`FMComposedPrompt` still leaked by `stream_response()` and `SystemLanguageModel.token_count()` (follow-up to #17 / #18)
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 4/5
- Tiempo estimado
- 3-5 días
- Aptitud para principiantes
- 35/100
Línea de trabajo
Read src/apple_fm_sdk/session.py at _stream_response_basic(), src/apple_fm_sdk/core.py at SystemLanguageModel.token_count(), and src/apple_fm_sdk/prompt.py at _composed_prompt_from_prompt(). Then inspect tests/test_composed_prompt_cleanup.py and its fake native bindings. Done means the composed prompt is released on success, error, cancellation, and rejected components, and invalid streaming prompts raise to the caller.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Description
#18 releases the native composed prompt in the three respond() paths. Three other places that
build one with _composed_prompt_from_prompt() still never release it:
LanguageModelSession._stream_response_basic(), which builds the prompt inside the stream thread:
https://github.com/apple/python-apple-fm-sdk/blob/0918b60/src/apple_fm_sdk/session.py#L833SystemLanguageModel.token_count(), in the prompt branch:
https://github.com/apple/python-apple-fm-sdk/blob/0918b60/src/apple_fm_sdk/core.py#L440_composed_prompt_from_prompt()itself, when a component is rejected (PromptError,
ImagePromptError): the pointer is created first and never returned to the caller:
https://github.com/apple/python-apple-fm-sdk/blob/0918b60/src/apple_fm_sdk/prompt.py#L300-L319
Each call leaks one ComposedPrompt. With an ImageAttachment it also keeps one file descriptor
open, which is the symptom from #17.
A related effect of (1): because the prompt is built in the stream thread, an invalid prompt
raises there and the exception is lost. stream_response() then waits indefinitely and
asyncio.wait_for() cannot interrupt it:
Exception in thread Thread-1 (_start_stream):
apple_fm_sdk.prompt.PromptError: Unsupported prompt component type <class 'int'>, ...
(still waiting after 10 s, despite asyncio.wait_for(..., 3))
Reproduction
import asyncio, gc, os, tempfile
from pathlib import Path
from PIL import Image
import apple_fm_sdk as fm
def open_fds(): return len(os.listdir("/dev/fd"))
async def main():
img = Path(tempfile.mkdtemp()) / "leak.png"
Image.new("RGB", (32, 32), "white").save(img)
for _ in range(2): # warm-up, then measure
before = open_fds()
for _ in range(15):
async for _ in fm.LanguageModelSession().stream_response(["Reply with OK.", fm.ImageAttachment(img)]):
pass
gc.collect()
print(f"stream_response: open fds {before} -> {open_fds()}")
asyncio.run(main())
Results with 15 calls, after warm-up (macOS 27.2.1, M1, Python 3.14.6):
main @ 0918b60 |
with the fix below | |
|---|---|---|
respond() with image (fixed in #18) |
fds 7 → 7 | fds 7 → 7 |
stream_response() with image |
+15 fds per 15 calls (the snippet prints 22 -> 37; the warm-up round already leaked 15) |
+0 (7 -> 7) |
token_count() with a 200 KB prompt, 60 calls |
RSS +12.7 MB | RSS +1.6 MB |
stream_response(123) |
hangs | raises PromptError immediately |
Proposed fix
Same approach as #18:
_stream_response_basic(): build the composed prompt before starting the stream thread, and
release it in the existingfinallyblock, next to the stream pointer.PromptErrorthen
reaches the caller.token_count(): release the composed prompt in afinallyaround_token_count()._composed_prompt_from_prompt(): release the pointer before re-raising when a component is
rejected.
FMLanguageModelSessionStreamResponse and FMSystemLanguageModelTokenCountForPrompt read
.promptRepresentation synchronously, so releasing afterwards is safe.
The patch extends tests/test_composed_prompt_cleanup.py in the same style as #18 (faked native
bindings, no model needed). It adds 8 tests: success, error and early exit for streaming, the
invalid-prompt case, success, error and cancellation for token_count, and the rejected
component. All 8 fail on main (0918b60) and pass with the fix. The existing 12 tests are
unchanged and still pass. With the on-device model, test_streaming.py, test_token_count.py,
test_prompts.py, test_image_prompts.py, test_session.py and test_respond_options.py also pass
on the branch.
Branch with the fix and tests:
https://github.com/apple/python-apple-fm-sdk/compare/main...luiacuaniello:python-apple-fm-sdk:fix/composed-prompt-leak-stream-token-count
Note: PyPI still serves 0.2.1, which predates #18, so respond() leaks too for anyone who
installs from PyPI.
- Lenguaje dominante
- Python
- Estrellas
- 1.4k
- Forks
- 95
- Merge medio
- 1 min
- PR fusionados (30 d)
- 1
Preparar el entorno
Este proyecto no incluye contenedor de desarrollo, Dockerfile ni guía de contribución, así que la configuración corre por tu cuenta: empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.
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 apple/python-apple-fm-sdk
-
Dificultad 1/5 Menos de una hora Aptitud para principiantes 90/100
apple/python-apple-fm-sdk#16 ·
-
Build fails with Command Line Tools only — Xcode.app should not be requiredPosiblemente ocupada @siva-acv la tomó hace 255 días. Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
apple/python-apple-fm-sdk#6 · 2 comentarios · 3 reacciones ·
-
Dificultad 4/5 3-5 días Aptitud para principiantes 28/100
apple/python-apple-fm-sdk#21 · 1 comentario ·
-
Add support for `LanguageModelFeedback` and `logFeedbackAttachment`Quizá libre de nuevo @mkery la tomó hace 256 días y no hay ningún pull request abierto. Abierto
apple/python-apple-fm-sdk#5 · 1 comentario · 1 asignado ·
Todos los issues de apple/python-apple-fm-sdk
Issues similares
-
bug triage
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
ultralytics/ultralytics#27258 ·
Los mantenedores suelen responder en 1 día
-
author-page correction move-papers
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
acl-org/acl-anthology#10969 · 1 comentario ·
Los mantenedores suelen responder en 1 día
-
Dificultad 1/5 Menos de una hora Aptitud para principiantes 86/100
Los mantenedores suelen responder en 1 día
-
Pin Python to 3.14 in the era5grib-parallel environment specificationPosiblemente ocupada @atteggiani la tomó hoy. Abierto
Dificultad 1/5 Menos de una hora Aptitud para principiantes 85/100
ACCESS-NRI/containerised-environments-infra#129 ·
Los mantenedores suelen responder en 2 días
-
priority middle
Dificultad 1/5 Menos de una hora Aptitud para principiantes 72/100
KATO-Hiro/AtCoderClans#13029 ·
Los mantenedores suelen responder en 1 día