{"version":"2.1.321","anchor":"agent-summary-aborts-when-the-model-calls-a-tool","canonical_anchor":"agent-summary-aborts-when-the-model-calls-a-tool","heading":"Agent summaries and prompt suggestions are dropped when the model calls a tool","tier":"notice","area":"Agents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.321\/e\/agent-summary-aborts-when-the-model-calls-a-tool","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.321","markdown":"### Agent summaries and prompt suggestions are dropped when the model calls a tool\n\nBackground agent summaries and auto prompt suggestions are now discarded if the model tries to call a tool instead of writing text\n\n**What**\n\nClaude Code runs some small background requests that should only produce text. A tool call, where the model asks to run one of its tools, now ends both of them without a result:\n\n- Agent summaries: when Claude Code writes a short progress summary of a subagent (a helper Claude starts to work on part of a task), the request is stopped as soon as the model starts a tool call or anything other than text. No summary is produced, and the skip is recorded with the reason `tool_call`. Before, the request returned whatever the model sent.\n\n- Prompt suggestions: the request that suggests what you might type next now reports whether it called a tool. If it did, the suggestion is dropped and the outcome is recorded as `tool_call`. Before, the only recorded outcomes were aborted, empty and unused.\n\n**Why**\n\nIn practice you may sometimes see no subagent summary or no suggestion, rather than one built from a request that went off course into a tool call.\n\n- Area: Agents\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}