{"version":"2.1.312","anchor":"partial-output-recovery-for-cut-off-agents-now-uses-a-helper","canonical_anchor":"partial-output-recovery-for-cut-off-agents-now-uses-a-helper","heading":"The note on partial output from a cut-off agent is now built a different way","tier":"internal","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.312\/e\/partial-output-recovery-for-cut-off-agents-now-uses-a-helper","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.312","markdown":"### The note on partial output from a cut-off agent is now built a different way\n\nClaude Code now builds the note marking a cut-off agent's recovered output in one shared place and passes on a filtered history\n\n**What**\n\nA subagent is a helper Claude starts to do part of a job. When one is cut off before finishing, Claude Code recovers what it had produced and adds a note saying everything below is partial output. That note is now built by a shared routine instead of being written out in place, and the conversation history passed on with it is the filtered one.\n\n**Why**\n\nThe wording the model sees when a subagent is cut off may differ from before.\n\n- Area: Subagents\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 0\/5\n- Scope: individual\n- Heads-up: no"}