langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-21 11:55:23 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #2835] docs: add AgentOps Cockpit integration #2932

New Issue
Open
opened 2026-06-05 18:20:26 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 18:20:26 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/2835
Author: @enriquekalven
Created: 2/26/2026
Status: 🔄 Open

Base: main ← Head: main

📝 Commits (4)

  • ad28d09 Create agentops_cockpit.mdxdocs: add AgentOps Cockpit provider documentation
  • 1a7a05d Create agentops_cockpit.mdx
  • 1c45bb5 Update all_providers.mdx
  • 672f64f Merge branch 'main' into main

📊 Changes

3 files changed (+113 additions, -3237 deletions)

View changed files

➕ src/oss/python/integrations/callbacks/agentops_cockpit.mdx (+54 -0)
➕ src/oss/python/integrations/providers/agentops_cockpit.mdx (+54 -0)
📝 src/oss/python/integrations/providers/all_providers.mdx (+5 -3237)

📄 Description

🚀 Overview

This PR introduces AgentOps Cockpit as a first-class integration for LangChain and LangGraph.

While LangChain excels at orchestration, the Cockpit provides a Sovereign Governance Layer that enables enterprise-grade control, security, and cost-efficiency. This integration features a high-fidelity CockpitCallbackHandler that monitors every turn of an agent's reasoning trace for structural and security risks.

✨ Key Features

  • 🛡️ Real-time PII Scrubbing: Automatically detects and redacts sensitive data (SSNs, emails, API keys) before they reach LLM endpoints.
  • 🧭 ASI-XX Security Mapping: The first integration aligned with the OWASP Agentic Top 10 (ASI). Detects un-sandboxed MCP tools (ASI-04), indirect prompt injection (ASI-01), and broken tool authorization (ASI-02).
  • 💰 FinOps Optimization: Identifies prompt saturation and provides real-time suggestions for Context Caching in high-token-volume LangGraph state machines.
  • 🏗️ Architectural Integrity: Uses AST-aware auditing to flag un-managed loops and "Spaghetti Agents" that create technical debt and logic failures.

🛠️ Quick Start

from langchain_cockpit import CockpitCallbackHandler
from langchain_openai import ChatOpenAI

# Initialize the Sovereign Governance layer
cockpit = CockpitCallbackHandler(app_name="enterprise-assistant")

# Attach to any LLM, Chain, or LangGraph invocation
llm = ChatOpenAI(model="gpt-4o", callbacks=[cockpit])

✅ Documentation Included

  • Provider Hub: New page at src/oss/python/integrations/providers/agentops_cockpit.mdx
  • Technical Implementation: New guide at src/oss/python/integrations/callbacks/agentops_cockpit.mdx
  • Global Registry: Alphabetical listing added to all_providers.mdx.

🔗 Resources

🔄 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/2835 **Author:** [@enriquekalven](https://github.com/enriquekalven) **Created:** 2/26/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (4) - [`ad28d09`](https://github.com/langchain-ai/docs/commit/ad28d093731566d893a8e06896990c939764de37) Create agentops_cockpit.mdxdocs: add AgentOps Cockpit provider documentation - [`1a7a05d`](https://github.com/langchain-ai/docs/commit/1a7a05dd190075ea465222330771c7c25beccc1a) Create agentops_cockpit.mdx - [`1c45bb5`](https://github.com/langchain-ai/docs/commit/1c45bb53b395c17d8b53657969f701cae87bb1cf) Update all_providers.mdx - [`672f64f`](https://github.com/langchain-ai/docs/commit/672f64f5692be4ae395904a9da6ab685b8d712ea) Merge branch 'main' into main ### 📊 Changes **3 files changed** (+113 additions, -3237 deletions) <details> <summary>View changed files</summary> ➕ `src/oss/python/integrations/callbacks/agentops_cockpit.mdx` (+54 -0) ➕ `src/oss/python/integrations/providers/agentops_cockpit.mdx` (+54 -0) 📝 `src/oss/python/integrations/providers/all_providers.mdx` (+5 -3237) </details> ### 📄 Description ## 🚀 Overview This PR introduces **AgentOps Cockpit** as a first-class integration for LangChain and LangGraph. While LangChain excels at orchestration, the Cockpit provides a **Sovereign Governance Layer** that enables enterprise-grade control, security, and cost-efficiency. This integration features a high-fidelity `CockpitCallbackHandler` that monitors every turn of an agent's reasoning trace for structural and security risks. ## ✨ Key Features - **🛡️ Real-time PII Scrubbing**: Automatically detects and redacts sensitive data (SSNs, emails, API keys) before they reach LLM endpoints. - **🧭 ASI-XX Security Mapping**: The first integration aligned with the **OWASP Agentic Top 10 (ASI)**. Detects un-sandboxed MCP tools (ASI-04), indirect prompt injection (ASI-01), and broken tool authorization (ASI-02). - **💰 FinOps Optimization**: Identifies prompt saturation and provides real-time suggestions for **Context Caching** in high-token-volume LangGraph state machines. - **🏗️ Architectural Integrity**: Uses AST-aware auditing to flag un-managed loops and "Spaghetti Agents" that create technical debt and logic failures. ## 🛠️ Quick Start ```python from langchain_cockpit import CockpitCallbackHandler from langchain_openai import ChatOpenAI # Initialize the Sovereign Governance layer cockpit = CockpitCallbackHandler(app_name="enterprise-assistant") # Attach to any LLM, Chain, or LangGraph invocation llm = ChatOpenAI(model="gpt-4o", callbacks=[cockpit]) ``` ## ✅ Documentation Included - **Provider Hub**: New page at `src/oss/python/integrations/providers/agentops_cockpit.mdx` - **Technical Implementation**: New guide at `src/oss/python/integrations/callbacks/agentops_cockpit.mdx` - **Global Registry**: Alphabetical listing added to `all_providers.mdx`. ## 🔗 Resources - **Repository**: [AgentOps Cockpit on GitHub](https://github.com/enriquekalven/agent-ops-cockpit) - **Framework**: Built on the **Agentic Trinity** v2.0.4 standard. --- <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 18:20:26 -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#2932
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?