langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-23 04:45:23 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #3523] docs: add Vequil callback handler integration #3567

New Issue
Open
opened 2026-06-05 18:23:30 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 18:23:30 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/3523
Author: @nxd914
Created: 4/9/2026
Status: 🔄 Open

Base: main ← Head: add-vequil-callback

📝 Commits (1)

  • 235e39a docs: add Vequil callback handler integration

📊 Changes

1 file changed (+63 additions, -0 deletions)

View changed files

➕ src/oss/python/integrations/callbacks/vequil.mdx (+63 -0)

📄 Description

Description

Adds Vequil to the callbacks integrations page.

Vequil is a reliability and observability layer for AI agent operators. It detects anomalies in real time (logic loops, retry storms, cost spikes, blocked tool calls), tracks spend by agent and tool, and generates shareable weekly report cards.

Integration

The VequilCallbackHandler is a BaseCallbackHandler subclass that works drop-in with any LangChain chain, agent, or LLM call:

from vequil import VequilClient
from vequil.integrations.langchain import VequilCallbackHandler

vq = VequilClient(workspace_key="vk_ws_...")
handler = VequilCallbackHandler(vq, agent_id="my-chain")

result = chain.invoke(
    {"input": "..."},
    config={"callbacks": [handler]},
)

Captures: tool start/end/error, LLM call start/end, chain errors, token usage.

🔄 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/3523 **Author:** [@nxd914](https://github.com/nxd914) **Created:** 4/9/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-vequil-callback` --- ### 📝 Commits (1) - [`235e39a`](https://github.com/langchain-ai/docs/commit/235e39a8fe3adc34d5a1d222989e0a4661be877f) docs: add Vequil callback handler integration ### 📊 Changes **1 file changed** (+63 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `src/oss/python/integrations/callbacks/vequil.mdx` (+63 -0) </details> ### 📄 Description ## Description Adds Vequil to the callbacks integrations page. [Vequil](https://vequil.com) is a reliability and observability layer for AI agent operators. It detects anomalies in real time (logic loops, retry storms, cost spikes, blocked tool calls), tracks spend by agent and tool, and generates shareable weekly report cards. ## Integration The `VequilCallbackHandler` is a `BaseCallbackHandler` subclass that works drop-in with any LangChain chain, agent, or LLM call: ```python from vequil import VequilClient from vequil.integrations.langchain import VequilCallbackHandler vq = VequilClient(workspace_key="vk_ws_...") handler = VequilCallbackHandler(vq, agent_id="my-chain") result = chain.invoke( {"input": "..."}, config={"callbacks": [handler]}, ) ``` Captures: tool start/end/error, LLM call start/end, chain errors, token usage. - PyPI: https://pypi.org/project/vequil/ - GitHub: https://github.com/nxd914/vequil --- <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 18:23:30 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
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: langchain-ai/docs#3567
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?