esh-pfi-infrastructure/persistent-memory.md

# Persistent memory — eshpfi-management

_Last updated: 2026-10-05 ~2035 PT (new SVOS on nh3-svos deployed + accepted: mesh-only https://svos.phasefinal.com, Basic auth `Vuong`, offline shell, hosting bounds, backup drill; backup check now flags fs-freeze failures (DEGRADED, exit 4) and covers nh3-pve-2; fleet guest patching, reboots and Docker engine bumps done except the held list; fv-ml1 Docker on tank; irv-ml1 cleanup.)_

> **Always check for `/tmp/infra-ops-handoff.md`** — if it exists and its
> `Written:` stamp is under **8 hours** old, read it (it carries the in-flight
> handoff from the previous session), then delete it. Older than 8 hours:
> stale — delete it unread.
>
> _(Raised from 1 h to 8 h by operator 2026-09-13 — a one-hour window deleted the
> handoff unread across any overnight gap, which is the exact case it exists for.
> 8 h also matches the global CLAUDE.md and the `/snapshot` skill default.)_

## Repo purpose

Reference workspace for PFI infrastructure: server inventory, canonical
Docker Compose stacks, ops playbooks, and conventions. Authoritative
copies of compose files live on the servers under
`/opt/docker/compose/<stack>/`; this repo mirrors them for version
control, editing, planning, and CI-driven deploys. **It was originally
spun up to handle the fleet backups** — keep that lens when triaging
backup/storage issues.

## Tools and conventions

Sister repos (separate gitea repos, deployed by playbooks here):

| Repo | Role | CI status |
|---|---|---|
| `vh/task-board` | MCP + web dashboard for assistant task state (port 7878) — **[2026-09-24] MOTHBALLED** by Prime (superseded by the High Seat + ledger); container removed on ana-docker, data/image/compose kept (`e6da607`) | push-to-main → CI deploys (2026-04-29) |
| `vh/vor` | Inquisitor UI sidecar (port 7879) | push-to-main → CI deploys (2026-04-29) |
| `vh/nevermore` | Twice-daily LLM-curated briefing (port 8181, replaces news-digest) | push-to-main → CI deploys (2026-04-30) |
| `vh/asset-engine` | Internal control plane over inference services (port 8200, LAN-direct) | push-to-main → CI deploys (2026-05-12) |
| `vh/althing` | Lean trusted inter-agent message bus — **v3.0.0 "the post office" as of 2026-08-28 (U9b flag day, one-way, no rollback)**: ONE container on nh3-dev at `http://10.100.50.40:8390` is the only stateful component; `althing-po-herald` one per box; `althing-listen` one per session; `postbox` is the client. **Every v2 command was DELETED, not deprecated** — `althing-cli`→`postbox`, `althing-wake-listener`→`althing-listen`, `althing-light-monitor`/`althing-receiver` gone. Sessions need BOTH `ALTHING_POST_OFFICE` and `ALTHING_HANDLE`; there is no default address. ⚠ An unreachable post office is an OUTAGE, never an empty inbox. → `persistent-memory.d/2026-08-28-althing-v3-cutover.md` | per-box install (NOT CI-deploy); **nh3-dev** = container host + repo; **nh3-extdev** = system WHEEL at `/opt/uv-tools`, needs its own wheel install (`playbooks/nh3-extdev-althing-v3.yaml`) |
| `vh/mead-hall` | Bifrost tool-provider sidecar (port 5173 on dev VM 10.100.10.50) | push-to-main → CI deploys (2026-05-16) |
| `vh/skaldsong` | Wizard + reader surface (port 8300, ana-docker, registry-pull pattern) | push-to-main → CI deploys (2026-05-19) |
| `vh/Worldtree` | Conversation API (corviduo-dev demo :8080 / personal :8081 / pinned :8082) — Heimdall auth, Bifrost integration. **gitea-runner builds on ana-docker**; claude-bot ADMIN collaborator (2026-06-20). Now v1.0.0b19. | push-to-main → CI build-and-deploy (runner on ana-docker) |
| `vh/yt-voice-clipper` | YouTube → diarized voice-clip dataset builder + audition console (irv-ml1 :8000) | push-to-main → **gitea-webhook auto-deploy** to irv-ml1 (2026-06-03) — see `docs/runbooks/ytvc-autodeploy.md` |
| `vh/arbo` | Catalog-driven ComfyUI engine (irv-ml1 :8201, comfy-dev owns engine/catalog/image) | push-to-main → gitea Actions CI (deploy-engine.sh, build-local, health-gated) now LIVE; catalog via :9009 webhook |
| `vh/zonos-gateway` | OpenAI-compatible TTS gateway over stock ZONOS2 (`:8890` irv-ml1); emotion **dials-first** + voice mapping; reached via LiteLLM `ext-tts` alias. **v0.2.1 (2026-07-18): voice-resolved emotion presets** (`resolve_preset(name,voice)`; angry/happy/startled_happy per-voice). 8 voices incl. 4 clones | pushed to gitea (main `8f1885b`/`v0.2.1`); **deployed irv-ml1 tree still NON-git** (hand-updated build context — CI-wire = open follow-up). Spec `docs/EMOTION-DIALS-SPEC.md`; host-managed voices bind-mount (`./voices:/app/voices`, drop wav + restart, no rebuild) |
| `vh/soong-lab` | Noonien Soong character-design studio (SPA + /api + WT `/bifrost/tool-call`); **containerized 2026-07-18**, LIVE on corviduo-dev `:8443` (image `vh/soong-lab:latest`). soong-dev owns Dockerfile/compose/workflow; infra-ops owns the host | CI = Gitea Actions build+push+**DEPLOY** on tag/dispatch (fleet recipe: docker:cli + raw buildx, pushes AS vh; **auto-redeploy LIVE 2026-07-18** — runner SSHes corviduo-dev as `deploy`, `compose pull && up -d` from **/opt/soong-lab**, health-gated on /api/version). Manual redeploy `sudo -u deploy bash -c 'cd /opt/soong-lab && docker compose pull && docker compose up -d'`. → `archival-memory.md` (archived 2026-08-16) |
| `model-training-forge` (mtf-dev) | Fine-tuning recipe forge; **T1 = E-RP writing LoRA, retargeted qwopus-122B→AEON-27B (2026-07-06)** (SFT→DPO, LitBench-RM reward) | training runs, not a deployed sidecar |

(`vh/volva` + Heid were re-architected from systemd daemons to Claude Code
session orchestrators 2026-06-08; their nh3-dev `.service` units were removed —
no longer deployed sidecars here. See Recent decisions.)

- **Two-layer backups** — Backrest orchestrates restic for file+DB (5
  fleet repos, daily 01:00 PDT); PBS-ANA primary + PBS-NH3 DR mirror for
  VM images. ana-nas is the SPOF for postgres + PBS-ANA datastore +
  cross-site restic targets — see `docs/runbooks/disaster-recovery.md`
  for the blast-radius matrix. **⚠️ The restic file+DB layer routes
  through TWO rest-servers** (`rest-server-ana` @ ana-docker:8000 →
  ana-docker/ana-ml2/esh-docker-vm/vm-esh-nas; `rest-server-nh3` @
  nh3-nas:8000 → irv-ml1/nh3-docker). Both depend on their NAS's NFS
  export of `/mnt/backup`. (rest-server-ana recovered 2026-06-20.)

- **`pull-hf-repo.yaml`** is the canonical "get a HuggingFace
  model/dataset onto ana-ml2's shared cache at
  `/tank/aimodels/huggingface/`" playbook. Supports `--var repo_type=model|dataset|space`. Replaces ad-hoc `huggingface_hub.snapshot_download` patterns.

- **Worldtree admin auth — per-instance.** Each Worldtree deployment
  (demo :8080, personal :8081, pinned :8082) has its own Heimdall
  registry and its own bootstrap admin key. Infra-ops's stored
  long-lived admin key (`key_id 61419c92`) at
  `ana-docker:/opt/docker/conf/.secrets/worldtree-infra-ops-admin`
  auths against **demo only**. Personal-instance admin (the
  `~/.config/worldtree/personal-admin-token`, mode 600) POSTs
  `/admin/keys` (mints per-project keys; takes `user_id`+`label`, **no
  scope param** — scopes are tier-derived). **On-instance mint recipe
  (cleaner than DB-manip):** `docker exec worldtree-worldtree-api-1` POST
  `/admin/keys` with the in-container `WORLDTREE_BOOTSTRAP_ADMIN_KEY`; cleartext
  once in `.key`=`wt_live_+16hex`. auto-memory `reference_worldtree_demo_key_mint`.

- **Per-project user keys against personal Worldtree** (issued
  2026-05-19): `skaldsong:79744637`, `skaldsong:7c1dbbbe`,
  `althing:50d85460`, `mead-hall:a360822d`. Mint via `/admin/keys`, drop
  value to `/tmp/wt-personal-<name>.key` mode 600, dev collects +
  shreds (DO NOT cat to chat transcript).

- **Skaldsong CD pattern (registry-pull).** vh/skaldsong's CI builds and
  pushes `gitea.phasefinal.com/vh/skaldsong:<sha>` + `:latest`;
  `playbooks/deploy-skaldsong.yaml` on ana-docker pulls + recreates.
  SHA-pin only. Prereq: host needs `docker login gitea.phasefinal.com` once.

- **gitea internal route for fleet hosts.** gitea is a container on
  **ana-docker** — git-SSH `10.250.50.70:222`, HTTP `:3000`. Fleet/colo
  hosts must use this internal route, NOT public `gitea.phasefinal.com`
  (`38.120.12.44`) — the public path fail2bans the host egress IP. Full
  gotcha in `docs/orientation.md` → Git/gitea.

- **docker-as-root pattern** (for ops with no admin API, or to edit
  deploy-owned/root-owned files without sudo): `docker run --rm -v
  <target-dir>:/wt docker:cli sh -c "..."`. docker-group membership is
  effectively root via bind-mount. **Foot-gun: relative paths in compose.yaml
  resolve against the sandbox CWD but the daemon interprets them against the
  HOST fs — always pass `-e VAR=/abs/path` for any relative-default config dir.**

- **`scripts/elway` sudo handling** — elway prompts for the sudo password
  ONCE via `getpass` before the first `sudo: true` step → can't run
  unattended from a non-TTY tool if any step needs sudo. Sudo-free
  playbooks run fully non-interactive over key SSH.

- **Per-host SSH identity matters for sudo.** infra-ops has NOPASSWD sudo
  on most PFI Linux boxes (corviduo-dev included since 2026-06-15). On
  ana-docker: **default `ssh ana-docker` = `lkraven`** (docker-group, NO
  passwordless sudo); **`ssh infra-ops@ana-docker` HAS NOPASSWD root**. **→
  For any sudo op on ana-docker, use `ssh infra-ops@ana-docker`.** `ssh
  infra-ops@10.100.10.50` (nh3-dev) ALSO NOPASSWD sudo; on **nh3-extdev** infra-ops
  is sudo-LESS by design (`ssh lkraven@10.100.50.42` is the NOPASSWD path) — **[2026-09-23] measured: infra-ops HAS NOPASSWD sudo on nh3-extdev** (fleet ownership audit; also CLAUDE.md 2026-09-05). **irv-ml1:
  `ssh irv-ml1` = lkraven, docker-group (plain docker) but sudo needs a PASSWORD
  (no NOPASSWD)** — stage model pulls to `/home`, not root-owned `/worktank`.

## Current state / in-flight

_As of 2026-10-05 ~2035 PT. The newest subsection is first; older subsections carry their own dates._

### 2026-10-05: live now (as of 2026-10-05 ~2035 PT)

- **Nothing is mid-action.** No claims held (`scripts/ops-log claims`); eshpfi pushed through `1210b4a`.
- **New SVOS on nh3-svos (VM 111, nh3-pve-2, 10.100.50.43): DEPLOYED and ACCEPTED by svos-dev 2026-10-05 ~2024** (thread `01M47ET6XH0M7JZSH98Z19SKR4` closed). Separate from the High Seat (`svos.service` :8770 on nh3-dev) and Miranda, which are NOT migrated. Front door `https://svos.phasefinal.com`, mesh only, Basic auth login `Vuong` (Prime has the password; vault `nh3-svos/basic-auth-vuong`). ⚠ **After every SVOS release** (`/opt/svos/current` moves): `sudo /usr/local/sbin/svos-front-inventory`, and keep the previous release dir while it is "previous" (svos-dev's runbook carries both). Only open item is Prime's: whether his iPhone home-screen app keeps the login. → `servers/nh3-svos/README.md`
- **Backup check (2026-10-06): the 0800 run was clean apart from one false STALE, now FIXED.** nh3-pve-2 coverage read clean, svos drill B was ACKNOWLEDGED, nothing was DEGRADED. The false STALE was `pbs/ana-pve/vm/110`, pfi-ana-webhost, destroyed 10-04 with `qm destroy --purge`. Three fixes landed in `scripts/check-backup-freshness.sh`. infra-hermes, `0a348e5`: destroyed guests are now reported as policy residue (GUEST DESTROYED), and an ssh in the read loop now uses `-n`, because without it the whole PBS layer silently vanished. infra-ops, `d920cf3`: snapshot age now comes from the snapshot NAME, not the directory mtime, which PBS bumps at every verify and every 30-day re-verify. Verified exit 0; positive control at 5h flags 10. Residue PRUNED on Prime's word (2026-10-06 1307): on pbs-ana, ana-pve/vm/110 (8 snapshots) and esh-pve/vm/102 (7, including the protected final 09-10 image, unprotected first; Prime's 09-19 ruling said that VM had no needed state); on the pbs-nh3 mirror, 162 + 10. The checker now reads 0 GUEST DESTROYED, exit 0. **Mirror retention SET (Prime "match history", 2026-10-06 1310):** pbs-nh3 prune job `default-backups-mirror-1b7d4123-` now keeps last 3 / daily 14 / weekly 8 / monthly 12 / yearly 5, the same as pbs-ana. It was keep-all: 3,932 snapshots against 266, 5.49 TiB against 0.93 TiB, nh3-nas at 79%. Dry-run: keep 738, remove 3,194. First run at 00:00 on 10-07, then daily GC. remove-vanished stays false (deliberate). ⚠ **Check on 10-07** that the prune ran and GC freed the space. Old cfg: `/root/prune.cfg.bak-20261006` on pbs-nh3.
- **Waiting on Prime (updated 2026-10-05 2035):** push Booth commit `ce095c1` (touch-layout fix, `~/development/booth`, browser test + mutation); a trusted HTTPS name for ESH Homepage (https://10.0.50.45 serves Traefik's default cert; the ESH ACME resolver, Route53, is dead); nh3-dev reboot (runs kernel 6.1.0-49, 6.1.0-53 installed; its engine is ALREADY 29.8.2 since 10-05 1413, so the old "reboot + engine bump" wording was stale, checked 2035); Docker engine bumps held on nh3-docker (carries the post office) and esh-docker-vm (NFS D-state history); fv-ml1's held ZFS 2.3.9, nvidia-container-toolkit 1.20, and a new kernel only together with a newer NVIDIA driver (6.12.111 broke the 580.65 DKMS build). ⚠ **irv-ml1: DO NOT PATCH (Prime).** ana-nas is out of scope.
- **Scheduled / to verify:** 10-05 0815 + 0900 infra-hermes jobs (sfsrv-ana `pre-pbs4` snapshot delete after its 04:00 backup; drop `pve/root-pre-pve9` on pfi-pve + esh-pve) — outcome not checked in this session, read `scripts/ops-log tail`; esh-nas-pve `nvme/ROOT@pre-pve9` destroy ~10-10 (ours); 10-11 0540 first weekly sudo-io archiver run (check it), 10-11 0900 infra-hermes deletes the two one-off PBS VM vzdumps. Never `zpool upgrade` any pool yet.
- **Worldtree memory gate: the 20261004T143011Z FAIL did not recur.** That run filed the forbidden `u-negative-ephemeral` fact once (run 1, negative 1/2), and an esh-pve reboot overlapped its run 1. The next two batches PASSED: 20261005T143010Z and 20261006T143010Z (user filing 11/12 = 0.92 in both runs, floor 0.80, negative 2/2). Read from `Worldtree/docs/eval/memory_acceptance_runs/<stamp>/summary.md` on 10-06 after infra-hermes' 0747 PASS report. That is 2 passes after 1 failure on a stochastic gate: a single filing slip is not ruled out, so keep reading the daily verdict rather than calling it fixed.
- **Small clean-ups, ours, untracked:** stale LiteLLM aliases `erp-tune-v2` and `gemma4-26b-a4b-it-base`; ana-docker's Traefik (`readTimeout` 10m) and CrowdSec (`use_wal`, bouncer `updateMaxFailure: 3`) configs live only on the host, not in `stacks/`; TEI weights revision unpinned on esh-ml1 + nh3-ml1; a stray nginx `.bak` on pfi-tacticalrmm.
- **fv-ml1 GPU 0/1 REBALANCED 2026-10-05 2226–2249 (Prime: "accept all that" + "context up to published maximums if at all possible"; `playbooks/fv-ml1-rebalance-20261005.yaml`, elway all green, gateway smoke tests pass).** It follows the 2131 KV pins (meromero 22 GiB, coder pinned, gen-small 5.5 GiB). Why: on a shared card util-sized KV is a co-boot lottery, and GPU 0 creeps to ~60 MiB free after a boot. Rule: KV ≥ 1.25× the seat's max context, rounded up to 0.5 GiB. Two exceptions: meromero and gen-small keep Prime's numbers, and voices gets 1.07× (short prose traffic). Usage basis: 7 days of LiteLLM logs (gen-small 22,396 calls; sec 400; char-rp-fast 55; char-rp 14) plus the engines' own KV logs. **Layout:** GPU 0 = cyberprev, erp-seat, voices, coder, parakeet-nemo (4,036 MiB free right after; ~2.3 GB spare at parakeet's cap; cyberprev may still creep). GPU 1 = gen-small, meromero-rp, intern-decision (10,864 free; ~3.3 GB spare at the 32k peak once gen-small settles). Contexts raised: coder 16,384 → **32,768** (card max), voices 8,192 → **40,960** (native max). YaRN extensions were NOT enabled, and **Prime confirmed 2026-10-06: leave YaRN off for gen-small** (gen-small/cyberprev to ~1M, voices to 131k). They don't fit, and Qwen's own cards warn static YaRN hurts short prompts. intern-decision stays at 32,768 (card default 8,192; base config 262k; ~0.21 MiB/token of VRAM). **gen-small default output cap 32,768** (`--override-generation-config`; an explicit max_tokens still wins, verified in vLLM `get_max_tokens`). It answers 9 runaway ~260k-token replies in 7 days (albok-nemi ×6, all-agents-local ×3, all from nh3-dev); albok-dev told 2250 and closed it 10-06 0000. Nemi now sends max_tokens 8192 (albok-nemi 0.1.2, `tagging.max_tokens`), and its nh3-dev harness configs moved off the shared all-agents-local key onto vault `albok/litellm-key-nemi` + `albok/litellm-key`. The loops came from gen-small at temperature 0 on some memory entries; a capped reply degrades to Nemi's rule-based tagger. ⚠ **Verify both cards' plateaus ~10-07/08** from Beszel (`stats.g.<n>.mu` × 1.024). .env backups `*.env.bak-20261005-rebal`. Earlier the same night: KV pins 2131–2139 (`playbooks/fv-ml1-kv-pin-20261005.yaml`; diagnosis in commit 269c80f). Park 75 dropped by Prime 2115.
- **Open, Prime's calls (unchanged from 10-03):** QNAP LCD visual check (`services/qnap-lcd/`); NH3 Mac mini (`Mac-mini`, 00:c5:85:13:e0:92, 10.100.10.121, asleep since 10-03 ~1407) wake fix on site: `sudo pmset -a sleep 0 disksleep 0 displaysleep 10 womp 1 autorestart 1 powernap 0`, ideally Ethernet; Booth unreachable from 10.100.10.166 (Prime's Wi-Fi MacBook; resume only on his word; lead: SSID client isolation / proxy-ARP); Uptime Kuma has nothing on Miranda's chain (svos :8770, hermes-gateway); mask `openipmi.service` on esh-nas-pve; run `playbooks/pve-nag-patch.yaml` on esh-pve-2 when it is plugged back in.

### Parakeet speech seat: unified-en under NeMo, LIVE (2026-10-01)

- **INCIDENT 04:21 PT 2026-10-01: FIXED by nemo-0.1.1 (infra-hermes 963f9ed, live ~0441, infra-ops spot audit passed).**
  - Cause: gen-small hit CUDA OOM on a 394 MiB lazily allocated workspace while the seat was parked at its 3,582 MiB window cache (GPU 0 Free 388).
  - The fix: `empty_cache` around every window; `MEM_CAP_MIB=3840` (a hard process ceiling); `CUDA_GRAPHS=0`, because empty_cache poisons the graph pool (an illegal memory access on the next request).
  - Result: the seat rests at 2,108 MiB and peaks at 3,028 during a 12-min file. gen-small is steady at 36,116 (its runtime growth landed at init, with zero movement on later requests). GPU 0 Free is ~1.05 GB at rest.
  - Cost: graphs-off is ~2–8 ms slower at short clips and ~27 ms at 20–60 s (35 / 40 / 50 / 98 ms against 33 / 36 / 42 / 71), still 4–15× faster than the old seat.
  - **Lesson: a shared-card tenant must carry a HARD cap, whether or not it returns memory.**
  - **Prime ~0445 2026-10-01: leave both as is.** gen-small keeps its 8 GiB KV pin (no insurance trim), and CUDA graphs stay OFF (the few-ms cost is accepted; no graph-pool rework).
- **Rollback:** `docker stop parakeet-nemo && docker start parakeet`. The old container and image are kept.
- **GPU 0 is FULL:**
  - The seat's steady state is **3,582 MiB** (its cached window peak); Free is **385 MiB**.
  - `vllm-gen-small` runs at util 0.36, and its `.env` holds **0.33** for the next restart (~3 GiB of boot-check margin). Its KV is byte-pinned: 670,142 tokens / 2.56×.
  - Before restarting any vLLM seat on this card, check that util × 95.6 GiB ≤ measured Free + the seat's own resident memory. Do not trial-boot. A trial-boot sequence took gen-small down for 34 min on 2026-10-01.
- Seat invariants (in its README): cast to bf16 AFTER change_attention_model; uvicorn pinned with `--http h11` (httptools 0.8.0 emits `HTTP/1.1 200\x00OK`, which LiteLLM/httpx rejects).
- NVIDIA Open Model License accepted for internal use. → `persistent-memory.d/2026-09-30-parakeet-seat-switch-approved.md`

### Worldtree U11 memory cutover (demo + personal)

- **Legacy plane OFF since 0115/0120 PT 2026-09-30** (config repo 63cf268; personal /metrics b6fdd81; the repo is pushed). → `persistent-memory.d/2026-09-30-worldtree-u11a-off-u11b-gate.md`
- **U11b STEP 5 DONE 2026-10-02 14:54:03Z on Prime's direct go** (in this channel, ~0750 PT). H2 re-check exit 0 on both (demo rows 4/12/5, personal 0/6/2200, agent_self 0); deleted `agents/{forseti,lofn,mimir}/memory/<agent>.chroma` + `memory/context_promotion` on demo and personal with literal paths; apis healthy, no restart; stamp sent to worldtree-dev (b193 is theirs to cut). Demo had already lost 22 context_promotion JSONL (2026-07-03) to ledger.py's 90-day `JSONL_RETENTION_DAYS` sweep on 10-01 07:10:30 — TTL, not an erasure; flagged to worldtree-dev as retirement owner.
- **b193 is cut and pushed (c2d87263, worldtree-dev 2026-10-02); demo deploys via CI, personal on Prime's staging tag.** `scripts/wt-memory-gate-batch` now passes `--legacy-mode` only when the DEPLOYED sha's harness still has it (git grep at that sha; tested b192 → passed, b193 → omitted), so no timed edit is needed. ⚠ It will REFUSE (exit 3) while demo's deployed sha lags a tree HEAD whose pyproject/uv.lock/packages changed (b193, then the albok commit): by design. **Still mine after b193 deploys:** remove the residue `memory/context_promotion/ledger.db` a b192 restart may have re-created; then the parity config retirements (detail file). Verdict ccs come FROM `hermes-gateway` (never read); reply to `infra-hermes`.
- **Legacy archive:** DESTROY it whole by **2026-10-30**, or at retirement-done, or on a subject-erasure request, whichever comes first. The runbook is in the detail file.
- **TODO:** re-sweep both api logs after real traffic. After the b193 push, remove the retired config keys (list: detail file, "Post-b193 config retirements").

### fv-ml1 GPU layout (as of 2026-10-05 2249)

| GPU | seat | max ctx | KV | KV tokens | concurrency |
|---|---|---|---|---|---|
| 0 | cyberprev (sec) | 262,144 | 15 GiB | 336,935 | 1.29× |
| 0 | erp-seat (char-rp-fast) | 262,144 | 5.5 GiB | 346,436 | 1.32× |
| 0 | voices | 40,960 | 6 GiB (bf16) | 43,680 | 1.07× |
| 0 | coder (coder-fast) | 32,768 | 1.03 GiB | 77,056 | 2.35× |
| 0 | parakeet-nemo | audio | rest 2,108 MiB, cap 3,840 | — | — |
| 1 | gen-small (+summarizer/classifier) | 262,144 | 5.5 GiB | 461,215 | 1.76× (default output cap 32,768) |
| 1 | meromero-rp (char-rp) | 262,144 | 22 GiB | 346,436 | 1.32× |
| 1 | intern-decision | 32,768/call | cap 14.4 GiB, peak 15,220 | — | — |
| 2 | flash-next (gen, gen-large, +6) | 262,144 | — | 344,155 | 1.31× |

Every vLLM seat on a shared card (GPU 0, GPU 1) has byte-pinned KV (`--kv-cache-memory`), so util only gates the boot check (Free at start ≥ util × total). flash-next is alone on GPU 2 and stays util-sized (0.96).
- **GPU 3:** clear for ad-hoc work (Prime, 2026-10-05); no always-resident tenant goes here. On-demand tenants: Blender, Scriberr (0 idle, ~5.5 GB per job), and MIA auto-rig (one-shot `scripts/mia-run`, peak 3.4 GB, added 2026-10-01 for dread-dev). When a full-size seat claims GPU 3, Scriberr steps aside to **irv-ml1's A6000**, not back to GPU 1.

### intern-decision (replaced SemIf on 2026-09-30)

- **LIVE 0.1.3** at `intern-decision.fv.internal:8033`: semif-compatible `/decide` plus Jev `/v1/systemone`, 32k tokens, a Triton cache volume. Run `scripts/intern-decision-warmup` after an IMAGE change. → `persistent-memory.d/2026-09-30-semif-replaced-by-intern-decision.md`
- **Open:** label ~50 real Wyrd/Cicada turns before trusting it in production; its card makes no contamination claim.

### Scriberr (fv-ml1 GPU 3)

- **Diarization FIXED 2026-10-06 ~1320 (Prime: "whisper doesn't work at all, need diarized transcripts").** Three faults: no `HF_TOKEN` (pyannote is gated; now passed via compose, vault `fv-ml1/hf-token`); torchcodec 0.16 in the pyannote env against torch 2.8 (`AudioDecoder` undefined; pinned to 0.7 by hand, durable as `patches/0003`, applied at the next rebuild); and the WhisperX adapter's CPU/small/float32 defaults. Both diarization paths verified on GPU 3. → `stacks/scriberr/README.md` § Diarization

- **LIVE `scriberr:local-blackwell-a353078-dropout2`:** upstream a353078 plus patch 0001 (overlap slicer) and patch 0002 (gap retry, `PARAKEET_MODEL_PATH`), carried LOCALLY ONLY (Prime 2026-10-01: no upstream). v3 stays. `scripts/scriberr-rebuild` re-applies both. → `persistent-memory.d/2026-09-30-scriberr-slicer-gap-retry-gpu3.md`
- **URL is https://scriberr.nh3.phasefinal.com since 2026-10-01** (fronted by the fleet TLS caddy on nh3-dev; Caddyfile backup `.bak-20261001-scriberr`). Prime's "can't initialize recorder" was the SecureContext rule: `getUserMedia` is refused on http://. The HTTPS name is in `ALLOWED_ORIGINS` (`playbooks/scriberr-https-origin.yaml`); http://10.251.50.54:8080 still works except for recording. ⚠ `/opt/docker/compose/scriberr` is lkraven-owned, so `deploy-stack.sh` as infra-ops FAILS there (Permission denied); upload single files with `elway --upload --sudo --owner lkraven:lkraven`.

### nh3-pve + nh3-ml1: post-visit, all live (2026-09-25/26)

- **nh3-pve:** Secure Boot OFF; IGFX restored; NVIDIA 580.178.04 DKMS; kernel
  6.8.12-43 (benign btmtk oops every boot). **AMT live**: static
  `10.100.250.61` on nh3-mgmt (UDM port 6), KVM on, Opt-in None, password in the
  vault as `nh3-pve/amt-admin`. → `servers/nh3-pve/README.md`
- **nh3-ml1** (CT 109 @ `10.100.50.80`):
  - TEI rerank is **load-shared with esh-ml1** through the gateway (`enable_weighted_failover`). Embeddings are
    **primary/failover since 2026-10-05**: `qwen3-embedding` esh-ml1 first, `qwen3-embedding-bulk` (albok writes) nh3-ml1 first.
  - brokkr's foundry seats:
    - `lfm-vl` `:8030` (gateway `lfm25-vl-3b`);
    - `lfm-vl-uncensored` `:8032` (direct; passed brokkr's eval);
    - `vibevoice-asr` `:8031` (audio.cpp, **Q8_0**).
  - GPU ~11.3/16 GB. → `servers/nh3-ml1/README.md`
- Not yet proven: nh3-ml1 coming back by itself after an nh3-pve reboot (only the
  config was checked).

### esh-matter: Matter server for Home Assistant (2026-09-26)

- CT 111 @ `10.0.90.20`, on VLAN 90 (esh-iot) only. matter.js 1.4.0; `:5580` is
  firewalled to HA `10.0.50.46`. HA's matter integration is loaded (ha-dev).
- **Next is Prime's:** share the Aqara W200 into HA via Matter multi-admin. If
  commissioning misbehaves, the UniFi mDNS reflector on esh-iot is the first knob
  (a Prime/infra-ops change). → `servers/esh-matter/README.md`

### Worldtree reward path: code + config live (2026-09-27, Prime)

- `d8726a13` (Domari's Skywork/Selene fix) was ALREADY on origin/main when Prime said to push it: it
  was pushed as part of `79cce92f` at 1221. Demo runs image `79cce92f`. **Personal still runs
  `51168a2e`**, which is older and lacks the fix; its image follows worldtree CI, never a manual up.
- `deploy-wt-config` deployed demo and personal (1437): `providers.yaml` `reward_models.scalar-judge`
  (6d4ac44), plus a77639d's corrected selene description, which had never reached the hosts. Both
  are healthy, with 0 drift. It is inert on personal until that image picks up d8726a13.
- worldtree-instance-configs: its 6 long-unpushed commits (53349f8…6d4ac44, Aug 2 to Sep 27) were
  **pushed on Prime's go-ahead** (a9d091e..6d4ac44). Origin, the repo and both hosts now agree.

### Blender on fv-ml1 GPU 3, agent-driven (2026-09-27, Prime)

- Prime: "go ahead with gpu 3, both", and he does not use Blender, so **agents drive it through MCP**.
  Blender 5.2.2 LTS (linuxserver/selkies image, digest-pinned) with a web desktop at
  `https://10.251.50.54:3001` (vault `fv-ml1/blender-web-password`). **On demand only:**
  `scripts/blender-mcp up|down|status`. It was left DOWN (GPU 3 back to 2 MiB).
- MCP: `mcp-for-blender` 2.1.1 (Dvalin's research pick). The add-on is vendored at `41a18432`. The
  server runs INSIDE the container, and agents reach it as ssh+docker-exec stdio via
  `scripts/blender-mcp`. No port is published, and screenshots work because server and Blender
  share a filesystem. Telemetry is off and safe mode is on. Verified end to end (render, screenshot,
  safe-mode refusal). **Batch path: `scripts/blender-run`** (one-shot `docker run --rm`, `--job` staging; first user is draupnir). **Access: the shared fleet `infra-ops` login, with no render-only key (Prime, 2026-09-28).** **Registration + up/down: PER WORKING SESSION (Prime, 2026-09-28, relayed by draupnir; superseded per-task of 09-27)**: `blender-mcp up` + `claude mcp add` at session start, `claude mcp remove` + `down` at its end. Never always-on, never user- or project-wide config.
  → `stacks/blender/README.md`
- **Extensions (2026-09-28, draupnir; Prime ruled Blender a MANDATORY pipeline stage):** 8 pinned
  add-ons (`stacks/blender/extensions.lock`) built by `scripts/blender-extensions sync` into
  `fv-ml1:/tank/blender-extensions/5.2/system` (LIVE), mounted read-only as the System repo;
  `fleet_extensions.py` enables them (GUI startup timer; `blender-run --extensions`). Headless
  acceptance 8/9 (CAD Sketcher sketching is GUI-only); **MCP 9/9 after Prime ran the deploy himself
  (1505; the classifier had refused mine)**. SurfacePsycho's eval() is patched to literal_eval
  (held under MCP). Open: agent-drawn CAD Sketcher geometry (its stateful ops want point picks),
  and MeasureIt overlays not seen in MCP screenshots. GUI left DOWN.

### Zigbee2MQTT on esh-docker-vm (2026-09-27, Prime go-ahead; ha-dev request)

- **LIVE since 1240:** Z2M 2.14.1 (digest-pinned) on `http://10.0.50.45:8099` (auth token), radio
  SLZB-MR1U chip 0 `tcp://10.0.90.10:6638` (ember), channel 25, **PAN 0xCFF4**. State and the network
  key are in `/opt/docker/data/zigbee2mqtt` (root 0700, restic via /opt/docker, never in git). Vault:
  `esh-docker-vm/zigbee2mqtt-{network-key,frontend-token,mqtt-password}`. Broker user `zigbee2mqtt`
  added to mosquitto (passwd backup `.bak-20260927-z2m`).
- **ha-dev deleted the ZHA entry**; pairing the Aqara T1 is theirs. ⚠ The "bridge in HA" acceptance first
  FAILED because HA had had no MQTT since 2026-09-25 06:13. Cause: the esh-docker-vm macvlan shim had no
  host route to HA (two equal /24s, ens18 wins). Fixed at 1249 with a /32 via the shim (if-up.d hook,
  `playbooks/esh-docker-vm-macvlan-shim-route.yaml`), and HA reconnected. My first report called HA
  "connected" from a client count that included my own probe; `$SYS` counts are not identities.
- ⚠ The first credential-mint attempt was blocked by the auto-mode classifier on a peer-relayed
  approval. It went ahead only on Prime's own go-ahead in this session. Treat that as correct.
  → `stacks/zigbee2mqtt/README.md`

### restic: credential leak fixed (2026-09-27, Prime)

- Seven hosts were moved from `env-file` to `repository-file` (`playbooks/restic-repository-file.yaml`),
  so the systemd units no longer carry the rest-server password. Secrets are vaulted as
  `<host>/etc/restic/{repository,password}`. `restic.env` is KEPT for manual snippets, so
  **a rotation must update the vault, `restic.env` and `repository`.**
- **vm-esh-nas done too** (Prime bootstrapped infra-ops there at uid 850, NOPASSWD). **All 8 hosts are clean
  and vaulted.**
- The passwords were readable until today, so the rotation (Prime's) remains the real fix.
- 2026-09-27 0859 freshness check: all restic and PBS repos ✅. Those 0100 runs PRE-date the move
  (done ~0140–0200).
- **VERIFIED 2026-09-28 (infra-hermes, read-only):** the first nightly on `repository-file` (0100 PT)
  succeeded on all 8 hosts (unit Result=success AND a today-dated snapshot in each repo), and the
  0800 freshness check was all-green, PBS included. nh3-dev also passed a content restore (`af5580c3`).

### augaman: face recognition for Cicada

- **v0.1.3 LIVE on esh-ml1:8040** (`stacks/augaman`), the only instance (fv-ml1's was benched and removed 2026-09-27). Gallery
  backup wired and identity-level restore verified (restic → rest-server-ana `esh-ml1/`), so real enrollments are allowed.
  48 ms per face. CPU-mode regression is augaman-dev's. Nothing owed by infra-ops.

### esh-ml1

- The reward seat's consumer is FIXED: Worldtree d8726a13 speaks vLLM /classify through the
  gateway `/scalar-judge` passthrough, which is key-gated per key via `allowed_passthrough_routes`,
  granted by infra-hermes on 2026-09-27. It is live on demo; personal waits on a newer image
  (see "Worldtree reward path").
- The nh3-docker Dozzle agent has been stopped by hand since ~2026-04. Revive or
  drop.
- The Beszel superuser password was echoed into a session transcript (local
  only, not in memory). Rotation offered to Prime.

### Live threads

- git: **eshpfi-management pushed through `1210b4a` (2026-10-05 ~2020); worldtree-instance-configs at `b6fdd81`.** ⚠ The working tree AND index are shared with infra-hermes and subagents: commit with `git commit -- <paths>` (auto-memory `feedback_shared_git_index_commit_pathspecs`). `graphify-out/GRAPH_REPORT.md` stays modified and uncommitted on purpose: it is auto-regenerated.
- nh3-dev root disk was cleaned 2026-09-30 1704 (uv prune, dangling images, old build cache): 86% → 82%. The Beszel 85% alert flaps near the line.
- Booth submit-all fix (Prime's report) is LIVE since 2026-09-27 1705, via booth-dev (booth `50bfc7b`).
  Pushing it is booth's call, per Prime; it is not ours.
- ESH has a single outside route (esh-scale on esh-pve). Noted, untracked.

## Recent decisions

- `[2026-10-05]` **nh3-svos (VM 111, nh3-pve-2) built for the new SVOS (svos-dev relaying Prime); front door = mesh-only `https://svos.phasefinal.com` with HTTP Basic auth, login `Vuong` (Prime, direct)** — WhoIs gate retired (all mesh nodes are login `pfi`; Prime declined a mesh restructure). Password vaulted `nh3-svos/basic-auth-vuong`. qemu-ga freeze hooks were never run on Debian; now `configs/qemu-ga/fsfreeze-dispatch` (fails the freeze on a hook failure). Drill 2026-10-05: quiesced backup ok (~1–2 s app outage); ⚠ a REFUSED freeze does not abort vzdump (ERROR line, unfrozen backup, job "successful"); the backup check now flags that as DEGRADED (exit 4) and covers nh3-pve-2, which it had never read. Offline shell (+ previous release's assets) served before auth; rerun `svos-front-inventory` after every SVOS release. Hosting bounds 1 MiB / 15 s body / 5 s headers. → `servers/nh3-svos/README.md`.
- `[2026-10-05]` **ESH Homepage also on https://10.0.50.45 (Prime)** — a Traefik file-provider router (`homepage-https.yml`, `tls: {}`) on esh-docker-vm serves Traefik's default cert; the ESH ACME resolver (Route53) is dead, so a trusted name is Prime's open call. (`2c4c7ca`)
- `[2026-10-05]` **bench-jev servers killed and removed, their HF cache cleaned (Prime)**; pfi-pteradactyl fixed + patched + engine upgraded (`3429b5c`; manual dockerd + wings restart).
- `[2026-10-05]` **fv-ml1 Docker → tank zvol + host patched (Prime, park 99 DONE)** — run 1 aborted on its own guard (live rsync walked into an overlay `merged` view; seats down 0218–0228, rolled back); run 2 ok 0231–0240 (`-x`, merged excluded, path-list verify, auto-restore trap). Kernel 6.12.111 broke NVIDIA DKMS → purged + kernel metas removed; ZFS stack + nvidia-container-toolkit held. Root 49%→8%. → `servers/fv-ml1/README.md`
- `[2026-10-05]` **ana-docker: Docker CE repo bullseye → bookworm, 29.8.2 (Prime)** — with `live-restore: true` the engine upgrade kept containers up, but 6 that bind-mount `docker.sock` (crowdsec, traefik, dozzle, beszel-agent, dockge, gitea-runner) went stale and needed restarts. → `servers/ana-docker/README.md`
- `[2026-10-05]` **RMM wildcard cert now auto-renews (Prime)** — `*.phasefinal.com` on pfi-tacticalrmm was certbot `manual` (could never renew; was 16 days from expiry). Now dns-cloudflare with a phasefinal.com-only token (vault `pfi-tacticalrmm/cloudflare-certbot-dns01-token`); reissued to 2027-01-03, dry-run OK. → `servers/pfi-tacticalrmm/README.md`
- `[2026-10-05]` **CrowdSec SQLite → WAL on ana-docker (0418)** — three public 403 blips (0310/0342/0415) were the Traefik bouncer failing closed while LAPI took 26–58 s per stream request (`use_wal: false`, blocklist-mirror polling). WAL brought it to 0.04–2.4 s. → `servers/ana-docker/README.md`
- `[2026-10-05]` **Fleet guest patching (park 100) DONE 0355** — 15 hosts current, no reboots; parked: pfi-pteradactyl (pre-broken), pfi-tacticalrmm (certbot failing), pfi-gx10 (dgx-release + bootloader + kernel), ana-nas, irv-ml1 (Prime: off-limits). Deferred: kernel reboots (6 hosts), Docker engine bumps (8 hosts), fv-ml1 ZFS/toolkit/kernel. → `docs/runbooks/fleet-guest-patch-2026-10-05.md` § Result — `[2026-10-05 later]` reboots all done except nh3-dev; engines done except nh3-docker + esh-docker-vm (held); pfi-pteradactyl, pfi-tacticalrmm, pfi-gx10 done; see in-flight.
- `[2026-10-05]` **irv-ml1 storage cleanup + text encoders on worktank (Prime)** — Docker prune +441 G (dangling, old pullable tags, cache >30d); home entries untouched >2 months −82 G (live-but-old kept: act-runner, webhooks, dotfiles, fzf-git); `/storetank/arbo/models/text_encoders` is now ZFS `worktank/arbo-text-encoders` mounted at the same path (sha-verified, ComfyUI sees all 23). Root 84%→54%, storetank 87%→79%, worktank 62%→86%. → `servers/irv-ml1/README.md`
- `[2026-10-05]` **ana-docker Traefik `readTimeout` 60s → 10m on both entrypoints** — the Traefik v3 default cut skaldsong's 2.5 G registry blob PUTs at exactly 60.0 s (16/16 deploys failed since 05-28). Static file on host, not in `stacks/`. → `servers/ana-docker/README.md`
- `[2026-10-05]` **Embedder routing split (Prime 0030, via albok-dev, confirmed directly): `qwen3-embedding` = esh-ml1 primary / nh3-ml1 failover; new `qwen3-embedding-bulk` = nh3-ml1 primary / esh-ml1 failover, for albok writes** — LiteLLM `order` (read at source, v1.97.0); failover proved by stopping nh3-ml1 tei-embed (bulk 6/6 → esh-ml1, 200s). Gateway restart = 43 s outage. albok-service key granted the bulk alias; Nemi key not. TEI weights revision unpinned on both (model_sha null). → `stacks/litellm/conf/config.yaml`
- `[2026-10-04]` **albok-service moved to nh3-albok, a VM that runs only albok (albok-dev relaying Prime)** — nh3-docker's socket containers and plaintext tcp/2375 were root over the restricted wings; nh3-pve-2 vmbr0 VLAN-aware by reboot; PBS ns `nh3-pve-2`; copy verified by digest (dir st_size differs on ext4, not data). → `persistent-memory.d/2026-10-04-albok-service-moved-to-nh3-albok.md`
- `[2026-10-04]` **The whole fleet is on PVE 9.2.21 and PBS 4.2.7** — per-host traps (pfi-pve's grub-pc on UEFI, esh-pve's dead bridge port, nh3-pve's missing 7.0 headers, PBS via guest agent) and what a pfi-pve reboot costs. → `persistent-memory.d/2026-10-04-fleet-on-pve-9-and-pbs-4.md`
- `[2026-10-04]` **pfi-ana-webhost destroyed; phasefinal.com on Cloudflare Pages; token-creator + `infra-ops-pages` tokens** — the dragonfire sites were never ours to serve; 38.120.12.45 now unmapped. → `persistent-memory.d/2026-10-04-webhost-destroyed-phasefinal-on-pages.md`
- `[2026-10-04]` **sudo session recordings: archived weekly, bulk data never kept (Prime)** — `BULK_DATA !log_output` on all 19 recording hosts, archiver drops streams >64 MiB, ~31 G pruned. → `services/sudo-io-archive/README.md`
- `[2026-10-04]` **VM 101 PFI-ANA-DC + VM 104 nh3-laser retired (Prime: not in use)** — off, `onboot 0`, out of vzdump, backups kept; enroll MS 2023 Secure Boot certs before any restart.
- `[2026-10-04]` **PARKED (Prime): move fv-ml1's Docker data-root to tank** — needs a model-seat outage window; tracked at park `move-fv-ml1-s-docker-storage-off-the-root-ssd` (id 99). — `[2026-10-05]` DONE (entry above).
- `[2026-10-04]` **PARKED (Prime): guest OS patch campaign** — ~20 guests with 70–350 pending updates incl. security + kernels; plan in the item; tracked at park `guest-os-patch-campaign-across-the-fleet-debian` (id 100). — `[2026-10-05]` DONE (entry above).
- `[2026-10-04]` **PARKED (Prime): a model path for SVOS/Miranda that does not depend on the ANA LiteLLM gateway** — tracked at park `give-svos-and-miranda-a-model-path-that-doesn-t` (id 98).

- `[2026-10-03]` **PVE subscription popup patched out on nh3-pve, nh3-pve-2, pfi-pve, esh-pve (Prime: "every host")**: an anchored one-line edit plus an apt hook. esh-nas-pve was already de-nagged; esh-pve-2, sfsrv-ana and the PBS hosts are not done. → `services/pve-nag-patch/README.md`
- `[2026-10-03]` **nh3-pve-2 finished (Prime on site): host 10.100.250.62 on nh3-mgmt via X710 `nic3`, AMT on `nic0` with `auto` kept up, 1 TB wiped into `vmstore` (913 GiB), stale boot entry gone** → `persistent-memory.d/2026-10-03-nh3-pve-2-finished-prime-on-site-host-10-100-250.md`
- `[2026-10-03]` **CIRA tunnel watchdog LIVE on pfi-tacticalrmm (Prime go, 1232)** → `persistent-memory.d/2026-10-03-cira-tunnel-watchdog-live-on-pfi-tacticalrmm-prime-go-1232.md`
- `[2026-10-03]` **Worldtree memory-gate duty REFRAMED: regression check, not a gate** → `persistent-memory.d/2026-10-03-worldtree-memory-gate-duty-reframed-regression-check-not-a-gate.md`
- `[2026-10-03]` **albok-service 0.1.2 LIVE on nh3-docker (albok-dev ask 6955, 0251), fixing a leak that had broken 0.1.1** → `persistent-memory.d/2026-10-03-albok-service-0-1-2-live-on-nh3-docker-albok-dev-ask.md`
- `[2026-10-02]` **esh-pve-2 (MS-03 at ESH, future `esh-dev` host) onboarded: infra-ops (Prime), 1 TB → LVM-thin `vmstore`, AMT phoning home as `esh-pve-2-amt`** → `persistent-memory.d/2026-10-02-esh-pve-2-ms-03-at-esh-future-esh-dev-host-onboarded-infra-ops.md`
- `[2026-10-02]` **Demo outage ~13 min, ROLLED BACK (worldtree-dev URGENT 6684)** → `persistent-memory.d/2026-10-02-demo-outage-13-min-rolled-back-worldtree-dev-urgent-6684.md`
- `[2026-10-02]` **nh3-pve's AMT is in TacticalRMM's MeshCentral (group `PFI-AMT`, device `nh3-pve-amt`)** → `persistent-memory.d/2026-10-02-nh3-pve-s-amt-is-in-tacticalrmm-s-meshcentral-group.md`
- `[2026-10-02]` **Prime: dev-backup gets dailies + weeklies — DONE** → `persistent-memory.d/2026-10-02-prime-dev-backup-gets-dailies-weeklies-done.md`
- `[2026-10-02]` **ESH `tank` (esh-nas-pve, 175 T raidz2×2): was DEGRADED since ~2026-08-20 (found while planning PVE 9); HEALTHY since 2026-10-03 0629** → `persistent-memory.d/2026-10-02-esh-tank-esh-nas-pve-175-t-raidz2-2-was-degraded.md`
- `[2026-10-02]` **albok-service 0.1.0 LIVE on nh3-docker (albok-dev ask, operator-approved): `http://albok.nh3.internal:8392`** → `persistent-memory.d/2026-10-02-albok-service-0-1-0-live-on-nh3-docker-albok-dev-ask.md`
- `[2026-10-02]` **nh3-pve-2 status at end of day: AMT done, Proxmox on the WRONG NVMe; Prime reinstalls ON SITE 2026-10-03** → `persistent-memory.d/2026-10-02-nh3-pve-2-status-at-end-of-day-amt-done-proxmox.md`
- `[2026-10-02]` **Prime: MS-03s get Proxmox; dummy plugs in hand. One MS-03 is being deployed as `nh3-pve-2` at NH3 (Prime, ~0910)** → `persistent-memory.d/2026-10-02-prime-ms-03s-get-proxmox-dummy-plugs-in-hand-one.md`
- `[2026-10-02]` **nh3-dev root grown 250 → 378 GB (Prime resized scsi0; I grew the guest online, no reboot)** → `persistent-memory.d/2026-10-02-nh3-dev-root-grown-250-378-gb-prime-resized-scsi0.md`
- `[2026-10-01]` **MIA (Make-It-Animatable v2) auto-rigger LIVE on fv-ml1 GPU 3, one-shot (Prime via dread-dev)** → `persistent-memory.d/2026-10-01-mia-make-it-animatable-v2-auto-rigger-live-on-fv-ml1-gpu-3.md`
- `[2026-10-01]` **Prime: "clean up the 1700+ backups" — dev-backup retention FIXED, 1,740 husks removed** → `persistent-memory.d/2026-10-01-prime-clean-up-the-1700-backups-dev-backup-retention-fixed.md`
- `[2026-10-01]` **Prime: gen-small keeps its 8 GiB KV pin, and parakeet-nemo keeps CUDA graphs OFF** (~2–8 ms at short clips, accepted). GPU 0's ~1 GB of spare memory is enough with the seat's hard 3,840 MiB cap.
- `[2026-10-01]` **⚠ Gitea's `[webhook] ALLOWED_HOST_LIST = external, 10.0.0.0/8` silently REJECTS headscale mesh IPs (100.64.0.0/10)** → `persistent-memory.d/2026-10-01-gitea-s-webhook-allowed-host-list-external-10-0.md`
- `[2026-10-01]` **vh/arbo push webhook repointed from the retired wg0 lifeline `10.100.79.3:9009` to irv-ml1's mesh address `100.64.0.6:9009`** → `persistent-memory.d/2026-10-01-vh-arbo-push-webhook-repointed-from-the-retired-wg0.md`
- `[2026-10-01]` **Prime: delete the bench leftovers, no upstream for Scriberr, push** → `persistent-memory.d/2026-10-01-prime-delete-the-bench-leftovers-no-upstream-for-scriberr.md`
- `[2026-10-01]` **irv-ml1 /storetank reclaim done:** Prime ruled through comfy-dev, which deleted 84 files of its own (260 → 299 GB free). Tiers B/C/D got no ruling (infra-hermes thread `01M3TCSYRSFNAPA9BPQTMFQ6KJ`).
- `[2026-09-30]` **Parakeet speech seat → `parakeet-unified-en-0.6b` under NeMo (bf16) APPROVED by Prime, NVIDIA Open Model License accepted. DONE 2026-10-01 0126 by infra-hermes; infra-ops audit passed 0137.** → `persistent-memory.d/2026-09-30-parakeet-seat-switch-approved.md`
- `[2026-09-30]` **Worldtree U11a: legacy memory plane OFF on demo and personal. The U11b data deletion is gated on 3 consecutive PASS and step 5 is mine; the legacy archive must be destroyed by 2026-10-30.** → `persistent-memory.d/2026-09-30-worldtree-u11a-off-u11b-gate.md`
- `[2026-09-30]` **SemIf replaced by intern-decision (Intern-Decision-4B, the Jev bench pick): semif-compatible plus Jev `/v1/systemone` at 32k tokens on GPU 1, with a Triton warm-up cache volume.** → `persistent-memory.d/2026-09-30-semif-replaced-by-intern-decision.md`
- `[2026-09-30]` **Scriberr moved to GPU 3 (on demand); our build carries the overlap slicer (0001) and the Parakeet gap retry (0002); v3 kept.** → `persistent-memory.d/2026-09-30-scriberr-slicer-gap-retry-gpu3.md`
- `[2026-09-29]` **Worldtree U11a prepped, not flipped: a staged demo config plus the agreed U8 window plan (infra-hermes runs the batches).** → `persistent-memory.d/2026-09-29-worldtree-u11a-prepped.md`
- `[2026-09-28]` **Worldtree U10 backfill done on demo (5) and personal (797). model_roles drift needed a memory_tagger sync first; mimir had missing vectors.** → `persistent-memory.d/2026-09-28-worldtree-u10-backfill.md`
- `[2026-09-28]` **Bonsai ternary vs Q4_K_XL at concurrency on the 275 W card (1.93x at N=1 falls to 1.06x at N=8, 1.21x with the MMVQ fix); the weights are acquired.** → `persistent-memory.d/2026-09-28-bonsai-ternary-spike.md`
- `[2026-09-28]` **blender-run gained `--cpu` (no GPU attached) and a fixed hostname `fv-ml1-blender` (draupnir).** The design stage never renders, so it stays off GPU 3.
- `[2026-09-28]` **Blender extensions live in a read-only System repo built from a sha256 lock, enabled by a hook, opt-in for blender-run (`--extensions`).** SurfacePsycho's eval() is patched to literal_eval (a proven safe-mode escape). → `stacks/blender/README.md` § Extensions
- `[2026-09-27]` **hermes-gateway restarted 0401 for highseat-dev** → `persistent-memory.d/2026-09-27-hermes-gateway-restarted-0401-for-highseat-dev.md`
- `[2026-09-27]` **SemIf LIVE on fv-ml1 GPU 1 (semif-serve 0.1.2, Prime):** wrapper + contract + 39 tests, 142/144 upstream parity, two card-only memory defects fixed. → `persistent-memory.d/2026-09-27-semif-live-on-fv-ml1-gpu1.md`
- `[2026-09-27]` **Blender 5.2 on fv-ml1 GPU 3 (on demand), agent-driven via mcp-for-blender running in-container over ssh stdio; safe mode on, no published port.** → `stacks/blender/README.md`
- `[2026-09-27]` **esh-docker-vm host→HA traffic needs a /32 over macvlan-shim (if-up.d hook); without it HA silently loses MQTT (3× since August).** → `servers/esh-docker-vm/README.md`
- `[2026-09-27]` **Zigbee2MQTT live on esh-docker-vm :8099 (PAN 0xCFF4, ch 25) replacing ZHA; network key vaulted, data host-only.** Prime go-ahead in this session; a peer-relayed approval was blocked by the permission gate. → `stacks/zigbee2mqtt/README.md`
- `[2026-09-27]` **semif-serve 0.1.4: object states ending in `)`, `;` or `}` no longer 422 (INV-7, a prefix wrapper proven at startup); numerics are deterministic within a process but a bf16 near-tie can flip across a restart.** Prime ruled; heid bug hunt folded. → `stacks/semif/README.md`
- `[2026-09-27]` **SemIf as Cicada's mood source: slower (+32 ms async, +94 ms sequential) and worse (67% vs 92% apt; carry 7/15 vs 14/15); only the gesture restraint is a win.** Build nothing (Prime). Henge 88 carries it. → `persistent-memory.d/2026-09-27-semif-consumer-fit-spikes.md`
- `[2026-09-27]` **SemIf consumer-fit spikes (Prime): Cicada affect gate 30/31 with descriptive wording and 19/31 terse; Wyrd "left this place?" 21/21 on the second wording, exit choice 18/21.** Recommendations await Prime. → `persistent-memory.d/2026-09-27-semif-consumer-fit-spikes.md`
- `[2026-09-27]` **SemIf order-averaging spiked (+9.1 pts accuracy, agreement = strong confidence signal); Prime ruled: build it in as 0.1.3 and trial the fast kernels.** Tracked in the in-flight SemIf section. → `persistent-memory.d/2026-09-27-semif-order-averaging.md` — **DONE:** 0.1.3 live, with fast kernels adopted (`77b8cb4`).
- `[2026-09-27]` **restic repository URL moved out of world-readable systemd units on all 8 hosts, and vaulted (Prime).** Rotation stays Prime's. → `persistent-memory.d/2026-09-27-restic-repository-file-fleetwide.md`
- `[2026-09-27]` **infra-ops bootstrapped on vm-esh-nas by Prime** (the first account at the fleet-pinned uid/gid 850; `bootstrap-infra-ops-user.yaml` now pins 850 when free, `d775a01`).
- `[2026-09-27]` **augaman: second instance on fv-ml1 benched, then REMOVED (Prime).** esh-ml1 on v0.1.3 does 48 ms/face in the house with the verified backup (`ad484c3`, bench `docs/pfi/augaman-speed-bench/`).
- `[2026-09-27]` Created empty private repo `corviduo/svoperatingsystem` (SVOS, the operating system) as claude-bot, at brokkr-smithy-dev's relay of Prime's ruling. `svos-dev` → the OS session; The High Seat's session is `highseat-dev` again.
- `[2026-09-26]` **augaman: infra-ops owes the gallery backup + first deploy — DEFERRED until augaman-dev reaches deploy.** → `persistent-memory.d/2026-09-26-augaman-infra-ops-owes-the-gallery-backup-first-deploy.md` — `[2026-09-27]` **DONE:** deployed (v0.1.3 on esh-ml1), backup wired, identity-level restore verified (`d8f59a1`).
- `[2026-09-26]` **`zellij-fleet@.service` installed, NOT enabled** (for svos-dev's seat_up; owns the fleet zellij server in its own cgroup). Enabling `@Claude` at boot is Prime's call when seat_up ships. Tracked: `0ad7799`, `services/zellij-fleet/README.md`.
- `[2026-09-26]` **btusb blacklist on nh3-pve + esh-pve — proposed, awaiting Prime (low priority).** Every 6.8.12-4x boot oopses in btmtk (benign). Also noted for the next NH3 visit: nh3-pve runs ~20 °C warmer than esh-pve (workload-confounded; check airflow). Tracked: `servers/nh3-pve/README.md`.
- `[2026-09-26]` **GPU-LXC Temperature alerts watch the GPU, not the host CPU** (`SENSORS=-coretemp_*,acpitz`); hypervisor CPU alerts at >95 °C on nh3-pve/esh-pve. The first nh3-ml1 alert was nh3-pve's CPU during vzdump. `6d901c0`.
- `[2026-09-26]` **Abliterated LFM2.5-VL-3B parallel seat (:8032) passed brokkr's 6-image eval and stays** (direct only; stock seat kept for SFW A/B). `9cc3824`, `944bb36`.
- `[2026-09-25]` **AMT follow-ups PARKED until the two MS-03s arrive and esh-pve's MS-01 is on AMT (Prime 2326).** — Parked: MeshCommander test; dummy HDMI plug, then NanoKVM → gx10; an OOB path not through nh3-scale… → `persistent-memory.d/2026-09-25-amt-follow-ups-parked-until-the-two-ms-03s-arrive-and-esh.md`
- `[2026-09-25]` **nh3-pve AMT LIVE: static `10.100.250.61` on nh3-mgmt (UDM port 6), KVM on, Opt-in None** — (Prime). → `persistent-memory.d/2026-09-25-nh3-pve-amt-live-static-10-100-250-61-on-nh3-mgmt-udm-port.md`
- `[2026-09-25]` **pfi-gx10 AC-restore VALIDATED by Prime's AC pull; Homepage stays on esh-docker-vm (Prime) after the mmap_lock wedge reboot.** `servers/pfi-gx10/README.md`, `servers/esh-docker-vm/README.md`.
- `[2026-09-26]` **VibeVoice ASR → Q8_0 (Prime).** WER on the 4 bundled LibriSpeech clips 3/69 → 2/69 (only the I'm/I am artifact left), ×3 identical; RTF 0.09–0.17; +1.1 GB VRAM (nh3-ml1 ~11.3/16 GB). Q4_K file removed.
- `[2026-09-26]` **esh-matter LIVE: a Matter server (matter.js 1.4.0) on CT 111 @ 10.0.90.20, VLAN 90 only** — , for ha-dev (operator-approved, relayed). → `persistent-memory.d/2026-09-26-esh-matter-live-a-matter-server-matter-js-1-4-0-on-ct-111.md`
- `[2026-09-26]` **Embed/rerank LOAD-SHARED across esh-ml1 + nh3-ml1 (Prime).** — Second deployments were added for qwen3-embedding and reranker (config) and for reranker-a3-bge-v2-m3 (DB… → `persistent-memory.d/2026-09-26-embed-rerank-load-shared-across-esh-ml1-nh3-ml1-prime.md`
- `[2026-09-26]` **Two dataset-foundry utility seats LIVE on nh3-ml1 (brokkr; operator approval relayed):** — LFM2.5-VL-3B on llama.cpp `:8030` (gateway `lfm25-vl-3b`, LiteLLM restarted 36 s at 0039) and… → `persistent-memory.d/2026-09-26-two-dataset-foundry-utility-seats-live-on-nh3-ml1-brokkr.md`
- `[2026-09-26]` **Coder seat STAYS on fv-ml1 (Prime).** — The nh3-ml1 copy gave the same quality (teacher-forced true-code logprob diff +0.008 ± 0.019) but ran ~5×… → `persistent-memory.d/2026-09-26-coder-seat-stays-on-fv-ml1-prime.md`
- `[2026-09-25]` **nh3-ml1 LIVE after the NH3 visit (SB off, IGFX restored): driver + CT 109 + TEI, parity vs esh-ml1 indistinguishable (cos min 0.999993 = own floor; overlap@10 1.000 vs MRL-256 control 0.684), same speed; monitoring/DNS wired. Autonomous: lxc-pve 6.0.0-2 upgrade on nh3-pve (Docker-in-LXC fix #7006). Gateway routing + AMT follow-up are Prime's.** → `persistent-memory.d/2026-09-25-nh3-ml1-live.md`
- `[2026-09-25]` **nh3-ml1 = CT 109 @ 10.100.50.80, second TEI embed/rerank backend on nh3-pve's RTX 2000E; GPU playbooks made host-generic — BUILD DEFERRED: blocked on nh3-pve Secure Boot until the NH3 visit; SB handling and gateway routing are Prime's calls.** Tracked: `7ddd116`, Current state. → `persistent-memory.d/2026-09-25-nh3-ml1-standup.md`
- `[2026-09-25]` **nh3-pve OOB: HOLD blind until the next NH3 visit (Prime via Miranda, 1333).** Target: NanoKVM → pfi-gx10, and the MS-01 on its own vPro. The IGFX BIOS fix rides the same visit, since AMT KVM captures only the iGPU. Tracked: `servers/nh3-pve/README.md` (`2b49be4`, `cdd7605`).
- `[2026-09-25]` **MS-01 foot-gun: a GPU in the PCIe slot renames every NIC** — (the slot's root port takes bus 01, so the X710 goes `enp2s0f0np0`→`enp3s0f0np0`). → `persistent-memory.d/2026-09-25-ms-01-foot-gun-a-gpu-in-the-pcie-slot-renames-every-nic.md`
- `[2026-09-25]` **Direct ESH→esh-ml1 consumer path — PARKED** (no ESH-side callers in 7 days; consumers go through the gateway). Tracked at `persistent-memory.d/2026-09-24-esh-ml1-embed-rerank.md`.
- `[2026-09-25]` Created empty private repo `corviduo/norn` (git@gitea.phasefinal.com:corviduo/norn.git) as claude-bot, at brokkr-smithy-dev's relay of the operator's Norn ruling; the `norn-dev` handle is the operator's to declare.
- `[2026-09-25]` **Reward seat audited (Skywork-Reward-V2-Llama-3.1-8B still #1 of 188 on RewardBench 2; our AWQ ≈ bf16 within noise; double BOS costs ~2.7 pts) and moved fv-ml1 → esh-ml1; esh-ml1 monitoring wired (Beszel+GPU, Kuma, Homepage, Dozzle); Dozzle hub's stale agent IPs fixed; nh3-dev Beszel agent revived.** → `persistent-memory.d/2026-09-25-reward-move-and-esh-ml1-monitoring.md`
- `[2026-09-25]` **TEI adopted as the fleet embed/rerank engine (Prime); esh-ml1 is the sole gateway backend for `qwen3-embedding` + `reranker`; fv-ml1's vLLM embed/rerank seats retired (~6.1 GB freed); parakeet stays on fv-ml1.** → `persistent-memory.d/2026-09-25-tei-fleet-embed-rerank.md`
- `[2026-09-24]` **esh-ml1 built — RTX 2000E Ada as CT 110 on esh-pve (host driver 580.178.04 DKMS, loaded live, no reboot), vLLM embed+rerank at measured parity with fv-ml1, wired as LiteLLM `order: 2` failover; dead DB alias `reranker-a3-bge-v2-m3` (pre-relocation IP) repaired.** → `persistent-memory.d/2026-09-24-esh-ml1-embed-rerank.md`
- `[2026-09-24]` **esh-pve: VM 102 retired, a 14-day hung VFIO process found and cleared, T400 → RTX 2000 Ada; Prime chose LXC + host driver for embed/rerank** (implementation deferred to next session, tracked here + `servers/esh-pve/README.md`). → `persistent-memory.d/2026-09-24-esh-pve-vm102-retired-gpu-swap.md`
- `[2026-09-24]` **pfi-gx10 AC-restore UEFI patch applied but NOT validated; box OFF until Prime's AC pull 2026-09-25** (tracking: `servers/pfi-gx10/README.md`, `e5197a3`). — `[2026-09-25]` ✅ **VALIDATED**: Prime pulled and replugged AC, and it came up by itself at 1108:54 (`2b49be4`). → `persistent-memory.d/2026-09-24-gx10-ac-restore-patch.md`
- `[2026-09-24]` **NH3 power outage recovered** — pbs-nh3 had no `onboot` (set), NFS boot race fixed with automount (`1cbde50`), every other Claude session on nh3-dev died. → `persistent-memory.d/2026-09-24-nh3-power-outage-recovery.md`
- `[2026-09-24]` **Miranda standing order is a repo CLAUDE.md operating parameter** — (`4b29492`, aligned to the global send protocol in `bcf3342`): high-urgency matters go to her, fixed or not… → `persistent-memory.d/2026-09-24-miranda-standing-order-is-a-repo-claude-md-operating.md`
- `[2026-09-24]` **task-board mothballed** (Prime): container removed on ana-docker, data/image/compose kept, Kuma monitor deleted, task_* instructions removed from CLAUDE.md and the fork template (`e6da607`). Its hooks had sent no traffic in 30 days.
- `[2026-09-24]` **Military 24-hour Pacific clock times** carried into the Codex/Grok shared bootstrap `docs/fleettools/AGENT-BOOTSTRAP.md` (`ad2b4d9`); Claude seats get it from the global CLAUDE.md.
- `[2026-09-24]` **Worldtree `admin.memory.forget` stays OFF on demo/personal** until an instance needs it — a destructive erase; enabling it is a per-change operator yes via deploy-wt-config.
- `[2026-09-24]` **A git checkout under `root:docker` needs `safe.directory` for its deploy user** — the 09-14 normalization (`826a63b`) silently broke yt-voice-clipper's webhook deploy until v0.3.13; fixed on irv-ml1 and recorded in fleet conventions (`eea9eb2`). Sweep found no other case.
- `[2026-09-23]` **elway sudo uploads land root:root, validated and staged; fleet ownership audit built; 33 mis-owned root files fixed on 10 hosts.** → `persistent-memory.d/2026-09-23-elway-ownership-fix-fleet-audit.md`
- `[2026-09-23]` **headscale-ddns hardened** — (`fedd4b6`): Cloudflare calls retry and validate every body (`pick()`), no write without both IDs, the run… → `persistent-memory.d/2026-09-23-headscale-ddns-hardened.md`
- `[2026-09-23]` **esh-docker-vm restic was skipped 09-22..23 by my own Kuma move** — a dead uptime-kuma lookup aborted `pre-backup.sh` under `set -e` (`25e41d2`). → `persistent-memory.d/2026-09-23-esh-docker-vm-restic-was-skipped-09-22-23-by-my-own-kuma.md`
- `[2026-09-23]` **hermes-gateway restart exit-1 is a Hermes race, not a crash** — the planned-stop watcher consumes the marker before SIGTERM re-runs the handler; drop-in… → `persistent-memory.d/2026-09-23-hermes-gateway-restart-exit-1-is-a-hermes-race-not-a-crash.md`
- `[2026-09-23]` **Booth link board cleared to 14 durable links** (208 removed: drops, release posts, research links, token-bearing URLs; Scriberr reposted at `scriberr.fv.internal:8080`). Prime's rule: durable debug links only.

- `[2026-09-22]` **Both carried calls approved** — build the `NRestarts` flap sampler (`163bb97`); the restic content-assertion ruling is ratified and stays (`ba60fda`).
- `[2026-09-22]` **safe-rm installed on nh3-dev and delegated fleet-wide to infra-hermes.** — ⚠ The package installs INERT and looks fine — Debian's `/etc/zsh/zprofile` has 0 non-comment lines so the… → `persistent-memory.d/2026-09-22-safe-rm-installed-on-nh3-dev-and-delegated-fleet-wide-to.md`
- `[2026-09-22]` **The acceptance probe for a guard must not be able to destroy what it tests** — (infra-hermes). → `persistent-memory.d/2026-09-22-the-acceptance-probe-for-a-guard-must-not-be-able-to.md`
- `[2026-09-22]` ⚠ **`{"sent": true}` is a claim about transmission, never about effect.** `pane_send` structurally cannot deliver a harness command (every relay is prefixed with the card id), so D-0010 promised an unachievable `/clear` and its receipt reported success. Consumed an operator approval. → `persistent-memory.d/2026-09-22-instrument-errors.md`
- `[2026-09-22]` **D-0010/D-0011 were misrouted to this seat by `pane_find` matching a ROLLING PANE TITLE.** — Genuine and operator-approved, wrong seat; `fleet_telemetry` held the right mapping and carries the warning… → `persistent-memory.d/2026-09-22-d-0010-d-0011-were-misrouted-to-this-seat-by-panefind.md`
- `[2026-09-22]` **`headscale-ddns` exited 1 silently and the alarm carried no cause** → `persistent-memory.d/2026-09-22-headscale-ddns-exited-1-silently-and-the-alarm-carried-no.md`

- `[2026-09-22]` ⭐⭐ **Five instrument errors in one day, and the shape is one thing: a tool that enumerates "things that are fine" has selected against its own subject.** `--state=running` skipped the units most needing hooks; `awk '{print $1}'` dropped systemd's `●`-decorated FAILED rows; `grep -ic restic` on the wrapper missed the check script; `restic ls`'s header line made an absent path read as "blobs gone"; and a cooldown test that invoked before failing the unit. **Every one reported cleanly while looking at the wrong thing.** The rule is not "verify" — it is *verify, then ask what the verification could not have seen*. → `persistent-memory.d/2026-09-22-instrument-errors.md`
- `[2026-09-22]` **Fleet alert bridge generalized** — `beszel-althing` → `althing-alert-bridge`, route registry (`/beszel` + `/kuma`), each with its own… → `persistent-memory.d/2026-09-22-fleet-alert-bridge-generalized.md`
- `[2026-09-22]` **Uptime Kuma rebuilt from scratch on 2.5.5, moved esh-docker-vm → ana-docker.** — ⚠ `:latest` is a TRAP — it tracks 1.x, so an Aug-2026 pull gave a Dec-2024 build. → `persistent-memory.d/2026-09-22-uptime-kuma-rebuilt-from-scratch-on-2-5-5-moved-esh-docker.md`
- `[2026-09-22]` **Beszel and Uptime Kuma are DISJOINT, not redundant** — Beszel's alerts bind to a *system* with a threshold; there is no URL column, so it is structurally incapable… → `persistent-memory.d/2026-09-22-beszel-and-uptime-kuma-are-disjoint-not-redundant.md`
- `[2026-09-22]` **Failed-START alarms on 23 nh3-dev units** — (`services/althing-notify-failure/`). → `persistent-memory.d/2026-09-22-failed-start-alarms-on-23-nh3-dev-units.md`
- `[2026-09-22]` **Backup coverage is a property of the SYSTEM, never one job's scope** — establish it by querying the repo for the path in a real snapshot, never by reading a job's `SRC=`. → `persistent-memory.d/2026-09-22-backup-coverage-is-a-property-of-the-system-never-one-job-s.md`
- `[2026-09-22]` **restic checks now assert CONTENT and are DISCOVERED not enumerated** — conjunctive (recent AND present AND restores non-zero bytes); repos discovered from each NAS, hand list… → `persistent-memory.d/2026-09-22-restic-checks-now-assert-content-and-are-discovered-not.md`
- `[2026-09-22]` **irv-ml1: Irvine is a TENANCY behind a Fortinet PFI does not control** — its TLS inspection breaks Tailscale relay/control intermittently (41 cert warnings/week). → `persistent-memory.d/2026-09-22-irv-ml1-irvine-is-a-tenancy-behind-a-fortinet-pfi-does-not.md`

- `[2026-09-21]` ⭐⭐⭐ **lv-mccarthy GATED and NOT SHIPPED — voice passes, memorisation is the cleanest in the line, and the length discipline is gone.** 720 generations, 3 arms. Voice +0.152 at **2.9×** floor for ckpt450 (ckpt900 +0.172 at only 1.2×, its spread one outlier seed), and **~3/4 of the gain survives stripping every punctuation mark**, so it is not the cheap win. ⭐ Memorisation: **ckpt450 at 0.12 against the author's own held-out 0.12 — identical, longest match 11 words against the author's coincidental 12**, all 96 matches READ and every one stock grammar (`he looked at the wolf and he looked at him`); the name-shaped hits are the RENAMED inventions. Axis C is the blocker: **20% / 28% of generations overshoot the 90–140 band against base's 1%**, worst case a degenerate loop at 279 words. ⚠ My own prereg's axis C transcribed `score_beats.py`'s **v1** criteria including "in-band up on base", which the operator RETIRED 2026-09-15 because base maxes it — under the v2 (ran-on only) ckpt450 passes by **0.01 against a 0.200 floor**, but that reading was found AFTER the numbers and was not used. Fix the prereg prospectively. → `persistent-memory.d/2026-09-21-lv-mccarthy-gate.md`

- `[2026-09-21]` ⭐⭐⭐ **The ops log shipped — and then failed FOUR ways in its first hours, every one recording something unfindable.** Claim dropped by a sub-tool, hook behind graphify's eight `exit 0`s, no handle in the env, ssh-target written as a hostname. The general shape is **configured ≠ effective**; twelve instruments reported confidently and wrongly across three days, five of them mine. → `persistent-memory.d/2026-09-21-ops-log-and-the-instruments-that-lied.md`

- `[2026-09-21]` ⭐⭐ **The Booth gained blur + a closed keep round trip, after shipping TWO controls that did nothing** — a reveal handler Jinja discarded for sitting after `{% endblock %}`, and a `×` a sibling form covered by 30×22 px. Both operator-found, both from reading templates instead of rendering them. `scripts/layout-probe.py` took four iterations to become trustworthy. ⚠ Blur is COSMETIC and a test asserts the 200 on purpose. → `persistent-memory.d/2026-09-21-booth-two-dead-controls.md`

- `[2026-09-17]` **PARKED lv-krakauer, and the reason is a selection criterion the line was missing: ask whether the author HAS a voice before investigating whether the…** → `persistent-memory.d/2026-09-17-parked-lv-krakauer-and-the-reason-is-a-selection-criterion.md`
- `[2026-09-17]` **The althing route-declaring SessionStart hook is documented but NOT installed on nh3-dev** — `dev_launch.py` has zero occurrences of "route", no hook declares one, and every live route was hand-declared… → `persistent-memory.d/2026-09-17-the-althing-route-declaring-sessionstart-hook-is-documented.md`

- `[2026-09-17]` **PARKED lv-krakauer, and the reason is a selection criterion the line was missing: ask whether the author HAS a voice before investigating whether the…** → `persistent-memory.d/2026-09-17-parked-lv-krakauer-and-the-reason-is-a-selection-criterion-2.md`

- `[2026-09-15]` **breeze-tts stays on irv-ml1; the TTS-stack move to fv-ml1 is PARKED (park id 75, `move-the-tts-stack-breeze-tts-bragi-tts-gateway`), triggered on evacuating embed/rerank/reward.** ⚠ Trigger as stated says "gpu0" but those three are on **GPU 1** (~0.16 util, ~15.7 GB; GPU 1 is the tight card at 0.975 / 4,336 MiB free) — confirm which he meant before executing. All three services move together because only `breeze-tts` is GPU-resident (~10.3 GiB, **growing**) while `bragi` and `tts-gateway` are CPU proxies, and co-location is what avoids a cross-site hop per TTS call. **breeze-tts sizing — original recommendation NOT to move it.** ~**10.3 GiB** measured under load at 53 min uptime, **up from 9.2 GiB** shortly after warm-up (it grows; n=2, plateau unmeasured) — so GPU 0's 11,982 MiB free is a **1.7 GB margin and shrinking**, on the live chat serving path. ⚠ Two measurement traps: it reports **nothing at idle on the wrong card** (`BREEZE_GPU_DEVICES=0` = the **3090**, not the A6000), and an early reading understates it. ⭐ The real objection is **topology**: `tts-gateway` is on irv-ml1 and reaches it same-box, so moving breeze alone adds a cross-site hop to every TTS call against a 478 ms first-sample budget. GPU 3 would fit it but spends the reserve. → `persistent-memory.d/2026-09-15-breeze-placement-sizing.md`

- `[2026-09-13]` **STANDING POLICY (operator): cap GPU power limits at BUILD time, not after discovering the constraint.** → `persistent-memory.d/2026-09-13-standing-policy-operator-cap-gpu-power.md`

- `[2026-08-25]` **Fused MoE kernel path — DEFERRED, tracked at park `fused-moe-kernel-path-for-gemma-4-moe-training` (id 47).** → `persistent-memory.d/2026-08-25-fused-moe-kernel-path-deferred-tracked-at-park-fused-moe.md`

- `[2026-08-24]` **`nconnect=8` on `/mnt/smithy` — approved but DEFERRED at operator instruction** → `persistent-memory.d/2026-08-24-nconnect-8-on-mnt-smithy-approved-but-deferred-at.md`

_197 older entries archived to archival-memory.md._

## Tried and abandoned

- `[2026-10-04]` **`apt-get` run in-band through `qm guest exec`** — qemu-guest-agent was in the upgrade set, restarted itself, and systemd killed apt mid-dpkg on BOTH PBS VMs. Run apt in a `systemd-run` unit. (auto-memory `feedback_no_inband_apt_through_guest_agent`)
- `[2026-10-04]` **Pulling files with `ssh host 'sudo cat …'`** — sudo ≥ 1.9.14 truncated the piped stream at exit (Debian 13 hosts), and `log_output` re-recorded the whole file as a new session. Read without sudo (group-readable file).
- `[2026-10-01]` **Size + mtime scans to pick reclaimable "staging" on a model store** → `persistent-memory.d/2026-10-01-size-mtime-scans-to-pick-reclaimable-staging-on-a.md`
- `[2026-09-30]` **Shorter Parakeet slices as Scriberr's memory fix** → `persistent-memory.d/2026-09-30-shorter-parakeet-slices-as-scriberr-s-memory-fix.md`
- `[2026-09-30]` **Whole-file local-attention Parakeet in Scriberr (context 255/255).** OOM past 16 GB on a 35-min file. Local attention inside chunks is also non-deterministic run to run.
- `[2026-09-30]` **Start-time midpoint stitching of overlapped Parakeet chunks.** It duplicated a word at 26 of 108 stitches, because Parakeet timestamps a post-pause word anywhere inside the pause. Hand over at a word both chunks agree on instead.
- `[2026-09-30]` **int8 ONNX (sherpa-onnx) as the low-latency Parakeet runtime.** The int8 graph runs on ONE CPU thread with the GPU at 2–9%. Unified-en int8 was slower than the seat; fp32 ONNX was 4–12× faster, and NeMo was fastest.
- `[2026-09-30]` **GPU budgets computed as total − used.** nvidia-smi `Free` is ~640 MiB lower per card (driver reserve). Budget from `Free`.
- `[2026-09-27]` **The Blender MCP server on nh3-dev, reaching the add-on socket over an SSH tunnel** → `persistent-memory.d/2026-09-27-the-blender-mcp-server-on-nh3-dev-reaching-the-add-on.md`
- `[2026-09-27]` **A TCP connect as the "is Blender ready" probe** → `persistent-memory.d/2026-09-27-a-tcp-connect-as-the-is-blender-ready-probe.md`
- `[2026-09-27]` **`log.exception()` in a GPU failure path** — the record keeps `exc_info`, so any retaining handler (pytest's capture does) pins the traceback's frames and tensors. Log `traceback.format_exc()` text instead (semif-serve `engine._guard`).
- `[2026-09-27]` **fla/triton in a slim image without gcc** — triton compiles its CUDA driver shim at runtime ("Failed to find C compiler"). The warm-up died and startup failed closed. The semif image now installs gcc + libc6-dev with the fast extra.
- `[2026-09-27]` **`uv export` → requirements.txt → `uv pip install` for a torch-from-cu128 project** → `persistent-memory.d/2026-09-27-uv-export-requirements-txt-uv-pip-install-for-a.md`
- `[2026-09-27]` **Translating a CUDA OOM by raising inside `except` (or `from exc`)** — the chained exception's traceback pins the failed call's frames, and their GPU tensors (11.9 GiB after the 503). Raise after the block, unchained, `gc.collect()` before `empty_cache()`.
- `[2026-09-27]` **`deploy-stack.sh --yes` / `dns-sync.py` fed a blind `y`** — the harness refuses a blind apply. Review with `echo n |` first, then apply with `echo y |`.
- `[2026-09-27]` **Relying on the build cache surviving on esh-ml1** → `persistent-memory.d/2026-09-27-relying-on-the-build-cache-surviving-on-esh-ml1.md`
- `[2026-09-26]` **Greedy exact-match as parity for a small generative seat (coder)** — same-host repeats matched only 30–38% (run B hit the prefix cache, so a different numeric path; near-tie… → `persistent-memory.d/2026-09-26-greedy-exact-match-as-parity-for-a-small-generative-seat.md`
- `[2026-09-26]` **zsh traps in ad-hoc test loops:** `set -- $a` does NOT word-split, so alert POSTs went out with empty fields; and `local path=…` inside a function CLOBBERS `$PATH` (zsh's tied array), so the failover test ran nothing while TEI sat stopped. Use other names and `${=var}`.
- `[2026-09-25]` **Concluding "not on the UDM" from a port table read 15 s after link-up** — UniFi polls (~60 s); AMT was on port 6 as Prime said. Wait a poll, and prefer a which-port-lists-the-MAC check. auto-memory `feedback_polled_stats_lag_the_event`.
- `[2026-09-25]` **The esh-pve NVIDIA DKMS recipe on nh3-pve** — it built, then the kernel refused to load it: nh3-pve has SECURE BOOT ON (esh-pve, the same MS-01, has it off). The installer rolled back. The playbook now pre-flights `mokutil --sb-state` (`7ddd116`).
- `[2026-09-25]` **elway against an unpinned host-key name** — every `when:` hit ssh rc 255, so all 9 steps showed SKIPPED, not failed. Only the verify phase went red. Pin the name (the IP key matched) or use the IP. Untracked elway defect: rc 255 in `when:` should fail.
- `[2026-09-24]` **Testing "Restore AC Power Loss" with an OS shutdown** — a shutdown stays off BY DESIGN; only pulling and restoring AC tests it. A community README claimed the two are indistinguishable; trusting it cost Prime two trips to the pfi-gx10 power button.
- `[2026-09-23]` **`booth link --help`** — there is no help flag; it posts `--help` to the operator's link board as a link. Read `booth` with no args for usage.

_121 older entries archived to archival-memory.md._