unsloth/.github/workflows/studio-load-orchestrator-ci.yml

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
#
# Event-loop regression test for the Unsloth model-load orchestrator.
# Pins down issue #5642 (Win10 UI freeze on model load): the /load
# route calls LlamaCppBackend.detect_audio_type synchronously, blocking
# the FastAPI event loop on a chain of sync httpx.Client.post() probes.
#
# The suite stands up a stdlib fake llama-server + a tiny FastAPI app
# via uvicorn and asserts that detect_audio_type runs via
# asyncio.to_thread so concurrent /api/inference/load-progress polling
# stays responsive. CPU-only, no torch, no real llama.cpp binary, no
# GPU -- the matching cross-OS staging proof lives on
# danielhanchen/unsloth-staging-2 (Ubuntu / macOS / Windows all
# green at PR time).

name: Unsloth load-orchestrator CI

on:
  pull_request:
    paths:
      - 'studio/backend/routes/inference.py'
      - 'studio/backend/core/inference/llama_cpp.py'
      - 'tests/studio/load_freeze/**'
      - '.github/workflows/studio-load-orchestrator-ci.yml'
  push:
    branches: [main]
    paths:
      - 'studio/backend/routes/inference.py'
      - 'studio/backend/core/inference/llama_cpp.py'
      - 'tests/studio/load_freeze/**'
      - '.github/workflows/studio-load-orchestrator-ci.yml'
  workflow_dispatch:

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

permissions:
  contents: read

jobs:
  test:
    runs-on: ubuntu-latest
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1  # v7.0.1
        with:
          persist-credentials: false
      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97  # v7.0.0
        with:
          python-version: '3.12'
          cache: 'pip'
      - name: Install minimal deps (no torch, no unsloth)
        # The test stubs `loggers` and `structlog`, imports
        # core.inference.llama_cpp directly, and drives a small
        # FastAPI app. Nothing here pulls torch or any GPU code,
        # so the entire job typically completes in well under 60 s.
        run: |
          python -m pip install --upgrade pip
          python -m pip install \
            'pytest>=8' \
            'httpx>=0.27,<1' \
            'fastapi>=0.110,<1' \
            'uvicorn>=0.30,<1' \
            'anyio>=4'
      - name: Run load-orchestrator tests
        run: python -m pytest -v --tb=short tests/studio/load_freeze/