langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 12:25:55 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #4034] docs: add Agentic SpendGuard provider integration page #4040

New Issue
Open
opened 2026-06-05 18:53:59 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 18:53:59 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/4034
Author: @m24927605
Created: 5/16/2026
Status: 🔄 Open

Base: main ← Head: add-agentic-spendguard-provider

📝 Commits (5)

  • 7ac8044 docs: add Agentic SpendGuard provider integration page
  • 46d6ac1 fix: address CI lint failures from PR #4034
  • 186a996 docs: simplify Agentic SpendGuard page to match merged-provider convention
  • 1951844 docs: note spendguard-sdk is pre-release; pip needs --pre
  • 661b2ce Merge branch 'main' into add-agentic-spendguard-provider

📊 Changes

2 files changed (+119 additions, -0 deletions)

View changed files

➕ src/oss/python/integrations/providers/agentic_spendguard.mdx (+111 -0)
📝 src/oss/python/integrations/providers/all_providers.mdx (+8 -0)

📄 Description

Summary

Adds a new provider page for Agentic SpendGuard, an open-source runtime budget gate that refuses LLM API calls which would exceed a configured budget before the request reaches the provider. Package: spendguard-sdk (PyPI).

Two ways to use it from LangChain are documented:

  • Local egress proxy: point ChatOpenAI(base_url=...) at the proxy. Over-budget calls receive HTTP 429 with a structured spendguard_blocked body before any upstream OpenAI request fires.
  • SDK wrapper: pip install 'spendguard-sdk[langchain]' and wrap any BaseChatModel in SpendGuardChatModel. Composes with LangGraph.

Files changed

  • src/oss/python/integrations/providers/agentic_spendguard.mdx — new provider page
  • src/oss/python/integrations/providers/all_providers.mdx — Card entry in alphabetical position (between AG-UI Protocol and AgentPhone)

Test plan

  • make install && make build succeeds with 0 errors
  • mint export end-to-end succeeds (869 pages rendered, no failures)
  • Vale + Check for incorrect langchain_core imports CI checks pass
  • All 14 CI checks pass

🔄 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/4034 **Author:** [@m24927605](https://github.com/m24927605) **Created:** 5/16/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-agentic-spendguard-provider` --- ### 📝 Commits (5) - [`7ac8044`](https://github.com/langchain-ai/docs/commit/7ac8044475baced2700d082e7a83021c0c1cd511) docs: add Agentic SpendGuard provider integration page - [`46d6ac1`](https://github.com/langchain-ai/docs/commit/46d6ac17c276d4fb3a66b34f492bc1ec2b299d2b) fix: address CI lint failures from PR #4034 - [`186a996`](https://github.com/langchain-ai/docs/commit/186a996d2aa41053253d04b4d269d750b0e815a1) docs: simplify Agentic SpendGuard page to match merged-provider convention - [`1951844`](https://github.com/langchain-ai/docs/commit/19518442f1ed9b450dfdf9d800dab75065877f18) docs: note spendguard-sdk is pre-release; pip needs --pre - [`661b2ce`](https://github.com/langchain-ai/docs/commit/661b2ce09c4f9378726efe491200b903edf0167c) Merge branch 'main' into add-agentic-spendguard-provider ### 📊 Changes **2 files changed** (+119 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `src/oss/python/integrations/providers/agentic_spendguard.mdx` (+111 -0) 📝 `src/oss/python/integrations/providers/all_providers.mdx` (+8 -0) </details> ### 📄 Description ## Summary Adds a new provider page for [Agentic SpendGuard](https://github.com/m24927605/agentic-spendguard), an open-source runtime budget gate that refuses LLM API calls which would exceed a configured budget before the request reaches the provider. Package: [`spendguard-sdk`](https://pypi.org/project/spendguard-sdk/) (PyPI). Two ways to use it from LangChain are documented: - Local egress proxy: point `ChatOpenAI(base_url=...)` at the proxy. Over-budget calls receive `HTTP 429` with a structured `spendguard_blocked` body before any upstream OpenAI request fires. - SDK wrapper: `pip install 'spendguard-sdk[langchain]'` and wrap any `BaseChatModel` in `SpendGuardChatModel`. Composes with LangGraph. ## Files changed - `src/oss/python/integrations/providers/agentic_spendguard.mdx` — new provider page - `src/oss/python/integrations/providers/all_providers.mdx` — Card entry in alphabetical position (between AG-UI Protocol and AgentPhone) ## Test plan - [x] `make install && make build` succeeds with 0 errors - [x] `mint export` end-to-end succeeds (869 pages rendered, no failures) - [x] Vale + `Check for incorrect langchain_core imports` CI checks pass - [x] All 14 CI checks pass --- <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 18:53:59 -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#4040
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?