The Connection That Dies Mid-Thought Is Being Killed by Your Relay, Not the Upstream
Put a proxy or Worker in front of Claude Code and long thinking pauses start dying. The cause is neither the model nor the upstream — it is your relay holding the byte stream. Six relay behaviors compared side by side, plus how to verify yours before it ships.
6 Traps I Hit Building In-App AI Chat with Claude API — A Record of Getting to Production
Six real design mistakes I encountered shipping Claude API in-app chat to production — covering context management, streaming error detection, guardrails, session persistence, model versioning, and cost monitoring. Includes working TypeScript code.
Combining Haiku 4.5, Streaming, and Prompt Caching to Cut Costs in a Personal App — An Implementation Record
A hands-on record of combining Claude Haiku 4.5, streaming, and prompt caching to improve both cost and response speed in a personal iOS/Android app — including the mistakes made along the way.
Claude API on Bun in Production: Migration Decisions and Implementation Patterns That Actually Survive Real Traffic
A practical guide to running Claude API services on Bun in production. Covers migration triggers from Node.js, built-in SQLite/WebSocket usage, streaming optimization, and the pitfalls that only surface after deployment — with working code and measured numbers.
Building a Scalable Real-Time AI Chat Server with Claude API × WebSocket × Redis Pub/Sub — Node.js Production Architecture, Multi-User Management, and Cost Control
Running a real-time AI chat server on Claude API, WebSocket, and Redis Pub/Sub in production. SSE trade-offs, multi-instance routing, and how stop latency quietly corrupts per-user budgets — with the instrumentation code to measure it.
Shipping Generative UI on Claude API: A Production Pattern for Streaming Dynamic Components with Tool Use and JSON Schema
Combine Claude's Tool Use, JSON Schema, and partial JSON streaming to render AI-assembled UI components safely. We cover registry design, type-safety, fallback, and the pitfalls you only learn after running this in production.
Building an AI Chatbot with Claude API — Streaming, Conversation History & Cost Optimization
A record of building a chatbot on the Claude API from a minimal script upward: conversation history, streaming, a FastAPI endpoint, cost trimming, LINE/Telegram/Discord, and PII masking. The retry logic was rebuilt around measured jitter and the retry-after header.
How Many Concurrent Claude API Requests Can You Actually Hold? Sizing Production Infrastructure with Little's Law and Measured Memory
Concurrency, queue depth, and memory are numbers you can derive, not guess. A working method for sizing Claude API production deployments with Little's Law, a memory probe, and a 30-minute load check — learned the hard way from an OOM crash.
Measure Streaming CPU and Dropped Chunks to Stabilize Long Batch Jobs
You start an overnight batch, and by morning only half of it finished. The culprits were CPU pinned during streaming and a quiet connection drop. Here is a monitor wrapper that measures stream CPU and throughput, and resumes from interruptions.
When You Fan Out Streaming Sessions, Your Laptop's CPU Gives Out First — An Adaptive Throttle That Caps Concurrency by Measured Load
Even with lighter streaming, fanning out many sessions on one machine saturates the host CPU before anything else. Here is why a fixed semaphore fails, plus a working adaptive gate that raises and lowers concurrency from measured CPU.
When Claude API Streaming Stops Without an Error: Detecting Silent Stalls and Resuming Mid-Stream
How to catch the 'silent stall' where Claude API streaming stops with no exception at all, using a content-level watchdog that times the gap between tokens, plus a resume path that carries received text forward as an assistant prefill, and a four-layer timeout budget for long-running automation.
When Thinking Is Always On, Prefill Quietly Stops Working — Fixing Streaming and Token Budgets for Fable 5
Fable 5 thinks by default. Prefill no longer applies, the first streamed block isn't text, and max_tokens has to leave room for reasoning. Here is how I fixed those three broken assumptions in my own automated publishing pipeline.