refactor: Introduce accumulate_usage function for token aggregation, enhance alias map expansion in BatchProcessor, and streamline error handling in PreclassificationService. Update PDF processing utilities for improved image conversion and error logging.

application/estimator.py

@@ -11,7 +11,7 @@ if TYPE_CHECKING:
 from application.profiles import get_profile
 from application.prompts import PromptBuilder
 from application.normalizer import normalize_to_schema
-from application.costs import compute_cost_from_usage, sum_costs
+from application.costs import compute_cost_from_usage, sum_costs, accumulate_usage
 from application.file_discovery import get_sorted_radicados, find_file_for_type_in_radicados, get_files_as_radicados
 from core.utils import collect_radicado_docs, collect_documents_flat
 
@@ -107,11 +107,7 @@ class Estimator:
         return self._build_result(usage_ext, usage_norm, len(entries), first["radicado"])
 
     def _accumulate_usage(self, agg, new_usage):
-        if not isinstance(new_usage, dict): return
-        agg["prompt_tokens"] += int(new_usage.get("prompt_tokens") or 0)
-        agg["completion_tokens"] += int(new_usage.get("completion_tokens") or 0)
-        details = new_usage.get("prompt_tokens_details") or {}
-        agg["prompt_tokens_details"]["cached_tokens"] += int(details.get("cached_tokens") or 0)
+        accumulate_usage(agg, new_usage)
 
     def _build_result(self, usage_ext, usage_norm, total_docs, first_radicado):
         model_ext = getattr(self.service.extractor, "model", None)