fix(text): implement proper structured output for multi-chunk processing

- Fix annotate_text_sync to return List[Span] when structured=True for chunked text
- Previously returned dict instead of structured spans for text > chunk_length
- Add proper span position adjustment across chunk boundaries
- Resolves benchmark test failure in test_structured_output_performance

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: sidmohan0

datafog/services/text_service.py

@@ -132,19 +132,34 @@ def annotate_text_sync(
         else:
             # Multi-chunk processing
             chunks = self._chunk_text(text)
-            chunk_annotations = []
-
-            for chunk in chunks:
-                chunk_result = self.annotate_text_sync(chunk, structured=False)
-                chunk_annotations.append(chunk_result)
 
             if structured:
-                # For structured output with chunking, we need to recalculate positions
-                # This is more complex, so for now return dict format
+                # For structured output, we need to handle span positions across chunks
+                all_spans = []
+                current_offset = 0
+
+                for chunk in chunks:
+                    chunk_spans = self.annotate_text_sync(chunk, structured=True)
+                    # Adjust span positions to account for chunk offset
+                    for span in chunk_spans:
+                        adjusted_span = Span(
+                            start=span.start + current_offset,
+                            end=span.end + current_offset,
+                            text=span.text,
+                            label=span.label,
+                        )
+                        all_spans.append(adjusted_span)
+                    current_offset += len(chunk)
+
+                return all_spans
+            else:
+                # Dictionary format - combine annotations
+                chunk_annotations = []
+                for chunk in chunks:
+                    chunk_result = self.annotate_text_sync(chunk, structured=False)
+                    chunk_annotations.append(chunk_result)
                 return self._combine_annotations(chunk_annotations)
 
-            return self._combine_annotations(chunk_annotations)
-
     async def annotate_text_async(
         self, text: str, structured: bool = False
     ) -> Union[Dict[str, List[str]], List[Span]]: