feat(extraction): map_roles — orchestrateur VLM ancrage strict (client injectable)

build_role_prompt (modes libre / guidé par rôles), parse_vlm_json (robuste :
tolère les fences, {} si invalide), map_roles (prompt -> VLM -> parse -> reconstruct).
Client VLM injecté => testable hors-ligne. 6 tests unit ajoutés (15 au total).
Non branché au runtime (brique validée isolément).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

tests/unit/test_role_mapper.py

@@ -8,6 +8,8 @@ import pytest
 
 from core.extraction.role_mapper import (
     OcrToken,
+    build_role_prompt,
+    map_roles,
     reconstruct_fields,
     tokens_from_grid,
 )
@@ -91,3 +93,60 @@ def test_tokens_from_grid_indexe_et_normalise_bbox():
     assert [t.id for t in tokens] == [0, 1]
     assert tokens[0].text == "Nom"
     assert tokens[1].bbox == (20, 0, 60, 8)
+
+
+# --- map_roles : orchestrateur (client VLM injectable, donc testable hors-ligne) ---
+
+def _fake_client(response, capture=None):
+    """Faux client VLM : enregistre éventuellement le prompt reçu, renvoie une réponse fixe."""
+    def client(image_path, prompt):
+        if capture is not None:
+            capture["prompt"] = prompt
+            capture["image_path"] = image_path
+        return response
+    return client
+
+
+def test_map_roles_reconstruit_via_client_injecte():
+    tokens = [_tok(0, "DUPONT"), _tok(1, "Jean")]
+    client = _fake_client('{"champs":[{"label":"Nom complet","value_ids":[0,1]}]}')
+    fields = map_roles("img.png", tokens, client)
+    assert len(fields) == 1
+    assert fields[0].label == "Nom complet"
+    assert fields[0].value == "DUPONT Jean"
+
+
+def test_map_roles_tolere_les_fences_json():
+    tokens = [_tok(0, "DUPONT")]
+    client = _fake_client('```json\n{"champs":[{"label":"Nom","value_ids":[0]}]}\n```')
+    fields = map_roles("img.png", tokens, client)
+    assert fields[0].value == "DUPONT"
+
+
+def test_map_roles_json_invalide_retourne_liste_vide():
+    # robustesse batch : une réponse VLM non-JSON ne doit pas crasher.
+    tokens = [_tok(0, "DUPONT")]
+    client = _fake_client("désolé, je n'ai pas compris")
+    fields = map_roles("img.png", tokens, client)
+    assert fields == []
+
+
+def test_build_role_prompt_inclut_les_tokens_avec_ids():
+    tokens = [_tok(0, "Poids"), _tok(1, "72")]
+    prompt = build_role_prompt(tokens)
+    assert "Poids" in prompt and "72" in prompt
+    assert "value_ids" in prompt  # on demande bien des ids, pas du texte recopié
+
+
+def test_build_role_prompt_guide_liste_les_roles_attendus():
+    tokens = [_tok(0, "X")]
+    prompt = build_role_prompt(tokens, roles=["Nom", "IPP", "Poids"])
+    assert "Nom" in prompt and "IPP" in prompt and "Poids" in prompt
+
+
+def test_map_roles_passe_les_roles_au_prompt():
+    tokens = [_tok(0, "X")]
+    cap = {}
+    client = _fake_client('{"champs":[]}', capture=cap)
+    map_roles("img.png", tokens, client, roles=["Diagnostic", "GEMSA"])
+    assert "Diagnostic" in cap["prompt"] and "GEMSA" in cap["prompt"]