llm-wiki/harness/runtime/workflow_connection_check.py

#!/usr/bin/env python3
"""Verify that R2 workflow sources are connected to deterministic gateways."""

from __future__ import annotations

import argparse
import json
from pathlib import Path
import sys
from typing import Any, Iterable


DEFAULT_ROOT = Path(__file__).resolve().parents[2]
RESULT_SCHEMA = "workflow-connection-result/v1"
WRITER_SOURCES = (
    Path("harness/source/agents/bodies/wiki-doc-author.md"),
    Path("harness/source/agents/bodies/wiki-source-summarizer.md"),
)
GLOBAL_REPORT_SOURCE = Path(".agents/plugins/wiki-superpowers/skills/wiki-workflow/SKILL.md")
WRITER_REQUIRED = (
    "harness/runtime/document_commit.py",
    "document-commit/v1",
    "document-commit-result/v1",
    "--dry-run",
    "plan_sha256",
    "--expected-plan-sha256",
    "--apply",
)
WRITER_FORBIDDEN = (
    "자동 rollback 미구현",
    "**C4. Parent hub Cluster 갱신**",
    "**M5. Parent hub Cluster 점검**",
    "### Step 6: Parent hub Cluster 갱신",
)
REPORT_REQUIRED = (
    "proof-request/v1",
    "harness/runtime/proof_runner.py",
    "proof-runner-result/v1",
    "proof-manifest/v1",
    "manifest_sha256",
    "proof_count",
    "pass_count",
    "fail_count",
    "1~3",
    "실패",
)
SEMANTIC_WORKFLOW_SOURCES = (
    Path("harness/source/skills/project-spec.md"),
    Path("harness/source/skills/branch-spec.md"),
    Path("harness/source/skills/sync.md"),
)
SEMANTIC_REQUIRED = (
    "semantic_surface_extractor.py",
    "semantic_candidate_builder.py",
    "wiki-semantic-coherence-auditor",
    "semantic_audit.py",
    "semantic certificate",
)
PARENT_CERTIFICATE_SOURCE = Path("harness/source/skills/branch-from-project.md")
PARENT_CERTIFICATE_REQUIRED = (
    "semantic_certificate.py",
    "--mode hub",
    "--path raw/project-notes/<project>.md",
)


class ConnectionCheckError(RuntimeError):
    pass


def _finding(code: str, path: Path, token: str) -> dict[str, str]:
    return {"code": code, "path": path.as_posix(), "token": token}


def _require_tokens(path: Path, text: str, tokens: Iterable[str]) -> list[dict[str, str]]:
    return [_finding("MISSING_REQUIRED_CONNECTION", path, token) for token in tokens if token not in text]


def _report_sources(root: Path) -> list[Path]:
    body_root = root / "harness/source/agents/bodies"
    sources = [
        path.relative_to(root)
        for path in body_root.glob("*.md")
        if "§7.1" in path.read_text(encoding="utf-8") or "Self-Grep" in path.read_text(encoding="utf-8")
    ]
    sources.append(GLOBAL_REPORT_SOURCE)
    return sorted(set(sources), key=lambda item: item.as_posix())


def check(root: Path) -> dict[str, Any]:
    root = root.resolve(strict=True)
    findings: list[dict[str, str]] = []
    for relative in WRITER_SOURCES:
        path = root / relative
        if not path.is_file():
            findings.append(_finding("MISSING_CONNECTION_SOURCE", relative, ""))
            continue
        text = path.read_text(encoding="utf-8")
        findings.extend(_require_tokens(relative, text, WRITER_REQUIRED))
        findings.extend(
            _finding("FORBIDDEN_DIRECT_WRITE_CONTRACT", relative, token)
            for token in WRITER_FORBIDDEN
            if token in text
        )

    for relative in SEMANTIC_WORKFLOW_SOURCES:
        path = root / relative
        if not path.is_file():
            findings.append(_finding("MISSING_CONNECTION_SOURCE", relative, ""))
            continue
        findings.extend(_require_tokens(relative, path.read_text(encoding="utf-8"), SEMANTIC_REQUIRED))
    parent_path = root / PARENT_CERTIFICATE_SOURCE
    if not parent_path.is_file():
        findings.append(_finding("MISSING_CONNECTION_SOURCE", PARENT_CERTIFICATE_SOURCE, ""))
    else:
        findings.extend(_require_tokens(PARENT_CERTIFICATE_SOURCE, parent_path.read_text(encoding="utf-8"), PARENT_CERTIFICATE_REQUIRED))

    reporters = _report_sources(root)
    for relative in reporters:
        path = root / relative
        if not path.is_file():
            findings.append(_finding("MISSING_CONNECTION_SOURCE", relative, ""))
            continue
        findings.extend(_require_tokens(relative, path.read_text(encoding="utf-8"), REPORT_REQUIRED))

    findings.sort(key=lambda item: (item["path"], item["code"], item["token"]))
    return {
        "schema_version": RESULT_SCHEMA,
        "status": "PASS" if not findings else "FAIL",
        "writer_sources": len(WRITER_SOURCES),
        "semantic_workflow_sources": len(SEMANTIC_WORKFLOW_SOURCES) + 1,
        "report_sources": len(reporters),
        "findings": findings,
    }


def main(argv: list[str] | None = None) -> int:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--root", type=Path, default=DEFAULT_ROOT)
    args = parser.parse_args(argv)
    try:
        result = check(args.root)
        exit_code = 0 if result["status"] == "PASS" else 1
    except (ConnectionCheckError, OSError, UnicodeError, ValueError) as exc:
        result = {
            "schema_version": RESULT_SCHEMA,
            "status": "ERROR",
            "errors": [{"code": "WORKFLOW_CONNECTION_ERROR", "message": str(exc)}],
        }
        exit_code = 2
    json.dump(result, sys.stdout, ensure_ascii=False, indent=2, sort_keys=True)
    sys.stdout.write("\n")
    return exit_code


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