# `reporters/record` Source: [`src/reporters/record.ts`](https://github.com/AI-for-dev/combo/blob/main/src/reporters/record.ts) The event stream, on disk: one JSON object per line, in the order it happened. pi's own JSONL already holds each subagent's transcript, one file each. What this adds is the two things that live between them: the **interleaving** - who was working while who else was reading - and **our timestamps**, since pi has no notion of the wall clock a workflow runs on. Written with `appendFileSync`, deliberately. It is one syscall per event and a streamed reply produces a great many of them, but the run worth reading afterwards is the one that was interrupted, and a buffered stream loses its tail exactly then. Durability over throughput, the same trade the export made. ## `recordReporter` *function* ```typescript export function recordReporter(file: string): EventListener { /* … */ } ``` Appends every event to `file` as `{"ts": , …event}`. The events are recorded **verbatim** - no filtering, no summarising. A recorder that edits its own record is worse than a large file, and the analysis this exists for is the one nobody planned in advance. Every failure is swallowed, including the one that creates the directory: a reporter is an observer, and an observer that takes the workflow down with it is a bug.