#!/usr/bin/env bash
# =============================================================================
# L0 static check (offline, no cluster) — placeholder-guard-coupling
# Serves: R-ENV-02 ("Same GitOps config promotes dev/test -> prod (authored once)."
#                   — spec docs/02-environments-and-provisioning.md)
#         R-STATE-03 ("Scheduled off-cluster backups + restore (DR)."
#                   — spec docs/04-storage-and-state.md)
#
# WHY THIS EXISTS — A GUARD KEYED ON A VALUE THAT LIVES IN ANOTHER FILE
# --------------------------------------------------------------------
# `bootstrap/standup.sh` refuses to resume tiers whose configuration is still a
# placeholder. Three of those guards keyed on the SHAPE of `S3_BACKUP_ENDPOINT`, which is
# authored in `clusters/base/cluster-vars.yaml`. On 2026-09-05 the placeholder changed
# from `TBD-PROD-S3-BACKUP-ENDPOINT` to `https://TBD-R2-ACCOUNT-ID.r2.cloudflarestorage.com`
# (the MinIO -> Cloudflare R2 move). The guards matched the glob `TBD-*` — a PREFIX match —
# and `fnmatch('https://TBD-R2-…','TBD-*')` is FALSE. All three guards silently stopped
# matching. `standup.sh resume` would then have resumed `velero` on prod against a hostname
# that does not exist: the HelmRelease installs clean, the Kustomization reports Ready, and
# NO BACKUPS EXIST. The only reason it was not shipped is that someone noticed by accident.
#
# The predicate is fixed (`s3_is_placeholder`, substring match). The COUPLING is what was
# never tested: a guard in one file keying on a value in another, with nothing tying them
# together. This check is that tie, and it is derived from BOTH real files — no current
# string is hardcoded here, so it does not rot when the placeholder or the guard changes.
#
# HOW THE REAL GUARD IS EXERCISED (and why not a copy)
# ---------------------------------------------------
# `bootstrap/standup.sh` is NOT sourceable: at top level it parses argv, hard-exits when
# --kubeconfig/--expect-server/<step> are absent, `cd`s to the repo root, exports
# KUBECONFIG, installs an EXIT trap and finally dispatches steps against a live cluster.
# So this check EXTRACTS the predicate's own source lines from the file and sources ONLY
# those, then calls the real function. That is the real bytes, not a reimplementation:
#   * every function whose name ends `_is_placeholder` is discovered, not named here;
#   * a duplicate definition of one is a failure (which of the two would run?);
#   * the extracted body must be a SELF-CONTAINED predicate — `case`/`return` and nothing
#     else, no command substitution, no call to another function. If the guard ever grows
#     a dependency, extraction stops being faithful and THIS CHECK FAILS LOUDLY, naming the
#     remedy (move the predicate into a small sourceable library that standup.sh sources)
#     rather than quietly falling back to testing a copy of the logic;
#   * a CANARY pins the extraction itself: the extracted function must refuse the empty
#     string and accept a realistic endpoint. An extraction that grabbed the wrong lines,
#     or a predicate degraded to always-true / always-false, fails there — this repo has
#     already been bitten by a check that passed when perturbed because it asked a question
#     that was always satisfiable.
# There is deliberately NO second implementation of the matching logic anywhere in this file.
#
# THE INDEPENDENT DETECTOR (the other half of the comparison)
# ----------------------------------------------------------
# Asking "does the guard agree with the guard?" proves nothing, so the set of
# placeholder-shaped values is decided by a detector written HERE, whose vocabulary is the
# UNION of two independent sources:
#   * SEED — universal loud-placeholder idioms (TBD, TODO, FIXME, PLACEHOLDER, REPLACE-ME,
#     CHANGE-ME, FILL-ME, SET-ME, XXXX), plus `<angle-bracket>` templates and the empty
#     string. These are NOT derived from the guard, so DELETING a guard arm cannot make a
#     value stop being placeholder-shaped — it makes assertion (1) fail, which is the point.
#     A value using an idiom the guard does not know is a finding either way: fix it by
#     giving the knob a real value, or by teaching the guard the idiom.
#   * the guard's OWN vocabulary, read out of its case-arms with the glob anchors STRIPPED.
#     Stripping the anchors is what makes the comparison non-circular in the dimension that
#     actually broke: the detector matches a word ANYWHERE, case-insensitively, and the
#     guard must agree. A prefix-anchored guard cannot pass.
#
# GIVEN the repository as authored,
# WHEN  the real predicate(s) are extracted from bootstrap/standup.sh and executed,
# THEN  (1) VALUES: for every knob a guard is responsible for, every authored value — the
#           base default AND each environment overlay's value — that the independent
#           detector calls placeholder-shaped is REFUSED by the real guard, and every value
#           it calls usable is ACCEPTED (a guard that refuses a real endpoint leaves velero
#           suspended forever, which is the same class of silent failure);
#       (2) OVERLAYS: no environment overlay's EFFECTIVE cluster-vars carries a
#           placeholder-shaped value for a knob that no guard refuses. (Base alone is
#           exempt: it is not a bootstrap target — `flux bootstrap --path=clusters/<env>` —
#           and its loud sentinels exist precisely to be overridden. A base placeholder an
#           overlay forgets to override IS caught, because it becomes that overlay's
#           effective value.)
#       (3) CONSUMERS: every function in standup.sh that reads a guarded knob (via `cvar`,
#           following one hop of variable aliasing) applies a placeholder guard to it. This
#           is the "all three guards died at once" regression stated as a property: the
#           guard being correct is worthless if a consumer stops calling it.
#       (4) ANCHORING: for each word in the guard's own vocabulary, the guard refuses a
#           value carrying that word in the MIDDLE (not at the start) — the precise defect
#           of 2026-09-05 — while still accepting a realistic endpoint.
#       (5) HARNESS: exactly one definition per predicate, the extracted body is verbatim
#           from the file and self-contained, the canary holds, no divergent second copy of
#           the matching logic exists elsewhere in standup.sh, and a floor on the number of
#           assertions run keeps a pass from degenerating into a no-op.
#   AND (6) LOAD-BEARING: ci/l0.sh runs the L0 conformance layer on every gate run and
#           ci/gate.sh sets the merge block when that stage fails.
#
# WHAT THIS DOES *NOT* PROVE (honest gaps)
#   - Nothing about RUNTIME: not that the endpoint resolves, not that credentials work, not
#     that a backup exists. `standup.sh s3check` probes reachability from a pod (operator-
#     run, cluster-gated) and conformance/tests/l3-fault-injection/dr-restore proves restore.
#   - It does not execute standup.sh's dispatch path, so it cannot prove the guard is
#     REACHED in a real run — only that, when reached, it refuses what it must. The
#     consumer property (3) is a static approximation of reachability: it is a text-level
#     taint trace over one file, not an interpreter, and a guard whose result is computed
#     and then ignored would satisfy it.
#   - It says nothing about guards keyed on shapes OTHER than placeholders (e.g. the
#     EXTERNALDNS_TXT_OWNER_ID == 'default' test), nor about placeholder-shaped values
#     outside cluster-vars (the Ansible inventory's BLOCKED/NOT-A-DEVICE sentinels are
#     asserted by the node_baseline role itself, at play time).
#   - Stage 3b of ci/l0.sh scopes the conformance run to the TOUCHED requirements. An edit
#     to bootstrap/* attributes NO requirement in ci/touched-requirements.sh's path map, so
#     the touched set is empty and the FULL L0 layer runs (verified: ci/lib.sh
#     load_touched_requirements) — this check runs. An edit to clusters/* maps to
#     R-ENV-02, which this check carries, so a cluster-vars value change also selects it.
#     A change that touches standup.sh ALONGSIDE some unrelated mapped path (say
#     platform/cilium/) would scope the run away from this check; closing that needs a
#     `bootstrap/*` entry in the path map, which is not this check's file to edit.
# =============================================================================
set -euo pipefail
DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ROOT="$(cd "${DIR}/../../../.." && pwd)"        # repo root
PYTHON="${PYTHON:-python3}"
STANDUP_REL="${STANDUP_REL:-bootstrap/standup.sh}"

cd "${ROOT}"

if [ ! -f "${ROOT}/${STANDUP_REL}" ]; then
  echo "check SKIPPED (placeholder-guard-coupling): ${STANDUP_REL} is absent — nothing to couple." >&2
  exit 3
fi

WORK="$(mktemp -d)"
trap 'rm -rf "${WORK}"' EXIT

# ---------------------------------------------------------------------------------------
# PHASE 1 (python): extract the real predicate(s), derive the corpus from the real files,
# and run every assertion that does not need a shell. Writes:
#   ${WORK}/guards.sh     the predicate source lines, verbatim, and nothing else
#   ${WORK}/corpus.tsv    <guard>\t<expect: placeholder|usable>\t<origin>\t<value>
#   ${WORK}/findings.txt  one line per failed assertion
#   ${WORK}/counts.txt    <assertions-run>
# ---------------------------------------------------------------------------------------
"${PYTHON}" - "${ROOT}" "${WORK}" "${STANDUP_REL}" <<'PY'
import re
import sys
from pathlib import Path

try:
    import yaml
except ImportError:                                  # pragma: no cover
    print("check FAIL: PyYAML is required (same dependency as catalog/render.py)",
          file=sys.stderr)
    raise SystemExit(1)

ROOT, WORK, STANDUP_REL = Path(sys.argv[1]), Path(sys.argv[2]), sys.argv[3]
FAILURES: list[str] = []
CHECKS = 0


def check(cond, msg):
    global CHECKS
    CHECKS += 1
    if not cond:
        FAILURES.append(msg)


def bail(msg):
    """A failure that makes the rest of the check meaningless: report and stop."""
    print(f"CHECK FAIL (placeholder-guard-coupling): {msg}", file=sys.stderr)
    (WORK / "findings.txt").write_text(msg + "\n")
    (WORK / "counts.txt").write_text("0\n")
    (WORK / "corpus.tsv").write_text("")
    (WORK / "guards.sh").write_text("")
    raise SystemExit(1)


TEXT = (ROOT / STANDUP_REL).read_text()
LINES = TEXT.splitlines()

# ------------------------------------------------------------------ (5) extract the guard
DEF_RE = re.compile(r"^([a-z0-9_]+_is_placeholder)\(\)\s*\{")
defs: dict[str, list[int]] = {}
for i, line in enumerate(LINES):
    m = DEF_RE.match(line)
    if m:
        defs.setdefault(m.group(1), []).append(i)

if not defs:
    bail(f"{STANDUP_REL} defines no *_is_placeholder predicate. Either the guard was renamed "
         "(update this check's discovery pattern in the SAME change) or it was DELETED, which "
         "is the 2026-09-05 failure with the guard removed instead of disarmed.")

# An "argument-shaped" call: <name> "<something>"
CALL_RE = re.compile(r"\b([a-z0-9_]+_is_placeholder)\s+\"([^\"]*)\"")

guard_src: list[str] = []
guard_words: dict[str, list[str]] = {}
ARM_RE = re.compile(r"^(?P<pats>[^()]*?)\)\s*return\s+[01]\s*;;$")
ALLOWED = (
    re.compile(r"^$"),
    re.compile(r"^#"),
    re.compile(r"^case\s+\"\$\{?[0-9A-Za-z_]+\}?\"\s+in$"),
    re.compile(r"^esac$"),
    re.compile(r"^return\s+[01]$"),
    ARM_RE,
)

for name, at in sorted(defs.items()):
    check(len(at) == 1,
          f"{STANDUP_REL} defines {name}() {len(at)} times (lines "
          f"{', '.join(str(a + 1) for a in at)}) — which one runs depends on file order, and "
          "this check can no longer say which one it extracted. Keep exactly one definition.")
    if len(at) != 1:
        continue
    start = at[0]
    end = next((j for j in range(start + 1, len(LINES)) if LINES[j] == "}"), None)
    if end is None:
        bail(f"{name}() at {STANDUP_REL}:{start + 1} has no closing brace at column 0 — the "
             "extraction boundary this check relies on is gone. Restore the conventional "
             "layout, or move the predicate into a sourceable library and point this check at it.")
    body = LINES[start:end + 1]
    block = "\n".join(body)
    check(block in TEXT,
          f"extracted {name}() is not a verbatim substring of {STANDUP_REL} — extraction bug; "
          "the harness would be testing something the script does not contain")

    words: list[str] = []
    for raw in body[1:-1]:
        s = raw.strip()
        if not any(rx.match(s) for rx in ALLOWED) or "$(" in s or "`" in s:
            bail(f"{name}() at {STANDUP_REL}:{start + 1} is no longer a SELF-CONTAINED "
                 f"case/return predicate (offending line: {s!r}). This check exercises the REAL "
                 "function by sourcing its own lines; a body that calls out to anything else "
                 "cannot be extracted faithfully, and silently testing a COPY of the logic is "
                 "exactly the failure mode this check exists to prevent. REMEDY: move the "
                 "predicate into a tiny library that standup.sh sources (e.g. "
                 "bootstrap/lib/placeholder.sh) and point STANDUP_REL/this extractor at it — do "
                 "NOT reimplement the matching here.")
        m = ARM_RE.match(s)
        if not m:
            continue
        for pat in m.group("pats").split("|"):
            pat = pat.strip()
            if pat in ('""', "''", ""):
                continue                      # the empty-value arm: covered by the canary
            words.append(pat.strip("'\"").strip("*"))
    check(len(words) >= 1,
          f"{name}() has no non-empty placeholder pattern left — every arm that recognises a "
          "loud placeholder string has been removed, so the guard now only refuses the empty "
          "value and any 'TBD'-style endpoint would sail straight through it")
    guard_words[name] = words
    guard_src.append(block)

(WORK / "guards.sh").write_text("\n".join(guard_src) + "\n")

# ------------------------------------------------- no divergent second copy of the logic
# Any of the guard's own vocabulary appearing in EXECUTABLE text outside the predicate means
# a second, independently-drifting implementation of the same test (which is how three
# guards came to disagree with one value in the first place).
guard_line_nums = {j for name, at in defs.items() if len(at) == 1
                   for j in range(at[0], next(k for k in range(at[0] + 1, len(LINES))
                                              if LINES[k] == "}") + 1)}
all_words = sorted({w.upper() for ws in guard_words.values() for w in ws if w})
divergent: list[str] = []
for j, line in enumerate(LINES):
    if j in guard_line_nums or line.strip().startswith("#"):
        continue
    code = line.split("#", 1)[0]
    hit = [w for w in all_words if w in code.upper()]
    if hit:
        divergent.append(f"{STANDUP_REL}:{j + 1} ({', '.join(hit)}): {line.strip()!r}")
check(not divergent,
      "the guard's own placeholder vocabulary appears in EXECUTABLE text outside the "
      f"predicate — a SECOND implementation of the same test, which is precisely how a value "
      f"change disarmed three guards at once. Call the predicate instead. Sites: "
      + " | ".join(divergent))

# ------------------------------------------------------------- cluster-vars, as authored
CV = ROOT / "clusters" / "base" / "cluster-vars.yaml"
if not CV.is_file():
    bail("clusters/base/cluster-vars.yaml is absent — the authored half of the coupling is "
         "missing and this check cannot mean anything")

base: dict[str, str] = {}
for d in yaml.safe_load_all(CV.read_text()):
    if isinstance(d, dict) and d.get("kind") == "ConfigMap" \
            and (d.get("metadata") or {}).get("name") == "cluster-vars":
        base = {str(k): "" if v is None else str(v) for k, v in (d.get("data") or {}).items()}
check(len(base) > 5, f"clusters/base/cluster-vars.yaml yielded {len(base)} knob(s) — the "
                     "ConfigMap parse failed, so every value assertion below would be vacuous")

overlays: dict[str, dict[str, str]] = {}
for overlay in sorted((ROOT / "clusters").glob("*/kustomization.yaml")):
    env = overlay.parent.name
    if env == "base":
        continue
    eff = dict(base)
    try:
        k = yaml.safe_load(overlay.read_text()) or {}
    except Exception as exc:                                   # noqa: BLE001
        check(False, f"clusters/{env}/kustomization.yaml does not parse as YAML ({exc}) — this "
                     "check cannot compute that overlay's effective values")
        continue
    for p in (k.get("patches") or []):
        tgt = p.get("target") or {}
        if tgt.get("kind") != "ConfigMap" or tgt.get("name") != "cluster-vars":
            continue
        try:
            ops = yaml.safe_load(p.get("patch") or "") or []
        except Exception:                                      # noqa: BLE001
            continue
        for op in ops if isinstance(ops, list) else []:
            if not isinstance(op, dict):
                continue
            m = re.match(r"^/data/([A-Za-z0-9_]+)$", str(op.get("path", "")))
            if m and str(op.get("op", "")) in ("replace", "add"):
                eff[m.group(1)] = "" if op.get("value") is None else str(op["value"])
    overlays[env] = eff
check(len(overlays) >= 1,
      "no clusters/<env>/kustomization.yaml overlay was parsed — assertion (2) would be vacuous")

# ------------------------------------------------ which knobs is a guard responsible for?
# Function bodies of standup.sh, then a one-hop taint trace from `x="$(cvar KEY)"` to a
# `*_is_placeholder "${x}"` call. Both halves are read out of the file; nothing is named here.
FUNC_RE = re.compile(r"^([a-z0-9_]+)\(\)\s*\{")
funcs: dict[str, list[str]] = {}
i = 0
while i < len(LINES):
    m = FUNC_RE.match(LINES[i])
    if m:
        end = next((j for j in range(i + 1, len(LINES)) if LINES[j] == "}"), len(LINES) - 1)
        funcs[m.group(1)] = LINES[i + 1:end]
        i = end + 1
        continue
    i += 1
check(len(funcs) > 5, f"parsed only {len(funcs)} function(s) out of {STANDUP_REL} — the "
                      "consumer assertion (3) would be vacuous")

CVAR_RE = re.compile(r"([A-Za-z_][A-Za-z0-9_]*)=\"\$\(\s*cvar\s+([A-Z0-9_]+)\s*\)\"")
ALIAS_RE = re.compile(r"([A-Za-z_][A-Za-z0-9_]*)=\"\$\{([A-Za-z_][A-Za-z0-9_]*)[:}]")

guarded_keys: set[str] = set()
consumers: list[tuple[str, str, bool]] = []      # (func, key, guarded-in-this-func)
for fname, body in funcs.items():
    text = "\n".join(body)
    keys_of_var: dict[str, set[str]] = {}
    for m in CVAR_RE.finditer(text):
        keys_of_var.setdefault(m.group(1), set()).add(m.group(2))
    # one hop of aliasing: ep="${live}" carries live's taint
    for _ in range(3):
        for m in ALIAS_RE.finditer(text):
            src = keys_of_var.get(m.group(2))
            if src:
                keys_of_var.setdefault(m.group(1), set()).update(src)
    called_on = {m.group(2) for m in CALL_RE.finditer(text)}
    called_vars = {re.sub(r"^\$\{?|\}?$", "", a) for a in called_on}
    # Aggregate per (function, knob): the knob is guarded HERE if ANY variable carrying its
    # value is passed to a predicate — `live="$(cvar K)"; ep="${live}"; guard "${ep}"` counts.
    guarded_here: dict[str, bool] = {}
    for var, keys in keys_of_var.items():
        for key in keys:
            guarded_here[key] = guarded_here.get(key, False) or (var in called_vars)
    for key, g in guarded_here.items():
        consumers.append((fname, key, g))
        if g:
            guarded_keys.add(key)

if not guarded_keys:
    bail(f"no cluster-vars knob in {STANDUP_REL} is passed to a *_is_placeholder predicate. "
         "Either the guards were removed, or the way the script reads cluster-vars changed and "
         "this check's derivation must be updated in the SAME change — it must never silently "
         "verify an empty set.")

# (3) CONSUMERS: every reader of a guarded knob must apply the guard to it.
for fname, key, guarded in sorted(consumers):
    if key not in guarded_keys:
        continue                       # nothing claims responsibility for this knob at all
    check(guarded,
          f"{STANDUP_REL}: {fname}() reads cluster-vars knob {key} but never passes it to a "
          "*_is_placeholder guard, while other functions do. On 2026-09-05 all three consumers "
          "of S3_BACKUP_ENDPOINT were disarmed at once; a consumer that reads the knob and skips "
          "the guard is that failure in one function.")

# ---------------------------------------------------------------- independent detector
# Deliberately NOT derived from the guard alone (see the header): SEED is universal
# loud-placeholder vocabulary, and the guard's own words are added so that a guard whose
# ANCHORING is wrong still has its vocabulary tested against real values.
SEED = ["TBD", "TODO", "FIXME", "PLACEHOLDER", "REPLACE-ME", "REPLACEME",
        "CHANGE-ME", "CHANGEME", "FILL-ME", "FILLME", "SET-ME", "XXXX"]
VOCAB = sorted({w.upper() for w in SEED} | set(all_words))
ANGLE = re.compile(r"<[^>\s]+>")


def placeholder_shaped(value: str) -> bool:
    if value.strip() == "":
        return True                                   # an unset endpoint is not a target
    up = value.upper()
    return any(w in up for w in VOCAB) or bool(ANGLE.search(value))


rows: list[tuple[str, str, str, str]] = []            # guard, expect, origin, value
GUARD = sorted(guard_words)[0] if len(guard_words) == 1 else None

# (1) VALUES: base default and every overlay's value, for every guarded knob.
for key in sorted(guarded_keys):
    seen: list[tuple[str, str]] = []
    if key in base:
        seen.append((f"clusters/base/cluster-vars.yaml:{key}", base[key]))
    for env, eff in sorted(overlays.items()):
        seen.append((f"clusters/{env} effective:{key}", eff.get(key, "")))
    check(bool(seen), f"guarded knob {key} is not defined in cluster-vars at all — the guard "
                      "protects a knob nothing authors")
    for origin, value in seen:
        expect = "placeholder" if placeholder_shaped(value) else "usable"
        for name in sorted(guard_words):
            rows.append((name, expect, origin, value))

# (2) OVERLAYS: a placeholder-shaped effective value for an UNGUARDED knob.
for env, eff in sorted(overlays.items()):
    for key, value in sorted(eff.items()):
        if key in guarded_keys or not placeholder_shaped(value):
            continue
        check(False,
              f"clusters/{env}: knob {key} resolves to the placeholder-shaped value {value!r}, "
              f"and NO guard in {STANDUP_REL} refuses it. Either give it a real value before it "
              "reaches an overlay, or guard it the way the S3 endpoint is guarded — an overlay "
              "that ships a placeholder no guard recognises is the 2026-09-05 failure with a "
              "different knob's name on it.")

# (4) ANCHORING: the guard's own vocabulary must match ANYWHERE, not just as a prefix,
#     and a realistic endpoint must still be accepted.
for name, words in sorted(guard_words.items()):
    for w in sorted(set(words)):
        rows.append((name, "placeholder",
                     f"anchoring:{name}:mid-string({w})",
                     f"https://account-{w}-id.r2.cloudflarestorage.com"))
        rows.append((name, "placeholder", f"anchoring:{name}:tail({w})",
                     f"https://r2-endpoint.example.invalid/{w}"))
    rows.append((name, "placeholder", f"canary:{name}:empty", ""))
    rows.append((name, "usable", f"canary:{name}:real-r2",
                 "https://0123456789abcdef0123456789abcd.r2.cloudflarestorage.com"))
    rows.append((name, "usable", f"canary:{name}:real-minio", "http://192.168.1.9:9000"))

# Every guarded knob must reach the oracle once per authored source (base + each overlay),
# so a knob silently dropping out of the corpus is a failure rather than a quiet pass.
authored = [r for r in rows if not r[2].startswith(("anchoring:", "canary:"))]
expected_rows = len(guarded_keys) * (1 + len(overlays)) * len(guard_words)
check(len(authored) == expected_rows,
      f"{len(authored)} authored value(s) reached the guard, expected {expected_rows} "
      f"({len(guarded_keys)} guarded knob(s) x base+{len(overlays)} overlay(s) x "
      f"{len(guard_words)} predicate(s)) — a guarded knob is missing from cluster-vars or from "
      "an overlay's effective values, and the coupling is only partly exercised")

# ------------------------------------------------------- (6) the check is load-bearing
L0 = (ROOT / "ci" / "l0.sh").read_text() if (ROOT / "ci" / "l0.sh").is_file() else ""
GATE = (ROOT / "ci" / "gate.sh").read_text() if (ROOT / "ci" / "gate.sh").is_file() else ""
check("--layer l0" in L0,
      "ci/l0.sh does not run the L0 conformance layer — this check would never execute in the gate")
check(bool(re.search(r"^for s in .*\bl0\b.*; do", GATE, re.M)) and bool(re.search(r"fail\).*BLOCK=1", GATE)),
      "ci/gate.sh does not set the merge block when the l0 stage fails")

# --------------------------------------------------------------------------- handoff
with (WORK / "corpus.tsv").open("w") as fh:
    for name, expect, origin, value in rows:
        fh.write(f"{name}\t{expect}\t{origin}\t{value}\n")
(WORK / "findings.txt").write_text("".join(f"{f}\n" for f in FAILURES))
(WORK / "counts.txt").write_text(f"{CHECKS}\n")

print(f"guards: {', '.join(sorted(guard_words))}  "
      f"vocabulary: {', '.join(VOCAB)}")
print(f"guarded knobs: {', '.join(sorted(guarded_keys))}  "
      f"consumers traced: {len(consumers)}  overlays: {', '.join(sorted(overlays))}")
for name, expect, origin, value in rows:
    if not origin.startswith(("anchoring:", "canary:")):
        print(f"  authored  {origin} = {value!r} -> expect {expect}")
PY

# ---------------------------------------------------------------------------------------
# PHASE 2 (bash): source the REAL predicate lines and run the corpus through them.
# ---------------------------------------------------------------------------------------
# shellcheck disable=SC1090,SC1091
source "${WORK}/guards.sh"

oracle_failures=0
oracle_rows=0
while IFS=$'\t' read -r guard expect origin value; do
  [ -n "${guard}" ] || continue
  oracle_rows=$((oracle_rows + 1))
  if "${guard}" "${value}"; then verdict=placeholder; else verdict=usable; fi
  if [ "${verdict}" != "${expect}" ]; then
    oracle_failures=$((oracle_failures + 1))
    if [ "${expect}" = placeholder ]; then
      printf '%s\n' "${guard}() in ${STANDUP_REL} ACCEPTS '${value}' (from ${origin}) as a usable value, but it is placeholder-shaped. This is the 2026-09-05 failure exactly: the guard is asked about a value it does not recognise, returns 'fine', and the tier it protects is enabled against something that does not exist. Fix the predicate (match the idiom anywhere, not as a prefix) or stop authoring that idiom." >> "${WORK}/findings.txt"
    else
      printf '%s\n' "${guard}() in ${STANDUP_REL} REFUSES '${value}' (from ${origin}), which is a usable value. An over-matching guard leaves the tier it protects suspended forever and reports it as an operator decision — a silent failure in the other direction." >> "${WORK}/findings.txt"
    fi
  fi
done < "${WORK}/corpus.tsv"

# ------------------------------------------------------------------------------ verdict
py_checks="$(cat "${WORK}/counts.txt")"
total=$((py_checks + oracle_rows))
findings="$(cat "${WORK}/findings.txt")"

# NO-OP GUARD: this repo has been bitten by a check that passed when perturbed because it
# asked a question that was always satisfiable. The floors below are the minimum evidence
# for the verdict to mean anything, not a style rule.
if [ "${oracle_rows}" -lt 6 ]; then
  findings="${findings}only ${oracle_rows} value(s) were put to the real guard — the coupling is not actually being exercised
"
fi
if [ "${total}" -lt 20 ]; then
  findings="${findings}only ${total} assertions ran — the check degenerated to a near-no-op and its pass would be meaningless
"
fi

if [ -n "${findings}" ]; then
  echo "CHECK FAIL (placeholder-guard-coupling): $(printf '%s' "${findings}" | grep -c . ) of ${total} assertions failed" >&2
  printf '%s' "${findings}" | sed 's/^/  - /' >&2
  exit 1
fi

echo "check OK: placeholder-guard-coupling — ${total} assertions; ${oracle_rows} value(s) run through the REAL extracted predicate(s) from ${STANDUP_REL} (no reimplementation), covering every authored cluster-vars value of every guarded knob in base and each overlay, the guard's own vocabulary matched mid-string, and the empty/real-endpoint canaries. Static slice only: refusal, not reachability — see the header."