python-bindings.yml

name: python-bindings

# The EVERY-PR gate for the PYTHON binding:
#   - lint:          generated-FFI drift gate (also regenerates the
#                    binding-neutral include/transcribe.abihash) +
#                    version-sync across the sources of truth.
#   - python-shared: a shared libtranscribe, the pure-C api_smoke as an
#                    exported-symbol canary, and the Python test suite (model
#                    tests un-skip when the canary GGUFs are fetchable).
#
# The binding-agnostic native gates (cpp-tests, cpp-tests-sanitized,
# provider-dl-vulkan, link-smoke, posture-lint) moved to native-ci.yml
# (2026-06-13, bindings-shared-infra): they certify the C contracts EVERY
# binding relies on, not just Python's. Job names were preserved across
# the move.
#
# The full WHEEL matrix (python-wheels.yml) deliberately does NOT run per PR:
# it runs on workflow_dispatch and on every publish (rehearsal or release).
# This workflow plus native-ci.yml is what must stay green on every change.

on:
  push:
    branches: [main]
    paths:
      - "bindings/python/**"
      - "include/**"
      - "src/**"
      - "scripts/lib/**"
      - "scripts/convert-gigaam.py"
      - "scripts/dump_reference_gigaam_author.py"
      - "scripts/test_convert_gigaam.py"
      - "tests/**"
      - "ggml/**"
      - "CMakeLists.txt"
      - ".github/workflows/python-bindings.yml"
      - ".github/actions/**"
      - "scripts/ci/vulkan_degradation_check.py"
  pull_request:
    paths:
      - "bindings/python/**"
      - "include/**"
      - "src/**"
      - "scripts/lib/**"
      - "scripts/convert-gigaam.py"
      - "scripts/dump_reference_gigaam_author.py"
      - "scripts/test_convert_gigaam.py"
      - "tests/**"
      - "ggml/**"
      - "CMakeLists.txt"
      - ".github/workflows/python-bindings.yml"
      - ".github/actions/**"
      - "scripts/ci/vulkan_degradation_check.py"
  workflow_dispatch:

# The generated FFI layer is pinned to one libclang so the drift gate's embedded
# `libclang: <version>` line is reproducible across runs.
env:
  LIBCLANG_PIN: "libclang==18.1.1"

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

jobs:
  lint:
    # Idle-friendly job on the Hetzner box (free); falls back to nothing —
    # an offline box fails bounded via the timeout. BEFORE the repo goes
    # public: move PR-triggered self-hosted jobs to hosted runners or gate
    # them on non-PR events (fork PRs + self-hosted = code exec on the box).
    runs-on: [self-hosted, Linux, X64, hetzner]
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@v6
      - uses: astral-sh/setup-uv@v8.2.0
        with:
          version: "0.12.19"
      - name: Install clang (libclang resource-dir headers)
        # Idempotent for the persistent self-hosted box: install once, no-op
        # after (and no sudo needed when clang is already present).
        run: |
          command -v clang >/dev/null || \
            { sudo apt-get update && sudo apt-get install -y clang; }
      - name: Generated-FFI drift gate
        run: |
          uv run --no-project --with "$LIBCLANG_PIN" \
            bindings/python/_generate/generate.py --check
      - name: Version sync (header / pyproject / __init__)
        run: uv run --no-project bindings/python/_generate/check_version_sync.py
      - name: GGUF writer layout
        run: uv run scripts/lib/test_gguf_writer.py
      - name: Hugging Face snapshot commit check
        run: uv run scripts/lib/test_hf_source.py
      - name: GigaAM variant sources and loader
        run: uv run scripts/lib/test_gigaam_hf.py
      - name: GigaAM converter profiles
        run: uv run scripts/test_convert_gigaam.py

  python-shared:
    runs-on: blacksmith-2vcpu-ubuntu-2404
    env:
      HF_TOKEN: ${{ secrets.HF_TOKEN }}
    steps:
      - uses: actions/checkout@v6
      - uses: astral-sh/setup-uv@v8.2.0
        with:
          version: "0.12.19"
      - name: Install build deps
        run: sudo apt-get update && sudo apt-get install -y cmake ninja-build ccache
      - name: CPU ISA signature (segregates ccache across the heterogeneous fleet)
        # ggml builds with -march=native here (the dev posture under test);
        # ccache hashes the literal flag, not the ISA it resolves to, so a
        # cache compiled on a richer CPU SIGILLs on a weaker one. Key the
        # cache by the CPU's feature flags instead.
        run: echo "CPU_SIG=$(grep -m1 '^flags' /proc/cpuinfo | sha256sum | cut -c1-8)" >> "$GITHUB_ENV"
      - name: ccache (compile cache across runs)
        uses: actions/cache@v5
        with:
          path: ~/.cache/ccache
          key: ccache-shared-${{ env.CPU_SIG }}-${{ github.sha }}
          restore-keys: ccache-shared-${{ env.CPU_SIG }}-
      # Shared build in the official-wheel posture (no OpenMP / system BLAS), so
      # the canary exercises the same configuration the provider wheels ship.
      - name: Configure (shared, wheel posture)
        run: |
          cmake -B build-shared -G Ninja -DCMAKE_BUILD_TYPE=Release \
            -DTRANSCRIBE_BUILD_SHARED=ON \
            -DTRANSCRIBE_USE_OPENMP=OFF \
            -DTRANSCRIBE_USE_SYSTEM_BLAS=OFF \
            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
      - name: Build
        run: cmake --build build-shared -j
      - name: api_smoke (exported-symbol canary) + extension umbrella
        run: ctest --test-dir build-shared --output-on-failure
      # The canary model upgrades this lane from "imports and ABI" to a real
      # end-to-end transcription. Guarded on HF_TOKEN (the model repo is
      # private for now; forks have no token) — without it the model tests
      # skip cleanly, exactly as before.
      - uses: ./.github/actions/fetch-canary
        with:
          hf-token: ${{ secrets.HF_TOKEN }}
      - name: Python tests (real transcription when the canary is present)
        run: |
          # libtranscribe.so is dlopen'd by ctypes; help it resolve its sibling
          # ggml shared libs in the build tree.
          export LD_LIBRARY_PATH="$(find "$PWD/build-shared" -name '*.so' \
            -printf '%h\n' | sort -u | tr '\n' ':')$LD_LIBRARY_PATH"
          # The loader auto-discovers build-shared/src/libtranscribe.so from the
          # repo root; the TRANSCRIBE_SMOKE_* vars (exported by fetch-canary
          # when HF_TOKEN exists) un-skip the offline AND streaming model
          # tests. The prompted (nemotron) streaming test still skips here —
          # its regression is pinned in CI by the sanitized C-level test.
          uv run --project bindings/python --extra test \
            pytest bindings/python/tests -q -rs