v2.14.12026-11-12
Bug Fixes
tracing:** turn off FastAPI's native tracing on Agent Engine (87e5399)
v2.14.02026-11-07
Highlights
This release graduates execution environments, A2A, evaluation, and core runtime modules from experimental, adds multi-run evaluation and semantic tool argument matching, adds Microsoft Teams and OpenAI Decisions integrations, and makes long multi-turn workflows faster.
Execution environments and sandboxes**:
* BaseEnvironment, LocalEnvironment, EnvironmentToolset, DaytonaEnvironment, and E2BEnvironment are now stable. (c54b253, 799fc94)
BaseEnvironment.readfile_stream streams files in chunks across LocalEnvironment, E2BEnvironment, and DaytonaEnvironment so ReadFileTool reads line ranges without loading the whole file into memory. See the unit guide for more details. (fd8d8c1)
* AgentEngineEnvironment reads and writes large files in chunks and reports commands over 570 seconds as timed out before the service deadline. See the unit guide and sample for more details. (4c88040, 5843c58, b13fa19, d3a199d)
* ContainerCodeExecutor supports input and output files, and RunSkillScriptTool runs skill scripts from validated paths and arguments instead of a shell command string. (effd641, ff61524)
Evaluation**:
MultiRunConfig (adk eval --numruns) and --parallelism run each eval case multiple times concurrently and combine scores or pass rates across runs. See the eval config and agent evaluator guides for more details. (7f3517e, e9e8f61)
AgentEvaluator accepts a BaseNode or App built at runtime, and --evalstorageuri stores eval files outside a read-only agentsdir. (ce92e92, ff66b1f)
* ToolArgsMatcher compares tool call arguments in evaluations and EnvironmentSimulation using exact, case-insensitive, numeric-tolerance, or LLM-backed semantic checks. See the unit guide for more details. (ed76f94, 08c289b)
A2A: The A2A integration is now stable, and adk generateagent_card builds an A2A agent card from the CLI. See the unit guide for more details. (95d4a56, 875e2ae)
Integrations**:
* TeamsRunner connects an ADK agent to Microsoft Teams chats and channels. See the unit guide for more details. (c4376a6)
* OpenAIDecisionsClassifier classifies workflow and tool-gating questions with the OpenAI Decisions API. See the unit guide for more details. (aa98d18)
MongoDbMemoryService adds vector search retrieval (retrievalmode="vector" or "auto") and TTL expiration (memoryttldays). See the unit guide for more details. (1c84bb9)
Stable APIs**: 26 auth, environment, app, CLI and cache modules, 16 toolset and integration features, and the mature evaluation and user simulation classes graduate from experimental, so you can build on them without experimental warnings. (c54b253, 799fc94, 1112606)
Workflow performance**: Long multi-turn workflows run faster and use less memory; a 30-node workflow's 200-turn run is 23% faster with 9% lower peak memory. (532580c, 1f21370)
Breaking changes
Enum tool arguments arrive as members: FunctionTool parameters annotated Enum, Optional[Enum], or list[Enum] now receive enum members instead of the raw strings the model sent (as FUNCTIONTOOLARGVALIDATION already did). For a plain Enum, arg == "value", string-keyed dict lookups, match on strings, json.dumps, and string methods no longer work. A callable requireconfirmation still receives the raw values (unless FUNCTIONTOOLARGVALIDATION is on). For a (str, Enum), str() and, on Python 3.11+, f-strings now render Cls.MEMBER. Compare against members, use .value, or switch to StrEnum. Enum members a tool returns in its result are still sent to the model as their values. (82fe029, 58332a2)
VertexAiSessionService.createsession accepts only session config options: extra keyword arguments are limited to displayname, ttl, expiretime, and labels (plus camelCase aliases). Other Sessions API config keys, such as httpoptions, sessionstate, sessionId, and waitforcompletion, now raise ValueError (HTTP 400 when sent as session options to adk apiserver). Use state= and sessionid= for state and IDs. (968cd86)
RunSkillScriptTool no longer takes command in environment mode: with a SkillToolset environment, the model now passes args, shortoptions, and positional_args instead of a free-form shell command, scripts run from the
v2.13.02026-10-23
Highlights
This release stabilizes core features while introducing TypeSafe workflow classification, live audio interactions, MongoDB integrations, and execution performance improvements.
Stability**: Access 12 mature experimental features now promoted to stable status. See the unit guide for more details. (ea298d4)
Classifiers**: Route workflows with TypeSafe's Jev models via the new TypesafeClassifier and ClassifierNode. Jev returns calibrated probabilities in a single forward pass, much faster than an LLM. See the unit guide for more details. (ddf8c55, e8c4bac)
Live Audio**: Enable natural real-time voice interactions with barge-in support alongside Gemini speech-to-text and text-to-speech integration. See the unit guide for more details. (2e7ef92)
MongoDB Sessions & Memory**: Persist sessions in MongoDB and share them across runner replicas with the new MongoDbSessionService. Add long-term memory without an embedding model using MongoDbMemoryService, which recalls past turns by keyword match on any MongoDB deployment, with no vector index needed. Both are experimental. See the session service and memory service guides for more details. (0df43f5, e40e349)
MongoDB**: Deploy MongoDbToolset to Agent Engine without packaging your connection string, and let Atlas Automated Embedding embed search queries server-side, with no Google embedding call or credentials needed. See the unit guide for more details. (bc3773f, 2f6c666, 8bbfc33)
Performance**: Enjoy up to 8x faster execution turns for string-model agents and reduced event-loading overhead. (772f139)
Breaking changes
Telemetry: Defaults to OpenTelemetry GenAI v2 (otelsemconv144, removing callllm); set ADKTELEMETRYSCHEMAVERSIONOPTIN=otelsemconv1_36 to keep the legacy v1 schema. See the unit guide for more details. (7838488)
<details>
<summary>All changes</summary>
⚠ BREAKING CHANGES
telemetry: deprecate callllm span and OpenTelemetry 1.36 GenAI semconv
Features
add deletememory api to BaseMemoryService (41e5c7b), closes #6949
* add MongoDB-backed memory service (e40e349)
* add MongoDB-backed session service (0df43f5)
* add OpenSandbox environment (69d1c90), closes #6758
classifiers:** add BaseClassifier and typed question/answer types (773418f)
classifiers:** add ClassifierNode for workflow routing (e8c4bac)
classifiers:** add LlmClassifier (772b577)
eval:** split invocation duration into model, tool and framework time (e3797a4)
features:** promote 12 mature experimental features to stable (ea298d4)
honor ADKSUPPRESSEXPERIMENTALFEATURE_WARNINGS (b592dee), closes #5114
integrations:** add TypesafeClassifier for TypeSafe's Jev models (ddf8c55)
integrations:** keep MongoDB credentials out of Agent Engine packages (ab5cb45)
live:** add barge-in support to CascadeLiveConnection (2e7ef92)
live:** add Gemini speech-to-text and text-to-speech for CascadeLive (f78149a)
live: add ZIPSTORED visual frame pack and unpack helpers (17d8a5a)
* make MongoDbToolset picklable for Agent Engine (2f6c666)
plugins:** add agent evaluation session and turn trace views (ab9c994)
plugins:** classify error-bearing tool results and extract shared callback helpers (a4b8ee9), closes #7112
plugins:** classify write-time 403 and 404 drops in BigQueryAgentAnalyticsPlugin (d5c87a6)
plugins:** log terminations, node results and tool result errors in the logging plugins (6a77d48)
record googlesearch grounding on LLM spans (ead208a), closes #7345
samples:** add Secret Manager and Parameter Manager integration samples (7391411), closes #7582
seed adk web sessions from initialstate.json (3c8c63e), closes #4961
* support Atlas Automated Embedding in MongoDB search ([8bbfc33](https://github.com/googl
v2.12.02026-10-13
Highlights
This release enhances execution performance in long sessions while introducing finer control over tool execution, workflow approvals, and deployment security.
Performance**: Cut time to first model request by 40% in long sessions. (1754b3e)
Tools: Intercept and filter tool outputs before returning them to the model using aftertool_callback. (fdda17c)
Workflows: Require human confirmation before executing workflow nodes via requireconfirmation. (988fd1a)
Deployment**: Deploy agents to Agent Engine using dedicated custom service accounts. (629e119)
Python 3.15**: Install and run ADK on Python 3.15. (75aef1e)
<details>
<summary>All changes</summary>
Features
add --statefile option to adk run (c390266), closes #7083
add aftertool_callback to screen tool output (fdda17c), closes #6966
* add skill-level security support to AgentCardBuilder (79a7e49)
agents:** adapt BaseNode in tool consumers and preserve ToolUnion compatibility (8350c14)
antigravity:** preserve model thinking parts, client tool responses, and sub-agent hierarchy in ADK events (fac77be)
cli:** source the agent builder assistant's ADK knowledge from the installed package (ab9fffc)
* continue with de-identified text when only SDP matched (315c3dd), closes #7369
* encrypt google credential in session (42a17a9)
eval:** report the efficiency metrics for evals run from the Dev UI (49bf291)
* install lightweight Gemini Enterprise (Agent Platform) SDK without the GAPIC stack (d92735d)
live:** add an internal model for Live background tool calls (3f25ab5)
live:** implement CascadeLive model & sample (128faab)
* migrate ADK to google-cloud-aiplatform v2.2 (agentplatform) (77d4dcd)
* migrate VertexAiExampleStore and VertexAiRagRetrieval away from vertexai.preview (9e411be)
* persist skill-script outputs as artifacts (beaef0d), closes #5579
plugins: add onschemaerror and onschema_ready callback hooks to BigQueryLoggerConfig (4d31fa9)
plugins: enrich AGENTSTARTING metadata in BigQueryAgentAnalyticsPlugin (c32ad3b)
* print next steps after adk create (06b7847)
* resume Gemini generations paused with a continuation token (b3cbb47)
skills: migrate GCPSkillRegistry.searchskills from GET to POST (e9464ca)
* support custom service accounts for agent engine deploy (629e119), closes #2951
telemetry:** name skill tool spans after the skill they touch (c11060c)
tools:** run a sync FunctionNode tool's callable on the tool thread pool (71d5ed7)
tools:** run non-live generator FunctionTools via FunctionNode (0ee891a)
tools: tag modelconsult advisor requests with client label (068610f)
* user feedback survey workflow (f5efa2a)
vmaas:** add sandbox lifecycle helpers to the sandbox manager (46dff4b)
vmaas:** find or create sandbox templates per container config (650394f)
workflow:** run a sync generator FunctionNode's steps on the tool thread pool (8112f4a)
workflow: support requireconfirmation in @node and FunctionNode (988fd1a)
workflow:** support scalar auto-boxing for ToolNode input (873eed5)
workflow:** support task sub-agent delegation and resume in task-mode wrapper (8d71635)
workflow: support tool authentication requests and credential resume in ToolNode (c001a6c)
Bug Fixes
a2a: support toolcall and tool_response in A2A part converter (a334bac)
* add JSON-tolerant LiteLLM tool call argument parsing (a01b226)
add namespaced mode for forwarded A2A session contextid (c213adf), closes #7305
* agent engine memory service with A2A endpoint activated (d919ec0), closes #3458
agents:** centralize resume routing decision and fix sub-branch/callback/abort routing ([8a43244](https://github.com/google/adk-python/co
v2.11.02026-10-02
Highlights
This release adds graceful cancellation and tool confirmation to workflows, a tool for consulting another model mid-task, and a built-in SQLite memory service.
Execution cancellation: Pass an abortsignal to Runner, Workflow, and nodes to stop a run gracefully; /run_sse now cancels the run when the client disconnects. See the unit guide for more details. (ef5bbcf, 3d73603)
Tool confirmation in workflows**: Tool nodes now pause for user approval via RequestInput, the same way an LlmAgent does, instead of passing an error downstream. (ce132b9)
ModelConsultTool**: Let an agent consult another model mid-task, capped by per-turn and per-session budgets. See the unit guide for more details. (84cc99a)
SQLite memory service**: Keep agent memory in a local SQLite database, selected with a sqlite:// memory service URI. (9625b06)
MCP SDK 2.x**: Connect to MCP servers over the modern protocol through a new opt-in path. (e738c26)
<details>
<summary>All changes</summary>
Features
* add a sample preloading memory profiles into the instruction (fdf1b7f)
* add avatar configuration to server commands (e4c0d94), closes #5435
* add max llm calls to server commands (14f4154), closes #5434
add optional abortsignal support to Runner, Workflow, and Nodes (ef5bbcf), closes #4796
add pagination to listaccessibledataagents in data_agent toolset (46d5a2d)
* add sqlite memory service (9625b06)
* add the model consult session context handover layer (b2da4c6)
cli: wire abortsignal to /run_sse on client disconnect (3d73603)
* default Vertex project from GCP metadata (8d8bbd2)
events:** add internal metadata for ADK events (8e29f16)
honor toolthreadpoolconfig for sync tools outside live mode (c50ade3)
* let BigQuery tools run where CMEK is required (4d06641), closes #3931
live:** default to a pre-built avatar for VIDEO live sessions (d5c9b11)
* mark spans whose response came from a callback (9633ab9)
mcp:** add an opt-in modern-protocol connect path for MCP SDK 2.x (e738c26)
plugins:** add optional ToolCallIntegrityPlugin (b7efc4e)
propagate grounding metadata from MCP meta (0960104), closes #6081
skip init__.py for config-based adk create (d594b69), closes #6753
* synthesize abort event and function response on cancellation (da65851)
telemetry:** move skill telemetry span attributes out of experimental (e0f4c97)
tools:** add ModelConsultTool with turn and session budgets (84cc99a)
tools: invoke advisor models without tools for modelconsult (28c47b5)
workflow:** pause tool nodes for tool confirmation via RequestInput (ce132b9)
workflow: propagate skipsummarization from node tools to tool response (5a0421c)
workflow:** run plugin tool callbacks around ToolNode calls (cfeece9)
Bug Fixes
* accept a client factory written against either httpx major (438c3eb)
* accept dotted registry ids in GCPSkillRegistry (cbbdec3), closes #7136
antigravity:** extract real execution output for built-in tool steps (3fd932d)
artifacts:** return None for negative versions in InMemoryArtifactService (6193957)
* cancel the in-flight tool call when the caller is cancelled (f0dd560)
* classify plugin output before persisting events (044a1ec), closes #7184
* detect a dead MCP session whose transport sits behind a dispatcher (8632980)
* drop stale replies to superseded tool updates (fdca5e7)
* drop unpairable trailing FRs in rearrange (643df96), closes #6751
eval:** skip content-less events when mapping Vertex multi-turn turns (fd2ca87)
flows:** detect thought-only and whitespac
v2.10.02026-09-25
Highlights
This release introduces advanced skill lifecycle management, expands database and model integration support, and brings richer efficiency metrics to agent evaluation.
Skills: Control resource usage and tool persistence dynamically using new ephemeral lifecycles and active skill limits (experimental; enable with ADKENABLESKILLLIFECYCLE=1). (43b73e4)
Database Integrations**: Perform high-performance vector and hybrid searches seamlessly within your agent flows with the new MongoDB toolset. (0961ced)
Evaluation**: Optimize agent execution costs and latency with new evaluation metrics for tracking duration, token consumption, and model call counts. (2d428ea)
Model Support**: Integrate OpenAI reasoning models more effectively with automated request parameter adaptation and precise reasoning token reporting. (52a2f0f)
Behavior changes
BigQuery protected write mode** now runs a non-SELECT statement only when the dry run places it in the session's anonymous dataset, so multi-statement scripts, CALL, EXPORT DATA and other statements the dry run gives no destination are rejected. (8b883d0)
BigQuery protected mode** keeps its BigQuery session in process memory instead of session state, so its temporary tables do not survive a restart or carry over to another replica. (094012b)
OpenAIResponsesLlm ignores thinkingconfig (thinkinglevel / thinkingbudget) with a warning; use OpenAIGenerateContentConfig.effort instead. (b3d1392)
AgentEvaluator.evaluate and evaluateevalset** raise ValueError when no eval cases are evaluated, instead of passing. (9dbc2ae)
Instruction templating** leaves ${var} and backslash-escaped \{var} as written instead of filling them from state. (0caecd2)
Legacy live-audio modules under google.adk.flows.llmflows (audiocachemanager, audiotranscriber, transcriptionmanager) emit a DeprecationWarning on import; move to google.adk.live. Test suites run with -W error will fail on these imports. (bf2bc56)
<details>
<summary>All changes</summary>
Features
* add a duration efficiency metric to ADK eval (49e7264)
add an EPHEMERAL skill lifecycle that lasts one turn (experimental, off by default; enable with ADKENABLESKILLLIFECYCLE=1) (f938abd)
add an opt-in unloadskill tool to SkillToolset (experimental, off by default; enable with ADKENABLESKILL_LIFECYCLE=1) (ce53a36)
* add dev-only deploy endpoints for Agent Runtime, Cloud Run, and GKE (1235104)
* add informational efficiency metrics (tokens, calls) to ADK eval (2d428ea)
* add MongoDB toolset with vector and hybrid search (0961ced)
* add name-based request processor helpers to BaseLlmFlow (fd335cd)
add onerror handler to skill listing functions (9b220e7)
add optional contextbuilder to RemoteA2aAgent (322e3bf), closes #3301
* add programmatic skill activation APIs to SkillToolset (a0f3955)
add skill lifecycle modes and an active-skill cap to SkillToolset (experimental, off by default; enable with ADKENABLESKILLLIFECYCLE=1) (43b73e4)
bigquery: add defaultprojectid and defaultdataset_id to BigQueryToolConfig (6f301fc)
cli:** add gemini-3.8-flash to the adk create model options (6592ee5)
cli:** auto-configure session and memory services on Agent Runtime (fede561)
context:** add abort signal primitives to InvocationContext and Context; the Runner and workflows do not act on an abort yet (d99b23f)
drop an unloaded skill's instructions from later requests (experimental, off by default; enable with ADKENABLESKILLLIFECYCLE=1) (accb906)
expose serving tier via RunConfig.servicetier (3e3d1dc)
expose session options in apiserver REST endpoint (fa4719e), closes #6342
integrations:** add a google-adk[openai] extra (9be86bf)
integrations:** move the OpenAI models to google.adk.integrations.openai; google.adk.labs.openai still re-exports them (95c0591)
* let SkillToolset notice that a loaded skill has changed (f848b7e)
mcp:** identify ADK in the MCP clientInfo handshake (5117f28)
mcp:** identify ADK in the User-Agent of MCP HTTP requests (061dcd6)
openai:** adapt request params for reasoning models on both surfaces (137eba8)
openai: add apikey/base_url with per-request key resolution to OpenAILlm (56aabce)
openai:** add OpenAIGenerateContentConfig and per-model reasoning effort (bb9023d)
openai: honor toolconfig mode and all tool declarations in OpenAILlm (ed758bb)
openai:** report reasoning tokens
v2.9.22026-09-18
Highlights
This release focuses on refining telemetry behavior by correcting how OpenTelemetry event names are handled across different environments.
Telemetry**: OpenTelemetry event names are now preserved on platforms outside of Agent Engine, ensuring more accurate and consistent tracking. (9110770)
Bug Fixes
telemetry:** only drop the OTel event name on Agent Engine (9110770)
v2.9.12026-09-15
Highlights
This release focuses on improving visibility into model reasoning steps when utilizing Claude's adaptive thinking capabilities.
Claude Integration**: Access the step-by-step reasoning process of Claude models by ensuring visible thoughts are requested during adaptive thinking tasks. (ba0d542)
Bug Fixes
* request visible thoughts for Claude adaptive thinking (ba0d542)
v2.9.02026-09-10
Highlights
This release focuses on agent resilience and ecosystem integration by introducing automatic model failover, native voice support via LiveKit, and compatibility with MCP SDK 2.x.
Models**: Safeguard agent uptime by automatically failing over to backup models when the primary model encounters errors. (c300b8d)
Integrations**: Build rich voice and telephony agents using the newly added LiveKit runner. (f277d91)
Workflows**: Simplify graph workflow management by authoring and loading ADK 2.0 graphs directly from declarative YAML configurations. (2a9461b)
MCP**: Upgrade to MCP SDK 2.x capabilities seamlessly while retaining full backward compatibility with 1.x servers. (856acf2)
Behavior changes
Workflow node resumption**: A node that failed now runs again when the workflow resumes, where before it replayed as though it had completed. Make node bodies idempotent: a node that performs an external side effect and then fails will perform that side effect again on every resume. (91573eb)
GCS tool local paths: The GCS tools now read and write local files only inside the directory named by localfile_root, and refuse local file access entirely when that setting is absent. Paths may be absolute or relative, and are judged by where they resolve. (c569796)
In-memory sessions only**: InMemorySessionService now raises SessionNotFoundError when an event is appended to a session it does not hold, instead of accepting the event and discarding it. The database-backed services already behaved this way, so this affects in-memory sessions alone. (15b1392)
<details>
<summary>All changes</summary>
Features
add a2astate_forwarding sample (1b28de4)
* add FallbackModel for automatic failover between models (c300b8d)
add getauthenticatedurl and getsigned_url to GcsArtifactService (10ac52b)
add ignoreargs option to tool trajectory evaluation (e2a213f)
add transferreason to transfertoagent to prevent loops (22ab4d8)
* agent evaluations print detailed results when all tests pass (e1ae543), closes #3891
* generalize docker build and run for multicloud environments (0673f05)
integrations:** add LiveKit runner for voice and telephony (f277d91)
* load ADK 2.0 graph workflows from YAML configuration (2a9461b)
mcp:** support MCP SDK 2.x alongside 1.x (856acf2)
* support hyphenated column names in BigQuery tools (b736b0d)
telemetry:** add ability to track skill loads (0cd24c8)
telemetry:** add script execution instrumentation (0dbc37d)
telemetry:** export logs over OTLP to telemetry.googleapis.com (5e6df42)
tools:** support FunctionNode auto-inference in NodeTool (ea8609d)
Bug Fixes
a2a:** quote a fetched card description and drop relayed auth responses (7ee3ae9)
a2a:** require https for a non-loopback agent card URL (fe30ebb)
a2a:** stop a completed task delegation breaking later peer delegations (04be48b), closes #6831
* add optional OIDC verification for Pub/Sub and Eventarc triggers (73d9fe0)
* append the user's next turn when it joins a paused task (678d7e9)
apply statedelta when resuming without a new_message (6de43b0), closes #6644
artifacts:** give concurrent gcs artifact saves distinct versions (0a12027)
auth: declare that AuthHandler.generateauth_uri can return None (e4c8994)
* balance callback lifecycle for hallucinated tool calls (f842a15), closes #4775
bigquery:** lazy-load Dataplex so BigQueryToolset imports without it (b65be01)
callables:** extract unified CallableSpec and resolve doc and unwrap edge cases (c506ddf)
* cancel the invocation when a sync run() generator is closed early (080d5e7)
cli: explicitly set memoryserviceuri='memory://' when --inmemory is passed (b0bb3dd)
cli:** make the decorators on API and dev server routes take effect (308cc32)
cli:** sync the Agent Engine class-method catalogue with its source (0043044)
* close a task-mode delegation when the remote agent finishes (4cd8aa4)
* coerce an integral float back to int for an int-typed tool parameter (adbee3c)
* coerce callable AgentInfo.instruction for app-info (ada8652), closes [#6909](https://gith
v1.39.12026-08-27
Bug Fixes
a2a:** Port event action allowlist, agent card description source and resume flattening to v1 (#6801) (1f898a6)
artifacts:** Port app-scoped file artifact storage and layout-derived payload paths to v1 (#6795) (0ae2bff)
artifacts:** Port artifact reference scoping and path-segment validation to v1 (#6794) (efc5bb8)
cli:** check the Host header on every local API server request (v1) (#6789) (15bf230)
cli:** Port deploy ignore-file handling to v1 (#6793) (8467bf0)
* close the residual gaps from the v1 backport review (#6890) (218061e)
integrations:** send api registry credentials only to google api endpoints (v1) (#6889) (1e9e117)
mcp:** Port config stdio opt-in and reserved tool name checks to v1 (#6796) (28b32b4)
models:** Port Gemini context cache fingerprint scoping to v1 (#6804) (f2f8456)
plugins:** sanitize BigQuery analytics rows and build GCS paths per call (v1) (#6808) (80e56de)
* Port A2A agent card RPC target origin validation to v1 (#6800) (ccb4812)
* Port agent loader and file path resolution fixes to v1 (#6788) (8bc927f)
Port agent-config code-reference and configpath validation to v1 (#6790) (15ae713)
* Port branch-scoped auth responses and OAuth2 nonce forwarding to v1 (#6803) (5817d30)
* Port code executor container and pod isolation defaults to v1 (#6807) (1b4da44)
* Port credential and inline-data field exclusions in logs, reprs and spans to v1 (#6797) (7c2075c)
* Port eval identifier validation and persona template rendering to v1 (#6806) (0a4a5c6)
* Port migration unpickle allowlist and database URL redaction to v1 (#6791) (6deda28)
* Port session id validation, thread id scoping and Vertex RAG cleanup fixes to v1 (#6809) (3fec8c5)
* Port skill resource path and skill name validation fixes to v1 (#6805) (1353e8d)
* Port URL validation, client timeout and credential scoping fixes to v1 (#6802) (7b6547f)
Route thread-pool and live-mode tool dispatch through runasync (v1) (#6799) (48c56c3)
* Scope custom eval metrics per registry and resolve their function path from the eval config (v1) (#6792) (9886410)
sessions:** accept a full session resource name again on v1 (#6888) (ef4f1e0)
* Validate user message parts and agent transfer targets (v1) (#6798) (d830355)