No heartbeat event during LLM-streamed tool-argument construction; watchdogs can't distinguish working from hung
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 4/5
- Tiempo estimado
- 3-5 días
- Aptitud para principiantes
- 52/100
- Tipo de issue
- Nueva funcionalidad
- Claridad
- Bastante claro
- Estado de actividad
- Tranquilo
- Stack tecnológico
- node.js, typescript
- Área
- api
Línea de trabajo
Comienza con nodejs/src/generated/session-events.ts y las definiciones de eventos assistant.streaming_delta, tool.execution_start y tool.execution_complete. Verifica si streaming_delta se activa durante la construcción en curso de los argumentos de una herramienta; se considera terminado si se documenta ese comportamiento o se define y emite un evento de progreso acotado que permita a los consumidores distinguir el trabajo activo de un bloqueo.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Summary
When the model streams a large tool-call argument value (e.g., a 20KB file_text for create), the event stream is functionally silent for 10–30 minutes between tool.execution_start and tool.execution_complete. A stall watchdog watching the event stream cannot distinguish "model is productively building a large output" from "session has hung."
Repro
const session = await client.createSession({ /* ... */ });
session.on((evt) => console.log(evt.type, evt.data));
await session.sendAndWait({
prompt: "Create a file at ./report.json containing a JSON document " +
"with at least 20KB of structured analysis data. Use the create tool.",
});
Observe the event stream between tool.execution_start (with empty arguments) and tool.execution_complete (with the full argument). Empirically, no events fire for the duration of argument construction.
Expected
A heartbeat event during argument streaming — byte count, token count, or even a simple tool.argument_progress ping — so consumers can tell a working session from a hung one.
Actual
tool.execution_start fires once, then silence for the duration of LLM argument streaming, then tool.execution_complete fires once when the full tool invocation finishes (which includes both arg construction AND tool execution).
assistant.streaming_delta exists with cumulative byte counts (totalResponseSizeBytes) and fires during response streaming, but it has not been verified whether it continues to fire during the tool-argument construction phase. This would be useful to clarify: if streaming_delta does cover that phase, the gap is consumer-side documentation; if it doesn't, the gap is upstream.
Evidence (SDK source)
nodejs/src/generated/session-events.ts: the SessionEvent union includes:
assistant.streaming_delta(AssistantStreamingDeltaData.totalResponseSizeBytes) — described as "Streaming response progress with cumulative byte count"assistant.reasoning_delta,assistant.message_delta— response-sidetool.execution_progress,tool.execution_partial_result— fire AFTERexecution_startfor tools that emit stdout (bash,powershell)
There is no tool.argument_progress or equivalent event specifically scoped to in-flight tool-argument streaming.
Consumer impact
Consumers with long-running tool calls must either tune stall watchdogs to ceilings that mask real failures (15+ minutes) or route artifact completion through filesystem polling instead of session events.
Suggested fix
Either:
- Confirm + document that
assistant.streaming_deltacontinues firing during in-flight tool-argument construction. If so, this is a doc-only fix. - Emit a
tool.argument_progressevent during LLM-streamed argument construction carrying byte/token count or a small delta. Even one event every ~10 seconds would let consumers tell working sessions from hung ones.
Related
- #590 — "Long-running prompt suddenly hangs forever with no error or exception" — describes the user-visible symptom. The missing in-flight heartbeat is one root cause: consumers can't distinguish hang-in-progress from work-in-progress without it.
- #1273 —
session.disconnect()cooperative — the recovery path when this stall does happen is also broken; the two issues compound.
Environment
- SDK: @github/copilot-sdk@0.3.0
- CLI: @github/copilot@1.0.45
- Node: 22 LTS
- OS: Windows 11
- Model: claude-sonnet-4-6
- Lenguaje dominante
- Java
- Estrellas
- 10.5k
- Forks
- 1.5k
- Merge medio
- 1 d 9 h
- PR fusionados (30 d)
- 130
Guía de contribución
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Más de github/copilot-sdk
-
agentic-workflows
Dificultad 2/5 1-3 horas Aptitud para principiantes 65/100
github/copilot-sdk#2760 ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 65/100
github/copilot-sdk#2759 ·
-
documentation
Dificultad 1/5 Menos de una hora Aptitud para principiantes 85/100
github/copilot-sdk#2758 ·
-
agentic-workflows
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
github/copilot-sdk#2709 · 1 comentario ·
-
Dificultad 1/5 Menos de una hora Aptitud para principiantes 78/100
github/copilot-sdk#2673 ·
Todos los issues de github/copilot-sdk
Issues similares
-
executions.Query — startDate and timeRange filters are sent with inverted comparison operators Abiertoarea/plugin
Dificultad 2/5 1-3 horas Aptitud para principiantes 75/100
kestra-io/plugin-kestra#190 ·
-
litertlm-android AAR ships no consumer ProGuard rules → "mid == null" SIGABRT in minified apps Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 70/100
google-ai-edge/LiteRT-LM#3739 ·
-
bug
Dificultad 2/5 1-3 horas Aptitud para principiantes 75/100
-
Add canonical URLs and a sitemap Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 75/100
integra-team-red/meet-map#249 ·
-
[Studio][Bug] Cancelled create-user dialog keeps the password and admin switch for the next attempt Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 75/100
apache/rocketmq-dashboard#5064 ·