[PR #4266] Add note that supervisor dispatches sequentially by default but supports parallel subagent offloading #4251

Open
opened 2026-06-05 19:13:16 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/4266
Author: @langsmith-fleet[bot]
Created: 6/2/2026
Status: 🔄 Open

Base: mainHead: docs/add-supervisor-parallel-dispatch-note


📝 Commits (1)

  • 0068fbd Add note that supervisor dispatches sequentially by default but supports parallel subagent offloading

📊 Changes

1 file changed (+7 additions, -3 deletions)

View changed files

📝 src/oss/langchain/multi-agent/subagents-personal-assistant.mdx (+7 -3)

📄 Description

Fixes DOC-1194

Summary

  • Added a <Note> callout after Example 2 on the personal assistant tutorial page clarifying that the supervisor dispatches tasks sequentially by default, but that LLMs can issue multiple tool calls in a single response (which the runtime executes in parallel), and linking to the create_supervisor reference docs for explicit parallel dispatch configuration
  • Updated the SUPERVISOR_PROMPT text in both Python and JS (tutorial and complete working example sections) to replace "in sequence" with "in sequence or in parallel as appropriate"

Links

Verification

Not run; docs-only copy change.

Reviewers

Requested review from: @npentrel, @lnhsingh


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/4266 **Author:** [@langsmith-fleet[bot]](https://github.com/apps/langsmith-fleet) **Created:** 6/2/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `docs/add-supervisor-parallel-dispatch-note` --- ### 📝 Commits (1) - [`0068fbd`](https://github.com/langchain-ai/docs/commit/0068fbdff380822987f3bbae42ae581106b20456) Add note that supervisor dispatches sequentially by default but supports parallel subagent offloading ### 📊 Changes **1 file changed** (+7 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `src/oss/langchain/multi-agent/subagents-personal-assistant.mdx` (+7 -3) </details> ### 📄 Description Fixes DOC-1194 ## Summary - Added a `<Note>` callout after Example 2 on the personal assistant tutorial page clarifying that the supervisor dispatches tasks sequentially by default, but that LLMs can issue multiple tool calls in a single response (which the runtime executes in parallel), and linking to the `create_supervisor` reference docs for explicit parallel dispatch configuration - Updated the `SUPERVISOR_PROMPT` text in both Python and JS (tutorial and complete working example sections) to replace "in sequence" with "in sequence or in parallel as appropriate" ## Links - Linear: https://linear.app/langchain/issue/DOC-1194/add-note-that-supervisor-is-sequential-by-default-but-supports - Slack: https://langchain.slack.com/archives/C09G1T60QV9/p1780399953068159 ## Verification Not run; docs-only copy change. ## Reviewers Requested review from: @npentrel, @lnhsingh --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 19:13:16 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#4251