Update annotated_casl_app.py

annotated_casl_app.py

@@ -96,174 +96,6 @@ def combine_sections_smartly(sections_dict):
     
     return '\n'.join(combined_parts)
 
-def call_claude_api_with_continuation(prompt, max_continuations=0):
-    """Call Claude API with smart continuation system - unlimited continuations until complete"""
-    if not ANTHROPIC_API_KEY:
-        return "❌ Claude API key not configured. Please set ANTHROPIC_API_KEY environment variable."
-    
-    # Define all required sections
-    required_sections = [
-        "1. SPEECH FACTORS",
-        "2. LANGUAGE SKILLS ASSESSMENT", 
-        "3. COMPLEX SENTENCE ANALYSIS",
-        "4. FIGURATIVE LANGUAGE ANALYSIS",
-        "5. PRAGMATIC LANGUAGE ASSESSMENT",
-        "6. VOCABULARY AND SEMANTIC ANALYSIS",
-        "7. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS",
-        "8. COGNITIVE-LINGUISTIC FACTORS",
-        "9. FLUENCY AND RHYTHM ANALYSIS",
-        "10. QUANTITATIVE METRICS",
-        "11. CLINICAL IMPLICATIONS",
-        "12. PROGNOSIS AND SUMMARY"
-    ]
-    
-    # Safety limits to prevent infinite loops
-    MAX_CONTINUATIONS = 30  # Increased from 20 to 30 API calls
-    MAX_TIME_MINUTES = 15   # Increased from 10 to 15 minutes total
-    MIN_PROGRESS_PER_CALL = 0  # Changed from 1 to 0 to allow more flexibility
-    
-    try:
-        all_sections = {}  # Store all sections found across all parts
-        continuation_count = 0
-        start_time = time.time()
-        last_section_count = 0  # Track progress between calls
-        
-        # Add continuation instruction to original prompt
-        initial_prompt = prompt + "\n\nCRITICAL INSTRUCTIONS: You MUST complete ALL 12 sections of the analysis. If your response is cut off or incomplete, end with <CONTINUE> to indicate more content is needed. Do not skip any sections. Use the checklist to ensure all sections are completed."
-        
-        while True:  # Unlimited continuations until complete
-            if continuation_count == 0:
-                current_prompt = initial_prompt
-            else:
-                # For continuations, provide context about what was already covered
-                missing_sections = [s for s in required_sections if s not in all_sections]
-                missing_text = "\n".join([f"- {section}" for section in missing_sections])
-                
-                current_prompt = prompt + f"\n\nCONTINUATION {continuation_count + 1}: The following sections are STILL MISSING and MUST be completed:\n\n{missing_text}\n\nCRITICAL: Provide ONLY these missing sections. Do not repeat any sections that are already complete. Focus exclusively on the missing sections listed above. Complete ALL missing sections in this response."
-            
-            headers = {
-                "Content-Type": "application/json",
-                "x-api-key": ANTHROPIC_API_KEY,
-                "anthropic-version": "2023-06-01"
-            }
-            
-            data = {
-                "model": "claude-sonnet-4-5",
-                "max_tokens": 4096,
-                "messages": [
-                    {
-                        "role": "user",
-                        "content": current_prompt
-                    }
-                ]
-            }
-            
-            response = requests.post(
-                "https://api.anthropic.com/v1/messages",
-                headers=headers,
-                json=data,
-                timeout=90
-            )
-            
-            if response.status_code == 200:
-                response_json = response.json()
-                response_text = response_json['content'][0]['text']
-                
-                # Log response for debugging
-                print(f"\n=== PART {continuation_count + 1} RESPONSE ===")
-                print(f"Length: {len(response_text)} characters")
-                print(f"Contains CONTINUE: {'<CONTINUE>' in response_text}")
-                print(f"First 200 chars: {response_text[:200]}...")
-                print(f"Last 200 chars: {response_text[-200:]}...")
-                print("=" * 50)
-                
-                # Segment this part and add new sections to our collection
-                part_sections = segment_response_by_sections(response_text)
-                for section, content in part_sections.items():
-                    if section not in all_sections:  # Only add if not already present
-                        all_sections[section] = content
-                        print(f"Added section: {section}")
-                    else:
-                        print(f"Skipped duplicate section: {section}")
-                
-                # Check completion status
-                completed_sections = len(all_sections)
-                missing_sections = [s for s in required_sections if s not in all_sections]
-                
-                print(f"Completed sections: {completed_sections}/12")
-                print(f"Missing sections: {missing_sections}")
-                
-                # Check if response indicates continuation is needed
-                needs_continuation = "<CONTINUE>" in response_text
-                
-                print(f"Needs continuation: {needs_continuation}")
-                print(f"Continuation count: {continuation_count}")
-                
-                # Safety checks to prevent infinite loops
-                current_time = time.time()
-                elapsed_minutes = (current_time - start_time) / 60
-                current_section_count = len(all_sections)
-                progress_made = current_section_count - last_section_count
-                
-                # Check if we're making progress
-                if continuation_count > 0 and progress_made < MIN_PROGRESS_PER_CALL:
-                    # Only stop if we've made multiple calls with no progress
-                    if continuation_count > 3:  # Allow more attempts before giving up
-                        logger.warning(f"No progress made in last call (added {progress_made} sections). Stopping to prevent infinite loop.")
-                        break
-                    else:
-                        logger.info(f"No progress in call {continuation_count}, but continuing to allow more attempts...")
-                
-                # Check time limit
-                if elapsed_minutes > MAX_TIME_MINUTES:
-                    logger.warning(f"Time limit exceeded ({elapsed_minutes:.1f} minutes). Stopping to prevent excessive API usage.")
-                    break
-                
-                # Check continuation limit
-                if continuation_count >= MAX_CONTINUATIONS:
-                    logger.warning(f"Continuation limit reached ({MAX_CONTINUATIONS} calls). Stopping to prevent excessive API usage.")
-                    break
-                
-                # Continue if <CONTINUE> is present and safety checks pass
-                if needs_continuation:
-                    continuation_count += 1
-                    last_section_count = current_section_count
-                    logger.info(f"Continuing analysis (attempt {continuation_count}/{MAX_CONTINUATIONS}, {elapsed_minutes:.1f} minutes elapsed)")
-                    continue
-                else:
-                    break
-            else:
-                logger.error(f"Claude API error: {response.status_code} - {response.text}")
-                return f"❌ Claude API Error: {response.status_code}"
-                
-    except Exception as e:
-        logger.error(f"Error calling Claude API: {str(e)}")
-        return f"❌ Error: {str(e)}"
-    
-    # Combine all sections in the correct order
-    final_response = combine_sections_smartly(all_sections)
-    
-    # Log final results
-    print(f"\n=== FINAL SMART VALIDATION ===")
-    print(f"Total sections found: {len(all_sections)}")
-    print(f"All sections present: {len(all_sections) == 12}")
-    print(f"Missing sections: {[s for s in required_sections if s not in all_sections]}")
-    print(f"Total time: {(time.time() - start_time) / 60:.1f} minutes")
-    print(f"Total API calls: {continuation_count + 1}")
-    print("=" * 50)
-    
-    # Add completion indicator with safety info
-    if continuation_count > 0:
-        final_response += f"\n\n[Analysis completed in {continuation_count + 1} parts over {(time.time() - start_time) / 60:.1f} minutes]"
-    
-    # Add warning if incomplete due to safety limits
-    if len(all_sections) < 12:
-        missing_sections = [s for s in required_sections if s not in all_sections]
-        final_response += f"\n\n⚠️ WARNING: Analysis incomplete due to safety limits. Missing sections: {', '.join(missing_sections)}"
-        final_response += f"\n\n💡 TIP: Try running the analysis again, or use the 'Targeted Analysis' tab to focus on specific areas."
-        final_response += f"\nThe 'Quick Questions' tab may also provide faster results for specific areas of interest."
-    
-    return final_response
 
 def call_claude_api_quick_analysis(prompt):
     """Call Claude API for quick focused analysis - single response only"""
@@ -1453,84 +1285,6 @@ def process_file(file):
     except Exception as e:
         return f"Error reading file: {str(e)}"
 
-def segment_response_by_sections(response_text):
-    """Segment response by section titles and return a dictionary of sections"""
-    required_sections = [
-        "1. SPEECH FACTORS",
-        "2. LANGUAGE SKILLS ASSESSMENT", 
-        "3. COMPLEX SENTENCE ANALYSIS",
-        "4. FIGURATIVE LANGUAGE ANALYSIS",
-        "5. PRAGMATIC LANGUAGE ASSESSMENT",
-        "6. VOCABULARY AND SEMANTIC ANALYSIS",
-        "7. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS",
-        "8. COGNITIVE-LINGUISTIC FACTORS",
-        "9. FLUENCY AND RHYTHM ANALYSIS",
-        "10. QUANTITATIVE METRICS",
-        "11. CLINICAL IMPLICATIONS",
-        "12. PROGNOSIS AND SUMMARY"
-    ]
-    
-    sections = {}
-    current_section = None
-    current_content = []
-    
-    lines = response_text.split('\n')
-    
-    for line in lines:
-        # Check if this line is a section header
-        is_section_header = False
-        for section in required_sections:
-            if section in line:
-                # Save previous section if exists
-                if current_section and current_content:
-                    sections[current_section] = '\n'.join(current_content).strip()
-                
-                # Start new section
-                current_section = section
-                current_content = []
-                is_section_header = True
-                break
-        
-        # If not a section header, add to current section content
-        if not is_section_header and current_section:
-            current_content.append(line)
-    
-    # Save the last section
-    if current_section and current_content:
-        sections[current_section] = '\n'.join(current_content).strip()
-    
-    return sections
-
-def combine_sections_smartly(sections_dict):
-    """Combine sections in the correct order without duplicates"""
-    required_sections = [
-        "1. SPEECH FACTORS",
-        "2. LANGUAGE SKILLS ASSESSMENT", 
-        "3. COMPLEX SENTENCE ANALYSIS",
-        "4. FIGURATIVE LANGUAGE ANALYSIS",
-        "5. PRAGMATIC LANGUAGE ASSESSMENT",
-        "6. VOCABULARY AND SEMANTIC ANALYSIS",
-        "7. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS",
-        "8. COGNITIVE-LINGUISTIC FACTORS",
-        "9. FLUENCY AND RHYTHM ANALYSIS",
-        "10. QUANTITATIVE METRICS",
-        "11. CLINICAL IMPLICATIONS",
-        "12. PROGNOSIS AND SUMMARY"
-    ]
-    
-    combined_parts = []
-    combined_parts.append("COMPREHENSIVE SPEECH SAMPLE ANALYSIS")
-    combined_parts.append("")
-    
-    for section in required_sections:
-        if section in sections_dict:
-            combined_parts.append(section)
-            combined_parts.append("")
-            combined_parts.append(sections_dict[section])
-            combined_parts.append("")
-    
-    return '\n'.join(combined_parts)
-
 def call_claude_api_with_continuation(prompt):
     """Call Claude API with smart continuation system - unlimited continuations until complete"""
     if not ANTHROPIC_API_KEY:
@@ -1629,8 +1383,15 @@ def call_claude_api_with_continuation(prompt):
                 print(f"Missing sections: {missing_sections}")
                 
                 # Check if response indicates continuation is needed
-                needs_continuation = "<CONTINUE>" in response_text
+                has_continue_marker = "<CONTINUE>" in response_text
+                has_missing_sections = len(missing_sections) > 0
+                
+                # Continuation needed if either marker present OR sections missing
+                needs_continuation = has_continue_marker or has_missing_sections
                 
+                print(f"Has <CONTINUE> marker: {has_continue_marker}")
+                print(f"Has missing sections: {has_missing_sections}")
+                print(f"Missing sections: {missing_sections}")
                 print(f"Needs continuation: {needs_continuation}")
                 print(f"Continuation count: {continuation_count}")