Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix /compact and auto-compaction both broken — fails across sessions/models/subscriptions; auto-compact sometimes fires at 30% context; /feedback also fails [2 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#45117•Fetched 2026-04-09 08:12:51
View on GitHub
Comments
2
Participants
1
Timeline
6
Reactions
0
Author
taur-ustaur-us
Participants
taur-ustaur-us
Timeline (top)
labeled ×3commented ×2subscribed ×1

Both manual /compact and automatic compaction have been non-functional across a full day of heavy use. Symptoms persist across many sessions, multiple Claude models (Opus 4.6, and others), and multiple subscription tiers. Additionally, the in-app /feedback bug report submission flow is also failing with a generic "Could not submit feedback. Please try again later." error, so users cannot report this issue through the normal channel.

Error Message

Both manual /compact and automatic compaction have been non-functional across a full day of heavy use. Symptoms persist across many sessions, multiple Claude models (Opus 4.6, and others), and multiple subscription tiers. Additionally, the in-app /feedback bug report submission flow is also failing with a generic "Could not submit feedback. Please try again later." error, so users cannot report this issue through the normal channel.

  1. Manual /compact fails. Running /compact produces an error and the conversation continues uncompacted. See attached screenshot of a failed /feedback submission (same underlying issue?).
  2. Try to file feedback via /feedback — also fails with the "try again later" error. Screenshot of the failed /feedback submission showing the verbatim error and the user's written description, from this evening's session.

Root Cause

Both manual /compact and automatic compaction have been non-functional across a full day of heavy use. Symptoms persist across many sessions, multiple Claude models (Opus 4.6, and others), and multiple subscription tiers. Additionally, the in-app /feedback bug report submission flow is also failing with a generic "Could not submit feedback. Please try again later." error, so users cannot report this issue through the normal channel.

Fix Action

Fix / Workaround

High severity. For long-running sessions (e.g., an orchestrator coordinating multiple instances over a full workday, as in this user's case), broken compaction means:

  • Context bloats until the session becomes unresponsive
  • The user must manually /clear and lose all continuity
  • Workarounds like persisting state to external files (runbook.md, etc.) are already in use but cannot fully compensate for the lost ability to compress conversation history
RAW_BUFFERClick to expand / collapse

Bug: /compact and auto-compaction both broken — manual and auto fail across many sessions/models/subscriptions. Auto-compact sometimes fires at ~30% context used.

Summary

Both manual /compact and automatic compaction have been non-functional across a full day of heavy use. Symptoms persist across many sessions, multiple Claude models (Opus 4.6, and others), and multiple subscription tiers. Additionally, the in-app /feedback bug report submission flow is also failing with a generic "Could not submit feedback. Please try again later." error, so users cannot report this issue through the normal channel.

Symptoms

  1. Manual /compact fails. Running /compact produces an error and the conversation continues uncompacted. See attached screenshot of a failed /feedback submission (same underlying issue?).

  2. Automatic compaction fires prematurely. In some sessions auto-compact triggers at approximately 30% context used (70% remaining) — far below any reasonable threshold. In other sessions auto-compact never fires at all until context is exhausted, at which point the session effectively becomes unusable.

  3. Cross-session, cross-model, cross-subscription. The user reports this has been broken ALL DAY across:

    • Multiple independent Claude Code sessions (different project dirs, different CWDs)
    • Multiple Claude models (Opus 4.6 with 1M context was confirmed affected; other models also reported affected)
    • Multiple subscription accounts

  4. /feedback submission ALSO fails. Attempting to file this bug through the in-app feedback flow returns:

    Could not submit feedback. Please try again later.

    See attached screenshot. This means users who hit the compaction bug cannot report it through the intended channel, which is presumably why this is being filed as a regular GitHub issue instead.

Impact

High severity. For long-running sessions (e.g., an orchestrator coordinating multiple instances over a full workday, as in this user's case), broken compaction means:

  • Context bloats until the session becomes unresponsive
  • The user must manually /clear and lose all continuity
  • Workarounds like persisting state to external files (runbook.md, etc.) are already in use but cannot fully compensate for the lost ability to compress conversation history

Reproduction

The user cannot reliably reproduce on demand (since auto-compact timing is non-deterministic), but the bug is highly reliable across a full working day:

  1. Start a long-running Claude Code session (Opus 4.6 recommended, 1M context)
  2. Use the session continuously with many tool calls (bash, read, edit, etc.)
  3. Observe either:
    • (a) Auto-compact fires at ~30% context (too early), OR
    • (b) Auto-compact never fires until the session is effectively dead
  4. Try to manually run /compact — fails.
  5. Try to file feedback via /feedback — also fails with the "try again later" error.

Environment

  • Platform: win32 (Windows 11 Pro 10.0.26200)
  • Shell: bash (Git Bash)
  • Model confirmed affected: claude-opus-4-6[1m] (Opus 4.6, 1M context)
  • Claude Code CLI (interactive mode)
  • User reports: "COMPACTING AUTO AND MANUAL HAS NOT WORKED ALL DAY, ACROSS MANY SESSIONS, MANY MODELS, EVEN DIFFERENT SUBSCRIPTIONS. SOMETIMES IT EVEN TRIES TO AUTO COMPACT WITH LIKE 30% CONTEXT USED (70% REMAINING)."

Expected behavior

  • Manual /compact should compress the conversation history and return a summary
  • Automatic compaction should fire at the configured threshold (presumably ~90-95% context used), not at 30%
  • /feedback submission should succeed and provide a confirmation message

Actual behavior

  • Manual /compact: fails
  • Auto-compact: fires at wrong threshold (e.g., 30%) or never fires
  • /feedback: returns "Could not submit feedback. Please try again later."

Attached

Screenshot of the failed /feedback submission showing the verbatim error and the user's written description, from this evening's session.

Filed from a working Claude Code session via gh issue create since the in-app feedback flow is broken.

extent analysis

TL;DR

The most likely fix involves investigating and resolving the underlying issue causing the /compact and /feedback endpoints to fail, potentially related to the compaction threshold configuration or a bug in the Claude Code implementation.

Guidance

  1. Verify compaction threshold configuration: Check the configured threshold for automatic compaction to ensure it is set correctly, as the current behavior suggests it might be triggering too early.
  2. Investigate /compact and /feedback endpoint issues: Since both manual compaction and feedback submission are failing, there might be a common underlying cause, such as a server-side error or a bug in the Claude Code CLI.
  3. Test with different models and subscriptions: Given that the issue persists across multiple models and subscriptions, testing with different configurations might help isolate the problem.
  4. Check for any recent updates or changes: Ensure that all components, including the Claude Code CLI and any dependent services, are up-to-date and that no recent changes could be causing the issue.

Example

No specific code snippet can be provided without more details on the implementation, but checking the configuration and logs for any error messages related to compaction or feedback submission could be a starting point.

Notes

The issue seems to be related to the Claude Code implementation and its interaction with the compaction and feedback mechanisms. Without more specific details on the configuration, logs, or error messages, it's challenging to provide a precise fix. The failures of both manual and automatic compaction, along with the feedback submission issue, suggest a potentially deeper problem that requires investigation into the application's backend or the CLI tool itself.

Recommendation

Apply a workaround by manually managing conversation history until the issue is resolved, such as periodically clearing the context or using external tools to manage state, as the user is already doing. This is not a permanent solution but can help mitigate the impact of the broken compaction feature.

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

  • Manual /compact should compress the conversation history and return a summary
  • Automatic compaction should fire at the configured threshold (presumably ~90-95% context used), not at 30%
  • /feedback submission should succeed and provide a confirmation message
#conversation history#integration issue#index setup#retrieval issue#search optimization

Still need to ship something?

×6

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

Back to top recommendations

TRENDING