feat(extraction): client vLLM serveur (image+prompt -> texte, post_fn injectable)

Factorise un client propre pour la lecture d'écran : downscale image (fenêtre
max_model_len), thinking off, post_fn injectable (testable sans vLLM). Sert de
vlm_client à extract_dossier_from_image dans le handler runtime. 4 tests.

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

tests/unit/test_vlm_client.py

@@ -0,0 +1,65 @@
+"""Tests du client vLLM serveur (image + prompt -> texte).
+
+Le POST réseau est injectable (`post_fn`) → testable sans vLLM. Sert de
+`vlm_client` à `extract_dossier_from_image` dans le handler runtime.
+"""
+import pytest
+
+from core.extraction.vlm_client import build_chat_body, img_data_url, make_vllm_client
+
+
+def _png(tmp_path, w=2000, h=1000):
+    from PIL import Image
+    p = tmp_path / "x.png"
+    Image.new("RGB", (w, h), (255, 255, 255)).save(p)
+    return str(p)
+
+
+class _Resp:
+    def __init__(self, code, payload=None, text=""):
+        self.status_code = code
+        self._p = payload or {}
+        self.text = text
+
+    def json(self):
+        return self._p
+
+
+def test_img_data_url_downscale(tmp_path):
+    url = img_data_url(_png(tmp_path), max_w=1280)
+    assert url.startswith("data:image/png;base64,")
+
+
+def test_build_chat_body_structure(tmp_path):
+    body = build_chat_body(_png(tmp_path), "PROMPT", model="M", max_tokens=1500, max_w=1280)
+    assert body["model"] == "M"
+    assert body["max_tokens"] == 1500
+    # thinking désactivé (vérifié hier : think=on -> vide/lent)
+    assert body["chat_template_kwargs"]["enable_thinking"] is False
+    content = body["messages"][0]["content"]
+    assert any(c["type"] == "image_url" for c in content)
+    assert any(c["type"] == "text" and c["text"] == "PROMPT" for c in content)
+
+
+def test_client_retourne_content(tmp_path):
+    captured = {}
+
+    def fake_post(url, json=None, headers=None, timeout=None):
+        captured["url"] = url
+        captured["body"] = json
+        return _Resp(200, {"choices": [{"message": {"content": "REPONSE"}}]})
+
+    client = make_vllm_client(model="M", post_fn=fake_post)
+    out = client(_png(tmp_path), "PROMPT")
+    assert out == "REPONSE"
+    assert "/v1/chat/completions" in captured["url"]
+    assert captured["body"]["messages"][0]["content"][1]["text"] == "PROMPT"
+
+
+def test_client_erreur_status_leve(tmp_path):
+    def fake_post(url, json=None, headers=None, timeout=None):
+        return _Resp(500, text="boom")
+
+    client = make_vllm_client(post_fn=fake_post)
+    with pytest.raises(RuntimeError):
+        client(_png(tmp_path), "PROMPT")