chore(similarity): Add temp metric for stacktraces with limited data (#…

…81700)

Add temporary metric for stacktraces with no header, filename, and only
have one frame

src/sentry/seer/similarity/utils.py

@@ -200,6 +200,7 @@ def get_stacktrace_string(data: dict[str, Any], platform: str | None = None) ->
     frame_count = 0
     html_frame_count = 0  # for a temporary metric
     is_frames_truncated = False
+    has_no_filename = False  # for a temporary metric
     stacktrace_str = ""
     found_non_snipped_context_line = False
 
@@ -209,6 +210,7 @@ def _process_frames(frames: list[dict[str, Any]]) -> list[str]:
         nonlocal frame_count
         nonlocal html_frame_count
         nonlocal is_frames_truncated
+        nonlocal has_no_filename
         nonlocal found_non_snipped_context_line
         frame_strings = []
 
@@ -229,6 +231,9 @@ def _process_frames(frames: list[dict[str, Any]]) -> list[str]:
             if not _is_snipped_context_line(frame_dict["context-line"]):
                 found_non_snipped_context_line = True
 
+            if not frame_dict["filename"]:
+                has_no_filename = True
+
             # Not an exhaustive list of tests we could run to detect HTML, but this is only
             # meant to be a temporary, quick-and-dirty metric
             # TODO: Don't let this, and the metric below, hang around forever. It's only to
@@ -311,6 +316,16 @@ def _process_frames(frames: list[dict[str, Any]]) -> list[str]:
         },
     )
 
+    # Metric for errors with no header, only one frame and no filename
+    # TODO: Determine how often this occurs and if we should send to seer, then remove metric
+    if has_no_filename and len(result_parts) == 1:
+        header, frames = result_parts[0][0], result_parts[0][1]
+        if header == "" and len(frames) == 1:
+            metrics.incr(
+                "seer.grouping.no_header_one_frame_no_filename",
+                sample_rate=options.get("seer.similarity.metrics_sample_rate"),
+            )
+
     return stacktrace_str.strip()
 
 

tests/sentry/seer/similarity/test_utils.py

@@ -1,10 +1,12 @@
 import copy
 from collections.abc import Callable
 from typing import Any, Literal, cast
+from unittest.mock import patch
 from uuid import uuid1
 
 import pytest
 
+from sentry import options
 from sentry.eventstore.models import Event
 from sentry.seer.similarity.utils import (
     BASE64_ENCODED_PREFIXES,
@@ -299,7 +301,7 @@ class GetStacktraceStringTest(TestCase):
         }
     }
 
-    MOBILE_THREAD_DATA = {
+    MOBILE_THREAD_DATA: dict[str, Any] = {
         "app": {
             "type": "component",
             "description": "in-app thread stack-trace",
@@ -865,6 +867,19 @@ def test_no_filename_or_module(self):
             == 'ZeroDivisionError: division by zero\n  File "None", function divide_by_zero\n    divide = 1/0'
         )
 
+    @patch("sentry.seer.similarity.utils.metrics")
+    def test_no_header_one_frame_no_filename(self, mock_metrics):
+        exception = copy.deepcopy(self.MOBILE_THREAD_DATA)
+        # Remove filename
+        exception["app"]["component"]["values"][0]["values"][0]["values"][0]["values"][1][
+            "values"
+        ] = []
+        get_stacktrace_string(exception)
+        sample_rate = options.get("seer.similarity.metrics_sample_rate")
+        mock_metrics.incr.assert_called_with(
+            "seer.grouping.no_header_one_frame_no_filename", sample_rate=sample_rate
+        )
+
 
 class EventContentIsSeerEligibleTest(TestCase):
     def get_eligible_event_data(self) -> dict[str, Any]: