unsloth/.github/workflows/studio-mac-ui-smoke.yml
Daniel Han 54a86c3514
ci: route every hf download through xet-tuned stall-retry wrapper (#5476)
Root cause of the Mac json-images 30 min timeout (run 25950714888 /
PR #5430): huggingface_hub>=1.15 deprecated `hf_transfer` and routes
every transfer through `hf-xet`. The CI step's unpinned
`pip install --upgrade huggingface_hub hf_transfer` jumped to 1.15.0
+ hf-xet 1.5.0, the 940 MB mmproj finished in ~21s, then the 3 GB
gemma-4 GGUF made it to ~46% and went completely silent for the
remaining 29 minutes -- no progress bytes, no error, no exit -- until
the job timeout fired.

This wraps every CI `hf download` in a new
`.github/scripts/hf-download-with-retry.sh`:

  * Drops the no-op `HF_HUB_ENABLE_HF_TRANSFER=1` prefix and the
    `hf_transfer` install (both are deprecated on 1.15+ and only
    emit a FutureWarning now).
  * Exports the hf-xet high-performance knobs Daniel asked for:
        HF_XET_HIGH_PERFORMANCE=1
        HF_XET_CHUNK_CACHE_SIZE_BYTES=0
        HF_XET_NUM_CONCURRENT_RANGE_GETS=64
        HF_XET_RECONSTRUCT_WRITE_SEQUENTIALLY=0
        HF_XET_CLIENT_READ_TIMEOUT=500
  * Watchdogs each attempt: if `hf download` has not exited after
    HF_DOWNLOAD_STALL_SECONDS (default 180s = 3 min), SIGTERM,
    sleep 2, SIGKILL, then loop. Retries are unbounded; the
    enclosing job's `timeout-minutes` is the real cap.
  * Optional 3rd positional `LOCAL_DIR` -- omitted lets `hf` use
    the default HF_HUB_CACHE, which is what the HF_HOME-priming
    jobs need.

19 call sites migrated across mlx-ci.yml + 9 studio-*-smoke.yml
workflows. The inline `python -c "from huggingface_hub import
hf_hub_download; ..."` block in mlx-ci.yml is also routed through
the wrapper so every hf transfer in CI gets the same treatment.

Also reverts the json-images timeout 45 -> 30 from #5475: the bump
was masking this hang, not fixing it.
2026-05-15 21:11:56 -07:00

343 lines
14 KiB
YAML

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
# Mac counterpart to studio-ui-smoke.yml. Same Playwright + Chromium
# end-to-end chat UI flow, but on macos-14 (M1) so we catch
# Mac-specific frontend / backend wiring regressions that the Linux
# job would miss (e.g. the Mac Tauri shell loading the same React
# bundle, or the Mac llama.cpp prebuilt's HTTP layer behaving
# differently from the Linux build).
name: Mac Studio UI CI
on:
pull_request:
paths:
- 'studio/**'
- 'unsloth/**'
- 'unsloth_cli/**'
- 'install.sh'
- 'pyproject.toml'
- 'tests/studio/**'
- '.github/workflows/studio-mac-ui-smoke.yml'
push:
branches: [main, pip]
workflow_dispatch:
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions:
contents: read
jobs:
ui-smoke:
name: Chat UI Tests
runs-on: macos-14
timeout-minutes: 35
env:
GGUF_REPO: unsloth/gemma-3-270m-it-GGUF
GGUF_VARIANT: UD-Q4_K_XL
GGUF_FILE: gemma-3-270m-it-UD-Q4_K_XL.gguf
STUDIO_PORT: '18896'
HF_HOME: ${{ github.workspace }}/hf-cache
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'
cache: 'pip'
- name: Restore HF_HOME for ${{ env.GGUF_REPO }}
id: cache-hf
uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
continue-on-error: true
with:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v1
- name: Prime HF_HOME with the GGUF
id: prime-hf
if: steps.cache-hf.outputs.cache-hit != 'true' || steps.cache-hf.outcome != 'success'
env:
HF_TOKEN: ${{ secrets.HF_TOKEN }}
run: |
python -m pip install --upgrade huggingface_hub
mkdir -p hf-cache
bash .github/scripts/hf-download-with-retry.sh "$GGUF_REPO" "$GGUF_FILE"
- name: Save HF_HOME for ${{ env.GGUF_REPO }}
if: always() && steps.prime-hf.outcome == 'success'
uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
with:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v1
- name: Install Studio (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
mkdir -p logs
set -o pipefail
bash install.sh --local --no-torch 2>&1 | tee logs/install.log
- name: Assert install.sh used the Mac llama.cpp prebuilt
run: |
if grep -q "falling back to source build" logs/install.log; then
echo "::error::install.sh fell back to source-build llama.cpp on Mac. Studio must install the prebuilt llama-bNNNN-bin-macos-arm64 on Apple Silicon."
grep -E "llama-prebuilt|llama.cpp" logs/install.log | tail -60
exit 1
fi
- name: Install Playwright + Chromium
# No --with-deps on Mac: that flag installs Linux apt packages.
# GitHub-hosted macos-14 ships the system frameworks Chromium
# needs already.
# Pinned <1.58 because all 1.55-1.58 drivers ship Node 24 on
# macos-14 and intermittently hit 'SyntaxError: Unexpected end
# of JSON input' in pipeTransport.js. Run 25491698868 showed
# the crash hitting 100% of three retry attempts -- not a
# rare race but a hard reproduction. Belt-and-suspenders fix:
# the test scripts pass --single-process to Chromium (see
# tests/studio/playwright_chat_ui.py) AND we patch
# pipeTransport.js below to swallow JSON parse errors instead
# of crashing the driver Node process. Both together let the
# in-script retry recover from any residual flakes.
run: |
pip install 'playwright>=1.55,<1.58'
python -m playwright install chromium
- name: Patch Playwright pipeTransport.js to tolerate malformed JSON
# In Playwright 1.55-1.58, pipeTransport.js does
# `JSON.parse(message)` with no try/catch; when Chromium dies
# mid-write the partial buffer crashes the driver Node
# process and the test script exits with 'Connection closed
# while reading from the driver'. Newer Playwright versions
# added a try/catch upstream. Backport that here.
run: |
python - <<'PY'
import os, re, sys
import playwright
driver_dir = os.path.join(os.path.dirname(playwright.__file__), "driver", "package", "lib", "server")
path = os.path.join(driver_dir, "pipeTransport.js")
src = open(path).read()
# Wrap both `this.onmessage.call(null, JSON.parse(...))` sites in try/catch.
patched = re.sub(
r"this\.onmessage\.call\(null, JSON\.parse\((message2?)\)\);",
r"try { this.onmessage.call(null, JSON.parse(\1)); } "
r"catch (e) { /* swallow malformed JSON from a crashing browser */ }",
src,
)
if patched == src:
# Already patched, or upstream changed -- either way, don't fail the build.
print(f"pipeTransport.js: no JSON.parse calls matched at {path}; skipping.")
else:
open(path, "w").write(patched)
print(f"pipeTransport.js: patched JSON.parse calls in {path}")
PY
- name: Reset auth + boot Studio
run: |
unsloth studio reset-password
mkdir -p logs
UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p "$STUDIO_PORT" \
> logs/studio.log 2>&1 &
echo "STUDIO_PID=$!" >> "$GITHUB_ENV"
- name: Wait for /api/health
run: |
for i in $(seq 1 180); do
if curl -fs "http://127.0.0.1:${STUDIO_PORT}/api/health" > /tmp/health.json; then
jq -e '.status == "healthy"' /tmp/health.json && break
fi
sleep 1
done
jq -e '.status == "healthy"' /tmp/health.json
- name: Pass bootstrap password to the Playwright step
run: |
OLD=$(cat ~/.unsloth/studio/auth/.bootstrap_password)
NEW="CIUi-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
NEW2="CIUi-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
echo "::add-mask::$OLD"
echo "::add-mask::$NEW"
echo "::add-mask::$NEW2"
echo "STUDIO_OLD_PW=$OLD" >> "$GITHUB_ENV"
echo "STUDIO_NEW_PW=$NEW" >> "$GITHUB_ENV"
echo "STUDIO_NEW2_PW=$NEW2" >> "$GITHUB_ENV"
- name: Drive the chat UI with Playwright
env:
BASE_URL: http://127.0.0.1:18896
PW_ART_DIR: logs/playwright
STUDIO_UI_STRICT: '1'
# macos-14 free runner is 3 vCPU / 7 GB / no Metal-accel
# available to llama.cpp from CI; gemma-3-270m turn latency
# has been observed to crowd the 180s default. Triple it.
STUDIO_UI_TURN_TIMEOUT_MS: '540000'
# Retry up to 3 times to absorb the racy Playwright Node 24
# pipeTransport.js 'Unexpected end of JSON input' crash that
# fires intermittently on macos-14 free runners (Chromium
# browser process dies mid-test → driver Node process can't
# parse the truncated JSON-RPC line and exits). The retry
# FULLY resets Studio (kill, reset-password, reboot, wait
# /api/health, re-export bootstrap pw) before re-running the
# script so the change-password flow finds a fresh bootstrap.
# A real test failure (assertion / timeout) does NOT match the
# JSON pattern so it bypasses retry and surfaces immediately.
run: |
mkdir -p logs/playwright
attempt=1
max_attempts=3
while : ; do
set +e
python tests/studio/playwright_chat_ui.py 2>&1 | tee logs/playwright_attempt_${attempt}.log
rc=${PIPESTATUS[0]}
set -e
if [ "$rc" -eq 0 ]; then
break
fi
if grep -q "Unexpected end of JSON input" logs/playwright_attempt_${attempt}.log \
&& [ "$attempt" -lt "$max_attempts" ]; then
echo "::warning::Playwright pipeTransport JSON crash on attempt ${attempt}; resetting Studio and retrying..."
kill "${STUDIO_PID}" 2>/dev/null || true
sleep 2
unsloth studio reset-password
UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p "$STUDIO_PORT" \
> "logs/studio_retry_${attempt}.log" 2>&1 &
STUDIO_PID=$!
echo "STUDIO_PID=$STUDIO_PID" >> "$GITHUB_ENV"
for i in $(seq 1 180); do
if curl -fs "http://127.0.0.1:${STUDIO_PORT}/api/health" > /tmp/health.json \
&& jq -e '.status == "healthy"' /tmp/health.json >/dev/null; then
break
fi
sleep 1
done
STUDIO_OLD_PW=$(cat ~/.unsloth/studio/auth/.bootstrap_password)
STUDIO_NEW_PW="CIUi-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
STUDIO_NEW2_PW="CIUi-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
echo "::add-mask::$STUDIO_OLD_PW"
echo "::add-mask::$STUDIO_NEW_PW"
echo "::add-mask::$STUDIO_NEW2_PW"
export STUDIO_OLD_PW STUDIO_NEW_PW STUDIO_NEW2_PW
attempt=$((attempt + 1))
sleep 3
continue
fi
exit "$rc"
done
- name: Stop Studio (chat-ui ends with Shutdown click; this is belt-and-suspenders)
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true
sleep 2
- name: Reset auth + boot Studio for extra UI tests (port 18897)
run: |
unsloth studio reset-password
mkdir -p logs
UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p 18897 \
> logs/studio_extra.log 2>&1 &
echo "STUDIO_EXTRA_PID=$!" >> "$GITHUB_ENV"
- name: Wait for /api/health on 18897
run: |
for i in $(seq 1 180); do
if curl -fs "http://127.0.0.1:18897/api/health" > /tmp/health2.json; then
jq -e '.status == "healthy"' /tmp/health2.json && break
fi
sleep 1
done
jq -e '.status == "healthy"' /tmp/health2.json
- name: Pass bootstrap pw for extra UI test
run: |
OLD=$(cat ~/.unsloth/studio/auth/.bootstrap_password)
NEW="CIUiExtra-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
echo "::add-mask::$OLD"
echo "::add-mask::$NEW"
echo "STUDIO_EXTRA_OLD_PW=$OLD" >> "$GITHUB_ENV"
echo "STUDIO_EXTRA_NEW_PW=$NEW" >> "$GITHUB_ENV"
- name: Drive Compare/Recipes/Export/Studio/Settings with Playwright
env:
BASE_URL: http://127.0.0.1:18897
STUDIO_OLD_PW: ${{ env.STUDIO_EXTRA_OLD_PW }}
STUDIO_NEW_PW: ${{ env.STUDIO_EXTRA_NEW_PW }}
PW_ART_DIR: logs/playwright_extra
STUDIO_UI_STRICT: '1'
# See "Drive the chat UI" step.
STUDIO_UI_TURN_TIMEOUT_MS: '540000'
GGUF_REPO: ${{ env.GGUF_REPO }}
GGUF_VARIANT: ${{ env.GGUF_VARIANT }}
# Same pipeTransport JSON-crash retry shape as "Drive the chat
# UI with Playwright" -- see comment there.
run: |
mkdir -p logs/playwright_extra
attempt=1
max_attempts=3
while : ; do
set +e
python tests/studio/playwright_extra_ui.py 2>&1 | tee logs/playwright_extra_attempt_${attempt}.log
rc=${PIPESTATUS[0]}
set -e
if [ "$rc" -eq 0 ]; then
break
fi
if grep -q "Unexpected end of JSON input" logs/playwright_extra_attempt_${attempt}.log \
&& [ "$attempt" -lt "$max_attempts" ]; then
echo "::warning::Playwright pipeTransport JSON crash on attempt ${attempt}; resetting Studio and retrying..."
kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true
sleep 2
unsloth studio reset-password
UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p 18897 \
> "logs/studio_extra_retry_${attempt}.log" 2>&1 &
STUDIO_EXTRA_PID=$!
echo "STUDIO_EXTRA_PID=$STUDIO_EXTRA_PID" >> "$GITHUB_ENV"
for i in $(seq 1 180); do
if curl -fs "http://127.0.0.1:18897/api/health" > /tmp/health2.json \
&& jq -e '.status == "healthy"' /tmp/health2.json >/dev/null; then
break
fi
sleep 1
done
STUDIO_OLD_PW=$(cat ~/.unsloth/studio/auth/.bootstrap_password)
STUDIO_NEW_PW="CIUiExtra-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
echo "::add-mask::$STUDIO_OLD_PW"
echo "::add-mask::$STUDIO_NEW_PW"
export STUDIO_OLD_PW STUDIO_NEW_PW
attempt=$((attempt + 1))
sleep 3
continue
fi
exit "$rc"
done
- name: Stop second Studio
if: always()
run: |
kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true
sleep 2
- name: Upload Playwright artifacts
if: always()
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
with:
name: mac-studio-ui-smoke-artifacts
path: |
logs/studio.log
logs/studio_extra.log
logs/install.log
logs/playwright
logs/playwright_extra
retention-days: 7