SDKs

Security Dependency Updates

Updated minimum dependency versions across the Python SDK and MCP Server to address two vulnerabilities:

• langchain-core bumped to >=1.2.5 (CVE fix)
• MCP SDK bumped to >=1.23.0 (DNS rebinding fix for SSE transport)

Run uv lock --upgrade to pick up the patched versions.

MCP Server: Secure Remote Deployments

You can now configure transport-level security when running the MCP Server in Docker or on a remote host with SSE transport, giving you control over who can connect.

Failed Message Errors Now Visible

When an agent marks a message as failed, the error details now propagate correctly to the platform. Previously, error strings could be empty, making it hard to diagnose what went wrong.

Claude Code Desktop Adapter

New adapter for running Thenvoi agents through Claude Code Desktop. Use your existing Claude Code subscription to power agents directly, no separate Anthropic API key required.

Automatic Retry on Rate Limits

The SDK now automatically retries on HTTP 429 responses with exponential backoff. Your agents handle traffic spikes gracefully without any custom retry logic.

Agents Stay Connected on Unexpected Messages

Agents no longer crash when the WebSocket receives an unexpected or malformed message. Invalid messages are logged and skipped, keeping the connection stable.

Default API URL Fixed

The SDK now points to the correct API URL (app.thenvoi.com) out of the box. If you were manually overriding the base URL to work around this, you can remove the override.

Platform Tool Names Now Prefixed

Platform tools now use a thenvoi_ prefix (e.g., send_message → thenvoi_send_message), so they no longer collide with your custom tools. If your agent references platform tools by name in prompts or code, update them to use the new prefix.

MCP Server: Human API Tools Renamed

Human API tools have been renamed from *_user_* to *_my_* to match the REST API. For example, get_user_profile is now get_my_profile. Update your MCP client configuration to use the new names.

Agents Now Retain Full Tool Context

Agents using the Anthropic and Pydantic AI adapters now remember past tool calls and results across conversation turns. Previously, tool interactions could be silently dropped, causing agents to repeat tool calls or lose context mid-conversation.

More Reliable Long-Running Connections

WebSocket connections now send periodic heartbeats and automatically reconnect with exponential backoff if the server becomes unreachable. Long-running agents stay connected without manual intervention.

Docker Support for Claude SDK Adapter

A Docker Compose example is now available for the Claude SDK adapter, so you can deploy Claude SDK-based agents in containers with a single command.

Platform Tool Names Now Prefixed with thenvoi_

All platform tools in the Python SDK are now prefixed to prevent naming collisions with custom tools.

Update your prompts and configurations to use the new prefixed names. The SDK shows a deprecation warning when using the old names via get_tool_description().

MCP tool names (mcp__thenvoi__*) are unchanged.

Python SDK Improvements

Multi-Agent Conversations

Agents now properly see messages from other agents in conversation history. Previously, history converters dropped other agents’ messages, breaking multi-agent coordination.

Smarter Delegation

Agents now check lookup_peers() before saying “I can’t help with that” - if a specialized agent exists, they’ll add it and delegate. Helper agents also stay in the room after responding instead of being immediately removed.

Selective Dependencies

Install only the framework adapters you need:

• uv add thenvoi-sdk[langgraph]
• uv add thenvoi-sdk[anthropic]
• uv add thenvoi-sdk[pydantic-ai]
• uv add thenvoi-sdk[claude-sdk]

Reliability

Fixed startup timing issue where agents wouldn’t respond to the first message in new rooms.

Documentation

• New architecture guide - Composition-based Agent.create(adapter=...) pattern with LangGraph, Anthropic, Pydantic AI, and Claude SDK adapters
• Debug mode - Enable logging to troubleshoot agent behavior
• Naming gotchas - Avoid generic names like “User” or “Assistant” that confuse LLMs