{"version":"2.1.318","anchor":"async-repl-script-checks-hook-gating-output-budgeting-and","canonical_anchor":"async-repl-script-checks-hook-gating-output-budgeting-and","heading":"REPL mode respects plugin hooks, auto mode and an output size limit","tier":"notice","area":"REPL Mode","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318\/e\/async-repl-script-checks-hook-gating-output-budgeting-and","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318","markdown":"### REPL mode respects plugin hooks, auto mode and an output size limit\n\nIn REPL mode, plugins that check tool calls can block REPL-made calls, queued scripts are judged by auto mode, and long output is cut to a size limit\n\n**Unclear.** It is not clear when Claude Code runs in REPL mode, so whether these changes reach you is unknown.\n\n**What**\n\nREPL mode is a way of working where Claude writes small scripts that call tools, instead of calling each tool one at a time. This release adds a large set of rules for it:\n\n- Certain hook events, including `PreToolUse` (the hook that runs before a tool call and can block it), now mark a plugin as one that may check tool calls\n\n- If such a plugin is installed, or Claude Code cannot tell whether one is, a tool call made from inside a script is refused with a message saying the call was not made\n\n- Queued scripts are checked by auto mode, the setting where Claude Code decides on its own which actions are safe to run\n\n- Output from a script that finishes later is cut once it passes a byte limit, with a note saying so\n\n- Shell commands run from a script get their results formatted, including text about saved output and background tasks\n\nA separate server-controlled switch makes MCP tools (tools supplied by outside servers you connect) raise an error inside a script when they fail. Its built-in fallback, used only when the server sends nothing, is on.\n\n**Why**\n\nTool calls made from inside a script can no longer slip past a plugin that is meant to inspect every tool call, and auto mode now applies to scripts too. Very long output from a script no longer floods the conversation.\n\n- Flag `tengu_repl_mcp_error_throw`: Not enough to say (read for one account on one subscription tier against v2.1.318; this account: no value returned, anonymous baseline: no value returned, compiled default: on) 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: REPL Mode\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 4\/5\n- Scope: individual\n- Heads-up: no"}