settled-reach/tooling/canvas_sources.py

#!/usr/bin/env python3
"""
canvas_sources — single source of truth for the Atlas canvas-generation path set.

`project.yaml`'s `version:` is the Atlas disk cache's ONLY invalidation signal
(client/scripts/build_version.gd, D-255). A change to how a canvas is GENERATED
is therefore only half a change; the other half is bumping that version, or every
warm cache keeps serving canvases built by code that no longer exists.

Nothing enforced that pairing, and it broke five times: project.yaml's own
comments record 0.4.2 (lake_margin_q semantics), 0.4.3 (coast_warp_px at orbital
sampling), 0.4.4 (the D-255 extent inversion), 0.4.5 (the Global sentinel), and
0.4.6 (T-1237 one-course-per-river) — every one of them bumped *after the fact*,
the last only after T-1239 spent eight days diagnosing a map drawn from a canvas
whose generating code had been replaced. The failure is invisible to its author:
it reproduces only where a warm cache exists, so a cold checkout looks fine.

This module is the registry `tooling/check-canvas-version` intersects against,
kept here rather than inline in the hook for the same reason
`tooling/generator_sources.py` exists (T-1067): one list, one place, imported by
everything that needs it.

WHY THIS DELIBERATELY OVER-INCLUDES
-----------------------------------
The set is collected by GLOB, not hand-listed, and covers the whole atlas module
rather than a traced dependency closure.

`step_canvas.rs` directly imports ten sibling modules and those pull in more
(district_profile -> domain_warp/detail_scatter/coast_invention/..., layer1 ->
drainage/hydrology_equilibrium/features). A hand-maintained closure of that would
be wrong within a month, and being wrong here is silent — exactly the failure
this registry exists to stop. Globbing is self-maintaining: a module added in a
future split is covered the moment it exists.

The cost asymmetry is the whole argument, and it is the ticket's own ruling
(T-1242): a false positive costs one version bump and one round of cache misses;
a false negative costs another week of a wrong map. So when the choice is
"include a file that might not change canvas bytes" versus "risk missing one that
does", this includes it.

Fail closed on an empty glob, per generator_sources.py's precedent: an empty set
would silently pass every push.

Usage:
    python3 tooling/canvas_sources.py --list
"""

import argparse
import sys
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parent.parent

# ---------------------------------------------------------------------------
# Server: the code that PRODUCES canvas bytes
# ---------------------------------------------------------------------------

# The whole atlas module. Canvas bytes are produced by step_canvas.rs out of
# layer1/TerrainAnalysis/district_profile/river_course/hydrology and a long tail
# of invention modules; see this file's header for why the boundary is the
# module rather than a traced import closure.
ATLAS_DIR: Path = REPO_ROOT / "server" / "src" / "atlas"

# The seed chain feeds every deterministic decision the cascade makes
# (step_canvas.rs: `use crate::seed::SeedChain`), so a change to seed derivation
# changes canvas bytes without touching atlas/ at all.
SEED_RS: Path = REPO_ROOT / "server" / "src" / "seed.rs"

# ---------------------------------------------------------------------------
# Client: the code that KEYS, STORES and INTERPRETS those bytes
# ---------------------------------------------------------------------------

# The step_canvas cluster: the disk cache and its index format, the in-memory
# cache, the request/transport layer that derives extents and spacing (and
# therefore cache KEYS), and the layers that decode the payload.
#
# The render-only members (terrain/annotation layers) are included on purpose.
# A pure draw change cannot make cached bytes wrong, so including them can force
# an unnecessary re-derive — but drawing the line *inside* this directory means
# hand-judging which file is "really" wire-shaped, and T-1237 changed the server
# course shape and the client annotation layer in the same commit. That judgement
# is precisely where a false negative would come from.
CLIENT_STEP_CANVAS_DIR: Path = (
    REPO_ROOT / "client" / "ui" / "implant" / "apps" / "atlas" / "step_canvas"
)

# The accessor the cache reads its invalidation tag through.
BUILD_VERSION_GD: Path = REPO_ROOT / "client" / "scripts" / "build_version.gd"


def _rust_sources(directory: Path, label: str) -> tuple[Path, ...]:
    """Every .rs file in `directory`, collected by glob and fail-closed."""
    sources = tuple(sorted(directory.rglob("*.rs")))
    if not sources:
        raise RuntimeError(
            f"{label} sources not found at {directory} — the canvas-generation "
            "path set would be incomplete, and this check would pass every push"
        )
    return sources


def _gdscript_sources(directory: Path, label: str) -> tuple[Path, ...]:
    """Every .gd file in `directory`, collected by glob and fail-closed.

    `.uid` sidecars are Godot bookkeeping and carry no behaviour, so they are
    excluded — a uid churn should not demand a version bump.
    """
    sources = tuple(sorted(directory.rglob("*.gd")))
    if not sources:
        raise RuntimeError(
            f"{label} sources not found at {directory} — the canvas-generation "
            "path set would be incomplete, and this check would pass every push"
        )
    return sources


def canvas_sources() -> tuple[Path, ...]:
    """Every file whose change may alter canvas bytes or their interpretation.

    This registry itself is a member: loosening the set must be as visible as
    any other canvas-generation change (generator_sources.py makes the same
    call for the same reason).
    """
    return (
        Path(__file__).resolve(),
        *_rust_sources(ATLAS_DIR, "server atlas"),
        SEED_RS,
        *_gdscript_sources(CLIENT_STEP_CANVAS_DIR, "client step_canvas"),
        BUILD_VERSION_GD,
    )


def relative_paths() -> tuple[str, ...]:
    """The registry as repo-relative POSIX paths, for matching git output."""
    return tuple(p.relative_to(REPO_ROOT).as_posix() for p in canvas_sources())


def main() -> None:
    parser = argparse.ArgumentParser(
        description="Single source of truth for the Atlas canvas-generation path set"
    )
    parser.add_argument(
        "--list",
        action="store_true",
        help="Print the canvas-generation paths, one repo-relative path per line",
    )
    args = parser.parse_args()

    if not args.list:
        parser.print_help()
        sys.exit(2)

    for path in relative_paths():
        print(path)


if __name__ == "__main__":
    main()