unsloth/.github/workflows/studio-inference-smoke.yml

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

# End-to-end smoke: install Studio via install.sh --local --no-torch, download
# a tiny GGUF, boot Studio, log in, change password, load the model, send a
# chat completion, assert a non-empty response. Only workflow that tests "the
# app actually works".
#
# Model: Qwen3.5-2B UD-IQ3_XXS (~890 MiB) -- small enough that the cache miss
# is cheap and inference fits in the 25 min CPU-runner budget. GGUF is cached
# across runs via actions/cache.

name: Studio GGUF CI

on:
  pull_request:
    paths:
      - 'studio/**'
      - 'unsloth/**'
      - 'unsloth_cli/**'
      - 'install.sh'
      - 'pyproject.toml'
      - '.github/workflows/studio-inference-smoke.yml'
  push:
    branches: [main, pip]
  # Manual trigger for pre-warming the GGUF cache on main, or re-running
  # against an arbitrary branch without pushing a no-op commit.
  workflow_dispatch:

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

env:
  GGUF_REPO: unsloth/Qwen3.5-2B-GGUF
  GGUF_FILE: Qwen3.5-2B-UD-IQ3_XXS.gguf
  STUDIO_PORT: '18888'

jobs:
  inference:
    name: Studio boots, loads a GGUF, answers a chat completion
    runs-on: ubuntu-latest
    timeout-minutes: 25
    steps:
      - uses: actions/checkout@v4

      - name: Linux dependencies for llama.cpp prebuilt
        run: |
          sudo apt-get update
          sudo apt-get install -y --no-install-recommends \
            libcurl4-openssl-dev libssl-dev jq

      - uses: actions/setup-node@v4
        with:
          node-version: '22'
          cache: 'npm'
          cache-dependency-path: studio/frontend/package-lock.json

      - uses: actions/setup-python@v5
        with:
          python-version: '3.12'
          cache: 'pip'

      - name: Cache GGUF model file
        id: cache-gguf
        uses: actions/cache@v4
        with:
          path: gguf-cache
          key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1

      - name: Download GGUF if cache miss
        if: steps.cache-gguf.outputs.cache-hit != 'true'
        run: |
          # huggingface-cli was deprecated in huggingface_hub 1.13; the new CLI is `hf`.
          python -m pip install --upgrade huggingface_hub hf_transfer
          mkdir -p gguf-cache
          HF_HUB_ENABLE_HF_TRANSFER=1 \
            hf download "$GGUF_REPO" "$GGUF_FILE" --local-dir gguf-cache

      - name: Install Studio (--local, --no-torch keeps the install lean)
        run: |
          mkdir -p logs
          set -o pipefail
          bash install.sh --local --no-torch 2>&1 | tee logs/install.log

      - name: Assert llama.cpp prebuilt was installed (no source-build fallback)
        # ubuntu-latest is CPU-only x86_64, so studio/setup.sh should route
        # to ggml-org/llama.cpp and grab bin-ubuntu-x64.tar.gz. A source
        # build here means the routing regressed.
        run: |
          if grep -q "falling back to source build" logs/install.log; then
            echo "::error::llama.cpp prebuilt path failed on ubuntu-latest. studio/setup.sh routing regressed; CPU-only Linux x86_64 should hit ggml-org/llama.cpp's bin-ubuntu-x64.tar.gz."
            grep -E "llama-prebuilt|llama.cpp" logs/install.log | tail -60
            exit 1
          fi
          if ! grep -qE "prebuilt installed and validated|prebuilt up to date and validated" logs/install.log; then
            echo "::error::install.log does not contain the success marker for the llama.cpp prebuilt path. Did setup.sh skip the prebuilt install?"
            grep -E "llama-prebuilt|llama.cpp" logs/install.log | tail -60
            exit 1
          fi
          echo "llama.cpp prebuilt path used successfully"

      - name: Reset auth + start Studio in the background
        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 $(seq 1 60); do
            if curl -fs "http://127.0.0.1:${STUDIO_PORT}/api/health" > /tmp/health.json; then
              echo "ready after ${i}s"
              cat /tmp/health.json
              jq -e '.status == "healthy"' /tmp/health.json
              exit 0
            fi
            sleep 1
          done
          echo "Studio did not become healthy in 60s"
          tail -200 logs/studio.log
          exit 1

      - name: Login + change bootstrap password
        run: |
          PW=$(cat ~/.unsloth/studio/auth/.bootstrap_password)
          NEW="CIPasswordSmoke12345!"
          TOKEN=$(curl -fs -X POST "http://127.0.0.1:${STUDIO_PORT}/api/auth/login" \
            -H 'content-type: application/json' \
            -d "{\"username\":\"unsloth\",\"password\":\"$PW\"}" | jq -r .access_token)
          curl -fs -X POST "http://127.0.0.1:${STUDIO_PORT}/api/auth/change-password" \
            -H "Authorization: Bearer $TOKEN" -H 'content-type: application/json' \
            -d "{\"current_password\":\"$PW\",\"new_password\":\"$NEW\"}" > /dev/null
          # Re-login to clear must_change_password flag.
          NEW_TOKEN=$(curl -fs -X POST "http://127.0.0.1:${STUDIO_PORT}/api/auth/login" \
            -H 'content-type: application/json' \
            -d "{\"username\":\"unsloth\",\"password\":\"$NEW\"}" | jq -r .access_token)
          echo "TOKEN=$NEW_TOKEN" >> "$GITHUB_ENV"

      - name: Load the GGUF into Studio
        run: |
          GGUF_PATH="$GITHUB_WORKSPACE/gguf-cache/${GGUF_FILE}"
          ls -lh "$GGUF_PATH"
          curl -fs -X POST "http://127.0.0.1:${STUDIO_PORT}/api/inference/load" \
            -H "Authorization: Bearer $TOKEN" -H 'content-type: application/json' \
            --max-time 600 \
            -d "{\"model_path\":\"$GGUF_PATH\",\"is_lora\":false,\"max_seq_length\":2048}" \
            | jq '{status, display_name, is_gguf, context_length}'

      - name: Send a chat completion + assert non-empty response
        run: |
          RESP=$(curl -fs -X POST "http://127.0.0.1:${STUDIO_PORT}/api/inference/chat/completions" \
            -H "Authorization: Bearer $TOKEN" -H 'content-type: application/json' \
            --max-time 900 \
            -d '{
              "messages":[{"role":"user","content":"Say hello in one short sentence."}],
              "max_tokens":40,
              "stream":false
            }')
          echo "raw response: $RESP"
          CONTENT=$(echo "$RESP" | jq -r '.choices[0].message.content // empty')
          echo "model response: $CONTENT"
          if [ -z "$CONTENT" ]; then
            echo "::error::Empty assistant response from Studio"
            exit 1
          fi

      - name: Stop Studio
        if: always()
        run: |
          kill "${STUDIO_PID}" || true
          sleep 2
          ss -tln | grep ":${STUDIO_PORT}" || true

      - name: Upload Studio + install logs on failure
        if: failure()
        uses: actions/upload-artifact@v4
        with:
          name: studio-inference-log
          path: |
            logs/studio.log
            logs/install.log
          retention-days: 7