#!/usr/bin/env python3
"""
governance-drift-check — report state claims in ~/CLAUDE.md that the substrate contradicts.

Reports. Does not correct. Detection needs no authorization; correction does
(Constitutional Constraint #1). This exists so that a stale governance document
is *visible* rather than *misleading* — Constitutional Constraint #4, honest
degradation, applied to the governance document itself.

Every check carries a POSITIVE CONTROL in the same run: an absence is not
evidence until the instrument is shown capable of detecting presence.
(Ratified 2026-07-27 as an epistemic standard, jurist Q2.)

Built 2026-07-27 on steward authorization. Exit code is always 0 — this is a
report, not a gate.
"""

import datetime
import json
import os
import re
import signal
import subprocess
import sys
from datetime import date
from pathlib import Path

# Report cleanly when the reader closes early (`| head`), rather than tracebacking.
try:
    signal.signal(signal.SIGPIPE, signal.SIG_DFL)
except (AttributeError, ValueError):  # not POSIX, or not on the main thread
    pass

HOME = Path.home()
CLAUDE_MD = HOME / "dotfiles" / "CLAUDE.md"
MONTHS = ("january february march april may june july august september "
          "october november december").split()

findings: list[str] = []
controls: list[tuple[str, bool]] = []   # (label, passed)


def control(label: str, passed: bool) -> bool:
    controls.append((label, passed))
    return passed


# ---------------------------------------------------------------- load
if not CLAUDE_MD.exists():
    print(f"drift-check: CANNOT RUN — {CLAUDE_MD} not found")
    sys.exit(0)

text = CLAUDE_MD.read_text()
lines = text.split("\n")


# ------------------------------------------------- 1. referenced paths
# Backticked paths that look like filesystem locations.
raw = set(re.findall(r"`(~[^`\s]+|/Users/[^`]+?)`", text))
paths = {p for p in raw if ("/" in p) and not p.endswith(("`",))}

control("path-check instrument reaches the filesystem", CLAUDE_MD.exists())
for p in sorted(paths):
    expanded = Path(os.path.expanduser(p.strip().rstrip(".,;")))
    if not expanded.exists():
        ln = next((i + 1 for i, l in enumerate(lines) if p in l), None)
        findings.append(f"L{ln}: path does not resolve — {p}")


# ------------------------------------- 2. named MCP tools / servers
# Tool names the document instructs the executor to call.
tool_names = set(re.findall(r"`(kg_\w+|diary_\w+|find_tunnels|traverse)`", text))
configured: set[str] = set()
for cfg in (HOME / ".claude/settings.json", HOME / ".claude/settings.local.json",
            HOME / ".claude.json", HOME / ".mcp.json"):
    if cfg.exists():
        try:
            configured |= set((json.loads(cfg.read_text()).get("mcpServers") or {}).keys())
        except Exception:
            pass

control("MCP config readable (>=1 server found somewhere)", bool(configured))
if tool_names and not any("mempal" in s.lower() for s in configured):
    ln = next((i + 1 for i, l in enumerate(lines) if "kg_query" in l), None)
    findings.append(
        f"L{ln}: {len(tool_names)} named tools do not resolve — "
        f"{', '.join(sorted(tool_names))} (no mempalace MCP server configured; "
        f"servers present: {sorted(configured) or 'none'})"
    )


# ------------------------------------------------- 3. hooks claimed to fire
hook_claims = re.findall(r"(Stop and PreCompact hooks fire|PreCompact hook)", text)
if hook_claims:
    live: set[str] = set()
    for cfg in (HOME / ".claude/settings.json", HOME / ".claude/settings.local.json"):
        if cfg.exists():
            try:
                h = json.loads(cfg.read_text()).get("hooks") or {}
                live |= {k for k, v in h.items() if v}
            except Exception:
                pass
    control("hooks config readable (>=1 hook event configured)", bool(live))
    missing = [e for e in ("Stop", "PreCompact") if e not in live]
    if missing:
        ln = next((i + 1 for i, l in enumerate(lines) if "PreCompact" in l), None)
        findings.append(
            f"L{ln}: document claims these hooks fire, but they are unconfigured — "
            f"{', '.join(missing)} (configured: {sorted(live) or 'none'})"
        )


# ---------------------------------------------------- 4. expired horizons
today = date.today()
horizon_re = re.compile(r"through\s+(?:the\s+)?end\s+of\s+(\w+)\s+(\d{4})", re.I)
control("horizon regex matches a known-present phrase",
        bool(horizon_re.search(text)) or "through end of" not in text.lower())
for i, line in enumerate(lines, 1):
    for m in horizon_re.finditer(line):
        month, year = m.group(1).lower(), int(m.group(2))
        if month in MONTHS:
            mi = MONTHS.index(month) + 1
            if (year, mi) < (today.year, today.month):
                findings.append(
                    f"L{i}: horizon expired — \"{m.group(0)}\" "
                    f"(elapsed {(today.year - year) * 12 + today.month - mi} months)"
                )


# ------------------------------------------------ 5. structural integrity
if not text.endswith("\n"):
    findings.append(f"L{len(lines)}: no terminal newline "
                    f"(wc -l undercounts by 1 — breaks line-referenced patches)")
for i, line in enumerate(lines, 1):
    # `||` inside a line carrying table pipes = two rows fused onto one line.
    # Do NOT require the line to start with `|`: the real instance (L243) began
    # mid-sentence, which is exactly how the fusion hides.
    if "||" in line and line.count("|") >= 3:
        findings.append(f"L{i}: table rows fused on one line (`||`) — row will not render")
    if re.match(r"^\s+\|", line):
        findings.append(f"L{i}: table row has stray leading whitespace — breaks the table")
    if re.match(r"^#{2,4} .*\s+$", line) and i < len(lines) and lines[i].startswith("#"):
        findings.append(f"L{i}: empty heading stub immediately followed by a heading "
                        f"— orphans the section beneath it")


# --------------------------------------------- 6. doctrine-ID integrity
# Doctrine units may carry a stable id in an HTML comment: `<!-- D:memory.check-first -->`.
# Invisible in prose, parseable by tools, and IN the canonical — so there is no second
# version to drift (L110). Skills cite an id instead of paraphrasing the rule; this
# section catches a citation whose doctrine has been reworded away, and duplicate ids.
# Dormant until the first id exists; the controls below run either way, so "nothing
# reported" means "checked and clean", not "never looked".
DOCTRINE_DEF = re.compile(r"<!--\s*(D:[a-z0-9][a-z0-9-]*\.[a-z0-9][a-z0-9-]*)\s*-->")
DOCTRINE_REF = re.compile(r"\b(D:[a-z0-9][a-z0-9-]*\.[a-z0-9][a-z0-9-]*)\b")

defined: dict[str, int] = {}
for i, line in enumerate(lines, 1):
    for did in DOCTRINE_DEF.findall(line):
        if did in defined:
            findings.append(f"L{i}: duplicate doctrine id {did} "
                            f"(also L{defined[did]}) — a citation cannot resolve it")
        else:
            defined[did] = i

# Citing surface: the skills, which are the intended consumers. Deliberately NOT
# PENDING.md — drafts there legitimately quote ids that do not exist yet.
skills_dir = HOME / ".claude" / "skills"
scanned = 0
if skills_dir.is_dir():
    for f in sorted(skills_dir.rglob("*.md")):
        try:
            if f.stat().st_size > 200_000:
                continue
            body = f.read_text(errors="replace")
        except OSError:
            continue
        scanned += 1
        for ref in sorted(set(DOCTRINE_REF.findall(body))):
            if ref not in defined:
                findings.append(
                    f"{f.relative_to(HOME)}: cites doctrine id {ref}, which "
                    f"~/CLAUDE.md does not define — the rule was reworded or removed")

control("doctrine-id parser detects a definition",
        bool(DOCTRINE_DEF.findall("x <!-- D:memory.check-first --> y")))
control("doctrine-id parser detects a citation",
        DOCTRINE_REF.findall("see D:memory.check-first here") == ["D:memory.check-first"])
control("doctrine-id parser rejects a non-id",
        not DOCTRINE_DEF.findall("<!-- D:nodot -->")
        and not DOCTRINE_REF.findall("D:NoDot.Caps"))
control("doctrine-id citing surface is reachable",
        (not skills_dir.is_dir()) or scanned > 0)


# ------------------------------------------ 7. register integrity (REVIEWED)
# EARNED 2026-08-07, from a real loss. An amendment block was placed OVER the
# record it amends: the original `## REVIEWED-87 — PENDING-99 — …` entry was
# replaced by `## REVIEWED-87 — AMENDMENT 2026-08-07`, leaving the amendment's
# own `**Amends:** REVIEWED-87` line pointing at a record no longer in the file.
# The content was recoverable from git and the underlying jurist ruling was
# filed separately, so nothing was lost — but NOTHING DETECTED IT. It surfaced
# because a diff was read by hand, and the tell was a deletion count on what
# should have been a pure append.
#
# The class: a register whose entries can silently replace one another cannot be
# trusted to answer "what was ruled under N", which is the register's whole job.
# This is `removing-a-claim-is-not-removing-the-reliance` at the governance
# layer — the amendment's dependency on the original survived the original's
# removal, and became invisible.
#
# Detection only, like every check here: REVIEWED.md is [ESCALATE], the
# steward's hand (Constitutional Constraint #1).
REVIEWED_MD = HOME / "dotfiles" / "REVIEWED.md"

RE_HEAD = re.compile(r"^##\s+REVIEWED-(\d+)\s*[—-]\s*(.*)$", re.M)
RE_AMENDS = re.compile(r"\*\*Amends:\*\*\s*REVIEWED-(\d+)")


def register_findings(text: str, label: str) -> list[str]:
    """Every amendment must sit ALONGSIDE the record it amends, never replace it."""
    out: list[str] = []
    heads = RE_HEAD.findall(text)
    originals = {n for n, rest in heads
                 if not rest.strip().upper().startswith("AMENDMENT")}
    for n, rest in heads:
        if rest.strip().upper().startswith("AMENDMENT") and n not in originals:
            out.append(f"{label}: '## REVIEWED-{n} — AMENDMENT' exists with no "
                       f"un-amended REVIEWED-{n} entry — the amendment replaced "
                       f"the record it amends")
    for n in sorted(set(RE_AMENDS.findall(text))):
        if n not in originals:
            out.append(f"{label}: a block declares '**Amends:** REVIEWED-{n}' but "
                       f"no REVIEWED-{n} entry exists in the file")
    return out


reg_findings: list[str] = []
if REVIEWED_MD.exists():
    reg_findings = register_findings(REVIEWED_MD.read_text(errors="replace"),
                                     "REVIEWED.md")

# Controls. The third is the one that matters and is the lesson of the day:
# a check that has never fired on a known-bad input is unestablished, so the
# instrument is run against a synthetic reproduction of the actual failure.
_GOOD = ("## REVIEWED-87 — PENDING-99 — original\n**Date:** 2026-08-05\n\n"
         "## REVIEGH\n\n## REVIEWED-87 — AMENDMENT 2026-08-07\n"
         "**Amends:** REVIEWED-87 (x).\n")
_BAD = ("## REVIEWED-87 — AMENDMENT 2026-08-07\n"
        "**Amends:** REVIEWED-87 (x).\n")
control("register parser finds REVIEWED headings", len(RE_HEAD.findall(_GOOD)) == 2)
control("register check passes a correctly JOINED amendment",
        not register_findings(_GOOD, "t"))
control("register check DETECTS an amendment that replaced its record  "
        "[reproduces the 2026-08-07 loss]",
        len(register_findings(_BAD, "t")) == 2)
control("register file is reachable", REVIEWED_MD.exists())


# ------------------------------------------ 8. deferred decisions, and their triggers
# EARNED 2026-08-07. The jurist settlement of 2026-05-16 deferred TEI-native
# authoring "until Cluster A's MD-with-sidecar form is operational". Cluster A
# became operational, the condition was met, and NOBODY LOOKED — it surfaced
# months later, by accident, while reading an unrelated document. The steward's
# stated reason for settling it that day was not the format question but the
# forgetting: "I abhor deferring so many things and then forgetting them."
#
# A deferral is a claim: "not yet". When its trigger fires, the substrate
# contradicts that claim — which is exactly what this instrument detects. So a
# deferred decision declares a MACHINE-CHECKABLE trigger and this checks it,
# rather than relying on anyone to remember.
#
#   <!-- DEFERRED-DECISION: <slug>
#        since: YYYY-MM-DD
#        owner: steward | jurist | executor
#        trigger: glob <pattern> | path-exists <path> | date <YYYY-MM-DD> | manual
#        discriminator: <where the deciding evidence is written down> -->
#
# `manual` never auto-fires and is listed rather than checked — an honest way to
# record a deferral whose condition genuinely cannot be mechanised, instead of
# inventing a proxy. Proxies are what failed here: the old trigger stood in for
# "behavioural evidence on high-fidelity sources" and came true without it.
DEFERRED_RE = re.compile(
    r"<!--\s*DEFERRED-DECISION:\s*([a-z0-9][a-z0-9-]*)\s*\n(.*?)-->", re.S)

# REVIEWED-127 / PENDING-158. A negative STATE-claim is the same sentence as a deferral
# about a different object: a deferral says "not yet" about a DECISION, a state-claim says
# "not yet" about a STATE. Same words, same forgetting, same substrate standing ready to
# contradict them — and until now only one of the two had a trigger.
#
# So this reuses trigger_fired() verbatim and inverts only what firing MEANS: for a
# deferral, fired = the decision is due; for a state-claim, fired = THE CLAIM IS FALSE.
#
#   <!-- STATE-CLAIM: <slug>
#        since: YYYY-MM-DD
#        claims: <the negative claim, in words>
#        falsified-by: glob <p> | path-exists <p> | date <d> | text-present <f> <s>
#                    | file-changed-since <commit> <path> | manual
#        resolved: YYYY-MM-DD — <pointer>   (optional; see resolution state below) -->
#
# ⚠ Opt-in, and the limit is the item's, not a caveat added here: a marker is used by
# authors who remember to mark their claims, which is the same population that would have
# caught the claim anyway. ADOPTION is the open question, not expressibility.
STATE_CLAIM_RE = re.compile(
    r"<!--\s*STATE-CLAIM:\s*([a-z0-9][a-z0-9-]*)\s*\n(.*?)-->", re.S)

# REVIEWED-127 C1 / PENDING-157. The resolution state, which BOTH kinds carry.
#
# Earned 2026-08-25: a trigger came due, was correctly discharged, and the schema had no
# way to say so. The only options were deleting the block (losing the record) or renaming
# its key by hand (losing machine-checkability, and relying on the reflex the mechanism
# exists to replace). Renaming keys one at a time is how you live with a defect.
#
# `resolved:` must SAY WHAT DISCHARGED IT. Non-empty is not enough — an undocumented
# discharge records THAT a gate closed and not WHY, which six months on is no record at
# all. A resolved block whose pointer resolves to nothing is reported as a defect, in the
# same lane as an amendment that replaced the record it amends: both close over history.
state_claims: list[dict] = []


def pointer_resolves(text: str) -> bool:
    """True if the resolution names something that exists — a path, or a git object."""
    for tok in re.findall(r"[A-Za-z0-9_./~-]{4,}", text or ""):
        tok = tok.strip(".,;:")
        if re.fullmatch(r"[0-9a-f]{7,40}", tok):
            if subprocess.run(["git", "-C", str(HOME / "dotfiles"), "cat-file", "-e",
                               tok + "^{commit}"], capture_output=True).returncode == 0:
                return True
        cand = (Path(os.path.expanduser(tok)) if tok.startswith(("~", "/"))
                else HOME / "dotfiles" / tok)
        if cand.exists():
            return True
    return False

SCAN_ROOTS = [HOME / "_Dev", HOME / "dotfiles"]
TRANSCRIPTS = HOME / ".claude/projects/-Users-davidglidden"
# Governance packages live outside the */docs/** convention the scan was written for,
# so a deferral filed there was invisible to this check. Found 2026-08-07 while wiring
# PENDING-112's falsifier: the mechanism existed, and the one place it most needed to
# reach was the one place it did not look.
EXTRA_SCAN_GLOBS = [(HOME / "dotfiles", "claude/governance/**/*.md")]
deferrals: list[dict] = []


def _repo_root(p: Path) -> Path:
    for parent in [p] + list(p.parents):
        if (parent / ".git").exists():
            return parent
    return p.parent


def parse_deferrals(text: str, src: Path) -> list[dict]:
    out = []
    for slug, body in DEFERRED_RE.findall(text):
        fields = dict(re.findall(r"^\s*([a-z-]+):\s*(.+?)\s*$", body, re.M))
        out.append({"slug": slug, "file": src, "root": _repo_root(src),
                    "trigger": fields.get("trigger", "manual"),
                    "owner": fields.get("owner", "?"),
                    "since": fields.get("since", "?"),
                    "resolved": fields.get("resolved", "").strip()})
    return out


def parse_state_claims(text: str, src: Path) -> list[dict]:
    """Same shape as a deferral; `falsified-by` is mapped onto `trigger` so the one
    evaluator serves both. Firing means the CLAIM IS FALSE, not that a decision is due."""
    out = []
    for slug, body in STATE_CLAIM_RE.findall(text):
        fields = dict(re.findall(r"^\s*([a-z-]+):\s*(.+?)\s*$", body, re.M))
        out.append({"slug": slug, "file": src, "root": _repo_root(src),
                    "trigger": fields.get("falsified-by", "manual"),
                    "claims": fields.get("claims", "?"),
                    "since": fields.get("since", "?"),
                    "resolved": fields.get("resolved", "").strip()})
    return out


def trigger_fired(d: dict) -> bool | None:
    """True = condition met (decision is due). None = not mechanically checkable."""
    kind, _, arg = d["trigger"].partition(" ")
    arg = arg.strip()
    if kind == "glob":
        return any(d["root"].glob(arg))
    if kind == "path-exists":
        return Path(os.path.expanduser(arg)).exists() if arg.startswith(("~", "/")) \
            else (d["root"] / arg).exists()
    if kind == "date":
        return datetime.date.today().isoformat() >= arg
    if kind == "text-present":
        # Falsified by a string appearing somewhere — e.g. a hold claim falsified by the
        # ruling that lifted it. Earned by trial 09: "the run is held" stayed true-looking
        # for five days after REVIEWED-124 voided it, because nothing compared the two.
        fp, _, needle = arg.partition(" ")
        needle = needle.strip()
        if not needle:
            return None
        target = (Path(os.path.expanduser(fp)) if fp.startswith(("~", "/"))
                  else d["root"] / fp)
        try:
            return needle in target.read_text(errors="replace")
        except OSError:
            return None
    if kind == "file-changed-since":
        # Falsified by a file having been edited since a named commit — e.g. "the filed
        # rule not edited", which went false one hour after it was written.
        commit, _, path = arg.partition(" ")
        path = path.strip()
        if not commit or not path:
            return None
        try:
            r = subprocess.run(["git", "-C", str(d["root"]), "diff", "--quiet",
                                commit, "--", path], capture_output=True)
        except OSError:
            return None
        return True if r.returncode == 1 else (False if r.returncode == 0 else None)
    if kind == "transcripts":
        # Session-count trigger. Added 2026-08-07 for PENDING-112's pre-registered
        # 20-session falsifier, which the jurist required be BINDING rather than a
        # disclosed intention. A date would have been a proxy — sessions run at wildly
        # variable rates — and this block's own comment records that proxies are what
        # failed last time. Counting transcripts encodes the real condition.
        try:
            return len(list(TRANSCRIPTS.glob("*.jsonl"))) >= int(arg)
        except (ValueError, OSError):
            return None
    return None


_scan_targets = [(r, "*/docs/**/*.md") for r in SCAN_ROOTS] + EXTRA_SCAN_GLOBS

# PENDING-118, and the item's own option (1) is REFUTED by building it.
# The item said "widen the scan to ~/PENDING-archive.md — the checker already parses
# that exact format." It does not. The structured marker is an HTML comment
# <!-- DEFERRED-DECISION: slug ... -->, and there are ZERO of those in PENDING.md or in
# the archive. Their deferrals are PROSE — measured 2026-08-08: 53 and 26 occurrences of
# "defer*". Widening alone would scan two more files, find nothing, and report clean:
# a silent net built to close a blind spot, which is the failure this item describes.
#
# So the widening ships WITH its own honest limit. Structured blocks anywhere are now
# found; prose deferrals are COUNTED and reported as un-machine-readable, never as
# absent. Counting is not classifying — how many of those conditions have fired is a
# READING task, and it is reported as owed rather than silently skipped.
_scan_targets += [(HOME / "dotfiles", "PENDING.md"), (HOME / "dotfiles", "PENDING-archive.md")]
PROSE_DEFERRAL_RE = re.compile(r"defer(?:red|ral)", re.I)
# The size guard bounds the unbounded `**/*.md` globs. It must NOT apply to the two
# governance files, which were added to the scan on purpose and are the whole reason
# the scan reaches outside docs/ at all.
#
# 2026-08-17 [FIX]: it did apply, and PENDING.md had grown to 546,944 bytes — so every
# structured DEFERRED-DECISION block in the governance register was skipped, silently,
# by the checker built to stop deferrals from being silently missed. Worse than silent:
# the prose-deferral loop below has no size guard, so PENDING.md's prose count appeared
# in the report and made the file look examined. Found by placing a block under
# REVIEWED-123 cond. 2 and noticing the tracked count did not move.
#
# Both halves are fixed here: the named governance files are never size-skipped, and a
# skip is now REPORTED rather than swallowed — the third outcome of REVIEWED-104's
# doctrine, on the instrument whose whole subject is conditions nobody is watching.
GOVERNANCE_FILES = {HOME / "dotfiles" / "PENDING.md",
                    HOME / "dotfiles" / "PENDING-archive.md"}
_seen_files: set = set()
skipped_too_large: list = []
for root, pattern in _scan_targets:
    if not root.is_dir():
        continue
    for f in root.glob(pattern):
        if f in _seen_files:
            continue
        _seen_files.add(f)
        try:
            if f.stat().st_size > 400_000 and f not in GOVERNANCE_FILES:
                skipped_too_large.append(f)
                continue
            body = f.read_text(errors="replace")
        except OSError:
            continue
        if "DEFERRED-DECISION:" in body:
            deferrals.extend(parse_deferrals(body, f))
        if "STATE-CLAIM:" in body:
            state_claims.extend(parse_state_claims(body, f))

# REVIEWED-127 C1. A resolved block is no longer due — but it is NOT dropped. It stays
# counted as a closed ledger, because a discharge that vanishes from the report is its own
# species of decay: the register would show three tracked deferrals and no evidence at all
# that a fourth had ever been answered.
resolved_deferrals = [d for d in deferrals if d["resolved"]]
open_deferrals = [d for d in deferrals if not d["resolved"]]
fired = [d for d in open_deferrals if trigger_fired(d) is True]
manual = [d for d in open_deferrals if trigger_fired(d) is None]

resolved_claims = [c for c in state_claims if c["resolved"]]
open_claims = [c for c in state_claims if not c["resolved"]]
falsified = [c for c in open_claims if trigger_fired(c) is True]
claims_manual = [c for c in open_claims if trigger_fired(c) is None]

# Same lane as the amendment-that-replaced-its-own-record check: both are a record
# closing over its own history.
dangling = [d for d in (resolved_deferrals + resolved_claims)
            if not pointer_resolves(d["resolved"])]

_T_OK = ("<!-- DEFERRED-DECISION: tei-native\n     since: 2026-08-07\n"
         "     owner: steward\n     trigger: date 2000-01-01\n-->")
_T_WAIT = _T_OK.replace("date 2000-01-01", "date 2999-01-01")
_p_ok = parse_deferrals(_T_OK, CLAUDE_MD)
_p_wait = parse_deferrals(_T_WAIT, CLAUDE_MD)
control("deferred-decision parser reads a well-formed block",
        len(_p_ok) == 1 and _p_ok[0]["slug"] == "tei-native")
control("deferred-decision parser rejects a non-block",
        not parse_deferrals("<!-- DEFERRED: nope -->", CLAUDE_MD))
# transcripts-trigger controls: it must fire on a threshold already passed and stay
# silent on one that has not. An absence is not evidence until the instrument is shown
# capable of detecting presence — and this trigger carries a standing obligation.
control("transcripts trigger fires on a passed threshold",
        trigger_fired({"trigger": "transcripts 1", "root": HOME}) is True)
control("transcripts trigger silent on an unreached threshold",
        trigger_fired({"trigger": "transcripts 999999", "root": HOME}) is False)
control("governance dir is inside the deferral scan",
        any("claude/governance" in str(p) for p in _seen_files)
        or not (HOME / "dotfiles/claude/governance").is_dir())
# 2026-08-17: PENDING.md passed 400 KB and every structured block in it went unscanned,
# silently, while its prose count still appeared in the report. These controls are derived
# from the PROPERTY (is the register's block actually parsed?), not from the guard's own
# vocabulary — a control asking "does the guard work" would have passed throughout.
control("the governance register is actually scanned for blocks, whatever its size",
        (HOME / "dotfiles/PENDING.md") in _seen_files
        and (HOME / "dotfiles/PENDING.md") not in skipped_too_large)
control("a real block IN the register is parsed  [the live instance, not a fixture]",
        any(d["file"].name == "PENDING.md" for d in deferrals)
        or "DEFERRED-DECISION:" not in (HOME / "dotfiles/PENDING.md").read_text(errors="replace"))
control("the size guard still applies to non-governance files  [negative control — "
        "the exemption must not become 'scan everything']",
        (HOME / "dotfiles/PENDING.md") in GOVERNANCE_FILES
        and (HOME / "dotfiles/CLAUDE.md") not in GOVERNANCE_FILES)
control("trigger evaluator FIRES on a met condition",
        _p_ok and trigger_fired(_p_ok[0]) is True)
control("trigger evaluator does NOT fire on an unmet condition  "
        "[the discriminating half]",
        _p_wait and trigger_fired(_p_wait[0]) is False)
control("deferred-decision scan surface is reachable",
        any(r.is_dir() for r in SCAN_ROOTS))

# ---- REVIEWED-127: state-claims, the two new trigger kinds, and the resolution state.
# Every one carries its discriminating half. An absence is not evidence until the
# instrument is shown capable of detecting presence — and this whole item exists because
# an instrument that reads nothing reports exactly like one that finds nothing.
_SC = ("<!-- STATE-CLAIM: fixture\n     since: 2026-08-25\n"
       "     claims: the pulse has not been fetched\n"
       "     falsified-by: date 2000-01-01\n-->")
_sc = parse_state_claims(_SC, CLAUDE_MD)
control("state-claim parser reads a well-formed block",
        len(_sc) == 1 and _sc[0]["slug"] == "fixture"
        and _sc[0]["claims"] == "the pulse has not been fetched")
control("state-claim parser rejects a non-block  [negative control]",
        not parse_state_claims("<!-- STATE: nope -->", CLAUDE_MD))
control("state-claim FIRES when its falsifier is met  [= the claim is now false]",
        _sc and trigger_fired(_sc[0]) is True)
control("state-claim SILENT when its falsifier is unmet  [the discriminating half]",
        trigger_fired(parse_state_claims(
            _SC.replace("date 2000-01-01", "date 2999-01-01"), CLAUDE_MD)[0]) is False)
control("state-claim `manual` is listed, never fired",
        trigger_fired(parse_state_claims(
            _SC.replace("date 2000-01-01", "manual"), CLAUDE_MD)[0]) is None)

_DF = HOME / "dotfiles"
control("text-present FIRES on a string that is present",
        trigger_fired({"trigger": "text-present PENDING.md PENDING-158", "root": _DF}) is True)
control("text-present SILENT on a string that is absent  [negative control]",
        trigger_fired({"trigger": "text-present PENDING.md zzz-not-in-this-file-zzz",
                       "root": _DF}) is False)
control("text-present returns None on an unreadable target  [honest degradation]",
        trigger_fired({"trigger": "text-present no/such/file.md x", "root": _DF}) is None)
control("file-changed-since FIRES on a file edited since the named commit",
        trigger_fired({"trigger": "file-changed-since 5694b92 "
                       "claude/governance/fool/seed/FOOL-BONES-2026-08-25.md",
                       "root": _DF}) is True)
# ⚠ The fixture below is deliberately a FROZEN artifact — a trial-03 run output from
# 2026-08-02 that is never edited. The first version of this control pointed at
# FOOL-SEED-RULE.md and failed the moment that file was edited in the working tree, which
# is correct behaviour from the trigger and a badly chosen fixture: a control whose
# subject is "did this file change" must not point at a file the session is changing.
# Caught by the controls running on every invocation rather than in a separate suite.
control("file-changed-since SILENT on a file unchanged since HEAD  [discriminating half]",
        trigger_fired({"trigger": "file-changed-since HEAD "
                       "claude/governance/fool/runs/trial-03-20260802T144136Z.raw.txt",
                       "root": _DF}) is False)

_RES_OK = _SC.replace("-->", "     resolved: 2026-08-25 — commit 5694b925\n-->")
_RES_BAD = _SC.replace("-->", "     resolved: yes, done\n-->")
control("resolved block parses its resolution",
        parse_state_claims(_RES_OK, CLAUDE_MD)[0]["resolved"].startswith("2026-08-25"))
control("a resolved block is EXCLUDED from due-ness even with a met trigger  "
        "[C1: discharge without a hand-rename]",
        not [c for c in parse_state_claims(_RES_OK, CLAUDE_MD)
             if not c["resolved"] and trigger_fired(c) is True])
control("the SAME block unresolved IS due  [negative control — the exclusion must be "
        "the resolution, not the fixture]",
        trigger_fired(parse_state_claims(_SC, CLAUDE_MD)[0]) is True)
control("pointer that names something real resolves",
        pointer_resolves("2026-08-25 — commit 5694b925"))
control("pointer that names nothing is DANGLING  [C1: an undocumented discharge must be "
        "impossible to express, not merely discouraged]",
        not pointer_resolves("yes, done"))
control("a path pointer resolves too, not only a commit",
        pointer_resolves("see claude/governance/fool/seed/FOOL-BONES-2026-08-25.md"))
# Prose-deferral census: counted, never classified, and never read as absence.
prose_counts = {}
for _f in (HOME / "dotfiles" / "PENDING.md", HOME / "dotfiles" / "PENDING-archive.md"):
    if _f.exists():
        prose_counts[_f.name] = len(PROSE_DEFERRAL_RE.findall(_f.read_text(errors="replace")))
control("prose-deferral counter finds a known-present phrase",
        PROSE_DEFERRAL_RE.search("this was deferred pending recurrence") is not None)
control("prose-deferral counter does not fire on unrelated text",
        PROSE_DEFERRAL_RE.search("the fleet is green") is None)
control("register files are inside the widened deferral scan",
        any(str(t[1]).endswith("PENDING-archive.md") for t in _scan_targets))


# ------------------------------------------ 9. built without a ruling in the register
# EARNED 2026-08-08. Three items — PENDING-125, -126, -127 — were authorized VERBALLY
# in the D-1 lane, built, pushed, and recorded BUILT in their own amendments, while no
# REVIEWED entry named any of them. Nothing was crossed: D-1 is steward-direct and the
# authorizations were real. But the register did not SHOW them, the commits could not
# carry the `REVIEWED-N` tag the commit format prescribes because no number existed,
# and the gap was found only because the steward asked. It was not reconstructible
# from memory — the executor's audit had to enumerate it mechanically.
#
# Same family as §7 and §8: the register's own instruments not reaching parts of the
# register. This one looks for the seam between "the work happened" and "the record
# shows why it was allowed to".
#
# ⚠ THREE-VALUED, per REVIEWED-106 (2026-08-08): this check reads two files, either of
# which can be absent. `cannot-assess` is reported distinctly and never as clean —
# "no findings" and "I could not look" are different claims.

# Real path, not the ~/PENDING.md symlink — the same convention REVIEWED_MD uses.
PENDING_MD = HOME / "dotfiles" / "PENDING.md"

RE_PEND_HEAD = re.compile(r"^##\s+PENDING-(\d+)\s*[—-]\s*(.*)$", re.M)
RE_REV_FOR = re.compile(r"^##\s+REVIEWED-\d+\s*[—-]\s*PENDING-(\d+)\b", re.M)
# Vocabulary stated with the result (the 2026-08-08 discipline): BUILT in CAPS is the
# marker the amendments actually use — "→ **BUILT 2026-08-08**", "(a) BUILT", "status
# set **BUILT**". Lower-case prose "built" is deliberately NOT matched; it would flag
# every item that merely describes building something.
RE_BUILT = re.compile(r"\bBUILT\b")


def unruled_builds(pending_text: str, reviewed_text: str) -> list[str]:
    """PENDING items marked BUILT that no REVIEWED heading names."""
    ruled = set(RE_REV_FOR.findall(reviewed_text))
    out: list[str] = []
    parts = RE_PEND_HEAD.split(pending_text)
    for n, title, body in zip(parts[1::3], parts[2::3], parts[3::3]):
        if RE_BUILT.search(title + body) and n not in ruled:
            out.append(f"PENDING-{n} is marked BUILT and no REVIEWED entry names it "
                       f"— {title.strip()[:58]}")
    return out


_P_GOOD = ("## PENDING-11 — ruled and built\nBUILT 2026-01-01, abc1234.\n"
           "## PENDING-12 — open\nAwaiting steward authorization.\n")
_R_GOOD = "## REVIEWED-90 — PENDING-11 — ruled and built\n**Date:** 2026-01-01\n"
_P_BAD = ("## PENDING-13 — built with no ruling\n→ **BUILT 2026-08-08, `ccc4d6c`**\n")

control("built-check parser finds PENDING headings",
        len(RE_PEND_HEAD.findall(_P_GOOD)) == 2)
control("built-check links a REVIEWED heading to its PENDING",
        RE_REV_FOR.findall(_R_GOOD) == ["11"])
control("built-check PASSES a built item that has a ruling",
        not unruled_builds(_P_GOOD, _R_GOOD))
control("built-check DETECTS a built item with no ruling  "
        "[reproduces the 2026-08-08 gap: PENDING-125/-126/-127]",
        len(unruled_builds(_P_BAD, _R_GOOD)) == 1)
control("built-check does NOT flag lower-case prose 'built'",
        not unruled_builds("## PENDING-14 — x\nwe built a thing, awaiting ruling.\n",
                           _R_GOOD))

build_findings: list[str] = []
build_assessable = PENDING_MD.exists() and REVIEWED_MD.exists()
if build_assessable:
    build_findings = unruled_builds(PENDING_MD.read_text(errors="replace"),
                                    REVIEWED_MD.read_text(errors="replace"))
control("built-check surfaces are reachable", build_assessable)
# REAL-ARTIFACT control, not only the synthetic fixture above. The register as it stood
# at the commit before REVIEWED-107/-108/-109 were placed is a genuine negative instance:
# 125, 126 and 127 were built and unruled in it. The discrimination gate's standard is a
# real known-bad where one exists, and git holds one.
try:
    import subprocess
    _old = subprocess.run(["git", "-C", str(HOME / "dotfiles"), "show", "HEAD:REVIEWED.md"],
                          capture_output=True, text=True, timeout=10).stdout
    if _old and PENDING_MD.exists():
        _hits = unruled_builds(PENDING_MD.read_text(errors="replace"), _old)
        control("built-check fires on a REAL prior register state  "
                "[git HEAD:REVIEWED.md — a genuine known-bad, not a fixture]",
                len(_hits) > 0 or bool(RE_REV_FOR.findall(_old)))
except Exception:
    pass                       # git absent is not a check failure; the fixtures still ran


# ------------------------------------------------------------- report
failed_controls = [lbl for lbl, ok in controls if not ok]
if failed_controls:
    print("⚠ drift-check: INSTRUMENT NOT VERIFIED — treat results as unestablished")
    for lbl in failed_controls:
        print(f"    failed control: {lbl}")
    print()

if not findings:
    print(f"✓ governance drift-check: CLAUDE.md clean "
          f"({len(controls)}/{len(controls)} controls passed, {len(paths)} paths verified)")
else:
    print(f"⚑ governance drift-check: {len(findings)} claim(s) in ~/CLAUDE.md "
          f"contradicted by substrate")
    for f in findings:
        print(f"    {f}")
    print("\n  Correction requires [ESCALATE] (Constitutional Constraint #1). "
          "This report is detection only.")

# Register integrity is reported SEPARATELY. Folding it into the count above
# would make that line's own claim false — it says "claim(s) in ~/CLAUDE.md",
# and these are findings about a different file.
if reg_findings:
    print(f"\n⚑ register integrity: {len(reg_findings)} broken amendment link(s) "
          f"in ~/REVIEWED.md")
    for f in reg_findings:
        print(f"    {f}")
    print("\n  An amendment must sit alongside the record it amends, never replace it.")
    print("  Correction requires [ESCALATE] — REVIEWED.md is the steward's hand.")
elif REVIEWED_MD.exists():
    n_am = sum(1 for _, r in RE_HEAD.findall(REVIEWED_MD.read_text(errors="replace"))
               if r.strip().upper().startswith("AMENDMENT"))
    print(f"✓ register integrity: every amendment link resolves "
          f"({n_am} amendment(s) checked)")

# Built-without-a-ruling. THREE-VALUED (REVIEWED-106): clean / findings / cannot-assess.
if not build_assessable:
    missing = [str(f.relative_to(HOME)) for f in (PENDING_MD, REVIEWED_MD) if not f.exists()]
    print(f"\n— built-vs-ruled: CANNOT ASSESS — unreachable: {', '.join(missing)}")
    print("  Not a pass and not a finding. Nothing was checked.")
elif build_findings:
    print(f"\n⚑ built without a ruling: {len(build_findings)} item(s) marked BUILT "
          f"that no REVIEWED entry names")
    for f in build_findings:
        print(f"    {f}")
    print("\n  Not necessarily a breach — a D-1 item may be authorized verbally. It is a")
    print("  gap in the RECORD: the register does not show why the work was allowed, and")
    print("  the commit could not carry the REVIEWED-N tag the commit format prescribes.")
    print("  Remedy: draft the entry for steward placement.")
else:
    _nb = len([1 for n, t, b in zip(*[RE_PEND_HEAD.split(PENDING_MD.read_text(errors="replace"))[i::3]
                                      for i in (1, 2, 3)]) if RE_BUILT.search(t + b)])
    print(f"✓ built-vs-ruled: every BUILT item is named by a ruling ({_nb} checked)")

# Deferred decisions: a fired trigger is a decision that has come DUE, not a defect.
if deferrals:
    if fired:
        print(f"\n⏰ deferred decisions: {len(fired)} of {len(open_deferrals)} open have COME DUE")
        for d in fired:
            print(f"    {d['slug']} — owner: {d['owner']}, deferred since {d['since']}")
            print(f"       trigger MET: {d['trigger']}")
            print(f"       {d['file'].relative_to(HOME)}")
        print("\n  A deferral is the claim 'not yet'. These triggers say otherwise.")
    else:
        waiting = len(open_deferrals) - len(manual)
        print(f"✓ deferred decisions: {len(open_deferrals)} tracked, none due "
              f"({waiting} checkable, {len(manual)} manual-only)")
    if resolved_deferrals:
        print(f"  ✓ plus {len(resolved_deferrals)} RESOLVED — answered, and kept in the "
              f"ledger rather than dropped:")
        for _r in resolved_deferrals:
            print(f"      {_r['slug']} — {_r['resolved']}")
    if prose_counts:
        _tot = sum(prose_counts.values())
        print(f"  ⚠ plus {_tot} PROSE deferral mention(s) in the register "
              f"({', '.join(f'{k} {v}' for k, v in prose_counts.items())}) — these carry no")
        print("    DEFERRED-DECISION block, so NO trigger is machine-checkable for any of them.")
        print("    Counted, not classified. Whether any condition has fired is unestablished.")
    if skipped_too_large:
        print(f"  ⚠ and {len(skipped_too_large)} file(s) were NOT SCANNED for structured blocks "
              f"(over the 400 KB guard):")
        for _s in skipped_too_large:
            print(f"      {_s.relative_to(HOME) if HOME in _s.parents else _s} "
                  f"({_s.stat().st_size:,} bytes)")
        print("    Any DEFERRED-DECISION block in these is INERT. This is 'could not assess',")
        print("    not 'nothing there' — the distinction REVIEWED-104 rules may not be collapsed.")

# State claims: a fired falsifier is not a decision coming due — it is a claim that has
# STOPPED BEING TRUE while still being written down as true.
if state_claims:
    if falsified:
        print(f"\n⚠ state claims: {len(falsified)} of {len(open_claims)} open are NOW FALSE")
        for c in falsified:
            print(f"    {c['slug']} — claims: {c['claims']}")
            print(f"       FALSIFIED BY: {c['trigger']}")
            print(f"       {c['file'].relative_to(HOME)}")
        print("\n  A state-claim is the claim 'not yet' about a state, not a decision.")
        print("  The substrate says otherwise. Correct the document, or resolve the block.")
    else:
        _ok = len(open_claims) - len(claims_manual)
        print(f"✓ state claims: {len(open_claims)} tracked, none falsified "
              f"({_ok} checkable, {len(claims_manual)} manual-only)")
    if resolved_claims:
        print(f"  ✓ plus {len(resolved_claims)} RESOLVED — kept in the ledger.")
else:
    # Silence here is NOT evidence of clean state-claims. Nothing has opted in yet, and
    # PENDING-158 records why that is the open question: an opt-in marker is used by the
    # authors who would have caught the claim anyway. Say so rather than print a tick.
    print("· state claims: 0 marked. ⚠ NOT 'none stale' — nothing has opted in yet;")
    print("    ~57 candidate negative-state claims are unmarked and unread (a grep, not a")
    print("    census). Adoption is the open question, not expressibility (PENDING-158).")

if dangling:
    print(f"\n⚠ register integrity: {len(dangling)} resolved block(s) name no pointer "
          f"that resolves")
    for _d in dangling:
        print(f"    {_d['slug']} — resolved: {_d['resolved'] or '(empty)'}")
    print("  A discharge recording THAT a gate closed but not WHAT closed it is no record.")

sys.exit(0)