langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-21 03:45:28 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #4213] docs(langgraph): add Vaultak runtime security integration guide #4202

New Issue
Open
opened 2026-06-05 19:13:07 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 19:13:07 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/4213
Author: @samueloladji-beep
Created: 5/29/2026
Status: 🔄 Open

Base: main ← Head: add-vaultak-langgraph

📝 Commits (3)

  • b36180c Add Vaultak runtime security integration for LangChain agents
  • 83b2040 docs(langgraph): add Vaultak runtime security integration guide
  • f1a0ec1 fix(vaultak): remove spaces around em dashes (LangChain.DashesSpaces)

📊 Changes

3 files changed (+248 additions, -1 deletions)

View changed files

📝 src/docs.json (+2 -1)
➕ src/oss/langgraph/vaultak.mdx (+197 -0)
➕ src/oss/python/integrations/providers/vaultak.mdx (+49 -0)

📄 Description

Summary

  • Adds src/oss/langgraph/vaultak.mdx — a new integration guide in the LangGraph Production section covering how to wire Vaultak runtime security into LangGraph agents and StateGraph workflows.
  • Updates src/docs.json to add oss/python/langgraph/vaultak to the Production nav group, directly after the existing Observability page.

Integration pattern

VaultakCallbackHandler extends LangChain's BaseCallbackHandler, so it plugs into LangGraph via the standard config dict with zero graph rewrites:

from langchain_vaultak import VaultakCallbackHandler

vaultak = VaultakCallbackHandler(
    api_key="vtk_...",
    agent_name="my-agent",
    block_on_high_risk=True,
    risk_threshold=7.0,
)

# Prebuilt ReAct agent — per invocation
result = agent.invoke(input, config={"callbacks": [vaultak]})

# StateGraph — at compile time (covers every run)
graph = builder.compile().with_config({"callbacks": [vaultak]})

Every tool call is risk-scored (0–10) before execution. Calls above the threshold raise an exception to halt the graph. Tool outputs are scanned for PII before they reach the next node.

Page contents

  • Install snippet (pip / uv tabs)
  • Prebuilt create_react_agent example with two realistic tools
  • Custom StateGraph workflow example with ToolNode
  • Per-invocation config pattern (varying threshold per request)
  • Configuration reference table
  • Event-coverage table (what LangGraph events Vaultak intercepts)

Test plan

  • Page renders at /oss/python/langgraph/vaultak without errors
  • Nav shows "Vaultak Runtime Security" in the Production group after Observability
  • Code blocks render correctly (pip/uv <CodeGroup>, Python snippets)
  • All internal links (back to observability, LangSmith docs) resolve

🤖 Generated with Claude Code

🔄 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/4213 **Author:** [@samueloladji-beep](https://github.com/samueloladji-beep) **Created:** 5/29/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-vaultak-langgraph` --- ### 📝 Commits (3) - [`b36180c`](https://github.com/langchain-ai/docs/commit/b36180cf92e243706f9ef6ab43ad8d4f2a100b9f) Add Vaultak runtime security integration for LangChain agents - [`83b2040`](https://github.com/langchain-ai/docs/commit/83b2040d7ccc54f2544970bc3ccfbe3fbb683369) docs(langgraph): add Vaultak runtime security integration guide - [`f1a0ec1`](https://github.com/langchain-ai/docs/commit/f1a0ec147e13e49d5828ac8cd2b15285bb9a5d80) fix(vaultak): remove spaces around em dashes (LangChain.DashesSpaces) ### 📊 Changes **3 files changed** (+248 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `src/docs.json` (+2 -1) ➕ `src/oss/langgraph/vaultak.mdx` (+197 -0) ➕ `src/oss/python/integrations/providers/vaultak.mdx` (+49 -0) </details> ### 📄 Description ## Summary - Adds `src/oss/langgraph/vaultak.mdx` — a new integration guide in the LangGraph Production section covering how to wire [Vaultak](https://vaultak.com) runtime security into LangGraph agents and StateGraph workflows. - Updates `src/docs.json` to add `oss/python/langgraph/vaultak` to the Production nav group, directly after the existing Observability page. ## Integration pattern `VaultakCallbackHandler` extends LangChain's `BaseCallbackHandler`, so it plugs into LangGraph via the standard `config` dict with zero graph rewrites: ```python from langchain_vaultak import VaultakCallbackHandler vaultak = VaultakCallbackHandler( api_key="vtk_...", agent_name="my-agent", block_on_high_risk=True, risk_threshold=7.0, ) # Prebuilt ReAct agent — per invocation result = agent.invoke(input, config={"callbacks": [vaultak]}) # StateGraph — at compile time (covers every run) graph = builder.compile().with_config({"callbacks": [vaultak]}) ``` Every tool call is risk-scored (0–10) before execution. Calls above the threshold raise an exception to halt the graph. Tool outputs are scanned for PII before they reach the next node. ## Page contents - Install snippet (pip / uv tabs) - Prebuilt `create_react_agent` example with two realistic tools - Custom `StateGraph` workflow example with `ToolNode` - Per-invocation config pattern (varying threshold per request) - Configuration reference table - Event-coverage table (what LangGraph events Vaultak intercepts) ## Test plan - [ ] Page renders at `/oss/python/langgraph/vaultak` without errors - [ ] Nav shows "Vaultak Runtime Security" in the Production group after Observability - [ ] Code blocks render correctly (pip/uv `<CodeGroup>`, Python snippets) - [ ] All internal links (back to observability, LangSmith docs) resolve 🤖 Generated with [Claude Code](https://claude.com/claude-code) --- <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 19:13:07 -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#4202
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?