CodeAgent

A repository called aattaran/deepclaude hit Hacker News front page 13 hours after launch, accumulating 498 points and 608 stars. The pitch is simple: keep Claude Code’s client exactly as-is, swap the backend from Anthropic to DeepSeek V4 Pro and V4 Flash, and claim a 17x cost reduction. But the real engineering meat isn’t in the 4-line export statement. It’s in proxy/model-proxy.js — a local service running on port 3200 that routes by path: /v1/messages gets rewritten to use a DeepSeek key and forward to api.deepseek.com, while everything else carries the Anthropic OAuth token through to api.anthropic.com. This layer solves the authentication collision problem where the bridge tunnel credentials and model inference credentials fight each other, all while the client remains completely unaware. ...

Recap: The Cache Mismatch Problem In our previous post, we explained why pairing OpenCode / ClaudeCode with DeepSeek destroys your cache hit rate: DeepSeek uses strict full-prefix matching — a cache hit only fires when every byte from position 0 is identical to the previous request. Agent loops insert tool messages in the middle of the message array, breaking the prefix hash every turn. Anthropic-style cache_control segment markers are silently ignored. Result: near-zero cache hit rate, even though DeepSeek’s billing dashboard shows caching is “enabled.” The problem is not DeepSeek. The problem is that generic agent frameworks were designed for a fundamentally different caching mechanic. ...

The Problem Nobody Talks About Every engineering team I’ve talked to in the past six months shares the same frustration: AI coding assistants are great, until you look at the bill. Let me give you a concrete example. We ran a React development task through a standard AI assistant setup. The task: implement a feature with proper error handling. The result? 20 minutes and 50,300 tokens consumed. For a single feature. In production, this compounds fast—multiplied across a team of ten engineers running dozens of sessions daily, you’re looking at serious API costs bleeding into your compute budget. ...

Introduction DeepSeek’s disk-based automatic context caching is famous for near 90% input token savings: cached prefix tokens cost just a tiny fraction of standard input pricing, with zero manual configuration required. Thousands of developers switch to DeepSeek chasing this aggressive discount for long system prompts, code rules, and repeated tool definitions. But a costly reality hits teams running ClaudeCode / OpenCode (code agent runtimes built for Anthropic-style cache_control) against the DeepSeek API: ...