#!/usr/bin/env python3
"""Self-check for the wizard-work triage report.

Re-derives the completion state of every top-level `wizard-work/` directory
from the filesystem (same deterministic markers as triage_work_status.py) and
cross-checks the committed report at
`wizard-work-triage-2026-10-21.md`:

  * every top-level dir appears in the report, and
  * the reported markers line matches what the disk now shows, and
  * the reported state is consistent with the markers under the documented rule.

Exit 0 = the artifact is correct; exit 1 = mismatch or missing report.
"""
import os
import re
import sys

REPO = "/root/troupe-standup"
SRC = os.path.join(REPO, "wizard-work")
REPORT = os.path.join(REPO, "wizard-work", "sol", "wizard-work-triage-2026-10-21.md")

MARKER_NAMES = [
    "has_CHECK", "has_final", "has_verification", "has_checksum",
    "has_verify_py", "has_test_py", "has_readme", "has_runbook",
]
NESTED = "nested_dirs"
DESC = "file_count"


def _walk_files(d):
    out = []
    for root, dirs, files in os.walk(d):
        dirs[:] = [x for x in dirs if x not in ("__pycache__", ".git")]
        for f in files:
            out.append(os.path.relpath(os.path.join(root, f), d))
    return out


def _markers(d):
    files = _walk_files(d)
    m = {
        "has_CHECK": os.path.exists(os.path.join(d, "CHECK"))
        and os.path.getsize(os.path.join(d, "CHECK")) > 0,
        "has_final": os.path.exists(os.path.join(d, "FINAL_REPORT.md")),
        "has_verification": any(
            os.path.exists(os.path.join(d, n)) for n in
            ("VERIFICATION.md", "VERIFICATION.txt", "VERIFICATION.json")
        ),
        "has_checksum": any(f.startswith("checksum") for f in files),
        "has_verify_py": any(
            f.endswith(".py") and (f.startswith("verify_") or f.startswith("_verify_"))
            for f in files
        ),
        "has_test_py": any(f.startswith("test_") and f.endswith(".py") for f in files),
        "has_readme": os.path.exists(os.path.join(d, "README.md"))
        and os.path.getsize(os.path.join(d, "README.md")) > 0,
        "has_runbook": any(
            f in ("runbook.md", "incident-runbook.md") for f in files
        ),
        NESTED: any(
            x not in ("__pycache__", ".git") and os.path.isdir(os.path.join(d, x))
            for x in os.listdir(d)
        ),
        DESC: len(files),
    }
    return m


def _state(m):
    if m["has_final"] and m["has_verification"] and m["has_checksum"]:
        return "verified"
    if m["has_final"] or m["has_checksum"] or m["has_test_py"]:
        return "done"
    if m["has_readme"] and m["has_verify_py"]:
        return "completed"
    if m["has_verify_py"] or m["has_runbook"]:
        return "in-progress"
    if m["has_readme"] and m["file_count"] <= 1:
        return "pending"
    if m["has_readme"]:
        return "completed"
    return "framework"


def rederived():
    rows = []
    if not os.path.isdir(SRC):
        return rows
    for name in sorted(os.listdir(SRC)):
        d = os.path.join(SRC, name)
        if not os.path.isdir(d):
            continue
        m = _markers(d)
        rows.append({"dir": name, "state": _state(m), "markers": m})
    return rows


def parse_report():
    """Return {dir: (state, [markers])} from the committed report markdown."""
    data = {}
    if not os.path.exists(REPORT):
        return data
    text = open(REPORT).read()
    for m in re.finditer(r"^### `([^`]+)` - `([^`]+)`", text, re.M):
        dir_name, state = m.group(1), m.group(2)
        rest = text[m.end():]
        mk = None
        for line in rest.splitlines():
            if line.startswith("- markers: "):
                val = line[len("- markers: "):].strip()
                mk = [] if val == "none" else [x.strip() for x in val.split(",")]
                break
        data[dir_name] = (state, mk)
    return data


def main():
    rederived_rows = rederived()
    report = parse_report()

    # 1) every top-level dir must be reported
    missing = [r["dir"] for r in rederived_rows if r["dir"] not in report]
    if missing:
        print("CHECK FAILED: dirs absent from report: %s" % ", ".join(missing))
        sys.exit(1)

    # 2) markers and state must match the disk
    ok = True
    for r in rederived_rows:
        dir_name, state, m = r["dir"], r["state"], r["markers"]
        rep_state, rep_markers = report[dir_name]
        exp_markers = [k for k in MARKER_NAMES if m.get(k)]
        if rep_state != state:
            print("CHECK FAILED: %s state is `%s`, disk says `%s`"
                  % (dir_name, rep_state, state))
            ok = False
        if rep_markers != exp_markers:
            print("CHECK FAILED: %s markers are %s, disk says %s"
                  % (dir_name, rep_markers, exp_markers))
            ok = False

    # 3) every reported dir must re-derive cleanly (no phantom rows)
    extra = [d for d in report if d not in {r["dir"] for r in rederived_rows}]
    if extra:
        print("CHECK FAILED: phantom dirs in report: %s" % ", ".join(extra))
        ok = False

    if ok:
        print("CHECK PASSED: %d directories match disk (markers + state)." % len(rederived_rows))
    else:
        sys.exit(1)


if __name__ == "__main__":
    main()