Repository navigation
Description
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 terminalObserved:
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_REQUIREDGetTask 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
- [Bug]: Blocking SendMessage drops in-flight final events: InternalError: Timeout waiting for task <id> consumption #1247 — blocking
SendMessagedrops in-flight final events (fixed in 1.5.0 by fix(server): deliver awaited final events to gracefully closed child queues #1227) - fix(server): align builder blocking timeouts with documented defaults #1249 — builder blocking timeouts aligned with documented defaults
- Provide an API/hook to close streams after INPUT_REQUIRED / AUTH_REQUIRED #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
Activity
[-][Bug]:[/-][+][Bug]:Blocking SendMessage returns stale task state when the agent ends in an interrupted state (INPUT_REQUIRED / AUTH_REQUIRED)[/+]WMK666666 commentedon Nov 10, 2026
Fixed in #1315.
Root cause I confirmed while reading the blocking path in
DefaultRequestHandler#onMessageSend:queueClosed.onEventreturns as soon as it has accepted the event; the actual persistence happens later inMainEventBusProcessor#processEvent, and only then is the semaphore permit released.input-required/auth-required), Step 5 can read theTaskStorebefore the lastTaskStatusUpdateEventhas been written, and returns the previous state instead.I took your Option A rather than a fixed sleep: added
EventQueue#awaitDrained(timeout, unit), which pollsMainQueue.size()(i.e.getQueueSize() - semaphore.availablePermits(), the number of events accepted but not yet processed) until it reaches zero, and called it between Step 3 and Step 5 for the interrupted branch only. Terminal states were already covered byawaitingFinalEvent, so they are unaffected.Tests:
EventQueueDrainTest(4) for the queue primitive,BlockingSendMessageStaleStateTest(3) coveringinput-required,auth-requiredandcompleted. Reverting the new step makes exactly the two interrupted-state tests fail (workingreturned instead ofinput-required/auth-required), while thecompletedone stays green — which matches the 2/3 ratio in your report.Shay-Deng commentedon Nov 12, 2026
I read #1314 and #1315 side by side, since both take Option A from the issue. Notes in case they help pick one. This is from the diffs and their CI (green on both); I haven't run either locally.
Common to both: the wait sits between Step 3 and the
TaskStoreread, it uses the in-flight countMainQueuealready has (getQueueSize() - availablePermits(), released inMainEventBusProcessor'sfinallyafter persist and distribute),ChildQueuedelegates to its parent, the timeout reusesconsumptionCompletionTimeoutSeconds, and a timeout falls back to today's behavior. Both also replace the Step 4 note from #611 that deliberately avoided an explicit wait here, so that is probably the main thing to sign off on.Differences:
public abstract boolean awaitDrained(...)toEventQueue.EventQueuehas protected constructors, so a subclass outside this repo would stop compiling. fix(server): wait for in-flight events before reading the task in blocking sendMessage #1314'sawaitInFlightEventsProcessedhas a no-op default and is overridden inMainQueueandChildQueue.releaseSemaphore()notifies and checkssize()while holding the same lock, so the last release can't be missed; it also routes themainEventBus.submitfailure path throughreleaseSemaphore(). fix(server): return the interrupted state from a blocking SendMessage #1315 pollssize()every 1 ms, which is simpler and can't miss it either. Both look correct. The remark in fix(server): return the interrupted state from a blocking SendMessage #1315 that a release-path signal "would still race" doesn't apply to fix(server): wait for in-flight events before reading the task in blocking sendMessage #1314's version.agentCompletionTimeoutSeconds, the response is documented as a snapshot; with fix(server): return the interrupted state from a blocking SendMessage #1315, a busy event bus can add up toconsumptionCompletionTimeoutSecondsto that response and log a warning.MainQueueand in the handler); fix(server): wait for in-flight events before reading the task in blocking sendMessage #1314 logs one DEBUG line.On balance #1314 looks a little safer to merge (no new abstract method, no extra wait while the agent is still running), and #1315's terminal-state test is worth carrying over.
fix(server): return the interrupted state from a blocking SendMessage (…