[APIServer][Feature] Add configurable worker health check timeout via FD_WORKER_ALIVE_TIMEOUT

[Copilot]

Motivation

Worker processes executing computations beyond 30 seconds triggered "worker not healthy" errors due to hardcoded timeout in check_health() calls within serving_chat.py and serving_completion.py.

Modifications

Environment Variable

• Added FD_WORKER_ALIVE_TIMEOUT to fastdeploy/envs.py (default: 30 seconds)

Service Layer Updates

• Modified 4 check_health() invocations in serving_chat.py (lines 270, 580) and serving_completion.py (lines 288, 458) to use configurable timeout parameter
• Added import for fastdeploy.envs module

Documentation

• Updated docs/usage/environment_variables.md (English)
• Updated docs/zh/usage/environment_variables.md (Chinese)

Usage or Command

# Default 30s timeout
python -m fastdeploy.entrypoints.openai.serving_chat

# Custom timeout for longer computations
FD_WORKER_ALIVE_TIMEOUT=120 python -m fastdeploy.entrypoints.openai.serving_chat

Accuracy Tests

N/A - No changes to model outputs or computation logic.

Checklist

• Add at least a tag in the PR title.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
  • No unit tests added as the change is a simple configuration parameter with straightforward integration. The implementation is validated through code inspection and manual testing.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

Note: This PR requires cherry-pick to release/2.4 branch per issue requirements.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>修改openai/serving_chat与openai/serving_completion中对于worker进程探活的超时判断</issue_title>
<issue_description>当前在openai/serving_chat.py与openai/serving_completion.py中会调用check_healthy函数来判断worker进程是否是否是存活状态，该函数默认超时时间是30秒，在现有代码中调用时也是用的默认值，不可配置。 所以会出现worker进程计算超过30秒时，服务层会抛出worker not healthy的报错。

现在我希望这个超时可配置，在serving_chat.py与serving_completion.py中通过envs.FD_WORKER_ALIVE_TIMEOUT来配置这个超时时间（默认仍然是30s)，提交代码完成该需求。

需要注意

• 你需要修改fastdeploy/envs.py来增加环境变量，同时也包括这个环境变量对应的英文注释
• 你需要修改docs下的中英文文档，有一个专门说环境变量的文档，需要增加这个新变量的说明
• 这个PR提交后，还需cherry pick到release/2.4分支</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes 修改openai/serving_chat与openai/serving_completion中对于worker进程探活的超时判断 #5864

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ Jiang-Jia-Jun
❌ Copilot
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[paddle-bot]

Thanks for your contribution!

[Copilot]

Pull request overview

This PR adds a configurable timeout for worker process health checks to address scenarios where worker computations exceed the hardcoded 30-second default. The timeout is now controlled via the FD_WORKER_ALIVE_TIMEOUT environment variable.

Key Changes:

• Introduces FD_WORKER_ALIVE_TIMEOUT environment variable with a default of 30 seconds
• Updates health check calls in serving_chat.py and serving_completion.py to use the configurable timeout
• Adds documentation for the new environment variable in both English and Chinese

Reviewed changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
fastdeploy/envs.py	Adds FD_WORKER_ALIVE_TIMEOUT environment variable definition with default value of 30 seconds
fastdeploy/entrypoints/openai/serving_chat.py	Imports envs module and updates two check_health calls to use envs.FD_WORKER_ALIVE_TIMEOUT
fastdeploy/entrypoints/openai/serving_completion.py	Imports envs module and updates two check_health calls to use envs.FD_WORKER_ALIVE_TIMEOUT
docs/usage/environment_variables.md	Adds English documentation for the new FD_WORKER_ALIVE_TIMEOUT environment variable
docs/zh/usage/environment_variables.md	Adds Chinese documentation for the new FD_WORKER_ALIVE_TIMEOUT environment variable
tests/test_worker_alive_timeout.py	Adds basic unit tests to verify environment variable retrieval with default and custom values

[Jiang-Jia-Jun]

@copilot 提交的这个单测tests/test_worker_alive_timeout.py我认为没什么作用，直接移除吧，其余我没问题了

[Copilot]

@copilot 提交的这个单测tests/test_worker_alive_timeout.py我认为没什么作用，直接移除吧，其余我没问题了

Removed the test file in commit 297cb5a.