`FMComposedPrompt` still leaked by `stream_response()` and `SystemLanguageModel.token_count()` (follow-up to #17 / #18)

未关闭
#23 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
35/100
Issue 类型
缺陷
描述清晰度
描述清楚
活跃度
活跃
技术栈
python
领域
backend

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:

  1. 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#L833
  2. SystemLanguageModel.token_count(), in the prompt branch:
    https://github.com/apple/python-apple-fm-sdk/blob/0918b60/src/apple_fm_sdk/core.py#L440
  3. _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 existing finally block, next to the stream pointer. PromptError then
    reaches the caller.
  • token_count(): release the composed prompt in a finally around _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

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 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

查看 apple/python-apple-fm-sdk 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。