langgenius/dify-official-plugins
1
0
Fork 0
mirror of https://github.com/langgenius/dify-official-plugins.git synced 2026-07-22 10:05:23 -04:00
Code Issues 54 Packages Projects Releases Wiki Activity

Plugin updates frequently fail. #811

New Issue
Closed
opened 2026-02-16 10:20:35 -05:00 by yindo · 5 comments
yindo commented 2026-02-16 10:20:35 -05:00
Owner
Copy Link
Copy Source

Originally created by @Moiyu1998 on GitHub (Nov 18, 2025).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues Dify issues & Dify Official Plugins, 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.

Dify version

1.9.0

Plugin version

0.2.7

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

We frequently encounter the following issues when updating plugins. Could you please advise on how to resolve this?

✔️ Error log

plugin_daemon-1 | 2025/11/18 08:15:50 full_duplex.go:65: [ERROR]init environment failed: failed to install dependencies: exit status 1, output: Resolved 44 packages in 20ms
plugin_daemon-1 | Downloading numpy (17.1MiB)
plugin_daemon-1 | × Failed to download numpy==1.26.4
plugin_daemon-1 | ├─▶ Failed to extract archive:
plugin_daemon-1 | │ numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
plugin_daemon-1 | ├─▶ I/O operation failed during extraction
plugin_daemon-1 | ╰─▶ Failed to download distribution due to network timeout. Try increasing
plugin_daemon-1 | UV_HTTP_TIMEOUT (current value: 30s).
plugin_daemon-1 | , retrying
plugin_daemon-1 | 2025/11/18 08:15:50 full_duplex.go:59: [INFO]init environment for plugin langgenius/openai:0.2.7

Originally created by @Moiyu1998 on GitHub (Nov 18, 2025). ### Self Checks - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [Dify issues](https://github.com/langgenius/dify/issues) & [Dify Official Plugins](https://github.com/langgenius/dify-official-plugins/issues), including closed ones. - [x] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:） - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 1.9.0 ### Plugin version 0.2.7 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce We frequently encounter the following issues when updating plugins. Could you please advise on how to resolve this? ### ✔️ Error log plugin_daemon-1 | 2025/11/18 08:15:50 full_duplex.go:65: [ERROR]init environment failed: failed to install dependencies: exit status 1, output: Resolved 44 packages in 20ms plugin_daemon-1 | Downloading numpy (17.1MiB) plugin_daemon-1 | × Failed to download `numpy==1.26.4` plugin_daemon-1 | ├─▶ Failed to extract archive: plugin_daemon-1 | │ numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl plugin_daemon-1 | ├─▶ I/O operation failed during extraction plugin_daemon-1 | ╰─▶ Failed to download distribution due to network timeout. Try increasing plugin_daemon-1 | UV_HTTP_TIMEOUT (current value: 30s). plugin_daemon-1 | , retrying plugin_daemon-1 | 2025/11/18 08:15:50 full_duplex.go:59: [INFO]init environment for plugin langgenius/openai:0.2.7
yindo added the bug label 2026-02-16 10:20:35 -05:00
yindo closed this issue 2026-02-16 10:20:35 -05:00
yindo commented 2026-02-16 10:20:35 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Nov 18, 2025):

Frequent plugin update failures during dependency installation (especially with numpy) in Dify self-hosted via Docker are usually caused by network timeouts or slow connectivity to PyPI. Here are the most effective solutions reported by other users and maintainers:

  • Set a PyPI mirror for faster and more reliable downloads by adding PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple to your plugin_daemon environment or .env file. This is especially helpful if you are in mainland China or have slow access to pypi.org.
  • Increase the timeout for dependency installation by setting PYTHON_ENV_INIT_TIMEOUT (e.g., 320 or higher) in your docker-compose.yaml under the plugin_daemon service.
  • Raise the UV_HTTP_TIMEOUT environment variable (try 120s or more) to give pip more time to download large packages like numpy.
  • If your Docker host or VM uses a lower MTU (e.g., 1450), adjust Docker's MTU settings to match. Add {"mtu": 1450} to /etc/docker/daemon.json and set the network MTU in your docker-compose.yaml: 
    networks:
  default:
    driver_opts:
      com.docker.network.driver.mtu: 1450
    Then restart Docker and your containers.
  • For persistent network issues, consider using network_mode: host for the plugin_daemon service in Docker to improve connectivity.
  • After making these changes, restart the plugin_daemon container for the settings to take effect.

These steps have resolved similar issues for other users (example 1, example 2). If you still encounter failures, check your Docker resource limits (CPU/memory), clean the pip cache, and verify your network/firewall settings.

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Join Discord Share on X

@dosubot[bot] commented on GitHub (Nov 18, 2025): <!-- Answer --> Frequent plugin update failures during dependency installation (especially with numpy) in Dify self-hosted via Docker are usually caused by network timeouts or slow connectivity to PyPI. Here are the most effective solutions reported by other users and maintainers: - Set a PyPI mirror for faster and more reliable downloads by adding `PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple` to your plugin_daemon environment or `.env` file. This is especially helpful if you are in mainland China or have slow access to pypi.org. - Increase the timeout for dependency installation by setting `PYTHON_ENV_INIT_TIMEOUT` (e.g., `320` or higher) in your `docker-compose.yaml` under the `plugin_daemon` service. - Raise the `UV_HTTP_TIMEOUT` environment variable (try `120s` or more) to give pip more time to download large packages like numpy. - If your Docker host or VM uses a lower MTU (e.g., 1450), adjust Docker's MTU settings to match. Add `{"mtu": 1450}` to `/etc/docker/daemon.json` and set the network MTU in your `docker-compose.yaml`: ```yaml networks: default: driver_opts: com.docker.network.driver.mtu: 1450 ``` Then restart Docker and your containers. - For persistent network issues, consider using `network_mode: host` for the plugin_daemon service in Docker to improve connectivity. - After making these changes, restart the plugin_daemon container for the settings to take effect. These steps have resolved similar issues for other users ([example 1](https://github.com/langgenius/dify/issues/25667#issuecomment-3289312335), [example 2](https://github.com/langgenius/dify/issues/19571)). If you still encounter failures, check your Docker resource limits (CPU/memory), clean the pip cache, and verify your network/firewall settings. <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/a438203c-8dcd-4414-bf42-63d6d64ac2d8?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/a438203c-8dcd-4414-bf42-63d6d64ac2d8?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/a438203c-8dcd-4414-bf42-63d6d64ac2d8?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/a438203c-8dcd-4414-bf42-63d6d64ac2d8?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/a438203c-8dcd-4414-bf42-63d6d64ac2d8?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/a438203c-8dcd-4414-bf42-63d6d64ac2d8?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/a438203c-8dcd-4414-bf42-63d6d64ac2d8?feedback_type=other)</sup>&nbsp;&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/2086)
yindo commented 2026-02-16 10:20:35 -05:00
Author
Owner
Copy Link
Copy Source

@Moiyu1998 commented on GitHub (Nov 18, 2025):

Where can I find the UV_HTTP_TIMEOUT parameter? It doesn't appear to be in the environment variables.

@Moiyu1998 commented on GitHub (Nov 18, 2025): Where can I find the UV_HTTP_TIMEOUT parameter? It doesn't appear to be in the environment variables.
yindo commented 2026-02-16 10:20:35 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Nov 18, 2025):

UV_HTTP_TIMEOUT is not present by default in the environment variables for the plugin_daemon container—you need to add it manually. To do this, add a line like UV_HTTP_TIMEOUT=120s (or your preferred value) to the environment section of your plugin_daemon service in docker-compose.yaml, or to your .env file if you use one. Then restart the plugin_daemon container for the change to take effect. This variable controls the HTTP timeout for dependency downloads during plugin initialization and is referenced in error logs, but it won't appear unless you explicitly set it yourself. For reference, see the environment variable setup in the Dify docker-compose.yaml file and related discussions about increasing this timeout to resolve network issues during plugin updates (example).

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Join Discord Share on X

@dosubot[bot] commented on GitHub (Nov 18, 2025): <!-- Answer --> UV_HTTP_TIMEOUT is not present by default in the environment variables for the plugin_daemon container—you need to add it manually. To do this, add a line like UV_HTTP_TIMEOUT=120s (or your preferred value) to the environment section of your plugin_daemon service in docker-compose.yaml, or to your .env file if you use one. Then restart the plugin_daemon container for the change to take effect. This variable controls the HTTP timeout for dependency downloads during plugin initialization and is referenced in error logs, but it won't appear unless you explicitly set it yourself. For reference, see the environment variable setup in the Dify docker-compose.yaml file and related discussions about increasing this timeout to resolve network issues during plugin updates [(example)](https://github.com/langgenius/dify/issues/25667). <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/5dd97d32-4778-4037-ad99-2652f7eea3d1?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/5dd97d32-4778-4037-ad99-2652f7eea3d1?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/5dd97d32-4778-4037-ad99-2652f7eea3d1?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/5dd97d32-4778-4037-ad99-2652f7eea3d1?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/5dd97d32-4778-4037-ad99-2652f7eea3d1?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/5dd97d32-4778-4037-ad99-2652f7eea3d1?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/5dd97d32-4778-4037-ad99-2652f7eea3d1?feedback_type=other)</sup>&nbsp;&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/2086)
yindo commented 2026-02-16 10:20:35 -05:00
Author
Owner
Copy Link
Copy Source

@nadazero commented on GitHub (Nov 20, 2025):

@Moiyu1998 别听AI在上面胡说，改timeout有屁用。
本质就是国内服务器连pip太慢了导致超时， .env文件中把这行放开(本质就是换国内源)就可以了

PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple

@nadazero commented on GitHub (Nov 20, 2025): @Moiyu1998 别听AI在上面胡说，改timeout有屁用。 本质就是国内服务器连pip太慢了导致超时， .env文件中把这行放开(本质就是换国内源)就可以了 # PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple
yindo commented 2026-02-16 10:20:35 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Dec 6, 2025):

Hi, @Moiyu1998. I'm Dosu, and I'm helping the dify-official-plugins team manage their backlog and am marking this issue as stale.

Issue Summary:

  • You experienced frequent plugin update failures on Dify 1.9.0 with plugin version 0.2.7 due to network timeouts downloading numpy in a self-hosted Docker setup.
  • Suggestions included setting a PyPI mirror (like Tsinghua), increasing UV_HTTP_TIMEOUT and PYTHON_ENV_INIT_TIMEOUT, adjusting Docker MTU, and using network_mode: host.
  • You asked where to set UV_HTTP_TIMEOUT; it was clarified it must be manually added to plugin_daemon environment variables.
  • Another user recommended enabling a domestic PyPI mirror in the .env file as increasing timeouts alone was ineffective.
  • The issue was resolved by enabling a domestic PyPI mirror to speed up pip downloads.

Next Steps:

  • Please confirm if this issue remains relevant with the latest version of dify-official-plugins.
  • If it is still a problem, feel free to comment to keep the discussion open; otherwise, I will automatically close this issue in 5 days.

Thank you for your understanding and contribution!

@dosubot[bot] commented on GitHub (Dec 6, 2025): Hi, @Moiyu1998. I'm [Dosu](https://dosu.dev), and I'm helping the dify-official-plugins team manage their backlog and am marking this issue as stale. **Issue Summary:** - You experienced frequent plugin update failures on Dify 1.9.0 with plugin version 0.2.7 due to network timeouts downloading numpy in a self-hosted Docker setup. - Suggestions included setting a PyPI mirror (like Tsinghua), increasing UV_HTTP_TIMEOUT and PYTHON_ENV_INIT_TIMEOUT, adjusting Docker MTU, and using network_mode: host. - You asked where to set UV_HTTP_TIMEOUT; it was clarified it must be manually added to plugin_daemon environment variables. - Another user recommended enabling a domestic PyPI mirror in the .env file as increasing timeouts alone was ineffective. - The issue was resolved by enabling a domestic PyPI mirror to speed up pip downloads. **Next Steps:** - Please confirm if this issue remains relevant with the latest version of dify-official-plugins. - If it is still a problem, feel free to comment to keep the discussion open; otherwise, I will automatically close this issue in 5 days. Thank you for your understanding and contribution!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
bug
bug
dependencies
documentation
enhancement
good first issue
invalid
pull-request
Mirrored from GitHub Pull Request
 question
stale
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify-official-plugins#811
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?