All Articles
When a Claude Code Refactor Passes Every Test but Behaves Differently in Production — Catching Silent Contract Drift with a Behavior Diff Harness
Hand Claude Code a large refactor and your tests can stay green while production behavior quietly shifts. Here is how I record exception channels, log shape, init order, and return values as a signature, then diff them per commit to catch contract drift before it ships.
A 40% Lower Price Doesn't Mean a 40% Lower Bill — Measuring the Opus 4.8 to Sonnet 5 Migration by Cost per Completed Task
Sonnet 5's intro pricing looks ~40% cheaper than Opus 4.8, yet extra tool turns can flip the math. Working TypeScript for consumption vectors, a paired-run harness, and break-even turn counts.
Which Model Ran Last Night's Unattended Session? Building Model Attribution and Default-Drift Detection After the Sonnet 5 Switch
Claude Code's default model switched to Sonnet 5, and unpinned headless runs changed models silently. Here is a working design for extracting the actual model from run output, appending an atomic run record, and deciding per task lineage whether to pin or follow the default.
Introductory Pricing Has an End Date — Effective-Dated Cost Forecasts for the Sonnet 5 Price Step
Claude Sonnet 5's introductory $2/$10 pricing ends on 2026-08-31 and reverts to $3/$15. A static price map will quietly understate your September forecast by a third. Here is an effective-dated price table and forecast design that absorbs the step.
When 41 of 20,000 Message Batches Requests Quietly Vanished — Field Notes on Reconciling and Requeuing Partial Failures
processing_status: ended does not mean every request succeeded. How errored and expired results hide inside a finished batch, and how a custom_id ledger catches every gap and requeues safely — with real cost and timing numbers.
Your Cache Hit Rate Resets to Zero the Morning You Switch Models — Prompt Cache Rewarm Design for the Opus 4.8 to Sonnet 5 Cutover
Prompt caches are scoped per model, so day one of a model migration starts at a 0% hit rate. Why percentage-based rollouts break cache economics twice over, and how cohort cutover by task family preserves them — with working measurement code.
How Many Tasks Fire in the Same Minute — Flattening Cowork Scheduled-Task Collisions from Cron
When Cowork scheduled tasks bunch up at the same time and fight over shared resources, you can expand every cron expression into fire times, count collisions and true concurrency, and shave the peak with a greedy offset that never moves your premium slots. With working code and measured before/after numbers.
Let the Downstream Task Verify the Upstream Actually Ran Today: A Completion Ledger and Dependency Barrier for Unattended Schedulers
Unattended schedulers have no notion of dependencies, so when a morning data-refresh task fails silently, the noon generation task keeps running on yesterday's leftovers. This is a design for recording upstream completion atomically and having downstream assert its preconditions before running, with working TypeScript and lessons from my own operations.
Don't Accept an Agent's Numbers and Citations As-Is — A Verification Gate Built on a Dedicated Auditor Subagent
A design that verifies every number and citation in an agent-generated summary using a separate subagent before accepting it — with working TypeScript for deterministic recomputation and fail-closed source matching.
When the Model Survives but One Parameter Expires: A Dated Deprecation Calendar for Claude API Requests
Your model ID can stay valid while a parameter you pinned quietly reaches its sunset date and takes the batch down with it. Here is a design that breaks a request into parts, gives each part its own expiry date, and catches the problem before the call goes out — with working TypeScript and real operational numbers.
My Claude Code Hooks Stopped Firing After an Update — the Hyphenated Matcher Exact-Match Change in v2.1.195
In Claude Code v2.1.195, hook matchers containing a hyphen switched from partial match to exact match, silently disabling an existing PreToolUse hook. Here is how I isolated the cause and how to write matchers that won't break.
When Claude API Document Extraction Is Confidently Wrong — Field Notes on Catching Silent Errors with Invariants
In structured extraction from invoices and contracts, the real danger isn't a crash — it's a value that's silently wrong while the schema validates and confidence reads high. Field notes on invariants, two-pass extraction, and tracking field-level error rates.