博客

Announcement

OpenAI Protocol Support Is Live — Codex CLI, OpenAI SDK, LiteLLM All Work Now

LLM API now exposes OpenAI-compatible endpoints (/v1/chat/completions and /v1/responses) alongside the existing Anthropic /v1/messages. One API key, both protocols. Includes Codex CLI 0.130 setup walkthrough.

2026-05-15 6

Yazhou Hu

Engineering Notes

Reasoning Blocks at the Relay: What Changes When the Upstream Emits Thinking

Open-weight reasoning models (DeepSeek V3.x, MiniMax M-series, Qwen3 reasoning) now ship interleaved thinking blocks. Notes on translating that to Claude Code's Anthropic-protocol contract — block ordering, signature handling, tool-use interleaving, and SSE shape.

2026-05-06 10

Yazhou Hu

Engineering Notes

A 15-Second CPU Stall From One Unclosed XML Tag

Postmortem on a relay process that pegged a single core for fifteen seconds straight. Catastrophic regex backtracking on user-controlled input. Three-character fix, three-layer defense (bounded quantifier + per-request watchdog + nginx next_upstream).

2026-05-06 9

Yazhou Hu

Engineering Notes

Tool-Use IDs in the Wild: When the Same ID Appears Twice

Long Claude Code sessions sometimes produced duplicate `tool_use_id` values from the upstream model. Naive fixes break round-trip correlation; the working answer is occurrence-counter dedup with two-direction translation. With diagnostic dumps for the cases that still slip.

2026-05-06 8

Yazhou Hu

Engineering

Why Claude Code Sessions Break Past 400K Tokens — And the Self-Audit Pattern That Fixes It

Long Claude Code conversations degrade past ~400K tokens: fabricated paths, skipped TODOs, contradicted decisions. The naive fix (open a new window) fails because self-summaries lie. Here is the self-audit pattern that catches the lying — and the open-source skill that automates it.

2026-04-24 9

Yazhou Hu

Troubleshooting

Fix Claude Code 429 "Rate Limit Exceeded": Complete Triage Guide

Step-by-step triage for Claude Code 429 errors. Learn the three types of rate limits, how to read headers, short-term workarounds, and the structural fix via a multi-provider relay.

2026-04-23 9

Yazhou Hu

Guide

Running Claude Code from China: A Practical 2026 Guide

Real options for running Claude Code productively from mainland China: VPN tradeoffs, domestic-accessible relays, self-hosted proxies, and a 60-second setup with Alipay/WeChat billing.

2026-04-23 10

Yazhou Hu

Guide

Claude Code Tool Use: A Complete Developer Guide

Deep dive into Claude Code's six core tools (Read, Edit, Write, Bash, Grep, Glob), how the model decides which tool to call, parallel tool calls, and how to debug when tool use fails.

2026-04-23 11

Yazhou Hu

Guide

Claude Code on a Budget: A Solo Developer Starter Guide

How to run Claude Code for free or under $5/month as a solo developer. Free tier tactics, when to upgrade, model selection, and the 2026 solo dev stack.

2026-04-23 9

Yazhou Hu

Guide

How to Use Claude Code Without Paying $200/Month

Learn how to use Claude Code without the expensive Max subscription. Free and cheap alternatives that give you the same agentic coding experience for under $15/month.

2026-04-11 8

Yazhou Hu

Comparison

Claude Code vs Cursor vs GitHub Copilot: Which AI Coding Tool is Best in 2026?

In-depth comparison of Claude Code, Cursor, and GitHub Copilot in 2026. Features, pricing, performance benchmarks, and which tool fits your workflow best.

2026-04-10 10

Yazhou Hu

Tutorial

Claude Code API Key: Complete Guide to Setup and Configuration

Step-by-step guide to getting and configuring your API key for Claude Code. Covers Anthropic keys, third-party providers, environment variables, and troubleshooting common errors.

2026-04-09 7

Yazhou Hu

Tutorial

Claude Code with Alternative Models — Complete Setup Guide

How to use Claude Code with alternative models like Qwen, DeepSeek, and Gemini. Why DIY proxy setups fail and how LLM API gives you a turnkey solution in 2 minutes.

2026-04-08 8

Yazhou Hu

Guide

Claude Code Rate Limits Explained: How to Avoid Getting Throttled

Understand Claude Code rate limits, what causes 429 errors, and practical solutions to avoid getting throttled. Covers Anthropic limits, Pro/Max plan caps, and alternative providers.

2026-04-08 8

Yazhou Hu

Guide

Claude Code for Teams: Scaling AI Coding Without Breaking the Budget

How engineering teams can adopt Claude Code at scale without $200/developer/month costs. Team plans, shared API keys, usage monitoring, and budget-friendly deployment strategies.

2026-04-07 9

Yazhou Hu

Guide

Claude Code Cost Optimization: 5 Strategies to Cut Your AI Coding Bills

Practical strategies to reduce Claude Code API costs from $500+/month to under $50, including compatible API providers, usage optimization, and smart model routing.

2026-04-06 10

Yazhou Hu

Comparison

Claude Code Alternatives in 2026: Comprehensive Comparison (Gemini CLI, Aider, OpenCode)

Detailed comparison of Claude Code alternatives including Gemini CLI, Aider, OpenCode, and compatible API providers. Benchmarks, pricing, and real-world experience.

2026-04-04 12

Yazhou Hu

Comparison

AI Coding Model Quality Comparison: What Powers Your Claude Code?

How do alternative coding models compare to Claude Sonnet 4.7? Benchmarks, tool calling accuracy, and why you should let your provider handle model selection.

2026-04-02 7

Yazhou Hu

Guide

Self-Hosted Claude Code Proxy vs Managed Service: Which Should You Choose?

Why self-hosting LiteLLM or claude-code-router for Claude Code leads to endless maintenance. Real failure stories and why a managed service like LLM API saves time and money.

2026-03-28 6

Yazhou Hu