{"version":"2.1.312","anchor":"web-fetch-truncation-note-computed-from-a-corrected-offset","canonical_anchor":"web-fetch-truncation-note-computed-from-a-corrected-offset","heading":"WebFetch's partial-page note now uses different start, end and length values","tier":"notice","area":"WebFetch","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.312\/e\/web-fetch-truncation-note-computed-from-a-corrected-offset","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.312","markdown":"### WebFetch's partial-page note now uses different start, end and length values\n\nThe WebFetch note saying an answer covers only part of a page now builds its character range and page length from different values\n\n**What**\n\nWhen Claude reads a long web page with WebFetch, it can add a note saying \"the answer above covers only characters\" from one point to another out of the page's total length. Claude Code now works out that start point, end point and total length from different values than before.\n\nThe word limit passed to the page-summarising step is unchanged, and still falls back to 0 when the server sends nothing.\n\n**Why**\n\nThis may correct the character range the note reports, so the note could more accurately tell you how much of a page Claude actually covered.\n\n- Flag `tengu_humming_waffle`: Not enough to say (read for one account on one subscription tier against v2.1.312; this account: no value returned, anonymous baseline: no value returned, compiled default: not a boolean we can read) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Area: WebFetch\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}