Claude Code + Codex Plugin: Two AI Brains, One Terminal
How to use OpenAI's Codex plugin inside Claude Code — turning Claude Opus and GPT-5.4 into a dual-brain coding system. Setup, commands, rescue workflows, and when each brain wins.
Read More[ Blog_Posts ]
Claude Code Deep Dive Part 4: Why It Uses Markdown Files Instead of Vector DBs
Claude Code's memory system looks simple on purpose. This piece breaks down the tradeoffs behind Markdown memories, Sonnet side-queries, and the decision to avoid vector databases.
Read MoreClaude Code Deep Dive Part 3: The 5-Level Compression Pipeline Behind 1M Tokens
Claude Code doesn't just stuff conversations into a 1M-token window. It uses a 5-level compression pipeline, cache-aware edits, and a final autocompact fallback to keep sessions alive.
Read MoreClaude Code Deep Dive Part 2: The 1,421-Line While Loop That Runs Everything
Inside query.ts — the 1,729-line async generator that is Claude Code's beating heart. 10 steps per iteration, 9 continue points, 4-stage compression, and streaming tool execution. With line numbers.
Read MoreObservability and Billing for AI API Calls: A T-Shaped Architecture
AI API calls are unlike ordinary RPC: per-request cost varies 100×, tokens and models are first-class, streaming muddies timing, caching changes the pricing. A T-shaped instrumentation architecture — shared stem, specialized arms — that handles tracing, billing, and cost analytics without any of them contaminating the others.
Read MoreClaude Code's Memory Is Simpler Than You Think — And That's a Problem
I read the leaked source code. Claude Code's memory system is just Markdown files + an LLM picker. No vector search, no embeddings, no RAG. Here's why that matters.
Read MoreClaude Code Source Leaked: 5 Hidden Features Found in 510K Lines of Code
Claude Code v2.1.88 accidentally exposed its entire source. We found hidden pets, undercover mode, permanent memory, and more.
Read MoreConsistency in Distributed Systems: Scenarios, Trade-offs, and What Actually Works
Strong, eventual, causal, read-your-writes, linearizable — consistency models are taught as a taxonomy. Production uses them as a menu. Ten scenarios, the right consistency choice for each, and the engineering that makes the choice work.
Read MoreThe AI Stack Explained: LLM Talks, Program Walks
A first-principles breakdown of the entire AI stack — from LLM to Agent in one mental model. An LLM can only output text. Everything else is the program.
Read MoregRPC Interceptors in Production: Design Patterns That Survive Real Load
gRPC interceptors are where cross-cutting concerns live — auth, tracing, retry, metrics, rate limiting. Most examples online show toy single-interceptor demos. Production systems need to stack, order, and compose them correctly. A practical guide.
Read More