langgenius/dify-plugin-daemon
1
0
Fork 0
mirror of https://github.com/langgenius/dify-plugin-daemon.git synced 2026-07-21 17:25:23 -04:00
Code Issues 111 Packages Projects Releases 10 Wiki Activity

Agent fails to retrieve large tool return values in workflow execution #122

New Issue
Open
opened 2026-02-16 00:19:58 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:19:58 -05:00
Owner
Copy Link
Copy Source

Originally created by @homeant on GitHub (May 23, 2025).

Versions
1. dify-plugin-daemon Version: 0.0.10
2. dify-api Version: 1.4.0

Describe the bug
When using an agent to call a tool in a workflow, if the tool returns a large amount of data, the agent is unable to receive or process the returned content.

To Reproduce
Steps to reproduce the behavior:
1. Create a workflow that includes a tool returning a large content payload.
2. Use an agent in chatflow to invoke this workflow.
3. Wait for the tool to return the data.
4. Observe that the agent does not receive the return value.

Expected behavior
The agent should be able to receive and process large return values from tools invoked within workflows.

Screenshots
(If applicable, please attach relevant screenshots showing the issue. You can leave this section empty if not available.)

Additional context
Related issue: https://github.com/langgenius/dify/issues/18501
During debugging, I found that the tool itself can return results properly, but the agent in ROUND 1 of the chatflow is unable to access the return value. It seems to be related to inconsistent nodeids, but I’m not sure how to fix this bug.

Image

Originally created by @homeant on GitHub (May 23, 2025). Versions 1. dify-plugin-daemon Version: 0.0.10 2. dify-api Version: 1.4.0 Describe the bug When using an agent to call a tool in a workflow, if the tool returns a large amount of data, the agent is unable to receive or process the returned content. To Reproduce Steps to reproduce the behavior: 1. Create a workflow that includes a tool returning a large content payload. 2. Use an agent in chatflow to invoke this workflow. 3. Wait for the tool to return the data. 4. Observe that the agent does not receive the return value. Expected behavior The agent should be able to receive and process large return values from tools invoked within workflows. Screenshots (If applicable, please attach relevant screenshots showing the issue. You can leave this section empty if not available.) Additional context Related issue: https://github.com/langgenius/dify/issues/18501 During debugging, I found that the tool itself can return results properly, but the agent in ROUND 1 of the chatflow is unable to access the return value. It seems to be related to inconsistent nodeids, but I’m not sure how to fix this bug. ![Image](https://github.com/user-attachments/assets/5473447c-3459-41a9-95c3-1e303100cea5)
yindo added the plugin-daemon label 2026-02-16 00:19:58 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Windows
bug
cmd
documentation
enhancement
go
good first issue
plugin-daemon
pull-request
Mirrored from GitHub Pull Request
 question
No Label plugin-daemon
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-plugin-daemon#122
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?