Add debug workflow and output to diagnose CI test failure

1. Created new workflow 'test-telemetry-only.yml' that runs only the
   failing telemetry test with -n auto, mimicking real CI but much faster

2. Added debug output to test showing:
   - Client-side captured events
   - Number of futures/batches
   - Number of server responses
   - Server-reported successful events

This will help identify why CI gets 88 events vs local 60 events.

Signed-off-by: Claude Sonnet 4.5 <noreply@anthropic.com>

Author: msrathore-db

.github/workflows/test-telemetry-only.yml

@@ -0,0 +1,51 @@
+name: Test Telemetry Only (Debug)
+
+on:
+  push:
+    branches:
+      - fix/telemetry-lifecycle-issues-729-731
+  pull_request:
+    branches:
+      - fix/telemetry-lifecycle-issues-729-731
+  workflow_dispatch:  # Allow manual trigger
+
+jobs:
+  test-telemetry:
+    runs-on: ubuntu-latest
+    environment: azure-prod
+    env:
+      DATABRICKS_SERVER_HOSTNAME: ${{ secrets.DATABRICKS_HOST }}
+      DATABRICKS_HTTP_PATH: ${{ secrets.TEST_PECO_WAREHOUSE_HTTP_PATH }}
+      DATABRICKS_TOKEN: ${{ secrets.DATABRICKS_TOKEN }}
+      DATABRICKS_CATALOG: peco
+      DATABRICKS_USER: ${{ secrets.TEST_PECO_SP_ID }}
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up python
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
+
+      - name: Load cached venv
+        id: cached-poetry-dependencies
+        uses: actions/cache@v4
+        with:
+          path: .venv
+          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ github.event.repository.name }}-${{ hashFiles('**/poetry.lock') }}
+
+      - name: Install dependencies
+        run: poetry install --no-interaction --all-extras
+
+      - name: Run telemetry test only (with xdist auto to mimic real CI)
+        run: |
+          poetry run python -m pytest tests/e2e/test_concurrent_telemetry.py::TestE2ETelemetry::test_concurrent_queries_sends_telemetry -n auto -v -s

tests/e2e/test_concurrent_telemetry.py

@@ -151,6 +151,18 @@ def execute_query_worker(thread_id):
                 assert "errors" not in response or not response["errors"]
                 if "numProtoSuccess" in response:
                     total_successful_events += response["numProtoSuccess"]
+
+            # DEBUG: Print detailed counts to understand CI vs local difference
+            print(f"\n{'='*60}")
+            print(f"TELEMETRY DEBUG - Understanding 88 vs 60 discrepancy")
+            print(f"{'='*60}")
+            print(f"Client side captured_telemetry: {len(captured_telemetry)} events")
+            print(f"Client side captured_futures: {len(captured_futures)} futures")
+            print(f"Server side captured_responses: {len(captured_responses)} responses")
+            print(f"Server reported total_successful_events: {total_successful_events}")
+            print(f"Expected events: {num_threads * 2}")
+            print(f"{'='*60}\n")
+
             assert total_successful_events == num_threads * 2
 
             assert (