mirror of
https://github.com/lahfir/agent-desktop.git
synced 2026-08-04 05:07:04 +00:00
9023f331b3
Completes the FFI plan: U9 adds a Python ctypes smoke harness proving the C ABI from a non-Rust host; U10 adds cross-platform parity CI gates for header drift, codegen drift, panic-unwind, and stub-adapter passthrough; U11 generates the command-backed wrappers from build.rs templates with a committed drift-gated output. The C ABI stays byte-identical and the surface is Windows and Linux ready with no new FFI code.
360 lines
14 KiB
YAML
360 lines
14 KiB
YAML
name: CI
|
||
|
||
on:
|
||
push:
|
||
branches: [main, master]
|
||
pull_request:
|
||
workflow_dispatch:
|
||
|
||
# Cancel in-progress runs for the same ref so stale PR builds don't burn minutes.
|
||
concurrency:
|
||
group: ci-${{ github.ref }}
|
||
cancel-in-progress: true
|
||
|
||
# Deny all permissions at workflow level; each job declares only what it needs.
|
||
permissions: {}
|
||
|
||
env:
|
||
CARGO_TERM_COLOR: always
|
||
RUST_BACKTRACE: 1
|
||
|
||
jobs:
|
||
fmt:
|
||
name: Format
|
||
runs-on: ubuntu-latest
|
||
timeout-minutes: 10
|
||
permissions:
|
||
contents: read
|
||
steps:
|
||
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||
- run: rustup component add rustfmt
|
||
- run: cargo fmt --all -- --check
|
||
|
||
test:
|
||
name: Test
|
||
runs-on: macos-latest
|
||
timeout-minutes: 30
|
||
permissions:
|
||
contents: read
|
||
steps:
|
||
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||
|
||
- name: Install Rust toolchain
|
||
run: rustup show
|
||
|
||
- name: Cache cargo registry
|
||
uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
|
||
with:
|
||
path: |
|
||
~/.cargo/registry/index/
|
||
~/.cargo/registry/cache/
|
||
~/.cargo/git/db/
|
||
key: ${{ runner.os }}-cargo-${{ hashFiles('Cargo.lock', 'Cargo.toml', 'crates/**/Cargo.toml', 'src/Cargo.toml') }}
|
||
restore-keys: ${{ runner.os }}-cargo-
|
||
|
||
- name: Cache build artifacts
|
||
uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
|
||
with:
|
||
path: target/
|
||
key: ${{ runner.os }}-build-ci-${{ hashFiles('Cargo.lock', 'Cargo.toml', 'crates/**/Cargo.toml', 'src/Cargo.toml') }}-${{ hashFiles('crates/**/*.rs', 'src/**/*.rs', 'tests/**/*.rs') }}
|
||
restore-keys: |
|
||
${{ runner.os }}-build-ci-${{ hashFiles('Cargo.lock', 'Cargo.toml', 'crates/**/Cargo.toml', 'src/Cargo.toml') }}-
|
||
${{ runner.os }}-build-ci-
|
||
|
||
- name: Check dependency isolation
|
||
run: |
|
||
if cargo tree --locked -p agent-desktop-core 2>/dev/null | grep -E 'agent-desktop-(macos|windows|linux)'; then
|
||
echo "FAIL: core crate depends on platform crates"
|
||
exit 1
|
||
fi
|
||
echo "OK: core crate has no platform dependencies"
|
||
|
||
- name: Check release metadata consistency
|
||
run: scripts/check-release-consistency.sh
|
||
|
||
- name: Clippy
|
||
run: cargo clippy --locked --all-targets -- -D warnings
|
||
|
||
- name: Unit tests
|
||
run: cargo test --locked --lib --workspace
|
||
|
||
- name: Binary command tests
|
||
run: cargo test --locked -p agent-desktop
|
||
|
||
# The FFI crate ships integration harnesses under crates/ffi/tests/ that
|
||
# exercise the C-ABI from outside the crate (raw extern "C" decls, enum
|
||
# fuzzing, out-param zeroing, last-error lifetimes). The workspace --lib
|
||
# run skips them, so wire them in explicitly so regressions fail PR CI.
|
||
- name: FFI integration tests
|
||
run: cargo test --locked -p agent-desktop-ffi --tests
|
||
|
||
# Use the ci profile (no LTO, opt-level 1) — fast compile, still checks the binary builds.
|
||
- name: Build binary (ci profile)
|
||
run: cargo build --locked --profile ci
|
||
|
||
- name: Check binary size
|
||
run: |
|
||
SIZE=$(stat -f%z target/ci/agent-desktop)
|
||
LIMIT=$((15 * 1024 * 1024))
|
||
echo "Binary size: $(du -sh target/ci/agent-desktop | cut -f1)"
|
||
if [ "$SIZE" -gt "$LIMIT" ]; then
|
||
echo "FAIL: binary exceeds 15MB limit (${SIZE} bytes)"
|
||
exit 1
|
||
fi
|
||
echo "OK: binary within 15MB limit"
|
||
|
||
- name: FFI cdylib build (release-ffi profile)
|
||
run: cargo build --locked --profile release-ffi -p agent-desktop-ffi
|
||
|
||
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
|
||
with:
|
||
node-version: '24'
|
||
|
||
- name: NPM package contents
|
||
run: node scripts/check-npm-package.js
|
||
|
||
- name: NPM wrapper smoke
|
||
run: |
|
||
case "$(uname -s)-$(uname -m)" in
|
||
Darwin-arm64) NAME=agent-desktop-darwin-arm64 ;;
|
||
Darwin-x86_64) NAME=agent-desktop-darwin-x64 ;;
|
||
*)
|
||
echo "Unsupported smoke-test platform: $(uname -s)-$(uname -m)"
|
||
exit 1
|
||
;;
|
||
esac
|
||
trap 'rm -f "npm/bin/${NAME}"' EXIT
|
||
cp target/ci/agent-desktop "npm/bin/${NAME}"
|
||
chmod +x "npm/bin/${NAME}"
|
||
node npm/bin/agent-desktop.js version > /tmp/agent-desktop-version.json
|
||
node -e "
|
||
const out = require('fs').readFileSync('/tmp/agent-desktop-version.json', 'utf8');
|
||
const json = JSON.parse(out);
|
||
if (json.ok !== true || !json.data || typeof json.data.version !== 'string') {
|
||
throw new Error('agent-desktop npm wrapper did not return version JSON');
|
||
}
|
||
"
|
||
|
||
ffi-python-smoke:
|
||
name: FFI Python Smoke
|
||
runs-on: macos-latest
|
||
timeout-minutes: 20
|
||
permissions:
|
||
contents: read
|
||
steps:
|
||
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||
|
||
- name: Install Rust toolchain
|
||
run: rustup show
|
||
|
||
- name: Cache cargo registry
|
||
uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
|
||
with:
|
||
path: |
|
||
~/.cargo/registry/index/
|
||
~/.cargo/registry/cache/
|
||
~/.cargo/git/db/
|
||
key: ${{ runner.os }}-cargo-${{ hashFiles('Cargo.lock', 'Cargo.toml', 'crates/**/Cargo.toml', 'src/Cargo.toml') }}
|
||
restore-keys: ${{ runner.os }}-cargo-
|
||
|
||
- name: Build FFI dylib (stub adapter)
|
||
run: >
|
||
cargo build --locked --profile release-ffi
|
||
-p agent-desktop-ffi --features stub-adapter
|
||
|
||
- name: Locate dylib
|
||
id: dylib
|
||
run: |
|
||
DYLIB=$(find target/release-ffi -name 'libagent_desktop_ffi.*' \
|
||
\( -name '*.dylib' -o -name '*.so' -o -name '*.dll' \) | head -1)
|
||
if [ -z "$DYLIB" ]; then
|
||
echo "FAIL: dylib not found under target/release-ffi"
|
||
exit 1
|
||
fi
|
||
echo "path=$DYLIB" >> "$GITHUB_OUTPUT"
|
||
|
||
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
|
||
with:
|
||
python-version: '3.12'
|
||
|
||
- name: Run FFI smoke harness
|
||
env:
|
||
AD_EXPECT_STUB: "1"
|
||
run: >
|
||
python3 tests/ffi-python/smoke.py
|
||
"${{ steps.dylib.outputs.path }}"
|
||
crates/ffi/include/agent_desktop.h
|
||
|
||
# Gate 1 — Header-drift: the committed crates/ffi/include/agent_desktop.h must
|
||
# match what cbindgen 0.29.4 would generate from the current source. A stale
|
||
# header means a consumer compiled against it sees different symbols/layouts
|
||
# than the dylib ships. cbindgen --verify exits non-zero when there is a diff.
|
||
#
|
||
# The cbindgen version is pinned so a generator upgrade cannot produce a
|
||
# false-positive failure — only a real header change triggers this gate.
|
||
ffi-header-drift:
|
||
name: FFI Header Drift
|
||
runs-on: macos-latest
|
||
timeout-minutes: 20
|
||
permissions:
|
||
contents: read
|
||
steps:
|
||
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||
|
||
- name: Install Rust toolchain
|
||
run: rustup show
|
||
|
||
- name: Cache cargo registry
|
||
uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
|
||
with:
|
||
path: |
|
||
~/.cargo/registry/index/
|
||
~/.cargo/registry/cache/
|
||
~/.cargo/git/db/
|
||
key: ${{ runner.os }}-cargo-${{ hashFiles('Cargo.lock', 'Cargo.toml', 'crates/**/Cargo.toml', 'src/Cargo.toml') }}
|
||
restore-keys: ${{ runner.os }}-cargo-
|
||
|
||
- name: Install pinned cbindgen 0.29.4
|
||
run: cargo install cbindgen --version 0.29.4 --locked
|
||
|
||
- name: Verify header matches source (cbindgen --verify)
|
||
run: >
|
||
cbindgen crates/ffi
|
||
--config crates/ffi/cbindgen.toml
|
||
--output crates/ffi/include/agent_desktop.h
|
||
--verify
|
||
|
||
# Gate 2 — Panic-trap guard: the release-ffi profile must keep panic="unwind"
|
||
# so the trap_panic boundary in the shipped dylib actually catches panics. A
|
||
# flip to panic="abort" silently defeats every catch_unwind in the cdylib and
|
||
# turns any Rust panic into an abort that kills the host process.
|
||
#
|
||
# This job proves the contract in two steps:
|
||
# 1. Assert the Cargo.toml profile setting directly (simpler and more
|
||
# reliable than a build.rs env check for a dual cdylib+rlib crate).
|
||
# 2. Build and run crates/ffi/examples/panic_spike under the release-ffi
|
||
# profile: an extern-C fn panics, catch_unwind catches it, and the
|
||
# example prints "PANIC CAUGHT OK (code = -1)" and exits 0. If the
|
||
# profile were flipped to panic="abort" the process would SIGABRT
|
||
# instead, making this step a runtime proof — not just a string check.
|
||
ffi-panic-guard:
|
||
name: FFI Panic Guard
|
||
runs-on: macos-latest
|
||
timeout-minutes: 20
|
||
permissions:
|
||
contents: read
|
||
steps:
|
||
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||
|
||
- name: Install Rust toolchain
|
||
run: rustup show
|
||
|
||
- name: Cache cargo registry
|
||
uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
|
||
with:
|
||
path: |
|
||
~/.cargo/registry/index/
|
||
~/.cargo/registry/cache/
|
||
~/.cargo/git/db/
|
||
key: ${{ runner.os }}-cargo-${{ hashFiles('Cargo.lock', 'Cargo.toml', 'crates/**/Cargo.toml', 'src/Cargo.toml') }}
|
||
restore-keys: ${{ runner.os }}-cargo-
|
||
|
||
- name: Assert release-ffi profile keeps panic=unwind
|
||
run: |
|
||
if ! grep -A5 '\[profile\.release-ffi\]' Cargo.toml | grep -q 'panic.*=.*"unwind"'; then
|
||
echo "FAIL: [profile.release-ffi] must set panic=\"unwind\" — a flip to"
|
||
echo " panic=\"abort\" defeats every trap_panic boundary in the dylib."
|
||
exit 1
|
||
fi
|
||
echo "OK: release-ffi profile retains panic=\"unwind\""
|
||
|
||
- name: Prove catch_unwind survives the release-ffi profile
|
||
run: cargo run --locked --profile release-ffi --example panic_spike -p agent-desktop-ffi
|
||
|
||
# Gate 3 — Stub-adapter passthrough tests: the Family-B command-backed
|
||
# entrypoints (ad_snapshot, ad_status, ad_wait, ad_execute_by_ref,
|
||
# ad_version) plus adapter lifecycle (ad_init / ad_destroy) and
|
||
# ad_check_permissions are exercised against the stub adapter. Each must
|
||
# return a structured PLATFORM_NOT_SUPPORTED envelope — or, for
|
||
# ad_check_permissions, the documented ErrPermDenied result. These tests are
|
||
# gated behind #[cfg(feature = "stub-adapter")] so the normal build is
|
||
# unaffected.
|
||
#
|
||
# Scope note: the ~35 Family-A entrypoints (ad_find, ad_execute_action,
|
||
# ad_list_windows, ad_screenshot, clipboard, notifications, etc.) are NOT
|
||
# covered by this passthrough job. Broader Family-A stub coverage is a
|
||
# documented follow-up.
|
||
#
|
||
# Per-target build coverage:
|
||
# - PR CI: this job runs on Linux (no main-thread guard off macOS, so the
|
||
# stub adapter is reached directly) to assert PLATFORM_NOT_SUPPORTED for
|
||
# every covered entrypoint — directly proving the non-macOS parity
|
||
# U10 targets.
|
||
# - Release: release.yml build-ffi matrix covers macOS×2 + Linux×2 +
|
||
# Windows×1 for the real cdylib. PR builds do not duplicate that
|
||
# cross-compile matrix to avoid bloating CI on every push.
|
||
ffi-passthrough:
|
||
name: FFI Stub-Adapter Passthrough
|
||
runs-on: ubuntu-latest
|
||
timeout-minutes: 20
|
||
permissions:
|
||
contents: read
|
||
steps:
|
||
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||
|
||
- name: Install Rust toolchain
|
||
run: rustup show
|
||
|
||
- name: Cache cargo registry
|
||
uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
|
||
with:
|
||
path: |
|
||
~/.cargo/registry/index/
|
||
~/.cargo/registry/cache/
|
||
~/.cargo/git/db/
|
||
key: ${{ runner.os }}-cargo-${{ hashFiles('Cargo.lock', 'Cargo.toml', 'crates/**/Cargo.toml', 'src/Cargo.toml') }}
|
||
restore-keys: ${{ runner.os }}-cargo-
|
||
|
||
- name: Run stub-adapter passthrough tests
|
||
run: >
|
||
cargo test --locked -p agent-desktop-ffi
|
||
--features stub-adapter --test c_abi_passthrough
|
||
|
||
# Gate 4 — Codegen drift: the committed src/commands/generated.rs must
|
||
# match what build.rs produces from the current templates. A stale committed
|
||
# file means the source diverged from the templates — either a hand-edit
|
||
# bypassed the generator or a template was changed without rebuilding.
|
||
ffi-codegen-drift:
|
||
name: FFI Codegen Drift
|
||
runs-on: ubuntu-latest
|
||
timeout-minutes: 15
|
||
permissions:
|
||
contents: read
|
||
steps:
|
||
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||
|
||
- name: Install Rust toolchain
|
||
run: rustup show
|
||
|
||
- name: Cache cargo registry
|
||
uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
|
||
with:
|
||
path: |
|
||
~/.cargo/registry/index/
|
||
~/.cargo/registry/cache/
|
||
~/.cargo/git/db/
|
||
key: ${{ runner.os }}-cargo-${{ hashFiles('Cargo.lock', 'Cargo.toml', 'crates/**/Cargo.toml', 'src/Cargo.toml') }}
|
||
restore-keys: ${{ runner.os }}-cargo-
|
||
|
||
- name: Regenerate FFI command wrappers via build.rs
|
||
run: cargo build --locked -p agent-desktop-ffi --features stub-adapter
|
||
|
||
- name: Assert no drift in commands/generated.rs
|
||
run: |
|
||
if ! git diff --exit-code crates/ffi/src/commands/generated.rs; then
|
||
echo ""
|
||
echo "FAIL: crates/ffi/src/commands/generated.rs is out of sync with build.rs templates."
|
||
echo " Run 'cargo build -p agent-desktop-ffi' locally and commit the updated file."
|
||
exit 1
|
||
fi
|
||
echo "OK: commands/generated.rs matches build.rs output"
|