Feature request: when we reach the token limit and waiting for a token limit reset, provide an option to allow continue working with the cheaper model haiku.

Related Claude Code issues

Matched on shared title terms, labels, topic and reported release — ranked so issues with real discussion come first.

• [FEATURE] Add `compactionModel` config to use a cheaper model during auto-compaction
  Resolved 💬 2 #38358
• [FEATURE] Add compactModel setting to use cheaper model for /compact
  Resolved 💬 2 #12660
• [FEATURE] Auto-continue after the limit is reset
  Resolved 💬 3 #18980
• can you please auto-compact and continue please - without waiting for user to hit /compact. In this specific case, I don't know what to do.
  Resolved 💬 5 #13867
• [Question] Why were internal Haiku model calls removed from main process in v2.1.63?
  Resolved 💬 4 v2.1.63 #29550
• [FEATURE] auto-compact with Haiku
  Resolved 💬 3 #10548
• [BUG] after rate limit reset it does not automatically continue
  Resolved 💬 2 v2.1.73 #33523
• [BUG] when session context reach 100%,no auto compact
  Resolved 💬 1 v2.1.162 #65334

Browse by topic

Same class of failure, ranked by community engagement — this issue is one of many, so it may not appear in the visible list: Context window & memory limits

Browse all Claude Code issue topics →