{"version":"2.1.274","anchor":"agent-summary-generation-now-rejects-unusable-replies-and-tr","canonical_anchor":"agent-summary-generation-now-rejects-unusable-replies-and-tr","heading":"Agent-summary generation now rejects unusable replies and tracks consecutive rejects","tier":"internal","area":"Elsewhere","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274\/e\/agent-summary-generation-now-rejects-unusable-replies-and-tr","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274","markdown":"### Agent-summary generation now rejects unusable replies and tracks consecutive rejects\n\nBackground-agent summaries now get rejected outright if unparseable, with a running count of failures\n\n**What**\n\nWhen Claude Code generates a short summary of what a background agent (a subagent running a task in the background) is doing, it now parses the model's reply and, if that parsing fails, throws the reply away instead of storing it as the summary. Previously it would just trim any non-empty reply and use it regardless. A count of consecutive rejected replies is now tracked and reported.\n\n**Why**\n\nThis avoids showing garbled or unusable text as a background agent's summary, at the cost of sometimes having no summary at all when the model's reply can't be parsed.\n\n- Area: Elsewhere\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 1\/5"}