feat: implement structured JSON logging

src/mlops_nlp/logging_config.py

@@ -1,12 +1,51 @@
+import json
 import logging
-from typing import Optional
+from datetime import datetime, timezone
+from typing import Any, Optional
+
+
+class JSONFormatter(logging.Formatter):
+    """
+    Custom JSON formatter for structured logging.
+    """
+    def format(self, record: logging.LogRecord) -> str:
+        log_record: dict[str, Any] = {
+            "timestamp": datetime.fromtimestamp(record.created, tz=timezone.utc).isoformat(),
+            "level": record.levelname,
+            "name": record.name,
+            "message": record.getMessage(),
+        }
+
+        # Include extra fields passed via 'extra' parameter
+        # Standard LogRecord attributes to ignore
+        standard_attrs = {
+            "name", "msg", "args", "levelname", "levelno", "pathname", "filename",
+            "module", "exc_info", "exc_text", "stack_info", "lineno", "funcName",
+            "created", "msecs", "relativeCreated", "thread", "threadName",
+            "processName", "process", "message"
+        }
+        for key, value in record.__dict__.items():
+            if key not in standard_attrs:
+                log_record[key] = value
+
+        if record.exc_info:
+            log_record["exception"] = self.formatException(record.exc_info)
+
+        return json.dumps(log_record)
 
 
 def configure_logging(level: str = "INFO") -> None:
-    logging.basicConfig(
-        level=getattr(logging, level.upper(), logging.INFO),
-        format="%(asctime)s | %(levelname)s | %(name)s | %(message)s",
-    )
+    handler = logging.StreamHandler()
+    handler.setFormatter(JSONFormatter())
+
+    root_logger = logging.getLogger()
+    root_logger.setLevel(getattr(logging, level.upper(), logging.INFO))
+
+    # Remove existing handlers to avoid duplicate logs
+    for h in root_logger.handlers[:]:
+        root_logger.removeHandler(h)
+
+    root_logger.addHandler(handler)
 
 
 def get_logger(name: Optional[str] = None) -> logging.Logger:

tests/verify_logging.py

@@ -0,0 +1,19 @@
+from mlops_nlp.logging_config import configure_logging, get_logger
+import json
+
+def test_logging():
+    configure_logging("INFO")
+    logger = get_logger("test_logger")
+
+    # We'll use a string buffer or just check the output manually
+    # For automated check, we can use capsys in pytest, but here we'll just run it.
+    logger.info("This is a test message")
+    logger.info("Message with extra context", extra={"request_id": "12345", "user_id": "abc"})
+
+    try:
+        1/0
+    except Exception:
+        logger.exception("An error occurred")
+
+if __name__ == "__main__":
+    test_logging()