Skip to content

feat: multi agent part 2 #1866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
sydney-runkle merged 54 commits into from
Dec 18, 2025
Merged

feat: multi agent part 2 #1866

sydney-runkle merged 54 commits into from
Dec 18, 2025

Conversation

@sydney-runkle
Copy link
Contributor

@sydney-runkle sydney-runkle commented Dec 11, 2025 •
edited
Loading

New and revamped multi agent docs!! Weeks in the making!

Added pages for:

  • Multi agent overview
    • Subagents
    • Router
    • Handoffs
    • Skills
    • Custom workflow

Added tutorials for:

  • Router
  • Handoffs
  • Skills

@github-actions github-actions bot added ci langchain For docs changes to LangChain oss internal labels Dec 11, 2025
@github-actions
Copy link
Contributor

github-actions bot commented Dec 11, 2025 •
edited
Loading

❌ Import check failed

This PR contains imports from langchain_core that should be imported from langchain instead.

Detailed issues 
Analyzing diff for import issues...
 Found 1 import issues:

File: src/oss/langchain/multi-agent/handoffs.mdx
Line: 343
Issue: Import from langchain.messages instead of langchain_core.messages
Current:   from langchain_core.messages import AIMessage, ToolMessage
Suggested: from langchain.messages import AIMessage, ToolMessage
--------------------------------------------------------------------------------

 Found 1 import issues that need to be fixed.

Why this is a problem

The langchain package re-exports many modules and classes from langchain_core. When possible, imports should use langchain instead of langchain_core for:

  • Better user experience (single import source)
  • Consistency across documentation
  • Reduced cognitive load for users

How to fix

Replace the imports as suggested above. For example:

  • ❌ from langchain_core.messages import HumanMessage
  • ✅ from langchain.messages import HumanMessage

🤖 Automated check

This check is based on the latest analysis of langchain re-exports from langchain_core.

@github-actions
Copy link
Contributor

github-actions bot commented Dec 11, 2025

Mintlify preview ID generated: preview-srmult-1765486358-912f048

@github-actions
Copy link
Contributor

github-actions bot commented Dec 16, 2025

Mintlify preview ID generated: preview-srmult-1765898309-14ce191

lnhsingh
lnhsingh approved these changes Dec 16, 2025
View reviewed changes
Copy link
Collaborator

@lnhsingh lnhsingh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice job @sydney-runkle and @eyurtsev !!!!!

@sydney-runkle @lnhsingh
Apply suggestions from code review
98ebd3a 
Co-authored-by: Lauren Hirata Singh <[email protected]>
@github-actions
Copy link
Contributor

github-actions bot commented Dec 16, 2025

Mintlify preview ID generated: preview-srmult-1765901258-9e41223

eyurtsev
eyurtsev reviewed Dec 16, 2025
View reviewed changes
eyurtsev
eyurtsev reviewed Dec 16, 2025
View reviewed changes
@github-actions
Copy link
Contributor

github-actions bot commented Dec 16, 2025

Mintlify preview ID generated: preview-srmult-1765902910-57c322e

@github-actions
Copy link
Contributor

github-actions bot commented Dec 17, 2025

Mintlify preview ID generated: preview-srmult-1765982084-dd256c0

@github-actions
Copy link
Contributor

github-actions bot commented Dec 17, 2025

Mintlify preview ID generated: preview-srmult-1765996983-00cab74

@sydney-runkle @eyurtsev
feat: multi agent, multi page! (#1952)
de421fd 
refactoring multi agent to be multiple pages (overview + spinoff pages
for each pattern)

new architecture
```
Multi Agent
Overview
    Why multi agent
    Patterns
        Choosing a pattern
    Performance Comparison
Subagents
Handoffs
Skills
Router
Custom Workflow
```

Each of the patterns pages has
```
* Intro paragraph
* Diagram
## Key characteristics
## When to use
## Basic implementation
* small code snippet
* tutorial link / card
## A bunch of sections specific to said pattern (context eng stuff, for e.g.)
```

- [ ] finish perf comparison section
- [x] finish router tutorial
- [x] figure out what we're doing w/ some of the collapsable snippets
- [ ] xrefs and links
- [x] handoffs - add more details on handoff specs for each of
middleware and graph jumps
- [x] router - add basic impl w/ command not send
- [x] figure out how we're organizing all of the tutorials (maybe a
multi agent section)

---------

Co-authored-by: Eugene Yurtsev <[email protected]>
@github-actions github-actions bot added the langgraph For docs changes to LangGraph label Dec 17, 2025
@github-actions
Copy link
Contributor

github-actions bot commented Dec 17, 2025

Mintlify preview ID generated: preview-srmult-1766003055-de13dcb

@github-actions
Copy link
Contributor

github-actions bot commented Dec 17, 2025

Mintlify preview ID generated: preview-srmult-1766003902-e4d91e6

@github-actions
Copy link
Contributor

github-actions bot commented Dec 17, 2025

Mintlify preview ID generated: preview-srmult-1766011159-0525fe2

@github-actions
Copy link
Contributor

github-actions bot commented Dec 18, 2025

Mintlify preview ID generated: preview-srmult-1766073225-8264b51

@sydney-runkle
Copy link
Contributor Author

sydney-runkle commented Dec 18, 2025

  • Rename supervisor to subagents (@sydney-runkle)
  • Review language for each pattern for accuracy / inaccuracy
  • State machine (owner @eugene)
    • More explanation about handoffs
    • Explanation about conversation fluidity
    • Expanation about handoffs from a subagent (i.e., jumping to parent)
    • Relax tip statement
  • Skills potentially include a bit of information about llms.txt (as it's the same idea)
  • Stateless router (owner @sydney-runkle):
    • Explain how to include conversation history as context (this doesn't mean it's stateful)
  • Custom workflow (owner @sydney-runkle)
    • Intro shouldn't suggest it's only for sequential pipelines (explain that branching / loops agentic logic is supported)
    • Refine example as agents typically need tools (otherwise it's just an LLM call)

@sydney-runkle sydney-runkle merged commit 95c110d into main Dec 18, 2025
12 of 13 checks passed
@sydney-runkle sydney-runkle deleted the sr/multi-agent-new-docs branch December 18, 2025 16:02
@github-actions
Copy link
Contributor

github-actions bot commented Dec 18, 2025

Mintlify preview ID generated: preview-srmult-1766073714-f1b83c7

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@eyurtsev eyurtsev eyurtsev left review comments

@lnhsingh lnhsingh lnhsingh approved these changes

@katmayb katmayb Awaiting requested review from katmayb katmayb is a code owner

Assignees

No one assigned

Labels

ci internal langchain For docs changes to LangChain langgraph For docs changes to LangGraph oss

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@sydney-runkle @eyurtsev @lnhsingh