{"version":"2.1.296","anchor":"read-tool-opt-in-raised-size-and-token-limits-allowlarge","canonical_anchor":"read-tool-opt-in-raised-size-and-token-limits-allowlarge","heading":"Reading files can raise its size limits to fit the context left","tier":"notice","area":"Read Tool","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.296\/e\/read-tool-opt-in-raised-size-and-token-limits-allowlarge","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.296","markdown":"### Reading files can raise its size limits to fit the context left\n\nFile reads can raise their size and token limits to fit remaining context, and cut-off messages now say how much room there was\n\n**Unclear.** It is not stated what allows a read to use the raised limits, so whether this is active is unknown.\n\n**What**\n\nWhen Claude reads a file, Claude Code limits how big the file can be and how many tokens (the units the model counts text in) it can take up. Reads can now be allowed past those fixed limits, up to raised limits, and the tokens they use come out of the room left in the conversation's context.\n\nWhen a file is cut short, the message now says the read \"had room for\" a number of tokens this turn, instead of naming a fixed cap.\n\n**Why**\n\nThis could let Claude read larger files when the conversation has room for them.\n\n- Area: Read Tool\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}