Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix Subscriber usage impact of 2.1.117 Opus 4.7 auto-compact threshold change not documented [1 comments, 1 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#52519•Fetched 2026-04-24 06:05:02
View on GitHub
Comments
1
Participants
1
Timeline
7
Reactions
1
Author
ericjreganericjregan
Participants
ericjreganericjregan
Timeline (top)
labeled ×3cross-referenced ×2closed ×1commented ×1

Claude Code 2.1.117 changed the auto-compact threshold for Opus 4.7 sessions from ~200K tokens to ~1M tokens. This is listed in the changelog as a bug fix:

Fixed Opus 4.7 sessions showing inflated /context percentages and autocompacting too early — Claude Code was computing against a 200K context window instead of Opus 4.7's native 1M.

However, this change has a significant subscriber impact that does not appear to have been communicated:

Because every turn re-sends the entire conversation context, letting sessions grow 5x larger before compacting results in up to 5x the tokens shipped per turn on Opus 4.7. For Pro/Max/Team subscribers whose quotas were implicitly sized around the prior compact-at-200K behavior, this is effectively a 5x reduction in how many turns a subscription can sustain per 5-hour window.

Root Cause

Because every turn re-sends the entire conversation context, letting sessions grow 5x larger before compacting results in up to 5x the tokens shipped per turn on Opus 4.7. For Pro/Max/Team subscribers whose quotas were implicitly sized around the prior compact-at-200K behavior, this is effectively a 5x reduction in how many turns a subscription can sustain per 5-hour window.

Fix Action

Workaround

```bash

Downgrade to last release before the change

(native installer — adjust for your platform)

ln -sf ~/.local/share/claude/versions/2.1.116 ~/.local/bin/claude export DISABLE_AUTOUPDATER=1 # add to shell rc ```

RAW_BUFFERClick to expand / collapse

Summary

Claude Code 2.1.117 changed the auto-compact threshold for Opus 4.7 sessions from ~200K tokens to ~1M tokens. This is listed in the changelog as a bug fix:

Fixed Opus 4.7 sessions showing inflated /context percentages and autocompacting too early — Claude Code was computing against a 200K context window instead of Opus 4.7's native 1M.

However, this change has a significant subscriber impact that does not appear to have been communicated:

Because every turn re-sends the entire conversation context, letting sessions grow 5x larger before compacting results in up to 5x the tokens shipped per turn on Opus 4.7. For Pro/Max/Team subscribers whose quotas were implicitly sized around the prior compact-at-200K behavior, this is effectively a 5x reduction in how many turns a subscription can sustain per 5-hour window.

Observed impact

Within 24 hours of 2.1.118 releasing (inheriting the 2.1.117 change), on an unchanged workflow:

  • Exhausted 93% of a 5-hour Max session limit during a ~40-minute research-only session (zero code written)
  • Cache-write volume was abnormally high: 207k cache writes / 386k cache reads for a session with only a handful of user turns
  • Both a Max 20x individual plan and a Premium Team plan were exhausted on the same day

Prior to 2.1.117, similar daily workloads used a small fraction of the same limits.

Compounding change in same release

2.1.117 also changed:

Default effort for Pro/Max subscribers on Opus 4.6 and Sonnet 4.6 is now high (was medium)

Which also increases per-turn token consumption.

Requested

  1. Acknowledge in release notes when platform changes materially affect subscriber quota consumption
  2. Consider notifying subscribers proactively when auto-compact thresholds or default effort change
  3. Confirm that downgrading to 2.1.116 + DISABLE_AUTOUPDATER=1 is a supported configuration until subscriber impact is addressed

Workaround

```bash

Downgrade to last release before the change

(native installer — adjust for your platform)

ln -sf ~/.local/share/claude/versions/2.1.116 ~/.local/bin/claude export DISABLE_AUTOUPDATER=1 # add to shell rc ```

Version info

  • Affected version: 2.1.117 / 2.1.118
  • Last unaffected version: 2.1.116
  • Platform: macOS (Darwin 24.6.0, arm64), native binary

extent analysis

TL;DR

Downgrade to version 2.1.116 and disable auto-updater to mitigate the increased token consumption issue.

Guidance

  • The increased auto-compact threshold in version 2.1.117 can lead to up to 5x more tokens being shipped per turn, affecting subscriber quotas.
  • To verify the issue, monitor cache-write volume and subscription limits after downgrading to version 2.1.116.
  • Consider adjusting workflows to reduce token consumption until a permanent fix is implemented.
  • Be aware that the default effort change for Pro/Max subscribers on Opus 4.6 and Sonnet 4.6 also increases per-turn token consumption.

Example

# Downgrade to last release before the change
ln -sf ~/.local/share/claude/versions/2.1.116 ~/.local/bin/claude
export DISABLE_AUTOUPDATER=1  # add to shell rc

Notes

The provided workaround may not be suitable for all users, and a permanent fix should be implemented to address the subscriber impact.

Recommendation

Apply the workaround by downgrading to version 2.1.116 and disabling the auto-updater, as this is the most straightforward way to mitigate the issue until a permanent fix is available.

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…
#agent setup#task chaining#parallel task#integration issue#index setup

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 Subscriber usage impact of 2.1.117 Opus 4.7 auto-compact threshold change not documented [1 comments, 1 participants]