unslothai--unsloth/.github/workflows/studio-ui-smoke.yml

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.

# End-to-end Studio chat UI smoke via Playwright + Chromium against a
# headless Linux runner. Boots Studio with the smallest GGUF
# (gemma-3-270m-it UD-Q4_K_XL, ~254 MiB), drives the actual frontend
# bundle, and asserts the full bootstrap-password / change-password /
# send-message / persist-on-reload journey works end to end.
#
# This is the only workflow that catches regressions in the wiring
# between the React frontend and the FastAPI backend, e.g. assistant-ui
# version drift, /api/auth response shape changes, runtime-provider
# regressions, or chat-history persistence breaking. Backend-only and
# frontend-only CI happily pass while the actual user-visible UI is
# broken (cf. the 2026.5.1 chat-history release).

name: Studio UI CI

on:
  pull_request:
    paths:
      - 'studio/**'
      - 'unsloth/**'
      - 'unsloth_cli/**'
      - 'install.sh'
      - 'pyproject.toml'
      # The Playwright test files themselves -- a PR that ONLY edits
      # the test must still trigger UI CI.
      - 'tests/studio/**'
      - '.github/workflows/studio-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: ubuntu-latest
    timeout-minutes: 25
    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: '18892'
      HF_HOME: ${{ github.workspace }}/hf-cache
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
        with:
          persist-credentials: false

      - name: Linux deps
        run: |
          sudo apt-get update
          sudo apt-get install -y --no-install-recommends \
            libcurl4-openssl-dev libssl-dev jq

      - 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 }}-v2

      - name: Prime HF_HOME with the GGUF
        id: prime-hf
        if: steps.cache-hf.outputs.cache-hit != 'true' || steps.cache-hf.outcome != 'success'
        env:
          # Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
          HF_TOKEN: ${{ github.event_name != 'pull_request' && secrets.HF_TOKEN || '' }}
        run: |
          python -m pip install --upgrade huggingface_hub
          mkdir -p hf-cache
          bash .github/scripts/hf-download-with-retry.sh "$GGUF_REPO" "$GGUF_FILE"
          bash .github/scripts/hf-download-with-retry.sh ggml-org/models tinyllamas/stories260K.gguf

      - 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 }}-v2

      - name: Install Studio (--local, --no-torch)
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          # Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
          HF_TOKEN: ${{ github.event_name != 'pull_request' && secrets.HF_TOKEN || '' }}
        run: |
          mkdir -p logs
          set -o pipefail
          bash install.sh --local --no-torch 2>&1 | tee logs/install.log

      - name: Install Playwright + Chromium
        run: |
          pip install 'playwright>=1.45'
          # --with-deps installs the OS-level runtime libs Chromium
          # needs (libnss3, libxkbcommon, etc.). About 30 s on a
          # warm runner.
          python -m playwright install --with-deps chromium

      - 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
        # 180 s -- a cold runner with venv warm-up + lazy imports has
        # been seen to exceed 60 s. Failing the wait is more expensive
        # than waiting an extra two minutes.
        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
        # The Playwright test does its OWN /change-password through the
        # UI (Setup your account / Choose a new password), then loads
        # the model via page.evaluate against /api/inference/load with
        # the JWT it got from change-password. So the only thing we
        # have to hand it is the bootstrap password (so it can verify
        # post-rotation that the OLD bootstrap pw now returns 401).
        #
        # NEW + NEW2 are generated freshly per CI run via secrets.token_urlsafe
        # rather than hardcoded. If a workflow gets compromised, the
        # attacker can't replay a known-good rotated password against
        # any future / parallel Studio install -- the rotated value
        # only ever exists for the lifetime of this single job, masked
        # in the log via ::add-mask::.
        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://127.0.0.1:18892
          # The test file lives in the repo so it can be run locally
          # against a freshly-installed Studio (BASE_URL=...; STUDIO_OLD_PW=
          # $(cat ~/.unsloth/studio/auth/.bootstrap_password); python ...).
          PW_ART_DIR: logs/playwright
          # Strict mode: in CI a missing button / nav / dialog must
          # FAIL the test. Locally the test still runs against partial
          # Studio installs without STUDIO_UI_STRICT.
          STUDIO_UI_STRICT: '1'
        run: |
          mkdir -p logs/playwright
          python tests/studio/playwright_chat_ui.py

      - 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

      # The chat UI test ends by clicking the Shutdown menuitem, which
      # leaves the server dead. The extra UI test (Compare / Recipes /
      # Export / Studio / Settings) needs a fresh Studio, so we boot a
      # second one on a different port. Boot is fast (~3-5s on the
      # warm install we already did) so this adds little wall time.
      - name: Reset auth + boot Studio for extra UI tests (port 18894)
        run: |
          unsloth studio reset-password
          mkdir -p logs
          UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p 18894 \
            > logs/studio_extra.log 2>&1 &
          echo "STUDIO_EXTRA_PID=$!" >> "$GITHUB_ENV"

      - name: Wait for /api/health on 18894
        run: |
          for i in $(seq 1 180); do
            if curl -fs "http://127.0.0.1:18894/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://127.0.0.1:18894
          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'
          GGUF_REPO: ${{ env.GGUF_REPO }}
          GGUF_VARIANT: ${{ env.GGUF_VARIANT }}
        run: |
          mkdir -p logs/playwright_extra
          python tests/studio/playwright_extra_ui.py

      - name: Stop second Studio
        if: always()
        run: |
          kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true
          sleep 2

      # IME + multilingual paste regression (issue #5318 / PR #5327).
      # Third Studio on its own port so a hang here cannot poison the
      # earlier UI tests. No GGUF -- the bug surface is the composer.
      - name: Reset auth + boot Studio for IME / i18n tests (port 18896)
        run: |
          unsloth studio reset-password
          mkdir -p logs
          UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p 18896 \
            > logs/studio_ime.log 2>&1 &
          echo "STUDIO_IME_PID=$!" >> "$GITHUB_ENV"

      - name: Wait for /api/health on 18896
        run: |
          for i in $(seq 1 180); do
            if curl -fs "http://127.0.0.1:18896/api/health" > /tmp/health3.json; then
              jq -e '.status == "healthy"' /tmp/health3.json && break
            fi
            sleep 1
          done
          jq -e '.status == "healthy"' /tmp/health3.json

      - name: Pass bootstrap pw for IME / i18n test
        # IME smoke does the change-password against the bootstrap that
        # Studio's frontend injects into the page, so it only needs the
        # NEW password.
        run: |
          NEW="CIIme-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
          echo "::add-mask::$NEW"
          echo "STUDIO_IME_NEW_PW=$NEW" >> "$GITHUB_ENV"

      - name: Drive IME + multilingual paste regression with Playwright
        env:
          BASE_URL: http://127.0.0.1:18896
          STUDIO_NEW_PW: ${{ env.STUDIO_IME_NEW_PW }}
          PW_ART_DIR: logs/playwright_ime
          STUDIO_UI_STRICT: '1'
        run: |
          mkdir -p logs/playwright_ime
          python tests/studio/playwright_chat_ime_i18n.py

      - name: Stop third Studio
        if: always()
        run: |
          kill "${STUDIO_IME_PID}" 2>/dev/null || true
          sleep 2
          # Capture backend + llama-server logs (all three Studios share this
          # dir) so a stray 500 has a server-side traceback.
          mkdir -p logs/server-logs
          cp -r ~/.unsloth/studio/logs/. logs/server-logs/ 2>/dev/null || true

      - name: Upload Playwright artifacts
        # Always upload so a green run's screenshots stay reviewable --
        # catches "passed but the UI is silently broken" regressions.
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a  # v7.0.1
        with:
          name: studio-ui-smoke-artifacts
          path: |
            logs/studio.log
            logs/studio_extra.log
            logs/studio_ime.log
            logs/install.log
            logs/server-logs/
            logs/playwright
            logs/playwright_extra
            logs/playwright_ime
          retention-days: 7