{"version":"2.1.234","anchor":"token-counting-no-longer-throws-on-incomplete-blocks","canonical_anchor":"token-counting-no-longer-throws-on-incomplete-blocks","heading":"Token counting no longer throws on incomplete blocks","tier":"notice","area":"Elsewhere","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234\/e\/token-counting-no-longer-throws-on-incomplete-blocks","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234","markdown":"### Token counting no longer throws on incomplete blocks\n\nToken counting handles incomplete blocks instead of throwing.\n\n**What**\n\nCounting input size across text, thinking and redacted thinking blocks now treats a missing field as zero length instead of reading it directly, so a malformed block cannot break the count.\n\n**Evidence**\n\n`inputTextCharLength`\n\n- Area: Elsewhere\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}