When Your Claude API Response Cache Returns Stale Answers and Near-Miss Wrong Ones — Field Notes on Freshness and False-Hit Suppression
A Claude API response cache improves latency and cost immediately, but the problems that hurt in production are not average hit rate — they are stale hits and semantic false hits. Here is the key design, freshness management, false-hit suppression, and observability that keep a cache honest.
Keeping Large Claude Code Refactors Revertible One Commit at a Time — Field Notes on Checkpoints and Rollback Detection
Hand a big refactor to Claude Code and the speed hides a real cost: review-proof, oversized diffs. Here are the field notes I actually run — declaring checkpoints in a manifest, enforcing commit granularity with a pre-push hook, and tying rollback calls to observability.
PII Masking for Claude API Lives or Dies on the Ledger — Restore, Encrypt, Measure
The hard part of masking PII before Claude API isn't detection — it's operating the token ledger you restore from. Encrypted storage, multi-instance sharing, and a daily leak-rate loop, with working code.
On the day the billing change took effect, I added per-stage cost metering to my headless runs
The June 15 billing change moved headless runs and agent delegation onto monthly credits. Here is a thin metering layer that records token usage per stage tag from response.usage and emits a daily cost report, with working code.
Make Agent Failures Reproducible: Deterministic Replay and Event Sourcing
An autonomous agent that fails at 2 a.m. can't be reproduced by simply running it again. Record every nondeterminism boundary as an append-only event log and replay the failed run deterministically — with working code and operational lessons.
Rewiring Claude API Observability with OpenTelemetry GenAI Conventions — A Design Memo for Model Migrations and Cost Audits
An implementation memo for rewiring production observability around Claude API to match the OpenTelemetry GenAI semantic conventions — span attributes, metrics, cost tracking, and model-migration replay — written from running this in indie services for six months.
Claude API Telemetry on ClickHouse: A Production Guide to Cost, Latency, and Error Analytics
Stream per-request Claude API telemetry into ClickHouse, build sub-second dashboards with materialized views, and detect cost spikes, retry loops, and silent failures with practical SQL recipes.
Building a Production Claude API Pipeline on Cloudflare Queues: Fault Tolerance, Backpressure, and Cost Control
A practical, code-first walkthrough for routing Claude API calls through Cloudflare Queues — covering producer/consumer code, retry-vs-DLQ branching, priority lanes, and token budgeting for production workloads.
Observability for Claude Code with OpenTelemetry — A Production-Grade Tracing Guide for Agentic Workflows
Trace Claude Code agent runs end to end with OpenTelemetry. Hook integration, per-tool spans, MCP propagation, cost attribution, and sampling patterns that survive thousands of runs per day.
Production Semantic Cache for Claude API — Similarity Thresholds, Pollution Defense, and What to Track
A production playbook for adding a semantic cache in front of Claude API — threshold tuning, multi-tenant isolation, pollution prevention, fallbacks, and the metrics that actually prove it works.
Production Infrastructure for Claude API — 8 Things You Need Between 'It Works' and 'It Holds Up'
There is a much bigger gap than you'd think between a working Claude API call on your laptop and a service that survives real users. Here are the eight pieces of infrastructure I now consider non-negotiable, learned the hard way.
Debugging Claude Code Hooks in Production — Where to Start When Logs Are Missing
Your Claude Code hooks work locally but go silent in production. Here is the three-layer observability pattern I use on real projects, plus a 60-second minimal reproduction recipe for isolating failures.