The article shows how modern inference APIs embed provider-only state—encrypted reasoning tokens, hidden searches, server-side compaction, and stored response IDs—making AI sessions nonportable. It proposes five tests (inspection, export, replay, audit, deletion) to verify true session ownership and warns that encrypted or ID-based state breaks continuity across providers.

Anthropic investigated user reports of degraded performance in Claude Code, the Agent SDK, and Cowork, and traced them to three separate changes: a lowered default reasoning effort, a bug that cleared session context on every turn after idle, and a prompt tweak to limit verbosity. All issues were reverted or fixed by April 20 (v2.1.116), and Anthropic is adding stricter testing, broader internal dogfooding, and more targeted evals to prevent similar regressions.