[Bug]:Blocking SendMessage returns stale task state when the agent ends in an interrupted state (INPUT_REQUIRED / AUTH_REQUIRED)
メンテナーはふだん 1 日以内に返信
評価
- 難易度
- 4/5
- 見積もり時間
- 3〜5日
- 初心者へのやさしさ
- 45/100
- issue の種類
- バグ
- 明瞭さ
- 明確に書かれている
- 活発さ
- 活発
- 技術スタック
- java
調査の方向性
Start with DefaultRequestHandler.onMessageSend, EventQueue.MainQueue.enqueueItemInternal, and MainEventBusProcessor; the report also gives a self-contained reproducer, InputRequiredStaleRepro.java. Trace when queued events are persisted and when the blocking response reads TaskStore, then reproduce with a delayed save and an INPUT_REQUIRED final event. Done means the blocking response returns the persisted interrupted state even when persistence lags.
索引モデルが issue の本文から書いたものです。
説明
What happened?
[Bug]: Blocking SendMessage returns stale task state when the agent ends in an interrupted state (INPUT_REQUIRED / AUTH_REQUIRED)
Version: org.a2aproject.sdk:*:1.5.0.Final (also present in main as of 2026-11-09)
Environment: macOS / OpenJDK 17.0.20.1, plain Java (no CDI), InMemoryTaskStore wrapped with a
fixed per-save delay, InMemoryQueueManager, MainEventBusProcessor, handler built via
DefaultRequestHandler.builder()
Affects: non-streaming SendMessage with returnImmediately omitted or false, when the last
event is INPUT_REQUIRED or AUTH_REQUIRED
Summary
For a blocking SendMessage, the returned Task is read from TaskStore
(DefaultRequestHandler.onMessageSend, Step 5, taskStore.get(taskId)), but the blocking path only
waits for the consumer future. If the agent's last event has not been persisted by
MainEventBusProcessor when Step 5 runs, the caller receives a stale state (SUBMITTED / WORKING)
even though the task is already INPUT_REQUIRED in the store a moment later.
Terminal states are protected by the awaitingFinalEvent machinery; interrupted states are not,
because TaskState.INPUT_REQUIRED.isFinal() == false and isInterrupted() == true.
This is the interrupted-state analogue of #1247 (fixed for terminal events by #1227).
Why it happens
EventQueue.MainQueue.enqueueItemInternalonly callsChildQueue.expectFinalEvent()when
isFinalEvent(event)is true.isFinalEventacceptsTaskState.isFinal()andA2AError—
INPUT_REQUIRED/AUTH_REQUIREDare excluded.- The blocking path (
DefaultRequestHandler.onMessageSend) closes the caller'sChildQueue
(Step 2) and waits for consumption (Step 3). WithisAwaitingFinalEvent() == false, the
consumer exits as soon as the queue is closed and empty
(ChildQueue.dequeueEventItem). - Step 5 then reads
TaskStore. Events still inMainQueue— acquired on the semaphore in
enqueueItemInternal, released only after persist + distribute — are invisible at this point. MainEventBusProcessoris asynchronous and persists before distributing, so the event is
durable shortly afterwards; the caller already returned.
The consumer's dequeueEventItem(QUEUE_WAIT_MILLISECONDS = 500) gives an accidental grace window:
with a fast store the event lands before the poll times out, which is why this is invisible in
simple examples and only shows up when persistence lags (slow DB, many events, write backlog)
beyond ~500 ms after the agent returns.
Reproduction
Self-contained single file, attached as InputRequiredStaleRepro.java. Only
a2a-java-sdk-server-common + a2a-java-sdk-spec 1.5.0.Final are required.
# pom: the two artifacts above at 1.5.0.Final
mvn -q dependency:build-classpath -Dmdep.outputFile=cp.txt
# interrupted last event, 600ms per persist -> stale
java -DsaveDelay=600 -Dcalls=3 -cp "$(cat cp.txt)" InputRequiredStaleRepro.java blocking
# same store, terminal last event -> correct
java -DsaveDelay=600 -Dcalls=3 -cp "$(cat cp.txt)" InputRequiredStaleRepro.java terminal
Observed:
mode=blocking expected=TASK_STATE_INPUT_REQUIRED saveDelay=600ms artifacts=0 calls=3
call#1 returned=TASK_STATE_SUBMITTED eventual=TASK_STATE_INPUT_REQUIRED STALE
call#2 returned=TASK_STATE_SUBMITTED eventual=TASK_STATE_INPUT_REQUIRED STALE
call#3 returned=TASK_STATE_SUBMITTED eventual=TASK_STATE_INPUT_REQUIRED STALE
=> 0/3 returned the expected state
mode=terminal expected=TASK_STATE_COMPLETED saveDelay=600ms artifacts=0 calls=3
call#1 returned=TASK_STATE_COMPLETED eventual=TASK_STATE_COMPLETED OK
call#2 returned=TASK_STATE_COMPLETED eventual=TASK_STATE_COMPLETED OK
call#3 returned=TASK_STATE_COMPLETED eventual=TASK_STATE_COMPLETED OK
=> 3/3 returned the expected state
A less artificial shape reproduces too — 50 ms per save with 12 artifact events before
requiresInput() (≈650 ms of persistence lag for the tail):
java -DsaveDelay=50 -Dartifacts=12 -Dcalls=3 -cp "$(cat cp.txt)" InputRequiredStaleRepro.java blocking
# => 0/3, e.g. returned=TASK_STATE_WORKING / SUBMITTED, eventual=INPUT_REQUIRED
GetTask immediately afterwards returns INPUT_REQUIRED — the state is not lost, only the blocking
response is wrong.
Suggested fix
The blocking path should guarantee the same invariant the terminal path gets from
awaitingFinalEvent: no event enqueued by the agent may still be in flight in MainQueue when
Step 5 reads TaskStore.
Option A (general): expose the existing in-flight count and wait for it to reach zero before Step 2,
e.g. QueueManager.awaitDrained(taskId, timeout) implemented on MainQueue
(size() == getQueueSize() - semaphore.availablePermits()), signalled from
releaseSemaphore() — which runs in MainEventBusProcessor's finally block, after persist and
distribute. A callback-based wake-up would miss the last event, so the signal has to be on the
release path.
Option B (narrower): extend the awaitingFinalEvent accounting to
state.isFinal() || state.isInterrupted(). This fixes the status-event case, but an artifact tail
(the last event being an artifact) would still race, so Option A is preferable.
Workaround for applications
Wrap the AgentExecutor so that execute() does not return until the task's queue is drained
(poll QueueManager.get(taskId).size() with a bounded timeout), or use
returnImmediately=true plus client-side GetTask polling.
Related
- #1247 — blocking
SendMessagedrops in-flight final events (fixed in 1.5.0 by #1227) - #1249 — builder blocking timeouts aligned with documented defaults
- #990 — API/hook to close streams after INPUT_REQUIRED / AUTH_REQUIRED
Relevant log output
Code of Conduct
- I agree to follow this project's Code of Conduct
- 主要言語
- Java
- スター
- 514
- フォーク
- 200
- 平均マージ
- 1日 2時間
- マージ済み PR(30日)
- 53
環境構築
- Dockerfile・Docker Compose ファイルなし
- プルリクエストのテンプレートあり
- コントリビューションガイドを読む
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
a2aproject/a2a-java のほかの issue
-
Document 1.x is the actively supported stream, and not 0.3.x対応中かも @Linux2010 が 2 日前に担当しました。 オープン
難易度 1/5 1〜3時間 初心者へのやさしさ 62/100
a2aproject/a2a-java#1321 ·
メンテナーはふだん 1 日以内に返信
-
HTTP+JSON CancelTask returns 409 Conflict instead of 400 Bad Request for TaskNotCancelableError再び着手できるかも @ravismash が 9 日前に担当しましたが、オープン中のプルリクエストはありません。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 76/100
a2aproject/a2a-java#1298 · コメント 5 件 ·
メンテナーはふだん 1 日以内に返信
-
fix: handle blank push notification config id consistently across transports対応中かも @prachisinghal-1 が 24 日前に担当しました。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 75/100
a2aproject/a2a-java#1012 · コメント 2 件 · 担当者 1 名 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 65/100
a2aproject/a2a-java#464 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信
-
Create a sample that demonstrates how to use a shared contextId across multiple tasks再び着手できるかも @tanish111 が 390 日前に担当しましたが、オープン中のプルリクエストはありません。 オープンsample
難易度 2/5 1〜3時間 初心者へのやさしさ 70/100
a2aproject/a2a-java#375 · コメント 5 件 · 担当者 1 名 ·
メンテナーはふだん 1 日以内に返信
a2aproject/a2a-java の issue をすべて見る
似ている issue
-
bug
難易度 2/5 1〜3時間 初心者へのやさしさ 78/100
apache/skywalking#14239 ·
メンテナーはふだん 1 日以内に返信
-
account bug exercise lecture modeling programming
難易度 2/5 1〜3時間 初心者へのやさしさ 64/100
メンテナーはふだん 1 日以内に返信
-
Re-executed query with IN condition on an index column returns deleted rows (stale IndexCursor)対応中かも @dbusche が今日担当しました。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 82/100
h2database/h2database#4580 ·
メンテナーはふだん 1 日以内に返信
-
vips-drift
難易度 2/5 1〜3時間 初心者へのやさしさ 74/100
Stirling-Tools/JPDFium#300 ·
メンテナーはふだん 1 日以内に返信
-
hermes-queue
難易度 1/5 1〜3時間 初心者へのやさしさ 85/100
chrisalunlloyd2-sudo/mindpalace#403 ·
メンテナーはふだん 1 日以内に返信