diff --git a/agent_factory_llama.py b/agent_factory_llama.py
index 4cc7b4d..5ae89e8 100644
--- a/agent_factory_llama.py
+++ b/agent_factory_llama.py
@@ -47,14 +47,9 @@ class AgentFactoryLlamaVision:
         actual_model = model_name if model_name else AgentFactoryLlamaVision.DEFAULT_MODEL_NAME
         logger.info(f"Initialisation du modèle llama_vision (modèle: {actual_model})")
         
-        # Assurer que le nom du modèle est normalisé pour éviter les doublons dans les noms de fichiers
-        normalized_model = actual_model.replace(".", "-").replace(":", "-").replace("_", "-")
+        # Créer l'instance avec le nom exact du modèle
+        model = LlamaVision(modele=actual_model)
         
-        start_time = time.time()
-        model = LlamaVision(modele=normalized_model)
-        init_time = time.time() - start_time
-        
-        logger.info(f"Modèle llama_vision initialisé en {init_time:.2f} secondes")
         return model
     
     @staticmethod
diff --git a/llm_classes/llama_vision.py b/llm_classes/llama_vision.py
index 17caa1d..f60ea9e 100644
--- a/llm_classes/llama_vision.py
+++ b/llm_classes/llama_vision.py
@@ -56,26 +56,14 @@ Respond in English unless specifically instructed otherwise."""
         Returns:
             Normalized model name
         """
-        # Check if model name already contains the backend-specific format
-        if ":" not in model_name and model_name != "llama3.2-vision:90b-instruct-q8_0":
-            # Convert standardized name to backend format
-            if model_name == "llama3-vision-90b-instruct":
-                return "llama3.2-vision:90b-instruct-q8_0"
+        # Pour la compatibilité avec pipeline_logger, stocker une version normalisée
+        self.pipeline_normalized_name = model_name.replace(".", "-").replace(":", "-").replace("_", "-")
         
-        # For pipeline_logger compatibility, ensure it's a normalized format
-        # that other parts of the code can recognize for normalization
-        if model_name.startswith("image_"):
-            model_name = model_name[6:]  # Remove redundant prefix
-        
-        # Make sure a standard model name is returned for pipeline_logger
-        # This is a backup in case pipeline_logger fails to normalize
-        if ":" in model_name and "llama" in model_name.lower():
-            self.pipeline_normalized_name = "llama3-vision-90b-instruct"
-        else:
-            # Store normalized version for pipeline_logger
-            self.pipeline_normalized_name = model_name
+        # Pour Ollama, retourner le nom exact du modèle
+        if model_name == "llama3-vision-90b-instruct":
+            return "llama3.2-vision:90b-instruct-q8_0"
             
-        # Return original name if it already has the correct format for Ollama
+        # Retourner le nom tel quel pour Ollama
         return model_name
 
     def urlBase(self) -> str:
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/analyse_ticket_llama3-2-vision-90b-instruct-q8-0_results.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/analyse_ticket_llama3-2-vision-90b-instruct-q8-0_results.json
index 4478f70..99839b7 100644
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/analyse_ticket_llama3-2-vision-90b-instruct-q8-0_results.json
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/analyse_ticket_llama3-2-vision-90b-instruct-q8-0_results.json
@@ -3,7 +3,7 @@
   "response_en": "Ticket content insufficient for analysis",
   "error": true,
   "metadata": {
-    "timestamp": "20250424_103126",
+    "timestamp": "20250424_104158",
     "source_agent": "AgentTicketAnalyser",
     "ticket_id": "T11143",
     "model_info": {
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/543d7da1b54c29ff43ce5712d1a9aa4962ed21795c4e943fcb8cb84fd4d7465a.jpg.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/543d7da1b54c29ff43ce5712d1a9aa4962ed21795c4e943fcb8cb84fd4d7465a.jpg.json
index df41632..42531cf 100644
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/543d7da1b54c29ff43ce5712d1a9aa4962ed21795c4e943fcb8cb84fd4d7465a.jpg.json
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/543d7da1b54c29ff43ce5712d1a9aa4962ed21795c4e943fcb8cb84fd4d7465a.jpg.json
@@ -5,7 +5,7 @@
   "translation_en_back_fr": "",
   "metadata": {
     "ticket_id": "T11143",
-    "timestamp": "20250424_103135",
+    "timestamp": "20250424_104207",
     "source_module": "ocr_utils + translate_utils",
     "lang_detected": "fr"
   }
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/a20f7697fd5e1d1fca3296c6d01228220e0e112c46b4440cc938f74d10934e98.gif.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/a20f7697fd5e1d1fca3296c6d01228220e0e112c46b4440cc938f74d10934e98.gif.json
index 4e0e53c..523eb28 100644
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/a20f7697fd5e1d1fca3296c6d01228220e0e112c46b4440cc938f74d10934e98.gif.json
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/a20f7697fd5e1d1fca3296c6d01228220e0e112c46b4440cc938f74d10934e98.gif.json
@@ -5,7 +5,7 @@
   "translation_en_back_fr": "",
   "metadata": {
     "ticket_id": "T11143",
-    "timestamp": "20250424_103135",
+    "timestamp": "20250424_104207",
     "source_module": "ocr_utils + translate_utils",
     "lang_detected": "fr"
   }
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/image.png.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/image.png.json
index 03c364e..8a10a8e 100644
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/image.png.json
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/image.png.json
@@ -5,7 +5,7 @@
   "translation_en_back_fr": "Apache Tomcat x +\n\nGc @ 2 zk1.brg-b.com\n\n@ Andre Demo Devmat @ Modèle de base\n\nÇa marche!\n\nSi vous voyez cette page via un navigateur Web, cela signifie que vous avez configuré Tomcat avec succès. Félicitations!\n\nIl s'agit de la page d'accueil par défaut de Tomcat. Il peut être trouvé sur le système de fichiers local à: /var/lib/tomcat7/webapps/root/index.html\n\nMatou? Les vétérans pourraient être ravis de lire cette instance système de Tomcat est installé avec cataina_home dans / usr / tomcat7 et cataina_base dans / var / 1ib / tomcat7, en suivant les règles de / usr / share / doc / tomcat7-commun / running. SMS. GZ.\nVous pourriez envisager d'installer les packages suivants, si vous avez fait Alreni:\n\nTomcat7-Docs: Ce package installe une application Web qui permet de parcourir la documentation Tomcat 7 localement. Une fois installé, vous pouvez y accéder en cliquant\n\nTomcat7-Exemple: Ce package installe une application Web qui permet d'accéder aux exemples de servlet Tomcat 7 et JSP. Une fois installé, vous pouvez y accéder en cliquant\n\nTomcat7-admin: Ce package installe deux applications Web qui peuvent aider à gérer cette instance Tomcat. Une fois installé, vous pouvez accéder au et le et le et\n\nRemarque: Pour des raisons de sécurité, l'utilisation du gestionnaire WebApp est limitée aux utilisateurs avec le rôle \"Manager-Gui\". Le manager host-manager est limité aux utilisateurs avec un rôle \"Admin-Gui\". Les utilisateurs sont définis dans / et / tomcat7 / tomcta-users.xml.",
   "metadata": {
     "ticket_id": "T11143",
-    "timestamp": "20250424_103130",
+    "timestamp": "20250424_104202",
     "source_module": "ocr_utils + translate_utils",
     "lang_detected": "fr"
   }
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/image_145435.png.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/image_145435.png.json
index c9fd1ee..2bfd397 100644
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/image_145435.png.json
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/ocr_traduction/image_145435.png.json
@@ -5,7 +5,7 @@
   "translation_en_back_fr": "C3 Giraudbrg-Lobicom / Brg-Lab / Page Progratsai / Zeaaahevngoaaaa\n\n Brglas cd béton cd foumasew tubo © masse\n\nECHANTILLION N ° 25-0007 ECEPTIAN le 02/04/2025 PR Bollé Victor prévu le 04/04/2025 Por Bollee Victor N ° Pédéwment 25-00078\nMatériau de sable 0/20 Carriere adceg\n\n[Fai Jemmarme | [M Porrouo || onservanons] [<suo] [v hisromou\n\nposé. à partir de 11 e ‘z2k1.brg-lab.com",
   "metadata": {
     "ticket_id": "T11143",
-    "timestamp": "20250424_103132",
+    "timestamp": "20250424_104204",
     "source_module": "ocr_utils + translate_utils",
     "lang_detected": "fr"
   }
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0.txt b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0.txt
index a892685..c28cd56 100644
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0.txt
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0.txt
@@ -1,4 +1,48 @@
 RAPPORT D'ANALYSE DU TICKET T11143
 ==================================================
 
-{"Error": "Model 'LLAMA3-2-Vision-90B-Instruct-Q8-0' Non trouvé"}
\ No newline at end of file
+** Rapport croisé: Analyse des billets et analyse d'image **
+
+** Aperçu des billets **
+-------------------
+
+* ID de billet: T11143
+* Agent source: agenticketalyse
+* Horodat: 20250424_104158
+
+** Résultats de l'analyse **
+--------------------
+
+### Analyse des billets
+
+L'analyse des billets a renvoyé une erreur due à un contenu insuffisant pour l'analyse. La réponse du modèle était:
+
+«Contenu insuffisant des billets pour l'analyse»
+
+Informations sur le modèle:
+
+* Modèle: LLAMA3-2-VISION-90B-INSTRUCT-Q8-0
+* Température: 0,1
+* Top_p: 0,5
+* Max_Tokens: 4000
+
+### Analyse d'image
+
+Deux images ont été analysées, mais les deux ont renvoyé une erreur due à l'objet «llamavision» n'ayant aucun attribut «can_analyse_images».
+
+** Tableau chronologique des échanges **
+------------------------------------
+
+Malheureusement, en raison du manque de contenu dans l'analyse des billets et des erreurs d'analyse d'image, il n'y a pas d'échanges à signaler. La table est vide.
+
+| Émetteur | Type | Date | Contenu | Éléments visuels |
+| --- | --- | --- | --- | --- |
+
+** Recommandations **
+-------------------
+
+* Fournir plus de contexte ou de contenu pour l'analyse des billets.
+* Mettez à jour l'objet «Llamavision» pour inclure les capacités d'analyse d'image.
+* Réinstaller l'analyse avec des modèles et des configurations mis à jour.
+
+Veuillez noter que sans plus d'informations ou des résultats d'analyse réussis, il n'est pas possible de fournir un rapport croisé complet.
\ No newline at end of file
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0_results.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0_results.json
deleted file mode 100644
index 6e29ee2..0000000
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0_results.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
-  "prompt": "Voici les données d'analyse pour un ticket de support :\n\n=== ANALYSE DU TICKET ===\n{'response': 'Contenu du ticket insuffisant pour analyse', 'response_en': 'Ticket content insufficient for analysis', 'error': True, 'metadata': {'timestamp': '20250424_103126', 'source_agent': 'AgentTicketAnalyser', 'ticket_id': 'T11143', 'model_info': {'model': 'llama3-2-vision-90b-instruct-q8-0', 'temperature': 0.1, 'top_p': 0.5, 'max_tokens': 4000}}}\n\n=== ANALYSES D'IMAGES ===\n\n\nGénère un rapport croisé en suivant les instructions précédentes, incluant un tableau chronologique des échanges entre CLIENT et SUPPORT. Utilise le format suivant pour le tableau :\n| ÉMETTEUR | TYPE | DATE | CONTENU | ÉLÉMENTS VISUELS |\n| --- | --- | --- | --- | --- |\n| CLIENT | question | date | texte de la question | éléments pertinents des images |\n| SUPPORT | réponse | date | texte de la réponse | éléments pertinents des images |\n\nCe tableau doit synthétiser les échanges tout en intégrant les données pertinentes des images avec le maximum de contexte technique.",
-  "prompt_en": "[ENGLISH RESPONSE REQUESTED]\n\nHere are the analysis data for a support ticket:\n\n=== Ticket analysis ====\n{'Response': 'Insufficient ticket content for analysis', 'responsive_en': 'Insufficient content content for analysis', 'error': true, 'metadata': {'timestamp': '20250424_103126', 'Source_agent': 'Agenticketalyse', 'Ticket_id': 't11143', 'Model_info': {'Model': 'Llama3-2-Vision-90b-Instruct-Q8-0', 'Temperature': 0.1, 'Top_p': 0.5, 'Max_tokens': 4000}}}\n\n=== Image analyzes ====\n\n\nGenerates a cross report following the previous instructions, including a chronological table of exchanges between customers and support. Use the following format for the table:\n| Transmitter | Type | Date | Contents | Visual elements |\n| --- | --- | --- | --- | --- |\n| Customer | Question | Date | Text of the question | Relevant elements of images |\n| Support | Answer | Date | Response text | Relevant elements of images |\n\nThis table must synthesize exchanges while integrating the relevant data of images with the maximum technical context.",
-  "response": "{\"Error\": \"Model 'LLAMA3-2-Vision-90B-Instruct-Q8-0' Non trouvé\"}",
-  "response_en": "{\"error\":\"model 'llama3-2-vision-90b-instruct-q8-0' not found\"}",
-  "metadata": {
-    "ticket_id": "T11143",
-    "timestamp": "20250424_103136",
-    "source_agent": "AgentReportGenerator",
-    "model_info": {
-      "model": "llama3-2-vision-90b-instruct-q8-0",
-      "temperature": 0.2,
-      "top_p": 0.8,
-      "max_tokens": 8000,
-      "presence_penalty": 0,
-      "frequency_penalty": 0,
-      "stop": [],
-      "stream": false,
-      "n": 1
-    },
-    "language": "en-fr"
-  }
-}
\ No newline at end of file
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0_results.txt b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0_results.txt
deleted file mode 100644
index 9132497..0000000
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-2-vision-90b-instruct-q8-0_results.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-RÉSULTATS DE L'ANALYSE RAPPORT_FINAL - TICKET T11143
-================================================================================
-
-{"Error": "Model 'LLAMA3-2-Vision-90B-Instruct-Q8-0' Non trouvé"}
-
-
-================================================================================
-Fichier original: rapport_final_llama3-2-vision-90b-instruct-q8-0_results.json
\ No newline at end of file
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-vision-90b-instruct_results.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-vision-90b-instruct_results.json
new file mode 100644
index 0000000..0761691
--- /dev/null
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-vision-90b-instruct_results.json
@@ -0,0 +1,23 @@
+{
+  "prompt": "Voici les données d'analyse pour un ticket de support :\n\n=== ANALYSE DU TICKET ===\n{'response': 'Contenu du ticket insuffisant pour analyse', 'response_en': 'Ticket content insufficient for analysis', 'error': True, 'metadata': {'timestamp': '20250424_104158', 'source_agent': 'AgentTicketAnalyser', 'ticket_id': 'T11143', 'model_info': {'model': 'llama3-2-vision-90b-instruct-q8-0', 'temperature': 0.1, 'top_p': 0.5, 'max_tokens': 4000}}}\n\n=== ANALYSES D'IMAGES ===\n--- IMAGE : image.png ---\nERROR: Erreur lors de l'analyse: 'LlamaVision' object has no attribute 'peut_analyser_images'\n\n--- IMAGE : image_145435.png ---\nERROR: Erreur lors de l'analyse: 'LlamaVision' object has no attribute 'peut_analyser_images'\n\n\nGénère un rapport croisé en suivant les instructions précédentes, incluant un tableau chronologique des échanges entre CLIENT et SUPPORT. Utilise le format suivant pour le tableau :\n| ÉMETTEUR | TYPE | DATE | CONTENU | ÉLÉMENTS VISUELS |\n| --- | --- | --- | --- | --- |\n| CLIENT | question | date | texte de la question | éléments pertinents des images |\n| SUPPORT | réponse | date | texte de la réponse | éléments pertinents des images |\n\nCe tableau doit synthétiser les échanges tout en intégrant les données pertinentes des images avec le maximum de contexte technique.",
+  "prompt_en": "[ENGLISH RESPONSE REQUESTED]\n\nHere are the analysis data for a support ticket:\n\n=== Ticket analysis ====\n{'Response': 'Insufficient ticket content for analysis', 'responsive_en': 'Insufficient content content for analysis', 'error': true, 'metadata': {'timestamp': '20250424_104158', 'Source_agent': 'Agenticketalyse', 'Ticket_id': 't11143', 'Model_info': {'Model': 'Llama3-2-Vision-90b-Instruct-Q8-0', 'Temperature': 0.1, 'Top_p': 0.5, 'Max_tokens': 4000}}}\n\n=== Image analyzes ====\n--- Image: image.png ---\nError: Error during the analysis: 'Llamavision' Object has no attribute 'can_analyse_images'\n\n--- Image: Image_145435.png ---\nError: Error during the analysis: 'Llamavision' Object has no attribute 'can_analyse_images'\n\n\nGenerates a cross report following the previous instructions, including a chronological table of exchanges between customers and support. Use the following format for the table:\n| Transmitter | Type | Date | Contents | Visual elements |\n| --- | --- | --- | --- | --- |\n| Customer | Question | Date | Text of the question | Relevant elements of images |\n| Support | Answer | Date | Response text | Relevant elements of images |\n\nThis table must synthesize exchanges while integrating the relevant data of images with the maximum technical context.",
+  "response": "** Rapport croisé: Analyse des billets et analyse d'image **\n\n** Aperçu des billets **\n-------------------\n\n* ID de billet: T11143\n* Agent source: agenticketalyse\n* Horodat: 20250424_104158\n\n** Résultats de l'analyse **\n--------------------\n\n### Analyse des billets\n\nL'analyse des billets a renvoyé une erreur due à un contenu insuffisant pour l'analyse. La réponse du modèle était:\n\n«Contenu insuffisant des billets pour l'analyse»\n\nInformations sur le modèle:\n\n* Modèle: LLAMA3-2-VISION-90B-INSTRUCT-Q8-0\n* Température: 0,1\n* Top_p: 0,5\n* Max_Tokens: 4000\n\n### Analyse d'image\n\nDeux images ont été analysées, mais les deux ont renvoyé une erreur due à l'objet «llamavision» n'ayant aucun attribut «can_analyse_images».\n\n** Tableau chronologique des échanges **\n------------------------------------\n\nMalheureusement, en raison du manque de contenu dans l'analyse des billets et des erreurs d'analyse d'image, il n'y a pas d'échanges à signaler. La table est vide.\n\n| Émetteur | Type | Date | Contenu | Éléments visuels |\n| --- | --- | --- | --- | --- |\n\n** Recommandations **\n-------------------\n\n* Fournir plus de contexte ou de contenu pour l'analyse des billets.\n* Mettez à jour l'objet «Llamavision» pour inclure les capacités d'analyse d'image.\n* Réinstaller l'analyse avec des modèles et des configurations mis à jour.\n\nVeuillez noter que sans plus d'informations ou des résultats d'analyse réussis, il n'est pas possible de fournir un rapport croisé complet.",
+  "response_en": "**Cross Report: Ticket Analysis and Image Analysis**\n\n**Ticket Overview**\n-------------------\n\n* Ticket ID: t11143\n* Source Agent: Agenticketalyse\n* Timestamp: 20250424_104158\n\n**Analysis Results**\n--------------------\n\n### Ticket Analysis\n\nThe ticket analysis returned an error due to insufficient content for analysis. The response from the model was:\n\n`Insufficient ticket content for analysis`\n\nModel information:\n\n* Model: Llama3-2-Vision-90b-Instruct-Q8-0\n* Temperature: 0.1\n* Top_p: 0.5\n* Max_tokens: 4000\n\n### Image Analysis\n\nTwo images were analyzed, but both returned an error due to the 'Llamavision' object having no attribute 'can_analyse_images'.\n\n**Chronological Table of Exchanges**\n------------------------------------\n\nUnfortunately, due to the lack of content in the ticket analysis and the errors in image analysis, there are no exchanges to report. The table is empty.\n\n| Transmitter | Type | Date | Contents | Visual elements |\n| --- | --- | --- | --- | --- |\n\n**Recommendations**\n-------------------\n\n* Provide more context or content for the ticket analysis.\n* Update the 'Llamavision' object to include image analysis capabilities.\n* Re-run the analysis with updated models and configurations.\n\nPlease note that without further information or successful analysis results, it is not possible to provide a comprehensive cross report.",
+  "metadata": {
+    "ticket_id": "T11143",
+    "timestamp": "20250424_104415",
+    "source_agent": "AgentReportGenerator",
+    "model_info": {
+      "model": "llama3.2-vision:90b-instruct-q8_0",
+      "temperature": 0.2,
+      "top_p": 0.8,
+      "max_tokens": 8000,
+      "presence_penalty": 0,
+      "frequency_penalty": 0,
+      "stop": [],
+      "stream": false,
+      "n": 1
+    },
+    "language": "en-fr"
+  }
+}
\ No newline at end of file
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-vision-90b-instruct_results.txt b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-vision-90b-instruct_results.txt
new file mode 100644
index 0000000..1990414
--- /dev/null
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/rapport_final_llama3-vision-90b-instruct_results.txt
@@ -0,0 +1,52 @@
+RÉSULTATS DE L'ANALYSE RAPPORT_FINAL - TICKET T11143
+================================================================================
+
+** Rapport croisé: Analyse des billets et analyse d'image **
+
+** Aperçu des billets **
+-------------------
+
+* ID de billet: T11143
+* Agent source: agenticketalyse
+* Horodat: 20250424_104158
+
+** Résultats de l'analyse **
+--------------------
+
+### Analyse des billets
+
+L'analyse des billets a renvoyé une erreur due à un contenu insuffisant pour l'analyse. La réponse du modèle était:
+
+«Contenu insuffisant des billets pour l'analyse»
+
+Informations sur le modèle:
+
+* Modèle: LLAMA3-2-VISION-90B-INSTRUCT-Q8-0
+* Température: 0,1
+* Top_p: 0,5
+* Max_Tokens: 4000
+
+### Analyse d'image
+
+Deux images ont été analysées, mais les deux ont renvoyé une erreur due à l'objet «llamavision» n'ayant aucun attribut «can_analyse_images».
+
+** Tableau chronologique des échanges **
+------------------------------------
+
+Malheureusement, en raison du manque de contenu dans l'analyse des billets et des erreurs d'analyse d'image, il n'y a pas d'échanges à signaler. La table est vide.
+
+| Émetteur | Type | Date | Contenu | Éléments visuels |
+| --- | --- | --- | --- | --- |
+
+** Recommandations **
+-------------------
+
+* Fournir plus de contexte ou de contenu pour l'analyse des billets.
+* Mettez à jour l'objet «Llamavision» pour inclure les capacités d'analyse d'image.
+* Réinstaller l'analyse avec des modèles et des configurations mis à jour.
+
+Veuillez noter que sans plus d'informations ou des résultats d'analyse réussis, il n'est pas possible de fournir un rapport croisé complet.
+
+
+================================================================================
+Fichier original: rapport_final_llama3-vision-90b-instruct_results.json
\ No newline at end of file
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-2-vision-90b-instruct-q8-0_results.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-2-vision-90b-instruct-q8-0_results.json
deleted file mode 100644
index a60f0ba..0000000
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-2-vision-90b-instruct-q8-0_results.json
+++ /dev/null
@@ -1,73 +0,0 @@
-[
-  {
-    "is_relevant": false,
-    "reason": "LlamaVision API Error (404): {\"error\":\"model 'llama3-2-vision-90b-instruct-q8-0' not found\"}",
-    "raw_response": "LlamaVision API Error (404): {\"error\":\"model 'llama3-2-vision-90b-instruct-q8-0' not found\"}",
-    "ocr_used": true,
-    "metadata": {
-      "image_path": "output/ticket_T11143/T11143_20250422_084617/attachments/image.png",
-      "image_name": "image.png",
-      "timestamp": "20250424_103135",
-      "model_info": {
-        "model": "llama3-2-vision-90b-instruct-q8-0",
-        "temperature": 0.1,
-        "top_p": 0.8,
-        "max_tokens": 1000
-      },
-      "ticket_id": "T11143",
-      "source_agent": "AgentImageSorter"
-    }
-  },
-  {
-    "is_relevant": false,
-    "reason": "LlamaVision API Error (404): {\"error\":\"model 'llama3-2-vision-90b-instruct-q8-0' not found\"}",
-    "raw_response": "LlamaVision API Error (404): {\"error\":\"model 'llama3-2-vision-90b-instruct-q8-0' not found\"}",
-    "ocr_used": true,
-    "metadata": {
-      "image_path": "output/ticket_T11143/T11143_20250422_084617/attachments/image_145435.png",
-      "image_name": "image_145435.png",
-      "timestamp": "20250424_103136",
-      "model_info": {
-        "model": "llama3-2-vision-90b-instruct-q8-0",
-        "temperature": 0.1,
-        "top_p": 0.8,
-        "max_tokens": 1000
-      },
-      "ticket_id": "T11143",
-      "source_agent": "AgentImageSorter"
-    }
-  },
-  {
-    "is_relevant": false,
-    "reason": "LlamaVision API Error (404): {\"error\":\"model 'llama3-2-vision-90b-instruct-q8-0' not found\"}",
-    "raw_response": "LlamaVision API Error (404): {\"error\":\"model 'llama3-2-vision-90b-instruct-q8-0' not found\"}",
-    "ocr_used": false,
-    "metadata": {
-      "image_path": "output/ticket_T11143/T11143_20250422_084617/attachments/543d7da1b54c29ff43ce5712d1a9aa4962ed21795c4e943fcb8cb84fd4d7465a.jpg",
-      "image_name": "543d7da1b54c29ff43ce5712d1a9aa4962ed21795c4e943fcb8cb84fd4d7465a.jpg",
-      "timestamp": "20250424_103136",
-      "model_info": {
-        "model": "llama3-2-vision-90b-instruct-q8-0",
-        "temperature": 0.1,
-        "top_p": 0.8,
-        "max_tokens": 1000
-      },
-      "ticket_id": "T11143",
-      "source_agent": "AgentImageSorter"
-    }
-  },
-  {
-    "is_relevant": false,
-    "reason": "ERROR: Erreur d'accès ou format d'image invalide",
-    "raw_response": "",
-    "error": true,
-    "metadata": {
-      "image_path": "output/ticket_T11143/T11143_20250422_084617/attachments/a20f7697fd5e1d1fca3296c6d01228220e0e112c46b4440cc938f74d10934e98.gif",
-      "image_name": "a20f7697fd5e1d1fca3296c6d01228220e0e112c46b4440cc938f74d10934e98.gif",
-      "ticket_id": "T11143",
-      "timestamp": "20250424_103136",
-      "error": true,
-      "source_agent": "AgentImageSorter"
-    }
-  }
-]
\ No newline at end of file
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-2-vision-90b-instruct-q8-0_results.txt b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-2-vision-90b-instruct-q8-0_results.txt
deleted file mode 100644
index 932e856..0000000
--- a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-2-vision-90b-instruct-q8-0_results.txt
+++ /dev/null
@@ -1,30 +0,0 @@
-RÉSULTATS DE L'ANALYSE TRI_IMAGE - TICKET T11143
-================================================================================
-
---- ÉLÉMENT 1 ---
-
-LlamaVision API Error (404): {"error":"model 'llama3-2-vision-90b-instruct-q8-0' not found"}
-
-----------------------------------------
-
---- ÉLÉMENT 2 ---
-
-LlamaVision API Error (404): {"error":"model 'llama3-2-vision-90b-instruct-q8-0' not found"}
-
-----------------------------------------
-
---- ÉLÉMENT 3 ---
-
-LlamaVision API Error (404): {"error":"model 'llama3-2-vision-90b-instruct-q8-0' not found"}
-
-----------------------------------------
-
---- ÉLÉMENT 4 ---
-
-
-
-----------------------------------------
-
-
-================================================================================
-Fichier original: tri_image_llama3-2-vision-90b-instruct-q8-0_results.json
\ No newline at end of file
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-vision-90b-instruct_results.json b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-vision-90b-instruct_results.json
new file mode 100644
index 0000000..e5108ca
--- /dev/null
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-vision-90b-instruct_results.json
@@ -0,0 +1,73 @@
+[
+  {
+    "is_relevant": true,
+    "reason": "Yes.\n\nThis image appears to be a technical screenshot of an Apache Tomcat setup page, which is relevant for a technical support issue related to the BRG_Lab software from CBAO enterprise. The text detected in the image (OCR) provides information about the Tomcat installation and configuration, which could be useful for troubleshooting or setup purposes.",
+    "raw_response": "Yes.\n\nThis image appears to be a technical screenshot of an Apache Tomcat setup page, which is relevant for a technical support issue related to the BRG_Lab software from CBAO enterprise. The text detected in the image (OCR) provides information about the Tomcat installation and configuration, which could be useful for troubleshooting or setup purposes.",
+    "ocr_used": true,
+    "metadata": {
+      "image_path": "output/ticket_T11143/T11143_20250422_084617/attachments/image.png",
+      "image_name": "image.png",
+      "timestamp": "20250424_104238",
+      "model_info": {
+        "model": "llama3.2-vision:90b-instruct-q8_0",
+        "temperature": 0.1,
+        "top_p": 0.8,
+        "max_tokens": 1000
+      },
+      "ticket_id": "T11143",
+      "source_agent": "AgentImageSorter"
+    }
+  },
+  {
+    "is_relevant": true,
+    "reason": "Yes.\n\nThe image appears to be a technical screenshot of the BRG_Lab software, showing a specific page related to concrete testing and material properties. The text detected in the image (OCR) also suggests that it is a legitimate technical document or record from the BRG_Lab system.",
+    "raw_response": "Yes.\n\nThe image appears to be a technical screenshot of the BRG_Lab software, showing a specific page related to concrete testing and material properties. The text detected in the image (OCR) also suggests that it is a legitimate technical document or record from the BRG_Lab system.",
+    "ocr_used": true,
+    "metadata": {
+      "image_path": "output/ticket_T11143/T11143_20250422_084617/attachments/image_145435.png",
+      "image_name": "image_145435.png",
+      "timestamp": "20250424_104253",
+      "model_info": {
+        "model": "llama3.2-vision:90b-instruct-q8_0",
+        "temperature": 0.1,
+        "top_p": 0.8,
+        "max_tokens": 1000
+      },
+      "ticket_id": "T11143",
+      "source_agent": "AgentImageSorter"
+    }
+  },
+  {
+    "is_relevant": false,
+    "reason": "No\n\nThe image appears to be a jumbled collection of characters and does not resemble any technical screenshot, error message, configuration screen, or system log that would be relevant for troubleshooting a technical support issue related to the BRG_Lab software from CBAO enterprise. It seems like corrupted or encoded data rather than an actual image.",
+    "raw_response": "No\n\nThe image appears to be a jumbled collection of characters and does not resemble any technical screenshot, error message, configuration screen, or system log that would be relevant for troubleshooting a technical support issue related to the BRG_Lab software from CBAO enterprise. It seems like corrupted or encoded data rather than an actual image.",
+    "ocr_used": false,
+    "metadata": {
+      "image_path": "output/ticket_T11143/T11143_20250422_084617/attachments/543d7da1b54c29ff43ce5712d1a9aa4962ed21795c4e943fcb8cb84fd4d7465a.jpg",
+      "image_name": "543d7da1b54c29ff43ce5712d1a9aa4962ed21795c4e943fcb8cb84fd4d7465a.jpg",
+      "timestamp": "20250424_104311",
+      "model_info": {
+        "model": "llama3.2-vision:90b-instruct-q8_0",
+        "temperature": 0.1,
+        "top_p": 0.8,
+        "max_tokens": 1000
+      },
+      "ticket_id": "T11143",
+      "source_agent": "AgentImageSorter"
+    }
+  },
+  {
+    "is_relevant": false,
+    "reason": "ERROR: Erreur d'accès ou format d'image invalide",
+    "raw_response": "",
+    "error": true,
+    "metadata": {
+      "image_path": "output/ticket_T11143/T11143_20250422_084617/attachments/a20f7697fd5e1d1fca3296c6d01228220e0e112c46b4440cc938f74d10934e98.gif",
+      "image_name": "a20f7697fd5e1d1fca3296c6d01228220e0e112c46b4440cc938f74d10934e98.gif",
+      "ticket_id": "T11143",
+      "timestamp": "20250424_104311",
+      "error": true,
+      "source_agent": "AgentImageSorter"
+    }
+  }
+]
\ No newline at end of file
diff --git a/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-vision-90b-instruct_results.txt b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-vision-90b-instruct_results.txt
new file mode 100644
index 0000000..54b9aba
--- /dev/null
+++ b/output/ticket_T11143/T11143_20250422_084617/T11143_rapports/pipeline/tri_image_llama3-vision-90b-instruct_results.txt
@@ -0,0 +1,36 @@
+RÉSULTATS DE L'ANALYSE TRI_IMAGE - TICKET T11143
+================================================================================
+
+--- ÉLÉMENT 1 ---
+
+Yes.
+
+This image appears to be a technical screenshot of an Apache Tomcat setup page, which is relevant for a technical support issue related to the BRG_Lab software from CBAO enterprise. The text detected in the image (OCR) provides information about the Tomcat installation and configuration, which could be useful for troubleshooting or setup purposes.
+
+----------------------------------------
+
+--- ÉLÉMENT 2 ---
+
+Yes.
+
+The image appears to be a technical screenshot of the BRG_Lab software, showing a specific page related to concrete testing and material properties. The text detected in the image (OCR) also suggests that it is a legitimate technical document or record from the BRG_Lab system.
+
+----------------------------------------
+
+--- ÉLÉMENT 3 ---
+
+No
+
+The image appears to be a jumbled collection of characters and does not resemble any technical screenshot, error message, configuration screen, or system log that would be relevant for troubleshooting a technical support issue related to the BRG_Lab software from CBAO enterprise. It seems like corrupted or encoded data rather than an actual image.
+
+----------------------------------------
+
+--- ÉLÉMENT 4 ---
+
+
+
+----------------------------------------
+
+
+================================================================================
+Fichier original: tri_image_llama3-vision-90b-instruct_results.json
\ No newline at end of file
diff --git a/reports/T11143/rapport_final_T11143.txt b/reports/T11143/rapport_final_T11143.txt
index e9a8d48..20c4004 100644
--- a/reports/T11143/rapport_final_T11143.txt
+++ b/reports/T11143/rapport_final_T11143.txt
@@ -1 +1,45 @@
-{"Error": "Model 'LLAMA3-2-Vision-90B-Instruct-Q8-0' Non trouvé"}
\ No newline at end of file
+** Rapport croisé: Analyse des billets et analyse d'image **
+
+** Aperçu des billets **
+-------------------
+
+* ID de billet: T11143
+* Agent source: agenticketalyse
+* Horodat: 20250424_104158
+
+** Résultats de l'analyse **
+--------------------
+
+### Analyse des billets
+
+L'analyse des billets a renvoyé une erreur due à un contenu insuffisant pour l'analyse. La réponse du modèle était:
+
+«Contenu insuffisant des billets pour l'analyse»
+
+Informations sur le modèle:
+
+* Modèle: LLAMA3-2-VISION-90B-INSTRUCT-Q8-0
+* Température: 0,1
+* Top_p: 0,5
+* Max_Tokens: 4000
+
+### Analyse d'image
+
+Deux images ont été analysées, mais les deux ont renvoyé une erreur due à l'objet «llamavision» n'ayant aucun attribut «can_analyse_images».
+
+** Tableau chronologique des échanges **
+------------------------------------
+
+Malheureusement, en raison du manque de contenu dans l'analyse des billets et des erreurs d'analyse d'image, il n'y a pas d'échanges à signaler. La table est vide.
+
+| Émetteur | Type | Date | Contenu | Éléments visuels |
+| --- | --- | --- | --- | --- |
+
+** Recommandations **
+-------------------
+
+* Fournir plus de contexte ou de contenu pour l'analyse des billets.
+* Mettez à jour l'objet «Llamavision» pour inclure les capacités d'analyse d'image.
+* Réinstaller l'analyse avec des modèles et des configurations mis à jour.
+
+Veuillez noter que sans plus d'informations ou des résultats d'analyse réussis, il n'est pas possible de fournir un rapport croisé complet.
\ No newline at end of file