Funk-lab/tools/hermes-auto-improve/auto-improve.py

#!/usr/bin/env python3
"""
hermes-auto-improve — Analyse les docs admin/ avec Hermes.
Génère des rapports d'amélioration dans la feature branch, ré-ingère dans Qdrant.

Usage :
  python3 auto-improve.py [--all] [--subdir ia] [--dry-run]
"""

import argparse
import json
import subprocess
import sys
from datetime import datetime
from pathlib import Path

REPO_DIR   = Path("/srv/data/lab/Funk-lab")
BRANCH     = "feature/hermes-auto-improve"
ADMIN_DIR  = REPO_DIR / "admin"
REPORTS_DIR = REPO_DIR / "tools/hermes-auto-improve/reports"
STATE_FILE  = Path("/var/lib/hermes-auto-improve/state.json")
MAX_FILES   = 6  # fichiers par run (sans --all)

HERMES_CMD = [
    "sudo", "-i", "-u", "hermes", "bash", "-c",
    'HERMES_HOME=/srv/data/hermes hermes --profile funk-ai -z "{prompt}"'
]


def git(args: list, check=False) -> subprocess.CompletedProcess:
    return subprocess.run(
        ["git", "-C", str(REPO_DIR)] + args,
        capture_output=True, text=True, check=check
    )


def ask_hermes(prompt: str) -> str:
    safe = prompt.replace("'", "'\\''").replace('"', '\\"')
    cmd = [
        "sudo", "-i", "-u", "hermes", "bash", "-c",
        f'HERMES_HOME=/srv/data/hermes hermes --profile funk-ai -z "{safe}"'
    ]
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=180)
    return result.stdout.strip()


def analyze_file(fpath: Path) -> dict:
    rel    = str(fpath.relative_to(REPO_DIR))
    content = fpath.read_text(encoding="utf-8")

    prompt = f"""Tu es l'agent d'analyse du homelab Funk. Analyse ce fichier de documentation :

Fichier : {rel}
---
{content[:4000]}
---

Réponds en JSON strict (pas de markdown) :
{{
  "status": "ok" | "à_améliorer",
  "score": 1-10,
  "problèmes": ["liste des problèmes concrets"],
  "améliorations": ["liste des améliorations prioritaires"],
  "contenu_amélioré": "contenu markdown complet si status=à_améliorer, sinon null"
}}

Critères d'évaluation :
- Informations obsolètes ou incorrectes par rapport à l'état actuel du homelab
- Sections manquantes importantes pour un ops
- Commandes ou chemins érronés
- Documentation incomplète pour reproduire une procédure

Si le document est à jour et complet, mettre status=ok et contenu_amélioré=null."""

    raw = ask_hermes(prompt)

    # Extraire le JSON de la réponse Hermes (qui peut contenir du texte autour)
    try:
        start = raw.find("{")
        end   = raw.rfind("}") + 1
        if start >= 0 and end > start:
            return json.loads(raw[start:end])
    except json.JSONDecodeError:
        pass

    return {
        "status": "erreur",
        "score": 0,
        "problèmes": ["Hermes n'a pas retourné de JSON valide"],
        "améliorations": [],
        "contenu_amélioré": None,
        "raw_response": raw[:500]
    }


def load_state() -> dict:
    if STATE_FILE.exists():
        return json.loads(STATE_FILE.read_text())
    return {"processed": [], "last_run": None}


def save_state(state: dict):
    STATE_FILE.parent.mkdir(parents=True, exist_ok=True)
    STATE_FILE.write_text(json.dumps(state, indent=2, ensure_ascii=False))


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--all",     action="store_true", help="Traiter tous les fichiers")
    parser.add_argument("--subdir",  default=None,        help="Sous-dossier admin/ à analyser (ex: ia, k8s)")
    parser.add_argument("--dry-run", action="store_true", help="Analyser sans commit ni push")
    parser.add_argument("--reset",   action="store_true", help="Réinitialiser l'état (retraiter tous les fichiers)")
    args = parser.parse_args()

    # ── Sync branche ────────────────────────────────────────────
    git(["fetch", "origin"])
    checkout = git(["checkout", BRANCH])
    if checkout.returncode != 0:
        git(["checkout", "-b", BRANCH, f"origin/{BRANCH}"])
    git(["pull", "origin", BRANCH])

    # ── Sélection des fichiers ───────────────────────────────────
    scan_root = ADMIN_DIR / args.subdir if args.subdir else ADMIN_DIR
    all_files = sorted(scan_root.rglob("*.md"))

    state = load_state()
    if args.reset:
        state["processed"] = []

    todo = [f for f in all_files if str(f) not in state["processed"]]
    if not todo:
        state["processed"] = []
        todo = all_files

    batch = todo if args.all else todo[:MAX_FILES]

    # ── Analyse ──────────────────────────────────────────────────
    run_ts  = datetime.now().strftime("%Y-%m-%d_%H-%M")
    results = []

    for fpath in batch:
        rel = str(fpath.relative_to(REPO_DIR))
        print(f"  → Analyse : {rel}", flush=True)
        analysis = analyze_file(fpath)
        analysis["file"] = rel
        results.append(analysis)

        # Appliquer les améliorations si Hermes en a proposé
        if analysis.get("status") == "à_améliorer" and analysis.get("contenu_amélioré"):
            if not args.dry_run:
                fpath.write_text(analysis["contenu_amélioré"], encoding="utf-8")
                print(f"    ✓ Améliorations appliquées (score: {analysis.get('score', '?')}/10)", flush=True)
        elif analysis.get("status") == "ok":
            print(f"    ✓ OK (score: {analysis.get('score', '?')}/10)", flush=True)
        else:
            print(f"    ⚠ {analysis.get('status', '?')}", flush=True)

        state["processed"].append(str(fpath))

    save_state(state)

    # ── Rapport ──────────────────────────────────────────────────
    REPORTS_DIR.mkdir(parents=True, exist_ok=True)
    report_file = REPORTS_DIR / f"{run_ts}.json"
    report_file.write_text(
        json.dumps({"run": run_ts, "results": results}, indent=2, ensure_ascii=False)
    )

    improved = [r["file"] for r in results if r.get("status") == "à_améliorer" and r.get("contenu_amélioré")]

    # ── Commit + push ────────────────────────────────────────────
    if not args.dry_run:
        git(["add", str(report_file.relative_to(REPO_DIR))])
        for f in improved:
            git(["add", f])

        if git(["diff", "--cached", "--quiet"]).returncode != 0:
            msg_files = f"\n\nFichiers améliorés :\n" + "\n".join(f"  - {f}" for f in improved) if improved else ""
            git(["commit", "-m",
                 f"docs(auto): analyse Hermes {run_ts}{msg_files}\n\n"
                 f"Co-Authored-By: Hermes <hermes@funk.lab>"])
            git(["push", "origin", BRANCH])
            print(f"\n✓ Commit + push → {BRANCH}", flush=True)

        # ── Ré-ingestion Qdrant ──────────────────────────────────
        if improved:
            print("\n⏳ Ré-ingestion Qdrant...", flush=True)
            ingest = subprocess.run(
                ["/usr/local/bin/rag-ingest"],
                capture_output=True, text=True, timeout=300
            )
            print(f"  {ingest.stdout.strip()[-200:] if ingest.stdout else 'OK'}", flush=True)

    # ── Résumé JSON (lu par n8n) ─────────────────────────────────
    summary = {
        "run":       run_ts,
        "branch":    BRANCH,
        "analyzed":  len(results),
        "improved":  len(improved),
        "ok":        len([r for r in results if r.get("status") == "ok"]),
        "errors":    len([r for r in results if r.get("status") == "erreur"]),
        "files_improved": improved,
        "dry_run":   args.dry_run,
        "details": [
            {
                "file":    r["file"],
                "status":  r.get("status"),
                "score":   r.get("score"),
                "issues":  r.get("problèmes", []),
                "suggestions": r.get("améliorations", [])
            }
            for r in results
        ]
    }

    print("\n" + json.dumps(summary, indent=2, ensure_ascii=False))
    return 0


if __name__ == "__main__":
    sys.exit(main())