ersatztv/scripts/decisions_validate.py

#!/usr/bin/env python3
"""Validate ErsatzTV decision-record lifecycle invariants.

Replaces the line-level append-only guard (ersatztv#303 H9) with lifecycle checks that preserve its
spirit — rationale is never silently rewritten or deleted; every history touch is deliberate and
reviewable. `[decisions-edit]` is kept ONLY for rationale-prose edits (see body-diff below); routine
lifecycle metadata writes are token-free. Fail-open on tooling trouble (missing refs, git errors,
parse issues), matching the old guard.
"""

from __future__ import annotations

import argparse
import subprocess
import sys
from pathlib import Path

import scripts.decisions_lib as dl  # noqa: E402  (run with PYTHONPATH=. or as module)

SKIP_HEADINGS = {"Index", "Active catalog"}
REQUIRED_META = ("key", "status", "since", "supersedes", "superseded_by")
EDIT_TOKEN = "[decisions-edit]"  # noqa: S105 (a commit-message marker, not a credential)


def _key_of(ref: str | None) -> str | None:
    if not ref or ref == "none":
        return None
    return ref.split("@", 1)[0].strip()


def validate(records, *, archive_keys, catalog_ok, budget_ok, removed, rewritten, archive_records=None) -> list[str]:
    errs: list[str] = []
    archive_records = archive_records or []
    decision_recs = [r for r in records if r.heading not in SKIP_HEADINGS and r.status != "legacy-unmigrated"]

    active_by_key: dict[str, int] = {}
    known_keys = set(archive_keys)
    for r in decision_recs:
        if r.status not in dl.STATUSES:
            errs.append(f"{r.heading}: invalid status {r.status!r}")
        if not r.key or not dl.KEY_RE.match(r.key):
            errs.append(f"{r.heading}: bad key format {r.key!r}")
            continue
        known_keys.add(r.key)
        for f in REQUIRED_META:
            if getattr(r, f) in (None, ""):
                errs.append(f"{r.heading}: missing required metadata {f}")
        if r.status == "active":
            active_by_key[r.key] = active_by_key.get(r.key, 0) + 1
        if r.status in ("superseded", "retired"):
            errs.append(
                f"{r.heading}: status {r.status} but still in the active set — relocate to docs/decisions/archive/"
            )

    for r in archive_records:
        if r.status == "active":
            errs.append(f"{r.heading}: active record must not live under docs/decisions/archive/")

    for key, n in active_by_key.items():
        if n > 1:
            errs.append(f"key {key!r}: more than one active record ({n})")

    # reciprocal supersession (successor may live in active OR archive)
    for r in decision_recs:
        sk = _key_of(r.superseded_by)
        if sk and sk not in known_keys:
            errs.append(f"{r.heading}: superseded-by points to unknown key {sk!r}")
        pk = _key_of(r.supersedes)
        if pk and pk not in known_keys:
            errs.append(f"{r.heading}: supersedes points to unknown key {pk!r}")

    for h in removed:
        errs.append(f"record removed from the active set without an archive copy: {h!r}")
    for h in rewritten:
        errs.append(f"rationale prose of {h!r} changed without the {EDIT_TOKEN} token")

    if not catalog_ok:
        errs.append("docs/decisions/README.md active catalog is stale — run build_decisions_catalog.py")
    if not budget_ok:
        errs.append("aggregate active-corpus budget exceeded (see --budget)")
    return errs


# ---- git helpers (all fail-open: return neutral values on any error) ----


def _run(args: list[str]) -> str | None:
    try:
        r = subprocess.run(args, capture_output=True, text=True, timeout=30)
    except (OSError, subprocess.SubprocessError):
        return None
    return r.stdout if r.returncode == 0 else None


def _merge_base(base: str, head: str) -> str | None:
    out = _run(["git", "merge-base", base, head])
    return out.strip() if out else None


def _active_paths_at(ref: str) -> list[str]:
    """Active decision files at a ref: decisions.md + docs/decisions/*.md minus README/archive."""
    out = _run(["git", "ls-tree", "-r", "--name-only", ref, "docs/decisions.md", "docs/decisions/"])
    if out is None:
        return []
    paths = []
    for p in out.splitlines():
        if not p.endswith(".md"):
            continue
        if p.startswith("docs/decisions/archive/") or p == "docs/decisions/README.md":
            continue
        paths.append(p)
    return paths


def _records_at(ref: str, paths: list[str]):
    """{heading: Record} across the given paths at a ref."""
    by_heading = {}
    for p in paths:
        blob = _run(["git", "show", f"{ref}:{p}"])
        if blob is None:
            continue
        for rec in dl.parse_text(blob, Path(p)):
            if rec.heading not in SKIP_HEADINGS:
                by_heading[rec.heading] = rec
    return by_heading


def _archive_records_at(ref: str):
    out = _run(["git", "ls-tree", "-r", "--name-only", ref, "docs/decisions/archive/"])
    paths = [p for p in (out or "").splitlines() if p.endswith(".md")]
    by_heading = {}
    for p in paths:
        blob = _run(["git", "show", f"{ref}:{p}"])
        if blob is None:
            continue
        for rec in dl.parse_text(blob, Path(p)):
            by_heading[rec.heading] = rec
    return by_heading


def _rationale(rec) -> str:
    """Record body with the contiguous top metadata block stripped, whitespace-normalized.

    Only the block from the first non-blank line (when it is the `key:` meta line) up to the first
    following blank line is metadata. A **Rule:**/**Signals:**/**Mechanics:**/`key:` line appearing
    later in rationale prose is prose, not metadata (mirrors decisions_lib's contiguous-block rule).
    """
    lines = rec.body.splitlines()
    start = 0
    while start < len(lines) and not lines[start].strip():
        start += 1
    if start < len(lines) and lines[start].strip().startswith("`key:"):
        end = start + 1
        while end < len(lines) and lines[end].strip():
            end += 1
        rest = lines[:start] + lines[end:]
    else:
        rest = lines
    return "\n".join(s for s in (ln.strip() for ln in rest) if s)


def _diff_findings(base: str, head: str) -> tuple[list[str], list[str]]:
    """(removed, rewritten) between merge-base(base,head) and head. Fail-open → ([], [])."""
    mb = _merge_base(base, head)
    if not mb:
        return [], []
    if EDIT_TOKEN.lower() in (_run(["git", "log", "--format=%B", f"{mb}..{head}"]) or "").lower():
        token = True
    else:
        token = False

    base_active = _records_at(mb, _active_paths_at(mb))
    head_active = _records_at(head, _active_paths_at(head))
    head_archive = _archive_records_at(head)

    gone = set(base_active) - set(head_active)
    removed = sorted(h for h in gone if h not in head_archive)

    rewritten: list[str] = []
    if not token:
        # surviving records whose rationale prose changed
        for h in set(base_active) & set(head_active):
            if _rationale(base_active[h]) != _rationale(head_active[h]):
                rewritten.append(h)
        # archived records must body-match their base active copy (no laundering rewrites via archive)
        for h in gone & set(head_archive):
            if _rationale(base_active[h]) != _rationale(head_archive[h]):
                rewritten.append(h)
    return removed, sorted(rewritten)


def _archive_keys() -> set[str]:
    keys: set[str] = set()
    if dl.ARCHIVE_DIR.exists():
        for f in dl.ARCHIVE_DIR.glob("*.md"):
            for r in dl.parse_file(f):
                if r.key:
                    keys.add(r.key)
    return keys


def _budget_ok(limit: int) -> bool:
    total = 0
    for f in dl.active_files():
        if f.exists():
            total += len(f.read_text(encoding="utf-8").splitlines())
    cat = dl.TOPIC_DIR / "README.md"
    if cat.exists():
        total += len(cat.read_text(encoding="utf-8").splitlines())
    return total <= limit


def _catalog_ok() -> bool:
    try:
        import scripts.build_decisions_catalog as bc  # pyright: ignore[reportMissingImports]
    except Exception:
        return True  # fail-open; the CI job also runs an independent --check step
    want = bc.render_catalog(dl.all_active_records())
    cat = dl.TOPIC_DIR / "README.md"
    have = cat.read_text(encoding="utf-8") if cat.exists() else ""
    return want.strip() == have.strip()


def main(argv=None) -> int:
    ap = argparse.ArgumentParser()
    ap.add_argument("--base")
    ap.add_argument("--head")
    ap.add_argument("--budget", type=int, default=4200)  # aggregate; ratchet down as archive grows
    args = ap.parse_args(argv)

    records = dl.all_active_records()
    archive_records = []
    if dl.ARCHIVE_DIR.exists():
        for f in dl.ARCHIVE_DIR.glob("*.md"):
            archive_records += dl.parse_file(f)
    removed, rewritten = _diff_findings(args.base, args.head) if args.base and args.head else ([], [])
    errs = validate(
        records,
        archive_keys=_archive_keys(),
        catalog_ok=_catalog_ok(),
        budget_ok=_budget_ok(args.budget),
        removed=removed,
        rewritten=rewritten,
        archive_records=archive_records,
    )

    unmigrated = [r for r in records if r.status == "legacy-unmigrated" and r.heading not in SKIP_HEADINGS]
    if unmigrated:
        print(f"::notice::{len(unmigrated)} legacy-unmigrated decision record(s) remain (must trend to 0).")
    if errs:
        for e in errs:
            print(f"decisions-validate: {e}", file=sys.stderr)
        return 1
    print("decisions-validate: OK")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())