From 2b40157a0d44af906f3acc1d9bab1cd4a3235d48 Mon Sep 17 00:00:00 2001 From: Travis Herbranson Date: Mon, 25 May 2026 14:21:02 -0400 Subject: [PATCH 1/2] web: add-to-queue form on /queue too, with per-page HTMX dispatch MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Travis's original ask put the form on the "queue page" but it landed only on /dashboard. Putting it on /queue too without duplicating any logic: - _add_to_queue_form.html — extracted the form markup into a shared partial. Callers set `{% set swap_target = "#-body" %}` before including it; that's the only knob that differs between the two pages. Same POST endpoint, same field set, same flash behaviour. - _dashboard_body.html — now {% include %}s the shared partial with swap_target="#dashboard-body". Net change: a six-line include replacing the inline form. - _queue_body.html (new) — `
` wrapping the shared form (swap_target="#queue-body") + the in-flight source list (same card markup as the Sources view, with the wrap-fix already applied). Empty state copy matches the queue context. - queue.html (new) — extends base.html, page-titles "Queue", and includes _queue_body.html. /queue no longer reuses index.html. - /queue route — renders queue.html via a new _build_queue_context helper. Same in-flight filter as before (PENDING/PULLED/TRANSCRIBED). - POST /sources/add — reads HX-Current-URL (HTMX sends it on every request; falls back to Referer) and picks the response partial: /queue → _queue_body.html, anything else → _dashboard_body.html. One endpoint, one service call, two render branches — neither side reaches into the other's state. Live-verified through the rebuilt container: - GET /queue (LAN + brain.herbylab.dev) — form present. - GET /dashboard — form still present (unchanged behaviour). - GET / — form still absent (Sources view stays clean). - POST from /queue → response carries id="queue-body" (and not dashboard-body); the freshly-added row appears in the swapped list. - POST from /dashboard → response carries id="dashboard-body". - Flash scenarios from /queue: queued / duplicate / playlist 13 videos / validation error — all four render correctly. --- src/second_brain/web/app.py | 82 +++++++++++++------ .../web/templates/_add_to_queue_form.html | 67 +++++++++++++++ .../web/templates/_dashboard_body.html | 64 +-------------- .../web/templates/_queue_body.html | 62 ++++++++++++++ src/second_brain/web/templates/queue.html | 15 ++++ 5 files changed, 201 insertions(+), 89 deletions(-) create mode 100644 src/second_brain/web/templates/_add_to_queue_form.html create mode 100644 src/second_brain/web/templates/_queue_body.html create mode 100644 src/second_brain/web/templates/queue.html diff --git a/src/second_brain/web/app.py b/src/second_brain/web/app.py index 350a2aa..b6eff16 100644 --- a/src/second_brain/web/app.py +++ b/src/second_brain/web/app.py @@ -141,32 +141,41 @@ async def source_detail(request: Request, source_id: int): ) +_IN_FLIGHT_STATUSES = [ + SourceStatus.PENDING, + SourceStatus.PULLED, + SourceStatus.TRANSCRIBED, +] + + +def _build_queue_context( + sess, + *, + add_flash: Optional[str] = None, + add_error: Optional[str] = None, +) -> dict: + """Context for queue.html / _queue_body.html (in-flight source list + form).""" + sources = ( + sess.query(Source) + .filter(Source.status.in_(_IN_FLIGHT_STATUSES)) + .order_by(Source.ingested_at.asc()) + .all() + ) + return { + "sources": [_source_to_dict(s) for s in sources], + "domains": DOMAINS, + "add_flash": add_flash, + "add_error": add_error, + } + + @app.get("/queue", response_class=HTMLResponse) async def queue_view(request: Request): - """Queue view: pending and in-flight sources.""" + """Queue view: pending and in-flight sources, with an add-to-queue form.""" db = get_database() - in_flight_statuses = [SourceStatus.PENDING, SourceStatus.PULLED, SourceStatus.TRANSCRIBED] with db.session() as sess: - sources = ( - sess.query(Source) - .filter(Source.status.in_(in_flight_statuses)) - .order_by(Source.ingested_at.asc()) - .all() - ) - source_list = [_source_to_dict(s) for s in sources] - - return templates.TemplateResponse( - request, - "index.html", - { - "sources": source_list, - "domains": DOMAINS, - "statuses": [s.value for s in SourceStatus], - "selected_domain": "", - "selected_status": "", - "page_title": "Queue", - }, - ) + ctx = _build_queue_context(sess) + return templates.TemplateResponse(request, "queue.html", ctx) # --------------------------------------------------------------------------- @@ -423,12 +432,31 @@ async def sources_add( except ValueError as exc: add_error = str(exc) - with db.session() as sess: - ctx = _build_dashboard_context( - sess, add_flash=add_flash, add_error=add_error - ) + # Dispatch the response partial based on which page submitted the form. + # HTMX always sends HX-Current-URL with the request URL of the user's + # current page; we parse the path and pick the matching body partial. + # Same /sources/add endpoint, same service call — only the rendered + # region differs, so each page refreshes its own list/counts inline. + from urllib.parse import urlparse as _urlparse - return templates.TemplateResponse(request, "_dashboard_body.html", ctx) + hx_url = request.headers.get("HX-Current-URL") or request.headers.get( + "Referer", "" + ) + source_path = _urlparse(hx_url).path if hx_url else "" + + with db.session() as sess: + if source_path.rstrip("/") == "/queue": + ctx = _build_queue_context( + sess, add_flash=add_flash, add_error=add_error + ) + template_name = "_queue_body.html" + else: + ctx = _build_dashboard_context( + sess, add_flash=add_flash, add_error=add_error + ) + template_name = "_dashboard_body.html" + + return templates.TemplateResponse(request, template_name, ctx) # --------------------------------------------------------------------------- diff --git a/src/second_brain/web/templates/_add_to_queue_form.html b/src/second_brain/web/templates/_add_to_queue_form.html new file mode 100644 index 0000000..126ed3d --- /dev/null +++ b/src/second_brain/web/templates/_add_to_queue_form.html @@ -0,0 +1,67 @@ +{# Add-to-queue form. Reused by /dashboard and /queue — the only + difference between the two callers is the HTMX swap target, which the + parent template sets via `{% set swap_target = "#…-body" %}` before + including this partial. POST goes to /sources/add either way; the + route inspects HX-Current-URL to pick the right body partial in its + response. #} +
+
+

+ Add to queue +

+

video on a known host (YouTube / Vimeo) → tower; otherwise treated as an article. YouTube /playlist?list=… fans out.

+
+ + {% if add_flash %} +
+ ✓ {{ add_flash }} +
+ {% endif %} + {% if add_error %} +
+ ✗ {{ add_error }} +
+ {% endif %} + +
+ +
+ + +
+ +
+ + +
+ +
+ + +
+ +
+ +
+ +
+ + +
+
+
diff --git a/src/second_brain/web/templates/_dashboard_body.html b/src/second_brain/web/templates/_dashboard_body.html index dfc1133..39b8dc1 100644 --- a/src/second_brain/web/templates/_dashboard_body.html +++ b/src/second_brain/web/templates/_dashboard_body.html @@ -18,68 +18,8 @@ } %}
- -
-
-

- Add to queue -

-

video on a known host (YouTube / Vimeo) → tower; otherwise treated as an article

-
- - {% if add_flash %} -
- ✓ {{ add_flash }} -
- {% endif %} - {% if add_error %} -
- ✗ {{ add_error }} -
- {% endif %} - -
- -
- - -
- -
- - -
- -
- - -
- -
- -
- -
- - -
-
-
+ {% set swap_target = "#dashboard-body" %} + {% include "_add_to_queue_form.html" %}
diff --git a/src/second_brain/web/templates/_queue_body.html b/src/second_brain/web/templates/_queue_body.html new file mode 100644 index 0000000..35384b2 --- /dev/null +++ b/src/second_brain/web/templates/_queue_body.html @@ -0,0 +1,62 @@ +{# HTMX-replaceable queue body. POST /sources/add re-renders this when + the form was submitted from /queue (dispatched server-side via + HX-Current-URL); hx-target="#queue-body" + hx-swap="outerHTML" keeps + the wrapping div in place for the next swap. #} +{% set status_colors = { + 'pending': 'bg-gray-100 text-gray-700', + 'pulled': 'bg-blue-100 text-blue-700', + 'transcribed': 'bg-yellow-100 text-yellow-700', + 'analyzed': 'bg-orange-100 text-orange-700', + 'accepted': 'bg-green-100 text-green-700', + 'published': 'bg-purple-100 text-purple-700', + 'failed': 'bg-red-100 text-red-700' +} %} +{% set domain_colors = { + 'development': 'bg-cyan-50 text-cyan-700 border-cyan-200', + 'content': 'bg-pink-50 text-pink-700 border-pink-200', + 'business': 'bg-amber-50 text-amber-700 border-amber-200', + 'homelab': 'bg-teal-50 text-teal-700 border-teal-200' +} %} +
+ + {% set swap_target = "#queue-body" %} + {% include "_add_to_queue_form.html" %} + + + {% if sources %} +
+ {% for source in sources %} + +
+
+

+ {{ source.title }} +

+

{{ source.url }}

+ {% if source.focus %} +

Focus: {{ source.focus }}

+ {% endif %} +
+
+ + {{ source.status }} + + + {{ source.domain }} + + {{ source.ingested_at }} +
+
+ + {% endfor %} +
+ {% else %} +
+

Queue is empty.

+

Add a URL above to get started.

+
+ {% endif %} +
diff --git a/src/second_brain/web/templates/queue.html b/src/second_brain/web/templates/queue.html new file mode 100644 index 0000000..faa8806 --- /dev/null +++ b/src/second_brain/web/templates/queue.html @@ -0,0 +1,15 @@ +{% extends "base.html" %} + +{% block title %}Queue — second-brain{% endblock %} + +{% block content %} +
+

+ Queue + ({{ sources|length }}) +

+ pending → pulled → transcribed +
+ +{% include "_queue_body.html" %} +{% endblock %} From b2e2359651f7d719c8abe207933e865c505ce37a Mon Sep 17 00:00:00 2001 From: Travis Herbranson Date: Mon, 25 May 2026 15:39:13 -0400 Subject: [PATCH 2/2] tower: pin CUDA-12 wheels + LD_LIBRARY_PATH wrapper for the systemd service MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Arch / EndeavourOS now ships CUDA 13 (libcublas.so.13); ctranslate2 4.7.2 (which faster-whisper rides) wants CUDA 12 + cuDNN 9 and won't load against the system libs. Travis got it working ad-hoc with a shell export of LD_LIBRARY_PATH + manual pip install, but systemd doesn't inherit either, so the next reboot would refire the libcublas.so.12 load error. Making it permanent + reproducible: - pyproject `tower` extra now pins the CUDA-12 runtime as pip wheels alongside faster-whisper: nvidia-cublas-cu12; sys_platform == 'linux' nvidia-cudnn-cu12>=9,<10; sys_platform == 'linux' uv.lock resolves nvidia-cublas-cu12 12.9.2.10 + nvidia-cudnn-cu12 9.22.0.52. Dev side (no --extra tower) stays clean — verified by a no-extra `uv sync` followed by `uv pip list | grep nvidia` returning empty. - deploy/tower/run-transcribe-worker.sh (new, +x): computes the venv's CUDA-12 lib dirs at runtime via `uv run python` (resolving nvidia.cublas / nvidia.cudnn through __path__ — they're PEP 420 namespace packages with no __file__), prepends them to LD_LIBRARY_PATH, then execs `uv run second-brain transcribe-worker`. No hard-coded python3.XX path so it survives Python upgrades. If the wheels aren't installed it aborts with a clear "uv sync --extra tower" hint instead of a silent libcublas load failure deep inside ctranslate2. - second-brain-transcribe.service: ExecStart now points at the wrapper. Also moves StartLimitIntervalSec / StartLimitBurst from [Service] into [Unit] where modern systemd expects them (systemd-analyze verify previously flagged the misplaced keys as silently ignored). Restart=always, EnvironmentFile, After=/Wants= wg-quick@wg-lan.service, User=herbyadmin all unchanged. - second-brain-transcribe.env.example: trimmed to just SECOND_BRAIN_DATABASE_URL with the placeholder spelled out, plus a clear pointer to the ready-to-scp env file generated on herbys-dev at /opt/backups/postgres-consolidation/second-brain-transcribe.env (mode 0600, regeneratable from credentials.env without ever echoing the password). The committed example never carries a real secret. - deploy/tower/README.md: documents the CUDA-13-vs-CUDA-12 gotcha upfront ("don't `pacman -S cuda cudnn`"), the wrapper-based ExecStart, the scp-from-dev EnvironmentFile recipe with the password-regen one-liner, and the EnvironmentFile-vs-shell-export note. Verified locally on dev (no GPU): - uv.lock resolves with the new tower deps. - A throwaway venv installed with the same `nvidia-cublas-cu12 nvidia-cudnn-cu12>=9,<10` pins produces lib dirs containing libcublas.so.12 and libcudnn.so.9 via the wrapper's path probe. - systemd-analyze verify is clean except the expected "/opt/projects/... not executable on this host" warning (the wrapper exists only in the tower's checkout). - 27 passed / 2 skipped in pytest; zero-check 5/5. GPU large-v3 + live service start under systemd remain tower-only validation steps. --- deploy/tower/README.md | 92 +++++++++++++++---- deploy/tower/run-transcribe-worker.sh | 64 +++++++++++++ .../tower/second-brain-transcribe.env.example | 44 ++++++--- deploy/tower/second-brain-transcribe.service | 24 +++-- pyproject.toml | 17 +++- uv.lock | 37 ++++++++ 6 files changed, 232 insertions(+), 46 deletions(-) create mode 100755 deploy/tower/run-transcribe-worker.sh diff --git a/deploy/tower/README.md b/deploy/tower/README.md index 9b391e7..6a66421 100644 --- a/deploy/tower/README.md +++ b/deploy/tower/README.md @@ -15,16 +15,31 @@ and all extraction/embedding stay on the dev side. # Build / runtime tooling. sudo pacman -S --needed base-devel git ffmpeg python uv -# NVIDIA — driver, CUDA, cuDNN. faster-whisper / CTranslate2 needs cuDNN -# at runtime; missing-symbol errors at first transcribe are usually a -# cuDNN install gap. Use whichever driver/cuda channel matches your -# Arch derivative; on stock EndeavourOS the AUR/community packages work: -sudo pacman -S --needed nvidia nvidia-utils cuda cudnn +# NVIDIA driver only — see the CUDA-12 gotcha below before installing +# the distro's `cuda` / `cudnn` packages. +sudo pacman -S --needed nvidia nvidia-utils # Confirm the GPU is visible. nvidia-smi ``` +### ⚠ CUDA-12 gotcha — do NOT install pacman's `cuda` / `cudnn` + +Arch / EndeavourOS now ships **CUDA 13** (`libcublas.so.13`). The +`ctranslate2` 4.7.x backend that `faster-whisper` 1.x rides on top of +wants **CUDA 12** (`libcublas.so.12`) + **cuDNN 9** (`libcudnn.so.9`) +and will not load against the system's CUDA-13 libs. + +Rather than fight the distro, this project pins the CUDA-12 runtime as +pip wheels in the venv via the `tower` extra (`nvidia-cublas-cu12`, +`nvidia-cudnn-cu12>=9,<10`). The `uv sync --extra tower` step in §2 +brings them in automatically; the systemd `ExecStart` wrapper +(`deploy/tower/run-transcribe-worker.sh`) prepends those wheel-bundled +`.so` directories to `LD_LIBRARY_PATH` at start time. + +If you've already installed pacman's `cuda` / `cudnn`, you can leave +them — the wrapper's `LD_LIBRARY_PATH` prepend wins for this service. + yt-dlp comes in via the Python project (`uv sync` step below), so the distro yt-dlp is *optional*. Leave it off the host unless you want it on your CLI PATH. @@ -45,12 +60,24 @@ cd second-brain uv sync --extra tower ``` -`faster-whisper` will pull a couple hundred MB of CUDA wheels. First-run -model download (~3 GB for large-v3) lands under `~/.cache/huggingface/` -the first time the worker transcribes; pre-warm it if you want: +`uv sync --extra tower` will pull ~1 GB of pinned CUDA-12 wheels +(`nvidia-cublas-cu12`, `nvidia-cudnn-cu12`, plus `faster-whisper` / +`ctranslate2`). First-run model download (~3 GB for large-v3) lands +under `~/.cache/huggingface/` the first time the worker transcribes; +pre-warm if you want: ```bash -uv run python -c "from faster_whisper import WhisperModel; WhisperModel('large-v3', device='cuda', compute_type='float16')" +# Run the wrapper so the CUDA-12 lib paths are pinned exactly the way +# the systemd service will see them — this is the cheapest end-to-end +# sanity check that the venv + LD_LIBRARY_PATH plumbing is correct. +deploy/tower/run-transcribe-worker.sh --once +``` + +Or just instantiate the model directly: + +```bash +LD_LIBRARY_PATH="$(uv run python -c 'import os, nvidia.cublas, nvidia.cudnn; print(":".join(os.path.join(os.path.dirname(m.__file__),"lib") for m in [nvidia.cublas, nvidia.cudnn]))')" \ + uv run python -c "from faster_whisper import WhisperModel; WhisperModel('large-v3', device='cuda', compute_type='float16')" ``` --- @@ -80,16 +107,41 @@ configured separately as part of Travis's infra. ## 4. EnvironmentFile -```bash -sudo install -m 0600 -o root -g root \ - deploy/tower/second-brain-transcribe.env.example \ - /etc/default/second-brain-transcribe -sudo $EDITOR /etc/default/second-brain-transcribe # paste the lovebug password +systemd reads this BEFORE dropping to `User=herbyadmin`. The file is +**not** a shell init script — `export VAR=…` in your shell does not +apply here, and changes require `systemctl restart` to take effect. + +There's a ready-to-scp file on **herbys-dev** with the real lovebug +password already populated, generated from +`/opt/backups/postgres-consolidation/credentials.env`: + +``` +/opt/backups/postgres-consolidation/second-brain-transcribe.env (mode 0600) ``` -The lovebug password lives in `/opt/backups/postgres-consolidation/credentials.env` -on the dev host. Copy it across through whatever channel you trust -(personal Bitwarden, scp over WG, etc.) — do not commit it. +Pull it across instead of hand-copying the password: + +```bash +# from the tower +scp herbys-dev:/opt/backups/postgres-consolidation/second-brain-transcribe.env /tmp/sb-env +sudo install -m 0600 -o root -g root /tmp/sb-env /etc/default/second-brain-transcribe +rm /tmp/sb-env +``` + +If you ever need to regenerate the dev-host file (e.g. after a password +rotation), the recipe is: + +```bash +# on herbys-dev — never echoes the password, mode 0600 +PW=$(grep ^LOVEBUG_PG_PASSWORD= /opt/backups/postgres-consolidation/credentials.env | cut -d= -f2-) +umask 077 +echo "SECOND_BRAIN_DATABASE_URL=postgresql://lovebug:${PW}@db.wg.herbylab.dev:5432/petalbrain" \ + > /opt/backups/postgres-consolidation/second-brain-transcribe.env +unset PW +``` + +The committed `deploy/tower/second-brain-transcribe.env.example` +documents the format and never carries a real secret. --- @@ -107,6 +159,12 @@ the worker starts after the tunnel comes up at boot. If the tunnel disappears mid-run the worker keeps polling and logs DB-unreachable warnings; it doesn't crash-loop. +`ExecStart=` calls the in-repo `deploy/tower/run-transcribe-worker.sh` +wrapper, which resolves the venv's CUDA-12 lib dirs at runtime and +prepends them to `LD_LIBRARY_PATH` before exec-ing `uv run`. systemd +does NOT inherit your shell's `LD_LIBRARY_PATH`, so the wrapper is +how the CUDA-12 pin survives across reboots and python upgrades. + ### Day-to-day commands ```bash diff --git a/deploy/tower/run-transcribe-worker.sh b/deploy/tower/run-transcribe-worker.sh new file mode 100755 index 0000000..6b342c9 --- /dev/null +++ b/deploy/tower/run-transcribe-worker.sh @@ -0,0 +1,64 @@ +#!/usr/bin/env bash +# +# Tower-side launcher for the transcribe worker. +# +# CTranslate2 4.7.2 needs libcublas.so.12 + libcudnn.so.9. Arch/EndeavourOS +# now ships CUDA 13, so we install the matching CUDA-12 runtime as pip +# wheels under the `tower` extra (nvidia-cublas-cu12, nvidia-cudnn-cu12). +# Those wheels drop their .so files into the venv's +# `site-packages/nvidia/{cublas,cudnn}/lib/` dirs, but nothing exports +# those onto LD_LIBRARY_PATH — systemd doesn't inherit Travis's shell. +# +# This wrapper resolves those paths at runtime from the venv's own +# Python (so it's robust to python-3.X upgrades, venv moves, and wheel +# version bumps), prepends them to LD_LIBRARY_PATH, and execs the +# worker. If the nvidia packages aren't importable we abort loudly so +# systemd surfaces a clear error instead of a silent libcublas load +# failure deep inside ctranslate2. + +set -euo pipefail + +cd "$(dirname "$(readlink -f "$0")")/../.." # project root: deploy/tower → ../.. + +# Resolve lib dirs from inside the project venv via `uv run`. Both +# packages must import cleanly — uv exits non-zero if not, and the +# `set -e` above propagates that. +NVIDIA_LIB_DIRS="$( + uv run python - <<'PY' +import os, sys +# nvidia.cublas / nvidia.cudnn are PEP 420 namespace packages — they +# have __path__ but no __init__.py and no __file__. Resolve via __path__ +# (which is a _NamespacePath; treat as iterable of strings). +mods = ("nvidia.cublas", "nvidia.cudnn") +dirs = [] +for m in mods: + try: + pkg = __import__(m, fromlist=["_"]) + except ImportError as exc: + sys.stderr.write( + f"[run-transcribe-worker] missing CUDA-12 runtime package {m!r}: {exc}\n" + "Install with: uv sync --extra tower\n" + ) + sys.exit(1) + paths = list(getattr(pkg, "__path__", []) or []) + if not paths: + sys.stderr.write( + f"[run-transcribe-worker] {m} has no __path__ — broken install?\n" + ) + sys.exit(1) + lib = os.path.join(paths[0], "lib") + if not os.path.isdir(lib): + sys.stderr.write( + f"[run-transcribe-worker] {m} is installed but {lib!r} is not a directory\n" + ) + sys.exit(1) + dirs.append(lib) +print(":".join(dirs)) +PY +)" + +# Prepend so our pinned CUDA-12 libs win over any system CUDA 13 left on +# the loader path. Preserve any existing LD_LIBRARY_PATH (rare but cheap). +export LD_LIBRARY_PATH="${NVIDIA_LIB_DIRS}${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}" + +exec uv run second-brain transcribe-worker "$@" diff --git a/deploy/tower/second-brain-transcribe.env.example b/deploy/tower/second-brain-transcribe.env.example index 2371c8c..8614a72 100644 --- a/deploy/tower/second-brain-transcribe.env.example +++ b/deploy/tower/second-brain-transcribe.env.example @@ -1,24 +1,38 @@ -# /etc/default/second-brain-transcribe +# /etc/default/second-brain-transcribe (template — copy + fill in the password). # -# Copy to /etc/default/second-brain-transcribe, chmod 0600, chown root:root -# (systemd reads it before dropping to User=herbyadmin so a non-readable -# permissions mode is fine — the herbyadmin user never touches this file). +# systemd reads this BEFORE dropping to User=herbyadmin, so installing it +# root:root mode 0600 is the right shape. NEVER commit the real value. +# +# Sourcing the password: +# The lovebug Postgres password is the LOVEBUG_PG_PASSWORD value in +# /opt/backups/postgres-consolidation/credentials.env on herbys-dev +# (mode 0600, host-only). It's a 64-character hex string — no URL +# encoding required. +# +# On herbys-dev there's already a ready-to-scp env file with the real +# password populated: +# /opt/backups/postgres-consolidation/second-brain-transcribe.env +# scp that to the tower instead of hand-copying: +# scp herbys-dev:/opt/backups/postgres-consolidation/second-brain-transcribe.env \ +# tower:/tmp/sb-env +# sudo install -m 0600 -o root -g root /tmp/sb-env \ +# /etc/default/second-brain-transcribe +# rm /tmp/sb-env +# +# DB host is db.wg.herbylab.dev:5432 over WireGuard, database name +# `petalbrain` (the post-consolidation rename). +# +# Note: this file is NOT a shell init script — `export VAR=...` +# additions in your interactive shell don't apply here, and changes +# require `systemctl restart second-brain-transcribe` to take effect. -# REQUIRED — petalbrain Postgres reached over the WireGuard tunnel. -# Hub-side hostname is db.wg.herbylab.dev (10.99.0.1); the tower is 10.99.0.2. -# No TLS — WireGuard already encrypts, and lovebug doesn't require SSL. -SECOND_BRAIN_DATABASE_URL=postgresql+psycopg://lovebug:REPLACE_ME@db.wg.herbylab.dev:5432/petalbrain +SECOND_BRAIN_DATABASE_URL=postgresql://lovebug:REPLACE_WITH_LOVEBUG_PG_PASSWORD@db.wg.herbylab.dev:5432/petalbrain -# OPTIONAL — only set if the tower has a non-standard whisper layout. -# Defaults from settings.toml: model=large-v3, device=cuda, compute_type=float16. +# OPTIONAL — only set to override the [whisper] block in settings.toml. +# Defaults are large-v3 / cuda / float16. # WHISPER_MODEL=large-v3 # WHISPER_DEVICE=cuda # WHISPER_COMPUTE_TYPE=float16 # OPTIONAL — identifier stamped into sources.claimed_by (default tower:). -# Useful if you ever run multiple tower workers and want to tell them apart. # SECOND_BRAIN_WORKER_ID=tower-main - -# OPTIONAL — bump worker log verbosity. INFO is the default. -# PYTHONUNBUFFERED=1 -# SECOND_BRAIN_LOG_LEVEL=DEBUG diff --git a/deploy/tower/second-brain-transcribe.service b/deploy/tower/second-brain-transcribe.service index 33805d9..0a0d2ce 100644 --- a/deploy/tower/second-brain-transcribe.service +++ b/deploy/tower/second-brain-transcribe.service @@ -7,6 +7,13 @@ Documentation=https://gitea.plantbasedsoutherner.com/petal-power/second-brain 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=herbyadmin @@ -18,20 +25,17 @@ WorkingDirectory=/opt/projects/homelab/second-brain # Env (SECOND_BRAIN_DATABASE_URL, optional knobs). 0600, owned by herbyadmin. EnvironmentFile=/etc/default/second-brain-transcribe -# `uv run` resolves the project venv. Keep the worker in the foreground so -# systemd owns the lifecycle; the worker handles SIGTERM/SIGINT cleanly and -# exits after the current iteration finishes. -ExecStart=/usr/bin/uv run second-brain transcribe-worker +# 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 -# 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. -StartLimitIntervalSec=300 -StartLimitBurst=5 - # 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 diff --git a/pyproject.toml b/pyproject.toml index 6a94e96..3485dbd 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -28,10 +28,19 @@ dependencies = [ # Max OAuth subscription and has no Python-side Anthropic dependency. api = ["anthropic>=0.40.0"] -# Tower-only: faster-whisper (CTranslate2) for the transcribe worker. -# Pulls in CUDA wheels — install with `uv sync --extra tower` on the -# tower box, leave it off on dev. CPU/int8 path works on this same wheel. -tower = ["faster-whisper>=1.0.0"] +# Tower-only: faster-whisper (CTranslate2) + the matched CUDA-12 runtime +# pulled in as wheels. Arch/EndeavourOS now ships CUDA 13 (libcublas.so.13) +# which ctranslate2 4.7+ cannot load — it wants libcublas.so.12 + cuDNN 9. +# Pinning the CUDA-12 runtime via pip wheels in the venv sidesteps the +# system CUDA mismatch entirely. sys_platform marker keeps these out of +# any non-Linux resolve (the nvidia wheels are Linux-only anyway, but the +# marker makes that explicit). Install with `uv sync --extra tower`; do +# not install on dev. +tower = [ + "faster-whisper>=1.0.0", + "nvidia-cublas-cu12; sys_platform == 'linux'", + "nvidia-cudnn-cu12>=9,<10; sys_platform == 'linux'", +] [dependency-groups] dev = [ diff --git a/uv.lock b/uv.lock index 9b9178b..0de1f93 100644 --- a/uv.lock +++ b/uv.lock @@ -988,6 +988,39 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/43/bb/e1c71a4295b1b1d1393d50dbb4f2a36283c6859d9d3892e84f00ec5a91d5/numpy-2.4.6-cp314-cp314t-win_arm64.whl", hash = "sha256:0c9136e14ed34a9e343a31c533d78a9813a69a3148332bce5e9821cb2f996e66", size = 10565867, upload-time = "2026-05-18T23:36:47.114Z" }, ] +[[package]] +name = "nvidia-cublas-cu12" +version = "12.9.2.10" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "nvidia-cuda-nvrtc-cu12" }, +] +wheels = [ + { url = "https://files.pythonhosted.org/packages/f7/a2/c96163a0fff1839c0c9548bbdeae7b853b867009e33b9b9264adc238b1cf/nvidia_cublas_cu12-12.9.2.10-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:5572131a59c3eebeeb1c4c8144f772d49372c20124916e072a0e3fc30df421d5", size = 575012079, upload-time = "2026-04-08T18:51:47.303Z" }, + { url = "https://files.pythonhosted.org/packages/cb/c0/0a517bfe63ccd3b92eb254d264e28fca3c7cab75d07daea315250fb1bf73/nvidia_cublas_cu12-12.9.2.10-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:e4f53a8ca8c5d6e8c492d0d0a3d565ecb59a751b19cfdaa4f6da0ab2104c1702", size = 581240110, upload-time = "2026-04-08T18:52:31.532Z" }, +] + +[[package]] +name = "nvidia-cuda-nvrtc-cu12" +version = "12.9.86" +source = { registry = "https://pypi.org/simple" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/b8/85/e4af82cc9202023862090bfca4ea827d533329e925c758f0cde964cb54b7/nvidia_cuda_nvrtc_cu12-12.9.86-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:210cf05005a447e29214e9ce50851e83fc5f4358df8b453155d5e1918094dcb4", size = 89568129, upload-time = "2025-06-05T20:02:41.973Z" }, + { url = "https://files.pythonhosted.org/packages/64/eb/c2295044b8f3b3b08860e2f6a912b702fc92568a167259df5dddb78f325e/nvidia_cuda_nvrtc_cu12-12.9.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:096d4de6bda726415dfaf3198d4f5c522b8e70139c97feef5cd2ca6d4cd9cead", size = 44528905, upload-time = "2025-06-05T20:02:29.754Z" }, +] + +[[package]] +name = "nvidia-cudnn-cu12" +version = "9.22.0.52" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "nvidia-cublas-cu12" }, +] +wheels = [ + { url = "https://files.pythonhosted.org/packages/51/ff/c6a098c1e0bccc68aac5f1684526cf8936abb7024dcc46dca315b8a6f47f/nvidia_cudnn_cu12-9.22.0.52-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:cd9011812498376f866b9826331cc965ac922eb2df8549c9f2989f10255e5001", size = 774536507, upload-time = "2026-05-08T15:36:09.067Z" }, + { url = "https://files.pythonhosted.org/packages/a0/8f/2ede6b758b7524608472010f632bdd3370ea271d715d1d66044614b84cdc/nvidia_cudnn_cu12-9.22.0.52-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:391b9a7ee6386daaca7f8dca41e83c2c99f760c9581a0400755e87b4287b8847", size = 718382818, upload-time = "2026-05-08T15:37:38.061Z" }, +] + [[package]] name = "onnxruntime" version = "1.26.0" @@ -1507,6 +1540,8 @@ api = [ ] tower = [ { name = "faster-whisper" }, + { name = "nvidia-cublas-cu12", marker = "sys_platform == 'linux'" }, + { name = "nvidia-cudnn-cu12", marker = "sys_platform == 'linux'" }, ] [package.dev-dependencies] @@ -1526,6 +1561,8 @@ requires-dist = [ { name = "faster-whisper", marker = "extra == 'tower'", specifier = ">=1.0.0" }, { name = "httpx", specifier = ">=0.28.0" }, { name = "jinja2", specifier = ">=3.1.0" }, + { name = "nvidia-cublas-cu12", marker = "sys_platform == 'linux' and extra == 'tower'" }, + { name = "nvidia-cudnn-cu12", marker = "sys_platform == 'linux' and extra == 'tower'", specifier = ">=9,<10" }, { name = "psycopg", extras = ["binary"], specifier = ">=3.2" }, { name = "psycopg-pool", specifier = ">=3.2" }, { name = "pydantic", specifier = ">=2.0.0" },