When Memory Store Listings Returned Half the Rows: Migrating to agent-memory-2026-07-22
agent-memory-2026-07-22 changed memories.list: fixed ordering, stricter depth, segment-based path_prefix matching. How an audit quietly halved, an access layer that survives it, and measured depth=1 traversal cost.
When Prompt Caching Was On but the Bill Didn't Move — Field Notes on Instrumenting cache_read to Close the Hit-Rate Gap
You added cache_control but your Claude API bill barely changed. Before guessing at fixes, record cache_read and cache_creation on every request and split the hit-rate gap into three causes: non-deterministic prefixes, TTL expiry, and sub-threshold blocks.
A Two-Stage Pre-Publish Gate for User-Facing AI Text in Consumer Apps
Design a two-stage pre-publish gate for short AI-generated text you ship to end users: a deterministic rule layer plus a Claude classifier, with fail-closed handling, generation-time vetting, and a cost model. Full implementation code included.
A Long Non-Streaming Response Was Billed Twice Past the 10-Minute Wall: Redesigning the SDK's Default Timeout and Retries
The Anthropic SDK's default 10-minute timeout and two automatic retries can silently re-run a long non-streaming response and bill you twice. Here is how the trap works, and how to close it with streaming, explicit timeout/max_retries, and a small local ledger — with measured before/after numbers.
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 Claude API Prompt Caching Quietly Stops Hitting in Production — Field Notes on TTL and Measured Savings
Prompt caching works beautifully the day you ship it, then quietly stops hitting in production. The five things that break the prefix, how to choose between 5-minute and 1-hour TTL, and how to measure real savings from usage instead of guessing.
Drop Your Static Claude API Keys: Moving CI and Production to Keyless Auth with Workload Identity Federation
Workload Identity Federation is now generally available on the Claude Platform. This guide walks through replacing long-lived sk-ant- keys with short-lived OIDC tokens, including keyless GitHub Actions auth, the migration steps, and token refresh design.
Putting a Ceiling on the pause_turn Loop: Running Long Server Tools Safely Unattended
A production design for continuing pause_turn safely in unattended runs, where long server tools like web_search and code execution are involved. Covers branching all four stop_reason values in one loop, capping continuations and wall-clock time, and accumulating usage across paused segments.
Connecting Managed Agents to Services You Don't Want to Expose: MCP Tunnel Design
How to connect Claude Managed Agents to an internal MCP server that is never exposed to the public internet. We cover the MCP tunnel, self-hosted sandboxes, authorization boundaries, and graceful degradation when things break.
Fixing Claude Code's 'Credit balance is too low' Error
You launch Claude Code and it immediately stops with 'Credit balance is too low' — even though you have an active subscription. The error looks like a money problem, but it is almost always a mismatch in which auth path is billing you. Here is how to tell them apart and fix it: switching auth routes, topping up credits, and setting auto-reload.
Catching Claude Quality Regressions With an Eval Harness
I tweaked a prompt by one line and, for a different set of inputs, the output quietly got worse. Here is the eval harness I built to protect Claude's production quality across every prompt change and model update, with full implementation code and real operating numbers.
Absorbing Claude API 529 Overloaded in Production — Resilience Patterns from a 50M-Download Indie Studio
529 Overloaded won't go away with a naive exponential backoff. Drawing on lessons from 50 million app downloads, this piece walks through queue-based absorption, model-aware fallback, and circuit-breaker design with working code.