{"version":"2.1.288","anchor":"code-review-output-all-findings-mode-and-tool-call-report","canonical_anchor":"code-review-output-all-findings-mode-and-tool-call-report","heading":"Code review can keep every finding or report through a tool","tier":"notice","area":"Code Review","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.288\/e\/code-review-output-all-findings-mode-and-tool-call-report","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.288","markdown":"### Code review can keep every finding or report through a tool\n\nThe code review prompt can now keep every finding with no limit, or have results reported through a tool call\n\n**Unclear.** It is not clear what decides which version or which limit a review uses.\n\n**What**\n\nThe instructions Claude Code gives the model when it reviews code now come in more forms. Previously the model returned a list capped at a fixed number of issues. Now:\n\n- One version says \"Keep every finding that survives. There is no maximum.\"\n\n- Another version tells the model to report through a tool, which is an action the model can call. It sends a level and a list of findings, each with a short summary and a category.\n\n**Why**\n\nA review can now return all of the issues it finds instead of stopping at a set number.\n\n- Area: Code Review\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}