the-custodian/tools/human_review_classifications.py

#!/usr/bin/env python3
"""Apply human-reviewed classification corrections (CUST-WP-0050 follow-up)."""
from __future__ import annotations

import subprocess
import sys
from pathlib import Path

import yaml

REPO_ROOT = Path(__file__).resolve().parent.parent
VALIDATOR = REPO_ROOT / "tools" / "validate_repo_classification.py"
HOME = Path.home()

# Curated human-reviewed classifications for high-blast-radius portfolio anchors.
HUMAN_REVIEWS: dict[str, dict] = {
    "helix-forge": {
        "category": "product",
        "domain": "infotech",
        "secondary_domains": ["agents"],
        "capability_tags": [
            "platform",
            "capability-registry",
            "coordination",
            "knowledge",
            "product-development",
        ],
        "business_stake": ["product", "technology", "execution", "automation", "intelligence"],
        "business_mechanics": ["intention", "coordination", "operation", "adaptation"],
        "notes": "Capability development platform; standard §13.1 — human confirmed.",
    },
    "reuse-surface": {
        "category": "product",
        "domain": "infotech",
        "secondary_domains": ["agents"],
        "capability_tags": ["capability-registry", "discovery", "reuse", "maturity", "evidence"],
        "business_stake": ["technology", "product", "intelligence", "automation"],
        "business_mechanics": ["intention", "control", "adaptation"],
        "notes": "Reuse discovery surface; standard §13.7 — human confirmed.",
    },
    "coordination-engine": {
        "category": "product",
        "domain": "communication",
        "secondary_domains": ["infotech", "agents"],
        "capability_tags": ["coordination", "workflow", "orchestration", "evidence", "platform"],
        "business_stake": ["product", "technology", "operations", "automation"],
        "business_mechanics": ["coordination", "operation", "adaptation"],
        "notes": "Goal-driven coordination framework; human confirmed.",
    },
    "markitect-main": {
        "category": "product",
        "domain": "communication",
        "secondary_domains": ["infotech", "agents"],
        "capability_tags": ["knowledge", "documentation", "product-development", "platform"],
        "business_stake": ["product", "technology", "execution"],
        "business_mechanics": ["intention", "coordination", "operation", "adaptation"],
        "notes": "Markitect successor to archived markitect-project; human confirmed.",
    },
    "citation-evidence": {
        "category": "product",
        "domain": "infotech",
        "secondary_domains": ["communication", "government"],
        "capability_tags": ["citations", "evidence", "knowledge", "traceability", "source-management"],
        "business_stake": ["intelligence", "legal", "product", "technology"],
        "business_mechanics": ["control", "coordination", "adaptation"],
        "notes": "Citation/evidence product; standard §13.5 — human confirmed.",
    },
    "adaptive-pricing": {
        "category": "product",
        "domain": "financials",
        "secondary_domains": ["infotech", "agents"],
        "capability_tags": ["pricing", "monetization", "lifecycle", "decision-support", "product-development"],
        "business_stake": ["finance", "product", "sales", "intelligence", "automation"],
        "business_mechanics": ["intention", "control", "adaptation"],
        "notes": "Adaptive pricing product; standard §13.6 — human confirmed.",
    },
    "identity-canon": {
        "category": "research",
        "domain": "infotech",
        "secondary_domains": ["government"],
        "capability_tags": ["identity", "access-control", "terminology", "canon", "governance"],
        "business_stake": ["technology", "legal", "operations", "intelligence"],
        "business_mechanics": ["intention", "control", "adaptation"],
        "notes": "Identity canon; standard §13.3 — human confirmed.",
    },
    "net-kingdom": {
        "category": "product",
        "domain": "infotech",
        "secondary_domains": [],
        "capability_tags": ["security", "identity", "platform", "operations", "access-control"],
        "business_stake": ["technology", "operations", "legal", "automation"],
        "business_mechanics": ["control", "operation", "adaptation"],
        "notes": "NetKingdom security/identity platform; standard §13.4 — human confirmed.",
    },
    "audit-core": {
        "category": "tooling",
        "domain": "infotech",
        "secondary_domains": [],
        "capability_tags": ["audit", "traceability", "security", "governance", "operations"],
        "business_stake": ["technology", "operations", "legal", "automation"],
        "business_mechanics": ["control", "operation"],
        "notes": "Multi-tenant audit emit capability; human confirmed.",
    },
    "key-cape": {
        "category": "product",
        "domain": "infotech",
        "secondary_domains": ["communication"],
        "capability_tags": ["identity", "access-control", "security", "platform", "operations"],
        "business_stake": ["technology", "operations", "legal", "product"],
        "business_mechanics": ["control", "operation", "adaptation"],
        "notes": "NetKingdom IAM Profile lightweight mode (Authelia/LLDAP/privacyIDEA); human corrected domain from communication→infotech.",
    },
    "flex-auth": {
        "category": "product",
        "domain": "infotech",
        "secondary_domains": ["government"],
        "capability_tags": ["identity", "access-control", "policy", "governance", "audit"],
        "business_stake": ["technology", "legal", "operations", "product"],
        "business_mechanics": ["control", "coordination", "adaptation"],
        "notes": "Policy-as-code authorization registry; human corrected domain from communication→infotech.",
    },
    "ops-hub": {
        "category": "tooling",
        "domain": "infotech",
        "secondary_domains": [],
        "capability_tags": ["operations", "platform", "observability", "coordination", "governance"],
        "business_stake": ["operations", "technology", "automation"],
        "business_mechanics": ["coordination", "operation", "control"],
        "notes": "Inter-Hub operations extension (environments, incidents, runbooks); human corrected category project→tooling.",
    },
    "railiance-platform": {
        "category": "tooling",
        "domain": "financials",
        "secondary_domains": ["infotech"],
        "capability_tags": ["platform", "operations", "configuration", "governance"],
        "business_stake": ["finance", "technology", "operations"],
        "business_mechanics": ["control", "operation", "coordination"],
        "notes": "Railiance platform substrate; human corrected category project→tooling.",
    },
}


def build_block(slug: str, data: dict) -> dict:
    notes = data.pop("notes", None)
    block = {
        "repo_classification": {
            "standard": "Repo Classification Standard",
            "version": "1.0",
            "classified_at": "2026-06-22",
            "classified_by": "human",
            **data,
        }
    }
    if notes:
        block["repo_classification"]["notes"] = notes
    return block


def main() -> int:
    updated: list[str] = []
    for slug, data in HUMAN_REVIEWS.items():
        repo_path = HOME / slug
        target = repo_path / ".repo-classification.yaml"
        if not repo_path.is_dir():
            print(f"skip {slug}: no checkout", file=sys.stderr)
            continue
        payload = build_block(slug, dict(data))
        target.write_text(yaml.dump(payload, sort_keys=False, allow_unicode=True))
        proc = subprocess.run([sys.executable, str(VALIDATOR), str(target)], capture_output=True, text=True)
        if proc.returncode != 0:
            print(proc.stdout, proc.stderr, file=sys.stderr)
            return 1
        subprocess.run(["git", "add", ".repo-classification.yaml"], cwd=repo_path, check=True)
        diff = subprocess.run(["git", "diff", "--cached", "--quiet"], cwd=repo_path)
        if diff.returncode != 0:
            subprocess.run(
                [
                    "git",
                    "commit",
                    "-m",
                    "Human-review .repo-classification.yaml (CUST-WP-0050 follow-up)",
                ],
                cwd=repo_path,
                check=True,
            )
        updated.append(slug)
    print(f"Human-reviewed: {len(updated)}")
    for slug in updated:
        print(f"  ✓ {slug}")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())