/ Claude Code v2.1.122

The --autocompact flag string now appears in the codebase, suggesting auto-compaction may be controllable as a CLI flag in the future. The implementation appears to be connected to existing compaction infrastructure with CLAUDE_AUTOCOMPACT_PCT_OVERRIDE and CLAUDE_CODE_BLOCKING_LIMIT_OVERRIDE environment variables.
The loopAutoEnabled user setting has been removed. If you relied on this setting, it no longer has any effect.
The Opus 4.7 image resolution limit change from 2576px to 2000px may affect workflows that rely on high-resolution image analysis.

The build it came inv2.1.122

28 Apr 2026 · 32 entries, this one is #32.

Either side of it

Open the release →

Names in this entry

cli--autocompact
Set the auto-compact window for this session without changing your saved settings. Accepts the same values as /autocompact; that section covers the value forms and what overrides the flag. Requires Claude Code v2.1.221 or later
envCLAUDE_AUTOCOMPACT_PCT_OVERRIDE
Set the percentage (1-100) of the auto-compact window at which auto-compaction triggers. Use lower values like 50 to compact earlier; the variable can't raise the threshold, so values above the default percentage are ignored. It applies only in sessions that compact before the model's context limit. Applies to both main conversations and subagents
envCLAUDE_CODE_BLOCKING_LIMIT_OVERRIDE
Token count, used when it parses to a number greater than 0. It replaces the context blocking limit, which is otherwise the model's context window less a per-model reserve of up to 20000 tokens and a further 3000. When the estimated conversation size reaches the limit and the turn was not compacted, Claude Code can end the turn with a Prompt is too long error instead of sending the request.

Is this right?