# Persistent memory — eshpfi-management

_Last updated: 2026-10-08 ~0740 PT (patch night: fv-ml1 kernel 6.12.111 + NVIDIA 580.178.04 + ZFS 2.3.9, Docker 29.8.2 on nh3-docker + esh-docker-vm; nh3-svos on SVOS a737a06 with knowledge/terminal/post office live; albok-service 0.1.13 → 0.1.14; gateway glm-5.3 + gen-frontier on 5.3; heid's runaway 76 GB sweep killed; Hermes launchers repaired.)_

> **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| `vh/task-board` | MCP + web dashboard for assistant task state (port 7878) — **[2026-09-24] MOTHBALLED** by Prime (superseded by the High Seat + ledger); container removed on ana-docker, data/image/compose kept (`e6da607`) | push-to-main → CI deploys (2026-04-29) |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 2026-10-08 ~0740 PT. The newest subsection is first; older subsections carry their own dates. What was DONE lives in Recent decisions; this section keeps only what is open, scheduled or being watched._

### 2026-10-08: live now (as of 2026-10-08 ~0740 PT)

- **Nothing is mid-action.** No claims held (`scripts/ops-log claims`). eshpfi is pushed through this snapshot's commit. ⚠ 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 (auto-regenerated).
- **Owed by me (no input needed):**
  - albok `.browse/` exposure test before ANY share: pick a surface (sshfs `follow_symlinks` is the lead), rename `.browse/` on nh3-albok, and a fresh open through the client's cached listing must FAIL; also record the failed-rename case. Report on albok-dev's thread; the operator's user needs the restricted wings' groups on the share host. → `stacks/albok-service/README.md`
  - fv-ml1 GPU 0/1 plateau read (Beszel `stats.g.<n>.mu` × 1.024), now ~10-10, since every seat restarted at 0034 10-08.
  - 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).
  - SVOS thaw fix needs repeats (one clean drill is evidence, not proof): after the nightly 21:30 nh3-pve-2 vzdumps, grep nh3-svos `journalctl -u 'svos-*' --since 21:29` for `startup or service failed`; if one reappears, send svos-dev one line.
  - Re-read nh3-nas usage after the 10-08 GC (79% at 10-07 2350; the mirror prune ran OK).
- **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:**
  - albok's 200-object load check, 2.01× against a 2× bar (albok-dev: the ruling is the operator's).
  - The cleanup bundle offered 10-05: close stale parks 49/46/40; refresh the fv-ml1 README stack tables plus the serial-keyed NVMe table and `zpool replace` line (the 2084-media-error drive is now `/dev/nvme6`, not nvme7); wire ZED pool alerts into althing-alert-bridge; prune the exited one-shot containers on fv-ml1 (keep the `parakeet` rollback).
  - Push Booth commit `ce095c1`. A trusted HTTPS name for ESH Homepage. nh3-dev reboot (kernel 6.1.0-53 installed).
  - ⚠ **irv-ml1: DO NOT PATCH (Prime)**; config changes are fine. ana-nas is out of scope.
- **Scheduled / unchecked:** 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. Next scheduled tank scrub on fv-ml1: Sun 10-11 0024 (the September slot was missed); check it ran.
- **Worldtree memory gate:** every FAIL since 09-30 (0930T0809, 1004, 1007) is ONE fixture, `u-negative-ephemeral` FILED in one run — the #416 ephemeral residual, ~3 of 42 fixture-runs since bbcc1788 (~1 batch in 5 FAILs on it), NOT a recall regression; recall (filing/user median 0.83–0.92, opener/cross_session/inline_core 100%) has held throughout. Negative is a structural class, so one run's leak fails the aggregate (`_run_structural_failed`); filing alone is judged by median. 10-07: infra-hermes told to classify FAILs by failing row (msg to its skill's daily-duty section); worldtree-dev told #416 is not closed (pull-only, unread 4 days) — reopen is theirs/Prime's.
- **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; meromero's Homepage label still says "Dormant / rollback"; Scriberr's `patches/0003` lands only at the next `scripts/scriberr-rebuild`. The LiteLLM compose.yaml on ana-docker differs from `stacks/litellm/compose.yaml` (found 10-07; only the conf side was pushed). nh3-dev holds ~33 GB of unused TAGGED Docker images (rollbacks; not pressing at 66%).
- **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.
- **Older open items, one line each:** esh-matter: Prime shares the Aqara W200 into HA via Matter multi-admin (if commissioning misbehaves, the UniFi mDNS reflector on esh-iot is the first knob). Restic: the rest-server password rotation stays Prime's (the units no longer leak it). esh-ml1: the nh3-docker Dozzle agent has been stopped by hand since ~2026-04 (revive or drop), and the Beszel superuser password rotation was offered to Prime. Blender: agent-drawn CAD Sketcher geometry and MeasureIt overlays in MCP screenshots are still open (`stacks/blender/README.md`). Worldtree reward path: confirm personal's image now includes d8726a13 (it ran `51168a2e` on 09-27). nh3-dev's root disk is at ~66% since heid's runaway sweep was killed 10-08 (it flapped on the Beszel 85% line before). ESH has a single outside route (esh-scale on esh-pve), noted and untracked.

### 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). ⚠ Before restarting any seat on a shared card, gate on the arithmetic (`scripts/oneoff/fv-ml1-gpucheck.sh`), never trial-boot. Before restarting a user-facing service, the idle check must STOP the restart, not just print (auto-memory `feedback_idle_check_must_gate_the_restart`).

- **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.

### Scriberr (fv-ml1 GPU 3)

- **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). `patches/0003` (pyannote env pins) is committed but in no image yet. `scripts/scriberr-rebuild` re-applies all. → `persistent-memory.d/2026-09-30-scriberr-slicer-gap-retry-gpu3.md`
- **Diarization works (fixed 2026-10-06):** model caches on /tank, `HF_TOKEN` a placeholder, saved profiles `WhisperX large-v3 · GPU · speakers` and `Parakeet · GPU · speakers`. A NEW gated model needs one download with vault `fv-ml1/hf-token`. → `persistent-memory.d/2026-10-06-scriberr-diarization-fixed.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`). `getUserMedia` is refused on http://, so recording needs the HTTPS name, which is in `ALLOWED_ORIGINS` (`playbooks/scriberr-https-origin.yaml`). ⚠ `/opt/docker/compose/scriberr` is lkraven-owned, so `deploy-stack.sh` as infra-ops FAILS there; upload single files with `elway --upload --sudo --owner lkraven:lkraven`.

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

- **Incident 2026-10-01 04:21, fixed by nemo-0.1.1** (infra-hermes 963f9ed). gen-small OOM'd on a lazily allocated workspace while the seat held its window cache. The fix: `empty_cache` around every window, `MEM_CAP_MIB=3840` (a hard ceiling), `CUDA_GRAPHS=0` (empty_cache poisons the graph pool). The seat rests at 2,108 MiB and peaks at 3,028 on a 12-min file. **Lesson: a shared-card tenant must carry a HARD cap, whether or not it returns memory.** Prime kept graphs OFF. His 10-01 "no insurance trim" on gen-small was superseded on 10-05 (KV 8 → 5.5 GiB) once the GPU 0 plateau turned out to be ~60 MiB free, not the ~1.05 GB read just after a restart.
- **Rollback:** `docker stop parakeet-nemo && docker start parakeet` (old container and image kept). 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").

### 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.

### nh3-pve + nh3-ml1 (2026-09-25/26)

- **nh3-pve:** Secure Boot OFF; IGFX restored; NVIDIA 580.178.04 DKMS. **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 load-shared with esh-ml1 through the gateway; embeddings primary/failover since 2026-10-05 (`qwen3-embedding` esh-ml1 first, `qwen3-embedding-bulk` for albok writes nh3-ml1 first). brokkr's foundry seats: `lfm-vl` `:8030` (gateway `lfm25-vl-3b`), `lfm-vl-uncensored` `:8032` (direct), `vibevoice-asr` `:8031` (audio.cpp, Q8_0). GPU ~11.3/16 GB. → `servers/nh3-ml1/README.md`

## Recent decisions

- `[2026-10-09]` **APPROVED by Prime (10-09), BUILD DEFERRED until after his snapshot/clear: SVOS app-traffic ingress for U13** (apps on nh3-dev reach the nh3-svos kernel). Shape agreed with svos-dev: (1) kernel `--app-listen 127.0.0.1:8410`, which never trusts loopback (svos-dev builds it in U9a); (2) a Caddy origin `svos-kernel.phasefinal.com` on 10.100.50.43, no Basic auth, bearer passed, app paths only, allowlisted to nh3-dev; (3) kernel→bridge over plain LAN HTTP; kernel→seat host (terminal) via nh3-dev's wildcard Caddy `svos-seathost.nh3.phasefinal.com` (TLS, because the leg carries secrets). nh3-dev is NOT on the mesh; the contracts now say "fleet network". Build in a later session once `--app-listen` is on main (svos-dev will say); do NOT build before the snapshot. Tracking: svos-dev thread `01M4GPXSBKQHCQ30FVPH4R3N7G`.
- `[2026-10-09]` **nh3-svos → kernel 0.0.8 (`b588510`, a bounded SQLite reader pool): the 10-08 22:55 EMFILE outage is fixed at the source and the LimitNOFILE stopgap is removed.** A 4-min browser soak held `svos.db` handles flat at 9–12 (0.0.7 grew +22 in 2 min). Root cause: one cached connection per short-lived anyio worker thread. → `servers/nh3-svos/README.md`
- `[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.
- `[2026-10-08]` **heid's runaway sweep killed on Prime's order: two `heidnotes/sweep.py` processes had written ~76 GB into a deleted-but-open file; nh3-dev root 86% → 66%** — the sweep read its own output. heid fixed it at the source. → `persistent-memory.d/2026-10-08-heid-runaway-sweep-killed.md`
- `[2026-10-08]` **SVOS post office LIVE on nh3-svos** — Prime declared `svos`; its `ns:notifications` write grant was approved on his word at 0731 (card `card:4d3a8b26c17f472d828b06fd495192db`); a test message was ingested and delivered; `reach` ok, unread 0. Reported to svos-dev.
- `[2026-10-07]` **No z.ai vision alias on the gateway (Prime).** glm-5.x is text-only at z.ai; glm-4.6v and glm-5.3-flash read images on our plan but stay off the gateway.
- `[2026-10-06]` **Scriberr diarization fixed: gated pyannote, a torchcodec/torch mismatch, and WhisperX's CPU defaults; model caches on /tank, HF_TOKEN a placeholder (Prime), GPU+speaker profiles.** Patch 0003 waits for the next rebuild (tracked at `stacks/scriberr/patches/README.md`). → `persistent-memory.d/2026-10-06-scriberr-diarization-fixed.md`
- `[2026-10-06]` **Backup checker: destroyed guests reported as residue, an ssh stdin swallow fixed, snapshot age from the name; residue pruned (Prime); pbs-nh3 mirror keeps pbs-ana's history (Prime "match history"), first prune 10-07 00:00.** → `persistent-memory.d/2026-10-06-backup-checker-fixes-and-mirror-retention.md`
- `[2026-10-08]` **Patch night (Prime's go): fv-ml1 kernel/NVIDIA/ZFS/toolkit + Docker 29.8.2 on esh-docker-vm and nh3-docker, all verified** — ZBM boot, the hand-verified NVIDIA driver path, holds re-applied. → `persistent-memory.d/2026-10-08-patch-night-fv-ml1-kernel-nvidia-zfs-docker-hosts.md`
- `[2026-10-07]` **nh3-svos refreshed to SVOS a737a06 (schema 11): knowledge, terminal (own origin) and post office apps** — acceptance 17/17 + Chromium; the thaw race. → `persistent-memory.d/2026-10-07-nh3-svos-refresh-a737a06-apps.md`
- `[2026-10-07]` **Gateway: glm-5.3 added, gen-frontier pair moved to 5.3 (effort low/high), 1M/128K advertised on GLM 5.2/5.3 (Prime)** — `thinking: disabled` is light thinking, not zero. → `persistent-memory.d/2026-10-07-gateway-glm-5-3-gen-frontier.md`
- `[2026-10-07]` **Hermes launchers repaired (Miranda relay 8462):** svos-dev's scratch probe had rewritten `~/.hermes/hermes-agent/.hermes/bin/{hermes,hermes-acp}` to exec a /tmp scratch Python. Repointed to `~/.hermes/tools/python-3.14.7…`; the gateway was not restarted. ⚠ Don't run `git` in `~/.hermes/hermes-agent`: a `status` there looped on auto-gc.
- `[2026-10-07]` **albok-service 0.1.14 (unit 4.3) deployed + all four wings reindexed** — the `.browse/` view exists on the box only; the share test is owed. → `persistent-memory.d/2026-10-07-albok-service-0-1-14.md`
- `[2026-10-07]` **albok-service 0.1.13 (unit 4.2, the sensitivity gate) deployed** — rollback to 0.1.12 needs the strip snippet first. → `persistent-memory.d/2026-10-07-albok-service-0-1-13-sensitivity-gate.md`
- `[2026-10-06]` **albok-service 0.1.11 (0202) then 0.1.12 (1254) deployed on nh3-albok at albok-dev's asks 7991/8199**, built from clean archives, pinned by digest, single-file upload (deploy-stack's `--delete` would wipe the on-host rollback copies). Every wing is now migrated to generation collections, so a 0.1.10 rollback needs a full reindex. albok's 2.01×-vs-2× load check awaits Prime. → `stacks/albok-service/README.md`
- `[2026-10-06]` **The LiteLLM gateway keeps no request/response content, and `store_prompts_in_spend_logs: false` is now a marked consumer guarantee (comfy-dev, arbo incognito).** Proved with a canary plus positive controls; per-request `no-log` does NOT cover the proxy's own spend-log callback (v1.97 source). irv-ml1 restic also excludes `input/incognito-*` (dry-run proved with a canary and a control). `847424c`, `0f6c7a0`.
- `[2026-10-06]` **jekyll moved from gen-large to sec-reasoning (Prime)** after its ~180k-token agent loop and Prime's ~140k session overflowed flash-next's KV. → `persistent-memory.d/2026-10-06-gen-large-contention-jekyll.md`
- `[2026-10-06]` **vh/rea created on gitea as a private pull mirror of github.com/morluto/rea (8h, wiki + LFS), matching the vh/ mirror convention.** Content verified (main sha, 20 branches, 29 tags).
- `[2026-10-05]` **fv-ml1: vLLM KV pinned in bytes on every shared-card seat, GPUs 0/1 rebalanced by measured usage, contexts at published (native) maximums, gen-small default output cap 32,768; YaRN stays OFF (Prime).** → `persistent-memory.d/2026-10-05-fv-ml1-kv-pins-and-rebalance.md`
- `[2026-10-05]` **Park 75 (TTS stack → fv-ml1) DROPPED (Prime, 2115):** its trigger fired 09-25, but intern-decision used the room, and the cross-site-hop objection still stands. Henge comment 63.
- `[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.** → `persistent-memory.d/2026-09-27-blender-on-fv-ml1-gpu3.md` (canonical: `stacks/blender/README.md`)
- `[2026-09-27]` **Worldtree reward path: d8726a13 + `providers.yaml` `reward_models.scalar-judge` live on demo; personal waited on a newer image.** → `persistent-memory.d/2026-09-27-worldtree-reward-path-live.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. → `persistent-memory.d/2026-09-27-zigbee2mqtt-on-esh-docker-vm.md` (canonical: `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]` **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.


- `[2026-09-17]` **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`

- `[2026-09-13]` **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`

_228 older entries archived to archival-memory.md._

## Tried and abandoned

- `[2026-10-08]` **NVIDIA's network debian12 repo on trixie via `cuda-keyring`** — trixie's sqv rejects the key's SHA1 binding signature, so `apt update` errors until the list is gone (`dpkg -r` keeps the conffile; it took `dpkg -P`). Fetch the debs and verify InRelease (gpgv) → Packages.gz → sha256 instead. → `servers/fv-ml1/README.md`
- `[2026-10-08]` **`secret get <name> | head` "to see its shape"** — a single-value secret IS its shape; it printed the fv-ml1 BMC password into the local transcript. Check with `secret list` or `wc -c`, never by printing.
- `[2026-10-07]` **An idle gate counting with `grep -c … || echo ERR`** — `grep -c` exits 1 on a ZERO count, so the value was "0\nERR" and never equalled "0"; two 75-min LiteLLM restart gates were blind to any quiet window. Use `|| true` and test the gate against a known-idle state first.
- `[2026-10-07]` **`pgrep -f <pattern>` to check that a process died** — it matched the checking shell's own command line and reported a survivor; check with `ps -eo … | grep '[x]…'`, as the same self-match bit `pkill -f` before.
- `[2026-10-06]` **Restarting a user-facing service after an idle check that only PRINTS** — `nvidia-smi … | wc -l` said 1 and the same command restarted Scriberr anyway, killing Prime's transcript run. Make the check gate (`&&` / exit). auto-memory `feedback_idle_check_must_gate_the_restart`.
- `[2026-10-06]` **Aging PBS snapshots by directory mtime** — verify jobs and notes edits rewrite `index.json.blob`, so a 10-04 snapshot read as 10-06. Age by the snapshot NAME. auto-memory `reference_pbs_snapshot_mtime_moves_on_verify`.
- `[2026-10-06]` **`deploy-stack.sh` on a stack whose host dir holds rollback copies** (albok-service `compose.yaml.pre-*`) — its rsync `--delete` removes them. Upload the single changed file with elway instead.
- `[2026-10-05]` **Sizing a vLLM seat's KV from `--gpu-memory-utilization` on a shared card** — co-booting neighbours corrupt the profile (non-torch −0.56 GiB), so the KV is a lottery per boot. Pin `--kv-cache-memory`. auto-memory `reference_vllm_util_kv_coboot_race`.
- `[2026-10-05]` **Reading GPU headroom just after a restart** — 10-01's "Free ~1.05 GB" was really a ~60 MiB plateau 2 days later. Size against Beszel history. auto-memory `feedback_vllm_headroom_at_plateau_not_boot`.
- `[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.

_123 older entries archived to archival-memory.md._