Add LangChain agent example connecting to ToolHive vMCP

User Story

As a ToolHive user attempting to build my own agent service with LangChain, I have no
reference implementation showing how to securely connect a LangChain agent to MCP
servers managed by ToolHive. Without this, I have to figure out the integration from
scratch.

Description

Create a self-contained LangChain agent example in the toolhive repository that
demonstrates connecting to a ToolHive-managed vMCP endpoint with Okta OIDC auth. This
should show users a realistic, runnable path for building LangChain agents on top of
ToolHive's MCP infrastructure.

Requirements

1. Create examples/agents/langchain/ directory with a runnable Python example
2. Demonstrate how to initiate the SSO flow from the agent service to authenticate to a vMCP
3. Show the agent invoking at least one MCP tool through the vMCP
4. Include a README.md with prerequisites, setup steps, and how to run
5. Keep dependencies minimal and pinned

Acceptance Criteria

• Example is checked into examples/agents/langchain/ in the toolhive repo
• A user can follow the README and run the example against their own vMCP
• The example demonstrates successful tool invocation through the vMCP
• The SSO flow is initiated from within the agent service
• README explains what each part of the code is doing

Start by locating the ToolHive vMCP endpoint and Okta OIDC authentication entry points, then create the runnable Python example under examples/agents/langchain/. Add examples/agents/langchain/README.md with prerequisites, pinned dependencies, setup, and explanation; done means a user can run the example, complete SSO, and invoke an MCP tool through their vMCP.