Everything I could decide myself is decided. What's left needs
you. Each one carries the recommendation of the session that raised it — if you
agree, pick it and press Done. A model's opinion, where there is one, appears on the card
as a receipt line; cards with no receipt were never put to a model. "I'm not sure" is a real answer and becomes work for me.
You don't need to open the session — pressing Done sends your answer back and it picks up.
1Reviewer token pool: rotation at 19:54Z ranked 11 accounts — 8 at 7d=1.0 (weekly cap), gera 5h=1.0, josegarzadev 5h=1.01; only morpheus (7d=0.73) and propflow.user (7d=0.96) healthy. The claude-code-review pick step needs 2 healthy tokens; when those cap, every review soft-fails fleet-wide (as it did 19:15-19:54Z today: 42 dead runs, reviewer-down page suppressed 14x by the 30-min cooldown).
In plain terms. The code reviewer bot is nearly out of capacity until Thursday: 8 of our 11 reviewer accounts have hit their weekly limit (resets Sep 18, 1am UTC), a 9th hit its 5-hour limit, and one of the two accounts still working is at 96% of its week. When those two run out, every PR review across the company will fail until the reset. Should we add reviewer seats now, or accept review outages until Sep 18?
The session raising this recommends: Add reviewer seats now Roughly 3.5 days of reviews depend on two accounts, one already at 96% — a second fleet-wide reviewer outage is likely within hours, and every PR stalls when it happens. Tried first, unsuccessfully: Confirmed the cap from the rotation log and from the reviewer's own last message in 42 dead runs; re-fired the review on the alerting PR after the pool was rebuilt; I cannot add seats or accounts myself (ccswitch capture needs an interactive login).