fb4bd0b777`actions/setup-node@v6.4.0` with `cache: 'npm'` silently aborts the entire job on Windows runners when the npm cache path returned by `npm config get cache` (`C:\npm\cache`) does not yet exist on a fresh runner -- the step exits 24s in with no error message and every following step gets skipped. See npm/cli#7308 for the underlying EEXIST / missing-dir race in the npm cache directory. This mirrors the existing precedent in `studio-windows-ui-smoke.yml`'s `setup-python` block, which already dropped `cache: 'pip'` for the same reason (post-step fatal error on a missing pip cache dir). The frontend `npm ci` is fast enough without the cache that the reliability gain is worth the ~30s.
279 lines
12 KiB
YAML
279 lines
12 KiB
YAML
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
|
|
|
|
# Windows counterpart to studio-update-smoke.yml /
|
|
# studio-mac-update-smoke.yml. Verifies that on the FREE
|
|
# windows-latest runner:
|
|
#
|
|
# 1. install.ps1 --local --no-torch installs Studio AND auto-fetches
|
|
# the prebuilt llama.cpp Windows binary (llama-bNNNN-bin-win-cpu-
|
|
# x64 from ggml-org/llama.cpp). Hitting the source-build fallback
|
|
# is treated as an Unsloth bug -- Studio must always pick the
|
|
# prebuilt on Windows.
|
|
# 2. unsloth studio update --local is idempotent. Two consecutive
|
|
# runs both report "prebuilt up to date and validated", no
|
|
# source-build fallback. The CLI's _find_setup_script picks
|
|
# setup.ps1 on Windows automatically.
|
|
# 3. The installed Studio still boots and /api/health returns
|
|
# healthy after the update path.
|
|
|
|
name: Windows Studio Update CI
|
|
|
|
on:
|
|
pull_request:
|
|
paths:
|
|
- 'install.ps1'
|
|
- 'studio/setup.ps1'
|
|
- 'studio/setup.bat'
|
|
- 'studio/install_python_stack.py'
|
|
- 'studio/install_llama_prebuilt.py'
|
|
- 'studio/backend/requirements/**'
|
|
- 'unsloth_cli/commands/studio.py'
|
|
- 'pyproject.toml'
|
|
- '.github/workflows/studio-windows-update-smoke.yml'
|
|
push:
|
|
branches: [main, pip]
|
|
workflow_dispatch:
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
permissions:
|
|
contents: read
|
|
|
|
jobs:
|
|
update-idempotency:
|
|
name: Studio Updating Tests
|
|
runs-on: windows-latest
|
|
timeout-minutes: 30
|
|
defaults:
|
|
run:
|
|
shell: bash
|
|
env:
|
|
# Force UTF-8 for stdio (Windows defaults to cp1252; hf
|
|
# download / Studio CLI print "✓" checkmarks and crash
|
|
# otherwise).
|
|
PYTHONIOENCODING: utf-8
|
|
PYTHONUTF8: '1'
|
|
steps:
|
|
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
|
|
with:
|
|
node-version: '22'
|
|
|
|
- uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
|
|
with:
|
|
python-version: '3.12'
|
|
# Don't cache pip: install.ps1 + setup.ps1 go through uv
|
|
# and never populate ~/.cache/pip; setup-python's post-step
|
|
# then fatal-errors with "Cache folder path is retrieved
|
|
# for pip but doesn't exist on disk".
|
|
|
|
- name: Pre-install Windows tweaks (npm 11 + Defender exclusions)
|
|
shell: pwsh
|
|
# Two surgical fixes against measured Windows-only install
|
|
# waste (vs Mac/Linux on the same SHA):
|
|
#
|
|
# (1) npm. setup.ps1 line 1109-1145 requires Node 22.12+ (or
|
|
# 20.19+ / 23+) AND npm >=11 because Vite 8 needs both.
|
|
# actions/setup-node@v4 with `node-version: '22'` lands
|
|
# Node 22.22.2 + the npm 10.9.7 it bundles, so the npm
|
|
# check fails and setup.ps1 falls through to the
|
|
# "winget install Node.js LTS" branch -- a ~35 s reinstall
|
|
# of Node we don't need. `npm install -g npm@^11` updates
|
|
# the bundled npm in-place in ~5 s, which makes setup.ps1
|
|
# short-circuit on the existing Node.
|
|
#
|
|
# (2) Defender. windows-latest's real-time scan opens / hashes
|
|
# every file Studio writes during install (Vite output =
|
|
# thousands of small chunks, uv pip = wheel-extraction =
|
|
# thousands of small files). The latency dominates the
|
|
# 200 s frontend build and the 90 s deps install. Adding
|
|
# ExclusionPath entries for the directories the install
|
|
# writes to drops per-file open latency from ~ms to ~us.
|
|
# Add-MpPreference needs admin; the runneradmin user has
|
|
# it, but wrap in try/catch so a permission flake leaves
|
|
# the install otherwise unaffected.
|
|
run: |
|
|
$ProgressPreference = 'SilentlyContinue'
|
|
Write-Host "npm version before upgrade: $(npm -v)"
|
|
npm install -g 'npm@^11' 2>&1 | Out-Host
|
|
Write-Host "npm version after upgrade: $(npm -v)"
|
|
# NOTE: do NOT pre-create these directories before adding the
|
|
# exclusion -- creating an empty studio/frontend/dist trips
|
|
# setup.ps1 line 1281-1296's mtime-based "is the frontend
|
|
# stale?" check into "up to date, skip rebuild", because the
|
|
# newly-created dist's mtime is younger than every source
|
|
# file. Studio then boots with an empty dist and 500s on
|
|
# GET / with FileNotFoundError: dist\index.html. See run
|
|
# 25546676715 / job 74984469728.
|
|
# Add-MpPreference accepts paths that do not yet exist; the
|
|
# exclusion is registered and applies when the path
|
|
# materialises.
|
|
foreach ($p in @(
|
|
"$env:USERPROFILE\.unsloth",
|
|
"$env:USERPROFILE\AppData\Local\uv",
|
|
"$env:GITHUB_WORKSPACE\studio\frontend\node_modules",
|
|
"$env:GITHUB_WORKSPACE\studio\frontend\dist"
|
|
)) {
|
|
try {
|
|
Add-MpPreference -ExclusionPath $p -ErrorAction Stop
|
|
Write-Host "Defender exclusion added: $p"
|
|
} catch {
|
|
Write-Host "Defender exclusion skipped ($($_.Exception.Message)): $p"
|
|
}
|
|
}
|
|
|
|
- name: Install Studio (--local, --no-torch)
|
|
shell: pwsh
|
|
env:
|
|
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
New-Item -ItemType Directory -Force -Path logs | Out-Null
|
|
# *>&1 captures Write-Host (Information stream) output;
|
|
# plain 2>&1 does not. setup.ps1 emits "prebuilt installed
|
|
# and validated" via Write-Host, and we grep for that.
|
|
$ProgressPreference = 'SilentlyContinue'
|
|
& ./install.ps1 --local --no-torch *>&1 | Tee-Object -FilePath logs/install.log
|
|
|
|
- name: Assert install.ps1 used the Windows llama.cpp prebuilt
|
|
run: |
|
|
# Filesystem-based check (setup.ps1's stream output isn't
|
|
# captured back through the parent pipeline).
|
|
LLAMA_DIR=~/.unsloth/llama.cpp
|
|
INFO="$LLAMA_DIR/UNSLOTH_PREBUILT_INFO.json"
|
|
BIN="$LLAMA_DIR/build/bin/Release/llama-server.exe"
|
|
if grep -q "falling back to source build" logs/install.log; then
|
|
echo "::error::install.ps1 fell back to source-build llama.cpp on Windows."
|
|
grep -E "llama-prebuilt|llama.cpp" logs/install.log | tail -60
|
|
exit 1
|
|
fi
|
|
if [ ! -f "$INFO" ]; then
|
|
echo "::error::no UNSLOTH_PREBUILT_INFO.json at $INFO."
|
|
ls -la "$LLAMA_DIR" || true
|
|
exit 1
|
|
fi
|
|
if [ ! -f "$BIN" ]; then
|
|
echo "::error::no llama-server.exe at $BIN."
|
|
ls -la "$LLAMA_DIR/build/bin" || true
|
|
exit 1
|
|
fi
|
|
echo "install.ps1 installed the Windows prebuilt llama.cpp:"
|
|
cat "$INFO"
|
|
|
|
- name: Add Studio shim to GITHUB_PATH
|
|
run: |
|
|
SHIM_DIR=~/.unsloth/studio/bin
|
|
if [ ! -f "$SHIM_DIR/unsloth.exe" ]; then
|
|
echo "::error::unsloth.exe shim not found at $SHIM_DIR"
|
|
ls -la ~/.unsloth/studio/ || true
|
|
exit 1
|
|
fi
|
|
cygpath -w "$SHIM_DIR" >> "$GITHUB_PATH"
|
|
|
|
- name: Patch Studio venv with full typer / pydantic dep trees
|
|
# install.ps1 runs `uv pip install --no-deps -r
|
|
# no-torch-runtime.txt` to keep torch out of transitive
|
|
# resolution from accelerate/peft/trl. That also drops
|
|
# typer's and pydantic's runtime deps unless they're
|
|
# explicitly pinned in no-torch-runtime.txt. We pin the
|
|
# known ones (click, shellingham, annotated-doc, rich,
|
|
# pydantic-core, annotated-types, typing-inspection, ...)
|
|
# but typer / pydantic minor versions can introduce new
|
|
# transitive deps that are NOT in our pin list.
|
|
#
|
|
# Belt-and-suspenders: re-install typer + pydantic +
|
|
# huggingface_hub WITH their deps into the Studio venv.
|
|
# `pip install --upgrade` only adds missing packages; it
|
|
# never down-shifts an installed version. Cannot pull
|
|
# torch (none of typer / pydantic / huggingface_hub depend
|
|
# on it).
|
|
run: |
|
|
STUDIO_PY=~/.unsloth/studio/unsloth_studio/Scripts/python.exe
|
|
if [ ! -f "$STUDIO_PY" ]; then
|
|
echo "::error::Studio venv python not at $STUDIO_PY"
|
|
ls -la ~/.unsloth/studio/ || true
|
|
exit 1
|
|
fi
|
|
"$STUDIO_PY" -m pip install --upgrade typer pydantic huggingface_hub
|
|
|
|
- name: First update should be a no-op (prebuilt already validated)
|
|
env:
|
|
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
set -o pipefail
|
|
unsloth studio update --local 2>&1 | tee logs/update.log
|
|
if grep -q "falling back to source build" logs/update.log; then
|
|
echo "::error::studio update fell back to source-build llama.cpp on Windows."
|
|
grep -E "llama-prebuilt|llama.cpp" logs/update.log | tail -60
|
|
exit 1
|
|
fi
|
|
if ! grep -qE "prebuilt up to date and validated|prebuilt installed and validated" logs/update.log; then
|
|
echo "::error::no prebuilt up-to-date marker in update.log."
|
|
grep -E "llama-prebuilt|llama.cpp" logs/update.log | tail -60
|
|
exit 1
|
|
fi
|
|
echo "update path took the prebuilt fast path"
|
|
|
|
- name: Second update must also be a no-op
|
|
env:
|
|
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
set -o pipefail
|
|
unsloth studio update --local 2>&1 | tee logs/update2.log
|
|
grep -q "falling back to source build" logs/update2.log && {
|
|
echo "::error::second update fell back to source build on Windows"
|
|
tail -60 logs/update2.log; exit 1; } || true
|
|
grep -qE "prebuilt up to date and validated|prebuilt installed and validated" logs/update2.log
|
|
echo "second update was clean"
|
|
|
|
- name: Boot Studio briefly to confirm the install is still usable
|
|
run: |
|
|
mkdir -p logs
|
|
UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p 18891 \
|
|
> logs/studio.log 2>&1 &
|
|
PID=$!
|
|
HEALTHY=""
|
|
# Use jq (a Git Bash builtin) instead of `python -c
|
|
# open('/tmp/health.json')` to read the saved health
|
|
# response. Bash on windows-latest is MSYS Git Bash, which
|
|
# resolves `/tmp/...` against the MSYS root, while the
|
|
# python interpreter is Windows-native and resolves it
|
|
# against the current drive's root. The two paths don't
|
|
# agree, so python never finds the file curl just wrote.
|
|
# jq reads through MSYS, so the path matches. Mirrors what
|
|
# studio-windows-api-smoke.yml and the other Windows smoke
|
|
# workflows already do.
|
|
for i in $(seq 1 60); do
|
|
if curl -fs http://127.0.0.1:18891/api/health > /tmp/health.json; then
|
|
if jq -e '.status == "healthy"' /tmp/health.json >/dev/null; then
|
|
HEALTHY=1
|
|
break
|
|
fi
|
|
fi
|
|
sleep 1
|
|
done
|
|
if [ -z "$HEALTHY" ]; then
|
|
echo "Studio failed to come up after \`update\`"
|
|
tail -200 logs/studio.log
|
|
kill "$PID" 2>/dev/null || true
|
|
exit 1
|
|
fi
|
|
kill "$PID" 2>/dev/null || true
|
|
echo "post-update Studio /api/health OK"
|
|
|
|
- name: Upload update logs
|
|
if: always()
|
|
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
|
|
with:
|
|
name: windows-studio-update-log
|
|
path: |
|
|
logs/install.log
|
|
logs/update.log
|
|
logs/update2.log
|
|
logs/studio.log
|
|
retention-days: 7
|