chore(release/candidate): release 2.4.0

[adk-bot]

🤖 I have created a release beep boop

2.4.0 (2026-07-07)

Features

• add error handling to VertexAiMemoryBankService.search_memory (f3529e9)
• add model_input_context for transient context in LLM requests (2aeb1e1)
• add mTLS support for DiscoveryEngineSearchTool (8ba0e6a)
• add mTLS support to Google API tools (3466586)
• add OpenAI Responses API support in labs (6b831d5), closes #3209
• add sub-branch creation and segment appending to _BranchPath (3009ec1)
• add support for reusing an existing SQLAlchemy AsyncEngine in DatabaseSessionService (f4c7e4c)
• add support for session TTL and expiration in Vertex AI session service (49d4441)
• log when an agent run is cancelled and warn on cleanup-queue failures (c84c17a)
• adk: add Anthropic effort config handling, thinking-parameter propagation, and conflict mitigation (4c862b9)
• agents: add ManagedAgent backed by the Managed Agents API (cf91b84)
• bigquery: expose thinking and tool-use token columns in analytics views (c14258d)
• bigtable: support parameterized views with secure parameter injection (14a24f2)
• expose branch property on Context (50c81eb)
• expose max_parallel_workers on the workflow.node decorator and Node class (199d954)
• expose parameter_binding in the @node decorator (bfc236d)
• expose SKIP_THOUGHT_SIGNATURE_VALIDATOR constant (6aad10d)
• add HTTP traces for MCP server requests/errors (4c4f77a)
• implement Workflow-as-Tool core feature (1263ed6)
• integrations: add DaytonaEnvironment for remote sandbox workspaces (df6baf4)
• interactions: stream thought, media, code-exec, and function-result deltas (b2dda6e)
• interactions: surface streamed grounding and final usage metadata (6a50b8d)
• memory: add Vertex AI load_profiles tool (fb2b3af)
• models: add configuration options to Gemini class (037ec12), closes #3813
• models: surface and recover environment_id from interactions (81f9f2e)
• pass invocation_id to _setup_invocation_context (73ecf8d)
• plugins: add otel correlation, custom_metadata allowlist, and column projection to BigQuery analytics (38d715c)
• refactor ADK CLI server to support nested agents in dev mode and simplify the API (35a3e4c)
• sessions: add public prepare_tables() for eager initialization (66221c4)
• skills: inject session state into SKILL.md via adk_inject_state (3afdb08)
• support file_data URI references in GcsArtifactService (43115b2)
• support mTLS and GOOGLE_API_USE_MTLS_ENDPOINT for the GDA client (e85a7b2)
• support passing dynamic custom headers to LiteLLM via RunConfig (000d74d)
• support provider-prefixed Gemini model IDs (816a87f)
• telemetry: add gen_ai.invoke_agent.{inference,tool}_calls metrics (dec2182)
• telemetry: add tool-type attribute to tool-execution duration (d5e8bc7)
• telemetry: emit entrypoint invoke_workflow span under schema v2 (e98633a)
• telemetry: introduce ADK_TELEMETRY_SCHEMA_VERSION_OPT_IN (84bbb35)
• telemetry: specify bucket boundaries for GenAI metrics (abf9258)
• tools: add response_scheduling to control Live function-response behavior (7443bfa)
• tools: expose configurable parameter as a property on McpToolset (cca8c56)
• tools: resolve built-in tools for managed-agent requests (f11d19d)
• tools: support tuple tool parameters (a57c3e4)
• utils: add support for nested state access in template injection (94c43a2)
• workflow: allow ToolNode to accept JSON string or Content inputs (4e44632)

Bug Fixes

• adapt interactions conversion to google-genai 2.9 SDK changes (9f3aeef)
• add credential_key to ApplicationIntegrationToolset and IntegrationConnectorTool (c6a94b8), closes #4553
• add DNS-rebinding protection to _OriginCheckMiddleware (9a4f479)
• add module blocklist for YAML agent-config code references (6a5be34)
• add parameter validation for sync tools in functions.py (9b9d27d)
• agents: persist output_key when before_agent_callback short-circuits LlmAgent (0e263f1)
• agents: preserve text streamed before tool calls in output_key (5a0b4af)
• agents: prevent path traversal in AgentTool config_path resolution (171ae9e)
• ApplicationIntegrationTool: implement dynamic mTLS endpoint resolution (37ca6fb)
• apply run_config custom_metadata to the user event in node runtime (066fbce)
• artifacts: preserve .text on GcsArtifactService load (ba51ff2), closes #3157
• auth: allow configuring the OAuth prompt parameter (ac99770)
• auth: strip redirect_uri from credential_key (ffa1843)
• avoid mutating event-validation input (6b385e4)
• avoid overwriting existing isolation scope in stamp_event_branch_context (798207a)
• avoid yielding a None function-response event in live mode (4d88a52)
• catch RecursionError in safe JSON serialization helpers (5515800), closes #5411
• check whether a transfer target is a sibling agent (fa18d26)
• cli: detailed error message on SSE stream, including client-side error type (56b84e1)
• cli: enable interspersed option parsing for the cloud_run command (7b049b9)
• cli: ensure ADK compatibility in agent-engine requirements (ea772b9), closes #5966
• cli: respect ignore files in adk deploy commands (ee79e71)
• cli: support flat-module agents in _determine_agent_language (7a553b7)
• concatenate list values in deep_merge_dicts during parallel tool-call merge (fda2347), closes #5190
• constrain artifact references to the caller scope (f863150), closes #6124 #6125
• correct misleading workflow-agent deprecation messages (53a8ab1)
• derive sandbox reasoning engine from template or snapshot name (5afa9db)
• emit standard OTel cloud.resource_id for Agent Engine telemetry (8fc25f1), closes #6247
• enable history_config on Vertex AI now that it is supported (2920145)
• enforce agent-config args denylist when loaded under adk web (e506fa6)
• ensure AgentTool text output when skip_summarization is True (b983fcf), closes #3881
• exclude live HTTP clients from trace serialization (59868ea)
• exit connection cleanly on expected GoAway signal in bidi streaming (4d165ef)
• fingerprint the cacheable context prefix (7c7f1e7)
• firestore: preserve update timestamps in list_sessions (99ba8ce)
• fix branch parsing and unify branch stamping (9e3b43f)
• prevent code-generation template injection via filenames (e042b8d)
• stop swallowing errors in the MCP session context (ccb8138)
• fix instructions_utils matching invalid nested paths (20ba01c)
• fix MCP debug-client factory compatibility with keyword-only factories (1ad8864)
• fix polling loop in IAM connector credentials provider when consent is pending (a614507)
• fix regression in instructions_utils placeholder matching (9ecbaed)
• fix Vertex AI Live API session replay on reconnect / modality switch (c007a87)
• guard against None converter results in RemoteA2aAgent handlers (2e3d717)
• guard user_content assignment against None in EvaluationGenerator (6bc9c9f)
• handle empty message in LiteLLM response (d3e793f)
• handle Pydantic models in safe_json_serialize for tool tracing (25d666a), closes #4629
• harden ContainerCodeExecutor sandbox by default (0a9ce0f)
• implement dynamic mTLS endpoint resolution for parameter manager (62b9700)
• implement dynamic mTLS endpoint resolution for secret manager (5d4a13f)
• import App lazily in _resolve_app to fix legacy Runner NameError (7481d07)
• check the authorization header case-insensitively in MCP mTLS logic (3870032)
• litellm: preserve Claude thinking blocks marked display "omitted" (7461863)
• litellm: preserve streamed reasoning deltas in the adapter (b9625bf)
• litellm: parse DeepSeek-V3 proprietary inline tool-call tokens (c5b2caa)
• litellm: recognize assistant- prefix as a valid OpenAI file ID (ea325c7), closes #5664
• live: correct the return type hint of handle_function_calls_live (9865e2b)
• live: forward thinking config (71d8c84)
• live: keep streaming tool yields from completing turns (07aa1e0)
• make EUC request args JSON-serializable (a181a39)
• map A2A Message.role to the correct GenAI content role (fe08a9f)
• mcp: await async MCP header providers (c01e538), closes #6090
• mcp: propagate trace context in the default streamable HTTP client (431e3c2), closes #4768
• migrate AgentRegistry base URLs from v1alpha to v1 (82432a3)
• models: gate Gemini cache creation on cacheable prefix tokens (1070036)
• fix N-sized sliding window (d00ad67)
• preserve Anthropic thinking blocks and signatures in the LiteLLM round-trip (febb250)
• preserve JSON-native types in A2A _serialize_value() (139c700), closes #5183
• prevent crash when parsing default values for typing.Any parameters (e360241)
• prevent empty responses after load_skill (7c79230)
• prevent VertexAiRagRetrieval from blocking the event loop (5898f37), closes #5033
• prevent warning logs when cancelling the MCP session runner task (4aa0fd8)
• propagate Gemini grounding metadata from ModelResponse (c303c62)
• raise ValueError for unsupported MIME types in the file_data URI path (42eceb3)
• reconnect on live connection 1011 error (f36d257), closes #5525
• recurse into JSON-native containers in A2A _serialize_value() (c08debc)
• remove unused userinfo_endpoint from GoogleApiToolset OIDC config (1509dcf)
• restore auth_token initialization for secret and parameter manager clients (46a2181)
• revert instruction-util refactoring that broke internal callers (59fe9b3)
• sandbox nested persona template rendering in evaluation prompts (30493ba)
• scope single-turn node inputs to the workflow branch (8d389e2)
• security: enable Jinja2 autoescape to prevent XSS in the gepa sample (a721c1e)
• send correct field names for sandbox input files (2b7e08a)
• sessions: drop unsupported part_metadata before Vertex appendEvent (40a0279), closes #6014
• sessions: strip tzinfo for MariaDB in DatabaseSessionService (2f799d5)
• strip tzinfo from datetime for MySQL in create_session (a012bb7)
• surface error for empty STOP model turn in non-streaming mode (932a9b5), closes #5631
• telemetry: always export Agent Engine logs to stdout (e6df097)
• telemetry: emit gen_ai.workflow.nested for nested workflows (20197de)
• terminate infinite retry loop in RunSkillScriptTool on SCRIPT_NOT_FOUND (89d9bda), closes #5684
• tools: accept dict output_schema in SetModelResponseTool (d69dedd), closes #5469
• tools: handle tuple schemas in the function-parsing fallback (4fa7741)
• truncate MCP HTTP debug logs over 1000 chars (3ebef82)
• apply custom Gemini connection logic to all 3.x models, not just 3.1 (8aff514)
• update litellm dependency constraint to 1.84.0+ (a912306)
• use branch-scoped events for auth responses (f706a1e)
• use the exchanged OAuth credential in ApplicationIntegrationToolset (e76df3d)
• use Modality enum for RunConfig.response_modalities (5c8c55a)
• use mTLS endpoint for Google OAuth2 token requests (ffe41f0)
• validate local eval path segments (7b87f91)

Performance Improvements

• avoid deepcopy of session contents when building LLM requests (400f512)
• create SQLite session schema once per service instance (10a2cc5)
• remove state injection when instruction has no placeholders (59970b6)
• skip event query in DB get_session when num_recent_events is 0 (7e8191a)

Documentation

• clarify is_final_response() is a public helper (978be4b), closes #4016
• update GoogleSearchTool docstring to refer to Gemini models (8b011f9)
• index missing reference guides in adk-agent-builder SKILL.md (c922b08)
• samples: add ManagedAgent code-execution sample (527e3c1)
• samples: add ManagedAgent sample using server-side google_search (969909f)
• workflow: add and update workflow developer guides (e5c7d20)

---

This PR was generated with Release Please. See documentation.