CATCH #785
DETECTED AUG 17, 2026 22:12 UTC
THE CATCHscore 6/10
EXHIBIT 785 · URGENT
Aug 17, 2026 22:12 UTC
web app
https://platform.claude.com
Anthropic's Claude platform console shows new strings related to detailed output token breakdowns, including internal reasoning tokens.
READY TO POST:
looks like anthropic's platform console might be getting more granular output token breakdowns, showing internal reasoning separately.
new strings in claude's console hint at better observability for output tokens, breaking down what's billed vs. internal reasoning.
EVIDENCE — the receipts
⚠️ FROM WEB-APP BUNDLE — may include vendored-dependency strings, verify before posting.
Anthropic Console (https://platform.claude.com) deployed new frontend code [292aeed8215fe7db -> aca8e3c38b49193a]: +954 strings, -1712 strings, 3 interesting
[feature_flag] (2)
+ Breakdown of output tokens by category.
`output_tokens` remains the inclusive, authoritative total used for billing.
This object provides a read-only decomposition for observability — for example,
how many of the billed output tokens were spent on internal reasoning that may
have been summarized be
+ Number of output tokens the model generated as internal reasoning, including
the thinking-block delimiter tokens.
Reflects the raw reasoning the model produced, not the (possibly shorter)
summarized thinking text returned in the response body. Computed by
re-tokenizing the raw reasoning text, so it
[endpoint] (1)
+ /api/bootstrap/${c}/current_user_access
caught by the 20-minute sweep ·
the live wire · all receipts