Back to feed
Dev.to
Dev.to
8/4/2026
The vendor documents this bug. A 30k-star repo shipped it anyway.

The vendor documents this bug. A 30k-star repo shipped it anyway.

Short summary

A detailed bug report on claude-code-templates (30k+ stars) where token analytics over-counted usage by 2.35× because each assistant message's usage object was summed once per JSONL content-block record instead of once per distinct message ID. Anthropic's own SDK documentation warns about this exact pattern and ships a reference fix. The author provides a one-assertion diagnostic and notes the PR has been approved only by AI reviewers with no human response in ten days.

  • •claude-code-templates inflated token counts 2.35× by summing usage per JSONL record instead of per distinct message ID
  • •Anthropic's SDK docs explicitly warn about this duplication pattern and provide a seenIds deduplication reference
  • •The fix PR has been open for 10 days with only AI reviewer approvals and zero human engagement

Generated with AI, which can make mistakes.

#ai-tools#open-source
Read full article at Dev.to

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

An append-only audit log caught two accounting bugs in a 216-star usage tracker
Dev.to
The original title is: "I type-check AI-generated SDK code against the real package. Claude refused a third of my Stripe tasks."
Dev.to
A missing `model:` line was half my AI agent overspend — auditing 34 days of multi-model Claude Code
Dev.to
The 33,000-token tax, a 30-hour star race, and where agents actually fail
Dev.to