Allocating the 200K Context Window in Claude API — Budgeting System, Tools, Memory, and History in Production
Treat Claude API's 200K context as a budget rather than an open shelf. A TypeScript-backed allocation architecture that carves system, tools, memory, history, and headroom into explicit envelopes — built and tuned in a wallpaper app earning real ad revenue.
Why tool_result could not be submitted Keeps Coming Back, and How to Build a Recovery Handler That Actually Holds
Run a Claude agent long enough and one day it starts: 'tool_result could not be submitted', back to back, and retries change nothing. The error message hides four completely different root causes. Here is what I learned debugging it on the always-on agent jobs I run as an indie developer, with the TypeScript recovery handler I now ship in production.
Forecasting Claude API token costs with ±10% accuracy from the first three days
A practical EWMA + seasonality decomposition model that forecasts month-end Claude API costs from only the first three days of token usage, with three-tier automated guardrails for prompt caching, model routing, and rate limiting.
Resolving Tool Name Collisions When Bundling Multiple MCP Servers in the Claude Agent SDK
When the GitHub MCP and Linear MCP both expose create_issue, Sonnet 4.6 cannot tell them apart. This article covers the structure of MCP tool name collisions, a TypeScript reconciler implementation, and a measured correction: the schemaHash I originally published missed all five schema drifts I tested it against.
Compressing Tool Results in Claude Agents — Aggregating Large Responses Without Bloating Context
When a database returns 8,000 rows, a scrape returns 200KB of HTML, or a file read returns several megabytes, dropping the raw payload into your Claude tool result wrecks both cost and quality. This guide presents a three-layer compression architecture — schema projection, summarization, and reference handles — with TypeScript examples from a production agent pipeline.
Hierarchical Chat History Summarization with Claude API: A 3-Tier Design That Cut Tokens by 70%
Working TypeScript design for compressing long in-app chat histories into three tiers — recent turns kept verbatim, mid-range episodes summarized with Haiku 4.5, and long-range memory distilled to JSON by Sonnet 4.6. Includes seven weeks of production data showing input tokens down 70% and monthly API cost down from $480 to $145.
Installing Safety Valves in Claude Agents: A Three-Layer Kill-Switch Design for Solo Operators
A design record from a real production incident — three hours of runaway retries that cost $32 — that led me to rebuild every Claude agent with a three-layer kill switch: in-process guards, platform-level kill flags on Cloudflare KV, and an observer worker that catches the warning signs within three minutes. Working TypeScript and operational metrics included.
What metadata.user_id in the Claude API Is Actually For — Designing the Abuse-Detection vs. Privacy Trade-off
The metadata.user_id field in the Messages API exists to sharpen abuse detection, but sending raw email addresses creates a privacy problem. Here is the HMAC-based stable pseudo-ID pattern I use, plus a clear set of rules for when to send it and when not to.
Bulletproof JSON Output with Claude API Prefill: A Four-Layer Defense Pattern from Indie SaaS
How I went from late-night JSON parse failures to a 99.98% parse success rate across thousands of monthly Claude API requests, and what a 1,081-sample truncation benchmark revealed about the repair code I had originally published here.
A Five-Layer Preflight Design for Claude API — How I Cut Hundreds of 400/422/529 Errors to Zero
A production-tested five-layer preflight design that catches Claude API failures before the network call — schema, token budget, model capability, content policy, and spend cap — with full TypeScript implementation and one month of operational numbers.
Implementing the Saga Pattern in Claude Agent SDK — Compensating Transactions and Idempotency
A practical guide to building safe multi-step Claude Agent SDK workflows. We cover compensating transactions, idempotency keys, and partial-failure state recovery, all from patterns that have run in production.
Implementing the Transactional Outbox Pattern with Claude Agent SDK — Eliminating Lost Side Effects in Production
Stop the 'the row was inserted but the email never went out' class of bugs in Claude Agent SDK apps. A production-grade walkthrough of the Transactional Outbox pattern using Postgres and Cloudflare Queues.