langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

[PR #28704] Add the return_direct capability to tools: supports skipping the LLM and directly returning the final answer #32143

New Issue
Closed
opened 2026-02-21 20:50:50 -05:00 by yindo · 0 comments
yindo commented 2026-02-21 20:50:50 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langgenius/dify/pull/28704

State: closed
Merged: No

Important

  1. Make sure you have read our contribution guidelines
  2. Ensure there is an associated issue and you have been assigned to it
  3. Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

After the tool is called, Dify's Agent will inject the tool response as an Observation into LLM, which will then output the final answer; When the tool returns excessively long text/JSON (such as ECharts configuration), it will significantly increase context load and latency, for example, my workflow may involve Echart charts for 2000 sets of data
Learn from Langchain to enable agents to skip LLM when calling certain tools.

-Add a return signal (strictly Boolean True) to pass from the tool message to the Agent Runner.
-FC Runner adopts the strategy of "short circuit only when all tools return directly": when all tools in the same round are return-direct=True, after executing all tools, aggregate the text as the final answer and return directly; Otherwise, continue back to LLM. Framework similar to Langgraph.

Provided some screenshots of the tests

Screenshots

1 3 4 5 6

Checklist

  • 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/28704 **State:** closed **Merged:** No --- > [!IMPORTANT] > > 1. Make sure you have read our [contribution guidelines](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) > 1. Ensure there is an associated issue and you have been assigned to it > 1. Use the correct syntax to link this PR: `Fixes #<issue number>`. ## Summary After the tool is called, Dify's Agent will inject the tool response as an Observation into LLM, which will then output the final answer; When the tool returns excessively long text/JSON (such as ECharts configuration), it will significantly increase context load and latency, for example, my workflow may involve Echart charts for 2000 sets of data Learn from Langchain to enable agents to skip LLM when calling certain tools. -Add a return signal (strictly Boolean True) to pass from the tool message to the Agent Runner. -FC Runner adopts the strategy of "short circuit only when all tools return directly": when all tools in the same round are return-direct=True, after executing all tools, aggregate the text as the final answer and return directly; Otherwise, continue back to LLM. Framework similar to Langgraph. Provided some screenshots of the tests ## Screenshots <img width="1875" height="627" alt="1" src="https://github.com/user-attachments/assets/c53f645c-d870-417e-af9b-ecb6c9d28f20" /> <img width="1404" height="801" alt="3" src="https://github.com/user-attachments/assets/91e079f0-139e-4adc-a9d9-d45c98bca9b2" /> <img width="897" height="536" alt="4" src="https://github.com/user-attachments/assets/8c534ce7-d579-4081-8485-9c16c8ecad7c" /> <img width="521" height="500" alt="5" src="https://github.com/user-attachments/assets/6b0354e9-1630-41ad-9f3a-899e2b002459" /> <img width="528" height="255" alt="6" src="https://github.com/user-attachments/assets/b2b2a8de-50ff-4d69-9e49-48312a157aec" /> ## Checklist - [ ] 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 20:50:50 -05:00
yindo closed this issue 2026-02-21 20:50:50 -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#32143
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?