claude-code - 💡(How to fix) Fix [Bug] Session/weekly token limits deplete disproportionately fast with Opus orchestrator + Haiku subagents [8 comments, 3 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#52502Fetched 2026-04-24 06:05:29
View on GitHub
Comments
8
Participants
3
Timeline
15
Reactions
0
Timeline (top)
commented ×8labeled ×4subscribed ×2mentioned ×1

Error Message

[{"error":"Error: NON-FATAL: Lock acquisition failed for /Users/lohonyaigyozo/.local/share/claude/versions/2.1.118 (expected in multi-process scenarios)\n at ai_ (/$bunfs/root/src/entrypoints/cli.js:2756:2177)\n at IK8 (/$bunfs/root/src/entrypoints/cli.js:2756:1257)\n at processTicksAndRejections (native:7:39)","timestamp":"2026-04-23T18:17:38.431Z"}]

Root Cause

There is no way for me to tell which, because the usage dashboard shows a single aggregate number with no per-model breakdown.

Code Example

[{"error":"Error: NON-FATAL: Lock acquisition failed for /Users/lohonyaigyozo/.local/share/claude/versions/2.1.118 (expected in multi-process scenarios)\n    at ai_ (/$bunfs/root/src/entrypoints/cli.js:2756:2177)\n    at IK8 (/$bunfs/root/src/entrypoints/cli.js:2756:1257)\n    at processTicksAndRejections (native:7:39)","timestamp":"2026-04-23T18:17:38.431Z"}]
RAW_BUFFERClick to expand / collapse

Bug Description Subject: Max 20x — session + weekly limits drain disproportionately fast when Opus is used as pure orchestrator with Haiku subagents

Plan: Max 20x ($200/month) Client: Claude Code CLI (latest)

Setup:

  • Main model: Opus 4.7 — used STRICTLY as an orchestrator. It does not write code, does not read large files, does not do heavy implementation work.
  • All custom subagents: explicitly pinned to model: haiku via frontmatter. They do 100% of the actual work (file reads, code edits, searches, tool calls).
  • Opus's job in my workflow is limited to: receive the user request, delegate to the right Haiku subagent, review the returned summary, delegate the next step.

Issue: After ~40 minutes of this workflow, the 5-hour session window shows 22% consumption. The weekly limit depletes at a rate that would exhaust it in 2-3 days of normal work, not 7. This is consistent with the behavior reported in GitHub issues #8449 and #26271, which remain unresolved.

Why this is wrong: With Opus acting purely as a router — short delegation prompts in, short summaries out — the Opus token consumption per turn should be minimal. The bulk of tokens (file contents, grep results, code generation) lives in the Haiku subagents' isolated context windows and should be billed at Haiku rates. If the numbers are correct, then either:

(a) Opus orchestration is being billed as if it were doing the full work of the subagents, or (b) Haiku subagent invocations are silently being routed to a more expensive model, or (c) There is a bug in how session/weekly consumption is calculated, as already reported in #8449 and #26271.

There is no way for me to tell which, because the usage dashboard shows a single aggregate number with no per-model breakdown.

Environment Info

  • Platform: darwin
  • Terminal: iTerm.app
  • Version: 2.1.118
  • Feedback ID: 326a7987-ee3d-4cee-8822-3205ffefa92c

Errors

[{"error":"Error: NON-FATAL: Lock acquisition failed for /Users/lohonyaigyozo/.local/share/claude/versions/2.1.118 (expected in multi-process scenarios)\n    at ai_ (/$bunfs/root/src/entrypoints/cli.js:2756:2177)\n    at IK8 (/$bunfs/root/src/entrypoints/cli.js:2756:1257)\n    at processTicksAndRejections (native:7:39)","timestamp":"2026-04-23T18:17:38.431Z"}]

extent analysis

TL;DR

The issue may be resolved by verifying the billing model for Opus orchestration and Haiku subagent invocations to ensure correct token consumption calculation.

Guidance

  • Review the usage dashboard to understand the billing model and token consumption calculation for Opus and Haiku subagents.
  • Check if there are any settings or configurations that can provide a per-model breakdown of token consumption.
  • Investigate if the issue is related to the reported bugs in GitHub issues #8449 and #26271, and consider reaching out to the development team for further assistance.
  • Verify that the Haiku subagents are indeed being billed at Haiku rates and not at a more expensive model rate.

Example

No code snippet is provided as the issue is related to billing and token consumption calculation, which is not directly related to code.

Notes

The issue lacks information about the exact billing model and token consumption calculation, making it difficult to provide a definitive solution. Further investigation and clarification from the development team may be necessary to resolve the issue.

Recommendation

Apply workaround: Reach out to the development team to request a per-model breakdown of token consumption and verify the billing model for Opus orchestration and Haiku subagent invocations. This will help to identify the root cause of the issue and potentially resolve the disproportionate token consumption.

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…

Still need to ship something?

×6

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

Back to top recommendations

TRENDING