feat: mode Validation DIM dans le viewer Flask

Permet aux médecins DIM de valider/corriger les codes CIM-10 extraits
par le pipeline pour construire un gold standard (50 dossiers).

- ValidationManager : gestion annotations JSON dans data/gold_standard/
- Script sélection 50 dossiers (25 CPAM + 25 stratifiés CMD/confiance)
- Routes /validation, /api/cim10/search, /api/validation/save, /validation/metrics
- Formulaire avec autocomplete CIM-10, boutons Correct/Modifier/Supprimer
- Dashboard métriques : precision, recall, F1, hallucination par confiance/source

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

scripts/select_validation_dossiers.py

@@ -0,0 +1,231 @@
+#!/usr/bin/env python3
+"""Sélectionne 50 dossiers pour le gold standard de validation DIM.
+
+- 25 dossiers CPAM (cas complexes, déjà contrôlés)
+- 25 dossiers non-CPAM stratifiés par CMD, confiance DP, nombre de DAS
+
+Crée data/gold_standard/_selection.json et initialise les annotations vides.
+"""
+
+from __future__ import annotations
+
+import json
+import random
+import sys
+from pathlib import Path
+
+# Ajouter le répertoire racine au path
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from src.config import STRUCTURED_DIR, BASE_DIR, DossierMedical
+
+GOLD_DIR = BASE_DIR / "data" / "gold_standard"
+TARGET_TOTAL = 50
+TARGET_CPAM = 25
+
+
+def load_all_dossiers() -> list[dict]:
+    """Charge tous les dossiers fusionnés depuis output/structured/."""
+    dossiers = []
+    for subdir in sorted(STRUCTURED_DIR.iterdir()):
+        if not subdir.is_dir():
+            continue
+        # Chercher le fichier fusionné
+        fusionne = None
+        for f in subdir.glob("*fusionne*.json"):
+            fusionne = f
+            break
+        if not fusionne:
+            # Prendre le premier JSON du dossier
+            jsons = sorted(subdir.glob("*.json"))
+            if jsons:
+                fusionne = jsons[0]
+        if not fusionne:
+            continue
+
+        try:
+            data = json.loads(fusionne.read_text(encoding="utf-8"))
+            dossier = DossierMedical.model_validate(data)
+            rel_path = str(fusionne.relative_to(STRUCTURED_DIR))
+            group_name = subdir.name
+            dossiers.append({
+                "dossier_id": f"{group_name}/{fusionne.stem}",
+                "group_name": group_name,
+                "path_rel": rel_path,
+                "dossier": dossier,
+            })
+        except Exception as e:
+            print(f"  Erreur chargement {fusionne.name}: {e}")
+    return dossiers
+
+
+def select_dossiers(all_dossiers: list[dict]) -> list[dict]:
+    """Sélectionne les 50 dossiers selon la stratégie définie."""
+    # Séparer CPAM / non-CPAM
+    cpam = [d for d in all_dossiers if d["dossier"].controles_cpam]
+    non_cpam = [d for d in all_dossiers if not d["dossier"].controles_cpam]
+
+    print(f"Dossiers CPAM disponibles : {len(cpam)}")
+    print(f"Dossiers non-CPAM disponibles : {len(non_cpam)}")
+
+    # Prendre tous les CPAM (ou max TARGET_CPAM)
+    selected_cpam = cpam[:TARGET_CPAM]
+    remaining_target = TARGET_TOTAL - len(selected_cpam)
+
+    # Stratifier les non-CPAM
+    selected_non_cpam = stratified_sample(non_cpam, remaining_target)
+
+    selected = selected_cpam + selected_non_cpam
+    print(f"\nSélection finale : {len(selected)} dossiers")
+    print(f"  - CPAM : {len(selected_cpam)}")
+    print(f"  - Non-CPAM : {len(selected_non_cpam)}")
+
+    return selected
+
+
+def stratified_sample(dossiers: list[dict], n: int) -> list[dict]:
+    """Échantillonnage stratifié par CMD, confiance DP et nombre de DAS."""
+    if len(dossiers) <= n:
+        return dossiers
+
+    # Grouper par CMD
+    by_cmd: dict[str, list[dict]] = {}
+    for d in dossiers:
+        ghm = d["dossier"].ghm_estimation
+        cmd = ghm.cmd if ghm else "inconnu"
+        by_cmd.setdefault(cmd or "inconnu", []).append(d)
+
+    selected = []
+    seen_ids = set()
+
+    # Phase 1 : 1 dossier par CMD (diversité maximale)
+    cmds = sorted(by_cmd.keys())
+    random.seed(42)  # Reproductible
+    for cmd in cmds:
+        if len(selected) >= n:
+            break
+        candidates = by_cmd[cmd]
+        # Préférer un mix de confiances
+        random.shuffle(candidates)
+        d = candidates[0]
+        selected.append(d)
+        seen_ids.add(d["dossier_id"])
+
+    # Phase 2 : compléter avec diversité confiance DP
+    if len(selected) < n:
+        remaining = [d for d in dossiers if d["dossier_id"] not in seen_ids]
+        # Trier par confiance DP (low > medium > high pour surreprésenter les cas difficiles)
+        conf_order = {"low": 0, "medium": 1, "high": 2, None: 3}
+        remaining.sort(key=lambda d: (
+            conf_order.get(
+                d["dossier"].diagnostic_principal.cim10_confidence
+                if d["dossier"].diagnostic_principal else None,
+                3
+            ),
+            -len(d["dossier"].diagnostics_associes),  # beaucoup de DAS d'abord
+        ))
+        for d in remaining:
+            if len(selected) >= n:
+                break
+            selected.append(d)
+
+    return selected[:n]
+
+
+def create_empty_annotation(dossier_id: str, dossier: DossierMedical) -> dict:
+    """Crée une annotation vide pour un dossier."""
+    dp = dossier.diagnostic_principal
+    das_list = []
+    for i, das in enumerate(dossier.diagnostics_associes):
+        das_list.append({
+            "index": i,
+            "texte_original": das.texte,
+            "code_pipeline": das.cim10_suggestion or "",
+            "confidence": das.cim10_confidence or "",
+            "source": das.source or "",
+            "statut": "correct",
+            "code_corrige": None,
+            "commentaire": "",
+        })
+
+    return {
+        "dossier_id": dossier_id,
+        "validateur": "",
+        "date_validation": "",
+        "statut": "non_commence",
+        "dp": {
+            "texte_original": dp.texte if dp else "",
+            "code_pipeline": dp.cim10_suggestion if dp else "",
+            "confidence": dp.cim10_confidence if dp else "",
+            "statut": "correct",
+            "code_corrige": None,
+            "commentaire": "",
+        },
+        "das": das_list,
+        "das_ajoutes": [],
+        "commentaire_general": "",
+    }
+
+
+def main():
+    print("=== Sélection des dossiers pour validation DIM ===\n")
+
+    all_dossiers = load_all_dossiers()
+    print(f"Total dossiers chargés : {len(all_dossiers)}\n")
+
+    if not all_dossiers:
+        print("Aucun dossier trouvé dans output/structured/")
+        sys.exit(1)
+
+    selected = select_dossiers(all_dossiers)
+
+    # Créer le répertoire gold standard
+    GOLD_DIR.mkdir(parents=True, exist_ok=True)
+
+    # Sauvegarder la sélection
+    selection = {
+        "date_selection": __import__("datetime").datetime.now().isoformat(timespec="seconds"),
+        "total": len(selected),
+        "cpam": sum(1 for d in selected if d["dossier"].controles_cpam),
+        "non_cpam": sum(1 for d in selected if not d["dossier"].controles_cpam),
+        "dossiers": [d["dossier_id"] for d in selected],
+    }
+    selection_path = GOLD_DIR / "_selection.json"
+    selection_path.write_text(
+        json.dumps(selection, ensure_ascii=False, indent=2),
+        encoding="utf-8",
+    )
+    print(f"\nSélection sauvegardée : {selection_path}")
+
+    # Initialiser les annotations vides
+    created = 0
+    for d in selected:
+        dossier_id = d["dossier_id"]
+        safe_name = dossier_id.replace("/", "__") + ".json"
+        annot_path = GOLD_DIR / safe_name
+        if not annot_path.exists():
+            annotation = create_empty_annotation(dossier_id, d["dossier"])
+            annot_path.write_text(
+                json.dumps(annotation, ensure_ascii=False, indent=2),
+                encoding="utf-8",
+            )
+            created += 1
+
+    print(f"Annotations vides créées : {created}")
+    print(f"Annotations existantes préservées : {len(selected) - created}")
+
+    # Résumé
+    print(f"\n--- Résumé ---")
+    for i, d in enumerate(selected, 1):
+        dos = d["dossier"]
+        dp_code = dos.diagnostic_principal.cim10_suggestion if dos.diagnostic_principal else "?"
+        dp_conf = (dos.diagnostic_principal.cim10_confidence or "?") if dos.diagnostic_principal else "?"
+        n_das = len(dos.diagnostics_associes)
+        cpam_flag = " [CPAM]" if dos.controles_cpam else ""
+        ghm = dos.ghm_estimation
+        cmd = ghm.cmd if ghm else "?"
+        print(f"  {i:2d}. {d['group_name']:<20s} DP={dp_code:<6s} conf={dp_conf:<7s} DAS={n_das:2d} CMD={cmd}{cpam_flag}")
+
+
+if __name__ == "__main__":
+    main()

src/viewer/app.py

@@ -22,6 +22,7 @@ from ..config import (
 )
 from .. import config as cfg
 from .referentiels import ReferentielManager
+from .validation import ValidationManager
 
 logger = logging.getLogger(__name__)
 
@@ -539,4 +540,158 @@ def create_app() -> Flask:
             logger.exception("Erreur lors du rebuild de l'index")
             return jsonify({"error": str(e)}), 500
 
+    # ------------------------------------------------------------------
+    # Routes validation DIM
+    # ------------------------------------------------------------------
+
+    val_manager = ValidationManager()
+
+    @app.route("/validation")
+    def validation_list():
+        groups = scan_dossiers()
+        selection = val_manager.load_selection()
+        annotations = {a["dossier_id"]: a for a in val_manager.list_annotations()}
+
+        # Construire la liste enrichie
+        items = []
+        for dossier_id in selection:
+            annot = annotations.get(dossier_id, {})
+            # Trouver les données pipeline
+            parts = dossier_id.split("/")
+            group_name = parts[0] if parts else ""
+            group_items = groups.get(group_name, [])
+            pipeline = None
+            for gi in group_items:
+                if "fusionne" in gi["name"]:
+                    pipeline = gi
+                    break
+            if not pipeline and group_items:
+                pipeline = group_items[0]
+
+            d = pipeline["dossier"] if pipeline else None
+            items.append({
+                "dossier_id": dossier_id,
+                "group_name": group_name,
+                "dp_code": d.diagnostic_principal.cim10_suggestion if d and d.diagnostic_principal else "",
+                "dp_texte": d.diagnostic_principal.texte if d and d.diagnostic_principal else "",
+                "dp_confidence": d.diagnostic_principal.cim10_confidence if d and d.diagnostic_principal else "",
+                "nb_das": len(d.diagnostics_associes) if d else 0,
+                "has_cpam": bool(d and d.controles_cpam),
+                "statut": annot.get("statut", "non_commence"),
+                "validateur": annot.get("validateur", ""),
+                "date_validation": annot.get("date_validation", ""),
+            })
+
+        total = len(items)
+        valides = sum(1 for i in items if i["statut"] == "valide")
+        en_cours = sum(1 for i in items if i["statut"] == "en_cours")
+
+        return render_template(
+            "validation_list.html",
+            items=items,
+            total=total,
+            valides=valides,
+            en_cours=en_cours,
+            groups=groups,
+        )
+
+    @app.route("/validation/<path:dossier_id>")
+    def validation_detail(dossier_id: str):
+        groups = scan_dossiers()
+        # Charger l'annotation
+        annotation = val_manager.load_annotation(dossier_id)
+        if not annotation:
+            abort(404)
+
+        # Charger les données pipeline
+        parts = dossier_id.split("/")
+        group_name = parts[0] if parts else ""
+        group_items = groups.get(group_name, [])
+        pipeline = None
+        for gi in group_items:
+            if "fusionne" in gi["name"]:
+                pipeline = gi
+                break
+        if not pipeline and group_items:
+            pipeline = group_items[0]
+
+        dossier = pipeline["dossier"] if pipeline else None
+
+        # Navigation : dossier précédent / suivant
+        selection = val_manager.load_selection()
+        current_idx = selection.index(dossier_id) if dossier_id in selection else -1
+        prev_id = selection[current_idx - 1] if current_idx > 0 else None
+        next_id = selection[current_idx + 1] if current_idx < len(selection) - 1 else None
+
+        return render_template(
+            "validation_detail.html",
+            annotation=annotation,
+            dossier=dossier,
+            dossier_id=dossier_id,
+            group_name=group_name,
+            prev_id=prev_id,
+            next_id=next_id,
+            groups=groups,
+        )
+
+    @app.route("/api/validation/save", methods=["POST"])
+    def api_validation_save():
+        data = request.get_json(silent=True)
+        if not data or "dossier_id" not in data:
+            return jsonify({"error": "dossier_id requis"}), 400
+        dossier_id = data["dossier_id"]
+        # Vérifier que le dossier fait partie de la sélection
+        selection = val_manager.load_selection()
+        if selection and dossier_id not in selection:
+            return jsonify({"error": "Dossier non sélectionné pour validation"}), 403
+        try:
+            val_manager.save_annotation(dossier_id, data)
+            return jsonify({"ok": True})
+        except Exception as e:
+            logger.exception("Erreur sauvegarde annotation %s", dossier_id)
+            return jsonify({"error": str(e)}), 500
+
+    @app.route("/api/cim10/search")
+    def api_cim10_search():
+        from ..medical.cim10_dict import load_dict, normalize_text
+        q = request.args.get("q", "").strip()
+        if len(q) < 2:
+            return jsonify({"results": []})
+
+        cim10 = load_dict()
+        q_norm = normalize_text(q)
+        q_upper = q.upper().strip()
+
+        results = []
+        # Recherche par code exact d'abord
+        for code, label in cim10.items():
+            if code.upper().startswith(q_upper):
+                results.append({"code": code, "label": label})
+                if len(results) >= 20:
+                    break
+
+        # Puis recherche par texte normalisé
+        if len(results) < 20:
+            for code, label in cim10.items():
+                if any(r["code"] == code for r in results):
+                    continue
+                if q_norm in normalize_text(label):
+                    results.append({"code": code, "label": label})
+                    if len(results) >= 20:
+                        break
+
+        return jsonify({"results": results})
+
+    @app.route("/validation/metrics")
+    def validation_metrics():
+        groups = scan_dossiers()
+        metrics = val_manager.compute_metrics(groups)
+        selection = val_manager.load_selection()
+        return render_template(
+            "validation_metrics.html",
+            metrics=metrics,
+            total_selection=len(selection),
+            groups=groups,
+        )
+
     return app

src/viewer/templates/base.html

@@ -262,6 +262,10 @@
        onmouseover="this.style.color='#f8fafc'" onmouseout="this.style.color='#cbd5e1'">
       Référentiels RAG
     </a>
+    <a href="/validation" style="display:block;color:#fbbf24;text-decoration:none;font-size:0.8rem;font-weight:600;padding:0.35rem 0;transition:color 0.15s;"
+       onmouseover="this.style.color='#fde68a'" onmouseout="this.style.color='#fbbf24'">
+      Validation DIM
+    </a>
   </div>
   <div class="sidebar-admin">
     <label for="model-select">Modèle Ollama</label>

src/viewer/templates/validation_detail.html

@@ -0,0 +1,404 @@
+{% extends "base.html" %}
+{% block title %}Validation — {{ group_name }}{% endblock %}
+
+{% block sidebar %}
+{% for gn, items in groups.items() %}
+  <div class="group-title">{{ gn | format_dossier_name }}</div>
+  {% for item in items %}
+    {% if 'fusionne' in item.name %}
+      <a href="/dossier/{{ item.path_rel }}" class="sidebar-fusionne">&#9733; Fusionné</a>
+    {% else %}
+      <a href="/dossier/{{ item.path_rel }}">{{ item.name | format_doc_name }}</a>
+    {% endif %}
+  {% endfor %}
+{% endfor %}
+{% endblock %}
+
+{% block content %}
+<style>
+  .seg-btn { display:inline-block;padding:4px 12px;border:1px solid #cbd5e1;font-size:0.8rem;font-weight:600;cursor:pointer;background:#fff;color:#475569;transition:all 0.15s; }
+  .seg-btn:first-child { border-radius:6px 0 0 6px; }
+  .seg-btn:last-child { border-radius:0 6px 6px 0; }
+  .seg-btn:not(:first-child) { border-left:none; }
+  .seg-btn.active-correct { background:#dcfce7;color:#16a34a;border-color:#16a34a; }
+  .seg-btn.active-modifie { background:#fef9c3;color:#ca8a04;border-color:#ca8a04; }
+  .seg-btn.active-supprime { background:#fee2e2;color:#dc2626;border-color:#dc2626; }
+  .code-input { padding:4px 8px;border:1px solid #cbd5e1;border-radius:6px;font-size:0.85rem;font-family:monospace;width:120px; }
+  .comment-input { padding:4px 8px;border:1px solid #e2e8f0;border-radius:6px;font-size:0.8rem;width:100%;max-width:300px; }
+  .autocomplete-wrapper { position:relative;display:inline-block; }
+  .autocomplete-dropdown { position:absolute;top:100%;left:0;z-index:100;background:#fff;border:1px solid #cbd5e1;border-radius:6px;box-shadow:0 4px 12px rgba(0,0,0,0.1);max-height:250px;overflow-y:auto;width:400px;display:none; }
+  .autocomplete-dropdown .ac-item { padding:6px 10px;cursor:pointer;font-size:0.8rem;border-bottom:1px solid #f1f5f9; }
+  .autocomplete-dropdown .ac-item:hover { background:#f1f5f9; }
+  .autocomplete-dropdown .ac-code { font-family:monospace;font-weight:700;color:#1e293b;margin-right:8px; }
+  .autocomplete-dropdown .ac-label { color:#64748b; }
+  .save-bar { position:sticky;bottom:0;background:#fff;border-top:2px solid #e2e8f0;padding:1rem;display:flex;align-items:center;gap:1rem;z-index:50; }
+  .btn-save { padding:8px 20px;border-radius:8px;border:none;font-size:0.85rem;font-weight:600;cursor:pointer;transition:all 0.15s; }
+  .btn-brouillon { background:#f1f5f9;color:#475569; }
+  .btn-brouillon:hover { background:#e2e8f0; }
+  .btn-valider { background:#16a34a;color:#fff; }
+  .btn-valider:hover { background:#15803d; }
+  .nav-link { font-size:0.85rem;color:#3b82f6;text-decoration:none;font-weight:600; }
+  .nav-link:hover { text-decoration:underline; }
+  .das-row-added { background:#f0fdf4; }
+</style>
+
+<!-- Navigation -->
+<div style="display:flex;align-items:center;gap:1rem;margin-bottom:1rem;">
+  <a href="/validation" class="back">Retour à la liste</a>
+  <span style="color:#cbd5e1;">|</span>
+  {% if prev_id %}
+  <a href="/validation/{{ prev_id }}" class="nav-link">Précédent</a>
+  {% endif %}
+  {% if next_id %}
+  <a href="/validation/{{ next_id }}" class="nav-link">Suivant</a>
+  {% endif %}
+  <span style="flex:1;"></span>
+  <a href="/dossier/{{ group_name }}/{{ group_name }}_fusionne_cim10.json" class="nav-link" target="_blank">Voir le dossier complet</a>
+</div>
+
+<h2>Validation : {{ group_name }}</h2>
+
+{% if dossier %}
+<!-- Infos séjour (lecture seule) -->
+<div class="card" style="margin-bottom:1rem;">
+  <h3>Séjour</h3>
+  <div class="info-grid">
+    {% if dossier.sejour.sexe %}<div class="info-item"><label>Sexe</label><span>{{ dossier.sejour.sexe }}</span></div>{% endif %}
+    {% if dossier.sejour.age is not none %}<div class="info-item"><label>Âge</label><span>{{ dossier.sejour.age }} ans</span></div>{% endif %}
+    {% if dossier.sejour.date_entree %}<div class="info-item"><label>Entrée</label><span>{{ dossier.sejour.date_entree }}</span></div>{% endif %}
+    {% if dossier.sejour.date_sortie %}<div class="info-item"><label>Sortie</label><span>{{ dossier.sejour.date_sortie }}</span></div>{% endif %}
+    {% if dossier.sejour.duree_sejour is not none %}<div class="info-item"><label>Durée</label><span>{{ dossier.sejour.duree_sejour }}j</span></div>{% endif %}
+  </div>
+</div>
+
+<!-- DP -->
+<div class="card" style="margin-bottom:1rem;">
+  <h3>Diagnostic Principal</h3>
+  {% set dp = annotation.dp %}
+  <div style="margin-bottom:0.75rem;">
+    <span style="font-size:0.9rem;">{{ dp.texte_original }}</span>
+  </div>
+  <div style="display:flex;align-items:center;gap:1rem;flex-wrap:wrap;">
+    <span style="font-family:monospace;font-size:1rem;font-weight:700;background:#dbeafe;color:#1d4ed8;padding:2px 10px;border-radius:6px;">{{ dp.code_pipeline }}</span>
+    {{ dp.confidence | confidence_badge }}
+
+    <!-- Boutons segmentés -->
+    <div class="seg-group" data-target="dp">
+      <span class="seg-btn active-correct" data-value="correct" onclick="setStatut(this)">Correct</span>
+      <span class="seg-btn" data-value="modifie" onclick="setStatut(this)">Modifier</span>
+      <span class="seg-btn" data-value="supprime" onclick="setStatut(this)">Supprimer</span>
+    </div>
+
+    <!-- Champ code alternatif -->
+    <div class="autocomplete-wrapper dp-code-field" style="display:none;">
+      <input type="text" class="code-input" placeholder="Code CIM-10" data-ac="dp"
+             value="{{ dp.code_corrige or '' }}" autocomplete="off">
+      <div class="autocomplete-dropdown"></div>
+    </div>
+
+    <input type="text" class="comment-input dp-comment" placeholder="Commentaire (optionnel)" value="{{ dp.commentaire or '' }}">
+  </div>
+</div>
+
+<!-- DAS -->
+<div class="card" style="margin-bottom:1rem;">
+  <h3>Diagnostics Associés ({{ annotation.das|length }})</h3>
+  <table id="das-table">
+    <thead>
+      <tr>
+        <th style="width:30px;">#</th>
+        <th>Texte</th>
+        <th>Code pipeline</th>
+        <th>Conf.</th>
+        <th>Source</th>
+        <th>Validation</th>
+        <th>Code corrigé</th>
+        <th>Commentaire</th>
+      </tr>
+    </thead>
+    <tbody>
+      {% for das in annotation.das %}
+      <tr class="das-row" data-index="{{ das.index }}">
+        <td style="color:#94a3b8;font-size:0.8rem;">{{ loop.index }}</td>
+        <td style="font-size:0.85rem;max-width:250px;">{{ das.texte_original }}</td>
+        <td><span style="font-family:monospace;font-weight:600;">{{ das.code_pipeline }}</span></td>
+        <td>{{ das.confidence | confidence_badge }}</td>
+        <td>
+          {% if das.source %}
+          <span style="font-size:0.7rem;padding:2px 6px;border-radius:4px;background:#f1f5f9;color:#475569;">{{ das.source }}</span>
+          {% endif %}
+        </td>
+        <td>
+          <div class="seg-group" data-target="das-{{ das.index }}">
+            <span class="seg-btn {% if das.statut == 'correct' %}active-correct{% endif %}" data-value="correct" onclick="setStatut(this)">OK</span>
+            <span class="seg-btn {% if das.statut == 'modifie' %}active-modifie{% endif %}" data-value="modifie" onclick="setStatut(this)">Mod</span>
+            <span class="seg-btn {% if das.statut == 'supprime' %}active-supprime{% endif %}" data-value="supprime" onclick="setStatut(this)">Sup</span>
+          </div>
+        </td>
+        <td>
+          <div class="autocomplete-wrapper das-code-field-{{ das.index }}" style="{% if das.statut != 'modifie' %}display:none;{% endif %}">
+            <input type="text" class="code-input" placeholder="CIM-10" data-ac="das-{{ das.index }}"
+                   value="{{ das.code_corrige or '' }}" autocomplete="off">
+            <div class="autocomplete-dropdown"></div>
+          </div>
+        </td>
+        <td>
+          <input type="text" class="comment-input das-comment" data-index="{{ das.index }}" placeholder="" value="{{ das.commentaire or '' }}">
+        </td>
+      </tr>
+      {% endfor %}
+    </tbody>
+  </table>
+
+  <!-- DAS ajoutés -->
+  <div id="das-ajoutes" style="margin-top:1rem;">
+    <h3 style="font-size:0.85rem;color:#16a34a;">DAS manquants (ajoutés par le DIM)</h3>
+    <div id="das-ajoutes-list">
+      {% for aj in annotation.das_ajoutes %}
+      <div class="das-added-row das-row-added" style="display:flex;align-items:center;gap:0.5rem;padding:0.5rem 0;border-bottom:1px solid #e2e8f0;" data-aj-index="{{ loop.index0 }}">
+        <input type="text" class="comment-input aj-texte" placeholder="Texte du diagnostic" value="{{ aj.texte or '' }}" style="flex:1;max-width:300px;">
+        <div class="autocomplete-wrapper">
+          <input type="text" class="code-input aj-code" placeholder="CIM-10" value="{{ aj.code or '' }}" autocomplete="off" data-ac="aj-{{ loop.index0 }}">
+          <div class="autocomplete-dropdown"></div>
+        </div>
+        <input type="text" class="comment-input aj-comment" placeholder="Commentaire" value="{{ aj.commentaire or '' }}" style="max-width:200px;">
+        <button onclick="removeAjoute(this)" style="background:none;border:none;color:#dc2626;cursor:pointer;font-size:1.1rem;padding:4px 8px;">&times;</button>
+      </div>
+      {% endfor %}
+    </div>
+    <button id="btn-add-das" onclick="addDasManquant()" style="margin-top:0.5rem;padding:6px 14px;border-radius:6px;border:1px dashed #16a34a;background:#f0fdf4;color:#16a34a;font-size:0.8rem;font-weight:600;cursor:pointer;">
+      + Ajouter un DAS manquant
+    </button>
+  </div>
+</div>
+
+<!-- Commentaire général -->
+<div class="card" style="margin-bottom:5rem;">
+  <h3>Commentaire général</h3>
+  <textarea id="commentaire-general" rows="3"
+            style="width:100%;padding:8px;border:1px solid #cbd5e1;border-radius:6px;font-size:0.85rem;resize:vertical;">{{ annotation.commentaire_general or '' }}</textarea>
+</div>
+{% endif %}
+
+<!-- Barre de sauvegarde sticky -->
+<div class="save-bar">
+  <button class="btn-save btn-brouillon" onclick="saveAnnotation('en_cours')">Enregistrer (brouillon)</button>
+  <button class="btn-save btn-valider" onclick="saveAnnotation('valide')">Marquer comme validé</button>
+  <span id="save-status" style="font-size:0.8rem;color:#64748b;"></span>
+  <span style="flex:1;"></span>
+  <span style="font-size:0.8rem;color:#94a3b8;">Dossier : {{ dossier_id }}</span>
+</div>
+
+{% endblock %}
+
+{% block scripts %}
+<script>
+const DOSSIER_ID = {{ dossier_id | tojson }};
+let ajouteCounter = {{ annotation.das_ajoutes|length }};
+
+// --- Boutons segmentés ---
+function setStatut(btn) {
+  const group = btn.parentElement;
+  const target = group.dataset.target;
+  const value = btn.dataset.value;
+
+  // Reset tous les boutons du groupe
+  group.querySelectorAll('.seg-btn').forEach(function(b) {
+    b.className = 'seg-btn';
+  });
+  btn.classList.add('active-' + value);
+
+  // Afficher/cacher le champ code
+  let codeField;
+  if (target === 'dp') {
+    codeField = document.querySelector('.dp-code-field');
+  } else {
+    const idx = target.replace('das-', '');
+    codeField = document.querySelector('.das-code-field-' + idx);
+  }
+  if (codeField) {
+    codeField.style.display = (value === 'modifie') ? '' : 'none';
+  }
+}
+
+// --- Autocomplete CIM-10 ---
+let acDebounceTimer = null;
+
+document.addEventListener('input', function(e) {
+  if (!e.target.matches('[data-ac]') && !e.target.matches('.aj-code')) return;
+
+  const input = e.target;
+  const dropdown = input.parentElement.querySelector('.autocomplete-dropdown');
+  const q = input.value.trim();
+
+  if (q.length < 2) {
+    dropdown.style.display = 'none';
+    return;
+  }
+
+  clearTimeout(acDebounceTimer);
+  acDebounceTimer = setTimeout(function() {
+    fetch('/api/cim10/search?q=' + encodeURIComponent(q))
+      .then(function(r) { return r.json(); })
+      .then(function(data) {
+        if (!data.results || !data.results.length) {
+          dropdown.style.display = 'none';
+          return;
+        }
+        dropdown.innerHTML = '';
+        data.results.forEach(function(item) {
+          const div = document.createElement('div');
+          div.className = 'ac-item';
+          div.innerHTML = '<span class="ac-code">' + item.code + '</span><span class="ac-label">' + item.label.substring(0, 80) + '</span>';
+          div.addEventListener('click', function() {
+            input.value = item.code;
+            dropdown.style.display = 'none';
+          });
+          dropdown.appendChild(div);
+        });
+        dropdown.style.display = 'block';
+      })
+      .catch(function() { dropdown.style.display = 'none'; });
+  }, 300);
+});
+
+// Fermer les dropdowns quand on clique ailleurs
+document.addEventListener('click', function(e) {
+  if (!e.target.matches('[data-ac]') && !e.target.matches('.aj-code') && !e.target.closest('.autocomplete-dropdown')) {
+    document.querySelectorAll('.autocomplete-dropdown').forEach(function(d) { d.style.display = 'none'; });
+  }
+});
+
+// --- Ajouter DAS manquant ---
+function addDasManquant() {
+  const list = document.getElementById('das-ajoutes-list');
+  const idx = ajouteCounter++;
+  const row = document.createElement('div');
+  row.className = 'das-added-row das-row-added';
+  row.style.cssText = 'display:flex;align-items:center;gap:0.5rem;padding:0.5rem 0;border-bottom:1px solid #e2e8f0;';
+  row.dataset.ajIndex = idx;
+  row.innerHTML = '<input type="text" class="comment-input aj-texte" placeholder="Texte du diagnostic" style="flex:1;max-width:300px;">' +
+    '<div class="autocomplete-wrapper">' +
+    '<input type="text" class="code-input aj-code" placeholder="CIM-10" autocomplete="off" data-ac="aj-' + idx + '">' +
+    '<div class="autocomplete-dropdown"></div>' +
+    '</div>' +
+    '<input type="text" class="comment-input aj-comment" placeholder="Commentaire" style="max-width:200px;">' +
+    '<button onclick="removeAjoute(this)" style="background:none;border:none;color:#dc2626;cursor:pointer;font-size:1.1rem;padding:4px 8px;">&times;</button>';
+  list.appendChild(row);
+}
+
+function removeAjoute(btn) {
+  btn.closest('.das-added-row').remove();
+}
+
+// --- Collecte et sauvegarde ---
+function collectAnnotation(statut) {
+  const validateur = document.getElementById('validateur-name');
+  const valName = validateur ? validateur.value : (localStorage.getItem('t2a_validateur') || '');
+
+  // DP
+  const dpGroup = document.querySelector('.seg-group[data-target="dp"]');
+  const dpActive = dpGroup ? dpGroup.querySelector('.seg-btn[class*="active-"]') : null;
+  let dpStatut = 'correct';
+  if (dpActive) {
+    if (dpActive.classList.contains('active-modifie')) dpStatut = 'modifie';
+    else if (dpActive.classList.contains('active-supprime')) dpStatut = 'supprime';
+  }
+  const dpCodeField = document.querySelector('.dp-code-field input');
+  const dpComment = document.querySelector('.dp-comment');
+
+  const dp = {
+    texte_original: {{ (annotation.dp.texte_original or '') | tojson }},
+    code_pipeline: {{ (annotation.dp.code_pipeline or '') | tojson }},
+    confidence: {{ (annotation.dp.confidence or '') | tojson }},
+    statut: dpStatut,
+    code_corrige: (dpStatut === 'modifie' && dpCodeField) ? dpCodeField.value : null,
+    commentaire: dpComment ? dpComment.value : ''
+  };
+
+  // DAS
+  const dasRows = document.querySelectorAll('.das-row');
+  const das = [];
+  dasRows.forEach(function(row) {
+    const idx = parseInt(row.dataset.index);
+    const group = row.querySelector('.seg-group');
+    const active = group ? group.querySelector('.seg-btn[class*="active-"]') : null;
+    let dasStatut = 'correct';
+    if (active) {
+      if (active.classList.contains('active-modifie')) dasStatut = 'modifie';
+      else if (active.classList.contains('active-supprime')) dasStatut = 'supprime';
+    }
+    const codeInput = row.querySelector('.code-input');
+    const commentInput = row.querySelector('.das-comment');
+
+    das.push({
+      index: idx,
+      texte_original: row.querySelector('td:nth-child(2)').textContent.trim(),
+      code_pipeline: row.querySelector('td:nth-child(3)').textContent.trim(),
+      confidence: {{ annotation.das | tojson }}.find(function(d) { return d.index === idx; })?.confidence || '',
+      source: {{ annotation.das | tojson }}.find(function(d) { return d.index === idx; })?.source || '',
+      statut: dasStatut,
+      code_corrige: (dasStatut === 'modifie' && codeInput) ? codeInput.value : null,
+      commentaire: commentInput ? commentInput.value : ''
+    });
+  });
+
+  // DAS ajoutés
+  const ajRows = document.querySelectorAll('.das-added-row');
+  const das_ajoutes = [];
+  ajRows.forEach(function(row) {
+    const texte = row.querySelector('.aj-texte').value.trim();
+    const code = row.querySelector('.aj-code').value.trim();
+    const comment = row.querySelector('.aj-comment').value.trim();
+    if (texte || code) {
+      das_ajoutes.push({ texte: texte, code: code, commentaire: comment });
+    }
+  });
+
+  return {
+    dossier_id: DOSSIER_ID,
+    validateur: valName,
+    statut: statut,
+    dp: dp,
+    das: das,
+    das_ajoutes: das_ajoutes,
+    commentaire_general: document.getElementById('commentaire-general').value
+  };
+}
+
+function saveAnnotation(statut) {
+  const data = collectAnnotation(statut);
+  const statusEl = document.getElementById('save-status');
+  statusEl.textContent = 'Sauvegarde...';
+  statusEl.style.color = '#64748b';
+
+  fetch('/api/validation/save', {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify(data)
+  })
+  .then(function(r) { return r.json(); })
+  .then(function(d) {
+    if (d.ok) {
+      statusEl.textContent = statut === 'valide' ? 'Validé !' : 'Brouillon enregistré';
+      statusEl.style.color = '#16a34a';
+    } else {
+      statusEl.textContent = d.error || 'Erreur';
+      statusEl.style.color = '#dc2626';
+    }
+  })
+  .catch(function() {
+    statusEl.textContent = 'Erreur réseau';
+    statusEl.style.color = '#dc2626';
+  });
+}
+
+// Raccourci clavier : Ctrl+S pour sauvegarder en brouillon
+document.addEventListener('keydown', function(e) {
+  if ((e.ctrlKey || e.metaKey) && e.key === 's') {
+    e.preventDefault();
+    saveAnnotation('en_cours');
+  }
+});
+</script>
+{% endblock %}

src/viewer/templates/validation_list.html

@@ -0,0 +1,179 @@
+{% extends "base.html" %}
+{% block title %}Validation DIM{% endblock %}
+
+{% block sidebar %}
+{% for group_name, items in groups.items() %}
+  <div class="group-title">{{ group_name | format_dossier_name }}</div>
+  {% for item in items %}
+    {% if 'fusionne' in item.name %}
+      <a href="/dossier/{{ item.path_rel }}" class="sidebar-fusionne">&#9733; Fusionné</a>
+    {% else %}
+      <a href="/dossier/{{ item.path_rel }}">{{ item.name | format_doc_name }}</a>
+    {% endif %}
+  {% endfor %}
+{% endfor %}
+{% endblock %}
+
+{% block content %}
+<div style="display:flex;align-items:center;gap:1rem;margin-bottom:1.5rem;">
+  <h2 style="margin:0;">Validation DIM</h2>
+  <a href="/validation/metrics" style="font-size:0.85rem;color:#3b82f6;text-decoration:none;font-weight:600;">Voir les métriques</a>
+</div>
+
+<!-- Barre de progression -->
+<div class="card" style="margin-bottom:1.5rem;">
+  <div style="display:flex;align-items:center;gap:1rem;margin-bottom:0.75rem;">
+    <span style="font-weight:600;font-size:0.9rem;">Progression</span>
+    <span style="font-size:0.85rem;color:#64748b;">{{ valides }} / {{ total }} validés</span>
+    {% if en_cours > 0 %}
+    <span style="font-size:0.85rem;color:#ca8a04;">{{ en_cours }} en cours</span>
+    {% endif %}
+  </div>
+  <div style="background:#e2e8f0;border-radius:9999px;height:12px;overflow:hidden;">
+    {% set pct_valide = (valides / total * 100) if total > 0 else 0 %}
+    {% set pct_encours = (en_cours / total * 100) if total > 0 else 0 %}
+    <div style="display:flex;height:100%;">
+      <div style="width:{{ pct_valide }}%;background:#16a34a;transition:width 0.3s;"></div>
+      <div style="width:{{ pct_encours }}%;background:#eab308;transition:width 0.3s;"></div>
+    </div>
+  </div>
+</div>
+
+<!-- Nom du validateur -->
+<div class="card" style="margin-bottom:1rem;padding:0.75rem 1.25rem;">
+  <div style="display:flex;align-items:center;gap:0.75rem;">
+    <label for="validateur-name" style="font-size:0.8rem;font-weight:600;color:#475569;white-space:nowrap;">Nom du validateur :</label>
+    <input type="text" id="validateur-name" placeholder="Dr. X"
+           style="flex:1;padding:0.35rem 0.6rem;border:1px solid #cbd5e1;border-radius:6px;font-size:0.85rem;max-width:300px;">
+  </div>
+</div>
+
+<!-- Filtres -->
+<div style="display:flex;gap:0.5rem;margin-bottom:1rem;">
+  <button class="filter-btn active" data-filter="all"
+          style="padding:0.35rem 0.75rem;border-radius:6px;border:1px solid #cbd5e1;background:#fff;font-size:0.8rem;font-weight:600;cursor:pointer;">
+    Tous ({{ total }})
+  </button>
+  <button class="filter-btn" data-filter="non_commence"
+          style="padding:0.35rem 0.75rem;border-radius:6px;border:1px solid #cbd5e1;background:#fff;font-size:0.8rem;font-weight:600;cursor:pointer;">
+    Non commencés ({{ total - valides - en_cours }})
+  </button>
+  <button class="filter-btn" data-filter="en_cours"
+          style="padding:0.35rem 0.75rem;border-radius:6px;border:1px solid #cbd5e1;background:#fff;font-size:0.8rem;font-weight:600;cursor:pointer;">
+    En cours ({{ en_cours }})
+  </button>
+  <button class="filter-btn" data-filter="valide"
+          style="padding:0.35rem 0.75rem;border-radius:6px;border:1px solid #cbd5e1;background:#fff;font-size:0.8rem;font-weight:600;cursor:pointer;">
+    Validés ({{ valides }})
+  </button>
+</div>
+
+<!-- Tableau -->
+<div class="card" style="padding:0;">
+<table>
+  <thead>
+    <tr>
+      <th>#</th>
+      <th>Dossier</th>
+      <th>DP</th>
+      <th>Conf. DP</th>
+      <th>DAS</th>
+      <th>CPAM</th>
+      <th>Statut</th>
+      <th>Validateur</th>
+    </tr>
+  </thead>
+  <tbody>
+    {% for item in items %}
+    <tr class="validation-row" data-statut="{{ item.statut }}">
+      <td style="color:#94a3b8;font-size:0.8rem;">{{ loop.index }}</td>
+      <td>
+        <a href="/validation/{{ item.dossier_id }}" style="color:#1e293b;text-decoration:none;font-weight:600;font-size:0.85rem;">
+          {{ item.group_name }}
+        </a>
+      </td>
+      <td>
+        <span style="font-family:monospace;font-size:0.85rem;font-weight:600;">{{ item.dp_code or '—' }}</span>
+        {% if item.dp_texte %}
+        <br><span style="font-size:0.75rem;color:#64748b;">{{ item.dp_texte[:50] }}{% if item.dp_texte|length > 50 %}…{% endif %}</span>
+        {% endif %}
+      </td>
+      <td>{{ item.dp_confidence | confidence_badge }}</td>
+      <td style="text-align:center;font-weight:600;">{{ item.nb_das }}</td>
+      <td style="text-align:center;">
+        {% if item.has_cpam %}
+        <span style="display:inline-block;padding:2px 8px;border-radius:9999px;font-size:0.7rem;font-weight:600;color:#7c3aed;background:#ede9fe;">CPAM</span>
+        {% endif %}
+      </td>
+      <td>
+        {% if item.statut == 'valide' %}
+        <span style="display:inline-block;padding:2px 8px;border-radius:9999px;font-size:0.7rem;font-weight:600;color:#16a34a;background:#dcfce7;">Validé</span>
+        {% elif item.statut == 'en_cours' %}
+        <span style="display:inline-block;padding:2px 8px;border-radius:9999px;font-size:0.7rem;font-weight:600;color:#ca8a04;background:#fef9c3;">En cours</span>
+        {% else %}
+        <span style="display:inline-block;padding:2px 8px;border-radius:9999px;font-size:0.7rem;font-weight:600;color:#6b7280;background:#f3f4f6;">Non commencé</span>
+        {% endif %}
+      </td>
+      <td style="font-size:0.8rem;color:#64748b;">{{ item.validateur }}</td>
+    </tr>
+    {% endfor %}
+  </tbody>
+</table>
+</div>
+
+{% if not items %}
+<div class="card" style="text-align:center;padding:2rem;">
+  <p style="color:#64748b;font-size:0.9rem;">Aucun dossier sélectionné pour validation.</p>
+  <p style="margin-top:0.5rem;font-size:0.85rem;color:#94a3b8;">
+    Lancez <code>python scripts/select_validation_dossiers.py</code> pour sélectionner les dossiers.
+  </p>
+</div>
+{% endif %}
+
+{% endblock %}
+
+{% block scripts %}
+<script>
+(function() {
+  // Persistance nom validateur dans localStorage
+  const input = document.getElementById('validateur-name');
+  if (input) {
+    const saved = localStorage.getItem('t2a_validateur');
+    if (saved) input.value = saved;
+    input.addEventListener('input', function() {
+      localStorage.setItem('t2a_validateur', this.value);
+    });
+  }
+
+  // Filtres
+  document.querySelectorAll('.filter-btn').forEach(function(btn) {
+    btn.addEventListener('click', function() {
+      document.querySelectorAll('.filter-btn').forEach(function(b) {
+        b.classList.remove('active');
+        b.style.background = '#fff';
+        b.style.color = '#1e293b';
+      });
+      this.classList.add('active');
+      this.style.background = '#1e293b';
+      this.style.color = '#fff';
+
+      const filter = this.dataset.filter;
+      document.querySelectorAll('.validation-row').forEach(function(row) {
+        if (filter === 'all' || row.dataset.statut === filter) {
+          row.style.display = '';
+        } else {
+          row.style.display = 'none';
+        }
+      });
+    });
+  });
+
+  // Activer le style du premier bouton
+  const firstBtn = document.querySelector('.filter-btn.active');
+  if (firstBtn) {
+    firstBtn.style.background = '#1e293b';
+    firstBtn.style.color = '#fff';
+  }
+})();
+</script>
+{% endblock %}

src/viewer/templates/validation_metrics.html

@@ -0,0 +1,243 @@
+{% extends "base.html" %}
+{% block title %}Métriques Validation DIM{% endblock %}
+
+{% block sidebar %}
+{% for group_name, items in groups.items() %}
+  <div class="group-title">{{ group_name | format_dossier_name }}</div>
+  {% for item in items %}
+    {% if 'fusionne' in item.name %}
+      <a href="/dossier/{{ item.path_rel }}" class="sidebar-fusionne">&#9733; Fusionné</a>
+    {% else %}
+      <a href="/dossier/{{ item.path_rel }}">{{ item.name | format_doc_name }}</a>
+    {% endif %}
+  {% endfor %}
+{% endfor %}
+{% endblock %}
+
+{% block content %}
+<div style="display:flex;align-items:center;gap:1rem;margin-bottom:1.5rem;">
+  <a href="/validation" class="back">Retour à la liste</a>
+  <h2 style="margin:0;">Métriques de qualité</h2>
+</div>
+
+{% if metrics.total_valides == 0 %}
+<div class="card" style="text-align:center;padding:2rem;">
+  <p style="color:#64748b;font-size:0.9rem;">Aucun dossier validé pour le moment.</p>
+  <p style="margin-top:0.5rem;font-size:0.85rem;color:#94a3b8;">
+    Validez des dossiers depuis la <a href="/validation">liste de validation</a> pour voir les métriques.
+  </p>
+</div>
+{% else %}
+
+<!-- Progression -->
+<div class="card" style="margin-bottom:1.5rem;">
+  <div style="display:flex;align-items:center;gap:1rem;margin-bottom:0.75rem;">
+    <span style="font-weight:600;font-size:0.9rem;">Progression</span>
+    <span style="font-size:0.85rem;color:#64748b;">{{ metrics.total_valides }} / {{ total_selection }} dossiers validés</span>
+  </div>
+  <div style="background:#e2e8f0;border-radius:9999px;height:12px;overflow:hidden;">
+    {% set pct = (metrics.total_valides / total_selection * 100) if total_selection > 0 else 0 %}
+    <div style="width:{{ pct }}%;background:#16a34a;transition:width 0.3s;height:100%;"></div>
+  </div>
+</div>
+
+<!-- Métriques DP + DAS côte à côte -->
+<div style="display:grid;grid-template-columns:1fr 1fr;gap:1rem;margin-bottom:1.5rem;">
+
+  <!-- DP -->
+  <div class="card">
+    <h3>Diagnostic Principal</h3>
+    <div class="info-grid" style="margin-top:0.75rem;">
+      <div class="info-item">
+        <label>Accuracy</label>
+        <span style="font-size:1.3rem;font-weight:700;color:#16a34a;">{{ "%.1f" | format(metrics.dp.accuracy * 100) }}%</span>
+      </div>
+      <div class="info-item">
+        <label>Correct</label>
+        <span>{{ metrics.dp.correct }} / {{ metrics.dp.total }}</span>
+      </div>
+      <div class="info-item">
+        <label>Modifié</label>
+        <span style="color:#ca8a04;">{{ metrics.dp.modifie }}</span>
+      </div>
+      <div class="info-item">
+        <label>Supprimé</label>
+        <span style="color:#dc2626;">{{ metrics.dp.supprime }}</span>
+      </div>
+    </div>
+    <!-- Barre visuelle -->
+    <div style="margin-top:1rem;display:flex;height:20px;border-radius:6px;overflow:hidden;">
+      {% set dp_t = metrics.dp.total or 1 %}
+      <div style="width:{{ metrics.dp.correct / dp_t * 100 }}%;background:#16a34a;" title="Correct"></div>
+      <div style="width:{{ metrics.dp.modifie / dp_t * 100 }}%;background:#eab308;" title="Modifié"></div>
+      <div style="width:{{ metrics.dp.supprime / dp_t * 100 }}%;background:#dc2626;" title="Supprimé"></div>
+    </div>
+    <div style="display:flex;gap:1rem;margin-top:0.35rem;font-size:0.7rem;color:#64748b;">
+      <span><span style="display:inline-block;width:8px;height:8px;border-radius:50%;background:#16a34a;margin-right:3px;"></span>Correct</span>
+      <span><span style="display:inline-block;width:8px;height:8px;border-radius:50%;background:#eab308;margin-right:3px;"></span>Modifié</span>
+      <span><span style="display:inline-block;width:8px;height:8px;border-radius:50%;background:#dc2626;margin-right:3px;"></span>Supprimé</span>
+    </div>
+  </div>
+
+  <!-- DAS -->
+  <div class="card">
+    <h3>Diagnostics Associés</h3>
+    <div class="info-grid" style="margin-top:0.75rem;">
+      <div class="info-item">
+        <label>Precision</label>
+        <span style="font-size:1.3rem;font-weight:700;color:#1d4ed8;">{{ "%.1f" | format(metrics.das.precision * 100) }}%</span>
+      </div>
+      <div class="info-item">
+        <label>Recall</label>
+        <span style="font-size:1.3rem;font-weight:700;color:#7c3aed;">{{ "%.1f" | format(metrics.das.recall * 100) }}%</span>
+      </div>
+      <div class="info-item">
+        <label>F1-score</label>
+        <span style="font-size:1.3rem;font-weight:700;color:#0f172a;">{{ "%.1f" | format(metrics.das.f1 * 100) }}%</span>
+      </div>
+      <div class="info-item">
+        <label>Hallucination</label>
+        <span style="font-size:1.3rem;font-weight:700;color:#dc2626;">{{ "%.1f" | format(metrics.das.hallucination_rate * 100) }}%</span>
+      </div>
+    </div>
+    <div style="margin-top:0.75rem;font-size:0.8rem;color:#64748b;">
+      <div style="display:flex;gap:1.5rem;">
+        <span>Pipeline : {{ metrics.das.total_pipeline }} DAS</span>
+        <span>Référence DIM : {{ metrics.das.reference }}</span>
+        <span style="color:#16a34a;">Correct : {{ metrics.das.correct }}</span>
+        <span style="color:#ca8a04;">Modifié : {{ metrics.das.modifie }}</span>
+        <span style="color:#dc2626;">Supprimé : {{ metrics.das.supprime }}</span>
+        <span style="color:#7c3aed;">Ajouté : {{ metrics.das.ajoutes }}</span>
+      </div>
+    </div>
+    <!-- Taux manqués -->
+    <div style="margin-top:0.5rem;font-size:0.8rem;">
+      <span style="color:#64748b;">Taux DAS manqués : </span>
+      <span style="font-weight:600;color:#7c3aed;">{{ "%.1f" | format(metrics.das.miss_rate * 100) }}%</span>
+      <span style="color:#94a3b8;font-size:0.75rem;"> ({{ metrics.das.ajoutes }} ajoutés / {{ metrics.das.reference }} référence)</span>
+    </div>
+  </div>
+</div>
+
+<!-- Ventilation par confiance -->
+{% if metrics.by_confidence %}
+<div class="card" style="margin-bottom:1rem;">
+  <h3>Par niveau de confiance</h3>
+  <table style="margin-top:0.75rem;">
+    <thead>
+      <tr>
+        <th>Confiance</th>
+        <th>Total DAS</th>
+        <th>Correct</th>
+        <th>Modifié</th>
+        <th>Supprimé</th>
+        <th>Precision</th>
+        <th>Hallucination</th>
+      </tr>
+    </thead>
+    <tbody>
+      {% for conf, bucket in metrics.by_confidence.items() %}
+      <tr>
+        <td>{{ conf | confidence_badge }}</td>
+        <td>{{ bucket.total }}</td>
+        <td style="color:#16a34a;">{{ bucket.correct }}</td>
+        <td style="color:#ca8a04;">{{ bucket.modifie }}</td>
+        <td style="color:#dc2626;">{{ bucket.supprime }}</td>
+        <td style="font-weight:600;">{{ "%.1f" | format(bucket.precision * 100) }}%</td>
+        <td style="font-weight:600;color:#dc2626;">{{ "%.1f" | format(bucket.hallucination * 100) }}%</td>
+      </tr>
+      {% endfor %}
+    </tbody>
+  </table>
+</div>
+{% endif %}
+
+<!-- Ventilation par source -->
+{% if metrics.by_source %}
+<div class="card" style="margin-bottom:1rem;">
+  <h3>Par source d'extraction</h3>
+  <table style="margin-top:0.75rem;">
+    <thead>
+      <tr>
+        <th>Source</th>
+        <th>Total DAS</th>
+        <th>Correct</th>
+        <th>Modifié</th>
+        <th>Supprimé</th>
+        <th>Precision</th>
+        <th>Hallucination</th>
+      </tr>
+    </thead>
+    <tbody>
+      {% for source, bucket in metrics.by_source.items() %}
+      <tr>
+        <td><span style="font-size:0.8rem;padding:2px 8px;border-radius:4px;background:#f1f5f9;font-weight:600;">{{ source }}</span></td>
+        <td>{{ bucket.total }}</td>
+        <td style="color:#16a34a;">{{ bucket.correct }}</td>
+        <td style="color:#ca8a04;">{{ bucket.modifie }}</td>
+        <td style="color:#dc2626;">{{ bucket.supprime }}</td>
+        <td style="font-weight:600;">{{ "%.1f" | format(bucket.precision * 100) }}%</td>
+        <td style="font-weight:600;color:#dc2626;">{{ "%.1f" | format(bucket.hallucination * 100) }}%</td>
+      </tr>
+      {% endfor %}
+    </tbody>
+  </table>
+</div>
+{% endif %}
+
+<!-- Top corrections DAS -->
+{% if metrics.top_corrections %}
+<div class="card" style="margin-bottom:1rem;">
+  <h3>Top corrections DAS (code pipeline &rarr; code DIM)</h3>
+  <table style="margin-top:0.75rem;">
+    <thead>
+      <tr>
+        <th>Code pipeline</th>
+        <th></th>
+        <th>Code corrigé</th>
+        <th>Occurrences</th>
+      </tr>
+    </thead>
+    <tbody>
+      {% for (code_from, code_to), count in metrics.top_corrections %}
+      <tr>
+        <td><span style="font-family:monospace;font-weight:600;color:#dc2626;">{{ code_from }}</span></td>
+        <td style="color:#94a3b8;">&rarr;</td>
+        <td><span style="font-family:monospace;font-weight:600;color:#16a34a;">{{ code_to }}</span></td>
+        <td>{{ count }}</td>
+      </tr>
+      {% endfor %}
+    </tbody>
+  </table>
+</div>
+{% endif %}
+
+<!-- Top corrections DP -->
+{% if metrics.dp_corrections %}
+<div class="card" style="margin-bottom:1rem;">
+  <h3>Top corrections DP (code pipeline &rarr; code DIM)</h3>
+  <table style="margin-top:0.75rem;">
+    <thead>
+      <tr>
+        <th>Code pipeline</th>
+        <th></th>
+        <th>Code corrigé</th>
+        <th>Occurrences</th>
+      </tr>
+    </thead>
+    <tbody>
+      {% for (code_from, code_to), count in metrics.dp_corrections %}
+      <tr>
+        <td><span style="font-family:monospace;font-weight:600;color:#dc2626;">{{ code_from }}</span></td>
+        <td style="color:#94a3b8;">&rarr;</td>
+        <td><span style="font-family:monospace;font-weight:600;color:#16a34a;">{{ code_to }}</span></td>
+        <td>{{ count }}</td>
+      </tr>
+      {% endfor %}
+    </tbody>
+  </table>
+</div>
+{% endif %}
+
+{% endif %}
+{% endblock %}

src/viewer/validation.py

@@ -0,0 +1,272 @@
+"""Gestionnaire de données pour la validation DIM (gold standard)."""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import tempfile
+from datetime import datetime
+from pathlib import Path
+
+from ..config import BASE_DIR
+
+logger = logging.getLogger(__name__)
+
+GOLD_DIR = BASE_DIR / "data" / "gold_standard"
+
+
+class ValidationManager:
+    """Gère les annotations de validation DIM (fichiers JSON par dossier)."""
+
+    def __init__(self, gold_dir: Path | None = None):
+        self.gold_dir = gold_dir or GOLD_DIR
+        self.gold_dir.mkdir(parents=True, exist_ok=True)
+
+    # ------------------------------------------------------------------
+    # Helpers
+    # ------------------------------------------------------------------
+
+    def _annotation_path(self, dossier_id: str) -> Path:
+        """Chemin du fichier annotation pour un dossier donné."""
+        safe_name = dossier_id.replace("/", "__") + ".json"
+        return self.gold_dir / safe_name
+
+    # ------------------------------------------------------------------
+    # CRUD
+    # ------------------------------------------------------------------
+
+    def load_annotation(self, dossier_id: str) -> dict | None:
+        """Charge l'annotation existante pour un dossier."""
+        path = self._annotation_path(dossier_id)
+        if not path.exists():
+            return None
+        try:
+            return json.loads(path.read_text(encoding="utf-8"))
+        except Exception:
+            logger.warning("Impossible de charger l'annotation %s", path)
+            return None
+
+    def save_annotation(self, dossier_id: str, data: dict) -> None:
+        """Sauvegarde atomique (write temp + rename) d'une annotation."""
+        path = self._annotation_path(dossier_id)
+        data["dossier_id"] = dossier_id
+        data.setdefault("date_validation", datetime.now().isoformat(timespec="seconds"))
+
+        fd, tmp_path = tempfile.mkstemp(
+            dir=str(self.gold_dir), suffix=".tmp", prefix=".annot_"
+        )
+        try:
+            with os.fdopen(fd, "w", encoding="utf-8") as f:
+                json.dump(data, f, ensure_ascii=False, indent=2)
+            os.replace(tmp_path, path)
+        except Exception:
+            # Nettoyage en cas d'erreur
+            try:
+                os.unlink(tmp_path)
+            except OSError:
+                pass
+            raise
+
+    def list_annotations(self) -> list[dict]:
+        """Liste toutes les annotations avec métadonnées (statut, validateur, date)."""
+        results = []
+        for path in sorted(self.gold_dir.glob("*.json")):
+            if path.name.startswith("_"):
+                continue
+            try:
+                data = json.loads(path.read_text(encoding="utf-8"))
+                results.append({
+                    "dossier_id": data.get("dossier_id", path.stem.replace("__", "/")),
+                    "statut": data.get("statut", "non_commence"),
+                    "validateur": data.get("validateur", ""),
+                    "date_validation": data.get("date_validation", ""),
+                })
+            except Exception:
+                logger.warning("Annotation illisible : %s", path)
+        return results
+
+    def load_selection(self) -> list[str]:
+        """Charge la liste des dossiers sélectionnés depuis _selection.json."""
+        selection_path = self.gold_dir / "_selection.json"
+        if not selection_path.exists():
+            return []
+        try:
+            data = json.loads(selection_path.read_text(encoding="utf-8"))
+            return data.get("dossiers", [])
+        except Exception:
+            return []
+
+    # ------------------------------------------------------------------
+    # Métriques
+    # ------------------------------------------------------------------
+
+    def compute_metrics(self, groups: dict) -> dict:
+        """Calcule precision, recall, F1 et hallucination rate depuis les annotations.
+
+        Args:
+            groups: résultat de scan_dossiers() pour accéder aux données pipeline.
+
+        Returns:
+            Dictionnaire de métriques globales et ventilées.
+        """
+        annotations = []
+        for path in sorted(self.gold_dir.glob("*.json")):
+            if path.name.startswith("_"):
+                continue
+            try:
+                data = json.loads(path.read_text(encoding="utf-8"))
+                if data.get("statut") == "valide":
+                    annotations.append(data)
+            except Exception:
+                continue
+
+        total = len(annotations)
+        if total == 0:
+            return {"total_valides": 0}
+
+        # --- Métriques DP ---
+        dp_correct = 0
+        dp_modifie = 0
+        dp_supprime = 0
+        dp_corrections: list[tuple[str, str]] = []  # (pipeline, corrige)
+
+        # --- Métriques DAS ---
+        das_correct = 0
+        das_modifie = 0
+        das_supprime = 0
+        das_ajoutes = 0
+        das_total_pipeline = 0
+        das_corrections: list[tuple[str, str]] = []
+
+        # --- Ventilation par confiance ---
+        by_confidence: dict[str, dict] = {}
+        # --- Ventilation par source ---
+        by_source: dict[str, dict] = {}
+
+        for annot in annotations:
+            dossier_id = annot.get("dossier_id", "")
+
+            # Trouver les données pipeline correspondantes
+            pipeline_data = self._find_pipeline_data(dossier_id, groups)
+
+            # DP
+            dp = annot.get("dp", {})
+            dp_statut = dp.get("statut", "correct")
+            if dp_statut == "correct":
+                dp_correct += 1
+            elif dp_statut == "modifie":
+                dp_modifie += 1
+                code_orig = dp.get("code_pipeline", "")
+                code_corr = dp.get("code_corrige", "")
+                if code_orig and code_corr:
+                    dp_corrections.append((code_orig, code_corr))
+            elif dp_statut == "supprime":
+                dp_supprime += 1
+
+            # DAS
+            das_list = annot.get("das", [])
+            das_aj = annot.get("das_ajoutes", [])
+            das_total_pipeline += len(das_list)
+            das_ajoutes += len(das_aj)
+
+            for das in das_list:
+                das_statut = das.get("statut", "correct")
+                conf = das.get("confidence", "")
+                source = das.get("source", "")
+
+                if das_statut == "correct":
+                    das_correct += 1
+                elif das_statut == "modifie":
+                    das_modifie += 1
+                    code_orig = das.get("code_pipeline", "")
+                    code_corr = das.get("code_corrige", "")
+                    if code_orig and code_corr:
+                        das_corrections.append((code_orig, code_corr))
+                elif das_statut == "supprime":
+                    das_supprime += 1
+
+                # Ventilation par confiance
+                if conf:
+                    bucket = by_confidence.setdefault(conf, {
+                        "correct": 0, "modifie": 0, "supprime": 0, "total": 0
+                    })
+                    bucket["total"] += 1
+                    bucket[das_statut] = bucket.get(das_statut, 0) + 1
+
+                # Ventilation par source
+                if source:
+                    bucket = by_source.setdefault(source, {
+                        "correct": 0, "modifie": 0, "supprime": 0, "total": 0
+                    })
+                    bucket["total"] += 1
+                    bucket[das_statut] = bucket.get(das_statut, 0) + 1
+
+        # --- Calculs ---
+        # DAS reference = correct + modifié + ajoutés (les vrais DAS selon le DIM)
+        das_reference = das_correct + das_modifie + das_ajoutes
+        # DAS pipeline valides = correct + modifié (non supprimés)
+        das_pipeline_valides = das_correct + das_modifie
+
+        precision = das_pipeline_valides / das_total_pipeline if das_total_pipeline > 0 else 0
+        recall = das_pipeline_valides / das_reference if das_reference > 0 else 0
+        f1 = 2 * precision * recall / (precision + recall) if (precision + recall) > 0 else 0
+        hallucination_rate = das_supprime / das_total_pipeline if das_total_pipeline > 0 else 0
+        miss_rate = das_ajoutes / das_reference if das_reference > 0 else 0
+
+        # Top corrections DAS
+        from collections import Counter
+        correction_counter = Counter(das_corrections)
+        top_corrections = correction_counter.most_common(10)
+
+        # Ventilation par confiance : calculer precision par bucket
+        for bucket in by_confidence.values():
+            t = bucket["total"]
+            valides = bucket.get("correct", 0) + bucket.get("modifie", 0)
+            bucket["precision"] = valides / t if t > 0 else 0
+            bucket["hallucination"] = bucket.get("supprime", 0) / t if t > 0 else 0
+
+        for bucket in by_source.values():
+            t = bucket["total"]
+            valides = bucket.get("correct", 0) + bucket.get("modifie", 0)
+            bucket["precision"] = valides / t if t > 0 else 0
+            bucket["hallucination"] = bucket.get("supprime", 0) / t if t > 0 else 0
+
+        return {
+            "total_valides": total,
+            "dp": {
+                "total": total,
+                "correct": dp_correct,
+                "modifie": dp_modifie,
+                "supprime": dp_supprime,
+                "accuracy": dp_correct / total if total > 0 else 0,
+            },
+            "das": {
+                "total_pipeline": das_total_pipeline,
+                "correct": das_correct,
+                "modifie": das_modifie,
+                "supprime": das_supprime,
+                "ajoutes": das_ajoutes,
+                "reference": das_reference,
+                "precision": precision,
+                "recall": recall,
+                "f1": f1,
+                "hallucination_rate": hallucination_rate,
+                "miss_rate": miss_rate,
+            },
+            "by_confidence": by_confidence,
+            "by_source": by_source,
+            "top_corrections": top_corrections,
+            "dp_corrections": Counter(dp_corrections).most_common(10),
+        }
+
+    def _find_pipeline_data(self, dossier_id: str, groups: dict) -> dict | None:
+        """Trouve les données pipeline pour un dossier_id donné."""
+        # dossier_id est de la forme "45_23183041/fusionne"
+        parts = dossier_id.split("/")
+        group_name = parts[0] if parts else ""
+        items = groups.get(group_name, [])
+        for item in items:
+            if "fusionne" in item["name"]:
+                return item
+        return items[0] if items else None