24055ad686
Two commits since the last merge: - web: add-to-queue form on /queue too, with per-page HTMX dispatch. Shared form partial reused by /dashboard and /queue; the POST /sources/add endpoint dispatches the response partial by inspecting HX-Current-URL so each page's own list/counts refresh inline. Same service call, same flash behavior. - tower: pin CUDA-12 wheels + LD_LIBRARY_PATH wrapper for the systemd service. ctranslate2 4.7.2 needs CUDA 12 + cuDNN 9 but Arch ships CUDA 13, so we pin nvidia-cublas-cu12 + nvidia-cudnn-cu12>=9,<10 in the `tower` extra and add deploy/tower/run-transcribe-worker.sh, which resolves the venv's lib dirs at runtime and prepends them to LD_LIBRARY_PATH before exec-ing the worker. systemd doesn't inherit shell exports, so this is what makes the service survive reboots and Python upgrades. ExecStart= now points at the wrapper, and the StartLimit* directives moved into [Unit] where modern systemd expects them. Travis's tower-side corrections on main (`User=trucktrav`, `gitea-pbs-trucktrav` clone alias, tower WG IP 10.99.0.3) auto-merge cleanly against these branch edits — different lines in the same files.
51 lines
1.9 KiB
Desktop File
51 lines
1.9 KiB
Desktop File
[Unit]
|
|
Description=second-brain transcribe worker (tower-side, faster-whisper on GPU)
|
|
Documentation=https://gitea.plantbasedsoutherner.com/petal-power/second-brain
|
|
# The worker reaches petalbrain over WireGuard, so the tunnel must be up first.
|
|
# `Wants=` is the soft form — if the tunnel disappears later the worker logs
|
|
# DB-unreachable warnings and retries, it doesn't crash-loop.
|
|
After=network-online.target wg-quick@wg-lan.service
|
|
Wants=network-online.target wg-quick@wg-lan.service
|
|
|
|
# Crash loop guard — systemd will give up after this if the unit keeps
|
|
# dying. The worker itself logs+backs-off on DB outages so this only
|
|
# trips on genuine failure. (StartLimit* directives live in [Unit] on
|
|
# modern systemd; placing them in [Service] is a silent no-op.)
|
|
StartLimitIntervalSec=300
|
|
StartLimitBurst=5
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=trucktrav
|
|
Group=trucktrav
|
|
|
|
# Adjust to wherever you `git clone`d the repo on the tower.
|
|
WorkingDirectory=/opt/projects/homelab/second-brain
|
|
|
|
# Env (SECOND_BRAIN_DATABASE_URL, optional knobs). 0600, owned by herbyadmin.
|
|
EnvironmentFile=/etc/default/second-brain-transcribe
|
|
|
|
# The wrapper resolves the venv's CUDA-12 lib dirs (nvidia-cublas-cu12 /
|
|
# nvidia-cudnn-cu12 pulled in by `uv sync --extra tower`), prepends them
|
|
# to LD_LIBRARY_PATH, then execs the worker via `uv run`. systemd does
|
|
# NOT inherit a shell's LD_LIBRARY_PATH, so doing this inline in the
|
|
# unit would require a brittle hard-coded `python3.XX` path and break
|
|
# on Python upgrades.
|
|
ExecStart=/opt/projects/homelab/second-brain/deploy/tower/run-transcribe-worker.sh
|
|
|
|
Restart=always
|
|
RestartSec=10
|
|
|
|
# A few sandboxing nice-to-haves. Loose on purpose — the worker needs
|
|
# /dev/nvidia* for CUDA and writes to user-owned media/subtitles dirs.
|
|
ProtectSystem=full
|
|
ProtectHome=no
|
|
NoNewPrivileges=true
|
|
|
|
# Stdout/stderr → journald.
|
|
StandardOutput=journal
|
|
StandardError=journal
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|