It is probably not just you, but I would be careful about blaming the 1M context window specifically.

Anthropic’s recent postmortem described several Claude Code regressions around default reasoning effort, context/thinking retention, and a system prompt change to reduce verbosity. Those seem more likely to explain the “less careful / forgetful / worse follow-through” behavior than the context window alone.

I would compare the same task in a fresh session, with the effort setting fixed, and ideally against a few repeatable tasks from your own codebase. Otherwise it is very hard to tell whether the regression is the model, Claude Code’s harness, context management, or just a stale session.