Command overview
beacon endpoint harness2 collects telemetry from Harness², Google Research’s framework for recursive agent harnessing, by reading the executor event streams Harness² records under its runs directory and converting them into Beacon endpoint events.
Command syntax
harness.collection_method=poll and harness.name=harness2. Beacon sees a rollout once Harness² recorded it, so nothing here can hold or deny a tool call.
Reading is local and offline. Nothing this command does reaches the network.
Commands
Flags
Both subcommands accept:sync also accepts:
Runs directories
Harness² writes toruns/ inside its own checkout unless HARNESS2_RUNS_DIR says otherwise, and a checkout can be anywhere. Name it once:
Read a checkout's runs directory
--runs-dir, and the install-time backfill, keep reading it alongside the default. Each new value of HARNESS2_RUNS_DIR, which Harness² recommends when changing models or task selection, is a new directory to name.
Sweeping
Sweep once
Preview without writing anything
Sweep continuously while an experiment runs
sync after an experiment, under whatever scheduler the platform already uses, or leave --watch running during one.
Status
Show rollouts and collection progress
collected means the file is unchanged since a sweep last read all of it.
Cursor behavior
The cursor keeps one entry per trajectory file: the last line whose events were all written, the file’s size and modification time, and the session it held. A stream still being written is read up to its last complete line, and the rest on a later sweep. When Harness² re-rolls a run into the same path, the file names a new session and is read from its start.
Re-reading is safe: each event’s id comes from its executor, session, line and kind, so the same line maps to the same event every time.
Related
Harness²
What Beacon records from Harness² rollouts, and the known gaps.
beacon endpoint install
The install-time backfill that runs every session collector once.