fix: use timezone-aware UTC timestamps

src/models/schemas.py

@@ -1,6 +1,6 @@
 from enum import Enum
 from typing import Any, Dict, List, Optional
-from datetime import datetime
+from datetime import UTC, datetime
 from pydantic import BaseModel, Field
 
 # --- Enums (from enhanced_extractor.py) ---
@@ -30,7 +30,7 @@ class ExtractionResult(BaseModel):
     source: DataSource
     confidence: ConfidenceLevel
     extraction_method: str
-    timestamp: str = Field(default_factory=lambda: datetime.utcnow().isoformat())
+    timestamp: str = Field(default_factory=lambda: datetime.now(UTC).isoformat())
     fallback_chain: List[str] = Field(default_factory=list)
 
     def __str__(self):

src/utils/analytics.py

@@ -1,6 +1,6 @@
 import os
 import logging
-from datetime import datetime
+from datetime import UTC, datetime
 from datasets import Dataset, load_dataset, concatenate_datasets
 from ..config import HF_REPO, HF_TOKEN
 
@@ -24,7 +24,7 @@ def _push_log():
             try:
                 normalized_model_id = model_id 
                 log_data = {
-                    "timestamp": [datetime.utcnow().isoformat()],
+                    "timestamp": [datetime.now(UTC).isoformat()],
                     "event": ["generated"],
                     "model_id": [normalized_model_id]
                 }

tests/test_schemas.py

@@ -0,0 +1,16 @@
+from datetime import datetime
+
+from src.models.schemas import ConfidenceLevel, DataSource, ExtractionResult
+
+
+def test_extraction_timestamp_is_timezone_aware_utc():
+    result = ExtractionResult(
+        value="value",
+        source=DataSource.HF_API,
+        confidence=ConfidenceLevel.HIGH,
+        extraction_method="test",
+    )
+
+    timestamp = datetime.fromisoformat(result.timestamp)
+    assert timestamp.utcoffset() is not None
+    assert timestamp.utcoffset().total_seconds() == 0