chore: pin jellyfin to 2026060106

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
frigate: sync config to live state, fix /tmp/cache size, enable VAAPI on house_east/pool_room, throttle shop_west detection
2026-06-03 21:37:46 -05:00 · 2026-06-01 15:07:36 -05:00 · 2026-05-31 20:36:02 -05:00 · 2026-05-31 18:05:30 -05:00 · 2026-05-28 18:48:44 -05:00
127 changed files with 2399 additions and 16100 deletions
@@ -142,7 +142,6 @@ When creating documentation:
 2. Full content in markdown format
 3. Mermaid diagrams embedded within the documentation
 4. Summary of what was documented and any follow-up actions needed
-5. Update the change logs

 When providing information to other agents:
 1. The specific information requested
@@ -36,8 +36,7 @@
      "Bash(docker version:*)",
      "Bash(/tmp/mcpo-config.json << 'EOF'\n{\n  \"servers\": []\n}\nEOF)",
      "Bash(/tmp/mcpo-config.json << 'EOF'\n{\n  \"mcpServers\": {}\n}\nEOF)",
-      "Bash(/tmp/mcpo-config.json << 'EOF'\n{\n  \"mcpServers\": {\n    \"example\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol/server-everything\"],\n      \"env\": {}\n    }\n  }\n}\nEOF)",
-      "Bash(sleep 20 && sshpass -p '&Rip8a115' ssh -o StrictHostKeyChecking=no glyptic@192.168.86.100 \"docker ps --filter name=n8n --format 'table {{.Names}}\\\\t{{.Status}}' && echo '---' && docker logs n8n --tail 15 2>&1\")"
+      "Bash(/tmp/mcpo-config.json << 'EOF'\n{\n  \"mcpServers\": {\n    \"example\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol/server-everything\"],\n      \"env\": {}\n    }\n  }\n}\nEOF)"
    ]
  }
 }
@@ -17,10 +17,3 @@ Thumbs.db
 .vscode/
 *.swp
 *.swo
-
-# Tool scratch output (not infrastructure)
-.playwright-mcp/
-.superpowers/
-
-# Has its own repo: git.hobbs.farm/jeremy/friday-voice.git
-/friday-voice/
@@ -23,7 +23,7 @@ This repository manages a **homelab infrastructure** with self-hosted services r
 hf-pdocker-01 (23GB RAM, i7-7700T, NVMe, HD 630 GPU) -- RESTORED (2026-03-08, hardware repaired)
 ├── [COMPOSE] Frigate NVR (:5000) -- Coral USB TPU (edgetpu), ~11ms inference, 13 cameras active
 ├── [COMPOSE] Frigate-Notify v2 (:5199) -- MQTT->AI->Matrix notifications
-├── [REMOVED] clip-service -- decommissioned 2026-07-13 (CLIP embeddings; ~2GB RAM freed, no config references from frigate-notify existed)
+├── [COMPOSE] clip-service (:5200) -- CLIP embeddings (ViT-L-14, CPU)
 ├── [COMPOSE] Home Assistant (:8123)
 ├── [COMPOSE] ESPHome (:6052)
 ├── [COMPOSE] Mosquitto (:1883, :8883)
@@ -31,38 +31,47 @@ hf-pdocker-01 (23GB RAM, i7-7700T, NVMe, HD 630 GPU) -- RESTORED (2026-03-08, ha
 ├── [COMPOSE] Guacamole (:8199) + guacd + guacamole-db (mysql, LOCAL /var/lib/guacamole-db)
 ├── [COMPOSE] AI Agents (margaret:18790, spirit:18795 [infra ops])
 ├── [COMPOSE] Traefik (reverse proxy, ports 80/443/8090)
-├── [REMOVED] AdGuard Home -- decommissioned 2026-07-13 (conf dir had been empty since 2026-05-17, DNS engine never ran, LAN uses router DNS). Ports 53/3000 freed on .192.
+├── [COMPOSE] AdGuard Home (:3000, :53)
 ├── [COMPOSE] Monitoring (Grafana :3001, Prometheus :9095, Alertmanager :9093, InfluxDB :8086, Blackbox :9115, matrix-receiver :9094)
 ├── [COMPOSE] Farm Manager API (:8888) -- dashboard + API server
 ├── [COMPOSE] Farm Agent (:8889)
 ├── [COMPOSE] Rongorongo decipherment engine -- 2 containers (rongorongo-web :8181, rongorongo-api). Server-synced state at /mnt/docker-data/configs/rongorongo/data. Traefik basicAuth on rongorongo.hobbs.farm.
-├── [COMPOSE] LinkedStorm (:8300 pipeline, :8310 api, cron no-port) -- whole-home audio assistant. VAD+Whisper STT+speaker-ID. Deployed 2026-05-28. Public: linkedstorm.hobbs.farm -> :8310.
-├── [REMOVED] VoiceCoach -- moved to GPU machine (192.168.86.150) 2026-04-04
-├── [COMPOSE] litellm (:4000?) + litellm-db -- LLM proxy (see Known Issue #15)
-├── [COMPOSE] synapse-admin -- Synapse admin UI
+├── [REMOVED] VoiceCoach -- moved to GPU machine (192.168.86.27) 2026-04-04, now Ubuntu
 ├── [COMPOSE] Node-exporter (:9100) -- standalone with pid:host
 ├── [COMPOSE] Telegraf -- metrics collection to InfluxDB
-├── [CRON] sync-frigate-to-nas (daily 2am), cleanup-frigate-media (weekly Sun 3am), restart-frigate (4x daily 4am/10am/4pm/10pm, log ~/frigate-restart.log)
+├── [CRON] sync-frigate-to-nas (daily 2am), cleanup-frigate-media (weekly Sun 3am), restart-frigate (daily 4am)
 ├── 5TB USB disk at /mnt/frigate-recordings (Frigate recordings storage)

 bart (15GB RAM, i5-4570T, HDD)
-├── [COMPOSE] Media Stack (Jellyfin, Sonarr, Radarr, SABnzbd, NZBHydra2, Jellyseerr) -- Sonarr config on LOCAL /var/lib/sonarr, NZBHydra config on LOCAL /var/lib/nzbhydra (2026-07-13), **Jellyfin config on LOCAL /var/lib/jellyfin (2026-07-19)** -- all moved off NFS after SQLite/lock crashes. **Jellyfin PINNED to jellyfin/jellyfin:2026060106 (v12.0.0 unstable)** -- its DB is on the v12 schema (ExtraIds column dropped); :latest is still 10.11.x and breaks on it. Do not unpin until official stable >= 12.
-├── [REMOVED] Onyx -- fully decommissioned 2026-07-13 (had been down since ~2026-06-08 unnoticed; containers, volumes, images removed)
-├── [REMOVED] OpenVAS -- decommissioned 2026-07-19 per user (containers, volumes incl. PG DB, image removed; ~39GB freed with other cleanup). Compose dir kept for reference. History: pg_upgrade crash-loop (Known Issue #21), DB wiped fresh 2026-07-15.
+├── [COMPOSE] Media Stack (Jellyfin, Sonarr, Radarr, SABnzbd, NZBHydra2, Jellyseerr)
+├── [COMPOSE] Onyx (:3005) -- redeployed 2026-05-20, all services :latest, Watchtower disabled on all 10
+├── [COMPOSE] OpenVAS (vulnerability scanner)
 ├── [COMPOSE] Farm Agent (:8889)
 ├── [COMPOSE] Node-exporter (:9100) -- standalone with pid:host
 ├── [COMPOSE] Telegraf -- metrics collection to InfluxDB
 ├── [COMPOSE] Watchtower

+GPU workstation / Jeremy's PC (192.168.86.27, Ubuntu 24.04 — migrated from Windows 2026-05-28)
+├── RTX 3090 (24GB VRAM), i7-13700KF, 32GB RAM
+├── [COMPOSE] Ollama (:11434) -- 21 local models, v0.24.0
+├── [COMPOSE] Open WebUI (:8080) -- AI chat, points to local Ollama
+├── [REMOVED] vLLM-Hermes -- removed 2026-05-29, VRAM freed for Speaches CUDA
+├── [COMPOSE] Speaches (:8000) -- STT/TTS via faster-whisper + Kokoro, CUDA
+├── [COMPOSE] LiveKit (:7880/:7881) -- WebRTC for VoiceCoach, key: devkey
+├── [COMPOSE] Portainer (:9000, :8002)
+├── [COMPOSE] Prometheus (:9090), DCGM-exporter (:9400), node-exporter (:9100)
+├── [COMPOSE] Watchtower (label-enable mode)
+├── Compose file: /home/glyptic/Docker/compose/docker-compose.yml
+├── vLLM compose: /home/glyptic/Docker/vllm-hermes/docker-compose.yml
+└── Model cache: /home/glyptic/Docker/data/models/
+
 hf-pdocker-02 (7.6GB RAM, i7-6700T, HDD)
-├── [COMPOSE] UniFi OS Server (container `unifi-os-server`, HTTPS on host :11443)
-├── [COMPOSE] Gitea + gitea-db (PostgreSQL) -- LevelDB queues on LOCAL /var/lib/gitea-queues (2026-07-13, stale NFS lock caused 7,972-restart loop)
-├── [COMPOSE] Semaphore + semaphore-db (MySQL, LOCAL /var/lib/semaphore-db since 2026-07-13)
+├── [COMPOSE] UniFi OS Server (:11443 HTTPS, :8080 inform, :3478/udp STUN) -- ghcr.io/lemker/unifi-os-server v5.1.15, replaced legacy linuxserver/unifi 2026-05-31. Data local at /var/lib/unifi-os/, /persistent on NAS.
+├── [COMPOSE] Gitea + gitea-db (PostgreSQL)
+├── [COMPOSE] Semaphore + semaphore-db (MySQL)
 ├── [COMPOSE] Wiki.js + wikijs-db (PostgreSQL)
-├── [COMPOSE] Vaultwarden, MCPO, Trivy
-├── [REMOVED] Actual Budget -- decommissioned 2026-07-13 (data kept at /mnt/docker-data/configs/actual-budget)
+├── [COMPOSE] Vaultwarden, Actual Budget, MCPO, Trivy
 ├── [COMPOSE] n8n + n8n-db (PostgreSQL) -- workflow automation
-├── [COMPOSE] CouchDB (:5984) -- Obsidian LiveSync backend for the Second Brain vault. LAN-only. LOCAL disk (NOT NFS).
 ├── [COMPOSE] Farm Agent (:8889)
 ├── [COMPOSE] Node-exporter (:9100) -- standalone with pid:host
 ├── [COMPOSE] Telegraf -- metrics collection to InfluxDB
@@ -74,9 +83,11 @@ hf-pdocker-02 (7.6GB RAM, i7-6700T, HDD)

 ### Environment Context

-You are working in a **WSL 2 environment** on Windows. Docker is NOT directly available in WSL - all Docker operations must be performed by connecting to the remote nodes via SSH.
+You are working on a **native Ubuntu 24.04 workstation** (previously WSL2 on Windows — migrated 2026-05-28). This machine IS the GPU inference box (RTX 3090, 192.168.86.27). Docker is available locally and runs the inference stack. All homelab node operations (hf-pdocker-01, hf-pdocker-02, bart) still require SSH.

-**Critical:** Docker is not available locally in WSL. All Docker operations must be performed by connecting to the remote nodes via SSH.
+**Local Docker on this machine** runs: Ollama, Open WebUI, vLLM-Hermes, Speaches, LiveKit, Portainer, Prometheus, DCGM-exporter.
+
+**Critical:** For homelab nodes, use the `docker-swarm-ops` agent via SSH. For local inference services, Docker commands run directly.

 ### Storage Architecture

@@ -145,21 +156,22 @@ compose/             # Standalone Compose definitions (deployed per-node)
 - Home Assistant: `yoda.hobbs.farm`
 - Vaultwarden: `vault.hobbs.farm`
 - Gitea: `git.hobbs.farm`
- FRIDAY Voice: `coach.hobbs.farm` (replaced VoiceCoach 2026-07-05; runs on .150 :8320)
+- VoiceCoach: `coach.hobbs.farm` (LiveKit WebRTC: `voice.hobbs.farm`)
 - Rongorongo: `rongorongo.hobbs.farm`
- LinkedStorm: `linkedstorm.hobbs.farm`

 ### Internal Services by Node

 **hf-pdocker-01 (192.168.86.192):**
 - Frigate: :5000
 - Frigate Alerts (v2): :5199 (web UI + REST API)
+- clip-service: :5200 (CLIP embeddings, ViT-L-14, CPU)
 - Home Assistant: :8123
 - ESPHome: :6052
 - Mosquitto: :1883
 - Matrix/Synapse: :8008
 - Well-known (Matrix federation): :8010
 - Guacamole: :8199
+- AdGuard Home: :3000 (DNS: :53)
 - Traefik Dashboard: :8090 (HTTP: :80, HTTPS: :443)
 - Grafana: :3001
 - Prometheus: :9095
@@ -171,19 +183,18 @@ compose/             # Standalone Compose definitions (deployed per-node)
 - Farm Manager: :8888 (dashboard + API)
 - Farm Agent: :8889
 - Rongorongo: :8181 (rongorongo-web nginx; reverse-proxies /api/* to rongorongo-api Flask backend on the internal `rongorongo` bridge net). State + images at /mnt/docker-data/configs/rongorongo/data/. Public URL gated by Traefik basicAuth (creds in Vaultwarden).
- LinkedStorm: :8300 (pipeline/VAD+STT+speaker-ID), :8310 (API/dashboard), cron (no port). Public: linkedstorm.hobbs.farm -> :8310. Source: /opt/linkedstorm (rsync from WSL). Data: /mnt/docker-data/configs/linkedstorm/. STT via Speaches GPU machine :8000, LLM via Ollama :11434 (qwen2.5:14b).
- ~~VoiceCoach~~ -- fully decommissioned 2026-07-05, replaced by FRIDAY Voice on .150 (see GPU Machine section + memory `friday-voice`)
+- ~~VoiceCoach~~ -- moved to GPU machine (192.168.86.150) 2026-04-04

 **hf-pdocker-02 (192.168.86.100):**
 - Farm Agent: :8889
- UniFi OS Server: :11443 (HTTPS, container 443)
+- Unifi: :8443
 - Gitea: :3003 (web), :2222 (SSH)
 - Semaphore: :3004
 - Wiki.js: :3002
 - Vaultwarden: :26226
+- Actual Budget: :5006
 - MCPO: :8001
 - Trivy: :4954
- CouchDB: :5984 -- Obsidian LiveSync backend. DB `secondbrain`; admin creds in Vaultwarden ("CouchDB - Obsidian LiveSync"). LAN-only (no Traefik route). Data on LOCAL disk `/var/lib/couchdb` (NFS breaks CouchDB file locking). **`local.ini` must be mounted READ-WRITE** -- with `:ro` CouchDB exits 1 and logs nothing. Auth required on everything except `/_up` (left open for the blackbox probe). Vault repo: git.hobbs.farm/jeremy/second-brain (private); vault lives at `C:\Users\Jeremy\second-brain` on the Windows box.

 **bart (192.168.86.167):**
 - Farm Agent: :8889
@@ -193,21 +204,25 @@ compose/             # Standalone Compose definitions (deployed per-node)
 - SABnzbd: :8082
 - NZBHydra2: :5076
 - Jellyseerr: :5055
+- OpenVAS: :9392

-**GPU Machine (192.168.86.150, RTX 3090):**
- **NOTE (2026-07-05):** .150 is actually the user's **Windows workstation** (runs the WSL/Claude Code session), not a headless Linux server. It runs **Docker Desktop** (WSL2 backend, RTX 3090 GPU passthrough working) alongside **UniFi OS Server** (Podman). Docker Desktop panics if UniFi/Podman claims `\\.\pipe\docker_engine` first — start Docker Desktop before UniFi OS Server. See memory `docker-desktop-unifi-podman-conflict`.
- **FRIDAY Voice replaced VoiceCoach (2026-07-05).** VoiceCoach fully decommissioned (v1+v2 removed from hf-pdocker-01; voice.hobbs.farm route removed). See memory `friday-voice`.
- [COMPOSE] **FRIDAY Voice stack (all on .150 Docker Desktop, via `docker.exe -c desktop-linux`):**
-  - **voicecoach-speaches-gpu**: :8000 — GPU Whisper large-v3-turbo (STT) + Kokoro-82M af_nova (TTS), CUDA float16. Compose: `compose/gpu-machine/voicecoach-speaches/`.
-  - **hermes**: `nousresearch/hermes-agent:latest` gateway — FRIDAY's reasoning agent. Settings transferred from WSL `~/.hermes` into named volume `hermes-data`. Compose: `compose/gpu-machine/hermes/`.
-  - **friday-voice**: :8320 — push-to-talk console. Calls speaches (`host.docker.internal:8000`) + hermes (`docker exec hermes hermes -Q` via wrapper). Public: **coach.hobbs.farm** → :8320. Compose: `compose/gpu-machine/friday-voice/`.
- Ollama: :11434 (qwen2.5:14b, Hermes-4.3-36B-GGUF, others)
+**GPU Machine (192.168.86.150, RTX 3090, 15GB RAM):**
+- Ollama: :11434 (llama3.1:8b for VoiceCoach LLM, qwen2.5:14b, others)
+- [COMPOSE] VoiceCoach (all services co-located):
+  - voicecoach-livekit: :7880/:7881, UDP 50000-50100 (public at voice.hobbs.farm)
+  - voicecoach-speaches-gpu: :8000 (GPU Whisper STT + Kokoro TTS, CUDA float16)
+  - voicecoach-speechbrain: :8001 (emotion analysis)
+  - voicecoach-token-server: :8080 (token + settings API)
+  - voicecoach-pipecat: pipeline agent (LLM via local Ollama llama3.1:8b)
+  - voicecoach-web: :8085 (public at coach.hobbs.farm)
+  - voicecoach-openclaw: :3100 (idle, kept for future Claude API routing)
+- Compose: ~/voicecoach-speaches/docker-compose.yml

 ### Port Conflict Notes

 Port conflicts already resolved:
 - Port 8000: Freed (MCPO moved to 8001, Portainer moved elsewhere)
- Port 3000: freed 2026-07-13 (was AdGuard Home, decommissioned; Gitea remains on 3003)
+- Port 3000: AdGuard Home (Gitea moved to 3003)
 - Port 3001: Grafana (Semaphore moved to 3004)
 - Port 5000: Frigate uses host networking (registry container stopped)
 - AI Agent ports re-spaced (2026-03-15): openclaw 2026.3.13 uses gateway+2 and gateway+3 for browser/chrome-relay. Agents spaced 5 apart: margaret=18790, spirit=18795
@@ -231,7 +246,6 @@ After ANY infrastructure change (deploy, remove, reconfigure, add service, chang
 2. **MEMORY.md** — Add/update relevant memory entries
 3. **Prometheus probes** — Add/remove blackbox targets, hot-reload Prometheus
 4. **Wiki** — Launch documentation-keeper agent to update wiki pages (run in background)
-5. **Farm Manager links page** — If a service was added/removed or its URL/port changed: edit the `serverLinks` array in `/opt/farm-manager/server/static/app.js` on hf-pdocker-01, then rebuild + redeploy: `docker build -f /opt/farm-manager/Dockerfile.server -t farm-manager:latest /opt/farm-manager && cd /mnt/docker-data/compose/hf-pdocker-01/farm-manager && docker compose up -d` (links are baked into the image, not mounted)

 Do NOT wait for the user to ask. Do NOT skip "because the change was small." Every change gets documented.

@@ -294,19 +308,8 @@ All persistent data on NAS at `/mnt/docker-data/`:
 4. **InfluxDB Connection**: Telegraf may show timeout errors if InfluxDB is not running
 5. **Frigate cameras**: Cameras on 192.168.44.x subnet may show RTSP timeouts (check camera network)
 6. **Registry container**: Stopped on hf-pdocker-01 to free port 5000 for Frigate
-7. **systemd-resolved DNSStubListener**: disabled on hf-pdocker-01 and hf-pdocker-02 via `/etc/systemd/resolved.conf.d/nostub.conf` (`DNSStubListener=no`) — originally for AdGuard Home's port 53. AdGuard was decommissioned 2026-07-13; the stub-listener change is harmless and left in place (re-enable only if something needs 127.0.0.53).
+7. **systemd-resolved DNSStubListener**: Must be disabled on any node running AdGuard Home (port 53 conflict). Fix: `/etc/systemd/resolved.conf.d/nostub.conf` with `DNSStubListener=no`, then `systemctl restart systemd-resolved`. Applied on hf-pdocker-01 and hf-pdocker-02.
 8. **NFS boot-mount race (hf-pdocker-01)**: NFS mounts failed at boot (network not ready in time). Fixed 2026-05-20 by adding `nofail,x-systemd.after=network-online.target,x-systemd.mount-timeout=60s` to both fstab entries. If mounts are missing after reboot: `sudo mount /mnt/docker-data && sudo mount /mnt/infrastructure`.
 9. **Guacamole schema**: App image pinned to `guacamole/guacamole:1.6.0` + `guacd:1.6.0` with Watchtower disabled. DB schema was reset to fresh 1.6.0 on 2026-05-20 (old schema was non-standard). Recreate connections after any DB reset.
 10. **Gitea image**: Pinned to `gitea/gitea:1.26.1` with Watchtower disabled (2026-05-20). Watchtower previously pulled broken `:latest` images causing missing git binary errors.
 11. **Home Assistant reverse proxy**: Config at `/mnt/docker-data/configs/homeassistant/configuration.yaml` (no hyphen). Must have `http: use_x_forwarded_for: true` + `trusted_proxies: [172.16.0.0/12, 127.0.0.1]` or proxied requests return 400.
-12. **hf-pdocker-01 memory pressure (2026-07-05, retrimmed 2026-07-11)**: Node runs hot (~15-18/23GB, chronic swap). Mitigations applied: `vm.swappiness` lowered 60→10 (persisted in `/etc/sysctl.d/99-swappiness.conf`), and VoiceCoach (v1+v2, ~10 containers) fully removed (replaced by FRIDAY Voice on .150). Frigate is the main consumer. **2026-07-11:** Frigate's built-in AI features (`semantic_search: large`, `face_recognition`, `lpr`, `classification.bird`) were found *enabled* (contradicting the intended baseline) and re-disabled — dropped the embeddings CLIP model ~1.2GB→168MB and cut CPU inference; host mem 18→~9GB, swap 3.9→1.3GB right after. Config `/mnt/docker-data/configs/frigate/config/config.yml` (backup `.bak.20260711-aitrim`). Recognition is instead handled externally by frigate-notify v2 (clip-service was removed 2026-07-13 — frigate-notify's config never referenced it). **2026-07-12 — WHOLE-NODE CRASH:** .192 froze hard (~14:15, sshd/HA/DNS all dead, required hard reboot). Cause: Frigate `memswap_limit` had drifted to **16G** vs `mem_limit` 12G, letting it spill ~4GB into host swap; with the ffmpeg leak pinning it at 12G all day (cgroup OOM every ~45min), the host swap-thrashed to death. **Fix: node compose `memswap_limit: 12G` (= mem_limit) so Frigate can never use host swap** — a hit now trims its own ffmpeg (contained cgroup OOM), not the host. Repo already had 12G; node had drifted (never redeployed). NOTE: recording ffmpeg still leaks ~0.8GB/h atop ~6GB baseline (fills 12G in ~7.5h); twice-daily 4am+4pm restart-frigate cron mitigates but doesn't fully beat it — consider every-6h restart + fixing broken cameras (gate_camera, garage_2). Always keep `memswap_limit == mem_limit` on this node.
-13. **Docker Desktop vs UniFi OS Server pipe conflict (Windows box .150, 2026-07-05)**: Both fight over `\\.\pipe\docker_engine`; Docker Desktop's backend nil-panics ("backend exited before becoming ready") if Podman wins. Fix: let Docker Desktop (auto-starts at login) claim the pipe first, launch UniFi OS Server manually after. Full detail in memory `docker-desktop-unifi-podman-conflict`.
-14. **MySQL InnoDB corruption on NFS**: `semaphore-db` (mysql:8.0 on NFS) hit system-tablespace page corruption and crash-looped 3789× (2026-07-11), same class as the Guacamole-on-NFS issue (#9). Recovered in-place via `--innodb-force-recovery=1` → mysqldump → fresh volume → reimport (DB was empty, no data lost); admin recreated with `semaphore user add`. Any MySQL DB on NFS is at risk — prefer LOCAL storage like guacamole-db. See memory `semaphore-db-nfs-corruption`.
-15. **litellm hangs after DB blip**: litellm does NOT self-recover from a transient `litellm-db` disconnect — it loops on "Prisma DB reconnect failed" forever; needs manual `docker restart litellm`. Its healthcheck was fixed from `curl` (absent from image, permanent false-unhealthy) to a python urllib check (2026-07-11).
-16. **Stale NFS locks after unclean reboot/power loss (2026-07-12 power event)**: NFS file locks held by pre-reboot client identities survive on the Synology and block relocking — gitea crash-looped 7,972× on its LevelDB queue lock, semaphore-db 975× on `ibdata1`, and nzbhydra2 sat unhealthy on its H2 database lock. Fix applied 2026-07-13: lock-prone data moved to LOCAL disk (gitea queues → `/var/lib/gitea-queues`, semaphore-db → `/var/lib/semaphore-db` on .100; sonarr config → `/var/lib/sonarr`, nzbhydra config → `/var/lib/nzbhydra` on bart; jellyfin config → `/var/lib/jellyfin` on bart 2026-07-19 after 60-100s "database is locked" stalls on jellyfin.db caused playback lockups). **Rule: anything holding long-lived file locks (MySQL, SQLite, LevelDB) goes on local disk, never NFS.**
-17. **Synapse rate-limited Alertmanager notifications**: default `rc_message` (0.2 msg/s) made every matrix-alertmanager-receiver send fail with M_LIMIT_EXCEEDED 429 — **no alerts reached Matrix for weeks** while outages accumulated (Onyx down 5 weeks, AdGuard dead 2 months, unnoticed). Fixed 2026-07-13: `rc_message: {per_second: 5, burst_count: 50}` in homeserver.yaml (backup `.bak-20260713-ratelimit`).
-18. **AdGuard Home decommissioned 2026-07-13**: its conf dir had been empty since 2026-05-17 (container ran the first-launch wizard, served no DNS, no backup existed) and the LAN had been using router DNS ever since. Container, data, compose dir, and Prometheus probe all removed; ports 53/3000 freed on .192. LAN DNS = the router.
-19. **Duplicate failover stacks removed from .100 and bart (2026-07-13)**: .100 ran a second monitoring stack (prometheus/grafana/alertmanager/influxdb/blackbox), an idle traefik (shared acme.json with .192 — ACME conflict risk), and a stray guacamole; bart ran a failover guacamole. All removed (~2GB RAM reclaimed). Compose dirs kept for reference; data volumes untouched.
-20. **UniFi OS Server probe port**: `unifi-os-server` on .100 serves HTTPS on host port **11443** (container 443), not 8443. Blackbox probe fixed 2026-07-13. solo.hobbs.farm returns 401 (Traefik basicAuth) when healthy — probed via `http_2xx_or_401` module.
-21. **OpenVAS pg_upgrade loop saturated bart's HDD (2026-07-15)**: `immauss/openvas:latest` looped on the PG 13→15 auto-upgrade for ~21h (158 restarts) — each cycle re-copied the 21GB DB, pinning sda at ~90% util/40% iowait and making Jellyfin (same disk) hang. The upgrade itself succeeded every time but the final `mv /data/database /data/database_13_old` failed with "Device or resource busy" because the openvas-db volume is mounted **at** `/data/database` (can't rename a mountpoint). Fixed by wiping the DB (`docker volume rm openvas_openvas-db`) and letting it initdb fresh on PG15 — scan history lost, feeds re-synced. **On the next major PG bump this will recur** unless the upgrade is done out-of-band (content-level swap) or the volume is remounted at `/data`. General rule: a service "hanging" on bart usually means another container is eating the single HDD — check `iostat -x`/`pidstat -d` first. **OpenVAS fully decommissioned 2026-07-19** (moot unless redeployed).
-22. **Jellyfin SQLite-on-NFS lockups (fixed 2026-07-19)**: jellyfin.db (WAL mode) on `/mnt/docker-data/configs/jellyfin` hit escalating `SQLite Error 5: 'database is locked'` (22→33→125/day), DB commands blocking 60-102s → healthcheck flaps + playback stalls ("Unexpected end of request content" on /Sessions/Playing/Progress). Config moved to LOCAL `/var/lib/jellyfin` (old copy left on NFS as backup). Same class as Known Issue #16.
@@ -1,322 +0,0 @@
-# RONGORONGO_DEPLOY.md
-# Rongorongo Decipherment Engine — Claude Code Deployment Guide
-# Target: hobbs.farm Docker Swarm infrastructure
-# Subdomain: rongorongo.hobbs.farm
-
---
-
-## CONTEXT
-
-This document instructs Claude Code to build, push, and deploy the Rongorongo
-Decipherment Engine as a containerized static web app to the hobbs.farm Swarm.
-
-The app is a single-file HTML/JS application served by nginx. It calls the
-Anthropic API directly from the browser. No backend, no database. All session
-state is stored in browser localStorage.
-
-Infrastructure assumptions (from existing hobbs.farm stack):
- Docker Swarm: nodes hf-pdocker-01, hf-pdocker-02, bart
- Traefik reverse proxy with wildcard *.hobbs.farm TLS via Cloudflare DNS
- External overlay network: traefik-public
- Registry: registry.hobbs.farm (if local) OR use Docker Hub as fallback
- Portainer CE available for stack management
- DNS: AdGuard Home with hairpin NAT for *.hobbs.farm
-
---
-
-## REPOSITORY STRUCTURE
-
-After cloning or creating the project, verify this structure exists:
-
-```
-rongorongo/
-├── Dockerfile
-├── nginx.conf
-├── stack.yml
-├── frontend/
-│   └── index.html
-└── RONGORONGO_DEPLOY.md  (this file)
-```
-
---
-
-## STEP 1 — VERIFY PREREQUISITES
-
-Run these checks before proceeding. Stop and report any failures.
-
-```bash
-# Confirm Docker and Swarm context
-docker info | grep -E "Swarm:|Manager:|Nodes:"
-
-# Confirm traefik-public network exists
-docker network ls | grep traefik-public
-
-# Confirm Traefik is running
-docker service ls | grep traefik
-
-# Test registry connectivity (if using local registry)
-curl -s https://registry.hobbs.farm/v2/_catalog || echo "Registry unreachable — will use build-and-load method"
-
-# Confirm you are on a Swarm manager node
-docker node ls
-```
-
-If registry.hobbs.farm is unreachable, use the ALTERNATIVE DEPLOYMENT method
-at the bottom of this document.
-
---
-
-## STEP 2 — BUILD THE IMAGE
-
-```bash
-cd rongorongo/
-
-# Build image
-docker build -t registry.hobbs.farm/rongorongo:latest .
-
-# Verify image was created
-docker images | grep rongorongo
-```
-
-Expected output: image tagged `registry.hobbs.farm/rongorongo:latest`, size
-should be ~25–40MB (nginx:alpine base + small HTML file).
-
---
-
-## STEP 3 — PUSH TO REGISTRY
-
-```bash
-# If registry requires auth:
-docker login registry.hobbs.farm
-
-# Push
-docker push registry.hobbs.farm/rongorongo:latest
-```
-
-If the push fails due to registry issues, fall through to ALTERNATIVE DEPLOYMENT.
-
---
-
-## STEP 4 — DEPLOY STACK
-
-```bash
-# Deploy or update the stack
-docker stack deploy -c stack.yml rongorongo --with-registry-auth
-
-# Watch rollout
-docker service ps rongorongo_rongorongo --no-trunc
-```
-
-Wait for the service to show `Running` status. This typically takes 15–30 seconds.
-
-```bash
-# Confirm healthy
-docker service ls | grep rongorongo
-curl -s http://localhost/health  # or via container exec
-```
-
---
-
-## STEP 5 — DNS VERIFICATION
-
-The stack.yml assumes `rongorongo.hobbs.farm` resolves to the Traefik entrypoint.
-
-```bash
-# Check AdGuard Home has the record (or wildcard covers it)
-nslookup rongorongo.hobbs.farm
-
-# Test internal access
-curl -sk https://rongorongo.hobbs.farm/health
-```
-
-If using AdGuard Home for internal DNS and the wildcard *.hobbs.farm is already
-configured for hairpin NAT, no additional DNS entry is needed.
-
---
-
-## STEP 6 — SMOKE TEST
-
-Open https://rongorongo.hobbs.farm in a browser and verify:
-1. App loads with "Rongorongo · Decipherment Engine" title
-2. Sidebar navigation works (Image Corpus, Glyph Catalog, etc.)
-3. Enter an Anthropic API key in the sidebar footer input
-4. Upload a test image to the corpus
-5. Navigate to Pattern Analyzer and run an analysis
-6. Confirm AI response appears in the result box
-
---
-
-## UPDATING THE APP
-
-When index.html is modified:
-
-```bash
-cd rongorongo/
-
-# Rebuild
-docker build -t registry.hobbs.farm/rongorongo:latest .
-
-# Push
-docker push registry.hobbs.farm/rongorongo:latest
-
-# Force service update (pull new image)
-docker service update --image registry.hobbs.farm/rongorongo:latest --force rongorongo_rongorongo
-
-# Watch update
-docker service ps rongorongo_rongorongo
-```
-
---
-
-## ROLLBACK
-
-If something breaks after an update:
-
-```bash
-docker service rollback rongorongo_rongorongo
-docker service ps rongorongo_rongorongo
-```
-
---
-
-## TEARDOWN
-
-To remove the service without destroying data (there is no persistent volume):
-
-```bash
-docker stack rm rongorongo
-```
-
---
-
-## ALTERNATIVE DEPLOYMENT (no registry)
-
-Use this if registry.hobbs.farm is unavailable. This method builds the image
-directly on the Swarm manager and uses `docker service create` instead of
-`stack deploy`.
-
-```bash
-# On the Swarm manager node:
-cd rongorongo/
-
-# Build locally
-docker build -t rongorongo:latest .
-
-# Create service manually (adjust Traefik labels as needed)
-docker service create \
-  --name rongorongo_rongorongo \
-  --network traefik-public \
-  --label "traefik.enable=true" \
-  --label "traefik.docker.network=traefik-public" \
-  --label "traefik.http.routers.rongorongo.rule=Host(\`rongorongo.hobbs.farm\`)" \
-  --label "traefik.http.routers.rongorongo.entrypoints=websecure" \
-  --label "traefik.http.routers.rongorongo.tls=true" \
-  --label "traefik.http.routers.rongorongo.tls.certresolver=cloudflare" \
-  --label "traefik.http.services.rongorongo.loadbalancer.server.port=80" \
-  --replicas 1 \
-  --restart-condition on-failure \
-  rongorongo:latest
-
-# Monitor
-docker service ps rongorongo_rongorongo
-```
-
-NOTE: With this method, to update you must rebuild locally and run:
-```bash
-docker service update --image rongorongo:latest --force rongorongo_rongorongo
-```
-
-This only works if your current node is the one running the replica. If you
-have a multi-node swarm, you should set up the registry to avoid placement issues.
-
---
-
-## PORTAINER DEPLOYMENT (optional GUI method)
-
-If you prefer Portainer CE:
-
-1. Navigate to https://portainer.hobbs.farm (or your Portainer URL)
-2. Select the Swarm endpoint
-3. Go to Stacks → Add Stack
-4. Name: `rongorongo`
-5. Paste the contents of stack.yml into the web editor
-6. Set `registry.hobbs.farm/rongorongo:latest` as the image
-   (you still need to build and push first)
-7. Click Deploy the stack
-
---
-
-## ENVIRONMENT NOTES
-
-The app does NOT use environment variables or Docker secrets. The Anthropic API
-key is entered by the user at runtime and stored in their browser's localStorage.
-This is intentional — the app is designed to be used by a single user (Jeremy)
-and no server-side key storage is needed or appropriate.
-
-If you want to pre-populate the API key for convenience (only if the deployment
-is strictly private/internal), you can inject it at build time by modifying
-frontend/index.html before building:
-
-Find this line:
-```javascript
-function getApiKey() {
-  return document.getElementById('apiKeyInput').value.trim()
-```
-
-And prepend a hardcoded fallback (NOT recommended for any externally accessible URL).
-
---
-
-## TRAEFIK ENTRYPOINT NAMES
-
-The stack.yml assumes:
- HTTP entrypoint name: `web`
- HTTPS entrypoint name: `websecure`
- Cert resolver name: `cloudflare`
-
-These match the standard hobbs.farm Traefik configuration. If your Traefik uses
-different names, edit the labels in stack.yml before deploying.
-
---
-
-## TROUBLESHOOTING
-
-**Service won't start:**
-```bash
-docker service ps rongorongo_rongorongo --no-trunc
-docker inspect $(docker ps -q --filter name=rongorongo) 2>/dev/null | grep -A5 '"State"'
-```
-
-**Traefik not routing:**
-```bash
-# Check Traefik logs for rongorongo
-docker service logs traefik_traefik 2>&1 | grep -i rongorongo | tail -20
-# Confirm labels are applied
-docker service inspect rongorongo_rongorongo | grep -A2 Labels
-```
-
-**TLS cert not issuing:**
-```bash
-# Wildcard cert should already cover rongorongo.hobbs.farm
-# If not, check Cloudflare DNS API token has Zone:Read and DNS:Edit
-docker service logs traefik_traefik 2>&1 | grep -i "acme\|certificate\|cloudflare" | tail -20
-```
-
-**API calls blocked (CORS/CSP):**
-The nginx.conf includes a Content-Security-Policy header that allows
-`connect-src https://api.anthropic.com`. If you see CORS errors in the browser
-console, verify the CSP header is present:
-```bash
-curl -I https://rongorongo.hobbs.farm/ | grep -i content-security
-```
-
-**App loads but AI calls fail:**
- Check API key is entered correctly in the sidebar
- Anthropic API key must start with `sk-ant-`
- Confirm outbound HTTPS to api.anthropic.com is not blocked by firewall rules
- The app sends `anthropic-dangerous-direct-browser-access: true` header which
-  is required for direct browser API access
-
---
-
-## END OF DEPLOYMENT GUIDE
@@ -1,18 +0,0 @@
-FROM nginx:1.25-alpine
-
-# Remove default nginx static content
-RUN rm -rf /usr/share/nginx/html/*
-
-# Copy app
-COPY frontend/index.html /usr/share/nginx/html/index.html
-
-# Copy nginx config
-COPY nginx.conf /etc/nginx/conf.d/default.conf
-
-# Healthcheck
-HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
-  CMD wget -qO- http://localhost/health || exit 1
-
-EXPOSE 80
-
-CMD ["nginx", "-g", "daemon off;"]
@@ -1,322 +0,0 @@
-# RONGORONGO_DEPLOY.md
-# Rongorongo Decipherment Engine — Claude Code Deployment Guide
-# Target: hobbs.farm Docker Swarm infrastructure
-# Subdomain: rongorongo.hobbs.farm
-
---
-
-## CONTEXT
-
-This document instructs Claude Code to build, push, and deploy the Rongorongo
-Decipherment Engine as a containerized static web app to the hobbs.farm Swarm.
-
-The app is a single-file HTML/JS application served by nginx. It calls the
-Anthropic API directly from the browser. No backend, no database. All session
-state is stored in browser localStorage.
-
-Infrastructure assumptions (from existing hobbs.farm stack):
- Docker Swarm: nodes hf-pdocker-01, hf-pdocker-02, bart
- Traefik reverse proxy with wildcard *.hobbs.farm TLS via Cloudflare DNS
- External overlay network: traefik-public
- Registry: registry.hobbs.farm (if local) OR use Docker Hub as fallback
- Portainer CE available for stack management
- DNS: AdGuard Home with hairpin NAT for *.hobbs.farm
-
---
-
-## REPOSITORY STRUCTURE
-
-After cloning or creating the project, verify this structure exists:
-
-```
-rongorongo/
-├── Dockerfile
-├── nginx.conf
-├── stack.yml
-├── frontend/
-│   └── index.html
-└── RONGORONGO_DEPLOY.md  (this file)
-```
-
---
-
-## STEP 1 — VERIFY PREREQUISITES
-
-Run these checks before proceeding. Stop and report any failures.
-
-```bash
-# Confirm Docker and Swarm context
-docker info | grep -E "Swarm:|Manager:|Nodes:"
-
-# Confirm traefik-public network exists
-docker network ls | grep traefik-public
-
-# Confirm Traefik is running
-docker service ls | grep traefik
-
-# Test registry connectivity (if using local registry)
-curl -s https://registry.hobbs.farm/v2/_catalog || echo "Registry unreachable — will use build-and-load method"
-
-# Confirm you are on a Swarm manager node
-docker node ls
-```
-
-If registry.hobbs.farm is unreachable, use the ALTERNATIVE DEPLOYMENT method
-at the bottom of this document.
-
---
-
-## STEP 2 — BUILD THE IMAGE
-
-```bash
-cd rongorongo/
-
-# Build image
-docker build -t registry.hobbs.farm/rongorongo:latest .
-
-# Verify image was created
-docker images | grep rongorongo
-```
-
-Expected output: image tagged `registry.hobbs.farm/rongorongo:latest`, size
-should be ~25–40MB (nginx:alpine base + small HTML file).
-
---
-
-## STEP 3 — PUSH TO REGISTRY
-
-```bash
-# If registry requires auth:
-docker login registry.hobbs.farm
-
-# Push
-docker push registry.hobbs.farm/rongorongo:latest
-```
-
-If the push fails due to registry issues, fall through to ALTERNATIVE DEPLOYMENT.
-
---
-
-## STEP 4 — DEPLOY STACK
-
-```bash
-# Deploy or update the stack
-docker stack deploy -c stack.yml rongorongo --with-registry-auth
-
-# Watch rollout
-docker service ps rongorongo_rongorongo --no-trunc
-```
-
-Wait for the service to show `Running` status. This typically takes 15–30 seconds.
-
-```bash
-# Confirm healthy
-docker service ls | grep rongorongo
-curl -s http://localhost/health  # or via container exec
-```
-
---
-
-## STEP 5 — DNS VERIFICATION
-
-The stack.yml assumes `rongorongo.hobbs.farm` resolves to the Traefik entrypoint.
-
-```bash
-# Check AdGuard Home has the record (or wildcard covers it)
-nslookup rongorongo.hobbs.farm
-
-# Test internal access
-curl -sk https://rongorongo.hobbs.farm/health
-```
-
-If using AdGuard Home for internal DNS and the wildcard *.hobbs.farm is already
-configured for hairpin NAT, no additional DNS entry is needed.
-
---
-
-## STEP 6 — SMOKE TEST
-
-Open https://rongorongo.hobbs.farm in a browser and verify:
-1. App loads with "Rongorongo · Decipherment Engine" title
-2. Sidebar navigation works (Image Corpus, Glyph Catalog, etc.)
-3. Enter an Anthropic API key in the sidebar footer input
-4. Upload a test image to the corpus
-5. Navigate to Pattern Analyzer and run an analysis
-6. Confirm AI response appears in the result box
-
---
-
-## UPDATING THE APP
-
-When index.html is modified:
-
-```bash
-cd rongorongo/
-
-# Rebuild
-docker build -t registry.hobbs.farm/rongorongo:latest .
-
-# Push
-docker push registry.hobbs.farm/rongorongo:latest
-
-# Force service update (pull new image)
-docker service update --image registry.hobbs.farm/rongorongo:latest --force rongorongo_rongorongo
-
-# Watch update
-docker service ps rongorongo_rongorongo
-```
-
---
-
-## ROLLBACK
-
-If something breaks after an update:
-
-```bash
-docker service rollback rongorongo_rongorongo
-docker service ps rongorongo_rongorongo
-```
-
---
-
-## TEARDOWN
-
-To remove the service without destroying data (there is no persistent volume):
-
-```bash
-docker stack rm rongorongo
-```
-
---
-
-## ALTERNATIVE DEPLOYMENT (no registry)
-
-Use this if registry.hobbs.farm is unavailable. This method builds the image
-directly on the Swarm manager and uses `docker service create` instead of
-`stack deploy`.
-
-```bash
-# On the Swarm manager node:
-cd rongorongo/
-
-# Build locally
-docker build -t rongorongo:latest .
-
-# Create service manually (adjust Traefik labels as needed)
-docker service create \
-  --name rongorongo_rongorongo \
-  --network traefik-public \
-  --label "traefik.enable=true" \
-  --label "traefik.docker.network=traefik-public" \
-  --label "traefik.http.routers.rongorongo.rule=Host(\`rongorongo.hobbs.farm\`)" \
-  --label "traefik.http.routers.rongorongo.entrypoints=websecure" \
-  --label "traefik.http.routers.rongorongo.tls=true" \
-  --label "traefik.http.routers.rongorongo.tls.certresolver=cloudflare" \
-  --label "traefik.http.services.rongorongo.loadbalancer.server.port=80" \
-  --replicas 1 \
-  --restart-condition on-failure \
-  rongorongo:latest
-
-# Monitor
-docker service ps rongorongo_rongorongo
-```
-
-NOTE: With this method, to update you must rebuild locally and run:
-```bash
-docker service update --image rongorongo:latest --force rongorongo_rongorongo
-```
-
-This only works if your current node is the one running the replica. If you
-have a multi-node swarm, you should set up the registry to avoid placement issues.
-
---
-
-## PORTAINER DEPLOYMENT (optional GUI method)
-
-If you prefer Portainer CE:
-
-1. Navigate to https://portainer.hobbs.farm (or your Portainer URL)
-2. Select the Swarm endpoint
-3. Go to Stacks → Add Stack
-4. Name: `rongorongo`
-5. Paste the contents of stack.yml into the web editor
-6. Set `registry.hobbs.farm/rongorongo:latest` as the image
-   (you still need to build and push first)
-7. Click Deploy the stack
-
---
-
-## ENVIRONMENT NOTES
-
-The app does NOT use environment variables or Docker secrets. The Anthropic API
-key is entered by the user at runtime and stored in their browser's localStorage.
-This is intentional — the app is designed to be used by a single user (Jeremy)
-and no server-side key storage is needed or appropriate.
-
-If you want to pre-populate the API key for convenience (only if the deployment
-is strictly private/internal), you can inject it at build time by modifying
-frontend/index.html before building:
-
-Find this line:
-```javascript
-function getApiKey() {
-  return document.getElementById('apiKeyInput').value.trim()
-```
-
-And prepend a hardcoded fallback (NOT recommended for any externally accessible URL).
-
---
-
-## TRAEFIK ENTRYPOINT NAMES
-
-The stack.yml assumes:
- HTTP entrypoint name: `web`
- HTTPS entrypoint name: `websecure`
- Cert resolver name: `cloudflare`
-
-These match the standard hobbs.farm Traefik configuration. If your Traefik uses
-different names, edit the labels in stack.yml before deploying.
-
---
-
-## TROUBLESHOOTING
-
-**Service won't start:**
-```bash
-docker service ps rongorongo_rongorongo --no-trunc
-docker inspect $(docker ps -q --filter name=rongorongo) 2>/dev/null | grep -A5 '"State"'
-```
-
-**Traefik not routing:**
-```bash
-# Check Traefik logs for rongorongo
-docker service logs traefik_traefik 2>&1 | grep -i rongorongo | tail -20
-# Confirm labels are applied
-docker service inspect rongorongo_rongorongo | grep -A2 Labels
-```
-
-**TLS cert not issuing:**
-```bash
-# Wildcard cert should already cover rongorongo.hobbs.farm
-# If not, check Cloudflare DNS API token has Zone:Read and DNS:Edit
-docker service logs traefik_traefik 2>&1 | grep -i "acme\|certificate\|cloudflare" | tail -20
-```
-
-**API calls blocked (CORS/CSP):**
-The nginx.conf includes a Content-Security-Policy header that allows
-`connect-src https://api.anthropic.com`. If you see CORS errors in the browser
-console, verify the CSP header is present:
-```bash
-curl -I https://rongorongo.hobbs.farm/ | grep -i content-security
-```
-
-**App loads but AI calls fail:**
- Check API key is entered correctly in the sidebar
- Anthropic API key must start with `sk-ant-`
- Confirm outbound HTTPS to api.anthropic.com is not blocked by firewall rules
- The app sends `anthropic-dangerous-direct-browser-access: true` header which
-  is required for direct browser API access
-
---
-
-## END OF DEPLOYMENT GUIDE
@@ -1,41 +0,0 @@
-server {
-    listen 80;
-    server_name _;
-
-    root /usr/share/nginx/html;
-    index index.html;
-
-    # Security headers
-    add_header X-Frame-Options "SAMEORIGIN" always;
-    add_header X-Content-Type-Options "nosniff" always;
-    add_header X-XSS-Protection "1; mode=block" always;
-    add_header Referrer-Policy "strict-origin-when-cross-origin" always;
-
-    # CSP — allows Anthropic API calls and Google Fonts
-    add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src 'self' https://fonts.gstatic.com; img-src 'self' data: blob:; connect-src 'self' https://api.anthropic.com; worker-src blob:;" always;
-
-    # Gzip
-    gzip on;
-    gzip_types text/html text/css application/javascript;
-    gzip_min_length 1024;
-
-    # Health endpoint
-    location /health {
-        access_log off;
-        return 200 "ok\n";
-        add_header Content-Type text/plain;
-    }
-
-    # SPA fallback
-    location / {
-        try_files $uri $uri/ /index.html;
-        expires -1;
-        add_header Cache-Control "no-store, no-cache, must-revalidate";
-    }
-
-    # Cache static assets aggressively if you add any
-    location ~* \.(js|css|png|jpg|jpeg|gif|ico|woff2)$ {
-        expires 1y;
-        add_header Cache-Control "public, immutable";
-    }
-}
@@ -1,48 +0,0 @@
-version: "3.8"
-
-services:
-  rongorongo:
-    image: registry.hobbs.farm/rongorongo:latest
-    networks:
-      - traefik-public
-    deploy:
-      replicas: 1
-      restart_policy:
-        condition: on-failure
-        delay: 10s
-        max_attempts: 3
-      update_config:
-        parallelism: 1
-        delay: 10s
-        failure_action: rollback
-      labels:
-        - "traefik.enable=true"
-        - "traefik.docker.network=traefik-public"
-
-        # HTTP → HTTPS redirect
-        - "traefik.http.routers.rongorongo-http.rule=Host(`rongorongo.hobbs.farm`)"
-        - "traefik.http.routers.rongorongo-http.entrypoints=web"
-        - "traefik.http.routers.rongorongo-http.middlewares=redirect-to-https"
-
-        # HTTPS router
-        - "traefik.http.routers.rongorongo.rule=Host(`rongorongo.hobbs.farm`)"
-        - "traefik.http.routers.rongorongo.entrypoints=websecure"
-        - "traefik.http.routers.rongorongo.tls=true"
-        - "traefik.http.routers.rongorongo.tls.certresolver=cloudflare"
-
-        # Service
-        - "traefik.http.services.rongorongo.loadbalancer.server.port=80"
-
-        # Middlewares
-        - "traefik.http.routers.rongorongo.middlewares=rongorongo-headers"
-        - "traefik.http.middlewares.rongorongo-headers.headers.customResponseHeaders.X-Robots-Tag=noindex,nofollow"
-    healthcheck:
-      test: ["CMD", "wget", "-qO-", "http://localhost/health"]
-      interval: 30s
-      timeout: 5s
-      retries: 3
-      start_period: 10s
-
-networks:
-  traefik-public:
-    external: true
@@ -1,30 +1,16 @@
 services:
  jellyfin:
-    # PINNED to the 12.0.0 unstable build that migrated the DB to the v12
-    # schema (DropExtraIdsColumn) — :latest is still 10.11.x and CANNOT read
-    # this DB ("no such column: b.ExtraIds"). Do not unpin until official
-    # stable >= 12 ships. (2026-07-14: a :latest deploy downgraded it and
-    # broke Resume/home sections; repinned.)
    image: jellyfin/jellyfin:2026060106
    container_name: jellyfin
    restart: unless-stopped
    environment:
      - PUID=1000
      - PGID=1000
-      - LIBVA_DRIVER_NAME=i965   # Haswell HD 4600 uses legacy i965 (iHD is Broadwell+)
    volumes:
-      # LOCAL disk, not NFS: jellyfin.db (SQLite WAL) on NFS caused 60-100s
-      # "database is locked" stalls -> server lockups during playback
-      # (2026-07-19). Old copy left at /mnt/docker-data/configs/jellyfin.
-      - /var/lib/jellyfin:/config
+      - /mnt/docker-data/configs/jellyfin:/config
      - /mnt/nas-media:/media
    ports:
      - "8096:8096"
-    devices:
-      - /dev/dri:/dev/dri        # Intel iGPU for VAAPI hardware transcoding
-    group_add:
-      - "993"   # render
-      - "44"    # video
    mem_limit: 2G
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8096/health || exit 1"]
@@ -47,9 +33,7 @@ services:
      - PGID=1000
      - TZ=America/Chicago
    volumes:
-      # LOCAL disk, not NFS: SQLite-on-NFS locking crashed Sonarr's DB migration
-      # after the 2026-07-12 power event ("waiting for user intervention")
-      - /var/lib/sonarr:/config
+      - /mnt/docker-data/configs/sonarr:/config
      - /mnt/nas-media:/media
    ports:
      - "8989:8989"
@@ -127,12 +111,10 @@ services:
      - PGID=1000
      - TZ=America/Chicago
    volumes:
-      # LOCAL disk, not NFS: stale NFS lock on the H2 database after the
-      # 2026-07-12 power event kept hydra unhealthy in a DB-retry loop
-      - /var/lib/nzbhydra:/config
+      - /mnt/docker-data/configs/nzbhydra:/config
    ports:
      - "5076:5076"
-    mem_limit: 1G
+    mem_limit: 512M
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:5076/ || exit 1"]
      interval: 30s
@@ -1,24 +0,0 @@
-services:
-  node-exporter:
-    image: prom/node-exporter:v1.7.0
-    container_name: node-exporter
-    hostname: bart
-    network_mode: host
-    pid: host
-    restart: unless-stopped
-    volumes:
-      - /proc:/host/proc:ro
-      - /sys:/host/sys:ro
-      - /:/rootfs:ro
-    command:
-      - '--path.procfs=/host/proc'
-      - '--path.rootfs=/rootfs'
-      - '--path.sysfs=/host/sys'
-      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
@@ -0,0 +1,231 @@
+services:
+  api_server:
+    image: onyxdotapp/onyx-backend:latest
+    command: >
+      /bin/sh -c "alembic upgrade head &&
+      echo Starting Onyx API Server &&
+      uvicorn onyx.main:app --host 0.0.0.0 --port 8080"
+    depends_on:
+      relational_db:
+        condition: service_healthy
+      index:
+        condition: service_healthy
+      cache:
+        condition: service_healthy
+    restart: "no"
+    mem_limit: 2G
+    memswap_limit: 2G
+    env_file:
+      - .env
+    environment:
+      - AUTH_TYPE=basic
+      - DISABLE_TELEMETRY=true
+      - POSTGRES_HOST=relational_db
+      - VESPA_HOST=index
+      - REDIS_HOST=cache
+      - MODEL_SERVER_HOST=inference_model_server
+      - INDEXING_MODEL_SERVER_HOST=indexing_model_server
+      - OPENSEARCH_HOST=opensearch
+      - ENABLE_OPENSEARCH_INDEXING_FOR_ONYX=false
+      - FILE_STORE_BACKEND=postgres
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - onyx_file_connector:/home/file_connector_storage
+    networks:
+      - onyx
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  background:
+    image: onyxdotapp/onyx-backend:latest
+    command: >
+      /bin/sh -c "/usr/bin/supervisord -c /etc/supervisor/conf.d/supervisord.conf"
+    depends_on:
+      relational_db:
+        condition: service_healthy
+      index:
+        condition: service_healthy
+      cache:
+        condition: service_healthy
+    restart: "no"
+    mem_limit: 3G
+    memswap_limit: 3G
+    env_file:
+      - .env
+    environment:
+      - AUTH_TYPE=basic
+      - DISABLE_TELEMETRY=true
+      - POSTGRES_HOST=relational_db
+      - VESPA_HOST=index
+      - REDIS_HOST=cache
+      - MODEL_SERVER_HOST=inference_model_server
+      - INDEXING_MODEL_SERVER_HOST=indexing_model_server
+      - OPENSEARCH_HOST=opensearch
+      - ENABLE_OPENSEARCH_INDEXING_FOR_ONYX=false
+      - FILE_STORE_BACKEND=postgres
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - onyx_file_connector:/home/file_connector_storage
+    networks:
+      - onyx
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  web_server:
+    image: onyxdotapp/onyx-web-server:latest
+    depends_on:
+      - api_server
+    restart: "no"
+    mem_limit: 512M
+    memswap_limit: 512M
+    environment:
+      - INTERNAL_URL=http://api_server:8080
+      - WEB_DOMAIN=https://onyx.hobbs.farm
+      - NEXT_PUBLIC_DISABLE_STREAMING=false
+      - AUTH_TYPE=basic
+    networks:
+      - onyx
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  inference_model_server:
+    image: onyxdotapp/onyx-model-server:latest
+    command: >
+      /bin/sh -c "exec uvicorn model_server.main:app --host 0.0.0.0 --port 9000"
+    restart: "no"
+    mem_limit: 2G
+    memswap_limit: 2G
+    environment:
+      - MIN_THREADS_ML_MODELS=1
+      - LOG_LEVEL=info
+    volumes:
+      - onyx_model_cache_huggingface:/root/.cache/huggingface/
+    networks:
+      - onyx
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  indexing_model_server:
+    image: onyxdotapp/onyx-model-server:latest
+    command: >
+      /bin/sh -c "exec uvicorn model_server.main:app --host 0.0.0.0 --port 9000"
+    restart: "no"
+    mem_limit: 2G
+    memswap_limit: 2G
+    environment:
+      - MIN_THREADS_ML_MODELS=1
+      - INDEXING_ONLY=true
+      - LOG_LEVEL=info
+    volumes:
+      - onyx_model_cache_huggingface:/root/.cache/huggingface/
+    networks:
+      - onyx
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  relational_db:
+    image: postgres:15.2-alpine
+    restart: "no"
+    mem_limit: 512M
+    memswap_limit: 512M
+    environment:
+      - POSTGRES_USER=postgres
+      - POSTGRES_PASSWORD=onyx_postgres_pw
+    volumes:
+      - onyx_db:/var/lib/postgresql/data
+    networks:
+      - onyx
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U postgres"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  index:
+    image: vespaengine/vespa:8.609.39
+    restart: "no"
+    mem_limit: 4G
+    memswap_limit: 4G
+    volumes:
+      - onyx_vespa:/opt/vespa/var
+    networks:
+      - onyx
+    healthcheck:
+      test: ["CMD-SHELL", "curl -sf http://localhost:19071/state/v1/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 10
+      start_period: 120s
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  opensearch:
+    image: opensearchproject/opensearch:2.11.1
+    restart: "no"
+    mem_limit: 2G
+    memswap_limit: 2G
+    environment:
+      - discovery.type=single-node
+      - plugins.security.disabled=true
+      - OPENSEARCH_JAVA_OPTS=-Xms1g -Xmx1g
+      - DISABLE_INSTALL_DEMO_CONFIG=true
+    volumes:
+      - onyx_opensearch:/usr/share/opensearch/data
+    networks:
+      - onyx
+    healthcheck:
+      test: ["CMD-SHELL", "curl -sf http://localhost:9200/_cluster/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 10
+      start_period: 120s
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  cache:
+    image: redis:7.4-alpine
+    restart: "no"
+    mem_limit: 256M
+    memswap_limit: 256M
+    command: redis-server --maxmemory 128mb --maxmemory-policy allkeys-lru
+    networks:
+      - onyx
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+  nginx:
+    image: nginx:1.25.5-alpine
+    restart: "no"
+    mem_limit: 128M
+    memswap_limit: 128M
+    depends_on:
+      - api_server
+      - web_server
+    ports:
+      - "3005:80"
+    volumes:
+      - ./nginx.conf:/etc/nginx/conf.d/default.conf:ro
+    networks:
+      - onyx
+    labels:
+      com.centurylinklabs.watchtower.enable: "false"
+
+volumes:
+  onyx_file_connector:
+  onyx_model_cache_huggingface:
+  onyx_db:
+  onyx_vespa:
+  onyx_opensearch:
+
+networks:
+  onyx:
+    driver: bridge
@@ -0,0 +1,36 @@
+server {
+    listen 80;
+    server_name _;
+
+    # Use Docker's internal DNS with a short TTL so container IP changes
+    # (e.g. after docker compose up -d for a single service) are picked up
+    # without requiring an nginx reload.
+    resolver 127.0.0.11 valid=10s;
+
+    client_max_body_size 100M;
+
+    location /api/ {
+        set $api_upstream http://api_server:8080;
+        rewrite ^/api/(.*)$ /$1 break;
+        proxy_pass $api_upstream;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+        proxy_read_timeout 300s;
+        proxy_connect_timeout 75s;
+        proxy_buffering off;
+        proxy_cache off;
+    }
+
+    location / {
+        set $web_upstream http://web_server:3000;
+        proxy_pass $web_upstream;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+        proxy_read_timeout 300s;
+        proxy_connect_timeout 75s;
+    }
+}
@@ -3,10 +3,6 @@ services:
    image: immauss/openvas:latest
    container_name: openvas
    restart: unless-stopped
-    labels:
-      # Watchtower pulled a new major that forced a pg_upgrade crash-loop
-      # (212 restarts, 2026-07-13); update OpenVAS deliberately instead
-      - "com.centurylinklabs.watchtower.enable=false"
    environment:
      - PASSWORD=${OPENVAS_PASSWORD}
      - USERNAME=${OPENVAS_USERNAME}
@@ -1,22 +0,0 @@
-services:
-  telegraf:
-    image: telegraf:latest
-    container_name: telegraf
-    hostname: bart
-    restart: unless-stopped
-    environment:
-      - HOST_PROC=/host/proc
-      - HOST_SYS=/host/sys
-      - HOST_ETC=/host/etc
-    volumes:
-      - /mnt/docker-data/configs/telegraf/telegraf.conf:/etc/telegraf/telegraf.conf:ro
-      - /var/run/docker.sock:/var/run/docker.sock:ro
-      - /sys:/host/sys:ro
-      - /proc:/host/proc:ro
-      - /etc:/host/etc:ro
-    mem_limit: 512M
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
@@ -1,17 +0,0 @@
-# Overlay on the friday-voice app image that adds the docker CLI + a wrapper so
-# the container can reach the hermes agent via `docker exec hermes hermes ...`.
-# Runs as root to access the mounted /var/run/docker.sock.
-FROM friday-voice:latest
-
-USER root
-
-# Static docker *client* only (~small), for `docker exec` into the hermes container.
-RUN curl -fsSL https://download.docker.com/linux/static/stable/x86_64/docker-27.5.1.tgz \
-      | tar -xz --strip-components=1 -C /usr/local/bin docker/docker \
-    && chmod +x /usr/local/bin/docker \
-    && docker --version
-
-COPY hermes-wrap /usr/local/bin/hermes-wrap
-RUN chmod +x /usr/local/bin/hermes-wrap
-
-# Keep the base image's CMD (uvicorn friday_voice.app:app :8320).
@@ -1,49 +0,0 @@
-# FRIDAY Voice on .150 (Docker Desktop) — replaces VoiceCoach.
-# STT/TTS via local GPU speaches (:8000). Reasoning via the hermes container
-# (invoked through the docker-exec wrapper). Runs as root for socket access.
-services:
-  friday-voice:
-    build:
-      context: .
-      dockerfile: Dockerfile.hermes
-    image: friday-voice-hermes:latest
-    container_name: friday-voice
-    restart: unless-stopped
-    user: "0:0"
-    ports:
-      - "8320:8320"
-    volumes:
-      - friday-voice-data:/data
-      - /var/run/docker.sock:/var/run/docker.sock
-    environment:
-      - DATA_DIR=/data
-      - SPEACHES_URL=http://host.docker.internal:8000
-      - HERMES_COMMAND=/usr/local/bin/hermes-wrap
-      - HERMES_SOURCE=friday-voice
-      - WHISPER_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
-      - TTS_MODEL=speaches-ai/Kokoro-82M-v1.0-ONNX
-      - TTS_VOICE=af_nova
-      - SPEAKER_CONFIRMED_THRESHOLD=0.85
-      - SPEAKER_PROBABLE_THRESHOLD=0.70
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    healthcheck:
-      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:8320/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 20s
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "20m"
-        max-file: "3"
-
-volumes:
-  friday-voice-data:
-
-networks:
-  default:
-    name: friday-voice
@@ -1,5 +0,0 @@
-#!/bin/sh
-# friday-voice invokes: hermes-wrap chat -q "<text>" --source friday-voice
-# We forward into the hermes container and add -Q (quiet) so only the final
-# response text is returned (no banner/spinner/box art) for clean TTS.
-exec docker exec hermes hermes "$@" -Q
@@ -1,30 +0,0 @@
-# Hermes Agent on .150 (Docker Desktop) — FRIDAY's reasoning agent.
-# Data/settings live in the `hermes-data` named volume, seeded from the user's
-# WSL ~/.hermes (settings preserved; SQLite state.db kept on the VM ext4, not a
-# bridged bind mount). friday-voice calls this via `docker exec hermes hermes ...`.
-services:
-  gateway:
-    image: nousresearch/hermes-agent:latest
-    container_name: hermes
-    restart: unless-stopped
-    volumes:
-      - hermes-data:/opt/data
-    environment:
-      - HERMES_UID=10000
-      - HERMES_GID=10000
-    command: ["gateway", "run"]
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
-
-  # dashboard: disabled — crash-loops under s6 on Docker Desktop and not needed
-  # by friday-voice (gateway + `docker exec hermes` is all that's required).
-  # Re-enable + debug later if the localhost:9119 web UI is wanted.
-
-volumes:
-  hermes-data:
-    external: true
@@ -1,36 +0,0 @@
-services:
-  speaches:
-    image: ghcr.io/speaches-ai/speaches:latest-cuda
-    container_name: voicecoach-speaches-gpu
-    restart: unless-stopped
-    environment:
-      - WHISPER__INFERENCE_DEVICE=cuda
-      - WHISPER__COMPUTE_TYPE=float16
-      - WHISPER__TTL=-1
-    volumes:
-      - speaches-models:/home/ubuntu/.cache
-    ports:
-      - "8000:8000"
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: 1
-              capabilities: [gpu]
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    healthcheck:
-      test: ["CMD", "curl", "-sf", "http://localhost:8000/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 180s
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
-
-volumes:
-  speaches-models:
@@ -0,0 +1,26 @@
+services:
+  adguardhome:
+    image: adguard/adguardhome:latest
+    container_name: adguardhome
+    restart: unless-stopped
+    volumes:
+      - /mnt/docker-data/configs/adguardhome/work:/opt/adguardhome/work
+      - /mnt/docker-data/configs/adguardhome/conf:/opt/adguardhome/conf
+    ports:
+      - "53:53/tcp"
+      - "53:53/udp"
+      - "3000:3000/tcp"
+      - "853:853/tcp"
+    mem_limit: 256M
+    memswap_limit: 256M
+    healthcheck:
+      test: ["CMD-SHELL", "wget -q --spider http://localhost:3000/ || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
@@ -36,7 +36,6 @@ services:
      - HOME=/home/glyptic
      - USER=glyptic
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
-      - GEMINI_API_KEY=${GEMINI_API_KEY}
      - WIKIJS_API_KEY=${WIKIJS_API_KEY}
      - OPENCLAW_STATE_DIR=/home/glyptic/.spirit
      - OPENCLAW_CONFIG_PATH=/home/glyptic/.spirit/openclaw.json
@@ -44,8 +43,6 @@ services:
      - /mnt/infrastructure/spirit:/home/glyptic/.spirit
      - /var/run/docker.sock:/var/run/docker.sock
      - /mnt/infrastructure/spirit/ssh:/root/.ssh:ro
-      - /mnt/docker-data/configs/prometheus:/prometheus-config
-      - /mnt/docker-data/configs/alertmanager:/alertmanager-config
    command: ["sh", "-c", "mkdir -p /home/glyptic && node --max-old-space-size=1500 /usr/local/lib/node_modules/openclaw/dist/index.js gateway --allow-unconfigured"]
    mem_limit: 3G
    memswap_limit: 3G
@@ -55,3 +52,74 @@ services:
        max-size: "50m"
        max-file: "3"

+  bob:
+    image: margaret-openclaw:latest
+    container_name: bob
+    restart: unless-stopped
+    network_mode: host
+    user: "0:0"
+    environment:
+      - NODE_ENV=production
+      - HOME=/home/glyptic
+      - USER=glyptic
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
+      - OPENCLAW_STATE_DIR=/home/glyptic/.bob
+      - OPENCLAW_CONFIG_PATH=/home/glyptic/.bob/openclaw.json
+    volumes:
+      - /mnt/infrastructure/bob:/home/glyptic/.bob
+    command: ["sh", "-c", "mkdir -p /home/glyptic && node --max-old-space-size=1500 /usr/local/lib/node_modules/openclaw/dist/index.js gateway --allow-unconfigured"]
+    mem_limit: 2G
+    memswap_limit: 2G
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  clippy:
+    image: margaret-openclaw:latest
+    container_name: clippy
+    restart: unless-stopped
+    network_mode: host
+    user: "0:0"
+    environment:
+      - NODE_ENV=production
+      - HOME=/home/glyptic
+      - USER=glyptic
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
+      - OPENCLAW_STATE_DIR=/home/glyptic/.clippy
+      - OPENCLAW_CONFIG_PATH=/home/glyptic/.clippy/openclaw.json
+    volumes:
+      - /mnt/infrastructure/clippy:/home/glyptic/.clippy
+    command: ["sh", "-c", "mkdir -p /home/glyptic && node --max-old-space-size=1500 /usr/local/lib/node_modules/openclaw/dist/index.js gateway --allow-unconfigured"]
+    mem_limit: 2G
+    memswap_limit: 2G
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  travis:
+    image: travis-nemoclaw:latest
+    container_name: travis
+    restart: unless-stopped
+    network_mode: host
+    user: "0:0"
+    environment:
+      - NODE_ENV=production
+      - HOME=/home/glyptic
+      - USER=glyptic
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
+      - OPENCLAW_STATE_DIR=/home/glyptic/.travis
+      - OPENCLAW_CONFIG_PATH=/home/glyptic/.travis/openclaw.json
+    volumes:
+      - /mnt/infrastructure/travis:/home/glyptic/.travis
+    command: ["sh", "-c", "mkdir -p /home/glyptic && openclaw plugins install /opt/nemoclaw 2>/dev/null; node --max-old-space-size=1500 /usr/local/lib/node_modules/openclaw/dist/index.js gateway --allow-unconfigured"]
+    mem_limit: 2G
+    memswap_limit: 2G
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
@@ -1,8 +0,0 @@
-SPEACHES_URL=http://192.168.86.150:8000
-HERMES_COMMAND=hermes
-HERMES_SOURCE=friday-voice
-WHISPER_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
-TTS_MODEL=speaches-ai/Kokoro-82M-v1.0-ONNX
-TTS_VOICE=af_nova
-SPEAKER_CONFIRMED_THRESHOLD=0.85
-SPEAKER_PROBABLE_THRESHOLD=0.70
@@ -1,39 +0,0 @@
-services:
-  friday-voice:
-    build:
-      context: /opt/friday-voice
-      dockerfile: Dockerfile
-    image: friday-voice:latest
-    container_name: friday-voice
-    restart: unless-stopped
-    ports:
-      - "8320:8320"
-    volumes:
-      - /mnt/docker-data/configs/friday-voice:/data
-    environment:
-      - DATA_DIR=/data
-      - SPEACHES_URL=${SPEACHES_URL:-http://192.168.86.150:8000}
-      - HERMES_COMMAND=${HERMES_COMMAND:-hermes}
-      - HERMES_SOURCE=${HERMES_SOURCE:-friday-voice}
-      - WHISPER_MODEL=${WHISPER_MODEL:-deepdml/faster-whisper-large-v3-turbo-ct2}
-      - TTS_MODEL=${TTS_MODEL:-speaches-ai/Kokoro-82M-v1.0-ONNX}
-      - TTS_VOICE=${TTS_VOICE:-af_nova}
-      - SPEAKER_CONFIRMED_THRESHOLD=${SPEAKER_CONFIRMED_THRESHOLD:-0.85}
-      - SPEAKER_PROBABLE_THRESHOLD=${SPEAKER_PROBABLE_THRESHOLD:-0.70}
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    healthcheck:
-      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:8320/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 20s
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "20m"
-        max-file: "3"
-
-networks:
-  default:
-    name: friday-voice
@@ -9,8 +9,6 @@ RUN pip install --no-cache-dir -r requirements.txt

 COPY app/ .

-RUN mkdir -p /data
-
 EXPOSE 5199

 CMD ["python", "-u", "main.py"]
@@ -1,35 +0,0 @@
-"""Automatic event cleanup based on retention settings."""
-
-import asyncio
-import logging
-
-from database import get_connection
-
-logger = logging.getLogger(__name__)
-
-
-async def cleanup_old_events():
-    """Delete events older than the configured retention period. Runs hourly."""
-    while True:
-        try:
-            conn = get_connection()
-            row = conn.execute(
-                "SELECT value FROM settings WHERE key='event_retention_days'"
-            ).fetchone()
-            days = int(row["value"]) if row else 90
-
-            result = conn.execute(
-                "DELETE FROM events WHERE created_at < datetime('now', ? || ' days')",
-                (f"-{days}",),
-            )
-            conn.commit()
-            if result.rowcount > 0:
-                logger.info(
-                    "Cleaned up %d events older than %d days",
-                    result.rowcount,
-                    days,
-                )
-        except Exception:
-            logger.exception("Cleanup failed")
-
-        await asyncio.sleep(3600)
@@ -1,56 +0,0 @@
-"""Centralized configuration for frigate-notify v2."""
-
-import os
-
-
-class Config:
-    """Application configuration read from environment variables."""
-
-    # MQTT
-    MQTT_HOST: str = os.environ.get("MQTT_HOST", "192.168.86.192")
-    MQTT_PORT: int = int(os.environ.get("MQTT_PORT", "1883"))
-
-    # Frigate
-    FRIGATE_URL: str = os.environ.get("FRIGATE_URL", "http://192.168.86.192:5000")
-
-    # Matrix
-    MATRIX_HOMESERVER: str = os.environ.get(
-        "MATRIX_HOMESERVER", "http://192.168.86.192:8008"
-    )
-    MATRIX_ACCESS_TOKEN: str = os.environ.get("MATRIX_ACCESS_TOKEN", "")
-    MATRIX_ROOM_ID: str = os.environ.get("MATRIX_ROOM_ID", "")
-
-    # Vision - CLIP service
-    CLIP_SERVICE_URL: str = os.environ.get(
-        "CLIP_SERVICE_URL", "http://192.168.86.150:5200"
-    )
-
-    # Vision - Ollama
-    OLLAMA_URL: str = os.environ.get("OLLAMA_URL", "http://192.168.86.150:11434")
-    OLLAMA_MODEL: str = os.environ.get("OLLAMA_MODEL", "llava:13b")
-
-    # Recognition thresholds
-    RECOGNITION_THRESHOLD_HIGH: float = float(
-        os.environ.get("RECOGNITION_THRESHOLD_HIGH", "0.85")
-    )
-    RECOGNITION_THRESHOLD_LOW: float = float(
-        os.environ.get("RECOGNITION_THRESHOLD_LOW", "0.60")
-    )
-
-    # Filtering
-    ALLOWED_LABELS: set = set(
-        os.environ.get("ALLOWED_LABELS", "person,car,dog,cat,bird").split(",")
-    )
-    MIN_SCORE: float = float(os.environ.get("MIN_SCORE", "0.7"))
-    RATE_LIMIT_SECONDS: int = int(os.environ.get("RATE_LIMIT_SECONDS", "60"))
-    DEDUP_WINDOW_SECONDS: int = int(os.environ.get("DEDUP_WINDOW_SECONDS", "30"))
-
-    # Server
-    SERVER_HOST: str = os.environ.get("SERVER_HOST", "0.0.0.0")
-    SERVER_PORT: int = int(os.environ.get("SERVER_PORT", "5199"))
-
-    # Database
-    DB_PATH: str = os.environ.get("DB_PATH", "/data/frigate-notify.db")
-
-
-config = Config()
@@ -1,109 +0,0 @@
-"""SQLite database schema and connection management for frigate-notify v2."""
-
-import logging
-import sqlite3
-import threading
-
-logger = logging.getLogger(__name__)
-
-# Thread-local storage for database connections
-_local = threading.local()
-
-_db_path: str = "/data/frigate-notify.db"
-
-
-def set_db_path(path: str) -> None:
-    """Set the database path. Closes any existing connection first."""
-    global _db_path
-    close_connection()
-    _db_path = path
-
-
-def get_connection() -> sqlite3.Connection:
-    """Get a thread-local database connection with WAL mode and foreign keys enabled."""
-    if not hasattr(_local, "connection") or _local.connection is None:
-        conn = sqlite3.connect(_db_path)
-        conn.execute("PRAGMA journal_mode=WAL")
-        conn.execute("PRAGMA foreign_keys=ON")
-        conn.row_factory = sqlite3.Row
-        _local.connection = conn
-    return _local.connection
-
-
-def close_connection() -> None:
-    """Close the thread-local database connection if one exists."""
-    if hasattr(_local, "connection") and _local.connection is not None:
-        _local.connection.close()
-        _local.connection = None
-
-
-def init_db() -> None:
-    """Create all tables and default settings."""
-    conn = get_connection()
-    cursor = conn.cursor()
-
-    cursor.executescript(
-        """
-        CREATE TABLE IF NOT EXISTS known_objects (
-            id INTEGER PRIMARY KEY AUTOINCREMENT,
-            name TEXT NOT NULL,
-            type TEXT NOT NULL CHECK(type IN ('person', 'vehicle', 'pet')),
-            action TEXT NOT NULL DEFAULT 'quiet' CHECK(action IN ('quiet', 'suppress', 'alert')),
-            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-            updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
-        );
-
-        CREATE TABLE IF NOT EXISTS embeddings (
-            id INTEGER PRIMARY KEY AUTOINCREMENT,
-            known_object_id INTEGER NOT NULL,
-            embedding BLOB NOT NULL,
-            snapshot_url TEXT,
-            thumbnail BLOB,
-            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-            FOREIGN KEY (known_object_id) REFERENCES known_objects(id) ON DELETE CASCADE
-        );
-
-        CREATE TABLE IF NOT EXISTS events (
-            id INTEGER PRIMARY KEY AUTOINCREMENT,
-            frigate_event_id TEXT UNIQUE NOT NULL,
-            camera TEXT NOT NULL,
-            label TEXT NOT NULL,
-            score REAL NOT NULL,
-            snapshot BLOB,
-            embedding BLOB,
-            match_status TEXT NOT NULL DEFAULT 'unreviewed'
-                CHECK(match_status IN ('known', 'unknown', 'ambiguous', 'unreviewed')),
-            matched_object_id INTEGER,
-            match_confidence REAL,
-            ai_description TEXT,
-            notified INTEGER NOT NULL DEFAULT 0,
-            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-            FOREIGN KEY (matched_object_id) REFERENCES known_objects(id) ON DELETE SET NULL
-        );
-
-        CREATE TABLE IF NOT EXISTS settings (
-            key TEXT PRIMARY KEY,
-            value TEXT NOT NULL
-        );
-
-        CREATE INDEX IF NOT EXISTS idx_events_created_at ON events(created_at);
-        CREATE INDEX IF NOT EXISTS idx_events_match_status ON events(match_status);
-        CREATE INDEX IF NOT EXISTS idx_events_camera ON events(camera);
-        CREATE INDEX IF NOT EXISTS idx_embeddings_known_object_id ON embeddings(known_object_id);
-        """
-    )
-
-    # Insert default settings if they don't exist
-    defaults = {
-        "vision_backend": "haiku",
-        "recognition_enabled": "false",
-        "event_retention_days": "90",
-    }
-    for key, value in defaults.items():
-        cursor.execute(
-            "INSERT OR IGNORE INTO settings (key, value) VALUES (?, ?)",
-            (key, value),
-        )
-
-    conn.commit()
-    logger.info("Database initialized at %s", _db_path)
@@ -1,5 +1,3 @@
-"""frigate-notify v2 — FastAPI application with MQTT listener."""
-
 import asyncio
 import json
 import logging
@@ -8,28 +6,29 @@ import signal
 import sys
 import time
 from collections import defaultdict
-from contextlib import asynccontextmanager
-from pathlib import Path
+from http.server import HTTPServer, BaseHTTPRequestHandler
 from threading import Thread

 import aiohttp
 import anthropic
 import paho.mqtt.client as mqtt
-import uvicorn
-from fastapi import FastAPI
-from fastapi.responses import FileResponse, JSONResponse
-from fastapi.staticfiles import StaticFiles

-from config import config
-from database import close_connection, get_connection, init_db, set_db_path
+from vision import analyze_snapshot
 from matrix_client import MatrixClient
-from routes.events import router as events_router
-from routes.known_objects import router as known_objects_router
-from routes.settings import router as settings_router
-from ollama_client import OllamaClient
-from recognition import recognize_event, get_clip_embedding, embedding_to_bytes
-from vision import get_description
-from cleanup import cleanup_old_events
+
+# --- Configuration ---
+MQTT_HOST = os.environ.get("MQTT_HOST", "192.168.86.192")
+MQTT_PORT = int(os.environ.get("MQTT_PORT", "1883"))
+FRIGATE_URL = os.environ.get("FRIGATE_URL", "http://192.168.86.192:5000")
+MATRIX_HOMESERVER = os.environ.get("MATRIX_HOMESERVER", "http://192.168.86.192:8008")
+MATRIX_ACCESS_TOKEN = os.environ["MATRIX_ACCESS_TOKEN"]
+MATRIX_ROOM_ID = os.environ["MATRIX_ROOM_ID"]
+HEALTH_PORT = int(os.environ.get("HEALTH_PORT", "5199"))
+
+ALLOWED_LABELS = {"person", "car", "dog", "cat", "bird"}
+MIN_SCORE = 0.7
+RATE_LIMIT_SECONDS = 60
+DEDUP_WINDOW_SECONDS = 30

 # --- Logging ---
 logging.basicConfig(
@@ -45,12 +44,46 @@ last_notify_per_camera: defaultdict[str, float] = defaultdict(float)
 events_processed = 0
 last_event_time: str | None = None
 mqtt_connected = False
-mqtt_client_instance: mqtt.Client | None = None
+
+
+# --- Health endpoint ---
+class HealthHandler(BaseHTTPRequestHandler):
+    protocol_version = "HTTP/1.1"
+
+    def do_GET(self):
+        if self.path == "/health":
+            body = json.dumps(
+                {
+                    "status": "ok",
+                    "mqtt_connected": mqtt_connected,
+                    "events_processed": events_processed,
+                    "last_event": last_event_time,
+                }
+            )
+            encoded = body.encode()
+            self.send_response(200)
+            self.send_header("Content-Type", "application/json")
+            self.send_header("Content-Length", str(len(encoded)))
+            self.end_headers()
+            self.wfile.write(encoded)
+        else:
+            self.send_response(404)
+            self.end_headers()
+
+    def log_message(self, format, *args):
+        pass  # suppress access logs
+
+
+def start_health_server():
+    server = HTTPServer(("0.0.0.0", HEALTH_PORT), HealthHandler)
+    thread = Thread(target=server.serve_forever, daemon=True)
+    thread.start()
+    logger.info("Health server started on port %d", HEALTH_PORT)


 # --- Snapshot fetching ---
 async def fetch_snapshot(event_id: str) -> bytes | None:
-    url = f"{config.FRIGATE_URL}/api/events/{event_id}/snapshot.jpg"
+    url = f"{FRIGATE_URL}/api/events/{event_id}/snapshot.jpg"
    try:
        async with aiohttp.ClientSession() as session:
            async with session.get(url) as resp:
@@ -70,8 +103,7 @@ async def fetch_snapshot(event_id: str) -> bytes | None:

 # --- Event processing ---
 async def process_event(
-    event_data: dict, claude: anthropic.Anthropic, matrix: MatrixClient,
-    ollama_client: OllamaClient = None,
+    event_data: dict, claude: anthropic.Anthropic, matrix: MatrixClient
 ):
    global events_processed, last_event_time

@@ -87,30 +119,27 @@ async def process_event(
    has_snapshot = after.get("has_snapshot", False)

    # --- Filtering ---
-    if label not in config.ALLOWED_LABELS:
+    if label not in ALLOWED_LABELS:
        return
-    if score < config.MIN_SCORE:
+    if score < MIN_SCORE:
        return
    if not has_snapshot:
        return

    # Dedup
    now = time.time()
-    if (
-        event_id in recent_events
-        and now - recent_events[event_id] < config.DEDUP_WINDOW_SECONDS
-    ):
+    if event_id in recent_events and now - recent_events[event_id] < DEDUP_WINDOW_SECONDS:
        return
    recent_events[event_id] = now

    # Rate limit per camera
-    if now - last_notify_per_camera[camera] < config.RATE_LIMIT_SECONDS:
+    if now - last_notify_per_camera[camera] < RATE_LIMIT_SECONDS:
        logger.info("Rate limited: %s on %s", label, camera)
        return
    last_notify_per_camera[camera] = now

    # Cleanup old dedup entries
-    cutoff = now - config.DEDUP_WINDOW_SECONDS * 2
+    cutoff = now - DEDUP_WINDOW_SECONDS * 2
    for eid in [k for k, v in recent_events.items() if v < cutoff]:
        del recent_events[eid]

@@ -121,84 +150,18 @@ async def process_event(
    # --- Fetch snapshot ---
    snapshot = await fetch_snapshot(event_id)

-    # --- Recognition ---
-    match_status = "unreviewed"
-    matched_id = None
-    match_conf = 0.0
-    matched_name = None
-
-    # Check if recognition is enabled
-    recognition_enabled = False
-    try:
-        conn = get_connection()
-        row = conn.execute("SELECT value FROM settings WHERE key='recognition_enabled'").fetchone()
-        if row:
-            recognition_enabled = row["value"].lower() == "true"
-    except Exception:
-        pass
-
-    if recognition_enabled and snapshot:
-        match_status, matched_id, match_conf, matched_name = await recognize_event(
-            snapshot, ollama_client
-        )
-        # Store embedding with event
-        embedding = await get_clip_embedding(snapshot)
-        if embedding:
-            embedding_blob = embedding_to_bytes(embedding)
-            try:
-                conn = get_connection()
-                conn.execute(
-                    "UPDATE events SET embedding=?, match_status=?, matched_object_id=?, match_confidence=? WHERE frigate_event_id=?",
-                    (embedding_blob, match_status, matched_id, match_conf, event_id),
-                )
-                conn.commit()
-            except Exception:
-                logger.exception("Failed to update event recognition")
-
-        # If known, check action - skip notification for quiet/suppress
-        if match_status == "known" and matched_id:
-            conn = get_connection()
-            obj = conn.execute("SELECT action FROM known_objects WHERE id=?", (matched_id,)).fetchone()
-            if obj and obj["action"] in ("quiet", "suppress"):
-                logger.info("Known object '%s' (%s), skipping notification", matched_name, obj["action"])
-                events_processed += 1
-                last_event_time = time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
-                return
-
-    # --- AI description ---
-    vision_backend = "haiku"
-    try:
-        conn = get_connection()
-        row = conn.execute("SELECT value FROM settings WHERE key='vision_backend'").fetchone()
-        if row:
-            vision_backend = row["value"]
-    except Exception:
-        pass
-
+    # --- AI analysis ---
    description = None
    if snapshot:
-        description = await get_description(snapshot, vision_backend, claude, ollama_client)
+        description = analyze_snapshot(claude, snapshot)
    if not description:
        description = f"{label.capitalize()} detected on {camera}."

-    # --- Store event in database ---
-    try:
-        conn = get_connection()
-        conn.execute(
-            """INSERT OR IGNORE INTO events
-               (frigate_event_id, camera, label, score, snapshot, match_status, ai_description, notified)
-               VALUES (?, ?, ?, ?, ?, ?, ?, 1)""",
-            (event_id, camera, label, score, snapshot, match_status, description),
-        )
-        conn.commit()
-    except Exception:
-        logger.exception("Failed to store event %s in database", event_id)
-
    # --- Format message ---
    score_pct = int(score * 100)
    ts = time.strftime("%I:%M:%S %p", time.localtime())
    date_str = time.strftime("%b %d, %Y", time.localtime())
-    frigate_link = f"{config.FRIGATE_URL}/review?id={event_id}"
+    frigate_link = f"{FRIGATE_URL}/review?id={event_id}"

    plain = (
        f"{camera} - {label.capitalize()} - {score_pct}%\n"
@@ -232,8 +195,7 @@ def create_mqtt_client(
    loop: asyncio.AbstractEventLoop,
    claude: anthropic.Anthropic,
    matrix: MatrixClient,
-    ollama_client: OllamaClient = None,
-) -> mqtt.Client:
+):
    global mqtt_connected

    def on_connect(client, userdata, flags, reason_code, properties):
@@ -251,7 +213,7 @@ def create_mqtt_client(
        try:
            payload = json.loads(msg.payload)
            asyncio.run_coroutine_threadsafe(
-                process_event(payload, claude, matrix, ollama_client), loop
+                process_event(payload, claude, matrix), loop
            )
        except json.JSONDecodeError:
            logger.warning("Invalid JSON on %s", msg.topic)
@@ -265,99 +227,33 @@ def create_mqtt_client(
    return client


-def start_mqtt(loop: asyncio.AbstractEventLoop) -> None:
-    """Start MQTT client in a background thread."""
-    global mqtt_client_instance
+# --- Main ---
+def main():
+    logger.info("Starting frigate-notify")

    claude = anthropic.Anthropic()
-    matrix = MatrixClient(
-        config.MATRIX_HOMESERVER,
-        config.MATRIX_ACCESS_TOKEN,
-        config.MATRIX_ROOM_ID,
-    )
-    ollama_client = OllamaClient(config.OLLAMA_URL, config.OLLAMA_MODEL)
+    matrix = MatrixClient(MATRIX_HOMESERVER, MATRIX_ACCESS_TOKEN, MATRIX_ROOM_ID)

-    mqtt_client_instance = create_mqtt_client(loop, claude, matrix, ollama_client)
-    mqtt_client_instance.connect(config.MQTT_HOST, config.MQTT_PORT)
+    loop = asyncio.new_event_loop()
+    loop_thread = Thread(target=loop.run_forever, daemon=True)
+    loop_thread.start()

-    thread = Thread(target=mqtt_client_instance.loop_forever, daemon=True)
-    thread.start()
-    logger.info("MQTT client started in background thread")
+    start_health_server()
+
+    mqtt_client = create_mqtt_client(loop, claude, matrix)
+    mqtt_client.connect(MQTT_HOST, MQTT_PORT)
+
+    def shutdown(signum, frame):
+        logger.info("Shutting down...")
+        mqtt_client.disconnect()
+        loop.call_soon_threadsafe(loop.stop)
+        sys.exit(0)
+
+    signal.signal(signal.SIGTERM, shutdown)
+    signal.signal(signal.SIGINT, shutdown)
+
+    mqtt_client.loop_forever()


-# --- FastAPI lifespan ---
-@asynccontextmanager
-async def lifespan(app: FastAPI):
-    """Startup and shutdown logic for the FastAPI application."""
-    logger.info("Starting frigate-notify v2")
-
-    # Initialize database
-    set_db_path(config.DB_PATH)
-    init_db()
-
-    # Start MQTT listener in background
-    loop = asyncio.get_event_loop()
-    start_mqtt(loop)
-
-    # Start periodic event cleanup
-    asyncio.create_task(cleanup_old_events())
-
-    yield
-
-    # Shutdown
-    logger.info("Shutting down frigate-notify v2")
-    if mqtt_client_instance:
-        mqtt_client_instance.disconnect()
-    close_connection()
-
-
-# --- FastAPI app ---
-app = FastAPI(
-    title="frigate-notify",
-    version="2.0.0",
-    lifespan=lifespan,
-)
-
-# Include API routers
-app.include_router(events_router)
-app.include_router(known_objects_router)
-app.include_router(settings_router)
-
-# Mount static files directory
-static_dir = Path(__file__).parent / "static"
-static_dir.mkdir(exist_ok=True)
-app.mount("/static", StaticFiles(directory=str(static_dir)), name="static")
-
-
-@app.get("/health")
-async def health():
-    """Health check endpoint."""
-    return {
-        "status": "ok",
-        "version": "2.0.0",
-        "mqtt_connected": mqtt_connected,
-        "events_processed": events_processed,
-        "last_event": last_event_time,
-    }
-
-
-@app.get("/")
-async def index():
-    """Serve the web UI index page."""
-    index_path = static_dir / "index.html"
-    if index_path.exists():
-        return FileResponse(str(index_path))
-    return JSONResponse(
-        {"message": "frigate-notify v2", "docs": "/docs"},
-        status_code=200,
-    )
-
-
-# --- Entrypoint ---
 if __name__ == "__main__":
-    uvicorn.run(
-        "main:app",
-        host=config.SERVER_HOST,
-        port=config.SERVER_PORT,
-        log_level="info",
-    )
+    main()
@@ -1,95 +0,0 @@
-"""Pydantic models for frigate-notify v2 API."""
-
-from datetime import datetime
-from typing import Optional
-
-from pydantic import BaseModel, Field
-
-
-# --- Known Objects ---
-
-
-class KnownObjectCreate(BaseModel):
-    """Request model for creating a known object."""
-
-    name: str = Field(..., min_length=1, max_length=255)
-    type: str = Field(..., pattern="^(person|vehicle|pet)$")
-    action: str = Field(default="quiet", pattern="^(quiet|suppress|alert)$")
-
-
-class KnownObjectUpdate(BaseModel):
-    """Request model for updating a known object."""
-
-    name: Optional[str] = Field(default=None, min_length=1, max_length=255)
-    type: Optional[str] = Field(default=None, pattern="^(person|vehicle|pet)$")
-    action: Optional[str] = Field(default=None, pattern="^(quiet|suppress|alert)$")
-
-
-class KnownObjectResponse(BaseModel):
-    """Response model for a known object."""
-
-    id: int
-    name: str
-    type: str
-    action: str
-    created_at: str
-    updated_at: str
-
-
-# --- Events ---
-
-
-class TagEventRequest(BaseModel):
-    """Request model for tagging an event with a known object.
-
-    Either provide known_object_id to link to an existing object,
-    or provide name + type to create a new known object.
-    """
-
-    known_object_id: Optional[int] = None
-    name: Optional[str] = Field(default=None, min_length=1, max_length=255)
-    type: Optional[str] = Field(default=None, pattern="^(person|vehicle|pet)$")
-
-
-class EventResponse(BaseModel):
-    """Response model for an event."""
-
-    id: int
-    frigate_event_id: str
-    camera: str
-    label: str
-    score: float
-    has_snapshot: bool = False
-    snapshot_base64: Optional[str] = None
-    match_status: str
-    matched_object_id: Optional[int] = None
-    matched_object_name: Optional[str] = None
-    match_confidence: Optional[float] = None
-    ai_description: Optional[str] = None
-    notified: bool
-    created_at: str
-
-
-# --- Settings ---
-
-
-class SettingsResponse(BaseModel):
-    """Response model for application settings."""
-
-    vision_backend: str
-    recognition_enabled: bool
-    event_retention_days: int
-
-
-# --- Stats ---
-
-
-class StatsResponse(BaseModel):
-    """Response model for application statistics."""
-
-    total_events: int = 0
-    known_matches: int = 0
-    unknown_events: int = 0
-    unreviewed: int = 0
-    known_objects_count: int = 0
-    events_today: int = 0
@@ -1,132 +0,0 @@
-"""Ollama vision LLM client for frigate-notify v2."""
-
-import base64
-import logging
-
-import aiohttp
-
-logger = logging.getLogger(__name__)
-
-
-class OllamaClient:
-    """Client for Ollama vision models (e.g., llava)."""
-
-    def __init__(self, base_url: str, model: str):
-        self.base_url = base_url.rstrip("/")
-        self.model = model
-
-    async def analyze_image(self, image_bytes: bytes, prompt: str) -> str | None:
-        """Send an image to Ollama for analysis.
-
-        Args:
-            image_bytes: Raw image bytes (JPEG).
-            prompt: Text prompt for the vision model.
-
-        Returns:
-            Response text or None on failure.
-        """
-        b64 = base64.b64encode(image_bytes).decode("utf-8")
-        payload = {
-            "model": self.model,
-            "prompt": prompt,
-            "images": [b64],
-            "stream": False,
-            "options": {"num_predict": 200},
-        }
-        try:
-            async with aiohttp.ClientSession() as session:
-                async with session.post(
-                    f"{self.base_url}/api/generate",
-                    json=payload,
-                    timeout=aiohttp.ClientTimeout(total=30),
-                ) as resp:
-                    if resp.status == 200:
-                        data = await resp.json()
-                        text = data.get("response", "").strip()
-                        logger.info(
-                            "Ollama analysis complete: %d chars", len(text)
-                        )
-                        return text if text else None
-                    body = await resp.text()
-                    logger.error(
-                        "Ollama analyze_image failed %s: %s", resp.status, body
-                    )
-        except Exception:
-            logger.exception("Ollama analyze_image request failed")
-        return None
-
-    async def compare_images(
-        self,
-        image_bytes: bytes,
-        reference_bytes: bytes,
-        object_name: str,
-    ) -> bool | None:
-        """Compare two images to determine if they show the same object/person.
-
-        Args:
-            image_bytes: The new event image bytes.
-            reference_bytes: The reference (known) image bytes.
-            object_name: Name of the known object for context.
-
-        Returns:
-            True if same, False if different, None on failure/inconclusive.
-        """
-        b64_new = base64.b64encode(image_bytes).decode("utf-8")
-        b64_ref = base64.b64encode(reference_bytes).decode("utf-8")
-        prompt = (
-            f"Look at these two images. The first image is from a security camera. "
-            f"The second image is a reference photo of '{object_name}'. "
-            f"Are these the same person/vehicle/animal? "
-            f"Answer with ONLY 'yes' or 'no'."
-        )
-        payload = {
-            "model": self.model,
-            "prompt": prompt,
-            "images": [b64_new, b64_ref],
-            "stream": False,
-            "options": {"num_predict": 200},
-        }
-        try:
-            async with aiohttp.ClientSession() as session:
-                async with session.post(
-                    f"{self.base_url}/api/generate",
-                    json=payload,
-                    timeout=aiohttp.ClientTimeout(total=30),
-                ) as resp:
-                    if resp.status == 200:
-                        data = await resp.json()
-                        text = data.get("response", "").strip().lower()
-                        logger.info("Ollama compare result: %s", text)
-                        if "yes" in text.split()[:3]:
-                            return True
-                        if "no" in text.split()[:3]:
-                            return False
-                        logger.warning(
-                            "Ollama compare inconclusive: %s", text
-                        )
-                        return None
-                    body = await resp.text()
-                    logger.error(
-                        "Ollama compare_images failed %s: %s",
-                        resp.status,
-                        body,
-                    )
-        except Exception:
-            logger.exception("Ollama compare_images request failed")
-        return None
-
-    async def is_available(self) -> bool:
-        """Check if Ollama is reachable and responding.
-
-        Returns:
-            True if Ollama responds with HTTP 200, False otherwise.
-        """
-        try:
-            async with aiohttp.ClientSession() as session:
-                async with session.get(
-                    f"{self.base_url}/api/tags",
-                    timeout=aiohttp.ClientTimeout(total=3),
-                ) as resp:
-                    return resp.status == 200
-        except Exception:
-            return False
@@ -1,232 +0,0 @@
-"""Recognition pipeline using CLIP embeddings with Ollama vision fallback."""
-
-import base64
-import logging
-import struct
-from typing import Optional
-
-import aiohttp
-import numpy as np
-
-from config import config
-from database import get_connection
-from ollama_client import OllamaClient
-
-logger = logging.getLogger(__name__)
-
-
-def embedding_to_bytes(embedding: list[float]) -> bytes:
-    """Pack a float32 embedding list into bytes for SQLite storage.
-
-    Args:
-        embedding: List of float values (typically 768-dimensional).
-
-    Returns:
-        Packed bytes (len(embedding) * 4 bytes).
-    """
-    return struct.pack(f"{len(embedding)}f", *embedding)
-
-
-def bytes_to_embedding(data: bytes) -> np.ndarray:
-    """Unpack bytes back into a float32 numpy array.
-
-    Args:
-        data: Packed bytes from embedding_to_bytes().
-
-    Returns:
-        Numpy array of float32 values.
-    """
-    count = len(data) // 4
-    values = struct.unpack(f"{count}f", data)
-    return np.array(values, dtype=np.float32)
-
-
-async def get_clip_embedding(image_bytes: bytes) -> list[float] | None:
-    """Get CLIP embedding for an image from the clip-service sidecar.
-
-    Args:
-        image_bytes: Raw image bytes (JPEG).
-
-    Returns:
-        List of float embedding values, or None on failure.
-    """
-    b64 = base64.b64encode(image_bytes).decode("utf-8")
-    try:
-        async with aiohttp.ClientSession() as session:
-            async with session.post(
-                f"{config.CLIP_SERVICE_URL}/embed",
-                json={"image": b64},
-                timeout=aiohttp.ClientTimeout(total=10),
-            ) as resp:
-                if resp.status == 200:
-                    data = await resp.json()
-                    embedding = data.get("embedding")
-                    if embedding:
-                        logger.info(
-                            "CLIP embedding received: %d dimensions",
-                            len(embedding),
-                        )
-                        return embedding
-                    logger.warning("CLIP response missing embedding field")
-                else:
-                    body = await resp.text()
-                    logger.error(
-                        "CLIP embed failed %s: %s", resp.status, body
-                    )
-    except Exception:
-        logger.exception("CLIP embedding request failed")
-    return None
-
-
-async def find_best_match(
-    query_embedding: list[float],
-) -> tuple[int | None, float, str | None]:
-    """Find the best matching known object for a query embedding.
-
-    Loads all embeddings from the database, computes cosine similarity,
-    groups by known_object_id and takes the max score per object.
-
-    Args:
-        query_embedding: The query embedding to match against.
-
-    Returns:
-        Tuple of (best_object_id, best_score, best_name).
-        Returns (None, 0.0, None) if no embeddings exist.
-    """
-    conn = get_connection()
-    cursor = conn.execute(
-        """
-        SELECT e.id, e.known_object_id, e.embedding, ko.name
-        FROM embeddings e
-        JOIN known_objects ko ON e.known_object_id = ko.id
-        """
-    )
-    rows = cursor.fetchall()
-
-    if not rows:
-        return (None, 0.0, None)
-
-    query_vec = np.array(query_embedding, dtype=np.float32)
-    query_norm = np.linalg.norm(query_vec)
-    if query_norm == 0:
-        return (None, 0.0, None)
-    query_vec = query_vec / query_norm
-
-    # Group scores by known_object_id, keeping max per object
-    best_per_object: dict[int, tuple[float, str]] = {}
-
-    for row in rows:
-        stored_vec = bytes_to_embedding(row["embedding"])
-        stored_norm = np.linalg.norm(stored_vec)
-        if stored_norm == 0:
-            continue
-        stored_vec = stored_vec / stored_norm
-
-        similarity = float(np.dot(query_vec, stored_vec))
-        obj_id = row["known_object_id"]
-        obj_name = row["name"]
-
-        if obj_id not in best_per_object or similarity > best_per_object[obj_id][0]:
-            best_per_object[obj_id] = (similarity, obj_name)
-
-    if not best_per_object:
-        return (None, 0.0, None)
-
-    best_id = max(best_per_object, key=lambda k: best_per_object[k][0])
-    best_score, best_name = best_per_object[best_id]
-
-    return (best_id, best_score, best_name)
-
-
-async def recognize_event(
-    image_bytes: bytes,
-    ollama_client: Optional[OllamaClient] = None,
-) -> tuple[str, int | None, float, str | None]:
-    """Full recognition pipeline for a Frigate event image.
-
-    Steps:
-        1. Get CLIP embedding for the image.
-        2. Find the best matching known object.
-        3. High confidence (>= threshold_high): return "known".
-        4. Low confidence (< threshold_low): return "unknown".
-        5. Ambiguous range: use Ollama vision LLM to confirm/deny.
-        6. If LLM unavailable or inconclusive: return "ambiguous".
-        7. If no embedding could be obtained: return "unreviewed".
-
-    Args:
-        image_bytes: Raw image bytes (JPEG).
-        ollama_client: Optional OllamaClient for ambiguous case fallback.
-
-    Returns:
-        Tuple of (match_status, object_id, score, object_name).
-        match_status is one of: "known", "unknown", "ambiguous", "unreviewed".
-    """
-    # Step 1: Get CLIP embedding
-    embedding = await get_clip_embedding(image_bytes)
-    if embedding is None:
-        logger.warning("Could not get CLIP embedding, returning unreviewed")
-        return ("unreviewed", None, 0.0, None)
-
-    # Step 2: Find best match
-    best_id, best_score, best_name = await find_best_match(embedding)
-
-    # No embeddings in DB at all
-    if best_id is None:
-        return ("unknown", None, 0.0, None)
-
-    high_threshold = config.RECOGNITION_THRESHOLD_HIGH
-    low_threshold = config.RECOGNITION_THRESHOLD_LOW
-
-    # Step 3: High confidence match
-    if best_score >= high_threshold:
-        logger.info(
-            "High confidence match: %s (%.3f)", best_name, best_score
-        )
-        return ("known", best_id, best_score, best_name)
-
-    # Step 4: Low confidence - clearly not a match
-    if best_score < low_threshold:
-        logger.info("Low confidence, no match (%.3f)", best_score)
-        return ("unknown", None, best_score, None)
-
-    # Step 5: Ambiguous range - try Ollama vision LLM
-    if ollama_client is not None:
-        logger.info(
-            "Ambiguous score %.3f for %s, trying Ollama comparison",
-            best_score,
-            best_name,
-        )
-        # Get a reference thumbnail from the embeddings table
-        conn = get_connection()
-        cursor = conn.execute(
-            """
-            SELECT thumbnail FROM embeddings
-            WHERE known_object_id = ? AND thumbnail IS NOT NULL
-            LIMIT 1
-            """,
-            (best_id,),
-        )
-        ref_row = cursor.fetchone()
-        if ref_row and ref_row["thumbnail"] is not None:
-            result = await ollama_client.compare_images(
-                image_bytes, ref_row["thumbnail"], best_name
-            )
-            if result is True:
-                logger.info(
-                    "Ollama confirmed match: %s (%.3f)",
-                    best_name,
-                    best_score,
-                )
-                return ("known", best_id, best_score, best_name)
-            elif result is False:
-                logger.info(
-                    "Ollama denied match: %s (%.3f)", best_name, best_score
-                )
-                return ("unknown", None, best_score, None)
-            # result is None: inconclusive, fall through to ambiguous
-
-    # Step 6: LLM unavailable or inconclusive
-    logger.info(
-        "Ambiguous match: %s (%.3f)", best_name, best_score
-    )
-    return ("ambiguous", best_id, best_score, best_name)
@@ -1,7 +1,3 @@
 paho-mqtt==2.1.0
 anthropic>=0.40.0
 aiohttp>=3.9.0
-fastapi>=0.115.0
-uvicorn[standard]>=0.34.0
-python-multipart>=0.0.18
-numpy>=1.26.0
@@ -1,226 +0,0 @@
-"""Event API endpoints for frigate-notify v2."""
-
-import base64
-import logging
-from typing import Optional
-
-from fastapi import APIRouter, HTTPException, Query
-from fastapi.responses import Response
-
-from database import get_connection
-from models import EventResponse, TagEventRequest
-
-logger = logging.getLogger(__name__)
-
-router = APIRouter(prefix="/api/events", tags=["events"])
-
-
-@router.get("", response_model=list[EventResponse])
-async def list_events(
-    camera: Optional[str] = Query(default=None),
-    label: Optional[str] = Query(default=None),
-    status: Optional[str] = Query(default=None),
-    limit: int = Query(default=50, ge=1, le=500),
-    offset: int = Query(default=0, ge=0),
-):
-    """List events with optional filters and pagination.
-
-    Returns events without snapshot/embedding BLOBs but with has_snapshot bool.
-    Joins to known_objects for matched_object_name.
-    """
-    conn = get_connection()
-
-    query = """
-        SELECT
-            e.id, e.frigate_event_id, e.camera, e.label, e.score,
-            CASE WHEN e.snapshot IS NOT NULL THEN 1 ELSE 0 END AS has_snapshot,
-            e.match_status, e.matched_object_id,
-            ko.name AS matched_object_name,
-            e.match_confidence, e.ai_description, e.notified, e.created_at
-        FROM events e
-        LEFT JOIN known_objects ko ON e.matched_object_id = ko.id
-    """
-    conditions = []
-    params: list = []
-
-    if camera:
-        conditions.append("e.camera = ?")
-        params.append(camera)
-    if label:
-        conditions.append("e.label = ?")
-        params.append(label)
-    if status:
-        conditions.append("e.match_status = ?")
-        params.append(status)
-
-    if conditions:
-        query += " WHERE " + " AND ".join(conditions)
-
-    query += " ORDER BY e.created_at DESC LIMIT ? OFFSET ?"
-    params.extend([limit, offset])
-
-    cursor = conn.execute(query, params)
-    rows = cursor.fetchall()
-
-    return [
-        EventResponse(
-            id=row["id"],
-            frigate_event_id=row["frigate_event_id"],
-            camera=row["camera"],
-            label=row["label"],
-            score=row["score"],
-            has_snapshot=bool(row["has_snapshot"]),
-            match_status=row["match_status"],
-            matched_object_id=row["matched_object_id"],
-            matched_object_name=row["matched_object_name"],
-            match_confidence=row["match_confidence"],
-            ai_description=row["ai_description"],
-            notified=bool(row["notified"]),
-            created_at=row["created_at"],
-        )
-        for row in rows
-    ]
-
-
-@router.get("/{event_id}", response_model=EventResponse)
-async def get_event(event_id: int):
-    """Get a single event detail. Includes base64-encoded snapshot if exists."""
-    conn = get_connection()
-    cursor = conn.execute(
-        """
-        SELECT
-            e.id, e.frigate_event_id, e.camera, e.label, e.score,
-            e.snapshot,
-            CASE WHEN e.snapshot IS NOT NULL THEN 1 ELSE 0 END AS has_snapshot,
-            e.match_status, e.matched_object_id,
-            ko.name AS matched_object_name,
-            e.match_confidence, e.ai_description, e.notified, e.created_at
-        FROM events e
-        LEFT JOIN known_objects ko ON e.matched_object_id = ko.id
-        WHERE e.id = ?
-        """,
-        (event_id,),
-    )
-    row = cursor.fetchone()
-    if not row:
-        raise HTTPException(status_code=404, detail="Event not found")
-
-    snapshot_b64 = None
-    if row["snapshot"] is not None:
-        snapshot_b64 = base64.b64encode(row["snapshot"]).decode("ascii")
-
-    return EventResponse(
-        id=row["id"],
-        frigate_event_id=row["frigate_event_id"],
-        camera=row["camera"],
-        label=row["label"],
-        score=row["score"],
-        has_snapshot=bool(row["has_snapshot"]),
-        snapshot_base64=snapshot_b64,
-        match_status=row["match_status"],
-        matched_object_id=row["matched_object_id"],
-        matched_object_name=row["matched_object_name"],
-        match_confidence=row["match_confidence"],
-        ai_description=row["ai_description"],
-        notified=bool(row["notified"]),
-        created_at=row["created_at"],
-    )
-
-
-@router.get("/{event_id}/snapshot")
-async def get_event_snapshot(event_id: int):
-    """Return raw JPEG snapshot for an event. 404 if no snapshot."""
-    conn = get_connection()
-    cursor = conn.execute(
-        "SELECT snapshot FROM events WHERE id = ?",
-        (event_id,),
-    )
-    row = cursor.fetchone()
-    if not row:
-        raise HTTPException(status_code=404, detail="Event not found")
-    if row["snapshot"] is None:
-        raise HTTPException(status_code=404, detail="No snapshot available")
-
-    return Response(content=row["snapshot"], media_type="image/jpeg")
-
-
-@router.post("/{event_id}/tag")
-async def tag_event(event_id: int, body: TagEventRequest):
-    """Tag an event as a known object.
-
-    Either provide known_object_id to link to an existing object,
-    or provide name + type to create a new known object.
-    If the event has an embedding, store it in the embeddings table.
-    """
-    conn = get_connection()
-
-    # Verify event exists
-    cursor = conn.execute(
-        "SELECT id, embedding FROM events WHERE id = ?",
-        (event_id,),
-    )
-    event_row = cursor.fetchone()
-    if not event_row:
-        raise HTTPException(status_code=404, detail="Event not found")
-
-    known_object_id = body.known_object_id
-
-    if known_object_id is not None:
-        # Verify the known object exists
-        cursor = conn.execute(
-            "SELECT id FROM known_objects WHERE id = ?",
-            (known_object_id,),
-        )
-        if not cursor.fetchone():
-            raise HTTPException(status_code=404, detail="Known object not found")
-    elif body.name and body.type:
-        # Create a new known object
-        cursor = conn.execute(
-            "INSERT INTO known_objects (name, type) VALUES (?, ?)",
-            (body.name, body.type),
-        )
-        known_object_id = cursor.lastrowid
-        conn.commit()
-    else:
-        raise HTTPException(
-            status_code=400,
-            detail="Must provide either known_object_id or both name and type",
-        )
-
-    # If event has an embedding, store it in the embeddings table
-    if event_row["embedding"] is not None:
-        conn.execute(
-            "INSERT INTO embeddings (known_object_id, embedding) VALUES (?, ?)",
-            (known_object_id, event_row["embedding"]),
-        )
-
-    # Update event
-    conn.execute(
-        """UPDATE events
-           SET match_status = 'known',
-               matched_object_id = ?,
-               match_confidence = 1.0
-           WHERE id = ?""",
-        (known_object_id, event_id),
-    )
-    conn.commit()
-
-    return {"status": "ok", "matched_object_id": known_object_id}
-
-
-@router.post("/{event_id}/dismiss")
-async def dismiss_event(event_id: int):
-    """Set event match_status to 'unknown'."""
-    conn = get_connection()
-
-    cursor = conn.execute("SELECT id FROM events WHERE id = ?", (event_id,))
-    if not cursor.fetchone():
-        raise HTTPException(status_code=404, detail="Event not found")
-
-    conn.execute(
-        "UPDATE events SET match_status = 'unknown' WHERE id = ?",
-        (event_id,),
-    )
-    conn.commit()
-
-    return {"status": "ok"}
@@ -1,177 +0,0 @@
-"""Known objects API endpoints for frigate-notify v2."""
-
-import logging
-from typing import Optional
-
-from fastapi import APIRouter, HTTPException, Query
-from fastapi.responses import Response
-
-from database import get_connection
-from models import KnownObjectResponse, KnownObjectUpdate
-
-logger = logging.getLogger(__name__)
-
-router = APIRouter(prefix="/api/known-objects", tags=["known-objects"])
-
-
-@router.get("")
-async def list_known_objects(
-    type: Optional[str] = Query(default=None, pattern="^(person|vehicle|pet)$"),
-):
-    """List all known objects with embedding_count. Optional type filter."""
-    conn = get_connection()
-
-    query = """
-        SELECT
-            ko.id, ko.name, ko.type, ko.action,
-            ko.created_at, ko.updated_at,
-            COUNT(e.id) AS embedding_count
-        FROM known_objects ko
-        LEFT JOIN embeddings e ON ko.id = e.known_object_id
-    """
-    params: list = []
-
-    if type:
-        query += " WHERE ko.type = ?"
-        params.append(type)
-
-    query += " GROUP BY ko.id ORDER BY ko.name"
-
-    cursor = conn.execute(query, params)
-    rows = cursor.fetchall()
-
-    return [
-        {
-            "id": row["id"],
-            "name": row["name"],
-            "type": row["type"],
-            "action": row["action"],
-            "created_at": row["created_at"],
-            "updated_at": row["updated_at"],
-            "embedding_count": row["embedding_count"],
-        }
-        for row in rows
-    ]
-
-
-@router.get("/{object_id}")
-async def get_known_object(object_id: int):
-    """Get a single known object with list of its embeddings (id, created_at only)."""
-    conn = get_connection()
-
-    cursor = conn.execute(
-        "SELECT id, name, type, action, created_at, updated_at FROM known_objects WHERE id = ?",
-        (object_id,),
-    )
-    row = cursor.fetchone()
-    if not row:
-        raise HTTPException(status_code=404, detail="Known object not found")
-
-    # Get embeddings list
-    emb_cursor = conn.execute(
-        "SELECT id, created_at FROM embeddings WHERE known_object_id = ? ORDER BY created_at",
-        (object_id,),
-    )
-    embeddings = [
-        {"id": e["id"], "created_at": e["created_at"]} for e in emb_cursor.fetchall()
-    ]
-
-    return {
-        "id": row["id"],
-        "name": row["name"],
-        "type": row["type"],
-        "action": row["action"],
-        "created_at": row["created_at"],
-        "updated_at": row["updated_at"],
-        "embeddings": embeddings,
-    }
-
-
-@router.get("/{object_id}/thumbnails/{embedding_id}")
-async def get_embedding_thumbnail(object_id: int, embedding_id: int):
-    """Return raw JPEG thumbnail from embeddings table."""
-    conn = get_connection()
-
-    cursor = conn.execute(
-        "SELECT thumbnail FROM embeddings WHERE id = ? AND known_object_id = ?",
-        (embedding_id, object_id),
-    )
-    row = cursor.fetchone()
-    if not row:
-        raise HTTPException(status_code=404, detail="Embedding not found")
-    if row["thumbnail"] is None:
-        raise HTTPException(status_code=404, detail="No thumbnail available")
-
-    return Response(content=row["thumbnail"], media_type="image/jpeg")
-
-
-@router.put("/{object_id}")
-async def update_known_object(object_id: int, body: KnownObjectUpdate):
-    """Update name/type/action for a known object. Sets updated_at."""
-    conn = get_connection()
-
-    cursor = conn.execute(
-        "SELECT id FROM known_objects WHERE id = ?",
-        (object_id,),
-    )
-    if not cursor.fetchone():
-        raise HTTPException(status_code=404, detail="Known object not found")
-
-    updates = []
-    params: list = []
-
-    if body.name is not None:
-        updates.append("name = ?")
-        params.append(body.name)
-    if body.type is not None:
-        updates.append("type = ?")
-        params.append(body.type)
-    if body.action is not None:
-        updates.append("action = ?")
-        params.append(body.action)
-
-    if not updates:
-        raise HTTPException(status_code=400, detail="No fields to update")
-
-    updates.append("updated_at = CURRENT_TIMESTAMP")
-    params.append(object_id)
-
-    conn.execute(
-        f"UPDATE known_objects SET {', '.join(updates)} WHERE id = ?",
-        params,
-    )
-    conn.commit()
-
-    # Return the updated object
-    cursor = conn.execute(
-        "SELECT id, name, type, action, created_at, updated_at FROM known_objects WHERE id = ?",
-        (object_id,),
-    )
-    row = cursor.fetchone()
-
-    return KnownObjectResponse(
-        id=row["id"],
-        name=row["name"],
-        type=row["type"],
-        action=row["action"],
-        created_at=row["created_at"],
-        updated_at=row["updated_at"],
-    )
-
-
-@router.delete("/{object_id}")
-async def delete_known_object(object_id: int):
-    """Delete a known object. Embeddings cascade delete automatically."""
-    conn = get_connection()
-
-    cursor = conn.execute(
-        "SELECT id FROM known_objects WHERE id = ?",
-        (object_id,),
-    )
-    if not cursor.fetchone():
-        raise HTTPException(status_code=404, detail="Known object not found")
-
-    conn.execute("DELETE FROM known_objects WHERE id = ?", (object_id,))
-    conn.commit()
-
-    return {"status": "ok"}
@@ -1,78 +0,0 @@
-"""Settings and stats API endpoints for frigate-notify v2."""
-
-import logging
-from datetime import date
-
-from fastapi import APIRouter
-
-from config import config
-from database import get_connection
-from models import StatsResponse
-
-logger = logging.getLogger(__name__)
-
-router = APIRouter(prefix="/api", tags=["settings"])
-
-
-@router.get("/settings")
-async def get_settings():
-    """Return all settings from DB plus runtime config values."""
-    conn = get_connection()
-    cursor = conn.execute("SELECT key, value FROM settings")
-    db_settings = {row["key"]: row["value"] for row in cursor.fetchall()}
-
-    # Merge with runtime config values
-    return {
-        **db_settings,
-        "recognition_threshold_high": config.RECOGNITION_THRESHOLD_HIGH,
-        "recognition_threshold_low": config.RECOGNITION_THRESHOLD_LOW,
-        "rate_limit_seconds": config.RATE_LIMIT_SECONDS,
-        "allowed_labels": list(config.ALLOWED_LABELS),
-        "min_score": config.MIN_SCORE,
-    }
-
-
-@router.put("/settings")
-async def update_settings(body: dict):
-    """Accept dict body, upsert each key/value into settings table."""
-    conn = get_connection()
-    for key, value in body.items():
-        conn.execute(
-            "INSERT INTO settings (key, value) VALUES (?, ?) "
-            "ON CONFLICT(key) DO UPDATE SET value = excluded.value",
-            (key, str(value)),
-        )
-    conn.commit()
-    return {"status": "ok"}
-
-
-@router.get("/stats", response_model=StatsResponse)
-async def get_stats():
-    """Return event and object counts."""
-    conn = get_connection()
-
-    total = conn.execute("SELECT COUNT(*) FROM events").fetchone()[0]
-    known = conn.execute(
-        "SELECT COUNT(*) FROM events WHERE match_status = 'known'"
-    ).fetchone()[0]
-    unknown = conn.execute(
-        "SELECT COUNT(*) FROM events WHERE match_status = 'unknown'"
-    ).fetchone()[0]
-    unreviewed = conn.execute(
-        "SELECT COUNT(*) FROM events WHERE match_status = 'unreviewed'"
-    ).fetchone()[0]
-    objects_count = conn.execute("SELECT COUNT(*) FROM known_objects").fetchone()[0]
-    today = date.today().isoformat()
-    events_today = conn.execute(
-        "SELECT COUNT(*) FROM events WHERE DATE(created_at) = ?",
-        (today,),
-    ).fetchone()[0]
-
-    return StatsResponse(
-        total_events=total,
-        known_matches=known,
-        unknown_events=unknown,
-        unreviewed=unreviewed,
-        known_objects_count=objects_count,
-        events_today=events_today,
-    )
@@ -1,578 +0,0 @@
-// Frigate Alerts - Web UI
-(function () {
-    'use strict';
-
-    let currentView = 'dashboard';
-    let currentTagEventId = null;
-    let refreshTimer = null;
-    let knownObjectsCache = [];
-
-    // --- Initialization ---
-
-    document.addEventListener('DOMContentLoaded', () => {
-        setupNavigation();
-        setupTagModal();
-        loadView('dashboard');
-        loadStats();
-    });
-
-    // --- Navigation ---
-
-    function setupNavigation() {
-        document.querySelectorAll('.sidebar-item').forEach(item => {
-            item.addEventListener('click', (e) => {
-                e.preventDefault();
-                const view = item.dataset.view;
-                loadView(view);
-            });
-        });
-    }
-
-    function setActiveNav(view) {
-        document.querySelectorAll('.sidebar-item').forEach(item => {
-            item.classList.toggle('active', item.dataset.view === view);
-        });
-    }
-
-    // --- View Router ---
-
-    function loadView(view) {
-        currentView = view;
-        setActiveNav(view);
-        clearAutoRefresh();
-
-        switch (view) {
-            case 'dashboard':
-                loadDashboard();
-                startAutoRefresh();
-                break;
-            case 'review':
-                loadReview();
-                startAutoRefresh();
-                break;
-            case 'known':
-                loadKnown();
-                break;
-            case 'settings':
-                loadSettings();
-                break;
-        }
-    }
-
-    // --- Auto Refresh ---
-
-    function startAutoRefresh() {
-        refreshTimer = setInterval(() => {
-            if (currentView === 'dashboard') {
-                loadDashboard();
-            } else if (currentView === 'review') {
-                loadReview();
-            }
-            loadStats();
-        }, 30000);
-    }
-
-    function clearAutoRefresh() {
-        if (refreshTimer) {
-            clearInterval(refreshTimer);
-            refreshTimer = null;
-        }
-    }
-
-    // --- Dashboard View ---
-
-    function loadDashboard() {
-        const content = document.getElementById('main-content');
-        content.innerHTML = '<div class="loading">Loading events</div>';
-
-        fetch('/api/events?limit=50')
-            .then(r => r.json())
-            .then(events => {
-                if (!events.length) {
-                    content.innerHTML = `
-                        <h1>Dashboard</h1>
-                        <div class="empty-state">
-                            <p>No events recorded yet.</p>
-                            <p>Events will appear here when Frigate detects objects.</p>
-                        </div>`;
-                    return;
-                }
-                content.innerHTML = `
-                    <div class="page-header">
-                        <h1>Dashboard</h1>
-                    </div>
-                    <div class="filters">
-                        <select id="filter-camera" onchange="window._applyFilters()">
-                            <option value="">All Cameras</option>
-                        </select>
-                        <select id="filter-label" onchange="window._applyFilters()">
-                            <option value="">All Labels</option>
-                        </select>
-                        <select id="filter-status" onchange="window._applyFilters()">
-                            <option value="">All Statuses</option>
-                            <option value="known">Known</option>
-                            <option value="unknown">Unknown</option>
-                            <option value="ambiguous">Ambiguous</option>
-                            <option value="unreviewed">Unreviewed</option>
-                        </select>
-                    </div>
-                    <div id="events-list"></div>`;
-
-                populateFilterOptions(events);
-                renderEvents(events);
-            })
-            .catch(err => {
-                content.innerHTML = `<h1>Dashboard</h1><div class="empty-state"><p>Error loading events: ${err.message}</p></div>`;
-            });
-    }
-
-    function populateFilterOptions(events) {
-        const cameras = [...new Set(events.map(e => e.camera).filter(Boolean))].sort();
-        const labels = [...new Set(events.map(e => e.label).filter(Boolean))].sort();
-
-        const cameraSelect = document.getElementById('filter-camera');
-        const labelSelect = document.getElementById('filter-label');
-
-        if (cameraSelect) {
-            cameras.forEach(c => {
-                const opt = document.createElement('option');
-                opt.value = c;
-                opt.textContent = c;
-                cameraSelect.appendChild(opt);
-            });
-        }
-
-        if (labelSelect) {
-            labels.forEach(l => {
-                const opt = document.createElement('option');
-                opt.value = l;
-                opt.textContent = l;
-                labelSelect.appendChild(opt);
-            });
-        }
-    }
-
-    // Expose filter function globally for inline onchange handlers
-    window._applyFilters = function () {
-        const camera = document.getElementById('filter-camera')?.value || '';
-        const label = document.getElementById('filter-label')?.value || '';
-        const status = document.getElementById('filter-status')?.value || '';
-
-        let url = '/api/events?limit=50';
-        if (camera) url += `&camera=${encodeURIComponent(camera)}`;
-        if (label) url += `&label=${encodeURIComponent(label)}`;
-        if (status) url += `&status=${encodeURIComponent(status)}`;
-
-        fetch(url)
-            .then(r => r.json())
-            .then(events => renderEvents(events))
-            .catch(err => console.error('Filter error:', err));
-    };
-
-    function renderEvents(events) {
-        const container = document.getElementById('events-list');
-        if (!container) return;
-
-        if (!events.length) {
-            container.innerHTML = '<div class="empty-state"><p>No events match the current filters.</p></div>';
-            return;
-        }
-
-        container.innerHTML = events.map(event => `
-            <div class="event-card" data-event-id="${event.id}">
-                <img src="/api/events/${event.id}/snapshot"
-                     onerror="this.style.display='none'"
-                     alt="${event.label || 'snapshot'}">
-                <div class="event-info">
-                    <div class="event-header">
-                        <span>
-                            <span class="event-camera">${escapeHtml(event.camera || 'unknown')}</span>
-                            <span class="event-label"> &mdash; ${escapeHtml(event.label || 'unknown')}</span>
-                            <span class="event-score">(${(event.score * 100).toFixed(0)}%)</span>
-                        </span>
-                        <span class="badge badge-${event.match_status || 'unreviewed'}">${event.match_status || 'unreviewed'}</span>
-                    </div>
-                    <div class="event-time">${formatTime(event.created_at)}</div>
-                    ${event.ai_description ? `<div class="event-description">${escapeHtml(event.ai_description)}</div>` : ''}
-                    ${event.matched_object_name ? `<div class="event-label">Identified as: <strong>${escapeHtml(event.matched_object_name)}</strong></div>` : ''}
-                    <div class="event-actions">
-                        <button class="btn btn-primary btn-sm" onclick="window._tagEvent('${event.id}')">Tag</button>
-                        <button class="btn btn-sm" onclick="window._dismissEvent('${event.id}')">Dismiss</button>
-                    </div>
-                </div>
-            </div>
-        `).join('');
-    }
-
-    // --- Review View ---
-
-    function loadReview() {
-        const content = document.getElementById('main-content');
-        content.innerHTML = '<div class="loading">Loading review queue</div>';
-
-        fetch('/api/events?limit=50&status=unreviewed')
-            .then(r => r.json())
-            .then(events => {
-                if (!events.length) {
-                    content.innerHTML = `
-                        <h1>Review Queue</h1>
-                        <div class="empty-state">
-                            <p>No events to review.</p>
-                            <p>All events have been reviewed or dismissed.</p>
-                        </div>`;
-                    return;
-                }
-                content.innerHTML = `
-                    <div class="page-header">
-                        <h1>Review Queue</h1>
-                        <span>${events.length} event${events.length !== 1 ? 's' : ''} to review</span>
-                    </div>
-                    <div id="events-list"></div>`;
-                renderEvents(events);
-            })
-            .catch(err => {
-                content.innerHTML = `<h1>Review Queue</h1><div class="empty-state"><p>Error loading events: ${err.message}</p></div>`;
-            });
-    }
-
-    // --- Known Objects View ---
-
-    function loadKnown() {
-        const content = document.getElementById('main-content');
-        content.innerHTML = '<div class="loading">Loading known objects</div>';
-
-        fetch('/api/known-objects')
-            .then(r => r.json())
-            .then(objects => {
-                knownObjectsCache = objects;
-
-                if (!objects.length) {
-                    content.innerHTML = `
-                        <h1>Known Objects</h1>
-                        <div class="empty-state">
-                            <p>No known objects registered.</p>
-                            <p>Tag events from the Dashboard to add known objects.</p>
-                        </div>`;
-                    return;
-                }
-
-                content.innerHTML = `
-                    <div class="page-header">
-                        <h1>Known Objects</h1>
-                        <span>${objects.length} object${objects.length !== 1 ? 's' : ''}</span>
-                    </div>
-                    <div class="known-grid">
-                        ${objects.map(obj => `
-                            <div class="known-card" data-object-id="${obj.id}">
-                                <h4>${escapeHtml(obj.name)}</h4>
-                                <span class="type-badge">${escapeHtml(obj.type)}</span>
-                                <div class="embedding-count">${obj.embedding_count || 0} embedding${(obj.embedding_count || 0) !== 1 ? 's' : ''}</div>
-                                ${obj.samples && obj.samples.length ? `
-                                    <div class="known-card-samples">
-                                        ${obj.samples.map(s => `<img src="${s}" onerror="this.style.display='none'" alt="sample">`).join('')}
-                                    </div>
-                                ` : ''}
-                                <div class="known-card-actions">
-                                    <button class="btn btn-danger btn-sm" onclick="window._deleteKnownObject('${obj.id}', '${escapeHtml(obj.name)}')">Delete</button>
-                                </div>
-                            </div>
-                        `).join('')}
-                    </div>`;
-            })
-            .catch(err => {
-                content.innerHTML = `<h1>Known Objects</h1><div class="empty-state"><p>Error loading objects: ${err.message}</p></div>`;
-            });
-    }
-
-    // --- Settings View ---
-
-    function loadSettings() {
-        const content = document.getElementById('main-content');
-        content.innerHTML = '<div class="loading">Loading settings</div>';
-
-        fetch('/api/settings')
-            .then(r => r.json())
-            .then(settings => {
-                content.innerHTML = `
-                    <h1>Settings</h1>
-                    <div class="settings-form">
-                        <div class="settings-section">
-                            <h3>Vision Analysis</h3>
-                            <div class="form-group">
-                                <label>Vision Backend</label>
-                                <select id="setting-vision-backend">
-                                    <option value="haiku" ${settings.vision_backend === 'haiku' ? 'selected' : ''}>Claude Haiku</option>
-                                    <option value="ollama" ${settings.vision_backend === 'ollama' ? 'selected' : ''}>Ollama (Local)</option>
-                                    <option value="both" ${settings.vision_backend === 'both' ? 'selected' : ''}>Both (Haiku + Ollama)</option>
-                                </select>
-                                <div class="help-text">Which AI backend to use for snapshot analysis</div>
-                            </div>
-                        </div>
-
-                        <div class="settings-section">
-                            <h3>Recognition</h3>
-                            <div class="form-group">
-                                <label class="checkbox-label">
-                                    <input type="checkbox" id="setting-recognition-enabled" ${settings.recognition_enabled ? 'checked' : ''}>
-                                    Enable object recognition
-                                </label>
-                                <div class="help-text">Match detected objects against known objects database</div>
-                            </div>
-                        </div>
-
-                        <div class="settings-section">
-                            <h3>Data Retention</h3>
-                            <div class="form-group">
-                                <label>Event Retention (days)</label>
-                                <input type="number" id="setting-retention-days" value="${settings.event_retention_days || 30}" min="1" max="365">
-                                <div class="help-text">How long to keep event records and snapshots</div>
-                            </div>
-                        </div>
-
-                        <div class="form-group">
-                            <button class="btn btn-primary" onclick="window._saveSettings()">Save Settings</button>
-                        </div>
-                    </div>`;
-            })
-            .catch(err => {
-                content.innerHTML = `<h1>Settings</h1><div class="empty-state"><p>Error loading settings: ${err.message}</p></div>`;
-            });
-    }
-
-    window._saveSettings = function () {
-        const settings = {
-            vision_backend: document.getElementById('setting-vision-backend').value,
-            recognition_enabled: document.getElementById('setting-recognition-enabled').checked,
-            event_retention_days: parseInt(document.getElementById('setting-retention-days').value, 10)
-        };
-
-        fetch('/api/settings', {
-            method: 'PUT',
-            headers: { 'Content-Type': 'application/json' },
-            body: JSON.stringify(settings)
-        })
-            .then(r => {
-                if (!r.ok) throw new Error('Failed to save settings');
-                return r.json();
-            })
-            .then(() => showToast('Settings saved', 'success'))
-            .catch(err => showToast('Error: ' + err.message, 'error'));
-    };
-
-    // --- Stats ---
-
-    function loadStats() {
-        fetch('/api/stats')
-            .then(r => r.json())
-            .then(stats => {
-                const el = document.getElementById('stats-summary');
-                if (!el) return;
-
-                el.innerHTML = `
-                    <div class="stat-item">
-                        <span>Total Events</span>
-                        <span class="stat-value">${stats.total_events || 0}</span>
-                    </div>
-                    <div class="stat-item">
-                        <span>Unreviewed</span>
-                        <span class="stat-value">${stats.unreviewed || 0}</span>
-                    </div>
-                    <div class="stat-item">
-                        <span>Known</span>
-                        <span class="stat-value">${stats.known_matches || 0}</span>
-                    </div>
-                    <div class="stat-item">
-                        <span>Unknown</span>
-                        <span class="stat-value">${stats.unknown_events || 0}</span>
-                    </div>
-                    <div class="stat-item">
-                        <span>Known Objects</span>
-                        <span class="stat-value">${stats.known_objects_count || 0}</span>
-                    </div>`;
-            })
-            .catch(() => {
-                // Stats are non-critical, silently fail
-            });
-    }
-
-    // --- Tag Modal ---
-
-    function setupTagModal() {
-        document.getElementById('tag-cancel').addEventListener('click', closeTagModal);
-        document.getElementById('tag-save').addEventListener('click', saveTag);
-
-        document.getElementById('tag-existing-object').addEventListener('change', (e) => {
-            const newFields = document.getElementById('tag-new-fields');
-            newFields.style.display = e.target.value ? 'none' : 'block';
-        });
-
-        // Close modal on backdrop click
-        document.getElementById('tag-modal').addEventListener('click', (e) => {
-            if (e.target === document.getElementById('tag-modal')) {
-                closeTagModal();
-            }
-        });
-
-        // Close modal on Escape key
-        document.addEventListener('keydown', (e) => {
-            if (e.key === 'Escape') closeTagModal();
-        });
-    }
-
-    window._tagEvent = function (eventId) {
-        currentTagEventId = eventId;
-
-        // Show snapshot in modal
-        const snapshotContainer = document.getElementById('tag-modal-snapshot');
-        snapshotContainer.innerHTML = `<img src="/api/events/${eventId}/snapshot" onerror="this.style.display='none'" alt="snapshot">`;
-
-        // Load known objects for dropdown
-        fetch('/api/known-objects')
-            .then(r => r.json())
-            .then(objects => {
-                knownObjectsCache = objects;
-                const select = document.getElementById('tag-existing-object');
-                select.innerHTML = '<option value="">-- Create new --</option>';
-                objects.forEach(obj => {
-                    const opt = document.createElement('option');
-                    opt.value = obj.id;
-                    opt.textContent = `${obj.name} (${obj.type})`;
-                    select.appendChild(opt);
-                });
-            })
-            .catch(() => { });
-
-        // Reset form
-        document.getElementById('tag-name').value = '';
-        document.getElementById('tag-type').value = 'person';
-        document.getElementById('tag-new-fields').style.display = 'block';
-        document.getElementById('tag-existing-object').value = '';
-
-        document.getElementById('tag-modal').classList.remove('hidden');
-    };
-
-    function closeTagModal() {
-        document.getElementById('tag-modal').classList.add('hidden');
-        currentTagEventId = null;
-    }
-
-    function saveTag() {
-        if (!currentTagEventId) return;
-
-        const existingId = document.getElementById('tag-existing-object').value;
-        let body;
-
-        if (existingId) {
-            body = { known_object_id: existingId };
-        } else {
-            const name = document.getElementById('tag-name').value.trim();
-            const type = document.getElementById('tag-type').value;
-            if (!name) {
-                showToast('Please enter a name', 'error');
-                return;
-            }
-            body = { name: name, type: type };
-        }
-
-        fetch(`/api/events/${currentTagEventId}/tag`, {
-            method: 'POST',
-            headers: { 'Content-Type': 'application/json' },
-            body: JSON.stringify(body)
-        })
-            .then(r => {
-                if (!r.ok) throw new Error('Failed to tag event');
-                return r.json();
-            })
-            .then(() => {
-                showToast('Event tagged successfully', 'success');
-                closeTagModal();
-                loadView(currentView);
-                loadStats();
-            })
-            .catch(err => showToast('Error: ' + err.message, 'error'));
-    }
-
-    // --- Event Actions ---
-
-    window._dismissEvent = function (eventId) {
-        fetch(`/api/events/${eventId}/dismiss`, {
-            method: 'POST',
-            headers: { 'Content-Type': 'application/json' }
-        })
-            .then(r => {
-                if (!r.ok) throw new Error('Failed to dismiss event');
-                return r.json();
-            })
-            .then(() => {
-                showToast('Event dismissed', 'success');
-                // Remove card from DOM for immediate feedback
-                const card = document.querySelector(`.event-card[data-event-id="${eventId}"]`);
-                if (card) {
-                    card.style.opacity = '0';
-                    card.style.transition = 'opacity 0.3s';
-                    setTimeout(() => card.remove(), 300);
-                }
-                loadStats();
-            })
-            .catch(err => showToast('Error: ' + err.message, 'error'));
-    };
-
-    // --- Known Object Actions ---
-
-    window._deleteKnownObject = function (objectId, name) {
-        if (!confirm(`Delete known object "${name}"? This cannot be undone.`)) return;
-
-        fetch(`/api/known-objects/${objectId}`, {
-            method: 'DELETE'
-        })
-            .then(r => {
-                if (!r.ok) throw new Error('Failed to delete object');
-                return r.json();
-            })
-            .then(() => {
-                showToast(`Deleted "${name}"`, 'success');
-                loadKnown();
-                loadStats();
-            })
-            .catch(err => showToast('Error: ' + err.message, 'error'));
-    };
-
-    // --- Utilities ---
-
-    function escapeHtml(str) {
-        if (!str) return '';
-        const div = document.createElement('div');
-        div.textContent = str;
-        return div.innerHTML;
-    }
-
-    function formatTime(timestamp) {
-        if (!timestamp) return '';
-        const date = new Date(timestamp);
-        const now = new Date();
-        const diffMs = now - date;
-        const diffMins = Math.floor(diffMs / 60000);
-        const diffHours = Math.floor(diffMs / 3600000);
-        const diffDays = Math.floor(diffMs / 86400000);
-
-        if (diffMins < 1) return 'Just now';
-        if (diffMins < 60) return `${diffMins}m ago`;
-        if (diffHours < 24) return `${diffHours}h ago`;
-        if (diffDays < 7) return `${diffDays}d ago`;
-
-        return date.toLocaleDateString() + ' ' + date.toLocaleTimeString([], { hour: '2-digit', minute: '2-digit' });
-    }
-
-    function showToast(message, type) {
-        const toast = document.createElement('div');
-        toast.className = `toast toast-${type}`;
-        toast.textContent = message;
-        document.body.appendChild(toast);
-        setTimeout(() => {
-            toast.style.opacity = '0';
-            toast.style.transition = 'opacity 0.3s';
-            setTimeout(() => toast.remove(), 300);
-        }, 3000);
-    }
-
-})();
@@ -1,61 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-    <meta charset="UTF-8">
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>Frigate Alerts</title>
-    <link rel="stylesheet" href="/static/style.css">
-</head>
-<body>
-    <nav id="sidebar">
-        <div class="sidebar-header">
-            <h2>Frigate Alerts</h2>
-        </div>
-        <div class="sidebar-section">
-            <a href="#" class="sidebar-item active" data-view="dashboard">Dashboard</a>
-            <a href="#" class="sidebar-item" data-view="review">Review Queue</a>
-            <a href="#" class="sidebar-item" data-view="known">Known Objects</a>
-            <a href="#" class="sidebar-item" data-view="settings">Settings</a>
-        </div>
-        <div class="sidebar-section sidebar-stats">
-            <div id="stats-summary"></div>
-        </div>
-    </nav>
-    <main id="content">
-        <div id="main-content"></div>
-    </main>
-
-    <div id="tag-modal" class="modal hidden">
-        <div class="modal-content">
-            <h3>Tag as Known Object</h3>
-            <div id="tag-modal-snapshot"></div>
-            <div class="form-group">
-                <label>Existing object:</label>
-                <select id="tag-existing-object">
-                    <option value="">-- Create new --</option>
-                </select>
-            </div>
-            <div id="tag-new-fields">
-                <div class="form-group">
-                    <label>Name:</label>
-                    <input type="text" id="tag-name" placeholder="e.g., Jeremy, Blue F-150, Max">
-                </div>
-                <div class="form-group">
-                    <label>Type:</label>
-                    <select id="tag-type">
-                        <option value="person">Person</option>
-                        <option value="vehicle">Vehicle</option>
-                        <option value="pet">Pet</option>
-                    </select>
-                </div>
-            </div>
-            <div class="modal-actions">
-                <button id="tag-save" class="btn btn-primary">Save</button>
-                <button id="tag-cancel" class="btn">Cancel</button>
-            </div>
-        </div>
-    </div>
-
-    <script src="/static/app.js"></script>
-</body>
-</html>
@@ -1,534 +0,0 @@
-* {
-    margin: 0;
-    padding: 0;
-    box-sizing: border-box;
-}
-
-body {
-    font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
-    background: #1a1a2e;
-    color: #e0e0e0;
-    display: flex;
-    min-height: 100vh;
-}
-
-/* Sidebar */
-#sidebar {
-    width: 220px;
-    background: #16213e;
-    padding: 20px 0;
-    position: fixed;
-    height: 100vh;
-    overflow-y: auto;
-}
-
-.sidebar-header {
-    padding: 0 20px 20px;
-    border-bottom: 1px solid #0f3460;
-}
-
-.sidebar-header h2 {
-    color: #00b4d8;
-    font-size: 1.2em;
-}
-
-.sidebar-section {
-    padding: 10px 0;
-}
-
-.sidebar-item {
-    display: block;
-    padding: 10px 20px;
-    color: #a0a0a0;
-    text-decoration: none;
-    transition: all 0.2s;
-}
-
-.sidebar-item:hover {
-    background: #0f3460;
-    color: #fff;
-}
-
-.sidebar-item.active {
-    background: #0f3460;
-    color: #00b4d8;
-    border-left: 3px solid #00b4d8;
-}
-
-.sidebar-stats {
-    padding: 20px;
-    font-size: 0.85em;
-    color: #888;
-}
-
-/* Main content */
-#content {
-    margin-left: 220px;
-    flex: 1;
-    padding: 20px;
-}
-
-/* Page headers */
-h1 {
-    margin-bottom: 20px;
-}
-
-.page-header {
-    display: flex;
-    justify-content: space-between;
-    align-items: center;
-    margin-bottom: 20px;
-}
-
-/* Filters */
-.filters {
-    display: flex;
-    gap: 10px;
-    margin-bottom: 20px;
-    flex-wrap: wrap;
-}
-
-.filters select,
-.filters input {
-    padding: 6px 10px;
-    background: #16213e;
-    border: 1px solid #0f3460;
-    color: #e0e0e0;
-    border-radius: 4px;
-}
-
-.filters select:focus,
-.filters input:focus {
-    outline: none;
-    border-color: #00b4d8;
-}
-
-/* Event cards */
-.event-card {
-    background: #16213e;
-    border-radius: 8px;
-    padding: 15px;
-    margin-bottom: 15px;
-    display: flex;
-    gap: 15px;
-    transition: border-color 0.2s;
-    border: 1px solid transparent;
-}
-
-.event-card:hover {
-    border-color: #0f3460;
-}
-
-.event-card img {
-    width: 160px;
-    height: 120px;
-    object-fit: cover;
-    border-radius: 4px;
-    background: #1a1a2e;
-}
-
-.event-info {
-    flex: 1;
-}
-
-.event-header {
-    display: flex;
-    justify-content: space-between;
-    align-items: center;
-    margin-bottom: 8px;
-}
-
-.event-camera {
-    font-weight: bold;
-    color: #00b4d8;
-}
-
-.event-label {
-    color: #a0a0a0;
-}
-
-.event-score {
-    color: #888;
-    font-size: 0.85em;
-}
-
-.event-description {
-    color: #ccc;
-    margin: 8px 0;
-    font-size: 0.9em;
-    line-height: 1.4;
-}
-
-.event-time {
-    color: #666;
-    font-size: 0.8em;
-    margin-bottom: 6px;
-}
-
-.event-actions {
-    margin-top: 10px;
-    display: flex;
-    gap: 8px;
-}
-
-/* Status badges */
-.badge {
-    padding: 3px 10px;
-    border-radius: 12px;
-    font-size: 0.8em;
-    font-weight: bold;
-}
-
-.badge-known {
-    background: #2d6a4f;
-    color: #95d5b2;
-}
-
-.badge-unknown {
-    background: #9a4c1a;
-    color: #f4a261;
-}
-
-.badge-ambiguous {
-    background: #7c6f09;
-    color: #ffd166;
-}
-
-.badge-unreviewed {
-    background: #444;
-    color: #aaa;
-}
-
-/* Buttons */
-.btn {
-    padding: 6px 14px;
-    border: none;
-    border-radius: 4px;
-    cursor: pointer;
-    font-size: 0.85em;
-    transition: all 0.2s;
-    color: #ccc;
-    background: #2a2a4a;
-}
-
-.btn:hover {
-    background: #3a3a5a;
-    color: #fff;
-}
-
-.btn-primary {
-    background: #0f3460;
-    color: #fff;
-}
-
-.btn-primary:hover {
-    background: #00b4d8;
-}
-
-.btn-danger {
-    background: #7c2929;
-    color: #fff;
-}
-
-.btn-danger:hover {
-    background: #c0392b;
-}
-
-.btn-sm {
-    padding: 4px 10px;
-    font-size: 0.8em;
-}
-
-/* Modal */
-.modal {
-    position: fixed;
-    top: 0;
-    left: 0;
-    width: 100%;
-    height: 100%;
-    background: rgba(0, 0, 0, 0.7);
-    display: flex;
-    align-items: center;
-    justify-content: center;
-    z-index: 1000;
-}
-
-.modal.hidden {
-    display: none;
-}
-
-.modal-content {
-    background: #16213e;
-    border-radius: 8px;
-    padding: 25px;
-    width: 450px;
-    max-width: 90vw;
-}
-
-.modal-content h3 {
-    margin-bottom: 15px;
-    color: #00b4d8;
-}
-
-.modal-actions {
-    display: flex;
-    gap: 10px;
-    justify-content: flex-end;
-    margin-top: 15px;
-}
-
-#tag-modal-snapshot {
-    margin-bottom: 15px;
-}
-
-#tag-modal-snapshot img {
-    width: 100%;
-    max-height: 200px;
-    object-fit: cover;
-    border-radius: 4px;
-}
-
-/* Form elements */
-.form-group {
-    margin-bottom: 12px;
-}
-
-.form-group label {
-    display: block;
-    margin-bottom: 4px;
-    color: #a0a0a0;
-    font-size: 0.9em;
-}
-
-.form-group input,
-.form-group select {
-    width: 100%;
-    padding: 8px 10px;
-    background: #1a1a2e;
-    border: 1px solid #0f3460;
-    color: #e0e0e0;
-    border-radius: 4px;
-}
-
-.form-group input:focus,
-.form-group select:focus {
-    outline: none;
-    border-color: #00b4d8;
-}
-
-.form-group input[type="checkbox"] {
-    width: auto;
-    margin-right: 8px;
-}
-
-.form-group .checkbox-label {
-    display: flex;
-    align-items: center;
-    cursor: pointer;
-}
-
-.form-group .help-text {
-    font-size: 0.8em;
-    color: #666;
-    margin-top: 4px;
-}
-
-/* Known objects grid */
-.known-grid {
-    display: grid;
-    grid-template-columns: repeat(auto-fill, minmax(250px, 1fr));
-    gap: 15px;
-}
-
-.known-card {
-    background: #16213e;
-    border-radius: 8px;
-    padding: 15px;
-    border: 1px solid transparent;
-    transition: border-color 0.2s;
-}
-
-.known-card:hover {
-    border-color: #0f3460;
-}
-
-.known-card h4 {
-    color: #00b4d8;
-    margin-bottom: 5px;
-}
-
-.known-card .type-badge {
-    font-size: 0.8em;
-    color: #a0a0a0;
-    text-transform: capitalize;
-}
-
-.known-card .embedding-count {
-    font-size: 0.8em;
-    color: #666;
-    margin-top: 6px;
-}
-
-.known-card .known-card-actions {
-    margin-top: 10px;
-    display: flex;
-    gap: 8px;
-}
-
-.known-card .known-card-samples {
-    display: flex;
-    gap: 5px;
-    margin-top: 10px;
-    overflow-x: auto;
-}
-
-.known-card .known-card-samples img {
-    width: 60px;
-    height: 60px;
-    object-fit: cover;
-    border-radius: 4px;
-    background: #1a1a2e;
-}
-
-/* Settings */
-.settings-form {
-    max-width: 600px;
-}
-
-.settings-form .form-group {
-    margin-bottom: 15px;
-}
-
-.settings-section {
-    margin-bottom: 30px;
-}
-
-.settings-section h3 {
-    color: #00b4d8;
-    margin-bottom: 15px;
-    padding-bottom: 8px;
-    border-bottom: 1px solid #0f3460;
-}
-
-/* Stats in sidebar */
-.stat-item {
-    display: flex;
-    justify-content: space-between;
-    margin-bottom: 8px;
-}
-
-.stat-value {
-    color: #00b4d8;
-    font-weight: bold;
-}
-
-/* Empty state */
-.empty-state {
-    text-align: center;
-    color: #666;
-    padding: 60px 20px;
-}
-
-.empty-state p {
-    margin-top: 10px;
-    font-size: 0.9em;
-}
-
-/* Loading spinner */
-.loading {
-    text-align: center;
-    padding: 40px;
-    color: #666;
-}
-
-.loading::after {
-    content: '';
-    display: inline-block;
-    width: 20px;
-    height: 20px;
-    border: 2px solid #0f3460;
-    border-top-color: #00b4d8;
-    border-radius: 50%;
-    animation: spin 0.8s linear infinite;
-    margin-left: 10px;
-    vertical-align: middle;
-}
-
-@keyframes spin {
-    to { transform: rotate(360deg); }
-}
-
-/* Toast notifications */
-.toast {
-    position: fixed;
-    bottom: 20px;
-    right: 20px;
-    padding: 12px 20px;
-    border-radius: 6px;
-    color: #fff;
-    font-size: 0.9em;
-    z-index: 2000;
-    animation: slideIn 0.3s ease-out;
-}
-
-.toast-success {
-    background: #2d6a4f;
-}
-
-.toast-error {
-    background: #7c2929;
-}
-
-@keyframes slideIn {
-    from {
-        transform: translateY(20px);
-        opacity: 0;
-    }
-    to {
-        transform: translateY(0);
-        opacity: 1;
-    }
-}
-
-/* Responsive */
-@media (max-width: 768px) {
-    #sidebar {
-        width: 100%;
-        height: auto;
-        position: relative;
-    }
-
-    .sidebar-section {
-        display: flex;
-        flex-wrap: wrap;
-    }
-
-    .sidebar-item {
-        padding: 8px 15px;
-    }
-
-    .sidebar-stats {
-        display: none;
-    }
-
-    #content {
-        margin-left: 0;
-    }
-
-    body {
-        flex-direction: column;
-    }
-
-    .event-card {
-        flex-direction: column;
-    }
-
-    .event-card img {
-        width: 100%;
-        height: auto;
-    }
-
-    .known-grid {
-        grid-template-columns: 1fr;
-    }
-}
@@ -1,11 +1,7 @@
 import base64
 import logging
-from typing import Optional
-
 import anthropic

-from ollama_client import OllamaClient
-
 logger = logging.getLogger(__name__)

 PROMPT = (
@@ -44,66 +40,3 @@ def analyze_snapshot(client: anthropic.Anthropic, image_bytes: bytes) -> str | N
    except Exception:
        logger.exception("Claude Vision API failed")
        return None
-
-
-async def analyze_snapshot_ollama(
-    ollama_client: OllamaClient, image_bytes: bytes
-) -> str | None:
-    """Send a snapshot to Ollama vision model for description.
-
-    Args:
-        ollama_client: Configured OllamaClient instance.
-        image_bytes: Raw image bytes (JPEG).
-
-    Returns:
-        Description string or None on failure.
-    """
-    return await ollama_client.analyze_image(image_bytes, PROMPT)
-
-
-async def get_description(
-    image_bytes: bytes,
-    vision_backend: str,
-    claude_client: Optional[anthropic.Anthropic] = None,
-    ollama_client: Optional[OllamaClient] = None,
-) -> str | None:
-    """Get a scene description using the configured vision backend.
-
-    Args:
-        image_bytes: Raw image bytes (JPEG).
-        vision_backend: One of "haiku", "ollama", or "both".
-            "both" tries Ollama first, falls back to Haiku.
-        claude_client: Anthropic client (required for "haiku" and "both").
-        ollama_client: OllamaClient instance (required for "ollama" and "both").
-
-    Returns:
-        Description string or None if all backends fail.
-    """
-    if vision_backend == "ollama":
-        if ollama_client is None:
-            logger.error("Ollama backend selected but no client provided")
-            return None
-        return await analyze_snapshot_ollama(ollama_client, image_bytes)
-
-    if vision_backend == "haiku":
-        if claude_client is None:
-            logger.error("Haiku backend selected but no client provided")
-            return None
-        return analyze_snapshot(claude_client, image_bytes)
-
-    if vision_backend == "both":
-        # Try Ollama first, fall back to Haiku
-        if ollama_client is not None:
-            result = await analyze_snapshot_ollama(ollama_client, image_bytes)
-            if result is not None:
-                return result
-            logger.info("Ollama failed, falling back to Haiku")
-
-        if claude_client is not None:
-            return analyze_snapshot(claude_client, image_bytes)
-
-        logger.error("Both backend selected but no clients provided")
-        return None
-
-    logger.error("Unknown vision backend: %s", vision_backend)
-    return None
@@ -12,8 +12,8 @@ services:
      - MQTT_HOST=192.168.86.192
      - MQTT_PORT=1883
      - MATRIX_HOMESERVER=http://192.168.86.192:8008
-      - CLIP_SERVICE_URL=http://localhost:5200
-      - OLLAMA_URL=http://192.168.86.150:11434
+      - CLIP_SERVICE_URL=http://192.168.86.196:5200
+      - OLLAMA_URL=http://192.168.86.196:11434
      - OLLAMA_MODEL=llava:13b
      - DB_PATH=/data/frigate-notify.db
    volumes:
@@ -8,7 +8,7 @@
 #     back_porch        192.168.44.63  kerberos:kerberos
 #     house_south_corner 192.168.44.61  admin:(blank)
 #     house_south_yard  192.168.44.62  admin:(blank)
-#     gate_camera       192.168.86.175 admin:(blank)
+#     gate_camera       192.168.86.175 admin:(blank)  <-- OFFLINE: wrong user/pass RTSP error
 #
 #   Profile cameras (/profile1 + /profile2, H.264):
 #     house_north       192.168.44.51  admin:123456
@@ -166,17 +166,17 @@ ffmpeg:

 # =============================================================================
 model:
-  path: /openvino-model/ssdlite_mobilenet_v2.xml
-  width: 300
-  height: 300
+  width: 320
+  height: 320
  input_tensor: nhwc
-  input_pixel_format: bgr
+  input_pixel_format: rgb
  labelmap_path: /openvino-model/coco_91cl_bkgr.txt

 detectors:
-  ov:
-    type: openvino
-    device: GPU
+  coral:
+    type: edgetpu
+    device: usb
+
 detect:
  enabled: true
  fps: 3
@@ -229,6 +229,21 @@ birdseye:
  enabled: true
  mode: objects

+semantic_search:
+  enabled: true
+  model_size: large
+
+face_recognition:
+  enabled: true
+  model_size: small
+
+lpr:
+  enabled: true
+
+classification:
+  bird:
+    enabled: true
+
 # =============================================================================
 # Camera definitions
 # =============================================================================
@@ -334,8 +349,19 @@ cameras:
          roles:
            - record

+  # shop_west: throttled to 2fps + stricter filters to reduce detection load
  shop_west:
    enabled: true
+    detect:
+      fps: 2
+    objects:
+      filters:
+        person:
+          min_area: 8000
+          threshold: 0.8
+        car:
+          min_area: 15000
+          threshold: 0.8
    ffmpeg:
      inputs:
        - path: rtsp://127.0.0.1:8554/shop_west_sub
@@ -374,13 +400,12 @@ cameras:
            - record

  # ---------------------------------------------------------------------------
-  # house_east - HEVC, VAAPI disabled (pw: admin)
+  # house_east - HEVC source, go2rtc provides H.264 sub, VAAPI enabled
  # ---------------------------------------------------------------------------

  house_east:
    enabled: true
    ffmpeg:
-      hwaccel_args: []
      inputs:
        - path: rtsp://127.0.0.1:8554/house_east_sub
          input_args: preset-rtsp-restream
@@ -459,6 +484,7 @@ cameras:

  # ---------------------------------------------------------------------------
  # ASH43-W cameras (HEVC main, H.264 sub - go2rtc transcodes main to H.264)
+  # VAAPI enabled - sub stream is H.264
  # ---------------------------------------------------------------------------

  pool_room:
@@ -14,12 +14,12 @@ services:
      - /mnt/frigate-recordings:/media/frigate
      - /etc/localtime:/etc/localtime:ro
    tmpfs:
-      - /tmp/cache:size=4G
+      - /tmp/cache:size=8G
    devices:
      - /dev/dri:/dev/dri
      - /dev/bus/usb:/dev/bus/usb
    mem_limit: 12G
-    memswap_limit: 12G
+    memswap_limit: 16G
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:5000/api/version || exit 1"]
      interval: 30s
@@ -1,2 +0,0 @@
-ANTHROPIC_API_KEY=your-anthropic-api-key
-OPENAI_API_KEY=your-openai-api-key
@@ -1,55 +0,0 @@
-services:
-  litellm:
-    image: ghcr.io/berriai/litellm:main-latest
-    container_name: litellm
-    restart: unless-stopped
-    ports:
-      - "4000:4000"
-    volumes:
-      - /mnt/docker-data/configs/litellm/config.yaml:/app/config.yaml
-    env_file:
-      - .env
-    command: ["--config", "/app/config.yaml", "--port", "4000"]
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    mem_limit: 1G
-    depends_on:
-      litellm-db:
-        condition: service_healthy
-    healthcheck:
-      test: ["CMD-SHELL", "python3 -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://localhost:4000/health/liveliness',timeout=5).status==200 else 1)\""]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 60s
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
-
-  litellm-db:
-    image: postgres:15-alpine
-    container_name: litellm-db
-    restart: unless-stopped
-    user: "1024:100"
-    environment:
-      - POSTGRES_DB=litellm
-      - POSTGRES_USER=litellm
-      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
-    volumes:
-      - /mnt/docker-data/databases/litellm-db:/var/lib/postgresql/data
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    mem_limit: 256M
-    healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U litellm -d litellm"]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-      start_period: 30s
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
@@ -1,24 +0,0 @@
-services:
-  node-exporter:
-    image: prom/node-exporter:v1.7.0
-    container_name: node-exporter
-    hostname: hf-pdocker-01
-    network_mode: host
-    pid: host
-    restart: unless-stopped
-    volumes:
-      - /proc:/host/proc:ro
-      - /sys:/host/sys:ro
-      - /:/rootfs:ro
-    command:
-      - '--path.procfs=/host/proc'
-      - '--path.rootfs=/rootfs'
-      - '--path.sysfs=/host/sys'
-      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
@@ -0,0 +1,29 @@
+services:
+  open-webui:
+    image: ghcr.io/open-webui/open-webui:main
+    container_name: open-webui
+    restart: unless-stopped
+    ports:
+      - "3010:8080"
+    env_file:
+      - .env
+    environment:
+      - TZ=America/Chicago
+      - OLLAMA_BASE_URL=http://192.168.86.196:11434
+    volumes:
+      - /mnt/docker-data/configs/openwebui:/app/backend/data
+    mem_limit: 1G
+    memswap_limit: 1G
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    healthcheck:
+      test: ["CMD-SHELL", "curl -sf http://localhost:8080/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
@@ -1,22 +0,0 @@
-services:
-  telegraf:
-    image: telegraf:latest
-    container_name: telegraf
-    hostname: hf-pdocker-01
-    restart: unless-stopped
-    environment:
-      - HOST_PROC=/host/proc
-      - HOST_SYS=/host/sys
-      - HOST_ETC=/host/etc
-    volumes:
-      - /mnt/docker-data/configs/telegraf/telegraf.conf:/etc/telegraf/telegraf.conf:ro
-      - /var/run/docker.sock:/var/run/docker.sock:ro
-      - /sys:/host/sys:ro
-      - /proc:/host/proc:ro
-      - /etc:/host/etc:ro
-    mem_limit: 512M
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
@@ -0,0 +1,6 @@
+LIVEKIT_API_KEY=voicecoach-89a06ad0
+LIVEKIT_API_SECRET=Dn16mQJU5lTCWwXOrUO8LPflODi3LGiMHdxKdQj4/iM
+ANTHROPIC_API_KEY=
+OPENCLAW_TOKEN=f31cc58c47c2aa420901576b4e90a0101d52e9ec0a084186
+HA_TOKEN=
+SSH_PASS=&Rip8a115
@@ -0,0 +1,16 @@
+FROM python:3.11-slim
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl libsndfile1 ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s \
+    CMD curl -sf http://localhost:8080/health || exit 1
+
+CMD ["python", "main.py", "start"]
@@ -0,0 +1,185 @@
+"""VoiceCoach v2 — livekit-agents 1.5."""
+import asyncio
+import json
+import logging
+import os
+import uuid
+
+from livekit import rtc
+from livekit.agents import (
+    Agent,
+    AgentSession,
+    AutoSubscribe,
+    JobContext,
+    RoomInputOptions,
+    llm as lk_llm,
+)
+from livekit.plugins import openai as lk_openai
+from livekit.plugins import silero
+
+import store
+from modes import DEFAULT_MODE, MODES, ModeConfig
+from tools import ALL_TOOLS
+from vocal import VocalAnalyzer
+
+logger = logging.getLogger(__name__)
+
+SPEACHES_URL = os.getenv("SPEACHES_URL", "http://192.168.86.27:8000")
+OPENCLAW_URL = os.getenv("OPENCLAW_URL", "http://voicecoach-openclaw:3100")
+OPENCLAW_TOKEN = os.getenv("OPENCLAW_TOKEN", "")
+WHISPER_MODEL = "deepdml/faster-whisper-large-v3-turbo-ct2"
+KOKORO_MODEL = "speaches-ai/Kokoro-82M-v1.0-ONNX-fp16"
+KOKORO_VOICE = os.getenv("KOKORO_VOICE", "af_nova")
+
+
+def _build_instructions(mode: ModeConfig, context: str = "") -> str:
+    if context:
+        return f"{mode.instructions}\n\n{context}"
+    return mode.instructions
+
+
+class VoiceCoachAgent(Agent):
+    def __init__(self, mode_name: str, context: str, session_id: str, room: rtc.Room):
+        mode = MODES[mode_name]
+        super().__init__(
+            instructions=_build_instructions(mode, context),
+            tools=ALL_TOOLS,
+        )
+        self._mode_name = mode_name
+        self._session_id = session_id
+        self._room = room
+        self._vocal = VocalAnalyzer()
+
+    async def on_enter(self):
+        await store.create_session(self._session_id, self._mode_name)
+        self.session.generate_reply(
+            instructions="Greet Jeremy warmly in one sentence. Be natural, not formal."
+        )
+
+    async def on_exit(self):
+        await store.end_session(self._session_id)
+
+    async def on_user_turn_completed(
+        self,
+        turn_ctx: lk_llm.ChatContext,
+        new_message: lk_llm.ChatMessage,
+    ):
+        content = new_message.text_content or ""
+        mode = MODES[self._mode_name]
+
+        # Inject vocal state tag into message if mode uses it
+        if mode.vocal_feedback and content:
+            vocal = self._vocal.current
+            if vocal.energy > 0.02:
+                tag = vocal.to_tag()
+                # Update message content to include vocal context
+                new_message.content = [f"{tag}\n{content}"]
+
+        asyncio.create_task(
+            store.add_message(
+                self._session_id,
+                "user",
+                content,
+                vocal_energy=self._vocal.current.energy,
+                vocal_emotion=self._vocal.current.emotion,
+            )
+        )
+
+        await self._push({
+            "type": "final_transcript",
+            "text": content,
+            "speaker": "user",
+        })
+
+    def switch_mode(self, mode_name: str):
+        if mode_name not in MODES:
+            logger.warning("Unknown mode: %s", mode_name)
+            return
+        self._mode_name = mode_name
+        self.update_instructions(_build_instructions(MODES[mode_name]))
+        asyncio.create_task(self._push({"type": "mode_ack", "mode": mode_name}))
+        logger.info("Mode → %s", mode_name)
+
+    async def _push(self, payload: dict):
+        try:
+            data = json.dumps(payload).encode()
+            await self._room.local_participant.publish_data(data, reliable=True)
+        except Exception as e:
+            logger.debug("Data push failed: %s", e)
+
+
+async def entrypoint(ctx: JobContext):
+    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)
+
+    session_id = uuid.uuid4().hex[:8]
+    context = await store.get_recent_context(limit=3)
+
+    agent = VoiceCoachAgent(
+        mode_name=DEFAULT_MODE,
+        context=context,
+        session_id=session_id,
+        room=ctx.room,
+    )
+
+    session = AgentSession(
+        stt=lk_openai.STT(
+            base_url=f"{SPEACHES_URL}/v1",
+            model=WHISPER_MODEL,
+            api_key="speaches",
+        ),
+        llm=lk_openai.LLM(
+            base_url=f"{OPENCLAW_URL}/v1",
+            model="openclaw/assistant",
+            api_key=OPENCLAW_TOKEN,
+        ),
+        tts=lk_openai.TTS(
+            base_url=f"{SPEACHES_URL}/v1",
+            model=KOKORO_MODEL,
+            voice=KOKORO_VOICE,
+            api_key="speaches",
+        ),
+        vad=silero.VAD.load(),
+        allow_interruptions=True,
+        min_endpointing_delay=0.4,
+        max_endpointing_delay=2.0,
+    )
+
+    # Data channel → mode switching
+    @ctx.room.on("data_received")
+    def on_data(packet: rtc.DataPacket):
+        try:
+            msg = json.loads(packet.data.decode())
+            if msg.get("type") == "mode_change":
+                agent.switch_mode(msg.get("mode", DEFAULT_MODE))
+        except Exception:
+            pass
+
+    # Session events → browser
+    @session.on("user_input_transcribed")
+    def on_transcribed(ev):
+        asyncio.create_task(agent._push({
+            "type": "partial_transcript" if not ev.is_final else "final_transcript",
+            "text": ev.transcript,
+            "speaker": "user",
+        }))
+
+    @session.on("conversation_item_added")
+    def on_item(ev):
+        item = ev.item
+        if hasattr(item, "role") and item.role == "assistant":
+            text = item.text_content or ""
+            if text:
+                asyncio.create_task(agent._push({
+                    "type": "agent_response",
+                    "text": text,
+                    "speaker": "assistant",
+                }))
+                asyncio.create_task(
+                    store.add_message(session_id, "assistant", text)
+                )
+
+    await session.start(
+        agent,
+        room=ctx.room,
+        room_input_options=RoomInputOptions(),
+    )
@@ -0,0 +1,29 @@
+"""VoiceCoach v2 — entry point."""
+import logging
+import os
+import threading
+
+from livekit.agents import WorkerOptions, cli
+
+import server
+from agent import entrypoint
+
+logging.basicConfig(level=logging.INFO)
+
+
+def run_api_server():
+    server.run()
+
+
+if __name__ == "__main__":
+    api_thread = threading.Thread(target=run_api_server, daemon=True)
+    api_thread.start()
+
+    cli.run_app(
+        WorkerOptions(
+            entrypoint_fnc=entrypoint,
+            ws_url=os.getenv("LIVEKIT_URL", "ws://voicecoach-livekit:7880"),
+            api_key=os.getenv("LIVEKIT_API_KEY"),
+            api_secret=os.getenv("LIVEKIT_API_SECRET"),
+        )
+    )
@@ -0,0 +1,61 @@
+from dataclasses import dataclass
+
+
+@dataclass
+class ModeConfig:
+    name: str
+    instructions: str
+    max_tokens: int
+    vocal_feedback: bool
+
+
+MODES: dict[str, ModeConfig] = {
+    "coaching": ModeConfig(
+        name="coaching",
+        instructions="""You are a personal voice coach and communication advisor. You are speaking with Jeremy.
+
+Keep responses conversational and concise (2-4 sentences unless asked for more). You receive a [VOCAL] tag before each message with paralinguistic analysis. Use it to provide feedback on BOTH what Jeremy says AND how he sounds.
+
+Never quote raw numbers from the vocal analysis. Translate them naturally: "I notice some tension in your voice" not "energy=0.8".
+
+Available modes (Jeremy switches by saying the phrase or clicking the UI):
+- "coaching mode" (default) — active feedback on content and delivery
+- "vent mode" — listen and reflect, minimal advice
+- "practice mode" — roleplay a difficult conversation partner
+- "briefing mode" — summarize tasks and context from memory
+
+You have tools to interact with Jeremy's homelab infrastructure. Use them when asked about system status, container health, alerts, or home automation. Be concise about results: "hf-pdocker-01 looks healthy, 38 containers running" not a full list.""",
+        max_tokens=512,
+        vocal_feedback=True,
+    ),
+    "vent": ModeConfig(
+        name="vent",
+        instructions="""You are a warm, non-judgmental listener. Jeremy wants to vent or think something through.
+
+Listen, reflect back what you hear, and ask one gentle follow-up question. Keep responses short (1-3 sentences). No coaching, no advice unless explicitly asked.
+
+Ignore the [VOCAL] tag data — just be present.""",
+        max_tokens=256,
+        vocal_feedback=False,
+    ),
+    "practice": ModeConfig(
+        name="practice",
+        instructions="""You are playing a difficult conversation partner for Jeremy to practice with.
+
+Stay in character as: a skeptical stakeholder, a demanding manager, or whoever Jeremy describes. Be realistic — push back, ask hard questions, don't cave too easily. Only break character if Jeremy says "stop practice".
+
+Keep your responses to 1-3 sentences to keep the conversation moving.""",
+        max_tokens=256,
+        vocal_feedback=False,
+    ),
+    "briefing": ModeConfig(
+        name="briefing",
+        instructions="""You are giving Jeremy a morning briefing. Check infrastructure status, pull any alerts, and summarize what needs attention.
+
+Be concise and actionable. Lead with anything that needs immediate attention, then routine status. Use tools to get current data — don't guess.""",
+        max_tokens=768,
+        vocal_feedback=False,
+    ),
+}
+
+DEFAULT_MODE = "coaching"
@@ -1,7 +1,7 @@
-pipecat-ai[livekit,silero,openai]==0.0.48
-httpx==0.27.0
-python-dotenv==1.0.1
-structlog==24.4.0
-livekit-api==0.7.1
+livekit-agents[openai,silero]==1.5.15
 fastapi==0.115.0
 uvicorn[standard]==0.30.0
+aiosqlite==0.20.0
+httpx==0.27.0
+structlog==24.4.0
+python-dotenv==1.0.1
@@ -0,0 +1,83 @@
+"""Token server + sessions REST API — FastAPI."""
+import asyncio
+import os
+from datetime import timedelta
+
+import uvicorn
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from livekit import api as livekit_api
+from pydantic import BaseModel
+
+import store
+
+LIVEKIT_API_KEY = os.environ["LIVEKIT_API_KEY"]
+LIVEKIT_API_SECRET = os.environ["LIVEKIT_API_SECRET"]
+LIVEKIT_PUBLIC_URL = os.getenv("LIVEKIT_PUBLIC_URL", "wss://voice.hobbs.farm")
+
+app = FastAPI(title="VoiceCoach API")
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+class TokenRequest(BaseModel):
+    identity: str = "jeremy"
+
+
+@app.on_event("startup")
+async def startup():
+    await store.init_db()
+
+
+@app.get("/health")
+async def health():
+    return {"status": "ok", "version": "2.0"}
+
+
+@app.post("/api/token")
+async def get_token(req: TokenRequest):
+    token = livekit_api.AccessToken(LIVEKIT_API_KEY, LIVEKIT_API_SECRET)
+    token.with_grants(livekit_api.VideoGrants(
+        room_join=True,
+        room="voicecoach",
+        can_publish=True,
+        can_subscribe=True,
+    ))
+    token.identity = req.identity
+    token.ttl = timedelta(hours=8)
+    return {"token": token.to_jwt(), "url": LIVEKIT_PUBLIC_URL}
+
+
+@app.get("/api/sessions")
+async def list_sessions(limit: int = 20):
+    return await store.get_sessions(limit=limit)
+
+
+@app.get("/api/sessions/{session_id}/messages")
+async def get_messages(session_id: str):
+    msgs = await store.get_session_messages(session_id)
+    if not msgs:
+        raise HTTPException(status_code=404, detail="Session not found")
+    return msgs
+
+
+@app.get("/api/profile/{key}")
+async def get_profile(key: str):
+    value = await store.get_profile(key)
+    if value is None:
+        raise HTTPException(status_code=404, detail="Key not found")
+    return {"key": key, "value": value}
+
+
+@app.put("/api/profile/{key}")
+async def set_profile_key(key: str, body: dict):
+    await store.set_profile(key, str(body.get("value", "")))
+    return {"ok": True}
+
+
+def run():
+    uvicorn.run(app, host="0.0.0.0", port=8080, log_level="info")
@@ -0,0 +1,140 @@
+"""SQLite session store — WAL mode, aiosqlite."""
+import json
+import os
+import time
+from typing import Optional
+
+import aiosqlite
+
+DB_PATH = os.getenv("DB_PATH", "/data/sessions.db")
+
+
+async def init_db():
+    async with aiosqlite.connect(DB_PATH) as db:
+        await db.execute("PRAGMA journal_mode=WAL")
+        await db.executescript("""
+            CREATE TABLE IF NOT EXISTS sessions (
+                id TEXT PRIMARY KEY,
+                started_at REAL NOT NULL,
+                ended_at REAL,
+                mode TEXT DEFAULT 'coaching',
+                summary TEXT
+            );
+
+            CREATE TABLE IF NOT EXISTS messages (
+                id INTEGER PRIMARY KEY AUTOINCREMENT,
+                session_id TEXT NOT NULL,
+                role TEXT NOT NULL,
+                content TEXT NOT NULL,
+                vocal_energy REAL,
+                vocal_emotion TEXT,
+                ts REAL NOT NULL,
+                FOREIGN KEY(session_id) REFERENCES sessions(id)
+            );
+
+            CREATE TABLE IF NOT EXISTS profile (
+                key TEXT PRIMARY KEY,
+                value TEXT NOT NULL,
+                updated_at REAL NOT NULL
+            );
+        """)
+        await db.commit()
+
+
+async def create_session(session_id: str, mode: str = "coaching"):
+    async with aiosqlite.connect(DB_PATH) as db:
+        await db.execute(
+            "INSERT OR IGNORE INTO sessions (id, started_at, mode) VALUES (?, ?, ?)",
+            (session_id, time.time(), mode),
+        )
+        await db.commit()
+
+
+async def end_session(session_id: str, summary: Optional[str] = None):
+    async with aiosqlite.connect(DB_PATH) as db:
+        await db.execute(
+            "UPDATE sessions SET ended_at=?, summary=? WHERE id=?",
+            (time.time(), summary, session_id),
+        )
+        await db.commit()
+
+
+async def add_message(
+    session_id: str,
+    role: str,
+    content: str,
+    vocal_energy: Optional[float] = None,
+    vocal_emotion: Optional[str] = None,
+):
+    async with aiosqlite.connect(DB_PATH) as db:
+        await db.execute(
+            "INSERT INTO messages (session_id, role, content, vocal_energy, vocal_emotion, ts) VALUES (?,?,?,?,?,?)",
+            (session_id, role, content, vocal_energy, vocal_emotion, time.time()),
+        )
+        await db.commit()
+
+
+async def get_recent_context(limit: int = 3) -> str:
+    """Return a brief context string from the last N sessions for injection into system prompt."""
+    async with aiosqlite.connect(DB_PATH) as db:
+        async with db.execute(
+            "SELECT id, started_at, mode, summary FROM sessions WHERE ended_at IS NOT NULL ORDER BY ended_at DESC LIMIT ?",
+            (limit,),
+        ) as cur:
+            rows = await cur.fetchall()
+
+    if not rows:
+        return ""
+
+    parts = ["Recent session context:"]
+    for session_id, started_at, mode, summary in rows:
+        import datetime
+        dt = datetime.datetime.fromtimestamp(started_at).strftime("%Y-%m-%d")
+        if summary:
+            parts.append(f"- {dt} ({mode}): {summary}")
+    return "\n".join(parts)
+
+
+async def get_sessions(limit: int = 20) -> list[dict]:
+    async with aiosqlite.connect(DB_PATH) as db:
+        async with db.execute(
+            "SELECT id, started_at, ended_at, mode, summary FROM sessions ORDER BY started_at DESC LIMIT ?",
+            (limit,),
+        ) as cur:
+            rows = await cur.fetchall()
+    return [
+        {
+            "id": r[0],
+            "started_at": r[1],
+            "ended_at": r[2],
+            "mode": r[3],
+            "summary": r[4],
+        }
+        for r in rows
+    ]
+
+
+async def get_session_messages(session_id: str) -> list[dict]:
+    async with aiosqlite.connect(DB_PATH) as db:
+        async with db.execute(
+            "SELECT role, content, vocal_emotion, ts FROM messages WHERE session_id=? ORDER BY ts",
+            (session_id,),
+        ) as cur:
+            rows = await cur.fetchall()
+    return [{"role": r[0], "content": r[1], "vocal_emotion": r[2], "ts": r[3]} for r in rows]
+
+
+async def get_profile(key: str) -> Optional[str]:
+    async with aiosqlite.connect(DB_PATH) as db:
+        async with db.execute("SELECT value FROM profile WHERE key=?", (key,)) as cur:
+            row = await cur.fetchone()
+    return row[0] if row else None
+
+
+async def set_profile(key: str, value: str):
+    async with aiosqlite.connect(DB_PATH) as db:
+        await db.execute(
+            "INSERT OR REPLACE INTO profile (key, value, updated_at) VALUES (?,?,?)",
+            (key, value, time.time()),
+        )
+        await db.commit()
@@ -0,0 +1,186 @@
+"""Homelab tools wired into the agent via @function_tool."""
+import asyncio
+import logging
+import os
+from typing import Annotated
+
+import httpx
+from livekit.agents import llm
+
+logger = logging.getLogger(__name__)
+
+# Homelab node config
+NODES = {
+    "hf-pdocker-01": "192.168.86.192",
+    "hf-pdocker-02": "192.168.86.100",
+    "bart": "192.168.86.167",
+    "gpu": "192.168.86.27",
+}
+SSH_USER = "glyptic"
+SSH_PASS = os.getenv("SSH_PASS", "&Rip8a115")
+FARM_MANAGER_URL = "http://192.168.86.192:8888"
+HA_URL = os.getenv("HA_URL", "http://192.168.86.192:8123")
+HA_TOKEN = os.getenv("HA_TOKEN", "")
+ALERTMANAGER_URL = "http://192.168.86.192:9093"
+SEARXNG_URL = "http://192.168.86.100:8888"
+
+
+async def _ssh_exec(host: str, cmd: str, timeout: float = 15.0) -> str:
+    """Run a command on a remote host via sshpass."""
+    proc = await asyncio.create_subprocess_exec(
+        "sshpass", "-p", SSH_PASS,
+        "ssh", "-o", "StrictHostKeyChecking=no", "-o", "ConnectTimeout=5",
+        f"{SSH_USER}@{host}", cmd,
+        stdout=asyncio.subprocess.PIPE,
+        stderr=asyncio.subprocess.PIPE,
+    )
+    try:
+        stdout, stderr = await asyncio.wait_for(proc.communicate(), timeout=timeout)
+    except asyncio.TimeoutError:
+        proc.kill()
+        return f"ERROR: command timed out after {timeout}s"
+    if proc.returncode != 0:
+        return f"ERROR: {stderr.decode().strip()}"
+    return stdout.decode().strip()
+
+
+@llm.function_tool
+async def infra_status(
+    node: Annotated[str, "Node name: hf-pdocker-01, hf-pdocker-02, bart, gpu, or 'all'"],
+) -> str:
+    """Check container health on a homelab node. Returns running container count and any unhealthy containers."""
+    nodes = list(NODES.keys()) if node == "all" else [node]
+    results = []
+    for n in nodes:
+        ip = NODES.get(n)
+        if not ip:
+            results.append(f"{n}: unknown node")
+            continue
+        out = await _ssh_exec(ip, "docker ps --format '{{.Names}}\\t{{.Status}}' | head -50")
+        lines = [l for l in out.splitlines() if l.strip()]
+        unhealthy = [l for l in lines if "unhealthy" in l.lower() or "exited" in l.lower()]
+        results.append(
+            f"{n}: {len(lines)} containers running"
+            + (f", ISSUES: {'; '.join(l.split(chr(9))[0] for l in unhealthy)}" if unhealthy else ", all healthy")
+        )
+    return "\n".join(results)
+
+
+@llm.function_tool
+async def container_action(
+    node: Annotated[str, "Node name: hf-pdocker-01, hf-pdocker-02, bart, gpu"],
+    container: Annotated[str, "Container name"],
+    action: Annotated[str, "Action: restart, stop, or start"],
+) -> str:
+    """Restart, stop, or start a Docker container on a homelab node."""
+    ip = NODES.get(node)
+    if not ip:
+        return f"Unknown node: {node}"
+    if action not in ("restart", "stop", "start"):
+        return f"Invalid action: {action}. Use restart, stop, or start."
+    result = await _ssh_exec(ip, f"docker {action} {container}")
+    return f"{action} {container} on {node}: {'done' if container in result or result == '' else result}"
+
+
+@llm.function_tool
+async def check_logs(
+    node: Annotated[str, "Node name"],
+    container: Annotated[str, "Container name"],
+    lines: Annotated[int, "Number of log lines to return (max 50)"] = 20,
+) -> str:
+    """Get recent logs from a container."""
+    ip = NODES.get(node)
+    if not ip:
+        return f"Unknown node: {node}"
+    lines = min(lines, 50)
+    return await _ssh_exec(ip, f"docker logs --tail {lines} {container} 2>&1")
+
+
+@llm.function_tool
+async def read_alerts() -> str:
+    """Check Prometheus Alertmanager for active alerts."""
+    try:
+        async with httpx.AsyncClient(timeout=5.0) as client:
+            r = await client.get(f"{ALERTMANAGER_URL}/api/v2/alerts?active=true&silenced=false")
+            r.raise_for_status()
+            alerts = r.json()
+        if not alerts:
+            return "No active alerts."
+        parts = []
+        for a in alerts[:10]:
+            name = a.get("labels", {}).get("alertname", "unknown")
+            severity = a.get("labels", {}).get("severity", "")
+            summary = a.get("annotations", {}).get("summary", "")
+            parts.append(f"[{severity}] {name}: {summary}" if summary else f"[{severity}] {name}")
+        return "\n".join(parts)
+    except Exception as e:
+        return f"Could not reach Alertmanager: {e}"
+
+
+@llm.function_tool
+async def home_assistant(
+    action: Annotated[str, "get_states, turn_on, turn_off, or toggle"],
+    entity_id: Annotated[str, "HA entity ID, e.g. light.living_room or 'all' for get_states"] = "all",
+) -> str:
+    """Interact with Home Assistant — check sensor states or control devices."""
+    if not HA_TOKEN:
+        return "HA_TOKEN not configured."
+    headers = {"Authorization": f"Bearer {HA_TOKEN}", "Content-Type": "application/json"}
+    try:
+        async with httpx.AsyncClient(timeout=5.0) as client:
+            if action == "get_states":
+                if entity_id == "all":
+                    r = await client.get(f"{HA_URL}/api/states", headers=headers)
+                    states = r.json()
+                    # Summarize lights/switches/sensors
+                    lights = [s for s in states if s["entity_id"].startswith("light.")]
+                    sensors = [s for s in states if s["entity_id"].startswith("sensor.")]
+                    on_lights = [s["entity_id"].split(".")[1] for s in lights if s["state"] == "on"]
+                    return (
+                        f"{len(lights)} lights ({len(on_lights)} on: {', '.join(on_lights[:5])}), "
+                        f"{len(sensors)} sensors"
+                    )
+                else:
+                    r = await client.get(f"{HA_URL}/api/states/{entity_id}", headers=headers)
+                    s = r.json()
+                    return f"{entity_id}: {s.get('state')} (attrs: {list(s.get('attributes', {}).keys())[:3]})"
+            else:
+                service = action.replace("turn_", "").replace("toggle", "toggle")
+                domain = entity_id.split(".")[0]
+                r = await client.post(
+                    f"{HA_URL}/api/services/{domain}/{action}",
+                    headers=headers,
+                    json={"entity_id": entity_id},
+                )
+                return f"{action} {entity_id}: {'done' if r.status_code in (200, 201) else r.text}"
+    except Exception as e:
+        return f"HA error: {e}"
+
+
+@llm.function_tool
+async def search_web(
+    query: Annotated[str, "Search query"],
+) -> str:
+    """Search the web using the local SearXNG instance."""
+    try:
+        async with httpx.AsyncClient(timeout=8.0) as client:
+            r = await client.get(
+                f"{SEARXNG_URL}/search",
+                params={"q": query, "format": "json", "categories": "general"},
+            )
+            r.raise_for_status()
+            data = r.json()
+        results = data.get("results", [])[:4]
+        if not results:
+            return "No results found."
+        parts = []
+        for res in results:
+            title = res.get("title", "")
+            content = res.get("content", "")[:150]
+            parts.append(f"• {title}: {content}")
+        return "\n".join(parts)
+    except Exception as e:
+        return f"Search failed: {e}"
+
+
+ALL_TOOLS = [infra_status, container_action, check_logs, read_alerts, home_assistant, search_web]
@@ -0,0 +1,110 @@
+"""Async vocal analysis — runs background, never blocks TTS path."""
+import asyncio
+import io
+import logging
+import math
+import struct
+import wave
+from dataclasses import dataclass
+from typing import Callable, Optional
+
+import httpx
+
+logger = logging.getLogger(__name__)
+
+SPEECHBRAIN_URL = "http://speechbrain-service:8001"
+
+
+@dataclass
+class VocalState:
+    emotion: str = "neutral"
+    confidence: float = 0.0
+    energy: float = 0.0
+    pitch_hz: Optional[float] = None
+    rate: float = 0.0
+
+    def to_tag(self) -> str:
+        parts = [f"emotion={self.emotion}", f"energy={self.energy:.2f}"]
+        if self.pitch_hz:
+            parts.append(f"pitch={self.pitch_hz:.0f}hz")
+        if self.rate:
+            parts.append(f"rate={'fast' if self.rate > 3 else 'slow' if self.rate < 1.5 else 'normal'}")
+        return f"[VOCAL {' '.join(parts)}]"
+
+
+def compute_energy(audio_bytes: bytes) -> float:
+    if len(audio_bytes) < 2:
+        return 0.0
+    samples = struct.unpack_from("<" + "h" * (len(audio_bytes) // 2), audio_bytes)
+    rms = math.sqrt(sum(x * x for x in samples) / len(samples)) / 32768.0
+    return round(min(rms * 10, 1.0), 3)
+
+
+async def analyze_audio(audio_bytes: bytes) -> VocalState:
+    """Call SpeechBrain for emotion/pitch. Falls back to energy-only if unavailable."""
+    energy = compute_energy(audio_bytes)
+    state = VocalState(energy=energy)
+
+    try:
+        buf = io.BytesIO()
+        with wave.open(buf, "wb") as wf:
+            wf.setnchannels(1)
+            wf.setsampwidth(2)
+            wf.setframerate(16000)
+            wf.writeframes(audio_bytes)
+        wav_bytes = buf.getvalue()
+
+        async with httpx.AsyncClient(timeout=3.0) as client:
+            r = await client.post(
+                f"{SPEECHBRAIN_URL}/analyze",
+                files={"audio": ("u.wav", wav_bytes, "audio/wav")},
+            )
+            r.raise_for_status()
+            d = r.json()
+            state.emotion = d.get("emotion", "neutral")
+            state.confidence = d.get("emotion_confidence", 0.0)
+            state.pitch_hz = d.get("pitch_mean_hz")
+            state.rate = d.get("speaking_rate_approx", 0.0)
+    except Exception as e:
+        logger.debug("SpeechBrain unavailable, using energy-only: %s", e)
+
+    return state
+
+
+class VocalAnalyzer:
+    """Holds the last completed vocal state; updates async after each utterance."""
+
+    def __init__(self, on_update: Optional[Callable[[VocalState], None]] = None):
+        self._state = VocalState()
+        self._on_update = on_update
+        self._audio_buffer: list[bytes] = []
+        self._collecting = False
+
+    @property
+    def current(self) -> VocalState:
+        return self._state
+
+    def start_collecting(self):
+        self._collecting = True
+        self._audio_buffer = []
+
+    def feed(self, audio_chunk: bytes):
+        if self._collecting:
+            self._audio_buffer.append(audio_chunk)
+
+    def stop_collecting_and_analyze(self) -> asyncio.Task:
+        self._collecting = False
+        audio = b"".join(self._audio_buffer)
+        self._audio_buffer = []
+        return asyncio.create_task(self._analyze_bg(audio))
+
+    async def _analyze_bg(self, audio_bytes: bytes):
+        if not audio_bytes:
+            return
+        try:
+            state = await analyze_audio(audio_bytes)
+            self._state = state
+            if self._on_update:
+                self._on_update(state)
+        except Exception as e:
+            logger.warning("Vocal analysis failed: %s", e)
@@ -1,6 +1,58 @@
 services:

-  # LiveKit WebRTC Server (unchanged)
+  # livekit-agents 1.5 worker + token/API server
+  voicecoach-agent:
+    build:
+      context: ./agent
+    image: voicecoach-agent:latest
+    container_name: voicecoach-agent
+    restart: unless-stopped
+    env_file: .env
+    environment:
+      - LIVEKIT_URL=ws://voicecoach-livekit:7880
+      - LIVEKIT_PUBLIC_URL=wss://voice.hobbs.farm
+      - SPEACHES_URL=http://192.168.86.27:8000
+      - OPENCLAW_URL=http://voicecoach-openclaw:3100
+      - DB_PATH=/data/sessions.db
+      - KOKORO_VOICE=af_nova
+    volumes:
+      - /mnt/docker-data/configs/voicecoach/sessions:/data
+    networks:
+      - voicecoach
+      - voicecoach_v1
+    mem_limit: 1G
+    memswap_limit: 1G
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  # SvelteKit web client
+  voicecoach-web:
+    build:
+      context: ./web-client
+    image: voicecoach-web-v2:latest
+    container_name: voicecoach-web-v2
+    restart: unless-stopped
+    ports:
+      - "8085:80"
+    depends_on:
+      - voicecoach-agent
+    networks:
+      - voicecoach
+    mem_limit: 128M
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  # LiveKit server — unchanged from v1
  livekit-server:
    image: livekit/livekit-server:latest
    container_name: voicecoach-livekit
@@ -16,7 +68,6 @@ services:
      - "50000-50100:50000-50100/udp"
    volumes:
      - ./livekit/livekit.yaml:/etc/livekit/livekit.yaml:ro
-    dns_search: [""]
    networks:
      - voicecoach
    mem_limit: 512M
@@ -28,66 +79,7 @@ services:
        max-size: "50m"
        max-file: "3"

-  # Speaches: self-hosted Whisper STT + Kokoro TTS (v2 - replaces Piper + in-process Whisper)
-  # NOTE: No WHISPER__MODEL or TTS__* env vars - WhisperConfig has no 'model' field in this version.
-  # Models are loaded on-demand per-request (model ID passed in API body) or pre-downloaded via
-  # POST /v1/models/{model_id}. TTS model/voice are also per-request in POST /v1/audio/speech body.
-  # Volume must map to /home/ubuntu/.cache (container runs as 'ubuntu', not root).
-  speaches:
-    image: ghcr.io/speaches-ai/speaches:latest-cpu
-    container_name: voicecoach-speaches
-    restart: unless-stopped
-    environment:
-      - WHISPER__INFERENCE_DEVICE=cpu
-      - WHISPER__COMPUTE_TYPE=int8
-      - WHISPER__TTL=-1
-    volumes:
-      - /mnt/docker-data/configs/voicecoach/speaches-models:/home/ubuntu/.cache
-    dns_search: [""]
-    networks:
-      - voicecoach
-    mem_limit: 3G
-    memswap_limit: 3G
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    healthcheck:
-      test: ["CMD", "curl", "-sf", "http://localhost:8000/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 120s
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
-
-  # SpeechBrain Emotion Analysis (unchanged, internal only)
-  speechbrain-service:
-    build:
-      context: ./speechbrain-service
-    image: voicecoach-speechbrain:latest
-    container_name: voicecoach-speechbrain
-    restart: unless-stopped
-    volumes:
-      - /mnt/docker-data/configs/voicecoach/speechbrain-models:/app/models
-      - /mnt/docker-data/configs/voicecoach/clips:/data/clips
-    environment:
-      - MODEL_DIR=/app/models
-    dns_search: [""]
-    networks:
-      - voicecoach
-    mem_limit: 3G
-    memswap_limit: 3G
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "50m"
-        max-file: "3"
-
-  # OpenClaw VoiceCoach Agent (v2 - LLM gateway with memory/skills)
+  # OpenClaw — LLM gateway with memory and tools
  voicecoach-openclaw:
    image: margaret-openclaw:latest
    container_name: voicecoach-openclaw
@@ -105,7 +97,6 @@ services:
    volumes:
      - /mnt/infrastructure/voicecoach:/home/glyptic/.voicecoach
    command: ["sh", "-c", "mkdir -p /home/glyptic && node --max-old-space-size=1500 /usr/local/lib/node_modules/openclaw/dist/index.js gateway --allow-unconfigured"]
-    dns_search: [""]
    networks:
      - voicecoach
    mem_limit: 2G
@@ -118,36 +109,21 @@ services:
        max-size: "50m"
        max-file: "3"

-  # Pipecat Voice Pipeline Agent (v2 - uses Speaches + OpenClaw gateway)
-  pipecat-agent:
+  # SpeechBrain — async vocal/emotion analysis (optional, agent falls back gracefully)
+  speechbrain-service:
    build:
-      context: ./pipecat-agent
-    image: voicecoach-pipecat:latest
-    container_name: voicecoach-pipecat
+      context: ./speechbrain-service
+    image: voicecoach-speechbrain:latest
+    container_name: voicecoach-speechbrain
    restart: unless-stopped
-    env_file:
-      - .env
-    environment:
-      - LIVEKIT_URL=ws://livekit-server:7880
-      - LIVEKIT_PUBLIC_URL=wss://voice.hobbs.farm
-      - SPEACHES_URL=http://192.168.86.150:8000
-      - SPEECHBRAIN_URL=http://speechbrain-service:8001
-      - OPENCLAW_URL=http://voicecoach-openclaw:3100
-      - OPENCLAW_AGENT_ID=voicecoach
-      - WHISPER_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
-      - KOKORO_VOICE=af_nova
-      - CLIPS_DIR=/data/clips/pending
    volumes:
-      - /mnt/docker-data/configs/voicecoach/clips:/data/clips
-    depends_on:
-      - livekit-server
-      - speechbrain-service
-      - voicecoach-openclaw
-    dns_search: [""]
+      - /mnt/docker-data/configs/voicecoach/speechbrain-models:/app/models
+    environment:
+      - MODEL_DIR=/app/models
    networks:
      - voicecoach
-    mem_limit: 1G
-    memswap_limit: 1G
+    mem_limit: 3G
+    memswap_limit: 3G
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    logging:
@@ -156,29 +132,10 @@ services:
        max-size: "50m"
        max-file: "3"

-  # Web Client (unchanged)
-  voicecoach-web:
-    build:
-      context: ./web-client
-    image: voicecoach-web:latest
-    container_name: voicecoach-web
-    restart: unless-stopped
-    ports:
-      - "8085:80"
-    depends_on:
-      - pipecat-agent
-    dns_search: [""]
-    networks:
-      - voicecoach
-    mem_limit: 128M
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    logging:
-      driver: "json-file"
-      options:
-        max-size: "10m"
-        max-file: "3"
-
 networks:
  voicecoach:
    driver: bridge
+  # Join the v1 voicecoach network to reach the shared livekit + openclaw containers
+  voicecoach_v1:
+    external: true
+    name: voicecoach_voicecoach
@@ -2,7 +2,7 @@ port: 7880
 rtc:
  tcp_port: 7881
  port_range_start: 50000
-  port_range_end: 60000
+  port_range_end: 50100
  use_external_ip: true

 logging:
@@ -0,0 +1,11 @@
+FROM node:20-alpine AS build
+WORKDIR /app
+COPY package.json .
+RUN npm install --legacy-peer-deps
+COPY . .
+RUN npm run build
+
+FROM nginx:alpine
+COPY --from=build /app/build /usr/share/nginx/html
+COPY nginx.conf /etc/nginx/conf.d/default.conf
+EXPOSE 80
@@ -3,10 +3,11 @@ server {
    root /usr/share/nginx/html;
    index index.html;

+    # Proxy API calls to the agent's FastAPI server
    location /api/ {
-        proxy_pass http://pipecat-agent:8080/;
-        proxy_http_version 1.1;
+        proxy_pass http://voicecoach-agent:8080/api/;
        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
    }

    location / {
@@ -0,0 +1,21 @@
+{
+  "name": "voicecoach-v2-web",
+  "version": "2.0.0",
+  "private": true,
+  "scripts": {
+    "dev": "vite dev",
+    "build": "vite build",
+    "preview": "vite preview"
+  },
+  "type": "module",
+  "devDependencies": {
+    "@sveltejs/adapter-static": "^3.0.0",
+    "@sveltejs/kit": "^2.0.0",
+    "@sveltejs/vite-plugin-svelte": "^3.0.0",
+    "svelte": "^5.0.0",
+    "vite": "^5.0.0"
+  },
+  "dependencies": {
+    "livekit-client": "^2.5.0"
+  }
+}
@@ -0,0 +1,40 @@
+*, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
+
+:root {
+  --bg: #0f1117;
+  --surface: #1a1d27;
+  --surface2: #22263a;
+  --accent: #6c63ff;
+  --accent2: #4ecdc4;
+  --text: #e8eaf0;
+  --muted: #7b8094;
+  --danger: #ff5252;
+  --success: #4caf50;
+  --warn: #ffc107;
+  --radius: 12px;
+  --font: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
+}
+
+html, body { height: 100%; background: var(--bg); color: var(--text); font-family: var(--font); }
+
+button {
+  cursor: pointer;
+  border: none;
+  font-family: inherit;
+  font-size: 0.875rem;
+  font-weight: 500;
+  border-radius: var(--radius);
+  padding: 0.5rem 1.2rem;
+  transition: opacity 0.15s, transform 0.1s;
+}
+button:active { transform: scale(0.97); }
+button:disabled { opacity: 0.4; cursor: default; }
+
+.btn-primary { background: var(--accent); color: #fff; }
+.btn-primary:hover:not(:disabled) { opacity: 0.85; }
+.btn-danger  { background: var(--danger); color: #fff; }
+.btn-ghost   { background: var(--surface2); color: var(--text); }
+.btn-ghost:hover:not(:disabled) { background: #2d3147; }
+
+a { color: var(--accent2); text-decoration: none; }
+a:hover { text-decoration: underline; }
@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1" />
+    <title>VoiceCoach</title>
+    %sveltekit.head%
+  </head>
+  <body>
+    <div>%sveltekit.body%</div>
+  </body>
+</html>
@@ -0,0 +1,66 @@
+import { Room, RoomEvent, Track } from 'livekit-client';
+
+const LIVEKIT_URL = 'wss://voice.hobbs.farm';
+const API_BASE = '/api';
+
+export let room = null;
+
+export async function connect(identity, onEvent) {
+  const res = await fetch(`${API_BASE}/token`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ identity: identity || `jeremy-${Date.now()}` }),
+  });
+  if (!res.ok) throw new Error(`Token fetch failed: ${res.status}`);
+  const { token, url } = await res.json();
+
+  room = new Room({
+    audioCaptureDefaults: {
+      echoCancellation: true,
+      noiseSuppression: true,
+      autoGainControl: true,
+    },
+  });
+
+  room.on(RoomEvent.Connected, () => onEvent({ type: 'connected' }));
+  room.on(RoomEvent.Disconnected, (reason) => onEvent({ type: 'disconnected', reason }));
+  room.on(RoomEvent.ParticipantConnected, (p) => onEvent({ type: 'participant_joined', identity: p.identity }));
+  room.on(RoomEvent.ParticipantDisconnected, (p) => onEvent({ type: 'participant_left', identity: p.identity }));
+
+  room.on(RoomEvent.TrackSubscribed, (track, _pub, participant) => {
+    if (track.kind === Track.Kind.Audio) {
+      const el = track.attach();
+      el.autoplay = true;
+      document.body.appendChild(el);
+      onEvent({ type: 'audio_attached', identity: participant.identity });
+    }
+  });
+
+  room.on(RoomEvent.TrackUnsubscribed, (track) => {
+    track.detach().forEach(el => el.remove());
+  });
+
+  room.on(RoomEvent.DataReceived, (payload, participant) => {
+    try {
+      const msg = JSON.parse(new TextDecoder().decode(payload));
+      onEvent(msg);
+    } catch (_) {}
+  });
+
+  await room.connect(url || LIVEKIT_URL, token);
+  await room.localParticipant.setMicrophoneEnabled(true);
+  return room;
+}
+
+export async function disconnect() {
+  if (room) {
+    await room.disconnect();
+    room = null;
+  }
+}
+
+export function sendData(payload) {
+  if (!room?.localParticipant) return;
+  const data = new TextEncoder().encode(JSON.stringify(payload));
+  room.localParticipant.publishData(data, { reliable: true });
+}
@@ -0,0 +1,2 @@
+export const prerender = false;
+export const ssr = false;
@@ -0,0 +1,6 @@
+<script>
+  import '../app.css';
+  let { children } = $props();
+</script>
+
+{@render children()}
@@ -0,0 +1,328 @@
+<script>
+  import { connect, disconnect, sendData } from '$lib/livekit.js';
+  import { onDestroy } from 'svelte';
+
+  let status = 'disconnected'; // disconnected | connecting | connected
+  let mode = 'coaching';
+  let transcript = [];    // {role, text, partial, id}
+  let tools = [];         // {action, detail, result, done}
+  let vocal = null;       // {energy, emotion, pitch_hz}
+  let error = '';
+  let nextId = 0;
+
+  const MODES = ['coaching', 'vent', 'practice', 'briefing'];
+
+  function handleEvent(ev) {
+    switch (ev.type) {
+      case 'connected':
+        status = 'connected';
+        error = '';
+        break;
+      case 'disconnected':
+        status = 'disconnected';
+        break;
+      case 'partial_transcript':
+        if (ev.speaker === 'user') {
+          const last = transcript[transcript.length - 1];
+          if (last && last.partial && last.role === 'user') {
+            transcript[transcript.length - 1] = { ...last, text: ev.text };
+          } else {
+            transcript = [...transcript, { role: 'user', text: ev.text, partial: true, id: nextId++ }];
+          }
+        }
+        break;
+      case 'final_transcript':
+        if (ev.speaker === 'user') {
+          // Replace last partial or add new
+          const lastIdx = transcript.findLastIndex(t => t.partial && t.role === 'user');
+          if (lastIdx >= 0) {
+            transcript = transcript.map((t, i) =>
+              i === lastIdx ? { ...t, text: ev.text, partial: false } : t
+            );
+          } else {
+            transcript = [...transcript, { role: 'user', text: ev.text, partial: false, id: nextId++ }];
+          }
+        }
+        break;
+      case 'agent_response':
+        transcript = [...transcript, { role: 'assistant', text: ev.text, partial: false, id: nextId++ }];
+        break;
+      case 'tool_start':
+        tools = [...tools, { action: ev.action, detail: ev.detail || '', result: '', done: false, id: nextId++ }];
+        break;
+      case 'tool_complete':
+        tools = tools.map(t =>
+          !t.done && t.action === ev.action ? { ...t, result: ev.result, done: true } : t
+        );
+        break;
+      case 'vocal_state':
+        vocal = { energy: ev.energy, emotion: ev.emotion, pitch_hz: ev.pitch_hz };
+        break;
+      case 'mode_ack':
+        mode = ev.mode;
+        break;
+    }
+  }
+
+  async function startSession() {
+    status = 'connecting';
+    error = '';
+    transcript = [];
+    tools = [];
+    try {
+      await connect(null, handleEvent);
+    } catch (e) {
+      status = 'disconnected';
+      error = e.message;
+    }
+  }
+
+  async function endSession() {
+    await disconnect();
+    status = 'disconnected';
+  }
+
+  function setMode(m) {
+    mode = m;
+    sendData({ type: 'mode_change', mode: m });
+  }
+
+  onDestroy(() => disconnect());
+
+  $: energyPct = vocal ? Math.round(vocal.energy * 100) : 0;
+  $: vadRing = status === 'connected' && vocal && vocal.energy > 0.1;
+</script>
+
+<main>
+  <header>
+    <div class="logo">
+      <div class="logo-dot" class:connected={status === 'connected'} class:connecting={status === 'connecting'}></div>
+      <span>VoiceCoach</span>
+    </div>
+    <nav>
+      <a href="/history">History</a>
+    </nav>
+  </header>
+
+  <div class="content">
+    <!-- Mode bar -->
+    <div class="mode-bar" class:disabled={status !== 'connected'}>
+      {#each MODES as m}
+        <button
+          class="mode-chip"
+          class:active={mode === m}
+          disabled={status !== 'connected'}
+          on:click={() => setMode(m)}
+        >{m}</button>
+      {/each}
+    </div>
+
+    <!-- Transcript -->
+    <div class="transcript" id="transcript-scroll">
+      {#if transcript.length === 0 && status === 'disconnected'}
+        <p class="hint">Press Start to connect your voice.</p>
+      {:else if transcript.length === 0 && status !== 'disconnected'}
+        <p class="hint">Listening…</p>
+      {/if}
+      {#each transcript as msg (msg.id)}
+        <div class="msg msg-{msg.role}" class:partial={msg.partial}>
+          <span class="msg-label">{msg.role === 'user' ? 'You' : 'Assistant'}</span>
+          <span class="msg-text">{msg.text}</span>
+        </div>
+      {/each}
+    </div>
+
+    <!-- Tool activity feed -->
+    {#if tools.length > 0}
+      <div class="tool-feed">
+        {#each tools.slice(-5) as t (t.id)}
+          <div class="tool-item" class:done={t.done}>
+            <span class="tool-icon">{t.done ? '✓' : '⚙'}</span>
+            <span class="tool-text">{t.action}{t.detail ? ` — ${t.detail}` : ''}</span>
+          </div>
+        {/each}
+      </div>
+    {/if}
+
+    <!-- Vocal meter -->
+    {#if status === 'connected'}
+      <div class="vocal-row">
+        <div class="energy-bar">
+          <div class="energy-fill" style="width: {energyPct}%"></div>
+        </div>
+        {#if vocal && vocal.emotion && vocal.emotion !== 'neutral'}
+          <span class="emotion-tag">{vocal.emotion}</span>
+        {/if}
+      </div>
+    {/if}
+
+    <!-- Error -->
+    {#if error}
+      <p class="error">{error}</p>
+    {/if}
+
+    <!-- Controls -->
+    <div class="controls">
+      {#if status === 'disconnected'}
+        <button class="btn-primary big-btn" on:click={startSession}>Start Session</button>
+      {:else if status === 'connecting'}
+        <button class="btn-ghost big-btn" disabled>Connecting…</button>
+      {:else}
+        <button class="btn-danger big-btn" on:click={endSession}>End Session</button>
+      {/if}
+    </div>
+  </div>
+
+  <!-- VAD ring -->
+  {#if vadRing}
+    <div class="vad-ring" style="opacity: {Math.min(vocal.energy * 3, 1)}"></div>
+  {/if}
+</main>
+
+<style>
+  main {
+    min-height: 100dvh;
+    display: flex;
+    flex-direction: column;
+    max-width: 680px;
+    margin: 0 auto;
+    padding: 0 1rem;
+    position: relative;
+  }
+
+  header {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 1rem 0;
+    border-bottom: 1px solid #2a2d3e;
+  }
+
+  .logo { display: flex; align-items: center; gap: 0.5rem; font-weight: 600; font-size: 1.1rem; }
+
+  .logo-dot {
+    width: 10px; height: 10px;
+    border-radius: 50%;
+    background: var(--muted);
+    transition: background 0.3s;
+  }
+  .logo-dot.connecting { background: var(--warn); animation: pulse 1s infinite; }
+  .logo-dot.connected  { background: var(--success); }
+
+  nav a { font-size: 0.875rem; color: var(--muted); }
+
+  .content { flex: 1; display: flex; flex-direction: column; padding: 1rem 0; gap: 1rem; }
+
+  .mode-bar {
+    display: flex; gap: 0.5rem; flex-wrap: wrap;
+  }
+  .mode-bar.disabled { opacity: 0.5; }
+
+  .mode-chip {
+    padding: 0.35rem 0.9rem;
+    border-radius: 999px;
+    background: var(--surface2);
+    color: var(--muted);
+    font-size: 0.8rem;
+    text-transform: capitalize;
+    border: 1px solid transparent;
+  }
+  .mode-chip.active {
+    background: var(--accent);
+    color: #fff;
+    border-color: var(--accent);
+  }
+
+  .transcript {
+    flex: 1;
+    min-height: 300px;
+    background: var(--surface);
+    border-radius: var(--radius);
+    padding: 1rem;
+    overflow-y: auto;
+    display: flex;
+    flex-direction: column;
+    gap: 0.75rem;
+  }
+
+  .hint { color: var(--muted); font-size: 0.875rem; text-align: center; margin: auto; }
+
+  .msg { display: flex; flex-direction: column; gap: 0.15rem; }
+
+  .msg-label {
+    font-size: 0.7rem;
+    font-weight: 600;
+    text-transform: uppercase;
+    letter-spacing: 0.05em;
+    color: var(--muted);
+  }
+
+  .msg-user .msg-label  { color: var(--accent2); }
+  .msg-assistant .msg-label { color: var(--accent); }
+
+  .msg-text { font-size: 0.95rem; line-height: 1.5; }
+  .msg.partial .msg-text { opacity: 0.6; font-style: italic; }
+
+  .tool-feed {
+    background: var(--surface);
+    border-radius: var(--radius);
+    padding: 0.75rem 1rem;
+    display: flex;
+    flex-direction: column;
+    gap: 0.3rem;
+  }
+
+  .tool-item {
+    display: flex; align-items: center; gap: 0.5rem;
+    font-size: 0.8rem; color: var(--muted);
+  }
+  .tool-item.done { color: var(--success); }
+  .tool-icon { font-size: 0.9rem; }
+
+  .vocal-row {
+    display: flex; align-items: center; gap: 0.75rem;
+  }
+
+  .energy-bar {
+    flex: 1; height: 6px; border-radius: 3px;
+    background: var(--surface2); overflow: hidden;
+  }
+  .energy-fill {
+    height: 100%; border-radius: 3px;
+    background: linear-gradient(90deg, var(--accent2), var(--accent));
+    transition: width 0.2s;
+  }
+
+  .emotion-tag {
+    font-size: 0.75rem; color: var(--muted);
+    background: var(--surface2);
+    padding: 0.2rem 0.5rem;
+    border-radius: 999px;
+    text-transform: capitalize;
+  }
+
+  .error { color: var(--danger); font-size: 0.85rem; }
+
+  .controls { display: flex; justify-content: center; padding-bottom: 1.5rem; }
+
+  .big-btn {
+    width: 100%; max-width: 320px; padding: 0.85rem;
+    font-size: 1rem; border-radius: var(--radius);
+  }
+
+  .vad-ring {
+    position: fixed; inset: 0; pointer-events: none;
+    border: 3px solid var(--accent2);
+    border-radius: inherit;
+    transition: opacity 0.1s;
+  }
+
+  @keyframes pulse {
+    0%, 100% { opacity: 1; }
+    50% { opacity: 0.4; }
+  }
+
+  @media (max-width: 480px) {
+    .big-btn { max-width: 100%; }
+  }
+</style>
@@ -0,0 +1,164 @@
+<script>
+  import { onMount } from 'svelte';
+
+  let sessions = [];
+  let expanded = null;
+  let messages = {};
+  let loading = true;
+
+  onMount(async () => {
+    try {
+      const res = await fetch('/api/sessions?limit=30');
+      sessions = await res.json();
+    } catch (e) {
+      console.error(e);
+    } finally {
+      loading = false;
+    }
+  });
+
+  async function toggleSession(id) {
+    if (expanded === id) { expanded = null; return; }
+    expanded = id;
+    if (!messages[id]) {
+      const res = await fetch(`/api/sessions/${id}/messages`);
+      messages[id] = await res.json();
+    }
+  }
+
+  function fmt(ts) {
+    if (!ts) return '';
+    return new Date(ts * 1000).toLocaleString();
+  }
+
+  function duration(s) {
+    if (!s.ended_at || !s.started_at) return '';
+    const mins = Math.round((s.ended_at - s.started_at) / 60);
+    return mins < 1 ? '<1m' : `${mins}m`;
+  }
+</script>
+
+<main>
+  <header>
+    <a href="/" class="back">← Back</a>
+    <h1>Session History</h1>
+  </header>
+
+  {#if loading}
+    <p class="hint">Loading…</p>
+  {:else if sessions.length === 0}
+    <p class="hint">No sessions yet.</p>
+  {:else}
+    <div class="session-list">
+      {#each sessions as s}
+        <div class="session-card" class:open={expanded === s.id}>
+          <button class="session-header" on:click={() => toggleSession(s.id)}>
+            <div class="session-meta">
+              <span class="session-date">{fmt(s.started_at)}</span>
+              <span class="session-chips">
+                <span class="chip mode-chip">{s.mode || 'coaching'}</span>
+                {#if duration(s)}
+                  <span class="chip">{duration(s)}</span>
+                {/if}
+              </span>
+            </div>
+            {#if s.summary}
+              <p class="session-summary">{s.summary}</p>
+            {/if}
+            <span class="toggle-icon">{expanded === s.id ? '▲' : '▼'}</span>
+          </button>
+
+          {#if expanded === s.id && messages[s.id]}
+            <div class="transcript">
+              {#each messages[s.id] as msg}
+                <div class="msg msg-{msg.role}">
+                  <span class="msg-label">
+                    {msg.role === 'user' ? 'You' : 'Assistant'}
+                    {#if msg.vocal_emotion && msg.vocal_emotion !== 'neutral'}
+                      <span class="vocal-badge">{msg.vocal_emotion}</span>
+                    {/if}
+                  </span>
+                  <span class="msg-text">{msg.content}</span>
+                </div>
+              {/each}
+            </div>
+          {/if}
+        </div>
+      {/each}
+    </div>
+  {/if}
+</main>
+
+<style>
+  main {
+    max-width: 680px; margin: 0 auto; padding: 1rem;
+    min-height: 100dvh;
+  }
+
+  header {
+    display: flex; align-items: center; gap: 1rem;
+    padding: 1rem 0; border-bottom: 1px solid #2a2d3e; margin-bottom: 1rem;
+  }
+  header h1 { font-size: 1.1rem; font-weight: 600; }
+  .back { font-size: 0.875rem; color: var(--muted); }
+
+  .hint { color: var(--muted); text-align: center; padding: 2rem; }
+
+  .session-list { display: flex; flex-direction: column; gap: 0.75rem; }
+
+  .session-card {
+    background: var(--surface);
+    border-radius: var(--radius);
+    overflow: hidden;
+    border: 1px solid transparent;
+    transition: border-color 0.2s;
+  }
+  .session-card.open { border-color: var(--accent); }
+
+  .session-header {
+    width: 100%; text-align: left;
+    background: none; padding: 1rem;
+    display: flex; flex-direction: column; gap: 0.4rem;
+    border-radius: 0; color: var(--text);
+    position: relative;
+  }
+
+  .session-meta { display: flex; align-items: center; gap: 0.5rem; flex-wrap: wrap; }
+  .session-date { font-size: 0.8rem; color: var(--muted); }
+
+  .session-chips { display: flex; gap: 0.35rem; }
+  .chip {
+    font-size: 0.7rem; padding: 0.15rem 0.5rem;
+    border-radius: 999px; background: var(--surface2); color: var(--muted);
+  }
+  .mode-chip { color: var(--accent2); }
+
+  .session-summary { font-size: 0.85rem; color: var(--text); line-height: 1.4; }
+
+  .toggle-icon {
+    position: absolute; right: 1rem; top: 1rem;
+    font-size: 0.7rem; color: var(--muted);
+  }
+
+  .transcript {
+    padding: 1rem; border-top: 1px solid #2a2d3e;
+    display: flex; flex-direction: column; gap: 0.75rem;
+  }
+
+  .msg { display: flex; flex-direction: column; gap: 0.1rem; }
+  .msg-label {
+    font-size: 0.7rem; font-weight: 600; text-transform: uppercase;
+    letter-spacing: 0.05em; color: var(--muted);
+    display: flex; align-items: center; gap: 0.4rem;
+  }
+  .msg-user .msg-label { color: var(--accent2); }
+  .msg-assistant .msg-label { color: var(--accent); }
+  .msg-text { font-size: 0.9rem; line-height: 1.5; }
+
+  .vocal-badge {
+    font-size: 0.65rem; background: var(--surface2);
+    padding: 0.1rem 0.4rem; border-radius: 999px;
+    text-transform: capitalize; color: var(--muted);
+    font-weight: 400; letter-spacing: 0;
+  }
+</style>
@@ -0,0 +1,7 @@
+import adapter from '@sveltejs/adapter-static';
+
+export default {
+  kit: {
+    adapter: adapter({ fallback: 'index.html' }),
+  },
+};
@@ -0,0 +1,8 @@
+import { sveltekit } from '@sveltejs/kit/vite'
+
+/** @type {import('vite').UserConfig} */
+const config = {
+  plugins: [sveltekit()]
+}
+
+export default config
@@ -1,9 +0,0 @@
-# VoiceCoach Environment Variables
-# Copy to .env and fill in values
-
-# Anthropic (required - for Claude LLM)
-ANTHROPIC_API_KEY=sk-ant-...
-
-# LiveKit (auto-generated on first deploy if not set)
-LIVEKIT_API_KEY=voicecoach-key
-LIVEKIT_API_SECRET=your-livekit-secret-here
@@ -1,63 +0,0 @@
-You are VoiceCoach, a personal communication and leadership coach for Jeremy.
-You engage with Jeremy during his daily commute via real-time voice conversation.
-
-## Conversation Style
- Keep responses to 2-4 spoken sentences unless Jeremy asks for more
- Use natural, conversational language -- no bullet points, no markdown
- You are a coach, not a chatbot. Ask questions. Challenge thinking. Give direct feedback.
-
-## Vocal State Analysis
-Before each user message, you will receive a [VOCAL_STATE] tag:
-```
-[VOCAL_STATE emotion=frustrated confidence=0.82 pitch=215hz energy=0.71 rate=4.8ops voiced=0.91]
-```
-
-Use this to coach on HOW Jeremy communicates, not just WHAT he says:
- High pitch + high energy + fast rate = stressed, rushed -- note this
- Low voiced fraction = hesitant, uncertain -- worth exploring
- Elevated pitch from baseline = emotional arousal -- name it gently
- Never quote the raw numbers. Translate to natural observations.
- Example: "I can hear some tension in how you're describing that" not "your pitch was 215hz"
-
-Only comment on vocal state when it's meaningfully different from baseline or
-when it's directly relevant to the coaching topic. Don't narrate every turn.
-
-## Coaching Modes
-Jeremy can switch modes mid-conversation. Honor the switch immediately.
-
-**coaching mode** (default): Active feedback on both content and delivery.
-  Ask probing questions. Notice patterns. Give direct recommendations.
-
-**vent mode**: Listen and reflect. Minimal advice. Validate feelings.
-  Mirror back what you hear. Let Jeremy process out loud.
-
-**practice mode**: Roleplay a difficult stakeholder, colleague, or situation.
-  Stay in character. Be realistic -- not easy. Give feedback after.
-
-**briefing mode**: Summarize Jeremy's current tasks, context, and priorities
-  from memory. Be crisp. Flag anything time-sensitive.
-
-## Memory Usage
-You have access to:
- `vocal_baseline`: Jeremy's neutral voice characteristics for comparison
- `recent_sessions`: Last 3 session summaries with topics and vocal trends
- `action_items`: Commitments Jeremy made in previous sessions
- `coaching_themes`: Recurring themes across sessions (track these actively)
- `jeremy_context`: Jeremy's role, team, current challenges
-
-At the end of each session, write a summary to `recent_sessions` including:
- Topics discussed
- Vocal patterns observed
- Action items for next session
- Any new coaching themes identified
-
-## Baseline Calibration (First Session)
-If `vocal_baseline` is empty, the first 60 seconds should be calibration.
-Say: "Before we dive in, let's do a quick baseline. Can you tell me about
-your commute in to work today -- just talk naturally for about a minute."
-Then write the averaged vocal readings to `vocal_baseline`.
-
-## Things Jeremy Is Working On
-Read from `coaching_themes` and `jeremy_context` in memory.
-Reference previous sessions naturally: "Last week you mentioned..."
-Track whether previous action items were attempted.
@@ -1,31 +0,0 @@
-FROM python:3.11-slim
-
-RUN apt-get update && apt-get install -y libsndfile1 ffmpeg && \
-    rm -rf /var/lib/apt/lists/*
-
-WORKDIR /app
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Patch pipecat LiveKit transport bugs:
-# 1. Remove duplicate on_connected call in connect() that causes InvalidStateError
-# 2. Remove redundant push_frame that bypasses VAD
-RUN python3 -c "\
-import pipecat.transports.services.livekit as m; \
-path = m.__file__; \
-content = open(path).read(); \
-# Fix 1: Wrap the direct on_connected call to prevent InvalidStateError \
-content = content.replace( \
-    'await self._callbacks.on_connected()', \
-    'try:\n                    await self._callbacks.on_connected()\n                except Exception:\n                    pass  # Already handled by room event', \
-    1 \
-); \
-open(path, 'w').write(content); \
-print(f'Patched {path}')"
-
-COPY . .
-
-HEALTHCHECK --interval=30s --timeout=10s --start-period=30s \
-    CMD python -c "import httpx; httpx.get('http://localhost:8080/health').raise_for_status()"
-
-CMD ["python", "main.py"]
@@ -1,113 +0,0 @@
-"""
-VoiceCoach pipeline entry point -- v2.
-Runs token server + restarts pipeline immediately after each session.
-"""
-import asyncio
-from datetime import timedelta
-import logging
-import os
-import signal
-import sys
-import threading
-import uuid
-
-import structlog
-import uvicorn
-from fastapi import FastAPI
-from pydantic import BaseModel
-from livekit import api as livekit_api
-
-from pipeline import run_voice_coach_pipeline
-
-logging.basicConfig(level=logging.INFO)
-logger = structlog.get_logger()
-
-LIVEKIT_API_KEY = os.environ["LIVEKIT_API_KEY"]
-LIVEKIT_API_SECRET = os.environ["LIVEKIT_API_SECRET"]
-LIVEKIT_WS_URL = os.getenv("LIVEKIT_URL", "ws://livekit-server:7880")
-LIVEKIT_PUBLIC_URL = os.getenv("LIVEKIT_PUBLIC_URL", "wss://voice.hobbs.farm")
-OPENCLAW_TOKEN = os.getenv("OPENCLAW_TOKEN", "")
-
-# --- Token HTTP server ---
-
-token_app = FastAPI(title="VoiceCoach Token Service")
-
-
-class TokenRequest(BaseModel):
-    identity: str = "jeremy"
-
-
-class TokenResponse(BaseModel):
-    token: str
-    url: str
-
-
-@token_app.get("/health")
-async def health():
-    return {"status": "ok", "version": "2.0"}
-
-
-@token_app.post("/token")
-async def get_token(req: TokenRequest):
-    token = livekit_api.AccessToken(LIVEKIT_API_KEY, LIVEKIT_API_SECRET)
-    token.with_grants(livekit_api.VideoGrants(
-        room_join=True, room="voicecoach",
-        can_publish=True, can_subscribe=True,
-    ))
-    token.identity = req.identity
-    return TokenResponse(token=token.to_jwt(), url=LIVEKIT_PUBLIC_URL)
-
-
-def run_token_server():
-    uvicorn.run(token_app, host="0.0.0.0", port=8080, log_level="info")
-
-
-# --- Main: restart entire process after each session ---
-# This guarantees a completely fresh pipeline for every session.
-# No stale transport state, no cancelled tasks, no dead queues.
-
-def run_pipeline_sync():
-    """Run one pipeline session, then exit the process.
-    Docker's restart: unless-stopped will bring us back immediately.
-    """
-    agent_identity = f"voicecoach-agent-{uuid.uuid4().hex[:8]}"
-    token = livekit_api.AccessToken(LIVEKIT_API_KEY, LIVEKIT_API_SECRET)
-    token.with_grants(livekit_api.VideoGrants(room_join=True, room="voicecoach"))
-    token.identity = agent_identity
-    token.ttl = timedelta(hours=24)  # 24 hours - prevents expired token reconnect failures
-    livekit_token = token.to_jwt()
-
-    logger.info("Starting VoiceCoach v2 pipeline", identity=agent_identity)
-
-    loop = asyncio.new_event_loop()
-    asyncio.set_event_loop(loop)
-    try:
-        loop.run_until_complete(run_voice_coach_pipeline(
-            livekit_url=LIVEKIT_WS_URL,
-            livekit_token=livekit_token,
-            openclaw_token=OPENCLAW_TOKEN,
-        ))
-    except Exception as e:
-        logger.error("Pipeline ended", error=str(e))
-    finally:
-        loop.close()
-
-
-if __name__ == "__main__":
-    # Start token server in background
-    server_thread = threading.Thread(target=run_token_server, daemon=True)
-    server_thread.start()
-    logger.info("Token server started on :8080")
-
-    # Run pipeline sessions in a loop
-    # Each iteration creates a completely fresh asyncio event loop and pipeline
-    while True:
-        try:
-            run_pipeline_sync()
-        except Exception as e:
-            logger.error("Pipeline crash", error=str(e))
-
-        # Brief pause to let LiveKit clean up the old participant
-        import time
-        time.sleep(3)
-        logger.info("Restarting pipeline with fresh state...")
@@ -1,34 +0,0 @@
-"""
-Piper TTS client for Pipecat pipeline.
-Calls the self-hosted Piper HTTP service.
-"""
-import io
-import logging
-import wave
-import httpx
-
-logger = logging.getLogger(__name__)
-
-
-class PiperTTSClient:
-    """HTTP client for the Piper TTS service."""
-
-    def __init__(self, base_url: str = "http://piper-tts:8003"):
-        self.base_url = base_url.rstrip("/")
-        self._client = httpx.AsyncClient(timeout=10.0)
-
-    async def synthesize(self, text: str) -> bytes:
-        """Convert text to WAV audio bytes via Piper service."""
-        try:
-            response = await self._client.post(
-                f"{self.base_url}/synthesize",
-                json={"text": text, "length_scale": 0.95, "sentence_silence": 0.15},
-            )
-            response.raise_for_status()
-            return response.content
-        except Exception as e:
-            logger.error(f"Piper TTS failed: {e}")
-            return b""
-
-    async def close(self):
-        await self._client.aclose()
@@ -1,76 +0,0 @@
-"""
-Builds Claude prompts with embedded vocal state metadata.
-"""
-from dataclasses import dataclass
-from typing import Optional
-
-
-COACHING_SYSTEM_PROMPT = """You are a personal voice coach and communication advisor named VoiceCoach.
-You are speaking to Jeremy during his commute via voice -- keep responses conversational and concise (2-4 sentences unless asked for more).
-
-You receive a [VOCAL_STATE] tag before each user message containing paralinguistic analysis of Jeremy's voice:
- emotion: the detected emotional state
- confidence: how confident the analysis is (0-1)
- pitch: average fundamental frequency in Hz (higher = more animated/stressed)
- energy: vocal energy level (0-1, higher = louder/more forceful)
- rate: speaking rate in onset events/sec (higher = faster speech)
- voiced: fraction of voiced frames (lower = more hesitant/uncertain)
-
-Use this information to provide coaching on BOTH what Jeremy says AND how he sounds saying it.
-Important: Never quote the raw numbers. Translate them into natural observations.
-Example: "I notice some tension in your voice..." not "Your pitch was 215hz..."
-
-{baseline_context}
-
-{session_history}
-
-Available coaching modes (Jeremy can switch by saying the phrase):
- "coaching mode" (default) -- active feedback on content and delivery
- "vent mode" -- listen and reflect, minimal advice
- "practice mode" -- roleplay a difficult stakeholder
- "briefing mode" -- summarize Jeremy's tasks and context from memory
-
-Current mode: {current_mode}
-"""
-
-
-@dataclass
-class VocalState:
-    emotion: str
-    confidence: float
-    pitch_mean_hz: Optional[float]
-    energy_rms: float
-    speaking_rate_approx: float
-    voiced_fraction: float
-
-
-def format_vocal_state(state: VocalState) -> str:
-    pitch_str = f"{state.pitch_mean_hz:.0f}hz" if state.pitch_mean_hz else "unknown"
-    return (
-        f"[VOCAL_STATE "
-        f"emotion={state.emotion} "
-        f"confidence={state.confidence:.2f} "
-        f"pitch={pitch_str} "
-        f"energy={state.energy_rms:.2f} "
-        f"rate={state.speaking_rate_approx:.1f}ops "
-        f"voiced={state.voiced_fraction:.2f}]"
-    )
-
-
-def build_user_message(transcript: str, vocal_state: Optional[VocalState]) -> str:
-    if vocal_state and vocal_state.confidence > 0.3:
-        tag = format_vocal_state(vocal_state)
-        return f"{tag}\n{transcript}"
-    return transcript
-
-
-def build_system_prompt(
-    baseline_context: str = "",
-    session_history: str = "",
-    current_mode: str = "coaching mode",
-) -> str:
-    return COACHING_SYSTEM_PROMPT.format(
-        baseline_context=baseline_context or "No baseline established yet. First session: ask Jeremy to read a short neutral calibration script.",
-        session_history=session_history or "No previous session history.",
-        current_mode=current_mode,
-    )
@@ -1,35 +0,0 @@
-"""
-Local STT service using faster-whisper.
-Replaces Deepgram with fully self-hosted speech-to-text.
-"""
-import io
-import logging
-import wave
-import numpy as np
-from faster_whisper import WhisperModel
-
-logger = logging.getLogger(__name__)
-
-
-class LocalWhisperSTT:
-    """Wraps faster-whisper for use in the Pipecat pipeline."""
-
-    def __init__(self, model_size: str = "medium", device: str = "cpu", compute_type: str = "int8"):
-        logger.info(f"Loading faster-whisper model: {model_size} on {device}")
-        self.model = WhisperModel(model_size, device=device, compute_type=compute_type)
-        logger.info("faster-whisper model loaded.")
-
-    def transcribe(self, audio_bytes: bytes, sample_rate: int = 16000) -> str:
-        """Transcribe raw PCM audio bytes to text."""
-        audio_array = np.frombuffer(audio_bytes, dtype=np.int16).astype(np.float32) / 32768.0
-
-        segments, info = self.model.transcribe(
-            audio_array,
-            beam_size=5,
-            language="en",
-            vad_filter=True,
-            vad_parameters=dict(min_silence_duration_ms=500),
-        )
-
-        text = " ".join(seg.text.strip() for seg in segments)
-        return text
@@ -1,27 +0,0 @@
-FROM python:3.11-slim
-
-RUN apt-get update && apt-get install -y \
-    libsndfile1 \
-    wget \
-    && rm -rf /var/lib/apt/lists/*
-
-WORKDIR /app
-
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Download Piper voice model at build time from HuggingFace (lessac medium - good quality, fast on CPU)
-RUN mkdir -p /app/models && \
-    wget -q "https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/lessac/medium/en_US-lessac-medium.onnx?download=true" \
-        -O /app/models/en_US-lessac-medium.onnx && \
-    wget -q "https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/lessac/medium/en_US-lessac-medium.onnx.json?download=true" \
-        -O /app/models/en_US-lessac-medium.onnx.json
-
-COPY . .
-
-EXPOSE 8003
-
-HEALTHCHECK --interval=30s --timeout=10s --start-period=30s \
-    CMD python -c "import httpx; httpx.get('http://localhost:8003/health').raise_for_status()"
-
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8003", "--workers", "1"]
@@ -1,72 +0,0 @@
-"""
-Piper TTS HTTP service.
-Self-hosted text-to-speech, internal network only.
-"""
-import io
-import logging
-import os
-import wave
-from contextlib import asynccontextmanager
-
-from fastapi import FastAPI, HTTPException
-from fastapi.responses import Response
-from pydantic import BaseModel
-import piper
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-MODEL_PATH = os.getenv("PIPER_MODEL", "/app/models/en_US-lessac-medium.onnx")
-voice = None
-
-
-@asynccontextmanager
-async def lifespan(app: FastAPI):
-    global voice
-    logger.info(f"Loading Piper model: {MODEL_PATH}")
-    voice = piper.PiperVoice.load(MODEL_PATH)
-    logger.info("Piper TTS ready.")
-    yield
-    logger.info("Shutting down.")
-
-
-app = FastAPI(title="Piper TTS Service", lifespan=lifespan)
-
-
-class TTSRequest(BaseModel):
-    text: str
-    speaker_id: int = None
-    length_scale: float = 1.0
-    sentence_silence: float = 0.2
-
-
-@app.get("/health")
-async def health():
-    if voice is None:
-        raise HTTPException(status_code=503, detail="Model not loaded")
-    return {"status": "ok", "model": os.path.basename(MODEL_PATH)}
-
-
-@app.post("/synthesize")
-async def synthesize(req: TTSRequest):
-    if voice is None:
-        raise HTTPException(status_code=503, detail="Model not loaded")
-
-    if not req.text.strip():
-        raise HTTPException(status_code=400, detail="Empty text")
-
-    buf = io.BytesIO()
-    with wave.open(buf, "wb") as wf:
-        synth_kwargs = {
-            "length_scale": req.length_scale,
-            "sentence_silence": req.sentence_silence,
-        }
-        if req.speaker_id is not None:
-            synth_kwargs["speaker_id"] = req.speaker_id
-        voice.synthesize(req.text, wf, **synth_kwargs)
-
-    return Response(
-        content=buf.getvalue(),
-        media_type="audio/wav",
-        headers={"Content-Disposition": "inline; filename=speech.wav"},
-    )
@@ -1,5 +0,0 @@
-fastapi==0.115.0
-uvicorn[standard]==0.30.0
-piper-tts==1.2.0
-httpx==0.27.0
-numpy==1.26.4
@@ -1,33 +0,0 @@
-FROM python:3.11-slim
-
-RUN apt-get update && apt-get install -y \
-    libsndfile1 \
-    ffmpeg \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-WORKDIR /app
-
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Pre-download the SpeechBrain model at build time
-RUN python -c "\
-from speechbrain.inference.interfaces import foreign_class; \
-foreign_class( \
-    source='speechbrain/emotion-recognition-wav2vec2-IEMOCAP', \
-    pymodule_file='custom_interface.py', \
-    classname='CustomEncoderWav2vec2Classifier', \
-    savedir='/app/models', \
-    run_opts={'device': 'cpu'}, \
-); \
-print('Model downloaded successfully.')"
-
-COPY . .
-
-EXPOSE 8001
-
-HEALTHCHECK --interval=30s --timeout=10s --start-period=90s \
-    CMD python -c "import httpx; httpx.get('http://localhost:8001/health').raise_for_status()"
-
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8001", "--workers", "1"]
@@ -1,119 +0,0 @@
-"""
-SpeechBrain + librosa vocal analysis.
-Performs emotion classification and acoustic feature extraction from audio.
-"""
-import io
-import logging
-import numpy as np
-import soundfile as sf
-import librosa
-from speechbrain.inference.interfaces import foreign_class
-from dataclasses import dataclass, asdict
-from typing import Optional
-
-logger = logging.getLogger(__name__)
-
-SAMPLE_RATE = 16000
-MIN_DURATION_SECONDS = 0.5
-
-
-@dataclass
-class VocalAnalysis:
-    emotion: str
-    emotion_confidence: float
-    emotion_scores: dict
-    pitch_mean_hz: Optional[float]
-    pitch_variance: Optional[float]
-    energy_rms: float
-    speaking_rate_approx: float
-    voiced_fraction: float
-    duration_seconds: float
-    analysis_error: Optional[str] = None
-
-
-class VocalAnalyzer:
-    """Loads models once at startup and provides analysis per audio chunk."""
-
-    def __init__(self, model_dir: str = "/app/models"):
-        logger.info("Loading SpeechBrain emotion model...")
-        self.classifier = foreign_class(
-            source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP",
-            pymodule_file="custom_interface.py",
-            classname="CustomEncoderWav2vec2Classifier",
-            savedir=model_dir,
-            run_opts={"device": "cpu"},
-        )
-        logger.info("SpeechBrain model loaded successfully.")
-
-    def analyze(self, audio_bytes: bytes, content_type: str = "audio/wav") -> VocalAnalysis:
-        try:
-            audio_buf = io.BytesIO(audio_bytes)
-            audio, sr = sf.read(audio_buf, dtype="float32")
-
-            if audio.ndim > 1:
-                audio = audio.mean(axis=1)
-
-            if sr != SAMPLE_RATE:
-                audio = librosa.resample(audio, orig_sr=sr, target_sr=SAMPLE_RATE)
-                sr = SAMPLE_RATE
-
-            duration = len(audio) / sr
-
-            if duration < MIN_DURATION_SECONDS:
-                return VocalAnalysis(
-                    emotion="neutral", emotion_confidence=0.0, emotion_scores={},
-                    pitch_mean_hz=None, pitch_variance=None, energy_rms=0.0,
-                    speaking_rate_approx=0.0, voiced_fraction=0.0,
-                    duration_seconds=duration,
-                    analysis_error=f"Audio too short: {duration:.2f}s < {MIN_DURATION_SECONDS}s minimum",
-                )
-
-            import tempfile, os
-            with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
-                sf.write(tmp.name, audio, sr)
-                tmp_path = tmp.name
-
-            try:
-                out_prob, score, index, text_lab = self.classifier.classify_file(tmp_path)
-                emotion = text_lab[0] if isinstance(text_lab, list) else text_lab
-                confidence = float(score[0]) if hasattr(score, "__iter__") else float(score)
-                labels = ["neu", "hap", "sad", "ang", "fru"]
-                prob_list = out_prob[0].tolist() if hasattr(out_prob[0], "tolist") else list(out_prob[0])
-                emotion_scores = {l: round(p, 4) for l, p in zip(labels, prob_list)}
-            finally:
-                os.unlink(tmp_path)
-
-            f0, voiced_flag, _ = librosa.pyin(
-                audio, fmin=librosa.note_to_hz("C2"), fmax=librosa.note_to_hz("C7"), sr=sr,
-            )
-
-            voiced_f0 = f0[voiced_flag] if voiced_flag is not None else np.array([])
-            pitch_mean = float(np.mean(voiced_f0)) if len(voiced_f0) > 0 else None
-            pitch_var = float(np.var(voiced_f0)) if len(voiced_f0) > 1 else None
-            voiced_fraction = float(np.sum(voiced_flag) / len(voiced_flag)) if voiced_flag is not None else 0.0
-
-            rms = librosa.feature.rms(y=audio)
-            energy_rms = float(np.mean(rms))
-
-            onset_frames = librosa.onset.onset_detect(y=audio, sr=sr)
-            speaking_rate = len(onset_frames) / duration if duration > 0 else 0.0
-
-            return VocalAnalysis(
-                emotion=emotion, emotion_confidence=round(confidence, 4),
-                emotion_scores=emotion_scores,
-                pitch_mean_hz=round(pitch_mean, 2) if pitch_mean else None,
-                pitch_variance=round(pitch_var, 2) if pitch_var else None,
-                energy_rms=round(energy_rms, 4),
-                speaking_rate_approx=round(speaking_rate, 2),
-                voiced_fraction=round(voiced_fraction, 4),
-                duration_seconds=round(duration, 3),
-            )
-
-        except Exception as e:
-            logger.exception(f"Analysis failed: {e}")
-            return VocalAnalysis(
-                emotion="neutral", emotion_confidence=0.0, emotion_scores={},
-                pitch_mean_hz=None, pitch_variance=None, energy_rms=0.0,
-                speaking_rate_approx=0.0, voiced_fraction=0.0,
-                duration_seconds=0.0, analysis_error=str(e),
-            )
@@ -1,66 +0,0 @@
-"""
-FastAPI service wrapping VocalAnalyzer.
-Internal-only -- not exposed via Traefik.
-"""
-import logging
-import os
-from contextlib import asynccontextmanager
-from fastapi import FastAPI, UploadFile, File, HTTPException
-from fastapi.responses import JSONResponse
-from dataclasses import asdict
-
-from analyzer import VocalAnalyzer
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-MODEL_DIR = os.getenv("MODEL_DIR", "/app/models")
-analyzer: VocalAnalyzer = None
-
-
-@asynccontextmanager
-async def lifespan(app: FastAPI):
-    global analyzer
-    logger.info("Starting VocalAnalyzer...")
-    analyzer = VocalAnalyzer(model_dir=MODEL_DIR)
-    logger.info("VocalAnalyzer ready.")
-    yield
-    logger.info("Shutting down.")
-
-
-app = FastAPI(title="SpeechBrain Vocal Analysis Service", lifespan=lifespan)
-
-
-@app.get("/health")
-async def health():
-    if analyzer is None:
-        raise HTTPException(status_code=503, detail="Model not loaded")
-    return {"status": "ok", "model": "emotion-recognition-wav2vec2-IEMOCAP"}
-
-
-@app.post("/analyze")
-async def analyze(audio: UploadFile = File(...)):
-    if analyzer is None:
-        raise HTTPException(status_code=503, detail="Model not loaded")
-
-    content = await audio.read()
-    if len(content) == 0:
-        raise HTTPException(status_code=400, detail="Empty audio file")
-
-    result = analyzer.analyze(content, content_type=audio.content_type or "audio/wav")
-    return JSONResponse(content=asdict(result))
-
-
-@app.post("/calibrate")
-async def calibrate(audio: UploadFile = File(...)):
-    if analyzer is None:
-        raise HTTPException(status_code=503, detail="Model not loaded")
-
-    content = await audio.read()
-    if len(content) == 0:
-        raise HTTPException(status_code=400, detail="Empty audio file")
-
-    result = analyzer.analyze(content, content_type=audio.content_type or "audio/wav")
-    result_dict = asdict(result)
-    result_dict["is_baseline"] = True
-    return JSONResponse(content=result_dict)
@@ -1,12 +0,0 @@
-fastapi==0.115.0
-uvicorn[standard]==0.30.0
-speechbrain==1.0.0
-huggingface_hub==0.19.4
-transformers==4.40.2
-torch==2.3.0
-torchaudio==2.3.0
-librosa==0.10.2
-soundfile==0.12.1
-numpy==1.26.4
-httpx==0.27.0
-python-multipart==0.0.9
@@ -1,8 +0,0 @@
-FROM nginx:alpine
-
-COPY index.html /usr/share/nginx/html/
-COPY app.js /usr/share/nginx/html/
-COPY style.css /usr/share/nginx/html/
-COPY nginx.conf /etc/nginx/conf.d/default.conf
-
-EXPOSE 80
@@ -1,158 +0,0 @@
-const LIVEKIT_URL = "wss://voice.hobbs.farm";
-let room = null;
-
-function log(msg, level) {
-  const el = document.getElementById("logOutput");
-  const time = new Date().toLocaleTimeString();
-  const cls = level === "error" ? "log-error" : level === "warn" ? "log-warn" : "log-info";
-  el.innerHTML += `<div class="${cls}"><span class="log-time">${time}</span> ${msg}</div>`;
-  el.scrollTop = el.scrollHeight;
-}
-
-function clearLog() {
-  document.getElementById("logOutput").innerHTML = "";
-}
-
-async function connect() {
-  setStatus("connecting", "Connecting...");
-  log("Requesting token from server...");
-  try {
-    const response = await fetch("/api/token", {
-      method: "POST",
-      headers: { "Content-Type": "application/json" },
-      body: JSON.stringify({ identity: "jeremy-" + Date.now() }),
-    });
-    if (!response.ok) {
-      const text = await response.text();
-      throw new Error("Token request failed: " + response.status + " " + text);
-    }
-    const data = await response.json();
-    log("Token received. LiveKit URL: " + data.url);
-
-    room = new LivekitClient.Room({
-      audioCaptureDefaults: {
-        echoCancellation: true,
-        noiseSuppression: true,
-        autoGainControl: true,
-      },
-    });
-
-    room.on(LivekitClient.RoomEvent.Connected, () => {
-      setStatus("connected", "Connected");
-      document.getElementById("connectBtn").style.display = "none";
-      document.getElementById("disconnectBtn").style.display = "block";
-      log("Connected to LiveKit room");
-      log("Participants in room: " + room.remoteParticipants.size);
-      if (room.remoteParticipants.size === 0) {
-        log("No agent participant yet - waiting for voicecoach-agent to join...", "warn");
-      }
-    });
-
-    room.on(LivekitClient.RoomEvent.Disconnected, (reason) => {
-      setStatus("disconnected", "Disconnected");
-      document.getElementById("connectBtn").style.display = "block";
-      document.getElementById("disconnectBtn").style.display = "none";
-      log("Disconnected from LiveKit" + (reason ? ": " + reason : ""), "warn");
-    });
-
-    room.on(LivekitClient.RoomEvent.ParticipantConnected, (participant) => {
-      log("Participant joined: " + participant.identity);
-    });
-
-    room.on(LivekitClient.RoomEvent.ParticipantDisconnected, (participant) => {
-      log("Participant left: " + participant.identity, "warn");
-    });
-
-    room.on(LivekitClient.RoomEvent.TrackSubscribed, (track, publication, participant) => {
-      log("Track subscribed: " + track.kind + " from " + participant.identity);
-      if (track.kind === LivekitClient.Track.Kind.Audio) {
-        const element = track.attach();
-        document.body.appendChild(element);
-        element.play().then(() => {
-          log("Audio playback started");
-        }).catch((err) => {
-          log("Audio play failed: " + err.message, "error");
-        });
-      }
-    });
-
-    room.on(LivekitClient.RoomEvent.TrackPublished, (publication, participant) => {
-      log("Track published by " + participant.identity + ": " + publication.kind);
-    });
-
-    room.on(LivekitClient.RoomEvent.TrackUnsubscribed, (track, publication, participant) => {
-      log("Track unsubscribed: " + track.kind + " from " + participant.identity, "warn");
-    });
-
-    room.on(LivekitClient.RoomEvent.DataReceived, (payload, participant) => {
-      try {
-        const msg = new TextDecoder().decode(payload);
-        log("Data from " + (participant ? participant.identity : "server") + ": " + msg);
-      } catch (e) {
-        log("Data received (binary, " + payload.byteLength + " bytes)");
-      }
-    });
-
-    room.on(LivekitClient.RoomEvent.ConnectionQualityChanged, (quality, participant) => {
-      if (participant.isLocal) {
-        log("Connection quality: " + quality);
-      }
-    });
-
-    room.on(LivekitClient.RoomEvent.MediaDevicesError, (err) => {
-      log("Media device error: " + err.message, "error");
-    });
-
-    room.on(LivekitClient.RoomEvent.RoomMetadataChanged, (metadata) => {
-      log("Room metadata changed: " + metadata);
-    });
-
-    log("Connecting to " + LIVEKIT_URL + "...");
-    await room.connect(data.url || LIVEKIT_URL, data.token);
-
-    log("Enabling microphone...");
-    await room.localParticipant.setMicrophoneEnabled(true);
-    log("Microphone enabled. Speak now.");
-
-    // Log local tracks
-    room.localParticipant.audioTrackPublications.forEach((pub) => {
-      log("Local audio track: " + pub.trackSid + " muted=" + pub.isMuted);
-    });
-
-  } catch (err) {
-    setStatus("disconnected", "Error: " + err.message);
-    log("Connection error: " + err.message, "error");
-    console.error(err);
-  }
-}
-
-async function disconnect() {
-  if (room) {
-    log("Disconnecting...");
-    await room.disconnect();
-    room = null;
-  }
-}
-
-function setMode(mode) {
-  document.getElementById("modeDisplay").textContent = "Mode: " + mode;
-  log("Mode changed to: " + mode);
-  if (room && room.localParticipant) {
-    const encoder = new TextEncoder();
-    room.localParticipant.publishData(
-      encoder.encode(JSON.stringify({ type: "mode_change", mode })),
-      { reliable: true }
-    );
-  }
-}
-
-function setStatus(state, text) {
-  const el = document.getElementById("status");
-  el.className = "status " + state;
-  el.textContent = text;
-}
-
-document.getElementById("connectBtn").addEventListener("click", connect);
-document.getElementById("disconnectBtn").addEventListener("click", disconnect);
-
-log("VoiceCoach client loaded. Ready to connect.");
@@ -1,46 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-  <meta charset="UTF-8">
-  <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0">
-  <title>VoiceCoach</title>
-  <link rel="stylesheet" href="style.css">
-</head>
-<body>
-  <div class="container">
-    <div class="header">
-      <h1>VoiceCoach</h1>
-      <div id="status" class="status disconnected">Disconnected</div>
-    </div>
-
-    <div class="controls">
-      <button id="connectBtn" class="btn btn-primary">Start Session</button>
-      <button id="disconnectBtn" class="btn btn-danger" style="display:none">End Session</button>
-    </div>
-
-    <div id="modeDisplay" class="mode-display">Mode: coaching</div>
-
-    <div id="transcript" class="transcript">
-      <p class="hint">Press "Start Session" to connect your voice.</p>
-    </div>
-
-    <div class="mode-buttons">
-      <button class="mode-btn" onclick="setMode('coaching mode')">Coaching</button>
-      <button class="mode-btn" onclick="setMode('vent mode')">Vent</button>
-      <button class="mode-btn" onclick="setMode('practice mode')">Practice</button>
-      <button class="mode-btn" onclick="setMode('briefing mode')">Briefing</button>
-    </div>
-
-    <div class="log-panel">
-      <div class="log-header">
-        <span>Log</span>
-        <button class="log-clear" onclick="clearLog()">Clear</button>
-      </div>
-      <div id="logOutput" class="log-output"></div>
-    </div>
-  </div>
-
-  <script src="https://cdn.jsdelivr.net/npm/livekit-client/dist/livekit-client.umd.min.js"></script>
-  <script src="app.js"></script>
-</body>
-</html>
@@ -1,131 +0,0 @@
-* { margin: 0; padding: 0; box-sizing: border-box; }
-
-body {
-  font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
-  background: #1a1a2e;
-  color: #eee;
-  min-height: 100vh;
-  display: flex;
-  justify-content: center;
-  align-items: center;
-}
-
-.container {
-  max-width: 420px;
-  width: 100%;
-  padding: 24px;
-}
-
-.header {
-  display: flex;
-  justify-content: space-between;
-  align-items: center;
-  margin-bottom: 24px;
-}
-
-h1 { font-size: 24px; font-weight: 600; }
-
-.status {
-  padding: 4px 12px;
-  border-radius: 12px;
-  font-size: 12px;
-  font-weight: 600;
-  text-transform: uppercase;
-}
-.status.disconnected { background: #444; color: #aaa; }
-.status.connecting { background: #553; color: #ffa; }
-.status.connected { background: #253; color: #5f5; }
-
-.controls { margin-bottom: 20px; }
-
-.btn {
-  width: 100%;
-  padding: 14px;
-  border: none;
-  border-radius: 8px;
-  font-size: 16px;
-  font-weight: 600;
-  cursor: pointer;
-  transition: opacity 0.2s;
-}
-.btn:hover { opacity: 0.85; }
-.btn-primary { background: #4a6cf7; color: #fff; }
-.btn-danger { background: #f74a4a; color: #fff; }
-
-.mode-display {
-  text-align: center;
-  font-size: 13px;
-  color: #888;
-  margin-bottom: 16px;
-}
-
-.transcript {
-  background: #16213e;
-  border-radius: 8px;
-  padding: 16px;
-  min-height: 200px;
-  max-height: 400px;
-  overflow-y: auto;
-  margin-bottom: 16px;
-}
-.transcript .hint { color: #666; font-style: italic; }
-
-.mode-buttons {
-  display: grid;
-  grid-template-columns: 1fr 1fr;
-  gap: 8px;
-}
-.mode-btn {
-  padding: 10px;
-  background: #16213e;
-  border: 1px solid #333;
-  border-radius: 6px;
-  color: #ccc;
-  font-size: 13px;
-  cursor: pointer;
-  transition: background 0.2s;
-}
-.mode-btn:hover { background: #1a2744; border-color: #4a6cf7; }
-
-.log-panel {
-  margin-top: 16px;
-  background: #0d1117;
-  border: 1px solid #333;
-  border-radius: 8px;
-  overflow: hidden;
-}
-.log-header {
-  display: flex;
-  justify-content: space-between;
-  align-items: center;
-  padding: 6px 12px;
-  background: #161b22;
-  font-size: 12px;
-  font-weight: 600;
-  color: #888;
-  text-transform: uppercase;
-  letter-spacing: 0.5px;
-}
-.log-clear {
-  background: none;
-  border: 1px solid #444;
-  border-radius: 4px;
-  color: #888;
-  font-size: 11px;
-  padding: 2px 8px;
-  cursor: pointer;
-}
-.log-clear:hover { border-color: #666; color: #ccc; }
-.log-output {
-  padding: 8px 12px;
-  max-height: 200px;
-  overflow-y: auto;
-  font-family: 'SF Mono', 'Fira Code', monospace;
-  font-size: 11px;
-  line-height: 1.6;
-}
-.log-output div { word-break: break-all; }
-.log-time { color: #555; margin-right: 6px; }
-.log-info { color: #8b949e; }
-.log-warn { color: #d29922; }
-.log-error { color: #f85149; }
@@ -0,0 +1,22 @@
+services:
+  actual-budget:
+    image: actualbudget/actual-server:latest
+    container_name: actual-budget
+    restart: unless-stopped
+    ports:
+      - "5006:5006"
+    volumes:
+      - /mnt/docker-data/configs/actual-budget:/data
+    mem_limit: 256M
+    memswap_limit: 256M
+    healthcheck:
+      test: ["CMD-SHELL", "node -e \"fetch('http://localhost:5006/').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))\""]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
@@ -1,2 +0,0 @@
-COUCHDB_USER=obsidian
-COUCHDB_PASSWORD=REPLACE_AT_DEPLOY
@@ -1,27 +0,0 @@
-services:
-  couchdb:
-    image: couchdb:3.4
-    container_name: couchdb
-    restart: unless-stopped
-    ports:
-      - "5984:5984"
-    environment:
-      - COUCHDB_USER=${COUCHDB_USER}
-      - COUCHDB_PASSWORD=${COUCHDB_PASSWORD}
-      - TZ=America/Chicago
-    volumes:
-      # LOCAL disk, not NFS: CouchDB's file locking breaks over NFSv3, the same
-      # way it did for guacamole-db (MySQL) and semaphore-db.
-      - /var/lib/couchdb/data:/opt/couchdb/data
-      # NOT :ro -- CouchDB 3.x writes runtime config back into the last-loaded ini.
-      # With a read-only mount it exits 1 immediately and logs NOTHING at all.
-      - /var/lib/couchdb/config/local.ini:/opt/couchdb/etc/local.d/local.ini
-    labels:
-      - "com.centurylinklabs.watchtower.enable=false"
-    mem_limit: 1g
-    healthcheck:
-      test: ["CMD", "curl", "-fsS", "http://localhost:5984/_up"]
-      interval: 60s
-      timeout: 10s
-      retries: 3
-      start_period: 30s
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
jeremy	e9a98f4855	chore: pin jellyfin to 2026060106 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-03 21:37:46 -05:00
jeremy	97e3cf12a7	frigate: sync config to live state, fix /tmp/cache size, enable VAAPI on house_east/pool_room, throttle shop_west detection - docker-compose.yml: increase /tmp/cache tmpfs from 4G to 8G, add Coral USB device passthrough (/dev/bus/usb), fix memswap_limit to 16G (was equal to mem_limit) - config.yml: replace OpenVINO detector with Coral edgetpu (usb), update model dimensions to 320x320 and pixel format to rgb, enable VAAPI on house_east and pool_room, throttle shop_west to 2fps with stricter person/car filters (min_area + threshold), add offline note for gate_camera, enable semantic_search (large), face_recognition (small), LPR, and bird classification Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-01 15:07:36 -05:00
jeremy	06e9db70d2	feat: replace legacy Unifi with UniFi OS Server v5.1.15 Deploys ghcr.io/lemker/unifi-os-server replacing linuxserver/unifi-network-application. Data dirs moved to /var/lib/unifi-os/ locally (NFS root_squash blocks chown needed by postgres/mongodb/nginx init). Only /persistent remains on NAS for config backups. Access: https://192.168.86.100:11443 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-31 20:36:02 -05:00
jeremy	b3bef75981	feat: VoiceCoach v2 — livekit-agents 1.5 personal voice assistant Replaces pipecat 0.0.48 (6 manual patches, DuplicateIdentity reconnect storms) with livekit-agents 1.5 SDK. New features: - SvelteKit UI with live transcript, VAD ring, mode bar, vocal meter, history view - SQLite session store with WAL mode (cross-session memory) - Async SpeechBrain vocal/emotion analysis injected per turn - Homelab tools: SSH/docker, Prometheus alerts, Home Assistant, SearXNG search - OpenClaw LLM gateway preserved (qwen2.5:14b via Ollama) - 4 modes: coaching, vent, practice, briefing Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-31 18:05:30 -05:00
jeremy	55f05a88d0	infra: migrate GPU workstation to Ubuntu, deploy vLLM-Hermes + voice stack - Migrated primary workstation (192.168.86.27) from Windows/WSL2 to Ubuntu 24.04 (2026-05-28) - Upgraded Ollama 0.15.6 → 0.24.0 (all 21 models preserved) - Fixed Watchtower crash loop (DOCKER_API_VERSION=1.44) - Fixed Open WebUI OLLAMA_BASE_URL to use Docker service name - Deployed Speaches :8000 (CUDA, STT/TTS for VoiceCoach) - Deployed LiveKit :7880/:7881 (WebRTC for VoiceCoach) - Deployed vLLM-Hermes :8001 (Hermes 4.3 36B AWQ, tool-call-parser hermes) - Endpoint: http://192.168.86.27:8001/v1, model: hermes - Tool-call test passed: structured tool_calls array confirmed - Added vllm-local provider to voicecoach-openclaw and margaret OpenClaw configs - Added OPENAI_API_BASE_URL to Open WebUI for Hermes access in chat UI - Updated CLAUDE.md: removed WSL2 references, added GPU workstation section Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-28 18:48:44 -05:00