Anthropic Unveils Claude Code Session Tools for 1M Token Context

Anthropic dropped a brand new /utilization command for Claude Code on April 15, alongside detailed steerage on managing periods inside the AI coding assistant’s a million token context window. The replace addresses a rising ache level builders have flagged: determining when to proceed, compact, or nuke a session solely.

The corporate’s technical employees member Thariq Shihipar laid out the logic in a weblog submit that reads extra like tribal information than typical documentation. The core downside? Context rot—the place mannequin efficiency degrades as extra tokens pile up and a spotlight will get unfold skinny throughout irrelevant cruft.

5 Methods to Deal with Context Bloat

Claude Code now affords builders a call tree at each flip:

Proceed works when every part within the window nonetheless issues. /rewind (or double-tap Esc) helps you to bounce again to any earlier message and reprompt, dropping every part after that time. Anthropic suggests this beats the intuition to sort “that did not work, attempt X as an alternative”—as an alternative, rewind to only after helpful file reads and provides cleaner directions.

/compact asks Claude to summarize the session and exchange historical past with that abstract. It is lossy however automated. You may steer it: “/compact concentrate on the auth refactor, drop the check debugging.” The catch? Autocompact fires when context is almost full, exactly when the mannequin performs worst resulting from context rot.

/clear places you in management. You write what issues and begin contemporary. Extra work, cleaner slate.

Subagents deal with the messiest situation—when the subsequent chunk of labor will generate tons of intermediate output you will not want once more. Spawning a subagent provides it a contemporary context window; solely the ultimate report comes again to the mum or dad session.

The Psychological Mannequin

Anthropic’s inner check: “Will I want this instrument output once more, or simply the conclusion?” If simply the conclusion, spin up a subagent for codebase searches, verification runs, or doc writing.

The steerage suggests beginning contemporary periods for genuinely new duties, though 1M context technically permits marathon periods. For associated follow-up work—like documenting a characteristic you simply constructed—staying in session avoids costly file rereads.

Unhealthy autocompacts sometimes occur when Claude cannot predict the place your work is heading. An extended debugging session will get summarized, then you definitely ask about “that different warning in bar.ts” that obtained dropped from the abstract. With the bigger context window, Anthropic recommends proactive /compact with specific path earlier than the automated set off fires.

The replace displays Anthropic’s push to make Claude Code extra sensible for prolonged improvement periods. Whether or not this strikes the needle on enterprise adoption stays to be seen, however builders burning by context on complicated codebases lastly have documented methods past trial and error.

Picture supply: Shutterstock