styling and edits

src/docs.json

@@ -1,25 +1,25 @@
 {
   "$schema": "https://mintlify.com/docs.json",
-  "theme": "maple",
+  "theme": "aspen",
   "name": "Docs by LangChain",
   "description": "Documentation for LangChain, LangGraph, LangGraph Platform, LangSmith, and more.",
   "colors": {
-    "primary": "#beb4fd",
-    "light": "#beb4fd",
-    "dark": "#1d3d3c"
+    "primary": "#2F6868",
+    "light": "#84C4C0",
+    "dark": "#84C4C0"
   },
   "logo": {
     "light": "/images/brand/langchain-docs-teal.svg",
     "dark": "/images/brand/langchain-docs-lilac.svg",
-    "href": "https://docs.langchain.com/langgraph-platform"
+    "href": "https://docs.langchain.com/oss/python"
   },
   "favicon": {
     "light": "/images/brand/favicon.svg",
     "dark": "/images/brand/favicon-dark-mode.svg"
   },
   "fonts": {
     "heading": {
-      "family": "Manrope"
+      "family": "Inter"
     }
   },
   "styling": {

src/hide-version-picker.js

@@ -28,6 +28,7 @@
                 button.classList.add('version-picker-button');
             }
         });
+
     }
 
     // Run immediately

src/index.mdx

@@ -8,7 +8,7 @@ mode: "wide"
 
 # Frameworks
 
-<CardGroup cols={3}>
+<CardGroup cols={2}>
   <Card
     title="LangChain - Python"
     href="https://python.langchain.com/docs/introduction/"
@@ -25,7 +25,7 @@ mode: "wide"
 
   <Card
     title="LangGraph"
-    href="/oss"
+    href="/oss/python"
   >
   Low-level orchestration framework for building, managing, and deploying long-running, stateful agents.
   </Card>

src/oss/1-build-basic-chatbot.mdx

@@ -3,6 +3,9 @@ title: 1. Build a basic chatbot
 ---
 
 import ChatModelTabs from '/snippets/chat-model-tabs.mdx';
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
 
 In this tutorial, you will build a basic chatbot. This chatbot is the basis for the following series of tutorials where you will progressively add more sophisticated capabilities, and be introduced to key LangGraph concepts along the way. Let's dive in! 🌟
 

src/oss/2-add-tools.mdx

@@ -2,6 +2,11 @@
 title: 2. Add tools
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 import chatTabs from '/snippets/chat-model-tabs.mdx';
 
 To handle queries that your chatbot can't answer "from memory", integrate a web search tool. The chatbot can use this tool to find relevant information and provide better responses.

src/oss/3-add-memory.mdx

@@ -2,6 +2,11 @@
 title: 3. Add memory
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 import chatTabs from '/snippets/chat-model-tabs.mdx';
 
 The chatbot can now [use tools](/oss/2-add-tools) to answer user questions, but it does not remember the context of previous interactions. This limits its ability to have coherent, multi-turn conversations.

src/oss/4-human-in-the-loop.mdx

@@ -2,6 +2,11 @@
 title: 4. Add human-in-the-loop controls
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 import chatTabs from '/snippets/chat-model-tabs.mdx';
 
 Agents can be unreliable and may need human input to successfully accomplish tasks. Similarly, for some actions, you may want to require human approval before running to ensure that everything is running as intended.

src/oss/5-customize-state.mdx

@@ -2,6 +2,11 @@
 title: 5. Customize state
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 import chatTabs from '/snippets/chat-model-tabs.mdx';
 
 In this tutorial, you will add additional fields to the state to define complex behavior without relying on the message list. The chatbot will use its search tool to find specific information and forward them to a human for review.

src/oss/6-time-travel.mdx

@@ -2,6 +2,11 @@
 title: 6. Time travel
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 import chatTabs from '/snippets/chat-model-tabs.mdx';
 
 In a typical chatbot workflow, the user interacts with the bot one or more times to accomplish a task. [Memory](/oss/3-add-memory) and a [human-in-the-loop](/oss/4-human-in-the-loop) enable checkpoints in the graph state and control future responses.

src/oss/GRAPH_RECURSION_LIMIT.mdx

@@ -1,6 +1,11 @@
 ---
 title: GRAPH_RECURSION_LIMIT
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 Your LangGraph [`StateGraph`](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.state.StateGraph) reached the maximum number of steps before hitting a stop condition.
 This is often due to an infinite loop caused by code like the example below:
 

src/oss/INVALID_CHAT_HISTORY.mdx

@@ -1,6 +1,11 @@
 ---
 title: INVALID_CHAT_HISTORY
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 :::python
 This error is raised in the prebuilt @[create_react_agent][create_react_agent] when the `call_model` graph node receives a malformed list of messages. Specifically, it is malformed when there are `AIMessages` with `tool_calls` (LLM requesting to call a tool) that do not have a corresponding `ToolMessage` (result of a tool invocation to return to the LLM).
 :::

src/oss/INVALID_CONCURRENT_GRAPH_UPDATE.mdx

@@ -1,6 +1,11 @@
 ---
 title: INVALID_CONCURRENT_GRAPH_UPDATE
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 A LangGraph [`StateGraph`](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.state.StateGraph) received concurrent updates to its state from multiple nodes to a state property that doesn't
 support it.
 

src/oss/INVALID_GRAPH_NODE_RETURN_VALUE.mdx

@@ -1,6 +1,11 @@
 ---
 title: INVALID_GRAPH_NODE_RETURN_VALUE
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 :::python
 A LangGraph [`StateGraph`](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.state.StateGraph)
 received a non-dict return type from a node. Here's an example:

src/oss/MULTIPLE_SUBGRAPHS.mdx

@@ -1,6 +1,11 @@
 ---
 title: MULTIPLE_SUBGRAPHS
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 You are calling subgraphs multiple times within a single LangGraph node with checkpointing enabled for each subgraph.
 
 This is currently not allowed due to internal restrictions on how checkpoint namespacing for subgraphs works.

src/oss/add-human-in-the-loop.mdx

@@ -2,6 +2,11 @@
 title: Enable human intervention
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 To review, edit, and approve tool calls in an agent or workflow, use interrupts to pause a graph and wait for human input. Interrupts use LangGraph's [persistence](/oss/persistence) layer, which saves the graph state, to indefinitely pause graph execution until you resume.
 
 <Info>

src/oss/add-memory.mdx

@@ -1,6 +1,11 @@
 ---
 title: Add and manage memory
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 AI applications need [memory](/oss/memory) to share context across multiple interactions. In LangGraph, you can add two types of memory:
 
 * [Add short-term memory](#add-short-term-memory) as a part of your agent's [state](/oss/graph-api#state) to enable multi-turn conversations.

src/oss/agent-supervisor.mdx

@@ -2,6 +2,11 @@
 title: Build a multi-agent supervisor
 sidebarTitle: Multi-agent supervisor
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 [**Supervisor**](/oss/multi-agent#supervisor) is a multi-agent architecture where **specialized** agents are coordinated by a central **supervisor agent**. The supervisor agent controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements.
 
 In this tutorial, you will build a supervisor system with two agents — a research and a math expert. By the end of the tutorial you will:

src/oss/agentic-architectures.mdx

@@ -3,6 +3,11 @@ title: Common architectures
 sidebarTitle: Overview
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 This guide reviews common patterns for agentic systems. In describing these systems, it can be useful to make a distinction between **workflows** and **agents**: 
 
 - A **workflow** is a predefined sequence of steps or processes that execute in a structured, often linear fashion.

src/oss/agentic-rag.mdx

@@ -2,6 +2,11 @@
 title: Build a RAG agent
 sidebarTitle: Agentic RAG
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 In this tutorial we will build a [retrieval agent](https://python.langchain.com/docs/tutorials/qa_chat_history). Retrieval agents are useful when you want an LLM to make a decision about whether to retrieve context from a vectorstore or respond to the user directly.
 
 By the end of the tutorial we will have done the following:

src/oss/application-structure.mdx

@@ -2,6 +2,11 @@
 title: Application Structure
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 ## Overview
 
 A LangGraph application consists of one or more graphs, a configuration file (`langgraph.json`), a file that specifies dependencies, and an optional `.env` file that specifies environment variables.

src/oss/call-tools.mdx

@@ -1,6 +1,11 @@
 ---
 title: Call tools
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 [Tools](/oss/tools) encapsulate a callable function and its input schema. These can be passed to compatible chat models, allowing the model to decide whether to invoke a tool and determine the appropriate arguments.
 
 You can [define your own tools](#define-a-tool) or use [prebuilt tools](#prebuilt-tools)

src/oss/case-studies.mdx

@@ -1,6 +1,11 @@
 ---
 title: Case studies
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 This list of companies using LangGraph and their success stories is compiled from public sources. If your company uses LangGraph, we'd love for you to share your story and add it to the list. You’re also welcome to contribute updates based on publicly available information from other companies, such as blog posts or press releases.
 
 | Company | Industry | Use case | Reference |

src/oss/common-errors.mdx

@@ -3,6 +3,11 @@ title: Error troubleshooting
 sidebarTitle: Overview
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 This page contains guides around resolving common errors you may find while building with LangGraph.
 Errors referenced below will have an `lc_error_code` property corresponding to one of the below codes when they are thrown in code.
 

src/oss/community-agents.mdx

@@ -1,3 +1,7 @@
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 [//]: # (This file is automatically generated using a script in docs/_scripts. Do not edit this file directly!)
 ---
 title: Community Agents

src/oss/context.mdx

@@ -1,6 +1,11 @@
 ---
 title: Context overview
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 **Context engineering** is the practice of building dynamic systems that provide the right information and tools, in the right format, so that an AI application can accomplish a task. Context can be characterized along two key dimensions:
 
 1. By **mutability**:

src/oss/durable-execution.mdx

@@ -2,6 +2,11 @@
 title: Durable execution
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 **Durable execution** is a technique in which a process or workflow saves its progress at key points, allowing it to pause and later resume exactly where it left off. This is particularly useful in scenarios that require [human-in-the-loop](/oss/human-in-the-loop), where users can inspect, validate, or modify the process before continuing, and in long-running tasks that might encounter interruptions or errors (e.g., calls to an LLM timing out). By preserving completed work, durable execution enables a process to resume without reprocessing previous steps -- even after a significant delay (e.g., a week later).
 
 LangGraph's built-in [persistence](/oss/persistence) layer provides durable execution for workflows, ensuring that the state of each execution step is saved to a durable store. This capability guarantees that if a workflow is interrupted -- whether by a system failure or for [human-in-the-loop](/oss/human-in-the-loop) interactions -- it can be resumed from its last recorded state.

src/oss/evals.mdx

@@ -2,6 +2,11 @@
 title: Evaluate agent performance
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 To evaluate your agent's performance you can use `LangSmith` [evaluations](https://docs.smith.langchain.com/evaluation). You would need to first define an evaluator function to judge the results from an agent, such as final outputs or trajectory. Depending on your evaluation technique, this may or may not involve a reference output:
 
 :::python

src/oss/functional-api.mdx

@@ -3,6 +3,11 @@ title: Functional API overview
 sidebarTitle: Overview
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 The **Functional API** allows you to add LangGraph's key features — [persistence](/oss/persistence), [memory](/oss/add-memory), [human-in-the-loop](/oss/human-in-the-loop), and [streaming](/oss/streaming) — to your applications with minimal changes to your existing code.
 
 It is designed to integrate these features into existing code that may use standard language primitives for branching and control flow, such as `if` statements, `for` loops, and function calls. Unlike many data orchestration frameworks that require restructuring code into an explicit pipeline or DAG, the Functional API allows you to incorporate these capabilities without enforcing a rigid execution model.

src/oss/graph-api.mdx

@@ -3,6 +3,11 @@ title: Graph API concepts
 sidebarTitle: Overview
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 ## Graphs
 
 At its core, LangGraph models agent workflows as graphs. You define the behavior of your agents using three key components:

src/oss/human-in-the-loop.mdx

@@ -3,6 +3,11 @@ title: Human-in-the-loop overview
 sidebarTitle: Overview
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 To review, edit, and approve tool calls in an agent or workflow, [use LangGraph's human-in-the-loop features](/oss/add-human-in-the-loop) to enable human intervention at any point in a workflow. This is especially useful in large language model (LLM)-driven applications where model output may require validation, correction, or additional context.
 
 

src/oss/local-server.mdx

@@ -2,6 +2,11 @@
 title: Run a local server
 ---
 
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
+
 This guide shows you how to run a LangGraph application locally.
 
 ## Prerequisites

src/oss/mcp.mdx

@@ -2,6 +2,11 @@
 title: MCP overview
 sidebarTitle: Overview
 ---
+
+import V1Alpha from '/snippets/v1-alpha.mdx';
+
+<V1Alpha />
+
 [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open protocol that standardizes how applications provide tools and context to language models. LangGraph agents can use tools defined on MCP servers through the `langchain-mcp-adapters` library.
 
 ![MCP](/oss/images/mcp.png)