37)

Bug Fixes

• Fix flaky evaluation test failures caused by thread execution order (9f97738)
• Fix SkillRevision state enum in Python SDK (1585602)
• GenAI Client(evals) - Map legacy RubricMetric.GROUNDEDNESS to grounding_v1 (9770c31)

Documentation

• Add Skill Registry SDK docs to Google Cloud Gen AI Modules (9702599)
• Rename to agentplatform (8915d23)

v1.153.1

1.153.1 (2026-05-15)

Bug Fixes

• Remove google-genai version contraints (cf4f183)
• Remove SDK workaround for async_retrieve_contexts. (5aabd30)
• Relax google-genai dep to >= 2.0 (6a17fdc)

Miscellaneous Chores

• Release 1.153.1 (addbff6)

v1.153.0

1.153.0 (2026-05-14)

Features

• GenAI Client(evals) - Add red_teaming_config support for create_evaluation_run (657f379)
• Migrate Agent Engines, Evaluation, Prompt Management, and Skill features to agentplatform (74ec5e1)

Bug Fixes

• Inject agents map from agent_info into agent_data for create_evaluation_run (a4ffb67)

Documentation

• Add Skill Registry Python SDK section in README (9f8e24c)

v1.152.0

1.152.0 (2026-05-11)

Features

• Add GetSkillRevision and ListSkillRevisions methods in Vertex AI Skill Registry SDK (e4fdb7a)
• Add ListSkills and DeleteSkill methods in Vertex AI Skill Registry SDK (8578bfd)
• Add mTLS support for telemetry endpoint in adk.py. (7b0c995)
• Add Update Skill method for Vertex AI Skill Registry SDK (48f792b)
• GenAI Client(evals) - Add allow_cross_region_model support for create_evaluation_run (3ce4b02)

Bug Fixes

• Fix name collision on SandboxEnvironment.state by renaming enum to SandboxState (1f9c8e0)
• Remove sandbox_hostname from JWT payload. (ea87edc)
• Support multi-regional locations in vertexai.Client (2834b9b)

v1.151.0

1.151.0 (2026-05-07)

Features

• Add client for Vertex AI Skill Registry - Get Skill method (6f89fd3)
• Add Create Skill method for Vertex AI Skill Registry SDK (67097eb)
• Add RetrieveSkills semantic search method in Vertex AI Skill Registry SDK (f5909b2)
• Migrate rag to agentplatform (d947295)

Bug Fixes

• Disable bound token sharing check for this Vertex AI SDK code path: google3/third_party/py/google/cloud/aiplatform/vertexai/agent_engines/ (b234d9d)
• GenAI Client(evals) - fix reference column visualization for eval_result (42de11b)

Documentation

• Update Prompts sample in readme to use create_version (e50f375)

v1.150.0

1.150.0 (2026-05-05)

Features

• Add Agent Engine Runtime Versioning support to SDK. (b8eaefb)
• Add Agent Engine Sandbox Snapshots Module (f48e54b)
• Add support for templates sub-module for Sandboxes in Vertex AI GenAI SDK. (68f053e)
• Add support for wait for operation complete for sandbox sub-modules (737ad1c)
• Disable streaming check that should have already been disabled (762d20c)
• Faster sandbox creation with templates and snapshots and improve dataplane routing and security. (9dccee2)
• GenAI Client(evals) - Support eval_cases with multi-turn agent_data in run_inference() (a1680d3)
• GenAI Client(evals) - Support N+1 Agent Engine inference via agent_data in run_inference() (9ea4aa6)
• GenAI SDK client(multimodal) - Accept an explicit bigquery_uri parameter in create_from_bigquery (0bb2ecd)
• Migrate model garden to agentplatform (d5e71ff)
• Migrate resources to agentplatform (5788c50)
• Update sdk to support python-a2a sdk 1.0 via a new GA A2a framework template (762d20c)

Bug Fixes

• Allow setting max_wait_duration to 0 for indefinite waiting with DWS (d9675fd)
• Custom job url after rebrand (aabe816)
• Flaky tests in feature store relates cases due to class instantiation (9fd0fe0)
• GenAI SDK client(multimodal) - Preserve existing metadata when creating from bigframes (bc2260d)