◉CLAUDE LABJP
●SUNSET — The legacy Workbench retires today, August 17: saved prompts, prompt versions, and evals become inaccessible after that, so exporting is a today-or-never job●API — The experimental prompt tool endpoints generate_prompt, improve_prompt, and templatize_prompt retire the same day and will return errors, so any script calling them needs switching over today●CONSOLE — The replacement Workbench is stateless: nothing is stored on Anthropic's servers, your draft stays in the browser, and any request can be exported as code●OSS — Claude for Open Source now grants six months of Claude Max 20x to qualifying maintainers, capped at 10,000 people, individual only, with no API credits and no auto-renewal●QUOTA — The 50 percent weekly usage boost for Claude Code subscribers runs through August 19, two days out●SELF-HOSTED — Self-hosted environments for Claude Code are in public beta, letting Team and Enterprise plans run sessions on their own infrastructure with internal network access and custom tooling●SUNSET — The legacy Workbench retires today, August 17: saved prompts, prompt versions, and evals become inaccessible after that, so exporting is a today-or-never job●API — The experimental prompt tool endpoints generate_prompt, improve_prompt, and templatize_prompt retire the same day and will return errors, so any script calling them needs switching over today●CONSOLE — The replacement Workbench is stateless: nothing is stored on Anthropic's servers, your draft stays in the browser, and any request can be exported as code●OSS — Claude for Open Source now grants six months of Claude Max 20x to qualifying maintainers, capped at 10,000 people, individual only, with no API credits and no auto-renewal●QUOTA — The 50 percent weekly usage boost for Claude Code subscribers runs through August 19, two days out●SELF-HOSTED — Self-hosted environments for Claude Code are in public beta, letting Team and Enterprise plans run sessions on their own infrastructure with internal network access and custom tooling
TAG

Contract Testing

2 articles
← Back to all tags
Related:
MCP1Claude API1Unattended Runs1TypeScript1Claude Code1Refactoring1Observability1Regression Detection1
⬡ API & SDK/2026-07-08Advanced

Contract-Test Every Tool Before You Submit or Automate an MCP Connector

A connector that works once in a chat can still break silently in an unattended job through misread response shapes or double-fired writes. Here is a small harness that machine-checks tool descriptions, response contracts, idempotency, and latency, with measured numbers.

⟐ Claude Code/2026-07-03Advanced

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.