`FMComposedPrompt` still leaked by `stream_response()` and `SystemLanguageModel.token_count()` (follow-up to #17 / #18)
还没有人认领这个 Issue。
评估
调研方向
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.
由索引模型根据 Issue 内容生成。
描述
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.
- 主要语言
- Python
- 星标
- 1.4k
- 派生
- 95
- 平均合并
- 1 分钟
- 30 天内合并 PR
- 1
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
apple/python-apple-fm-sdk 的其他 Issue
-
难度 1/5 1 小时以内 新手友好度 90/100
apple/python-apple-fm-sdk#16 ·
-
Build fails with Command Line Tools only — Xcode.app should not be required可能已有人在做 @siva-acv 于 255 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 72/100
apple/python-apple-fm-sdk#6 · 2 条评论 · 3 个 reaction ·
-
难度 4/5 3-5 天 新手友好度 28/100
apple/python-apple-fm-sdk#21 · 1 条评论 ·
-
Add support for `LanguageModelFeedback` and `logFeedbackAttachment`可能重新可做 @mkery 于 256 天前认领,目前没有进行中的 PR。 未关闭
apple/python-apple-fm-sdk#5 · 1 条评论 · 已指派 1 人 ·
查看 apple/python-apple-fm-sdk 的全部 Issue
相似的 Issue
-
bug triage
难度 2/5 1-3 小时 新手友好度 78/100
ultralytics/ultralytics#27258 ·
维护者通常 1 天内回复
-
author-page correction move-papers
难度 2/5 1-3 小时 新手友好度 72/100
acl-org/acl-anthology#10969 · 1 条评论 ·
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 86/100
维护者通常 1 天内回复
-
Pin Python to 3.14 in the era5grib-parallel environment specification可能已有人在做 @atteggiani 今天认领。 未关闭
难度 1/5 1 小时以内 新手友好度 85/100
ACCESS-NRI/containerised-environments-infra#129 ·
维护者通常 2 天内回复
-
priority middle
难度 1/5 1 小时以内 新手友好度 72/100
KATO-Hiro/AtCoderClans#13029 ·
维护者通常 1 天内回复