langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 12:05:30 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

[PR #20391] fix: inner invoke llm token too long #29381

New Issue
Closed
opened 2026-02-21 20:45:27 -05:00 by yindo · 0 comments
yindo commented 2026-02-21 20:45:27 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langgenius/dify/pull/20391

State: closed
Merged: Yes

Summary

Since Agent Node calls the inner model invoke API, the Dify backend returns both LLMChunkResult and LLMChunk with the original prompt_messages included. This causes responses to become extremely lengthy during multi-turn conversations, eventually exceeding the Plugin Daemon service scanner's default 32k read limit. While this issue has been resolved in the regular Invoke model, it still persists in the inner invoke implementation.
Example scenario in Agent Node:

First query → Returns first query + answer (~100 bytes) + tool invocation (20k)
Second query → Returns first query + answer + tool results + second answer (~22k) + tool invocation (20k)
Third query → Returns accumulated content from rounds 1-2 + third answer (LLM fails to output because scanner data exceeds 32k limit and returns empty, causing Agent Node to return nothing)

Solution: We have removed the Prompt Messages from the response payload to prevent this accumulation issue.

Fixes #20037
Fixes https://github.com/langgenius/dify/issues/19489
Fixes https://github.com/langgenius/dify/issues/19978

Screenshots

Before After
... ...

Checklist

Important

Please review the checklist below before submitting your pull request.

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods
**Original Pull Request:** https://github.com/langgenius/dify/pull/20391 **State:** closed **Merged:** Yes --- # Summary Since Agent Node calls the inner model invoke API, the Dify backend returns both LLMChunkResult and LLMChunk with the original prompt_messages included. This causes responses to become extremely lengthy during multi-turn conversations, eventually exceeding the Plugin Daemon service scanner's default 32k read limit. While this issue has been resolved in the regular Invoke model, it still persists in the inner invoke implementation. Example scenario in Agent Node: First query → Returns first query + answer (~100 bytes) + tool invocation (20k) Second query → Returns first query + answer + tool results + second answer (~22k) + tool invocation (20k) Third query → Returns accumulated content from rounds 1-2 + third answer (LLM fails to output because scanner data exceeds 32k limit and returns empty, causing Agent Node to return nothing) Solution: We have removed the Prompt Messages from the response payload to prevent this accumulation issue. Fixes #20037 Fixes https://github.com/langgenius/dify/issues/19489 Fixes https://github.com/langgenius/dify/issues/19978 # Screenshots | Before | After | |--------|-------| | ... | ... | # Checklist > [!IMPORTANT] > Please review the checklist below before submitting your pull request. - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs) - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!) - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change. - [x] I've updated the documentation accordingly. - [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods
yindo added the pull-request label 2026-02-21 20:45:27 -05:00
yindo closed this issue 2026-02-21 20:45:27 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label pull-request
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#29381
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?