Commit Graph
736 Commits
Author SHA1 Message Date
vh 4eacb746fa docs(albok): old nemi token revoked after the personal/inbox swap 2026-10-13 17:43:15 -07:00
vh 7ca2f76d21 feat(albok): personal/inbox wing on nh3-albok + /srv/nemi/inbox capture root on nh3-dev (unit 4.4 slice C, gate 2)
Prime ruled albok subsumes note intake (1530). The wing is like personal/notes
(albok-personal 1511, not service-restricted); health reads 7 wings ready.
Nemi's token was re-minted with read+write on the new wing and vaulted over
albok/token-nemi. /srv/nemi/inbox is lkraven:nemi-drop 2770 with a default ACL,
plus u:lkraven:rx on /srv/nemi, so Nemi reaches it from lkraven's user manager,
whose groups predate nemi-drop. Both paths are verified by the playbook.
2026-10-13 17:31:49 -07:00
vh eda7025ed1 ops(svos): A171 — miranda's app-postoffice write grant autonomous (Prime 2026-10-13 1400) 2026-10-13 13:59:30 -07:00
vh a630fe46d6 memory: correct the 7f95e54 deploy time (0906, not 0914) 2026-10-13 09:06:57 -07:00
vh c4c35ae951 memory: nh3-svos static release 7f95e54 (UI 0.0.15) 2026-10-13 09:06:44 -07:00
vh 5000916a7b memory: app-terminal PATH fix; nh3-svos static release 89dad7a (UI 0.0.14) 2026-10-13 08:57:53 -07:00
vh 499678979a docs(gitea-runner): vh/albok green on the nh3-docker runner; its CI was slow fsync, not a hang 2026-10-12 23:25:09 -07:00
vh 9f833b2e90 memory: h2o cutover walk closed — personal reading (18 vs 6) is the one open margin 2026-10-12 18:13:29 -07:00
vh 5af8e2bc17 feat(intern-decision): h2o-lightning-4b is the production decision seat; fix forward, no INC fallback
Prime (18:05, via albok-dev): go to h2o and fix forward, do not fall back to
INC. albok-dev removed the chapter margin first (the two published nonfiction
titles declared visibility: public). switch-to-h2o.sh ran 18:05:13, h2o healthy
18:07:40; /health at the pin, /decide/shared 200, 422 over the cap, inline image
answers, image URL refused by the shim and by vLLM's media-domain backstop.
rollback-to-inc.sh stays on the host as an artifact only.
2026-10-12 18:08:31 -07:00
vh c991d939f9 memory: second h2o rollback closed out — counts restored, timer back 2026-10-12 17:51:46 -07:00
vh d2fb840bfa fix(intern-decision): second rollback to Intern-Decision-4B; h2o staged until the judge's two margins are fixed
The v2 walk on h2o (17:05-17:45) held notes at 0 adult but moved two margins
past albok-dev's pre-named rollback line: library/nonfiction adult 0 -> 79 (one
textbook chapter at 0.531 on the book profile, INC 0.438, with 77 concepts
inheriting) and fleet/memory personal 6 -> 18. rollback-to-inc.sh ran 17:47:46,
INC healthy 17:48:11. compose.yaml is INC again.
2026-10-12 17:48:43 -07:00
vh 0da7df7534 memory: Prime's 10-12 rulings (CI A, push, no judge-token rotation); card 05cf119e was approved, not pending 2026-10-12 17:22:59 -07:00
vh 6a01da759d memory: decision seat live on h2o again since 1704 under the re-fitted judge 2026-10-12 17:06:20 -07:00
vh 8d9fcd9ffb memory: h2o judge investigation closed — v1 note question was the cause, re-fitted in albok-nemi 0.1.18; eval seat down 2026-10-12 16:20:49 -07:00
vh 2b40805b84 feat(h2o-eval): round 2 eval seat on GPU 3 with floor-on/floor-off fronts for the judge investigation
Prime (via albok-dev): understand why h2o failed and re-fit the judge. One
vLLM on GPU 3 behind two fronts: :8034 with the shim's yes/no floor at 0.801
exactly as the cutover ran (same judge stamp), :8035 with SHIM_NOUL_FLOOR=0 and
a distinct stamp (h2o-lightning-4b+noul-floor-0). Both refuse image URLs; the
vLLM --allowed-media-domains backstop is now verified (400, no fetch).
2026-10-12 14:29:15 -07:00
vh 501bda078d memory: decision-seat rollback closed out — hidden set back to INC counts 2026-10-12 14:09:11 -07:00
vh f979cca1ea fix(intern-decision): roll the decision seat back to Intern-Decision-4B; h2o staged with inline-images-only
albok-dev withdrew the judge sign-off on fleet-scale evidence and brokkr
concurred: over 10,841 texts judged by both models, h2o flagged 242 adult at
0.5 against INC's 88, and no threshold reproduces INC's set. rollback-to-inc.sh
ran 14:03:28, INC healthy 14:03:56, /decide/shared smoke 200 x3.

compose.yaml is INC again; the h2o compose is kept as compose.h2o.yaml with
switch-to-h2o.sh (GPU 1 free-memory gate, falls back to INC). It now carries
Prime's inline-images-only setting: LIGHTNING_IMAGE_URLS=off on the front
(verified live: an https image URL is refused before any fetch, inline images
still answer) and vLLM --allowed-media-domains media.invalid as a backstop.
rollback-to-inc.sh no longer leaves timestamped compose copies behind.
2026-10-12 14:05:44 -07:00
vh c08992f95f feat(intern-decision): decision seat swapped to h2o-lightning-4b on fv-ml1 GPU 1; eval seat down
The :8033 seat now serves h2oai/h2o-lightning-4b @ b43f759b on vLLM 0.30.0 with
byte-pinned KV (4.48 GiB, 135,558 tokens) behind services/h2o-decision-front:
32k refuse-not-trim admission, the seat's bearer token, and /decide +
/decide/shared translated onto /v1/systemone for albok-nemi's judge. URL, port,
token and stack name are unchanged. INC down 13:08:18, h2o healthy 13:11:27.

Post-checks on the live seat: /health at the pinned revision; JevBench public
205/231 (= bench); 422 over the cap; 16q at the cap warm 2.0-2.16 s; seat peak
16,164 MiB under 4 concurrent 16q x 32k calls against a 16,847 budget.

compose.inc.yaml + rollback-to-inc.sh restore Intern-Decision-4B in one step.
The temporary GPU 3 eval seat (stacks/h2o-eval) is down.
2026-10-12 13:19:46 -07:00
vh 152137e41d memory: decision-seat swap held for albok's judge; h2o eval seat on GPU 3 2026-10-12 13:02:04 -07:00
vh 0fe081042d memory: U13 seat-host 403 regression fixed 2026-10-12 09:44:12 -07:00
vh ca9e385316 memory: CI runner slowness diagnosed (ospool fsync ~145 ms on ana-docker); A/B/C pending Prime 2026-10-12 09:41:23 -07:00
vh 8d5e720534 memory: nh3-dev SVOS units still run from dc241f8 — keep it until they restart 2026-10-12 00:04:46 -07:00
vh 87105374c6 memory: worldtree-dev back on mail — #416 residual reopened (second writer pass); gate-audience question moot 2026-10-11 22:20:08 -07:00
vh b3d69ea5f1 memory: nh3-svos static-only UI 0.0.13 (8fa229d) deployed 2026-10-11 17:58:35 -07:00
vh 131e39a452 memory: nh3-svos static-only UI 0.0.12 (61459d2) deployed 2026-10-11 17:37:29 -07:00
vh 44ee37e7c3 memory: nh3-svos static-only UI 0.0.11 (627a9fb, build id on the top bar) deployed 2026-10-11 17:18:35 -07:00
vh ad79071d20 memory: nh3-svos processes still run from adc862e — keep it until restart 2026-10-11 17:16:40 -07:00
vh 61ff32d116 memory: nh3-svos static-only UI 0.0.10 (ad255a2) deployed 2026-10-11 17:16:24 -07:00
vh b7a0b0e441 memory: nh3-svos static-only UI 0.0.9 (34476a7) deployed 2026-10-11 17:11:39 -07:00
vh 31e03af692 memory: v0.0.10 deployed (kernel 0.0.10, UI 0.0.8, miranda 0.0.4); correction — card 05cf119e was never approved 2026-10-11 14:12:46 -07:00
vh 2e6bac9731 memory: svos-dev's U13 answers — Miranda bus-tag fix in the next release; the non-autonomous send grant is intended 2026-10-11 14:00:13 -07:00
vh fd87f8b513 memory: U13 acceptance closed (Miranda's reply arrived 1354) 2026-10-11 13:54:49 -07:00
vh 5202847abb memory: snapshot — 2026-10-11 U13 cutover executed + accepted (one card + svos-dev answers open), fv-ml1 hang + evidence capture, stale snapshots gone; 6 entries archived 2026-10-11 13:54:24 -07:00
vh df7161bbe0 memory: U13 E2 through step 6; fv-ml1 evidence capture staged; scheduled 10-11 checks closed 2026-10-11 09:01:14 -07:00
vh 3c05ae8ba2 memory: fv-ml1 hard hang 2026-10-11 ~0005 (self-reset); hold the pre-patch snapshot destroy 2026-10-11 00:19:46 -07:00
vh 6b541fb557 memory: U13 payload 7d7ed1f — whole app directories move at E2; hashes filled from the vault 2026-10-10 17:35:52 -07:00
vh b7a9f82d2f memory: Prime's U13 rulings (dev+ops, keep the nh3-svos artifact label, matrix-relay) 2026-10-10 17:34:25 -07:00
vh fa567fa150 ops(svos): U13 phase B amendment — full kernel-origin path list, Miranda's env and origin on nh3-dev, enrollment secrets, app-high-seat declared
Per svoperatingsystem dc241f8 u13-svos-edit.md items 1, 4, 5 and 6 (Prime's
go stands): the kernel origin passes exactly the method-pinned list (apps and
Miranda's agent connector; 15 pairs reach the kernel, the rest are Caddy 404);
nh3-dev's apps env is rebuilt as dc241f8 with svos-miranda 0.0.3 and
svos-agent 0.0.3 and gains the svos-miranda origin (nh3-svos only); three
enrollment secrets minted into the vault; app-high-seat declared with one
reload. Also fixes nh3-dev's fleet Caddy sharing admin localhost:2019 with
ttyd-caddy via SO_REUSEPORT (reloads could land on either): now :2021.
2026-10-10 16:56:47 -07:00
vh feef8330ca ops(svos): U13 phase B — nh3-svos on v0.0.9 (schema 12), kernel app origin, seat-host and high-seat origins, bridge env on nh3-dev
Prime approved svos-dev's U13 pre-edit ask (2026-10-10 1639).
- B1: release afab123 on nh3-svos (kernel 0.0.9, migration 11->12) after a
  vzdump and an offline svos.db copy; app-terminal and app-postoffice held on
  b588510 by drop-ins until the edit.
- B2: --app-listen 127.0.0.1:8410 (drop-in) fronted by Caddy as
  svos-kernel.phasefinal.com on the LAN, allowlisted to nh3-dev; the path list
  adds /auth/kernel-key, which every connector client needs. DNS rewrite on
  the three internal AdGuards.
- B3/B4: svos-seathost (-> :8404) and svos-highseat (-> :8773) on nh3-dev's
  fleet Caddy, allowlisted to nh3-svos; /opt/svos apps env on nh3-dev with
  svos-postoffice[push] (althing-core 3.7.0 from althing 7a2a1c1) and
  svos-terminal. The fleet Caddyfile is now tracked in configs/.
2026-10-10 16:50:18 -07:00
vh 129122d9b4 memory: 10-10 gate PASS closes the filing watch; esh-nas-pve pre-pve9 snapshot destroyed 2026-10-10 07:50:50 -07:00
vh 70b7281182 ops(albok): vh joins every albok read group; macOS withdrawal-test run staged
Prime, 2026-10-09: "vh gets albok-everything". playbooks/nh3-albok-vh-viewer.yaml
joins vh to albok-read, albok-personal and albok-feedback on nh3-albok and
authorizes his four Macs' public keys for vh; verified at a fresh login that
every wing's .browse/ lists and reads.

The withdrawal harness gains a macOS driver (run-mac.sh: every mountable FUSE
backend, a read-only smoke of the real wings, results copied back), env
overrides for a non-container client, and summarize.py. Sanity-checked as vh
from the Linux container before staging.
2026-10-09 22:45:52 -07:00
vh 172d893cdf test(albok): sshfs pathname-withdrawal test for the .browse/ view passes (unit 4.3 exposure gate)
Replica of a browse view on nh3-albok, Linux sshfs 3.7.3 client in an ephemeral
container on nh3-dev, N=5 per condition. Fresh open of a never-opened child
through a cached listing: ENOENT 5/5 with sshfs defaults and 5/5 with hour-long
client caches. Null control (no rename) opens 5/5; held fd and failed-rename
positive controls read 5/5. Replica removed afterwards.

Also closes the post-clear checks in persistent-memory: fv-ml1 GPU 0/1 plateau,
nh3-nas usage, and the mislabelled sfsrv-ana pre-pbs4 item.
2026-10-09 20:23:30 -07:00
vh 9ba2ce476b memory: correct the snapshot time stamp (1955, not 1610) 2026-10-09 19:56:07 -07:00
vh d89864b5c4 memory: snapshot — 2026-10-09 SVOS LAN/voice/ac42ace/kernel 0.0.8 (fd outage fixed), U13 ingress approved+deferred, albok library, gate watch; 11 entries archived 2026-10-09 19:56:00 -07:00
vh 65fffe21aa memory: SVOS v0.0.9 (afab123) cut for U13; edit doc docs/operations/u13-svos-edit.md 2026-10-09 12:53:07 -07:00
vh 841cde1029 memory: --app-listen on main (68c9933); U9a release notes (kernel 0.0.9, schema 12, bridge grants, push extra) 2026-10-09 09:40:02 -07:00
vh 8a149a9719 memory: Prime approved the SVOS app-traffic ingress shape; build deferred until after snapshot 2026-10-09 09:39:09 -07:00
vh f613047ccf memory: pending Prime — SVOS app-traffic ingress shape for U13 2026-10-09 09:14:18 -07:00
vh 51da9ff5ea docs(nh3-svos): kernel 0.0.8 reader pool live; LimitNOFILE stopgap removed; soak flat 2026-10-09 05:45:14 -07:00
vh 457707c9ff memory: SVOS leak root-caused; kernel 0.0.8 (b588510) awaits Prime's push 2026-10-09 00:01:52 -07:00