#!/usr/bin/env python3
"""build_art_meta.py — regenerate scripts/og-gen/art-meta.json's per-slug entries.

`evidence` is the short factual line printed inside the card's evidence bar. It is
editorial text: every line below quotes a number, log line, file path or command
that exists in that post's body — nothing is derived from the title, and nothing is
invented. The renderer refuses to run for a slug that has no entry, so this file is
also the checklist for the 72-post rollout.

Every slug uses the renderer's default `<art-dir>/<slug>.png`, so no entry needs an `art`
key — that is what lets `banner-plan.json` (keyed by slug) cover all of them.

Usage:  python scripts/og-gen/build_art_meta.py            # rewrite art-meta.json
        python scripts/og-gen/build_art_meta.py --check     # report coverage only
"""
from __future__ import annotations

import argparse
import json
from pathlib import Path

ROOT = Path(__file__).resolve().parents[2]
META = ROOT / "scripts" / "og-gen" / "art-meta.json"

ABOUT = (
    "Inputs for scripts/og-gen/render_from_art.mjs ('one art, four targets'). One entry per post: "
    "`art` = the zero-text base frame (default <art-dir>/<slug>.png), `evidence` = the short factual line "
    "shown in the card's evidence bar (REQUIRED, written by hand — never derived), optional `ogTitle_en` / "
    "`ogTitle_zh` = shortened display titles for the card only (consultant question 1, option C: the article "
    "keeps its real title), optional `tags` = override the three badge tags. Cards render from the post's own "
    "frontmatter (title/description/category) unless an ogTitle override is present."
)

# slug -> evidence line. Each fact is taken from that post's own body.
EVIDENCE: dict[str, str] = {
    "adding-a-domain-to-someone-elses-mail-server": "4 DNS records · 554 antispam reject",
    "adding-english-mode-to-a-chinese-only-web-app": "no browser API · sub_filter EN mode",
    "ai-furniture-compositing-with-flux-kontext": "kontext multi-image · tainted canvas fix",
    "authentik-css-greater-than-bug": "1 escaped '>' · CSS silently dropped",
    "authentik-forward-auth-gate-wasnt-live": "host 302 · public 200 · 2 ingress layers",
    "authentik-major-upgrade-gotchas": "2025.8 → 2026.8 · auth_flow mixup",
    "automating-cyberpanel-without-the-ui": "v2 JSON API gone · session + CSRF",
    "best-ai-video-generators-2026": "free vs paid · local LTX-2.3 test",
    "calibrating-intel-quick-sync-hevc-quality": "ICQ 28-30 cliff · fast == medium",
    "chainlink-vrf-v2-lottery-contract": "VRF v2.5 · mock-funding bug",
    "docker-reported-exit-0-the-oom-killer-disagreed": "exit 0 · dmesg: 6x cgroup OOM kills",
    "does-hevc-actually-shrink-your-files": "NVENC cq27 bigger · x265 -10-22%",
    "embedding-fonts-so-a-pdf-looks-the-same-everywhere": "4 families · 8 faces · 2 renderers",
    "every-player-stuttered-the-file-was-fine": "5818/5818 intervals · 0 duplicate PTS",
    "five-step-ai-roadmap-what-i-actually-run": "whisper + mem0 in production · step 4 skipped",
    "fully-on-chain-svg-nfts": "base64 SVG in tokenURI() · mood flip on-chain",
    "hardening-a-tor-onion-service": "bind 0.0.0.0:80 denied · onion v3",
    "hello-world": "~140-container homelab · self-hosted",
    "how-i-built-the-digikedai-telegram-bot": "Telegram + WhatsApp · LiteLLM gateway",
    "how-i-host-this-blog": "git push · act_runner · nginx",
    "how-i-made-my-own-songs-with-suno-ai": "7 songs · lyrics + prompts",
    "how-i-vetted-20-vps-providers-with-parallel-subagents": "20 providers · 3 hours · subagents",
    "how-to-verify-a-hosting-provider-before-you-buy": "rdap.org domain age · AUP read",
    "i-let-an-agent-manage-my-shopee-vouchers": "mode=propose gate · RM140 voucher unapproved",
    "it-reported-success-nothing-had-changed": "12.5 MB of 403 MB · rename never landed",
    "jpa-version-field-lost-update": "@Version · stale PUT → 409",
    "loop-engineering-without-a-coding-agent": "11 cron jobs · 8 zero-AI loops",
    "migrating-codeigniter-iis-to-openlitespeed": "17,000-line CI4 · env() fatal",
    "my-backup-was-using-someone-elses-api-quota": "1 TB restic seed · shared rclone quota",
    "n8n-v1-to-v2-upgrade-gotchas": "1.x → 2.40.1 · 7 silent breaks",
    "nocodb-sso-is-a-licensed-feature": "OIDC env accepted · first login crashes",
    "one-hostname-public-tracker-sso-dashboard": "1 host · tracker public, dashboard SSO",
    "one-prometheus-for-unraid-synology-and-a-vps": "3 hosts · 1 prometheus · 0 false panels",
    "passbolt-hang-three-failure-modes": "null fingerprint · 3 failure modes",
    "patching-workbench-26-for-mariadb": "26.7.0 TypeError · 3 patches",
    "putting-a-front-door-on-an-app-you-cant-modify": "5879-byte SPA · 3 injected lines",
    "read-only-nocodb-dashboard-for-a-remote-database": "SNAT source IP · 0 rows copied",
    "reading-a-containers-own-api-docs": "4 docker commands · image is the spec",
    "replacing-rdpguard-with-ipban": "RDPGuard 7.8.7 → IPBan 4.1.0 · 12 IPs",
    "running-production-infrastructure-solo": "162 containers · 3 hosts · 78 compose stacks",
    "running-tts-as-a-service-with-token-sidecars": "tokens expire 10 min / 1 h · sidecars",
    "scraping-bot-walled-marketplace-warm-browser-session": "warm CDP session · split waits",
    "self-healing-digital-goods-entitlements": "5 workflows · NocoDB + n8n + AList",
    "self-hosted-speech-to-text-api": "whisper.cpp large-v3 · ~5x typing",
    "self-hosting-mem0-memory-stack": "mem0 + LiteLLM + pgvector · :20015",
    "shipping-an-ai-photo-editor-as-a-wordpress-plugin": "22 versions · fal.ai async queue",
    "smartctl-exit-code-32-skips-the-disks-that-matter": "rc=32 is not failure · skips bad disks",
    "space-reclamation-wasnt-stuck-it-was-waiting": "121 GiB returned · scheduled 09:29",
    "stop-writing-agent-prompts-for-deterministic-work": "29 straight failures · 1 string compare",
    "syncing-a-self-improving-ai-agent-across-machines": "git-backed profile · manual sync",
    "synology-api-401-with-the-correct-password": "401 twice · 2 causes · 3 commands",
    "synology-spreadsheet-api-is-a-container": "1515 APIs · 4 traps",
    "that-dying-ssd-was-just-a-bad-sata-cable": "WRITE FPDMA timeout · 1 SATA cable",
    "the-cause-was-trim-not-the-ssds": "corruption_errs 27 / 31 · queued TRIM",
    "the-nocodb-attachment-that-wouldnt-update": "300 rows · 1 lookahead regex miss",
    "the-upstream-was-deleted-then-came-back-rewritten": "repo 404 · 233 commits rewrite",
    "two-ways-a-javascript-file-stops-working-and-looks-fine": "shadowed name · let below call",
    "unraid-stop-array-hangs-on-swapfile": "8 GB swapfile pins /mnt/cache",
    "upgrading-codeigniter-46-to-47": "4.6 → 4.7 · 2 unlisted fatals",
    "using-chinese-llm-apis-from-malaysia": "GLM-5.3 · DeepSeek V4 · RMB top-up",
    "verifying-a-pdf-report-page-by-page": "19 pages · every deviation < 2 pt",
    "vetting-an-open-source-dependency-before-you-bet-on-it": "6 checks · grep beats the README",
    "when-smart-says-healthy-but-your-raid-is-corrupting-data": "SMART healthy · checksum 0x8941f998",
    "why-500000-lines-of-commit-churn-only-left-230000-in-production": "518,000 added · 235,000 kept · 5 repos",
    "why-chrome-forgets-its-tabs-in-a-container": "RestoreOnStartup=1 · 70-line keeper",
    "why-i-still-bought-a-local-gpu": "stronger frontier · local for retries + batch",
    "why-my-on-chain-nft-art-changed-on-windows": "autocrlf CRLF · base64 differs",
    "why-telegram-bot-notifications-die": "400 on sendPhoto · getMe fine · IPv6-only DNS",
    "why-your-cdp-clicks-silently-fail": "scroll-behavior:smooth · rect expired",
    "why-your-grafana-dashboard-shows-no-data": "41 panels No data · variable filtered itself",
    "why-your-headless-browser-cant-scrape-everything": "Goofish blocks · Carousell serves",
    "your-disk-full-alert-is-lying": "3% free = 500 GB · alert fires wrong way",
}

# No overrides any more. Two slugs used to point at the hand-accepted consultant samples
# (sample_oom_169_00001_.png / sample_prod_169_00001_.png); those frames were the ones that
# carried the HUD readouts the consultant flagged, and both slugs now have proper zero-text
# art of their own, so every entry goes through the renderer's default `<art-dir>/<slug>.png`.
# Keeping the old paths would also hide them from banner-plan.json, which is keyed by slug.
ART_OVERRIDES: dict = {}


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--check", action="store_true")
    args = ap.parse_args()

    posts = {p.stem for p in (ROOT / "src" / "content" / "posts").glob("*.md")}
    missing = posts - set(EVIDENCE)
    extra = set(EVIDENCE) - posts
    print(f"posts {len(posts)} · evidence {len(EVIDENCE)} · missing {sorted(missing)} · extra {sorted(extra)}")
    if missing or extra:
        raise SystemExit("coverage mismatch — fix the map before rendering")
    if args.check:
        dupes = [e for e in EVIDENCE.values() if list(EVIDENCE.values()).count(e) > 1]
        print(f"duplicate evidence lines: {sorted(set(dupes)) or 'none'}")
        print(f"longest line: {max(len(e) for e in EVIDENCE.values())} chars")
        return

    out: dict = {"_about": ABOUT, "_status": f"{len(EVIDENCE)} of {len(posts)} posts have a hand-written evidence line; "
                                              "base art is generated from C:/AI/ideogram4/captions/<slug>.json"}
    for slug in sorted(EVIDENCE):
        entry: dict = {}
        if slug in ART_OVERRIDES:
            entry["art"] = ART_OVERRIDES[slug]
        entry["evidence"] = EVIDENCE[slug]
        out[slug] = entry
    META.write_text(json.dumps(out, ensure_ascii=False, indent=1), encoding="utf-8")
    print(f"wrote {META} ({len(EVIDENCE)} entries)")


if __name__ == "__main__":
    main()