Release 1.21.0

1.21.0 (2025-12-11)

Features

• [Interactions API Support]

  • The newly released Gemini Interactions API is supported in ADK Now. To use it:

  Agent(
    model=Gemini(
        model="gemini-3-pro-preview",
        use_interactions_api=True,
    ),
    name="...",
    description="...",
    instruction="...",
  )

  see samples for details

• [Services]

  • Add add_session_to_memory to CallbackContext and ToolContext to explicitly save the current session to memory (7b356dd)

• [Plugins]

  • Add location for table in agent events in plugin BigQueryAgentAnalytics (507424a)
  • Upgrade BigQueryAgentAnalyticsPlugin to v2.0 with improved performance, multimodal support, and reliability (7b2fe14)

• [A2A]

  • Adds ADK EventActions to A2A response (32e87f6)

• [Tools]

  • Add header_provider to OpenAPIToolset and RestApiTool (e1a7593)
  • Allow overriding connection template (cde7f7c)
  • Add SSL certificate verification configuration to OpenAPI tools using the verify parameter (9d2388a)
  • Use json schema for function tool declaration when feature enabled (cb3244b)

• [Models]

  • Add Gemma3Ollama model integration and a sample (e9182e5)

Bug Fixes

• Install dependencies for py 3.10 (9cccab4)
• Refactor LiteLLM response schema formatting for different models (894d8c6)
• Resolve project and credentials before creating Spanner client (99f893a)
• Avoid false positive "App name mismatch" warnings in Runner (6388ba3)
• Update the code to work with either 1 event or more than 1 events (4f54660)
• OpenAPI schema generation by skipping JSON schema for judge_model_config (56775af)
• Add tool_name_prefix support to OpenAPIToolset (82e6623)
• Pass context to client interceptors (143ad44)
• Yield event with error code when agent run raised A2AClientHTTPError (b7ce5e1)
• Handle string function responses in LiteLLM conversion (2b64715)
• ApigeeLLM support for Built-in tools like GoogleSearch, BuiltInCodeExecutor when calling Gemini models through Apigee (a9b853f)
• Extract and propagate task_id in RemoteA2aAgent (82bd4f3)
• Update FastAPI and Starlette to fix CVE-2025-62727 (ReDoS vulnerability) (c557b0a)
• Add client id to token exchange (f273517)

Improvements

• Normalize multipart content for LiteLLM's ollama_chat provider (055dfc7)
• Update adk web, fixes image not rendering, state not updating, update drop down box width and trace icons (df86847)
• Add sample agent for interaction api integration (68d7048)
• Update genAI SDK version (f0bdcab)
• Introduce build_function_declaration_with_json_schema to use pydantic to generate json schema for FunctionTool (51a638b)
• Update component definition for triaging agent (ee743bd)
• Migrate Google tools to use the new feature decorator (bab5729)
• Migrate computer to use the new feature decorator (1ae944b)
• Add Spanner execute sql query result mode using list of dictionaries (f22bac0)
• Improve error message for missing invocation_id and new_message in run_async (de841a4)

1.20.0

1.20.0 (2025-12-01)

Features

• [Core]

  • Add enum constraint to agent_name for transfer_to_agent (4a42d0d)
  • Add validation for unique sub-agent names (#3557) (2247a45)
  • Support streaming function call arguments in progressive SSE streaming feature (786aaed)

• [Models]

  • Enable multi-provider support for Claude and LiteLLM (d29261a)

• [Tools]

  • Create APIRegistryToolset to add tools from Cloud API registry to agent (ec4ccd7)
  • Add an option to disallow propagating runner plugins to AgentTool runner (777dba3)

• [Web]

  • Added an endpoint to list apps with details (b57fe5f)

Bug Fixes

• Allow image parts in user messages for Anthropic Claude (5453b5b)
• Mark the Content as non-empty if its first part contains text or inline_data or file_data or func call/response (631b583)
• Fixes double response processing issue in base_llm_flow.py where, in Bidi-streaming (live) mode, the multi-agent structure causes duplicated responses after tool calling. (cf21ca3)
• Fix out of bounds error in _run_async_impl (8fc6128)
• Fix paths for public docs (cd54f48)
• Ensure request bodies without explicit names are named 'body' (084c2de), closes #2213
• Optimize Stale Agent with GraphQL and Search API to resolve 429 Quota errors (cb19d07)
• Update AgentTool to use Agent's description when input_schema is provided in FunctionDeclaration (52674e7)
• Update LiteLLM system instruction role from "developer" to "system" (2e1f730), closes #3657
• Update session last update time when appending events (a3e4ad3), closes #2721
• Update the retry_on_closed_resource decorator to retry on all errors (a3aa077)
• Windows Path Handling and Normalize Cross-Platform Path Resolution in AgentLoader (a1c09b7)

Documentation

• Add Code Wiki badge to README (caf23ac)

1.19.0

1.19.0 (2025-11-19)

Highlights

• Breaking! Raise minimum Python version to 3.10
• Add a File based Artifact Service
• Reduce ADK API server startup latency by lazy loading
• ADK web light mode support
• BigQuery Agent Analytics Plugin

Features

• [Core]

  • Add id and custom_metadata fields to MemoryEntry (4dd28a3)
  • Add progressive SSE streaming feature (a5ac1d5)
  • Add a2a_request_meta_provider to RemoteAgent init (d12468e)
  • Add feature decorator for the feature registry system (871da73)
  • Breaking: Raise minimum Python version to 3_10 (8402832)
  • Refactor and rename BigQuery agent analytics plugin (6b14f88)
  • Pass custom_metadata through forwarding artifact service (c642f13)
  • Update save_files_as_artifacts_plugin to never keep inline data (857de04)

• [Evals]

  • Add support for InOrder and AnyOrder match in ToolTrajectoryAvgScore Metric (e2d3b2d)

• [Integrations]

  • Enhance BQ Plugin Schema, Error Handling, and Logging (5ac5129)
  • Schema Enhancements with Descriptions, Partitioning, and Truncation Indicator (7c993b0)

• [Services]

  • Add file-backed artifact service (99ca6aa)
  • Add service factory for configurable session and artifact backends (a12ae81)
  • Add SqliteSessionService and a migration script to migrate existing DB using DatabaseSessionService to SqliteSessionService (e218254)
  • Add transcription fields to session events (3ad30a5)
  • Full async implementation of DatabaseSessionService (7495941)

• [Models]

  • Add experimental feature to use parameters_json_schema and response_json_schema for McpTool (1dd97f5)
  • Add support for parsing inline JSON tool calls in LiteLLM responses (22eb7e5)
  • Expose artifact URLs to the model when available (e3caf79)

• [Tools]

  • Add BigQuery related label handling (ffbab4c)
  • Allow setting max_billed_bytes in BigQuery tools config (ffbb0b3)
  • Propagate application_name set for the BigQuery Tools as BigQuery job labels (f13a11e)
  • Set per-tool user agent in BQ calls and tool label in BQ jobs (c0be1df)

• [Observability]

  • Migrate BigQuery logging to Storage Write API (a2ce34a)

Bug Fixes

• Add jsonschema dependency for Agent Builder config validation (0fa7e46)
• Add None check for event in remote_a2a_agent.py (744f94f)
• Add vertexai initialization for code being deployed to AgentEngine (b8e4aed)
• Change LiteLLM content and tool parameter handling (a19be12)
• Change name for builder agent (131d39c)
• Ensure event compaction completes by awaiting task (b5f5df9)
• Fix deploy to cloud run on Windows (29fea7e)
• Fix error handling when MCP server is unreachable (ee8106b)
• Fix error when query job destination is None (0ccc43c)
• Fix Improve logic for checking if a MCP session is disconnected (a754c96)
• Fix McpToolset crashing with anyio.BrokenResourceError (8e0648d)
• Fix Safely handle FunctionDeclaration without a required attribute (93aad61)
• Fix status code in error message in RestApiTool (9b75456)
• Fix Use async for to loop through event iterator to get all events in vertex_ai_session_service (9211f4c)
• Fix: Fixes DeprecationWarning when using send method (2882995)
• Improve logic for checking if a MCP session is disconnected (a48a1a9)
• Improve handling of partial and complete transcriptions in live calls (1819ecb)
• Keep vertex session event after the session update time (0ec0195)
• Let part converters also return multiple parts so they can support more usecases (824ab07)
• Load agent/app before creating session (236f562)
• Remove app name from FileArtifactService directory structure (12db84f)
• Remove hardcoded google-cloud-aiplatform version in agent engine requirements (e15e19d)
• Stop updating write mode in the global settings during tool execution (5adbf95)
• Update description for load_artifacts tool (c485889)

Improvements

• Add BigQuery related label handling (ffbab4c)
• Add demo for rewind (8eb1bdb)
• Add debug logging for live connection (5d5708b)
• Add debug logging for missing function call events (f3d6fcf)
• Add default retry options as fall back to llm_request that are made during evals (696852a)
• Add plugin for returning GenAI Parts from tools into the model request (116b26c)
• Add support for abstract types in AFC (2efc184)
• Add support for structured output schemas in LiteLLM models (7ea4aed)
• Add tests for max_query_result_rows in BigQuery tool config (fd33610)
• Add type hints in cleanup_unused_files.py (2dea573)
• Add util to build our llms.txt and llms-full.txt files
• ADK changes (f1f4467)
• Defer import of google.cloud.storage in GCSArtifactService ([9...

Release 1.18.0

1.18.0 (2025-11-05)

Features

• [ADK Visual Agent Builder]

  • Core Features
    • Visual workflow designer for agent creation
    • Support for multiple agent types (LLM, Sequential, Parallel, Loop, Workflow)
    • Agent tool support with nested agent tools
    • Built-in and custom tool integration
    • Callback management for all ADK callback types (before/after agent, model, tool)
    • Assistant to help you build your agents with natural language
    • Assistant proposes and writes agent configuration yaml files for you
    • Save to test with chat interfaces as normal
    • Build and debug at the same time in adk web!

• [Core]

  • Add support for extracting cache-related token counts from LiteLLM usage (4f85e86)
  • Expose the Python code run by the code interpreter in the logs (a2c6a8a)
  • Add run_debug() helper method for quick agent experimentation (0487eea)
  • Allow injecting a custom Runner into agent_to_a2a (156d235)
  • Support MCP prompts via the McpInstructionProvider class (88032cf)

• [Models]

  • Add model tracking to LiteLlm and introduce a LiteLLM with fallbacks demo (d4c63fc)
  • Add ApigeeLlm as a model that lets ADK Agent developers to connect with an Apigee proxy (87dcb3f)

• [Integrations]

  • Add example and fix for loading and upgrading old ADK session databases (338c3c8)
  • Add support for specifying logging level for adk eval cli command (b1ff85f)
  • Propagate LiteLLM finish_reason to LlmResponse for use in callbacks (71aa564)
  • Allow LLM request to override the model used in the generate content async method in LiteLLM (ce8f674)
  • Add api key argument to Vertex Session and Memory services for Express Mode support (9014a84)
  • Added support for enums as arguments for function tools (240ef5b)
  • Implement artifact_version related methods in GcsArtifactService (e194ebb)

• [Services]

  • Add support for Vertex AI Express Mode when deploying to Agent Engine (d4b2a8b)
  • Remove custom polling logic for Vertex AI Session Service since LRO polling is supported in express mode (546c2a6)
  • Make VertexAiSessionService fully asynchronous (f7e2a7a)

• [Tools]

  • Add Bigquery detect_anomalies tool (9851340)
  • Extend Bigquery detect_anomalies tool to support future data anomaly detection (38ea749)
  • Add get_job_info tool to BigQuery toolset (6429457)

• [Evals]

  • Add "final_session_state" to the EvalCase data model (2274c4f)
  • Marked expected_invocation as optional field on evaluator interface (b17c8f1)
  • Adds LLM-backed user simulator (54c4ecc)

• [Observability]

  • Add BigQueryLoggingPlugin for event logging to BigQuery (b7dbfed)

• [Live]

  • Add token usage to live events for bidi streaming (6e5c0eb)

Bug Fixes

• Reduce logging spam for MCP tools without authentication (11571c3)
• Fix typo in several files (d2888a3)
• Disable SetModelResponseTool workaround for Vertex AI Gemini 2+ models (6a94af2)
• Bug when callback_context_invocation_context is missing in GlobalInstructionPlugin (f81ebdb)
• Support models slash prefix in model name extraction (8dff850)
• Do not consider events with state delta and no content as final response (1ee93c8)
• Parameter filtering for CrewAI functions with **kwargs (74a3500)
• Do not treat FinishReason.STOP as error case for LLM responses containing candidates with empty contents (2f72ceb)
• Fixes null check for reflect_retry plugin sample (86f0155)
• Creates evalset directory on evalset create (6c3882f)
• Add ADK_DISABLE_LOAD_DOTENV environment variable that disables automatic loading of .env when running ADK cli, if set to true or 1 (15afbcd)
• Allow tenacity 9.0.0 (ee8acc5)
• Output file uploading to artifact service should handle both base64 encoded and raw bytes (496f8cd)
• Correct message part ordering in A2A history (5eca72f)
• Change instruction insertion to respect tool call/response pairs (1e6a9da)
• DynamicPickleType to support MySQL dialect (fc15c9a)
• Enable usage metadata in LiteLLM streaming (f9569bb)
• Fix issue with MCP tools throwing an error (1a4261a)
• Remove redundant format field from LiteLLM content objects (489c39d)
• Update the contribution analysis tool to use original write mode (54db3d4)
• Fix agent evaluations detailed output rows wrapping issue(4284c61)
• Update dependency version constraints to be based on PyPI versions(0b1784e)

Improvements

• Add Community Repo section to README (432d30a)
• Undo adding MCP tools output schema to FunctionDeclaration (92a7d19)
• Refactor ADK README for clarity and consistency (b0017ae)
• Add support for reversed proxy in adk web (a0df75b)
• Avoid rendering empty columns as part of detailed results rendering of eval results (5cb35db)
• Clear the behavior of disallow_transfer_to_parent (48ddd07)
• Disable the scheduled execution for issue triage workflow (a02f321)
• Include delimiter when matching events from parent nodes in content processor (b8a2b6c)
• Improve Tau-bench ADK colab stability ([04dbc42](https://gi...

v1.17.0

1.17.0 (2025-10-22)

Features

• [Core]

  • Add a service registry to provide a generic way to register custom service implementations to be used in FastAPI server. See short instruction here. (391628f)
  • Add the ability to rewind a session to before a previous invocation (9dce06f)
  • Support resuming a parallel agent with multiple branches paused on tool confirmation requests (9939e0b)
  • Support content union as static instruction (cc24d61)

• [Evals]

  • ADK cli allows developers to create an eval set and add an eval case (ae139bb)

• [Integrations]

  • Allow custom request and event converters in A2aAgentExecutor (a17f3b2)

• [Observability]

  • Env variable for disabling llm_request and llm_response in spans (e50f05a)

• [Services]

  • Allow passing extra kwargs to create_session of VertexAiSessionService (6a5eac0)
  • Implement new methods in in-memory artifact service to support custom metadata, artifact versions, etc. (5a543c0)
  • Add create_time and mime_type to ArtifactVersion (2c7a342)
  • Support returning all sessions when user id is none (141318f)

• [Tools]

  • Support additional headers for Google API toolset (ed37e34)
  • Introduces a new AgentEngineSandboxCodeExecutor class that supports executing agent-generated code using the Vertex AI Code Execution Sandbox API (ee39a89)
  • Support dynamic per-request headers in MCPToolset (6dcbb5a)
  • Add bypass_multi_tools_limit option to GoogleSearchTool and VertexAiSearchTool (9a6b850, 6da7274)
  • Extend ReflectAndRetryToolPlugin to support hallucinating function calls (f51380f)
  • Add require_confirmation param for MCP tool/toolset (78e74b5)

• [UI]

  • Granular per agent speech configuration (409df13)

Bug Fixes

• Returns dict as result from McpTool to comply with BaseTool expectations (4df9263)
• Fixes the identity prompt to be one line (7d5c6b9)
• Fix the broken langchain importing caused their 1.0.0 release (c850da3)
• Fix BuiltInCodeExecutor to support visualizations (ce3418a)
• Relax runner app-name enforcement and improve agent origin inference (dc4975d)
• Improve error message when adk web is run in wrong directory (4a842c5)
• Handle App objects in eval and graph endpoints (0b73a69)
• Exclude additionalProperties from Gemini schemas (307896a)
• Overall eval status should be NOT_EVALUATED if no invocations were evaluated (9fbed0b)
• Create context cache only when prefix matches with previous request (9e0b1fb)
• Handle App instances returned by agent_loader.load_agent (847df16)
• Add support for file URIs in LiteLLM content conversion (85ed500)
• Only exclude scores that are None (998264a)
• Better handling the A2A streaming tasks (bddc70b)
• Correctly populate context_id in remote_a2a_agent library (2158b3c)
• Remove unnecessary Aclosing (2f4f561)
• Fix pickle data was truncated error in database session using MySql (36c96ec)

Improvements

• Improve hint message in agent loader (fe1fc75)
• Fixes MCPToolset --> McpToolset in various places (d4dc645)
• Add span for context caching handling and new cache creation (a2d9f13)
• Checks gemini version for 2 and above for gemini-builtin tools (0df6759)
• Refactor and fix state management in the session service (8b3ed05)
• Update agent builder instructions and remove run command details (89344da)
• Clarify how to use adk built-in tool in instruction (d22b8bf)
• Delegate the agent state reset logic to LoopAgent (bb1ea74)
• Adjust the instruction about default model (214986e)
• Migrate invocation_context to callback_context (e2072af)
• Correct the callback signatures (fa84bcb)
• Set default for bypass_multi_tools_limit to False for GoogleSearchTool and VertexAiSearchTool (6da7274)
• Add more clear instruction to the doc updater agent about one PR for each recommended change (b21d0a5)
• Add a guideline to avoid content deletion (16b030b)
• Add an sample agent for the ReflectAndRetryToolPlugin (9b8a4aa)
• Improve error message when adk web is run in wrong directory (4a842c5)
• Add an sample agent for the ReflectAndRetryToolPlugin (9b8a4aa)
• Add span for context caching handling and new cache creation (a2d9f13)
• Disable the scheduled execution for issue triage workflow (bae2102)
• Correct the callback signatures (fa84bcb)

Documentation

• Format README.md for samples (0bdba30)
• Bump models in llms and llms-full to Gemini 2.5 (ce46386)
• Update gemini_llm_connection.py - typo spelling correction (e6e2767)
• Announce the first ADK Community Call in the README ([731bb90](https://github.com/google/adk-python/...

Release 1.16.0

1.16.0 (2025-10-08)

Features

• [Core]
  • Implementation of LLM context compaction (e0dd06f)
  • Support pause and resume an invocation in ADK (ce9c39f, 2f1040f, 1ee01cc, f005414, fbf7576)
• [Models]
  • Add citation_metadata to LlmResponse (3f28e30)
  • Add support for gemma model via gemini api (2b5acb9)
• [Tools]
  • Add dry_run functionality to BigQuery execute_sql tool (960eda3)
  • Add BigQuery analyze_contribution tool (4bb089d)
  • Spanner ADK toolset supports customizable template SQL and parameterized SQL (da62700)
  • Support Oauth2 client credentials grant type (5c6cdcd)
  • Add ReflectRetryToolPlugin to reflect from errors and retry with different arguments when tool errors (e55b894)
  • Support using VertexAiSearchTool built-in tool with other tools in the same agent (4485379)
  • Support using google search built-in tool with other tools in the same agent (d3148da)
• [Evals]
  • Add HallucinationsV1 evaluation metric (8c73d29)
  • Add Rubric based tool use metric (c984b9e)
• [UI]
  • Adds adk web options for custom logo (822efe0)
• [Observability]
  • otel: Switch CloudTraceSpanExporter to telemetry.googleapis.com (bd76b46)

Bug Fixes

• Adapt to new computer use tool name in genai sdk 1.41.0 (c6dd444)
• Add AuthConfig json serialization in vertex ai session service (636def3)
• Added more agent instructions for doc content changes (7459962)
• Convert argument to pydantic model when tool declares it accepts pydantic model as argument (571c802)
• Do not re-create App object when loader returns an App (d5c46e4)
• Fix compaction logic (3f2b457)
• Fix the instruction in workflow_triage example agent (8f3ca03)
• Fixes a bug that causes intermittent pydantic validation errors when uploading files (e680063)
• Handle A2A Task Status Update Event when streaming in remote_a2a_agent (a5cf80b)
• Make compactor optional in Events Compaction Config and add a default (3f4bd67)
• Rename SlidingWindowCompactor to LlmEventSummarizer and refine its docstring (f1abdb1)
• Rollback compaction handling from _get_contents (84f2f41)
• Set max_output_tokens for the agent builder (2e2d61b)
• Set default response modality to AUDIO in run_session (68402bd)
• Update remote_a2a_agent to better handle streaming events and avoid duplicate responses (8e5f361)
• Update the load_artifacts tool so that the model can reliably call it for follow up questions about the same artifact (238472d)
• Fix VertexAiSessionService base_url override to preserve initialized http_options (8110e41, c51ea0b)
• Handle App instances returned by agent_loader.load_agent (847df16)

Improvements

• Migrate VertexAiSessionService to use Agent Engine SDK (90d4c19)
• Migrate VertexAiMemoryBankService to use Agent Engine SDK (d1efc84, 97b950b, 83fd045)
• Add support for resolving $ref and $defs in OpenAPI schemas (a239716)

Documentation

• Update BigQuery samples README (3021266)

Release 1.15.1

1.15.1 (2025-09-26)

Bug Fixes

• Fix the deployment failure for Agent Engine (e172811)

Release 1.15.0

1.15.0 (2025-09-24)

Features

• [Core]
  • Adding the ContextFilterPlugin (a06bf27)
  • Adds plugin to save artifacts for issue #2176 (657369c)
  • Expose log probs of candidates in LlmResponse (f7bd3c1)
• [Context Caching]
  • Support context caching (c66245a)

    • Support explicit context caching auto creation and lifecycle management.

      Usage: App(root_agent=..., plugins=..., context_cache_config=...)

  • Support non-text content in static instruction (61213ce)
  • Support static instructions (9be9cc2)

    • Support static instruction that won't change, put at the beginning of
      the instruction.
      Static instruction support inline_data and file_data as contents.
      Dynamic instruction moved to the end of LlmRequest, increasing prefix
      caching matching size.

      Usage:
      LlmAgent(model=...,static_instruction =types.Content(parts=...), ... )

• [Telemetry]
  • Add --otel_to_cloud experimental support (1ae0b82, b131268, 7870480)
  • Add GenAI Instrumentation if --otel_to_cloud is enabled (cee365a)
  • Support standard OTel env variables for exporter endpoints (f157b2e)
  • Temporarily disable Cloud Monitoring integration in --otel_to_cloud (3b80337)
• [Services]
  • Add endpoint to generate memory from session (2595824)
• [Tools]
  • Add Google Maps Grounding Tool to ADK (6b49391)
  • MCP: Initialize tool_name_prefix in MCPToolse (86dea5b)
• [Evals]
  • Data model for storing App Details and data model for steps (01923a9)
  • Adds Rubric based final response evaluator (5a485b0)
  • Populate AppDetails to each Invocation (d486795)
• [Samples]
  • Make the bigquery sample agent run with ADC out-of-the-box (10cf377)

Bug Fixes

• Close runners after running eval (86ee6e3)
• Filter out thought parts when saving agent output to state (632bf8b)
• Ignore empty function chunk in LiteLlm streaming response (8a92fd1)
• Introduces a raw_mcp_tool method in McpTool to provide direct access to the underlying MCP tool (6158075)
• Make a copy of the columns instead of modifying it in place (aef1ee9)
• Prevent escaping of Latin characters in LLM response (c9ea80a)
• Retain the consumers and transport registry when recreating the ClientFactory in remote_a2a_agent.py (6bd33e1)
• Remove unsupported 'type': 'unknown' in test_common.py for fastapi 0.117.1 (3745221)

Documentation

• Correct the documentation of after_agent_callback (b9735b2)

Release 1.14.1

1.14.1 (2025-09-14)

Bug Fixes

• Fix logging issues with RemoteA2aAgent 0c1f1fa

Release 1.14.0

1.14.0 (2025-09-10)

Features

• [A2A]
  • Allow users to pass their own agent card to to_a2a method a1679da
  • Allow custom part converters in A2A classes b05fef9
• [Tools]
  • Allow setting agent/application name and compute project for BigQuery tools 11a2ffe
  • Add BigQuery forecast tool 0935a40
  • Add GkeCodeExecutor for sandboxed code execution on GKE 72ff9c6
  • Add a tool confirmation flow that can guard tool execution with explicit confirmation and custom input a17bcbb
  • Add audience and prompt as configurable for OAuth flows edda922
  • Allow user specify embedding model for file retrieval 67f23df
• [Core]
  • Allow all possible values for agent_class field in all Agent Configs 3bc2d77
  • Allow agent loader to load built-in agents from special directories in adk folder 578fad7
  • Upgrade ADK runner to use App in addition to root_agent 4df79dd
  • Allow inject artifact into instructions bb4cfde
• [Misc] Create an initial ADK release analyzer agent to find the doc updates needed between releases e3422c6

Bug Fixes

• Add custom_metadata to DatabaseSessionService fb009d8
  • NOTE: This requires DB migration, run ALTER TABLE events ADD COLUMN custom_metadata JSON; to migrate existing database tables.
• Add a NOTE to agent transfer instructions listing available agents 43eec82
• Fix pagination of list_sessions in VertexAiSessionService e63fe0c
• Fix AttributeError and indentation in parameter processing of LiteLlm 1e23652
• Allow AgentTool to inherit/use plugins from its invocation context when running 1979dcf
• Enforce foreign key constraint for SQLite DB 0c87907
• Add back installing requirements.txt to Dockerfile template for cloud run 8e43f0d
• Only process the auth responses in the last event with content (if applicable i.e. it's authored by user) 3b922a2
• Extract a utility for aggregating partial streaming responses and emitting LlmResponses for them as needed 7975e8e
• Support saving text artifacts in GCS artifact service cecf7e8
• Fixes thought handling in contents.py and refactors its unit tests a30851e
• Fixes the thought field handling in _planning.py fe8b37b
• Pass state_delta to runner in /run endpoint a3410fa
• Fix discussion answering github action workflow to escape the quote in the discussion content JSON 43c9681
• Send full MIME types for image/video/pdf in get_content e45c3be
• Fix flaky unit tests: tests/unittests/flows/llm_flows/test_functions_simple.py b92b288
• Make UT of a2a consistent about how tests should be skipped when python verison < 3.10 98b0426

Improvements

• Update contribution guide 8174a29
• Skip PR triage for already triaged or Google-contributor PRs 78eea1a
• Avoid mutable default arguments in local_eval_service and runners 64f11a6
• Avoid mutable default arguments in local_eval_service and runners 5b465fd
• Reorder dependencies in pyproject.toml ca5f7f1
• Follow pydantic convention to make field_validator a public method 1448406
• Update comment to clarify after_run callbacks 7720616
• Tune instructions to not ask root directory if it's already provided in the context 25df6c2
• Load discussion data from event content to avoid additional GraphQL API call a503a0c
• Refactor discussion answering agent to merge answer_discussions.py into main.py 408d3df
• Add community repo dependency group to pyproject toml 7b077ac
• Add warning for using Gemini models via LiteLLM 9291daa

Documentation

• Update root_agent description for clarity 467df1a
• Update the ask_data_insights docstring aad1533
• Add contributing Spanner tools RAG agent sample fcd748e

Tests

• Add functional telemetry tests bc6b546
• Add unit tests for the App class and improve Runner initialization tests fc90ce9

Chores

• Use lazy % formatting in logging functions to fix pylint warnings b431072
• Update release cadence in README decc19b
• Update create_session endpoint to use Request message as post body 219815d