diff --git a/persistent-memory.md b/persistent-memory.md
index c35ee51..3048b89 100644
--- a/persistent-memory.md
+++ b/persistent-memory.md
@@ -178,6 +178,7 @@ Every vLLM seat on a shared card (GPU 0, GPU 1) has byte-pinned KV (`--kv-cache-
 
 ## Recent decisions
 
+- `[2026-10-12]` **Decision-seat swap (Prime via brokkr): h2o-lightning-4b @ b43f759b replaces Intern-Decision-4B, AFTER albok-dev re-validates Nemi's sensitivity judge on it.** The swap was held at 1234: the seat's only production traffic is albok-nemi's `/decide/shared` judge (57,108 calls 10-05..10-10), and h2o's shim has no /decide. TEMPORARY eval seat `stacks/h2o-eval` up since 1300 on fv-ml1 GPU 3 :8034 (~14.4 GB; Scriberr/MIA still fit beside it), with `services/h2o-decision-front` (32k refuse-not-trim admission from infra-hermes 30f36f2, bearer, the /decide/shared translator, /health model {name, revision}); weights `/tank/aimodels/h2o-lightning-4b-b43f759b` (hashes = HF). **Next, on albok-dev's sign-off (threshold, route):** GPU 1 cutover on :8033 with the same front and byte-pinned KV (budget 16,847 MiB, peak 15,566), rollback = the INC compose; post-checks (health rev, JevBench 205, 422 probe, 16q@32k ~2 s, GPU 1 peak); then `docker compose down` h2o-eval. Thread `01M4RSFC9J2R0J07EEBD4N04W3`.
 - `[2026-10-12]` **U13 regression fixed 0943 (svos-dev's URGENT, Prime saw every app pane 403):** the browser frames a pane at the registry `base_url`, and U13 had set app-terminal's to the seat-host origin, which admits only nh3-svos. Fix: `base_url` back to `https://svos-terminal.phasefinal.com` (config_gen `acae45206bbc9fcb`), plus POST `/seats/{observe,check,launch,retire-launch}` allowed from the box on that origin. svos-dev's one-line fix alone would have 404'd the kernel's seat-host calls; the origin never carried them before. svos-dev owes a separate browser-facing origin field; then the seat-host goes back to being kernel-facing.
 - `[2026-10-12]` **Shared CI runner (ana-docker act_runner, capacity 2, `timeout: 30m`) is slow because pfi-pve's `ospool` is HDD mirrors with no SLOG:** 8 KiB `oflag=dsync` writes measured ~145 ms on ana-docker vs ~2.7 ms on nh3-docker (n=3 each; pfi-pve host on ospool 18–32 ms; corviduo-dev ~75 ms). Jobs past 30 min are killed with a truncated log and no footer (albok every run since 10-04; vastblue 10935). Worse since the 10-04 PVE 9 reboot, cause not pinned (drive write cache was the same before and after: sda WCE on, sdb–sdd off). vastblue fixed its side with PostgreSQL on tmpfs (run 11033 green, pytest 14m17s vs 7–8 min per 72-test batch); albok is adding pytest-timeout + durations in 0.1.19. **Prime's call, pending:** A opt-in fast runner on nh3-docker (recommended), B SLOG for ospool on the BOSS (check endurance), C leave it. ana-docker vCPU is x86-64-v2-AES (no AVX2), a separate lean-against.
 - `[2026-10-11]` **worldtree-dev is reading mail again (2219), answering four of our threads at once**: #416 residual REOPENED for a second writer pass (a filer-side deterministic expiry guard, U4 rev 1.17, after #422/#423; acceptance = 0 leaks over 10 daily batches with the filing/user median in band). Keep the daily report's "known #416 residual" classification until then. The writer/gate never call embed/rerank and the gate fails CLOSED, so the 10-04 leak was the writer's judgment. No confirmatory batch for 10-09 (10-10/10-11 = 0.83). Nothing of theirs sets a small max_tokens on gen-frontier. This makes Prime's "who sees gate failures" question moot. Thread `01M4BDETDGMNVDTFXN3T3Y63DP`.