Better reporting from api-gateway's metric endpoint (#845)

- Connect failures (DNS, connect refused, server disconnect) now
  return 502 Bad Gateway with a body that names the upstream URL.
- Other exceptions still return 500 but now include the exception
  message in the body and log with exc_info=True so the stack trace
  lands in the gateway log.
- Also fixed the logging.error → logger.error inconsistency in the
  same block (module had a named logger at the top that wasn't being
  used).

trustgraph-flow/trustgraph/gateway/endpoint/metrics.py

@@ -47,26 +47,37 @@ class MetricsEndpoint:
         if not self.auth.permitted(token, self.operation):
             return web.HTTPUnauthorized()
 
-        try:
-
         path = request.match_info["path"]
-
-            async with aiohttp.ClientSession() as session:
-
         url = (
             self.prometheus_url + "/api/v1/" + path + "?" +
             request.query_string
         )
 
+        try:
+
+            async with aiohttp.ClientSession() as session:
                 async with session.get(url) as resp:
                     return web.Response(
                         status=resp.status,
                         text=await resp.text()
                     )
 
+        except aiohttp.ClientConnectionError as e:
+
+            # Upstream unreachable (connect refused, DNS failure,
+            # server disconnect).  Distinguish from our own errors so
+            # callers know where the fault is.
+            logger.error(f"Metrics upstream {url} unreachable: {e}")
+            return web.Response(
+                status=502,
+                text=f"Bad Gateway: metrics upstream unreachable: {e}",
+            )
+
         except Exception as e:
 
-            logging.error(f"Exception: {e}")
-
-            raise web.HTTPInternalServerError()
+            logger.error(f"Metrics proxy exception: {e}", exc_info=True)
+            return web.Response(
+                status=500,
+                text=f"Internal Server Error: {e}",
+            )