vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

docs(nh3-svos): refreshed to SVOS ac42ace — kernel 0.0.7 + Type=notify pair, thaw race fixed (drill 2 -> 0)

Browse Source
This commit is contained in:
vh
2026-10-08 15:17:56 -07:00
parent b04cee5579
commit d2f9f561c2
2 changed files with 21 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
persistent-memory.md
+1 -1
View File
@@ -124,7 +124,6 @@ _As of 2026-10-08 ~0740 PT. The newest subsection is first; older subsections ca
- Destroy `zroot/ROOT/debian@pre-patch-20261008` on fv-ml1 ~10-15 if nothing regressed.
- sfsrv-ana `pre-pbs4` snapshot delete is unverified (infra-ops has no key there; ask infra-hermes).
- Re-read nh3-nas usage after the 10-08 GC (79% at 10-07 2350; the mirror prune ran OK).
- Install SVOS kernel 0.0.7 (the thaw-race fix Prime accepted; on svoperatingsystem main at `b672fda` since 10-08) with the NEXT nh3-svos refresh, as a PAIR or not at all: the 0.0.7 wheel (sends `READY=1` once bound) plus `svos-kernel.service` with `Type=notify`, `NotifyAccess=main`, `TimeoutStartSec=300`. `Type=notify` on the old kernel times the unit out. Afterwards run one freeze/thaw drill: the interface must NOT restart. Edge: if the notify cannot reach systemd, a healthy kernel is killed at 300 s, with the cause on stderr. Not urgent; until then the interface restarts once per thaw, which is known.
- **Verified 2026-10-07/08 (closed):** the 10-07 0800 backup check read all fresh with no DESTROYED/DEGRADED lines; the pbs-nh3 mirror prune ran OK at 00:00 on 10-07 and 10-08; `pre-pve9` snapshots are gone on pfi-pve and esh-pve.
- **Watching: jekyll on `sec-reasoning` (cyberprev, GPU 0)** since ~1435 10-06 (Prime moved it off gen-large). sec holds 337k KV tokens. jekyll's ~180k context plus a long sec prompt (up to 192k) can overflow it, as gen-large did (preemptions; decode down to 2–16 tok/s). jekyll's context grows ~1k/call toward the 262k ceiling. It runs on the shared all-agents-local key; a key of its own would make its traffic attributable.
- **Waiting on Prime:**
@@ -187,6 +186,7 @@ Every vLLM seat on a shared card (GPU 0, GPU 1) has byte-pinned KV (`--kv-cache-
## Recent decisions
- `[2026-10-08]` **nh3-svos refreshed to ac42ace (interface UI 0.0.7 polish + kernel 0.0.7 with the `Type=notify` unit as a pair); thaw race FIXED**: the pre-refresh drill (old kernel) made two apps fail at thaw, the post-refresh drill made 0. Previous release is now a737a06; 6c6abbe is deletable. → `servers/nh3-svos/README.md`
- `[2026-10-08]` **SVOS voice ON (Prime, via svos-dev): app-voice on 127.0.0.1:8402, apps up 4 + terminal degraded; Connect → "Voice connected", Enable lists the gateway's 30 voices (Chromium over the LAN door).** `/voice/*` is routed BEFORE Basic auth, because the browser sends `Authorization: Bearer <lease>` there (`web/src/lib/voice.ts`) and Basic auth would reject it. All four app credentials are now vaulted as `nh3-svos/svos-<app>-credential`. → `servers/nh3-svos/README.md`
- `[2026-10-08]` **SVOS served on the LAN too (Prime):** Caddy binds `10.100.50.43:443` as well as `100.64.0.9:443`; the internal AdGuards answer `svos`/`svos-terminal.phasefinal.com` → `10.100.50.43` (MagicDNS still answers 100.64.0.9). Verified from LAN hosts at all three sites. → `servers/nh3-svos/README.md`
- `[2026-10-08]` **fv-ml1 is OFF the mesh again, by design**: its tailscaled is disabled, and the break-glass watchdog joins only on fleet loss (09-15 design, archived). The 0030 reboot closed a door that had been left open, so mesh-side tests need another peer, not fv-ml1. The watchdog timer is active.