making sure end page always greater than start page and in the same seeing getting the same value output even if the pipeline generated is different

services/pipeline_generator.py

@@ -116,12 +116,15 @@ For general questions, greetings, or information requests - just have a normal c
 - Use "classify" (NOT "classify_text")
 - For text-processing tools (summarize, ner, translator, classify): ALWAYS use start_page=1, end_page=1
 - For extraction tools (extract_text, extract_tables, images, signatures, stamps): use actual page ranges
+- **NEVER use negative page numbers (e.g., end_page: -1 is FORBIDDEN)**
+- **To process ALL pages, ALWAYS use end_page: 999 (NOT -1!)**
+- **start_page and end_page must ALWAYS be positive integers >= 1**
 
 Return ONLY valid JSON:
 {{
   "pipeline_name": "descriptive-name",
   "components": [
-    {{"tool_name": "extract_text", "start_page": 1, "end_page": 5, "params": {{"encoding": "utf-8"}}}},
+    {{"tool_name": "extract_text", "start_page": 1, "end_page": 999, "params": {{"encoding": "utf-8"}}}},
     {{"tool_name": "summarize", "start_page": 1, "end_page": 1, "params": {{"max_length": 500}}}}
   ],
   "target_lang": null,