Hacktoberfest 2026: as issues que os mantenedores marcaram para outubro, abertas e boas para iniciantes. Ver issues do Hacktoberfest

[core] Client disconnects don't cancel the model stream (per-step flow is cached) — and there is no public API to cancel an in-flight run

Aberta
  • Algo errado?
#1,618 6 comentários 0 reações 1 responsável Ver no GitHub

Mantenedores costumam responder em até 2 dias

@hemasekhar-p já está trabalhando nisso.

Desde 6/10/2026.

  • #1621 de @sangkyoonnam — aberto

Avaliação

Esta issue ainda não foi avaliada.

Descrição

needs review
Describe the Bug

When a client disconnects while an agent is streaming (e.g. the SSE consumer cancels its subscription to Runner's event flow), the underlying model call keeps running to completion. Tokens continue to be billed with no consumer attached. In one production incident the model kept generating for 3+ minutes after the client went away (observed via gateway-side logs and token metering).

The cause appears to be BaseLlmFlow.java line 530 (main at the time of writing):

Flowable<Event> currentStepEvents = runOneStep(spanContext, invocationContext).cache();

With RxJava cache(), the upstream connection is only disposed when all subscribers of the cached flow cancel. As long as any subscriber attached by the framework itself (event handling/aggregation within the invocation) is alive, a user-side cancellation cannot reach the model stream.

On top of that, there is no public API to cancel an in-flight run: neither Runner nor InvocationContext nor the session exposes a "stop generating" handle. The only way to stop a long generation is to let it finish.

To Reproduce
  1. Serve an agent behind SSE; start a streaming run with a slow/long model response (or a multi-round tool loop).
  2. Disconnect the SSE client mid-generation and dispose the event-flow subscription.
  3. Observe on the model/gateway side (or via token metering) that generation continues until the model finishes naturally.
Expected behavior

Cancelling the downstream subscription (or any public cancellation entry point) must reach the model stream: the in-flight LLM request is disposed (or aborted at the next chunk/round boundary), and no further rounds are started.

Environment
  • google/adk-java main (1.11.1-SNAPSHOT at the time of writing)
  • Spring AI bridge + SSE transport, but the cache() behavior is in core (BaseLlmFlow) and should affect any transport
Additional context

In production we could only implement "stop generating" with a cooperative cancellation protocol outside the framework: a per-run cancel flag (REST endpoint sets it) that the model-stream loop checks at every chunk and at tool-round boundaries, plus setCancellable hooks for the current round. It works, but it is entirely application-side — the framework neither propagates the cancellation nor offers a canonical way to express it.

Suggested directions (happy to discuss or contribute):

  1. Replace the unbounded cache() with cancellation-propagating semantics (e.g. publish().refCount()-style sharing, or a scoped subscription that disposes the source when the invocation ends/cancels), or
  2. Expose a first-class cancellation handle per run/invocation, and document that model loops should check it at chunk/round boundaries (cooperative cancellation), or
  3. At minimum, document the current behavior prominently — today it silently leaks billable model calls.
Linguagem predominante
Java
Estrelas
1.8k
Forks
446
Merge médio
5d 3h
PRs com merge (30d)
68

Preparar o ambiente

Abrir no Codespaces

Inicia o contêiner de desenvolvimento do projeto no navegador, com a sua própria conta do GitHub.

Primeiros passos

  1. Leia a issue inteira e depois o guia de contribuição do projeto.
  2. Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
  3. Faça um fork do repositório e trabalhe em uma branch.
  4. Abra um pull request que referencie o número da issue.

Mais de google/adk-java

Todas as issues de google/adk-java

Issues semelhantes

Mais issues de Java

Receba novas issues na sua caixa de entrada

Um resumo curto de issues do GitHub para quem está começando.