Knowledge Share
Technical articles, tutorials, and insights
Code Agent Anatomy (14): Harness Design Part 4 — Fault Recovery
Examining MyCodeAgent's fault recovery system from a harness engineering perspective: model error classification and tiered retry, Transcript append-only fact log, state reconstruction after crashes, and UncertainAction handling. This is the fourth article in Part 4 Harness Engineering, focusing on 'how an agent self-heals when errors occur and how it resumes after a crash'.
Code Agent Dissection (10): When the Agent Crashes, How Does It Recover? Where Is Conversation History Stored?
A deep dive into MyCodeAgent's persistence and recovery mechanism: TranscriptStore's append-only JSONL event stream, five event types, ResumeLoader rebuilding runtime state from events, UncertainAction's tool interruption handling, and SessionMemory for cross-run feed-forward memory. Understand why agents can't rely on memory for history, and the complete chain for deterministic crash recovery.