{"version":"2.0.28","anchor":"agent-transcript-resumption","canonical_anchor":"agent-transcript-resumption","heading":"Agent Transcript Resumption","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.0.28\/e\/agent-transcript-resumption","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.0.28","markdown":"### Agent Transcript Resumption\n\n**What:** Agents can now resume from previous execution transcripts, allowing you to continue where a previous agent left off.\n\n**How to use:**\n\n`# The Agent tool now accepts a 'resume' parameter # When invoking an agent programmatically: { \"subagent_type\": \"investigator\", \"prompt\": \"Continue analyzing the codebase\", \"resume\": \"agent-abc123\" \/\/ ID of previous agent execution }` **Details:**\n\n- New `resume` parameter in Agent tool input schema\n- Loads previous agent's message chain from transcript file\n- Filters messages by agent ID and reconstructs conversation history\n- Prepends previous messages to new prompt for continuity\n- Previous messages are not re-recorded to session storage\n- **Evidence**: New function `b_2() at line 465741`; `resume` parameter schema at line 449027-449032; resume logic at lines 449114-449130"}