Fix Claude Code qwen3.8-max Warning: Remove 200k Token Limit & Model Catalog Error
20 days ago 高效码农How to Fix the “qwen3.8-max isn’t described by this version’s model catalog” Warning in Claude Code CLI If you run non-standard, custom, or self-hosted LLM endpoints (such as qwen3.8-max routed through a proxy or an OpenAI-compatible gateway) inside Claude Code CLI, your terminal will throw a long, persistent warning on startup: “qwen3.8-max” isn’t described by this version’s model catalog; update Claude Code, or map it with behavesAs on a modelPicker row (or modelOverrides, if it is a provider id of a model this version knows). Until then auto-compact keeps this session within 200k tokens… This warning triggers because Claude …
DeepSeek Harness Troubleshooting: How I Fixed the ‘deployment:persona already registered’ Error
1 months ago 高效码农DeepSeek Harness Error deployment:persona already registered: A Real-World Troubleshooting Journey from Reinstallation to .dsh Profile Conflicts Most DeepSeek Harness installation issues tend to revolve around model providers, API authentication, MCP connections, or tool integrations. This one was different. The error looked like a simple configuration problem at first glance: internal: resume failed for session “session-3836a0e6-9fe9-40d7-884e-876b3ebba209” Error: agent-presets: preset “standard” failed to mount failed to apply loader entry persona (@deepseek-ai/dsh-persona): prompt section “deployment:persona” is already registered The natural assumption is that a Persona configuration was duplicated somewhere inside the preset configuration. After several rounds of investigation, the root cause turned out …
Stop Just Reviewing Diffs: An Evidence-Based Approach to Evaluating AI Coding Agent Workflows
1 months ago 高效码农Better Hands-On Guide: How to Review AI Coding Agent Workflows with Evidence Reviewing Diffs is Not Enough: How to Evaluate AI Coding Agent Workflows AI coding agents write code quickly, but the workflows surrounding them are often fragile. If you only review the final code diff, you miss systemic issues. Better Harness is an open-source tool that analyzes the workflow behind the changes, gathers project and session evidence, and translates specific gaps into prioritized improvements. It focuses the analysis on a closed loop of feedforward guidance and feedback sensors. Feedforward guidance includes AGENTS.md, specs, and acceptance criteria. Feedback sensors include …
Magika AI File Detection: Stop Guessing File Types – Google’s Open-Source Tool Is 99% Accurate
2 months ago 高效码农Stop Guessing File Types: Google’s Magika Uses AI to Identify Files Accurately Ever received a file with no extension? Or extracted a batch of .dat files from an old system and had no idea what’s inside? You try opening it with a text editor – garbled mess. You run the system file command – vague answer. Then you start dragging it into different applications, hoping one of them will open it. Minutes turn into hours. Google has open‑sourced a tool called Magika that solves exactly this problem. It uses a deep‑learning model to detect file types – not by looking …
Gemini API Managed Agents Just Got Free Tier, Budget Controls, and Cron Triggers – Here’s What That Means for You
2 months ago 高效码农Gemini API Managed Agents Just Got Free Tier, Budget Controls, and Cron Triggers – Here’s What That Means for You If you’ve been following the Gemini API’s managed agents (the ones that run in an isolated sandbox with code execution, file management, and network access), you probably had two reactions: “this is incredibly useful” and “how do I keep costs under control?” Google just addressed both. The latest updates – free tier availability, budget guardrails, and scheduled triggers – turn managed agents from a powerful but slightly risky tool into something you can actually deploy without holding your breath. I’ve …
CodeX Reconnecting 5/5? Fix WebSocket Issues with This Simple HTTP Config Twea
2 months ago 高效码农CodeX Stuck on “Reconnecting 5/5”? Stop Blaming the Model—Here’s How to Skip WebSocket and Go Straight to HTTP You ask CodeX to change one line of code. Instead of editing, it spends 30 seconds showing “Reconnecting 1/5 … 5/5”, then “Thinking…” for a while longer. You stare at the terminal: is it deep in reasoning, or just stalling? It’s neither. The model hasn’t even started. The network layer is busy retrying a path that won’t work—five times, back to back—before it finally falls back to a working connection. Your internet speed isn’t the problem. The culprit is your proxy, …
How to Install Hermes Agent on Windows: Complete Troubleshooting Guide for Common Errors
3 months ago 高效码农How to Install Hermes Agent on Windows: A Complete Troubleshooting Guide Hermes Agent is an open-source AI agent framework built by Nous Research. It supports multiple inference backends — including OpenAI, Anthropic, and Ollama — and is designed to run locally on your machine. On paper, the installation is straightforward. In practice, Windows users regularly hit a handful of the same walls: GitHub timeouts, PowerShell script restrictions, and large binary downloads that stall or 404. This guide walks through the full installation process on Windows, explains why each error happens, and gives you a working fix for each one. If …
Codex AI Engineering Agent: Complete Hands-On Guide from Installation to Real-World Projects
3 months ago 高效码农Codex Orange Paper: A Complete Hands-On Guide from Installation to Real-World Projects This is not a product review. It’s a practical walkthrough based on real project experience. Before We Start This article is distilled from an unofficial open‑source guide to Codex. I’ve stripped out the fluff and kept only what actually helps you get work done. It’s written for two groups of people: Complete beginners who have never used an AI coding tool but want to start – you’ve probably heard that ChatGPT can write code, but you don’t know how to bring it into your real project. Experienced users …
AI Agents Group Chat: How I Made Claude, Codex, CodeBuddy, and Grok Collaborate Automatically
3 months ago 高效码农I Shoved Claude, Codex, CodeBuddy, and Grok Into a Group Chat. Here’s What Happened. How I went from being a human USB cable between four AI terminals to sipping tea while they argue, code, and review each other’s work. My desktop has been occupied by four black terminal windows for far too long. Claude Code on the left. Codex on the right. CodeBuddy down below. And recently, Grok squeezed its way in. Each AI sits in its own window, separated by mere pixels on my screen. But for me, those pixels felt like an uncrossable chasm. My old workflow was …
Open Code Review: The Open Source AI Tool That Finally Makes Code Reviews Reliable
3 months ago 高效码农Tired of Unreliable AI Code Reviews? Try This Open Source Tool from Alibaba Have you ever found that during team code reviews, some basic mistakes keep slipping through? Or when you ask a general-purpose AI coding assistant to review your code, it either skips half the files, reports issues with wrong line numbers, or gives inconsistent results every time? If you’ve used tools like Claude Code for code review, you’ve probably run into these problems. When the changeset is large, the AI tends to take shortcuts and only looks at a subset of files. The line numbers in its comments …
Fix Dify MCP Server 403 Forbidden Error: SSRF Proxy Blocking SSE Connection
3 months ago 高效码农How to Fix Dify MCP Server 403 Forbidden Error (SSE Connection Failed) TL;DR: If Dify throws httpx.ProxyError: 403 Forbidden when connecting to an MCP Server, the request is being blocked by Dify’s built-in SSRF protection proxy (Squid). The fix is to whitelist your MCP Server’s address in squid.conf and restart the proxy container. The Problem When adding an MCP tool provider in the Dify console, you may encounter the following error in your API container logs: api-1 | ERROR [sse_client.py:300] – Error connecting to SSE endpoint … httpcore.ProxyError: 403 Forbidden The above exception was the direct cause of the following …
Tavily Search Integration Guide for Cherry Studio: Fix Connection Closed Errors and Enable Real-Time Web Search
4 months ago 高效码农From “Connection Closed” to “Active Green”: The Definitive Guide to Integrating Tavily Search in Cherry Studio Abstract: Local LLM clients often suffer from connection crashes (such as the -32000 Connection closed error) when invoking web search capabilities, typically triggered by environment conflicts in multi-version Node.js setups or incorrect npm package names. By precisely refactoring local executable paths, correcting official package identifiers, or pivoting to a highly efficient remote Server-Sent Events (SSE) protocol, you can completely eliminate this friction and empower your large language models with flawless, real-time web retrieval capabilities. 1. Why Does Your LLM Client’s Web Search Constantly Fail …
OpenHuman Memory Trees Show 0 buffer(s): Why Local Vault Sync Can’t Build Summary Trees (Complete Guide)
4 months ago 高效码农Why OpenHuman Memory Trees Show 0 buffer(s): A Complete Troubleshooting Guide from Vault Sync to Summary Tree ❝ 「Core question this article answers:」 Why does OpenHuman show Building summary trees · 0 buffer(s) even after files have synced successfully? ❞ Here is the short answer: 「If you only added a local Vault (such as Markdown or TXT files), OpenHuman may show synced successfully but still fail to build a memory tree. In the observed workflow, Summary Trees only work with supported data sources like Gmail, Slack, and Notion. Local Vault files sync successfully, but they do not automatically enter the …
OpenAI Codex: From Coding Tool to Enterprise Work Platform Transforming Knowledge Workers
4 months ago 高效码农From Coding Tool to Enterprise Work Platform: How OpenAI Codex Is Changing the Daily Work of Knowledge Workers 5M weekly active users | 40% of new users are non-developers | AI agents are redefining “work” On June 3, 2026, OpenAI held a live event titled “Intelligence at Work,” announcing three major upgrades to its AI coding agent, Codex: role‑specific plugins, Sites, and Annotations. OpenAI also revealed that Codex’s core capabilities will be integrated directly into the ChatGPT app in the coming weeks—giving nearly 1 billion users worldwide a single interface for both conversational thinking and hands‑on execution. Codex started as …
Claude Opus 4.8 Dynamic Workflows: How AI Solves Massive Engineering Tasks at Scale
4 months ago 高效码农Claude Opus 4.8 and Dynamic Workflows: How AI Actually Solves Large‑Scale Engineering Tasks Core question this article answers: What makes Claude Opus 4.8 better than the previous generation? What kinds of huge tasks can dynamic workflows handle? And how can you, as a developer or tech lead, start using these capabilities today? Anthropic just released Claude Opus 4.8 – a new version with noticeable improvements in honesty, judgment, and autonomous work. Alongside it, Claude Code introduces dynamic workflows, which let Claude orchestrate tens to hundreds of parallel sub‑agents and finish complex engineering tasks in days that used to take a …
Claude Code Automation: Turn Your AI Chat Tool Into an Autonomous Developer
4 months ago 高效码农From Chat Tool to Automated Employee: A Complete Guide to Claude Code Article cover image You open your terminal, type a command, and the AI responds with code. You say “format it,” and it does. You say “run the tests,” and it does. A month later, you’re still repeating the same conversation. The problem isn’t the AI. The problem is you don’t know what it can do on its own. A lot of people think they’re programming with AI, but they’re really just chatting. The people who really know how to use it have already started letting the AI work …
OpenHuman AI Agent Review: Persistent Memory That Actually Knows You
4 months ago 高效码农OpenHuman: The Personal AI Agent That Actually Knows You In a world flooded with AI agents and frameworks—AutoGPT, CrewAI, LangGraph, OpenClaw, Hermes, Claude-based tools, and more—most promise autonomy but deliver stateless chatbots with fragile context. They forget you the moment the conversation ends. Enter OpenHuman, an open-source desktop AI assistant from TinyHumans AI that flips the script: it’s built as your persistent memory and proactive doer, deeply integrated into your digital life. The Core Problem with Most AI Agents Today’s popular agent frameworks excel at specific tasks: CrewAI and AutoGen shine in multi-agent collaboration and role-based workflows but often require …
OpenClaw 2026.5.12-beta.3: Granular Tool Permissions, Smoother Channel Integrations, and a Cleaner Plugin SDK
4 months ago 高效码农OpenClaw 2026.5.12-beta.3 Release: Finer Tool Permissions, Smoother Channel Integrations, and a Cleaner Plugin SDK We have just released OpenClaw 2026.5.12-beta.3. This update focuses on three main areas: granular per‑sender tool policies, stability and feature enhancements for mainstream messaging channels (Slack, iMessage, Discord), and plugin SDK clean‑up with better developer experience. There are also several practical improvements like automatic Gemini model ID migration, cron job inspection by ID, and session context visualisation. Whether you are a daily user, a self‑hosting operator, or someone building plugins on top of OpenClaw, this release brings valuable changes. 1. Gateway and LLM Providers: API‑Friendly Token …
DeepSeek TUI: The Complete 2026 Guide to Your 1-Million-Token Terminal Coding Agent
5 months ago 高效码农DeepSeek TUI Complete Guide: Running a 1 Million Token Coding Agent Inside Your Terminal Imagine this: you’re deep in a refactoring session inside your terminal. You suddenly need to analyze a dozen log files while cross-referencing API documentation from three different versions. What if an assistant could read files directly from your workspace, execute shell commands, search the web, and manage Git—without you ever taking your hands off the keyboard? DeepSeek TUI is exactly that kind of terminal-native coding partner. It’s not a browser plug-in, nor a web app that needs a separate runtime. It’s a single Rust binary. If your …
Fix Claude Code Installation on Windows: From npm Errors to Official Native Method
5 months ago 高效码农Troubleshooting Claude Code Installation on Windows: From npm Errors to the Official Native Method You were probably excited to try out Anthropic’s Claude Code assistant on your Windows machine. You opened your terminal, typed npm install -g @anthropic-ai/claude-code, and hit Enter. Instead of a success message, you were greeted with a frustrating cascade of red error text, including something like link … ENOENT and perhaps a username in a non-Latin script. Don’t worry. You haven’t done anything wrong, and you’re not alone. This guide will walk you through exactly why these standard-looking installation steps fail, provide you with verified, clear …