#!/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 json
import os
import re
import subprocess
import sys
from datetime import date
from pathlib import Path

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")


# ------------------------------------------------------------- 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.")

sys.exit(0)