`FMComposedPrompt` still leaked by `stream_response()` and `SystemLanguageModel.token_count()` (follow-up to #17 / #18)
Ninguém assumiu esta issue ainda.
Avaliação
- Dificuldade
- 4/5
- Tempo estimado
- 3-5 dias
- Facilidade para iniciantes
- 35/100
Direção de pesquisa
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.
Escrita pelo modelo de indexação a partir do texto da issue.
Descrição
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.
- Linguagem predominante
- Python
- Estrelas
- 1.4k
- Forks
- 95
- Merge médio
- 1min
- PRs com merge (30d)
- 1
Preparar o ambiente
Este projeto não oferece contêiner de desenvolvimento, Dockerfile nem guia de contribuição, então a configuração fica por sua conta: comece pelo README e veja nosso guia da primeira contribuição para os passos gerais.
Primeiros passos
- Leia a issue inteira e depois o guia de contribuição do projeto.
- Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
- Faça um fork do repositório e trabalhe em uma branch.
- Abra um pull request que referencie o número da issue.
Mais de apple/python-apple-fm-sdk
-
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 90/100
apple/python-apple-fm-sdk#16 ·
-
Build fails with Command Line Tools only — Xcode.app should not be requiredTalvez já em andamento @siva-acv assumiu há 255 dias. Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 72/100
apple/python-apple-fm-sdk#6 · 2 comentários · 3 reações ·
-
Dificuldade 4/5 3-5 dias Facilidade para iniciantes 28/100
apple/python-apple-fm-sdk#21 · 1 comentário ·
-
Add support for `LanguageModelFeedback` and `logFeedbackAttachment`Talvez livre de novo @mkery assumiu há 256 dias e não há nenhum pull request aberto. Aberta
apple/python-apple-fm-sdk#5 · 1 comentário · 1 responsável ·
Todas as issues de apple/python-apple-fm-sdk
Issues semelhantes
-
bug triage
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 78/100
ultralytics/ultralytics#27258 ·
Mantenedores costumam responder em até 1 dia
-
author-page correction move-papers
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 72/100
acl-org/acl-anthology#10969 · 1 comentário ·
Mantenedores costumam responder em até 1 dia
-
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 86/100
Mantenedores costumam responder em até 1 dia
-
Pin Python to 3.14 in the era5grib-parallel environment specificationTalvez já em andamento @atteggiani assumiu hoje. Aberta
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 85/100
ACCESS-NRI/containerised-environments-infra#129 ·
Mantenedores costumam responder em até 2 dias
-
priority middle
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 72/100
KATO-Hiro/AtCoderClans#13029 ·
Mantenedores costumam responder em até 1 dia