RemoteA2AAgent never attaches Message.metadata() - no way to propagate any custom data to the remote agent
维护者通常 1 天内回复
@hemasekhar-p 已经在做这个了。
开始于 2026年8月18日。
评估
这个 Issue 还没有评估数据。
描述
Is your feature request related to a problem? Please describe.
RemoteA2AAgent builds the outbound io.a2a.spec.Message via prepareMessage() / newA2AMessage(),
but neither method ever calls Message.Builder#metadata(...). This means there is currently no way
for a Java ADK application to pass any custom data - session.state(), a user id, a tenant id, an
auth-scoped identifier the remote agent's tools need - to a remote A2A agent. The remote agent's tools
receive the conversation content only; anything the calling agent knows about the current user/session
is silently unavailable on the other side of the A2A boundary.
This is a real limitation for a common pattern: a tool on the remote agent needs to resolve a resource
(e.g. an OAuth access token) that is looked up by a caller-supplied identifier (e.g. user_id) stored
in session.state(). In-process sub-agent calls get this for free (session.state() is shared); A2A
calls get nothing.
Note this is not the same as two issues I filed previously, and I want to make the distinction
explicit so it's easy to keep this one scoped:
- #1240 (fixed in
410ff810) is about the receiving side:AgentExecutorused to silently drop
incomingMessageSendParams.metadata()instead of routing it intoRunConfig.customMetadata().
That's fixed - a receiving agent can now reada2a_metadatafromRunConfig.customMetadata()and,
via a nativebeforeAgentCallback, copy whatever it needs intosession.state(). - #1258 is about
RemoteA2AAgenthardcoding the 4th argument (ClientCallContext) of
a2aClient.sendMessage(...)tonull, which breaks transport-level concerns (HTTP header
resolution, credential services used to authenticate the A2A call itself). - This issue is about a third, independent gap: even with both of the above fixed, the
Messageobject itself - the 1st argument tosendMessage, built byprepareMessage()- never
gets.metadata(...)attached at all. There is no code path, and no builder hook, to put anything
there. Fixing #1258 alone would not address this:ClientCallContextandMessageare separate
parameters built independently.
Describe the solution you'd like
adk-python's RemoteA2aAgent already solves exactly this with an opt-in callback:
# src/google/adk/agents/remote_a2a_agent.py:146-148
a2a_request_meta_provider: Optional[
Callable[[InvocationContext, A2AMessage], dict[str, Any]]
] = None
# src/google/adk/agents/remote_a2a_agent.py:739-742
if self._a2a_request_meta_provider:
parameters.request_metadata = self._a2a_request_meta_provider(
ctx, a2a_request
)
A caller can implement this to explicitly select what to forward, e.g.:
def my_meta_provider(ctx: InvocationContext, message: A2AMessage) -> dict[str, Any]:
return {"user_id": ctx.session.state.get("user_id")}
remote_agent = RemoteA2aAgent(..., a2a_request_meta_provider=my_meta_provider)
I'd like RemoteA2AAgent (Java) to expose the equivalent extension point, e.g.:
@FunctionalInterface
public interface A2ARequestMetadataProvider {
Map<String, Object> provide(InvocationContext invocationContext, Message outgoingMessage);
}
RemoteA2AAgent.builder()
...
.requestMetadataProvider((ctx, message) -> Map.of("user_id", ctx.session().state().get("user_id")))
.build();
and, inside prepareMessage(), call it and attach the result via .metadata(...) on the Message.Builder.
This is deliberately opt-in and lets the caller pick exactly what crosses the A2A boundary - it does not
ask for session.state() to be forwarded automatically or in full, which I understand is intentionally
avoided elsewhere in ADK (per the #1240 resolution comment).
The provider is a plain callback with no fixed/whitelisted set of keys baked into the API - ADK would
simply attach whatever Map<String, Object> the caller's implementation returns. It's entirely up to the
application to decide what to include: a single identifier, several selected keys, or (if it chooses to)
all of session.state(). This mirrors the full flexibility of a2a_request_meta_provider in adk-python -
the library imposes no restriction on which keys or how many can be returned, it only wires the callback
through to Message.metadata().
Minimal reproducible example (runnable today, no external services needed)
Drop this test method into
a2a/src/test/java/com/google/adk/a2a/agent/RemoteA2AAgentTest.java (it uses only fixtures/imports
already present in that file) and run:
mvn -pl a2a test -Dtest=RemoteA2AAgentTest#runAsync_doesNotPropagateSessionStateToOutboundMessage
The test passes today, which is the bug: it proves session.state() - set up exactly the way an
application would populate it via stateDelta before running the agent - never reaches the Message
sent to the remote peer, even though mockClient.sendMessage(...) is the exact call site
prepareMessage() feeds.
@Test
@SuppressWarnings("unchecked") // cast for Mockito
public void runAsync_doesNotPropagateSessionStateToOutboundMessage() {
RemoteA2AAgent agent = createAgent();
// Simulates an application that populated session.state() via stateDelta before this run -
// e.g. a user id a remote tool would need to resolve an OAuth token, exactly as it would for
// an in-process sub-agent call.
Session sessionWithState =
Session.builder("session-state-repro")
.appName("demo")
.userId("user")
.state(ImmutableMap.of("user_id", "user-42", "tenant_id", "tenant-7"))
.events(
ImmutableList.of(
Event.builder()
.id("e1")
.author("user")
.content(
Content.builder()
.role("user")
.parts(ImmutableList.of(Part.builder().text("hello").build()))
.build())
.build()))
.build();
InvocationContext context =
InvocationContext.builder()
.sessionService(new InMemorySessionService())
.artifactService(new InMemoryArtifactService())
.pluginManager(new PluginManager())
.invocationId("invocation-state-repro")
.agent(new TestAgent())
.session(sessionWithState)
.runConfig(RunConfig.builder().build())
.build();
mockStreamResponse(consumer -> consumer.accept(createFinalEvent("ok"), agentCard));
var unused = agent.runAsync(context).toList().blockingGet();
ArgumentCaptor<Message> messageCaptor = ArgumentCaptor.forClass(Message.class);
verify(mockClient)
.sendMessage(messageCaptor.capture(), any(List.class), any(Consumer.class), any());
Message sentMessage = messageCaptor.getValue();
// BUG: session.state() (user_id, tenant_id) is fully known to invocationContext at this point,
// but prepareMessage()/newA2AMessage() never call .metadata(...), so it never reaches the
// outbound Message. A remote agent's tools have no way to see it - even though the exact same
// data would be visible via session.state() for an in-process sub-agent call.
assertThat(sentMessage.getMetadata()).isAnyOf(null, ImmutableMap.of());
}
Environment
google-adk-a2a: 1.8.0 (currentmain, confirmed present atRemoteA2AAgent.java:196-213
(newA2AMessage/prepareMessage) andRemoteA2AAgent.java:240(thesendMessagecall site))- Java 17
- 主要语言
- Java
- 星标
- 1.7k
- 派生
- 433
- 平均合并
- 3 天 13 小时
- 30 天内合并 PR
- 42
环境准备
在浏览器里用你自己的 GitHub 账号启动这个项目的开发容器。
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
google/adk-java 的其他 Issue
-
GeminiUtil placeholder user turn ("Continue output. DO NOT look at this line ...") is flagged by prompt injection filters可能已有人在做 @hemasekhar-p 于 3 天前认领。 未关闭needs review
难度 2/5 1-3 小时 新手友好度 76/100
google/adk-java#1628 · 1 条评论 · 已指派 1 人 ·
维护者通常 1 天内回复
-
[spring-ai] ToolConverter silently drops enum and items from tool parameter schemas可能已有人在做 @hirematha 于 6 天前认领。 未关闭needs review
难度 2/5 1-3 小时 新手友好度 76/100
google/adk-java#1609 · 2 条评论 · 已指派 1 人 ·
维护者通常 1 天内回复
-
[spring-ai] Streaming responses ending with CJK punctuation (。!?) are misclassified as partial and never persisted to the session可能已有人在做 @hirematha 于 6 天前认领。 未关闭needs review
难度 2/5 1-3 小时 新手友好度 84/100
google/adk-java#1608 · 3 条评论 · 已指派 1 人 ·
维护者通常 1 天内回复
-
FirestoreSessionService compares event timestamps as text, reordering or skipping same-second events未关闭
难度 3/5 1-2 天 新手友好度 50/100
维护者通常 1 天内回复
-
难度 4/5 3-5 天 新手友好度 45/100
维护者通常 1 天内回复
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 66/100
-
难度 2/5 1-3 小时 新手友好度 64/100
utopia-rise/godot-jvm#1004 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
spring-projects/spring-grpc#442 ·
-
Expose numberOfPermits in RateLimiterEvent.toString() and the ratelimiterevents actuator DTO可能已有人在做 关联的 PR 仍在进行中或已合并。 未关闭
难度 2/5 1-3 小时 新手友好度 72/100
resilience4j/resilience4j#2547 ·
维护者通常 9 天内回复
-
Clock.MakeDate continues execution and returns a rolled-over instant after dispatching error on invalid date可能已有人在做 关联的 PR 仍在进行中或已合并。 未关闭
难度 1/5 1 小时以内 新手友好度 82/100
mit-cml/appinventor-sources#4155 ·
维护者通常 1 天内回复