Measure silent money errors in LLM tool calls across strict formats and deterministic locale parsers.
-
Updated
Sep 25, 2026 - Python
Measure silent money errors in LLM tool calls across strict formats and deterministic locale parsers.
Parse and format human-readable integers (1.5k, 2M, 3.2B). Zero dependencies.
Format large numbers with human-readable suffixes (1.2M) and parse them back, auto-detecting direction.
To associate your repository with the number-formatting topic, visit your repo's landing page and select "manage topics."