local-ci-cd-system/src/ci_orchestrator/commands/smoke.py

"""``smoke`` sub-commands.

Phase C4 ports the manual smoke / E2E build tooling to Python so the Linux
host no longer needs ``pwsh``:

* ``smoke run`` — end-to-end no-op (or real build) job, replacing
  ``Test-Smoke.ps1`` and ``Test-*Build-Linux.ps1``.

The command runs **one** full end-to-end job through the in-process
``job`` orchestrator (reusing ``commands/job.py`` — no re-spawn of
``python -m ci_orchestrator``) and then asserts the three smoke
invariants of ``Test-Smoke.ps1``:

1. the pipeline exited 0,
2. the per-job artifact directory was created, and
3. a ``job``/``success`` event is present in the ``invoke-ci.jsonl``
   event log (the same JSONL format ``report job`` consumes).

Because the in-process ``job`` command does not itself emit the JSONL
event log (that was the job of the retired ``Invoke-CIJob.ps1``), this
command writes the ``job``/``start`` and ``job``/``success`` events
around the orchestration, exactly as the PowerShell wrapper did.

Design rule: import ``backends.load_backend`` and the existing transports
only — never ``WorkstationVmrunBackend`` directly (keeps the Phase D ESXi
path open).
"""

from __future__ import annotations

import json
import time
from datetime import UTC, datetime
from pathlib import Path

import click

from ci_orchestrator.commands.job import job as job_command
from ci_orchestrator.config import Config, load_config

# ─────────────────────────────────────────────────────── OS presets

# Per-guest defaults mirroring ``Test-Smoke.ps1``: a trivial build that
# writes a marker file into the standard output directory, plus the
# matching template / snapshot / artifact-source for the OS family.
_LINUX_TEMPLATE = "/var/lib/ci/templates/LinuxBuild2404/LinuxBuild2404.vmx"
_WINDOWS_TEMPLATE = r"F:\CI\Templates\WinBuild2025\WinBuild2025.vmx"

_NOOP_BUILD_LINUX = "mkdir -p /opt/ci/output && echo smoke-ok > /opt/ci/output/smoke.txt"
_NOOP_BUILD_WINDOWS = (
    "New-Item -ItemType Directory -Path C:\\CI\\output -Force | Out-Null; "
    'Set-Content C:\\CI\\output\\smoke.txt "smoke-ok"'
)

# Real Linux build E2E presets (ports of ``Test-*Build-Linux.ps1``).
# Exposed via ``--preset`` so the no-op default is never overridden by a
# hard-coded ``F:\`` Windows path. Each preset supplies a build command
# and the in-guest artifact source directory.
_PRESETS: dict[str, tuple[str, str]] = {
    "ns7zip": (
        "python3 build_plugin.py --host linux --7zip-version 26.01 "
        "--configs x64-unicode --verbose",
        "plugins",
    ),
    "nsinnounp": (
        "python3 build_plugin.py --final --dist-dir dist",
        "dist",
    ),
}


def _default_template(guest_os: str) -> str:
    return _LINUX_TEMPLATE if guest_os == "linux" else _WINDOWS_TEMPLATE


def _default_snapshot(guest_os: str) -> str:
    return "BaseClean-Linux" if guest_os == "linux" else "BaseClean"


def _noop_build_command(guest_os: str) -> tuple[str, str]:
    """Return ``(build_command, guest_artifact_source)`` for the marker job."""
    if guest_os == "linux":
        return _NOOP_BUILD_LINUX, "/opt/ci/output"
    return _NOOP_BUILD_WINDOWS, "C:\\CI\\output"


def _utcnow_iso() -> str:
    return datetime.now(tz=UTC).isoformat()


def _write_event(
    jsonl_path: Path,
    *,
    job_id: str,
    phase: str,
    status: str,
    elapsed_sec: float | None = None,
    error: str | None = None,
) -> None:
    """Append one event to ``invoke-ci.jsonl`` in ``report job`` format."""
    data: dict[str, object] = {}
    if elapsed_sec is not None:
        data["elapsedSec"] = int(elapsed_sec)
    if error is not None:
        data["error"] = error
    record: dict[str, object] = {
        "jobId": job_id,
        "phase": phase,
        "status": status,
        "ts": _utcnow_iso(),
        "data": data,
    }
    jsonl_path.parent.mkdir(parents=True, exist_ok=True)
    with jsonl_path.open("a", encoding="utf-8") as fh:
        fh.write(json.dumps(record) + "\n")


def _has_job_success(jsonl_path: Path) -> bool:
    """True iff the JSONL log contains a ``job``/``success`` event."""
    try:
        text = jsonl_path.read_text(encoding="utf-8")
    except OSError:
        return False
    for line in text.splitlines():
        line = line.strip()
        if not line:
            continue
        try:
            obj = json.loads(line)
        except json.JSONDecodeError:
            continue
        if not isinstance(obj, dict):
            continue
        if obj.get("phase") == "job" and obj.get("status") == "success":
            return True
    return False


# ────────────────────────────────────────────────────────── command


@click.group("smoke")
def smoke() -> None:
    """End-to-end smoke and build validation."""


@smoke.command("run")
@click.option(
    "--guest-os",
    type=click.Choice(["windows", "linux"], case_sensitive=False),
    default="linux",
    show_default=True,
    help="Guest OS family to smoke-test.",
)
@click.option(
    "--build-command",
    "build_command",
    default="",
    help="Build command to run (default: a marker no-op job).",
)
@click.option(
    "--preset",
    type=click.Choice(sorted(_PRESETS), case_sensitive=False),
    default=None,
    help="Real Linux build E2E preset (ns7zip / nsinnounp). Linux only.",
)
@click.option(
    "--repo-url",
    "repo_url",
    default="https://example.invalid/smoke-test.git",
    show_default=True,
    help="Repository to build (default: a placeholder; the no-op marker "
    "job never depends on the clone).",
)
@click.option("--branch", default="main", show_default=True)
@click.option(
    "--job-id",
    "job_id",
    default=None,
    help="Job id (default: smoke-<timestamp>).",
)
@click.option(
    "--template-path",
    "template_path",
    default=None,
    help="Template VMX path (default: per-guest-os standard template).",
)
@click.option(
    "--snapshot-name",
    "snapshot_name",
    default=None,
    help="Snapshot to clone from (default: per-guest-os BaseClean[-Linux]).",
)
@click.option(
    "--ssh-key-path",
    "ssh_key_path",
    default=None,
    help="SSH private key for the guest (Linux).",
)
@click.option(
    "--log-dir",
    "log_dir",
    default=None,
    help="Base directory for invoke-ci.jsonl logs (default: CI_ARTIFACTS).",
)
def smoke_run(
    guest_os: str,
    build_command: str,
    preset: str | None,
    repo_url: str,
    branch: str,
    job_id: str | None,
    template_path: str | None,
    snapshot_name: str | None,
    ssh_key_path: str | None,
    log_dir: str | None,
) -> None:
    """Run one end-to-end job and assert success + artifact + event."""
    guest_os = guest_os.lower()

    if preset is not None:
        preset = preset.lower()
        if guest_os != "linux":
            raise click.UsageError("--preset is only supported with --guest-os linux.")
        if build_command:
            raise click.UsageError("--preset and --build-command are mutually exclusive.")
        preset_cmd, artifact_source = _PRESETS[preset]
        effective_build_command = preset_cmd
    elif build_command:
        effective_build_command = build_command
        # A custom command writes to the standard output dir for the OS.
        _, artifact_source = _noop_build_command(guest_os)
    else:
        effective_build_command, artifact_source = _noop_build_command(guest_os)

    config: Config = load_config()
    resolved_job_id = job_id or f"smoke-{datetime.now(tz=UTC).strftime('%Y%m%d-%H%M%S')}"
    resolved_template = template_path or _default_template(guest_os)
    resolved_snapshot = snapshot_name or _default_snapshot(guest_os)

    artifact_base: Path = config.paths.artifacts
    # Logs live alongside (not inside) the artifacts tree so that writing the
    # event log never accidentally creates the per-job artifact directory and
    # masks a build that produced no artifacts (mirrors F:\CI\Logs vs
    # F:\CI\Artifacts in Test-Smoke.ps1).
    log_base = Path(log_dir) if log_dir else config.paths.root / "logs"
    job_artifact_dir = artifact_base / resolved_job_id
    jsonl_path = log_base / resolved_job_id / "invoke-ci.jsonl"

    click.echo("=" * 60)
    click.echo(f"[smoke] Guest OS   : {guest_os}")
    click.echo(f"[smoke] Template   : {resolved_template}")
    click.echo(f"[smoke] Snapshot   : {resolved_snapshot}")
    click.echo(f"[smoke] Job id     : {resolved_job_id}")
    if preset is not None:
        click.echo(f"[smoke] Preset     : {preset}")
    click.echo(f"[smoke] Artifacts  : {job_artifact_dir}")
    click.echo("=" * 60)

    _write_event(
        jsonl_path, job_id=resolved_job_id, phase="job", status="start"
    )

    start = time.monotonic()
    failed = False
    try:
        job_command.callback(  # type: ignore[misc]
            job_id=resolved_job_id,
            repo_url=repo_url,
            branch=branch,
            commit="",
            configuration="Release",
            build_command=effective_build_command,
            guest_artifact_source=artifact_source,
            submodules=True,
            use_git_clone=True,
            use_shared_cache=False,
            skip_artifact=False,
            use_xvfb=False,
            gitea_credential_target="GiteaPAT",
            template_path=resolved_template,
            snapshot_name=resolved_snapshot,
            clone_base_dir=None,
            artifact_base_dir=str(artifact_base),
            guest_os=guest_os,
            guest_credential_target=None,
            ssh_key_path=ssh_key_path,
            ssh_user="ci_build",
            ssh_known_hosts_file=None,
            extra_env_json="",
            guest_cpu=0,
            guest_memory_mb=0,
            ready_timeout=600.0,
            poll_interval=5.0,
            vmrun_path=None,
        )
    except click.ClickException as exc:
        failed = True
        _write_event(
            jsonl_path,
            job_id=resolved_job_id,
            phase="job",
            status="failure",
            elapsed_sec=time.monotonic() - start,
            error=exc.format_message(),
        )
        click.echo(f"[smoke] FAIL: pipeline raised: {exc.format_message()}", err=True)

    if not failed:
        _write_event(
            jsonl_path,
            job_id=resolved_job_id,
            phase="job",
            status="success",
            elapsed_sec=time.monotonic() - start,
        )

    # ── Assert the three smoke invariants ───────────────────────────────
    click.echo("\n[smoke] Verifying results...")
    checks_ok = True

    if failed:
        checks_ok = False
    else:
        click.echo("[smoke] OK: pipeline exit 0")

    if job_artifact_dir.is_dir():
        click.echo(f"[smoke] OK: artifact dir exists: {job_artifact_dir}")
    else:
        click.echo(
            f"[smoke] FAIL: artifact dir not found: {job_artifact_dir}", err=True
        )
        checks_ok = False

    if _has_job_success(jsonl_path):
        click.echo("[smoke] OK: JSONL contains job/success event")
    else:
        click.echo(
            f"[smoke] FAIL: JSONL missing job/success event in: {jsonl_path}",
            err=True,
        )
        checks_ok = False

    click.echo("")
    if checks_ok:
        click.echo(f"[smoke] PASSED — {guest_os} smoke test completed successfully.")
        return
    raise click.ClickException("smoke test FAILED — one or more checks did not pass.")


__all__ = ["smoke"]