langgenius/dify-official-plugins
1
0
Fork 0
mirror of https://github.com/langgenius/dify-official-plugins.git synced 2026-07-21 17:45:23 -04:00
Code Issues 54 Packages Projects Releases Wiki Activity

Volcengine plugin error: token too long #256

New Issue
Closed
opened 2026-02-16 10:18:37 -05:00 by yindo · 14 comments
yindo commented 2026-02-16 10:18:37 -05:00
Owner
Copy Link
Copy Source

Originally created by @Nothing1024 on GitHub (May 7, 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 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.

Dify version

1.3.1

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

Request Configuration

  • model : doubao-1.5-vision-pro
  • api_url: offical
  • input params: one image(file id format) and some string params (for type selection)
  • output params: just text
  • method: workflow API request

The whole step flow is

  1. upload the file to dify and get the file id
  1. request the dify workflow API
  1. get the response

The whole step is automatic. Every epoch the step will request 3 times and wait for 2 seconds.

✔️ Expected Behavior

When I request the workflow API, it should give me the text result.

❌ Actual Behavior

But Sometimes the request will be error, the fetch response content is

TypeError: fetch failed
  1 |
  2 | export const DifyLLMRequest  = async (type: string, file_type: string, id: string)=>{
> 3 |   const response = await fetch("http://{dify-site}/v1/workflows/run", {
    |                   ^
  4 |     method: "POST",
  5 |     headers: {
  6 |       "Content-Type": "application/json", {
  [cause]: [Error [HeadersTimeoutError]: Headers Timeout Error] 
{
    code: 'UND_ERR_HEADERS_TIMEOUT'
  }
}

The dashboard show nothing, just the ”FAILED“ status task. When I try to find the logs, the error step just showed "running" status, no other outputs.

Then I try to get the docker logs (docker-plugin_daemon-1), I found that the plugin is always killed, so when it restart, the related request will be down.

Related logs

2025/05/07 07:05:37 stdio.go:166: [ERROR]plugin langgenius/volcengine_maas:0.0.13 has an error on stdout: bufio.Scanner: token too long
2025/05/07 07:05:37 run.go:132: [ERROR]plugin langgenius/volcengine_maas:0.0.13 exited with error: signal: killed

The token in token too long maybe not my prompt token, because I found various size image also have the same error.

Originally created by @Nothing1024 on GitHub (May 7, 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 [search for existing issues](https://github.com/langgenius/dify/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 1.3.1 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce ## Request Configuration - model : doubao-1.5-vision-pro - api_url: offical - input params: one image(file id format) and some string params (for type selection) - output params: just text - method: workflow API request ## The whole step flow is 1. upload the file to dify and get the file id - method: NextJS fetch method - request url : http://{dify-server}/v1/files/upload 2. request the dify workflow API - method: NextJS fetch method - request url: http://{dify-server}/v1/workflows/run - params: image_url (Dify's id splice) 3. get the response The whole step is automatic. Every epoch the step will request 3 times and wait for 2 seconds. ### ✔️ Expected Behavior When I request the workflow API, it should give me the text result. ### ❌ Actual Behavior But Sometimes the request will be error, the fetch response content is ``` TypeError: fetch failed 1 | 2 | export const DifyLLMRequest = async (type: string, file_type: string, id: string)=>{ > 3 | const response = await fetch("http://{dify-site}/v1/workflows/run", { | ^ 4 | method: "POST", 5 | headers: { 6 | "Content-Type": "application/json", { [cause]: [Error [HeadersTimeoutError]: Headers Timeout Error] { code: 'UND_ERR_HEADERS_TIMEOUT' } } ``` The dashboard show nothing, just the ”FAILED“ status task. When I try to find the logs, the error step just showed "running" status, no other outputs. Then I try to get the docker logs (`docker-plugin_daemon-1`), I found that the plugin is always killed, so when it restart, the related request will be down. Related logs ``` 2025/05/07 07:05:37 stdio.go:166: [ERROR]plugin langgenius/volcengine_maas:0.0.13 has an error on stdout: bufio.Scanner: token too long 2025/05/07 07:05:37 run.go:132: [ERROR]plugin langgenius/volcengine_maas:0.0.13 exited with error: signal: killed ``` The `token` in `token too long` maybe not my prompt token, because I found various size image also have the same error.
yindo added the good first issue label 2026-02-16 10:18:37 -05:00
yindo closed this issue 2026-02-16 10:18:37 -05:00
yindo commented 2026-02-16 10:18:37 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (May 7, 2025):

The "token too long" error you're encountering with the Volcengine plugin in Dify could be related to the handling of large data inputs, such as images, which are converted to base64 encoding. This can result in a token length that exceeds the limits set by the system. Here are some steps you can take to address this issue:

  1. Reduce Image Size: Try reducing the size of the images before uploading them to Dify. This can help prevent the base64 encoded data from exceeding the token limit.

  2. Check Token Limits: Ensure that the token limits for your model and API requests are configured correctly. Dify imposes a generation length limit of 2k tokens for reasoning models, which might be relevant if your workflow involves such models [1].

  3. Switch Model Provider: If you're using the openai_api_compatible provider, consider switching to a different model provider that might handle larger token sizes more effectively [2].

  4. Review Workflow Configuration: Double-check your workflow configuration to ensure that all parameters and settings are optimized for handling the data sizes you're working with.

By implementing these suggestions, you should be able to mitigate the "token too long" error and improve the stability of your plugin operations.

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other

@dosubot[bot] commented on GitHub (May 7, 2025): <!-- Answer --> The "token too long" error you're encountering with the Volcengine plugin in Dify could be related to the handling of large data inputs, such as images, which are converted to base64 encoding. This can result in a token length that exceeds the limits set by the system. Here are some steps you can take to address this issue: 1. **Reduce Image Size**: Try reducing the size of the images before uploading them to Dify. This can help prevent the base64 encoded data from exceeding the token limit. 2. **Check Token Limits**: Ensure that the token limits for your model and API requests are configured correctly. Dify imposes a generation length limit of 2k tokens for reasoning models, which might be relevant if your workflow involves such models <sup>[[1]](https://github.com/langgenius/dify/issues/17120)</sup>. 3. **Switch Model Provider**: If you're using the `openai_api_compatible` provider, consider switching to a different model provider that might handle larger token sizes more effectively <sup>[[2]](https://github.com/langgenius/dify/issues/18657)</sup>. 4. **Review Workflow Configuration**: Double-check your workflow configuration to ensure that all parameters and settings are optimized for handling the data sizes you're working with. By implementing these suggestions, you should be able to mitigate the "token too long" error and improve the stability of your plugin operations. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=other)</sup>
yindo commented 2026-02-16 10:18:37 -05:00
Author
Owner
Copy Link
Copy Source

@Nothing1024 commented on GitHub (May 7, 2025):

The "token too long" error you're encountering with the Volcengine plugin in Dify could be related to the handling of large data inputs, such as images, which are converted to base64 encoding. This can result in a token length that exceeds the limits set by the system. Here are some steps you can take to address this issue:您在使用 Dify 中的 Volcengine 插件时遇到的 "标记太长 "错误可能与处理大数据输入（如转换为 base64 编码的图像）有关。这可能导致标记长度超出系统设置的限制。以下是解决此问题的一些步骤：

  1. Reduce Image Size: Try reducing the size of the images before uploading them to Dify. This can help prevent the base64 encoded data from exceeding the token limit.**减小图片大小 **：在将图片上传到 Dify 之前，请尝试减小图片大小。这有助于防止 base64 编码数据超出令牌限制。
  2. Check Token Limits: Ensure that the token limits for your model and API requests are configured correctly. Dify imposes a generation length limit of 2k tokens for reasoning models, which might be relevant if your workflow involves such models [1].**检查令牌限制 **：确保正确配置模型和 API 请求的令牌限制。Dify 为推理模型规定了 2k 标记的生成长度限制，如果您的工作流涉及此类模型，则可能与此相关 [1] 。
  3. Switch Model Provider: If you're using the openai_api_compatible provider, consider switching to a different model provider that might handle larger token sizes more effectively [2].**切换模型提供程序 **：如果您正在使用 openai_api_compatible 提供程序，请考虑切换到不同的模型提供程序，这样可以更有效地处理更大的标记大小 [2] 。
  4. Review Workflow Configuration: Double-check your workflow configuration to ensure that all parameters and settings are optimized for handling the data sizes you're working with.**审查工作流程配置 **：仔细检查您的工作流程配置，确保所有参数和设置都经过优化，以处理您正在处理的数据大小。

By implementing these suggestions, you should be able to mitigate the "token too long" error and improve the stability of your plugin operations.通过实施这些建议，您应该可以减少 "标记太长 "错误，并提高插件运行的稳定性。

To continue talking to Dosu, mention @dosu.要继续与 Dosu 通话，请提及 。

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other帮助 Dosu 学习！给它反馈： 好回答 | 不相关的回答 | 来源不正确 | 太啰嗦 | 幻觉 | 错误报告 | 其他 。

Step 1 and Step 2 are tried to fix, but failed.
Step 3 is not fit, because I use the offical Volcengine plugin.
Step 4 is not clear.

@Nothing1024 commented on GitHub (May 7, 2025): > The "token too long" error you're encountering with the Volcengine plugin in Dify could be related to the handling of large data inputs, such as images, which are converted to base64 encoding. This can result in a token length that exceeds the limits set by the system. Here are some steps you can take to address this issue:您在使用 Dify 中的 Volcengine 插件时遇到的 "标记太长 "错误可能与处理大数据输入（如转换为 base64 编码的图像）有关。这可能导致标记长度超出系统设置的限制。以下是解决此问题的一些步骤： > > 1. **Reduce Image Size**: Try reducing the size of the images before uploading them to Dify. This can help prevent the base64 encoded data from exceeding the token limit.**减小图片大小 **：在将图片上传到 Dify 之前，请尝试减小图片大小。这有助于防止 base64 编码数据超出令牌限制。 > 2. **Check Token Limits**: Ensure that the token limits for your model and API requests are configured correctly. Dify imposes a generation length limit of 2k tokens for reasoning models, which might be relevant if your workflow involves such models [[1]](https://github.com/langgenius/dify/issues/17120).**检查令牌限制 **：确保正确配置模型和 API 请求的令牌限制。Dify 为推理模型规定了 2k 标记的生成长度限制，如果您的工作流涉及此类模型，则可能与此相关 [[1]](https://github.com/langgenius/dify/issues/17120) 。 > 3. **Switch Model Provider**: If you're using the `openai_api_compatible` provider, consider switching to a different model provider that might handle larger token sizes more effectively [[2]](https://github.com/langgenius/dify/issues/18657).**切换模型提供程序 **：如果您正在使用 `openai_api_compatible` 提供程序，请考虑切换到不同的模型提供程序，这样可以更有效地处理更大的标记大小 [[2]](https://github.com/langgenius/dify/issues/18657) 。 > 4. **Review Workflow Configuration**: Double-check your workflow configuration to ensure that all parameters and settings are optimized for handling the data sizes you're working with.**审查工作流程配置 **：仔细检查您的工作流程配置，确保所有参数和设置都经过优化，以处理您正在处理的数据大小。 > > By implementing these suggestions, you should be able to mitigate the "token too long" error and improve the stability of your plugin operations.通过实施这些建议，您应该可以减少 "标记太长 "错误，并提高插件运行的稳定性。 > > _To continue talking to [Dosu](https://dosu.dev), mention [@dosu](https://github.com/dosu).要继续与 [Dosu](https://dosu.dev) 通话，请提及 。_ > > Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=other)帮助 Dosu 学习！给它反馈：[ 好回答 ](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=great_response) | [ 不相关的回答 ](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=irrelevant_answer) | [ 来源不正确 ](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=incorrect_sources) | [ 太啰嗦 ](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=too_verbose) | [ 幻觉 ](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=hallucination) | [ 错误报告 ](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=bug_report) | [ 其他 ](https://app.dosu.dev/response-feedback/4394e3dc-f373-4604-9d72-99bdfe5b5874?feedback_type=other)。 Step 1 and Step 2 are tried to fix, but failed. Step 3 is not fit, because I use the offical Volcengine plugin. Step 4 is not clear.
yindo commented 2026-02-16 10:18:37 -05:00
Author
Owner
Copy Link
Copy Source

@DevilMayCrySamsara commented on GitHub (May 8, 2025):

same problem

@DevilMayCrySamsara commented on GitHub (May 8, 2025): same problem
yindo commented 2026-02-16 10:18:37 -05:00
Author
Owner
Copy Link
Copy Source

@764852987 commented on GitHub (May 19, 2025):

Unable to reproduce this issue with Dify online 1.4.0, doubao-1.5-vision-pro-250328
Try upgrading your local version of Dify

Image

Image

@764852987 commented on GitHub (May 19, 2025): Unable to reproduce this issue with Dify online 1.4.0, doubao-1.5-vision-pro-250328 Try upgrading your local version of Dify ![Image](https://github.com/user-attachments/assets/3c1e92c7-f54a-42db-aca3-0e7990a2e137) ![Image](https://github.com/user-attachments/assets/b155fbe1-b07c-4d5e-9d6c-1cfb31b01e2e)
yindo commented 2026-02-16 10:18:37 -05:00
Author
Owner
Copy Link
Copy Source

@AnoyiX commented on GitHub (May 20, 2025):

@764852987 你拿个大图片试试，超过 5MB 的

@AnoyiX commented on GitHub (May 20, 2025): @764852987 你拿个大图片试试，超过 5MB 的
yindo commented 2026-02-16 10:18:37 -05:00
Author
Owner
Copy Link
Copy Source

@Nothing1024 commented on GitHub (May 20, 2025):

Unable to reproduce this issue with Dify online 1.4.0, doubao-1.5-vision-pro-250328 Try upgrading your local version of Dify

Image

Image

目前的情况是，偶发性产生，WEB-GUI调试是没问题的，API会高频次产生，而且无论图片大小都会有这种情况出现。

@Nothing1024 commented on GitHub (May 20, 2025): > Unable to reproduce this issue with Dify online 1.4.0, doubao-1.5-vision-pro-250328 Try upgrading your local version of Dify > > ![Image](https://github.com/user-attachments/assets/3c1e92c7-f54a-42db-aca3-0e7990a2e137) > > ![Image](https://github.com/user-attachments/assets/b155fbe1-b07c-4d5e-9d6c-1cfb31b01e2e) 目前的情况是，偶发性产生，WEB-GUI调试是没问题的，API会高频次产生，而且无论图片大小都会有这种情况出现。
yindo commented 2026-02-16 10:18:38 -05:00
Author
Owner
Copy Link
Copy Source

@TaylorSwift5201314 commented on GitHub (May 29, 2025):

I don't encounter this issue with GPT-4.1, but when using Doubao-1.5-vision-pro, if the image size exceeds 3MB, it directly prompts: "failed to read response body: bufio.Scanner: token too long".

Version: 1.4.1

Image

Image

@TaylorSwift5201314 commented on GitHub (May 29, 2025): I don't encounter this issue with GPT-4.1, but when using Doubao-1.5-vision-pro, if the image size exceeds 3MB, it directly prompts: "failed to read response body: bufio.Scanner: token too long". Version: 1.4.1 ![Image](https://github.com/user-attachments/assets/5f4fee8e-68e6-4937-8047-b387837e7c55) ![Image](https://github.com/user-attachments/assets/b0061613-5f2e-48db-ab20-b598e0be705e)
yindo commented 2026-02-16 10:18:38 -05:00
Author
Owner
Copy Link
Copy Source

@EndlessSeeker commented on GitHub (Jun 4, 2025):

From the reason description above, the cause of the problem is the limit of bufio.Scanner. But it is a Go struct in deamon-plugin, that should be a common problem in model plugin, i'd like to ask why the problem only occurs in volcengine and openai-compatible plugin?

@EndlessSeeker commented on GitHub (Jun 4, 2025): From the reason description above, the cause of the problem is the limit of bufio.Scanner. But it is a Go struct in deamon-plugin, that should be a common problem in model plugin, i'd like to ask why the problem only occurs in volcengine and openai-compatible plugin?
yindo commented 2026-02-16 10:18:38 -05:00
Author
Owner
Copy Link
Copy Source

@yueru-mylove commented on GitHub (Jul 2, 2025):

save error with plugin: hjlarry/markdown-editor: 0.0.2
2025/07/02 10:59:24 stdio.go:188: [ERROR]plugin hjlarry/markdown-editor:0.0.2 has an error on stdout: bufio.Scanner: token too long
2025/07/02 10:59:24 run.go:135: [ERROR]plugin hjlarry/markdown-editor:0.0.2 exited with error: signal: killed

@yueru-mylove commented on GitHub (Jul 2, 2025): save error with plugin: hjlarry/markdown-editor: 0.0.2 2025/07/02 10:59:24 stdio.go:188: [ERROR]plugin hjlarry/markdown-editor:0.0.2 has an error on stdout: bufio.Scanner: token too long 2025/07/02 10:59:24 run.go:135: [ERROR]plugin hjlarry/markdown-editor:0.0.2 exited with error: signal: killed
yindo commented 2026-02-16 10:18:38 -05:00
Author
Owner
Copy Link
Copy Source

@sgguo commented on GitHub (Jul 2, 2025):

Same issue happened: plugin_daemon-1 | 2025/07/02 14:33:57 stdio.go:188: [ERROR]plugin hjlarry/agent:0.0.1 has an error on stdout: bufio.Scanner: token too long
plugin_daemon-1 | 2025/07/02 14:33:57 run.go:135: [ERROR]plugin hjlarry/agent:0.0.1 exited with error: signal: killed. VERSION: 1.5.0

@sgguo commented on GitHub (Jul 2, 2025): Same issue happened: plugin_daemon-1 | 2025/07/02 14:33:57 stdio.go:188: [ERROR]plugin hjlarry/agent:0.0.1 has an error on stdout: bufio.Scanner: token too long plugin_daemon-1 | 2025/07/02 14:33:57 run.go:135: [ERROR]plugin hjlarry/agent:0.0.1 exited with error: signal: killed. VERSION: 1.5.0
yindo commented 2026-02-16 10:18:38 -05:00
Author
Owner
Copy Link
Copy Source

@sgguo commented on GitHub (Jul 2, 2025):

A similar here: plugin_daemon-1 | 2025/07/02 14:27:41 stdio.go:182: [INFO]plugin junjiem/mcp_see_agent:0.2.2: response content: b''
plugin_daemon-1 | 2025/07/02 14:27:55 stdio.go:182: [INFO]plugin junjiem/mcp_see_agent:0.2.2: response status: 200 OK
plugin_daemon-1 | 2025/07/02 14:27:55 stdio.go:182: [INFO]plugin junjiem/mcp_see_agent:0.2.2: response headers: Headers({'date': 'Wed, 02 Jul 2025 14:27:40 GMT', 'server': 'uvicorn', 'cache-control': 'no-cache, no-transform', 'connection': 'keep-alive', 'content-type': 'text/event-stream', 'mcp-session-id': 'f85208f7ab6b41b79480fe497b4bf5ce', 'x-accel-buffering': 'no', 'transfer-encoding': 'chunked'})
plugin_daemon-1 | 2025/07/02 14:27:55 stdio.go:188: [ERROR]plugin junjiem/mcp_see_agent:0.2.2 has an error on stdout: bufio.Scanner: token too long
plugin_daemon-1 | 2025/07/02 14:27:55 run.go:135: [ERROR]plugin junjiem/mcp_see_agent:0.2.2 exited with error: signal: killed
plugin_daemon-1 | 2025/07/02 14:27:55 run.go:190: [INFO]plugin junjiem/mcp_see_agent:0.2.2 stopped
plugin_daemon-1 | 2025/07/02 14:28:00 run.go:147: [INFO]plugin junjiem/mcp_see_agent:0.2.2 started

@sgguo commented on GitHub (Jul 2, 2025): A similar here: plugin_daemon-1 | 2025/07/02 14:27:41 stdio.go:182: [INFO]plugin junjiem/mcp_see_agent:0.2.2: response content: b'' plugin_daemon-1 | 2025/07/02 14:27:55 stdio.go:182: [INFO]plugin junjiem/mcp_see_agent:0.2.2: response status: 200 OK plugin_daemon-1 | 2025/07/02 14:27:55 stdio.go:182: [INFO]plugin junjiem/mcp_see_agent:0.2.2: response headers: Headers({'date': 'Wed, 02 Jul 2025 14:27:40 GMT', 'server': 'uvicorn', 'cache-control': 'no-cache, no-transform', 'connection': 'keep-alive', 'content-type': 'text/event-stream', 'mcp-session-id': 'f85208f7ab6b41b79480fe497b4bf5ce', 'x-accel-buffering': 'no', 'transfer-encoding': 'chunked'}) plugin_daemon-1 | 2025/07/02 14:27:55 stdio.go:188: [ERROR]plugin junjiem/mcp_see_agent:0.2.2 has an error on stdout: bufio.Scanner: token too long plugin_daemon-1 | 2025/07/02 14:27:55 run.go:135: [ERROR]plugin junjiem/mcp_see_agent:0.2.2 exited with error: signal: killed plugin_daemon-1 | 2025/07/02 14:27:55 run.go:190: [INFO]plugin junjiem/mcp_see_agent:0.2.2 stopped plugin_daemon-1 | 2025/07/02 14:28:00 run.go:147: [INFO]plugin junjiem/mcp_see_agent:0.2.2 started
yindo commented 2026-02-16 10:18:38 -05:00
Author
Owner
Copy Link
Copy Source

@yueru-mylove commented on GitHub (Jul 11, 2025):

doesn't this bug fixed in 1.6.0? I still got this probem in 1.6.0 with plugin hjlarry/dify-plugin-markdown-editor.

@yueru-mylove commented on GitHub (Jul 11, 2025): doesn't this bug fixed in 1.6.0? I still got this probem in 1.6.0 with plugin hjlarry/dify-plugin-markdown-editor.
yindo commented 2026-02-16 10:18:38 -05:00
Author
Owner
Copy Link
Copy Source

@1107186916 commented on GitHub (Aug 5, 2025):

Image Image Image

After I modified the limit of dify, changing from 12288 to 24576, I reported an error:"[volcengine_maas] Error: PluginInvokeError: {"args":{},"error_type":"ArkBadRequestError","message":"Error code: 400 - {'error': {'code': 'InvalidParameter', 'message': 'The parameter max_tokens specified in the request are not valid: integer above maximum value, expected a value \u003c= 12288, but got 24576 instead. Request id: 021754374445564519af2f3595cfd396cd863a5a5db32d63d28db', 'param': 'max_tokens', 'type': 'BadRequest'}}, request_id: 20250805061405iijIAgF0P2boGUQOrbJY"}"

Is this the limitation of dify itself or the limitation of doubao model?

How can I increase this limit?

my dify is 1.7.1

@1107186916 commented on GitHub (Aug 5, 2025): <img width="385" height="420" alt="Image" src="https://github.com/user-attachments/assets/11a49ca3-0fd7-4852-b647-934e06a35cca" /> <img width="1482" height="603" alt="Image" src="https://github.com/user-attachments/assets/1eef31b3-9603-425b-896e-9f16c55594ef" /> <img width="1730" height="282" alt="Image" src="https://github.com/user-attachments/assets/24fe51c1-ebe7-4098-a3bf-b1c730a486a0" /> After I modified the limit of dify, changing from 12288 to 24576, I reported an error:"[volcengine_maas] Error: PluginInvokeError: {"args":{},"error_type":"ArkBadRequestError","message":"Error code: 400 - {'error': {'code': 'InvalidParameter', 'message': 'The parameter `max_tokens` specified in the request are not valid: integer above maximum value, expected a value \u003c= 12288, but got 24576 instead. Request id: 021754374445564519af2f3595cfd396cd863a5a5db32d63d28db', 'param': 'max_tokens', 'type': 'BadRequest'}}, request_id: 20250805061405iijIAgF0P2boGUQOrbJY"}" Is this the limitation of dify itself or the limitation of doubao model? How can I increase this limit? my dify is 1.7.1
yindo commented 2026-02-16 10:18:38 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Aug 15, 2025):

@1107186916

https://github.com/langgenius/dify/pull/23980

You can add these environment variables in the compose file and restart the plugin daemon service.

@crazywoola commented on GitHub (Aug 15, 2025): @1107186916 https://github.com/langgenius/dify/pull/23980 You can add these environment variables in the compose file and restart the plugin daemon service.
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 good first issue
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#256
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?