chore(main): release 0.6.0

[release-please]

🤖 I have created a release beep boop

0.6.0 (2026-05-08)

Features

• Add .gitignore file. (#362) (1c00922)
• Add Agent Engine-level configuration for generation_trigger_config. (365a14a)
• Add AgentEngine Sessions module (286401c)
• Add CachedContent resource to Vertex AI client library. (8c8963e)
• Add consolidation customization to Memory Bank (9df74eb)
• Add GoogleApi error in ClientError.cause (d5c67bd)
• Add ingest_events method for Memory Bank. (365a14a)
• Add memory_id to Create Memory (73207d3)
• Add memory_types filter to RetrieveMemories (90e3f69)
• Add model_status to GenerateContentResponse (Gemini API only) (5a3101b)
• Add part_metadata in Part (Gemini API only) (5a3101b)
• Add raw_event to Append Event (73207d3)
• Add responseSchema to GenerateContentRequest. (d3715da)
• Add RetrieveProfiles. (90e3f69)
• Add session_id to Create Session to allow custom session id (fed70af)
• Add structured data and context to MemoryRevision. (90e3f69)
• Add structured data and memory type to Memory. (90e3f69)
• Add subset_topics to Memory Bank GenerateMemories (7932c2b)
• Add support for agent gateway in agent engine (b3ea8e3)
• add support for audioTimestamp in GenerationConfig (#467) (598d955)
• add support for container_spec in AgentEngines (274e0ff)
• add support for keep alive probe in agent engines (088c5ad)
• Add tool config (f618132)
• added userAgent option to RequestOptions to allow setting User-Agent header (ca43e2f)
• Adds cancel_query_job to SDK for agent engine long running async tasks. (bc19f31)
• Adds run_query_job and check_query_job to SDK for long running async tasks. (ff93dc5)
• Allow labels in GenerateContentRequest (d210d06)
• Allow labels in GenerateContentRequest (#466) (#501) (0075baa)
• allow users to pass string as system instruction (a824162)
• BREAKING CHANGE - Update minimum supported Node version to Node 20 (e2a384e)
• enable dynamic retrieval for Google Search Retrieval grounding (3f9eee6)
• enable inference request to tuned model. (de9c4c2)
• enable response style in generation config (46b0836)
• enable system instruction for GenerativeModel (590ca5a)
• enable system instruction in chat experience (7e71f75)
• enable turn off the safety filter in HarmBlockThreshold enum (1737c66)
• Execute all test cases. (#363) (dccd44c)
• exposing customHeader in requestOptions to allow users pass in customer headers. (b47d733)
• faster sandbox creation with templates and snapshots and improve dataplane routing and security. (450dfee)
• Implement cached_content with generateContent methods (c604b8c)
• In run_query_job, rename gcs_bucket to gcs_uri and allow the case that user sets the filename for the output. (4a1a387)
• include grounding metadata to stream aggregated response. (d32755e)
• infer location if user doesn't specifies it. (b8d4af1)
• infer project ID when user don't specify and throw if inference fails (6b3e68e)
• remove response style in generation config (87d8b58)
• Rename the package @google-cloud/agentplatform (adf4388)
• Support responseMimeType parameter in the generationConfig object. (eecb271)
• Support functionCalls property in GenerationContentCandidate interface for non streaming mode (89568a6)
• Support RAG in public preview (5ade755)
• Support rendered_parts in GroundingSupport (5a3101b)
• support responseMimeType in GenerationConfig to allow users specify output response mimetype of the generated candidate text. (93f6d70)
• update grounding metadata (d3c0a64)

Bug Fixes

• a typo in chat session and missed toolConfig on chat start (b552fea)
• Add Context Cache support for ChatSessionPreview class (#433) (df6f040)
• Add Context Cache support for ChatSessionPreview class (#433) (a3beab1)
• Add Context Cache support for ChatSessionPreview class (#433) (f8a3bdf)
• aggregate text & functionCall(s) correctly (5a53266)
• aggregate text & functionCall(s) correctly (5a53266)
• aggregate text & functionCall(s) correctly (5a53266)
• aggregate text & functionCall(s) correctly (#497) (b62483a)
• check optional field in aggregate response (f7718ae)
• correct CitationMetadata interface. refactor nested function (722b7fd)
• correct code snippets in README (bdcc5fd)
• correct GenerateContentCandidate interface and GenerateContentResponse interface (7a366ab)
• correct sys test logic on stream endpoint for funcion calling (1fd5b72)
• Fix a bug in the Vertex AI client library. (8ad7dfb)
• fix bug in safetyRatings handling, fix incomplete content interfaces, and add unit test for stream response handling (e573ce6)
• Fix cached contents list url (2c4b769)
• Fix docstring order and add node version badge in README (d330fe3)
• Fix name collision on SandboxEnvironment.state by renaming enum to SandboxState (71a1d79)
• for function call, role should be model. (3b80dc8)
• functionResponse should be user role (d092ab4)
• handle case when content is undefined in candidate. (f16f040)
• improve error message to help with debugging (8a937d5)
• include cachedContent in generate request (#469) (a16b9d4)
• log instead of throw appendHistory errors to avoid unhandled rejection (2ec9e7d)
• Make appendHistory private. (a1bedcd)
• missing property frequencyPenalty in type defintions (#394) (7557a83)
• pass tools from getGenerativeModel and startChat methods to top level functions (bbaf78a)
• pass tools from getGenerativeModel to chatSession. (907ad74)
• remove any type in token signature (add084c)
• remove defaulting value of candidates in unary api. remove unused variables and imports. remove throwing GoogleAIError when candidates undefined or empty. (6c0c31c)
• remove restriction on gsc uri for file data part. (e694c44)
• Removing Python 3.9 support due to EOL (bce97bd)
• replace any type with explicit types in post fetch processing functions (4099129)
• replace snake_case in docs to camelCase (5893581)
• SDK should be released to 1.0.0 (4cab5fd)
• update finish reason enum list to be complete (f16b2e7)
• update prompt feedback interface (0d3754a)

Documentation

• update README (e9705cb)
• update README (a052132)

Miscellaneous Chores

• release 0.6.0 (f839ac7)
• release 1.10.1 (3c7a6e6)
• release 1.10.2 (431950d)
• release 1.10.3 (6a68cbe)
• release 1.10.4 (15988b8)
• release as 1.9.2 (d54a91b)

---

This PR was generated with Release Please. See documentation.