daily.dev built Huginn, a coding agent integrated into Linear that automates the full workflow from ticket to PR. The post covers the hard engineering problems encountered: wrapping Claude Code and Codex as child processes with their undocumented streaming formats, building a three-tier fallback parser for structured LLM output, debugging session continuity failures caused by working directory changes, and using Linear labels as a crash-resilient state machine. The team also describes their 'Digital Twin Universe' (DTU) testing approach — in-memory replicas of Linear, GitHub, and KMS running in Docker containers — which made a 99% AI-generated codebase viable. Known limitations include ongoing output parsing fragility, rough BYOK credential handling, and poor fit for tight iterative or architecturally complex tasks.
Table of contents
Wrapping CLI agents as child processesThe output parsing warSession continuity and the CWD trapState machine on Linear labelsWhat a 99% AI-generated codebase actually meansWhat's still jankyThe moment it clicked6 Comments
Sort: