old plugin still run, not exit

[fatelei]

Self Checks

To make sure we get to you in time, please check the following :)

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)
• "Please do not modify this template :) and fill in all the required fields."

Versions

1. dify-plugin-daemon Version
2. dify-api Version

Describe the bug

📊 进程分析结果
容器内共 219 个 Python 插件进程，大量插件的多个历史版本同时在跑：
插件运行版本数
langgenius/tongyi15 个版本
langgenius/anthropic14 个版本
langgenius/agent13 个版本
langgenius/openai11 个版本
langgenius/jina8 个版本
langgenius/deepseek8 个版本
......
以 jina 为例，0.0.4 / 0.0.5 / 0.0.6 / 0.0.8 / 0.0.11 / 0.0.12 全都还活着，每次升级都没有杀掉旧版本进程。

To Reproduce
Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Expected behavior
A clear and concise description of what you expected to happen.

Screenshots
If applicable, add screenshots to help explain your problem.

Additional context
Add any other context about the problem here.

[dosubot]

This is a documented issue with the plugin daemon's lifecycle management. There are actually two related problems at play:

1. Zombie process accumulation — This was fixed in v0.5.2 (PR #544). The root cause was that cmd.Process.Wait() was never called after killing plugin subprocesses, so child processes were never properly reaped [1].

2. Old plugin versions continuing to run after upgrades — This is the more complex issue you're hitting. During an upgrade, RemovePluginIfNeeded is supposed to shut down the old version, but it only runs when the plugin's reference count reaches zero [2]. In multi-tenant setups where multiple tenants share the same plugin, the reference count stays positive and cleanup is skipped entirely. On top of that, the daemon's watchdog rescans plugin storage every 30 seconds [3] and relaunches any plugin it finds there — so even if a process is killed, it gets restarted if the old files remain on disk.

Several users have reported the same behavior [4] [5].

Workaround: A cleanup command has been added to the main branch [6]:

go run ./cmd/commandline plugin cleanup -p ./cwd -y
# or preview first with:
go run ./cmd/commandline plugin cleanup -p ./cwd --dry-run

This scans plugin working directories and removes all but the latest version of each plugin [7]. After running the cleanup, restart the daemon container to clear the accumulated processes.

For manual cleanup, you'd need to remove old entries from both the database tables (plugin_installations, plugin_declarations, plugins) and the storage directories (plugin, plugin-working, persistence, plugin-root under /app/storage/cwd/plugins/) [4].

To reply, just mention @dosu.

---

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}