How-Tos & Practical Guides

If you’re running a production MCP server with sticky sessions, a shared session store, or Mcp-Session-Id header handling — pay attention. The MCP 2026-07-28 release candidate is the largest revision to the protocol since its launch, and the headline change is a breaking one: sessions are gone entirely. The final specification ships July 28, 2026. If you haven’t started preparing your MCP server implementations, you have less than a month. ...

Tencent just made a significant move in the open-weights AI race. The full Hunyuan Hy3 model is officially live — and after months of preview builds, the final release is everything the preview promised and more. What Is Hy3? Hy3 is a 295B total parameter Mixture-of-Experts (MoE) model from the Tencent Hy Team. MoE means not all those parameters are active at once: only 21B parameters activate per token, plus a 3.8B MTP (Multi-Token Prediction) layer. The result is a model with frontier-class capability but substantially lower compute costs than dense 295B models. ...

Claude Code v2.1.200 shipped a breaking change that caught a lot of automated workflows by surprise: the default permission mode is now Manual. If you had scripts, CI jobs, or headless agent pipelines relying on the old default behavior — where Claude would proceed without explicit permission approval — those workflows may now be stalling waiting for input that never comes. This guide covers exactly what changed, what it means for your setup, and how to update your configuration so automated workflows keep running. ...

If you’ve used Claude Code’s background agents before v2.1.198, you know the rhythm: kick off a task in the Agent View, let it run in the background, and then check back periodically to see if it’s waiting for you to review changes or commit them. Starting with v2.1.198, that last step is gone. Background agents now automatically commit their work, push it to a branch, and open a draft pull request when a coding task completes — no prompt, no hand-holding, no manual step required. ...

With the release of OpenClaw 2026.7.1-beta.2, ClawRouter ships as a bundled provider plugin — meaning it’s available to every OpenClaw installation without a separate install step. If you’ve been manually managing multiple LLM provider credentials and routing logic, this is worth understanding. This guide explains what ClawRouter is, how its routing model works, and how to think about using it for multi-model agentic deployments. For the exact configuration syntax and CLI flags, always refer to the official ClawRouter README — some specifics will vary by OpenClaw version. ...

Building an AI agent is one thing. Getting it into production — containerized, evaluated, CI/CD’d, and running on scalable infrastructure — is a whole other problem. Google just made that second part significantly easier with Agents CLI v1.0, which reached General Availability on July 1, 2026. This guide walks through what Agents CLI does, how the v1.0 workflow is structured, and how to use it to go from a scaffolded agent project to a deployed Cloud Run service. All commands and configuration patterns described below are sourced from the official Google Agents CLI documentation and GitHub repository. ...

Imagine giving your web app the ability to understand and execute natural language commands like “fill out this form,” “click the login button,” or “navigate me to checkout” — without a Python backend, without Selenium, and without any screenshots going over the wire. That’s exactly what Alibaba’s newly open-sourced PageAgent delivers. Released under the MIT license, PageAgent is a pure JavaScript/TypeScript GUI agent that lives directly inside your webpage. It’s not a browser automation framework that drives a browser from the outside — it is the page, reading the live DOM and acting within it in response to natural language. This guide walks through how it works and how to get started. ...

Claude Fable 5’s Safety Classifiers: A Field Guide to the Opus 4.8 Fallback After 19 days of unavailability due to export control review, Claude Fable 5 was redeployed on July 1, 2026, with a significant architectural addition: upgraded safety classifiers that detect when an agent loop is handling cybersecurity or biological topics and route those tasks to Claude Opus 4.8 instead. For most general-purpose applications, you’ll never encounter this. For operators building security agents, penetration testing assistants, threat intelligence tools, or any application touching biological research — it’s a core operational reality you need to understand. ...

Protecting Your Agent Sessions: Claude Code Workspace Isolation Best Practices On July 4, a GitHub issue filed against the Claude Code repository — issue #74066, “[Bug] Potential session/cache leakage between workspace instances or consumer accounts” — trended to #1 on Hacker News with 54+ points within its first hour. As of this writing, Anthropic has not confirmed the bug. But here’s what’s not in dispute: Claude Code has had prior documented session isolation issues. GitHub issue #29342 documented cross-session transcript leakage where entries were written to the wrong JSONL file. That issue was resolved, but the pattern of cross-session contamination is now a twice-appearing vulnerability class. ...

ZCode for Enterprise: Data Sovereignty Checklist Before Switching from Claude Code or Cursor Z.ai just launched ZCode as a genuinely compelling free alternative to Cursor and Claude Code. It’s powered by GLM-5.2’s 1M context window, ships on macOS, Windows, and Linux, includes a multi-agent “Goal Mode,” mobile bot control, and a plugin architecture — all at zero cost for the daily free quota tier. For individual developers, it’s hard to argue with the price. ...