Follow Discord
Sweep 28 Sep 2026 · 18:16Z Build v2.1.284 505 read Stable v2.1.277 Latest v2.1.284 Next v2.1.284 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.284 ·

Saved cost data with impossible token totals is now rejected

Saved cost data is now rejected when its token totals across models are larger than the limit allowed for a single number

Under the hood Internal Changes
JSON All of v2.1.284
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
ElsewhereArea: what it touches
Internal ChangesKind: in v2.1.284,
Internal ChangesSection of the release
What

Claude Code saves a record of cost and token usage for each model. When that record is read back, it is now checked more strictly. For input tokens, output tokens, cache-read tokens and cache-creation tokens, the total across all models must not be larger than the limit already applied to each single number. A saved record that breaks this is treated as invalid.

Why

This protects the figures shown by /cost from being filled with corrupted or overflowing totals from a damaged saved record.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtIt is not stated what happens to the saved cost data when it fails this check, or what the limit is.

See this entry in the whole of v2.1.284 →

Feedback