claude-code - 💡(How to fix) Fix Max plan 1M context window not used — compaction triggers at 200K [3 comments, 4 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#46998Fetched 2026-04-13 05:44:12
View on GitHub
Comments
3
Participants
4
Timeline
7
Reactions
0
Timeline (top)
commented ×3labeled ×3subscribed ×1

On the Max subscription plan, Claude Code compacts conversation context at ~200K tokens instead of using the advertised 1M token context window for Opus 4.6.

Root Cause

On the Max subscription plan, Claude Code compacts conversation context at ~200K tokens instead of using the advertised 1M token context window for Opus 4.6.

Fix Action

Workaround

None known. There is no user-facing configuration to set the context window size or compaction threshold.

RAW_BUFFERClick to expand / collapse

Description

On the Max subscription plan, Claude Code compacts conversation context at ~200K tokens instead of using the advertised 1M token context window for Opus 4.6.

Environment

  • Plan: Max (1M context window)
  • Model: Claude Opus 4.6 (claude-opus-4-6)
  • Claude Code: CLI (latest)
  • OS: macOS (Darwin 24.6.0)

Expected behavior

With the Max plan, the context window should be 1M tokens. Compaction should trigger near that limit, not at 200K.

Actual behavior

Compaction triggers at approximately 200K tokens — the default context window size for Opus 4.6 on non-Max plans. The status line also reports (200K) as the total context capacity, confirming that Claude Code does not recognize the extended 1M limit.

Steps to reproduce

  1. Subscribe to Max plan
  2. Start a Claude Code session with opus model
  3. Work on a large task that fills context past ~180-200K tokens
  4. Observe automatic compaction at ~200K instead of continuing to 1M

Additional context

  • No compaction-related settings exist in ~/.claude/settings.json or project settings
  • No environment variables (CLAUDE_AUTOCOMPACT_*) are set
  • The status line (read-only display) shows (200K) as total capacity, suggesting Claude Code itself reports 200K regardless of subscription tier
  • This means Max plan users are paying for 1M context but only getting 200K in Claude Code

Workaround

None known. There is no user-facing configuration to set the context window size or compaction threshold.

extent analysis

TL;DR

The issue can be resolved by ensuring Claude Code recognizes the Max subscription plan's 1M token context window, potentially through a configuration update or a fix in the Claude Code CLI.

Guidance

  • Verify that the Max plan subscription is correctly applied and recognized by Claude Code, as the reported behavior suggests it's using the default 200K token context window.
  • Check for any potential updates to the Claude Code CLI that may address this issue, as the latest version is being used.
  • Investigate if there are any hidden or undocumented settings in ~/.claude/settings.json or environment variables that could override the default context window size.
  • Consider reaching out to the Claude Code support team to report this issue and request assistance, as it appears to be a bug or misconfiguration on their end.

Example

No code snippet is provided as this issue seems to be related to configuration or a bug in the Claude Code CLI rather than a coding error.

Notes

The issue seems to be specific to the Max plan and the Claude Opus 4.6 model, so any solution or workaround may need to take these specifics into account. Without further information from the Claude Code team or documentation, it's challenging to provide a definitive fix.

Recommendation

Apply a workaround is not feasible at this point, so the recommendation is to wait for an update or fix from the Claude Code team that correctly implements the 1M token context window for Max plan subscribers.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

With the Max plan, the context window should be 1M tokens. Compaction should trigger near that limit, not at 200K.

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix Max plan 1M context window not used — compaction triggers at 200K [3 comments, 4 participants]