Skip to content

More Token usage when used with Claude code starting from Fable 5 start and now from last 2 days in 5.6 Sol too #1301

Open

Description

@Veerus007

Version

codebase-memory-mcp 0.7.0

Platform

macOS (Intel)

Install channel

npm

Binary variant

standard

What happened, and what did you expect?

Hi ,
I have been using using it for quite some time but after release of Fable 5 I saw this mcp used 5% , 10% or 20% jump when I asked Claude. I noticed even worst is when we are in the middle of some task and we hit the limit and once the reset happens and it starts working then it even some times consumed 50% of token in less than 5 min so I stopped using this map in Claude code by setting it in Claude.md and etc.

Fast forward till 2 days before we saw/seeing even now this (you might be aware of heavy drain of Codex tokens) heavy drain in GPT tokens , weekly is working like hourly drain and thing that has to work for week is exhausted in less than few hours in sol 5.6 medium too.,

Note I use this only in Claude & CODEX CLI VERSION. no other web/app only for coding purpose .

Now I have stopped using , if any fix for this please let me know.

Thanks & Regards,
Veeru

Reproduction

I have written above.

Regular use in Claudecode
Just one hit consumes 1% of 5hr .

More importantly what I noticed even drastic as mentioned in the above message :
when we are in the middle of some task and we hit the limit of Claude code CLI and once the reset to 100% happens and we start or ask it to continue , it starts working then it consumes upto50% of token in less than 5 min(I realised 1st time so noticed and intentionally tried at 99% and gave a task to see if it happens after token exhaust in next session and it was running like a minute/seconds of clock) so I stopped using this map in Claude code by setting it in Claude.md and etc.

Logs


Diagnostics trajectory (memory / performance / leak issues)


Project scale (if relevant)

No response

Confirmations

  • I searched existing issues and this is not a duplicate.
  • My reproduction uses shareable code (a dummy snippet or a public OSS repository), not proprietary code.

Activity

  1. added this to the 0.9.1-rc milestone on Jul 28, 2026
  2. added
    priority/normalStandard review queue; useful PR with ordinary maintainer urgency.
    awaiting-reporterWaiting on the reporter for info/repro; stale bot will warn then close
    on Jul 28, 2026
  3. DeusData commented on Jul 28, 2026

    @DeusData
    Owner

    Thanks for raising this and for describing when the jump becomes visible. The reported CBM version is 0.7.0, which predates the current compact output path. On current main, search_graph emits grouped compact rows and blocks internal fingerprint/profile/body-token fields from agent output (src/mcp/mcp.c:3014-3025).

    A client quota percentage does not identify which tool response caused the spend. Could you retest with 0.9.0 or the current 0.9.1 release candidate and provide one exact CBM tool name, its arguments, and the response byte size from a high-usage turn? That will let us separate CBM payload size from client/model accounting. Marked awaiting-reporter; thank you for helping pin it down.

  4. github-actions commented on Jul 28, 2026

    @github-actions

    Thanks for the report! To move this forward we need a bit more so we can reproduce it ourselves:

    • the codebase-memory-mcp --version you're on
    • the exact steps or command you ran
    • a public repo (or a small dummy snippet) that shows the problem — please don't paste proprietary code

    Once that's here we'll pick it straight back up. Heads-up: issues left awaiting-reporter are automatically closed after a few weeks of silence, but a comment reopens the door anytime.

  5. github-actions commented on Aug 19, 2026

    @github-actions

    This issue has been waiting on more information for 21 days (a version, exact steps, or a public repro), so it's now marked stale. It will not be closed automatically — a maintainer reviews stale issues by hand. Adding a comment with the details clears the label and puts it straight back in the queue. We're happy to pick it back up the moment we can reproduce it.

  6. added
    staleNo activity after an info request; will be closed soon
    on Aug 19, 2026
  7. added
    priority/highNeeds near-term maintainer attention; high-impact bug, regression, safety issue, or release blocker.
    and removed
    priority/normalStandard review queue; useful PR with ordinary maintainer urgency.
    on Sep 5, 2026
  8. removed
    staleNo activity after an info request; will be closed soon
    on Sep 6, 2026
  9. github-actions commented on Sep 27, 2026

    @github-actions

    This issue has been waiting on more information for 21 days (a version, exact steps, or a public repro), so it's now marked stale. It will not be closed automatically — a maintainer reviews stale issues by hand. Adding a comment with the details clears the label and puts it straight back in the queue. We're happy to pick it back up the moment we can reproduce it.

  10. added
    staleNo activity after an info request; will be closed soon
    on Sep 27, 2026
  11. Veerus007 commented on Sep 27, 2026

    @Veerus007
    Author
  12. removed
    staleNo activity after an info request; will be closed soon
    on Sep 28, 2026
  13. added
    awaiting-reporterWaiting on the reporter for info/repro; stale bot will warn then close
    and removed
    awaiting-reporterWaiting on the reporter for info/repro; stale bot will warn then close
    on Oct 19, 2026
  14. DeusData commented on Oct 19, 2026

    @DeusData
    Owner

    Thank you, Veeru, for the additional reset/session scenario. That describes when the usage jump appears, but still does not identify a particular CBM response or its size. Please share the installed CBM version and one affected tool name, arguments, and response byte count from an existing example, with private content redacted; there is no need to deliberately exhaust another account quota for this.

  15. github-actions commented on Oct 20, 2026

    @github-actions

    Thanks for the report! To move this forward we need a bit more so we can reproduce it ourselves:

    • the codebase-memory-mcp --version you're on
    • the exact steps or command you ran
    • a public repo (or a small dummy snippet) that shows the problem — please don't paste proprietary code

    Once that's here we'll pick it straight back up. Heads-up: issues left awaiting-reporter are automatically closed after a few weeks of silence, but a comment reopens the door anytime.

  16. DeusData commented on Oct 25, 2026

    @DeusData
    Owner

    Thank you for clarifying the reset scenario. One existing affected tool call, its arguments, response byte count and installed version are still needed; please do not deliberately exhaust another quota.

  17. github-actions commented on Nov 17, 2026

    @github-actions

    This issue has been waiting on more information for 21 days (a version, exact steps, or a public repro), so it's now marked stale. It will not be closed automatically — a maintainer reviews stale issues by hand. Adding a comment with the details clears the label and puts it straight back in the queue. We're happy to pick it back up the moment we can reproduce it.

  18. added
    staleNo activity after an info request; will be closed soon
    on Nov 17, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    awaiting-reporterWaiting on the reporter for info/repro; stale bot will warn then closebugSomething isn't workingeditor/integrationEditor compatibility and CLI integrationpriority/highNeeds near-term maintainer attention; high-impact bug, regression, safety issue, or release blocker.staleNo activity after an info request; will be closed soon

    Projects

    No projects

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions