settled-reach/tooling/main.py

"""`reach` — one command for every repo tool (D-263).

**This file is a router and nothing else.** No logic, no I/O, no pydantic, no
domain imports at module level. It is the file most likely to accumulate "just
one small thing", and the only defence is that it stays short enough that an
addition is obvious in review.

The root is a `typer.Typer`, and the reason is worth recording because the
original plan was different. T-1259 specified a `click.Group` root, on the
theory that it would keep typer off the `reach --help` path. **That is no longer
possible: typer vendors click as of 0.26.0** — there is no top-level `click`
package to import, and the docs are explicit that "extracting the internal Click
app" is unsupported. Mixing a real `click.Group` root with typer sub-apps would
mean two different Click implementations in one process.

So the customisation surface is `typer.Typer(cls=...)` with a `TyperGroup`
subclass, which is the supported path and is what `LazyDomainGroup` below uses
to register domains lazily.

`rich_markup_mode=None` is not a style preference — it is worth 94 ms of the
168 ms an empty `--help` otherwise costs, and it keeps `rich` and `pygments`
off the import path entirely (verified absent from `sys.modules`). It also
stops typer drawing box-art help, which it does **even when stdout is a pipe**,
so hook logs and agent output stay readable. One line to revert if the boxes
are ever wanted more than the milliseconds.

The callback below is not decoration. A `typer.Typer` with **no commands and no
callback** raises `RuntimeError: Could not get a command for this Typer
instance` at build time; with a callback it builds fine. Since every domain is
registered lazily and none is eager, the callback is what makes the root legal.
"""

from __future__ import annotations

import importlib

import typer

from tooling.core.cli import ReachGroup

# The domain registry: name -> (import target, one-line help).
#
# This table is the ONLY thing `reach --help` reads. The short help lives here
# as a literal string rather than being pulled off the loaded command, because
# reading it off the command is precisely what would import the world — see
# LazyDomainGroup.format_commands.
#
# Adding a domain is adding a line here plus a `router.py` that exposes `app`.
DOMAINS: dict[str, tuple[str, str]] = {
    "check": (
        "tooling.domains.check.router:app",
        "Consistency gates — the checks the push hook runs",
    ),
    "validate": (
        "tooling.domains.validate.router:app",
        "Content, checklists and RON against their schemas",
    ),
    "godot": (
        "tooling.domains.godot.router:app",
        "Does the client parse, and does it parse cold",
    ),
    "visual": (
        "tooling.domains.visual.router:app",
        "Compare captures against goldens, and catch blank ones",
    ),
    "jobs": (
        "tooling.domains.jobs.router:app",
        "Detached runs — status, logs and outcomes",
    ),
    "dev": (
        "tooling.domains.dev.router:app",
        "Developer environment and self-diagnosis",
    ),
}


class LazyDomainGroup(ReachGroup):
    """Lists domains without importing them; imports exactly the one invoked.

    Extends `ReachGroup`, so bare `reach` prints the domain list and exits 0
    like every domain group does. Only the laziness and the domain-specific
    wording live here.

    Three overrides, and the third is the one that matters. `TyperGroup`'s own
    `format_commands` loops over `list_commands` calling `get_command` on each,
    just to read a short help string off the loaded command — which, with lazy
    loading underneath, imports every domain in the registry to render `--help`.
    That would defeat the whole mechanism silently, while looking correct.

    So `format_commands` is overridden to read help from `DOMAINS` and never
    touch `get_command`. The cost of `reach --help` is then flat no matter how
    many domains exist, which is the property that has to hold as this grows
    from one domain to a dozen.
    """

    def list_commands(self, ctx: typer.Context) -> list[str]:
        return sorted({*super().list_commands(ctx), *DOMAINS})

    def get_command(self, ctx: typer.Context, cmd_name: str):
        if cmd_name in DOMAINS:
            return _load_domain(cmd_name)
        return super().get_command(ctx, cmd_name)

    def resolve_command(self, ctx: typer.Context, args: list[str]):
        # Closed-set enumeration (D-263). Click's default is "No such command
        # 'x'" — which tells you that you are wrong without telling you what
        # would be right, the exact gap measured in pql. The accepted set is
        # sitting in DOMAINS, already loaded for --help, so naming it is free.
        if args and args[0] not in DOMAINS and super().get_command(ctx, args[0]) is None:
            listed = ", ".join(sorted({*DOMAINS, *super().list_commands(ctx)}))
            ctx.fail(f"unknown domain {args[0]!r}\n\nChoose one of: {listed}")
        return super().resolve_command(ctx, args)

    def format_commands(self, ctx: typer.Context, formatter) -> None:
        # Deliberately does NOT call get_command. See the class docstring.
        rows = [(name, short) for name, (_target, short) in sorted(DOMAINS.items())]
        for name in sorted(super().list_commands(ctx)):
            command = super().get_command(ctx, name)
            if command is not None and not command.hidden:
                rows.append((name, command.get_short_help_str(80)))
        if rows:
            with formatter.section("Domains"):
                formatter.write_dl(sorted(rows))


def _load_domain(name: str):
    """Import one domain's router and convert its Typer app to a command."""
    target, _short = DOMAINS[name]
    module_name, _, attr = target.partition(":")
    module = importlib.import_module(module_name)
    return typer.main.get_command(getattr(module, attr))


cli = typer.Typer(
    name="reach",
    cls=LazyDomainGroup,
    help="Repo tooling for The Settled Reach.\n\nRun `reach <domain> --help` to see what a domain can do.",
    no_args_is_help=True,
    add_completion=False,
    rich_markup_mode=None,
    # See core/cli.py — a second rich path that renders unhandled exceptions as
    # box-art, arriving through a different door than rich_markup_mode.
    pretty_exceptions_enable=False,
    context_settings={"help_option_names": ["-h", "--help"], "max_content_width": 100},
)


def main() -> None:
    """Console entry point — `reach`.

    Exists so a detached child records its completion at the PROCESS's exit
    rather than at a command's. Recording it inside `@command` looked right and
    was subtly wrong: a child that fails before any command runs — bad
    arguments, an unknown verb, an import error — never reaches that decorator,
    so its metadata said `running` forever. A failed job that looks busy is the
    exit-0 trap wearing a new disguise, and worse than the original because
    nothing is watching a background job.

    Here, every exit path passes through one `finally`.
    """
    exit_code = 0
    try:
        cli()
    except SystemExit as exc:
        exit_code = exc.code if isinstance(exc.code, int) else 1
        raise
    except BaseException:
        exit_code = 1
        raise
    finally:
        # Imported lazily and only when detached, so `reach --help` never pays
        # for it — the laziness T-1260 protects applies here too.
        import os

        from tooling.core import jobs

        if os.environ.get(jobs.ENV_JOB_ID):
            from tooling.core import process

            process.finish_if_detached(exit_code)


@cli.callback()
def root(
    verbose: bool = typer.Option(
        False, "--verbose", "-v", help="Show progress events and full tracebacks."
    ),
    no_input: bool = typer.Option(
        False, "--no-input", help="Never prompt. Hooks and agents should always pass this."
    ),
    detach: bool = typer.Option(
        False, "--detach", help="Run in the background; print a job id and return at once."
    ),
) -> None:
    """Global options, declared once here so every domain inherits them.

    A per-domain copy of these is how the two would drift apart — one router
    growing a `--verbose` that sets a different level, or forgetting `--no-input`
    entirely.

    Note `--no-input` is about PROMPTING, not output format. Console already
    chooses JSONL versus rendered text from `isatty` with an `SR_OUTPUT_FORMAT`
    override; making this flag a second, conflicting way to say the same thing
    would leave nobody sure which one wins.
    """
    from tooling.core import console, runtime

    if verbose:
        console.set_level("debug")
    runtime.set_no_input(no_input)

    if detach:
        # Handled here, before any domain loads, because detaching is a property
        # of the INVOCATION rather than of the verb — every command gets it and
        # no command implements it. The child re-runs this same argv with
        # --detach stripped, so it does the work instead of forking again.
        from tooling.core import process

        job_id = process.spawn_detached(process.current_argv())
        console.out(job_id)
        console.verdict(
            f"started job {job_id} — this exit status means STARTED, not succeeded",
            fix=None,
        )
        raise typer.Exit(0)