CATCH #823
DETECTED AUG 19, 2026 05:15 UTC
THE CATCHscore 6/10
EXHIBIT 823 · URGENT
Aug 19, 2026 05:15 UTC
web app
https://platform.claude.com
Anthropic's Claude platform console deployed new frontend code, adding strings for output token breakdown by category, internal reasoning token counts, and a 'ccr_plan_mode_enabled' feature flag, along with a new commercial pricing API endpoint.
READY TO POST:
looks like claude's platform console got an update, with new strings suggesting more detailed output token breakdowns and insights into internal reasoning token counts. neat for observability!
anthropic might be working on new pricing or plan modes, with a 'ccr_plan_mode_enabled' flag and a new '/api/billing/:organization/commercial_pricing' endpoint showing up in their console.
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 [5d2daa3bd82efe17 -> 0c66aad6364982e4]: +163 strings, -562 strings, 4 interesting
[feature_flag] (3)
+ 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
+ ccr_plan_mode_enabled
[endpoint] (1)
+ /api/billing/:organization/commercial_pricing
caught by the 20-minute sweep ·
the live wire · all receipts