almost ready

worker/blworker/log.py

@@ -0,0 +1,47 @@
+"""Stdlib logging setup — one stream handler on stdout, human or JSON.
+
+Workers used to print() everything; that gives no levels, no timestamps, and nothing
+Loki can parse. Default is a compact human format for local runs; set LOG_JSON=1 in the
+container so Grafana Alloy -> Loki gets structured fields (ts, level, logger, msg) plus
+any `extra=` keys a call site attaches.
+"""
+
+import json
+import logging
+import sys
+
+# logging.LogRecord built-ins we don't want to echo into a JSON line as "extra" fields.
+_RESERVED = set(
+    logging.makeLogRecord({}).__dict__
+) | {"message", "asctime", "taskName"}
+
+
+class _JsonFormatter(logging.Formatter):
+    def format(self, record: logging.LogRecord) -> str:
+        payload = {
+            "ts": self.formatTime(record, "%Y-%m-%dT%H:%M:%S%z"),
+            "level": record.levelname,
+            "logger": record.name,
+            "msg": record.getMessage(),
+        }
+        for key, value in record.__dict__.items():
+            if key not in _RESERVED and not key.startswith("_"):
+                payload[key] = value
+        if record.exc_info:
+            payload["exc"] = self.formatException(record.exc_info)
+        return json.dumps(payload, default=str)
+
+
+def configure(level: str = "INFO", json_logs: bool = False) -> None:
+    """Install a single stdout handler on the root logger (idempotent)."""
+    handler = logging.StreamHandler(sys.stdout)
+    if json_logs:
+        handler.setFormatter(_JsonFormatter())
+    else:
+        handler.setFormatter(
+            logging.Formatter("%(asctime)s %(levelname)-5s %(name)s | %(message)s", "%H:%M:%S")
+        )
+    root = logging.getLogger()
+    root.handlers.clear()
+    root.addHandler(handler)
+    root.setLevel(level)