phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 18:00:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

ci: Temperarily disable Telemetry during tests

Browse source 
We can re-enable again when thew problem is fixed.
Closes: #4089

Signed-off-by: Derek Higgins <derekh@redhat.com>
This commit is contained in:
Derek Higgins 2025-11-06 13:39:59 +00:00 • committed by leseb
parent 03d23db910
commit ad4caf7b4a
2 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
scripts/integration-tests.sh
View file

@ -231,7 +231,8 @@ if [[ "$STACK_CONFIG" == *"server:"* && "$COLLECT_ONLY" == false ]]; then
# Use a fixed port for the OTEL collector so the server can connect to it # Use a fixed port for the OTEL collector so the server can connect to it
COLLECTOR_PORT=4317 COLLECTOR_PORT=4317
export LLAMA_STACK_TEST_COLLECTOR_PORT="${COLLECTOR_PORT}" export LLAMA_STACK_TEST_COLLECTOR_PORT="${COLLECTOR_PORT}"
export OTEL_EXPORTER_OTLP_ENDPOINT="http://127.0.0.1:${COLLECTOR_PORT}" # Disabled: https://github.com/llamastack/llama-stack/issues/4089
#export OTEL_EXPORTER_OTLP_ENDPOINT="http://127.0.0.1:${COLLECTOR_PORT}"
export OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf" export OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf"
export OTEL_BSP_SCHEDULE_DELAY="200" export OTEL_BSP_SCHEDULE_DELAY="200"
export OTEL_BSP_EXPORT_TIMEOUT="2000" export OTEL_BSP_EXPORT_TIMEOUT="2000"
@ -337,7 +338,8 @@ if [[ "$STACK_CONFIG" == *"docker:"* && "$COLLECT_ONLY" == false ]]; then
DOCKER_ENV_VARS="" DOCKER_ENV_VARS=""
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_INFERENCE_MODE=$INFERENCE_MODE" DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_INFERENCE_MODE=$INFERENCE_MODE"
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_STACK_CONFIG_TYPE=server" DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_STACK_CONFIG_TYPE=server"
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:${COLLECTOR_PORT}" # Disabled: https://github.com/llamastack/llama-stack/issues/4089
#DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:${COLLECTOR_PORT}"
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_METRIC_EXPORT_INTERVAL=200" DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_METRIC_EXPORT_INTERVAL=200"
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_BSP_SCHEDULE_DELAY=200" DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_BSP_SCHEDULE_DELAY=200"
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_BSP_EXPORT_TIMEOUT=2000" DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_BSP_EXPORT_TIMEOUT=2000"

5
tests/integration/telemetry/test_completions.py
View file

@ -12,9 +12,13 @@ before and after each test, ensuring test isolation.
import json import json
import pytest
def test_streaming_chunk_count(mock_otlp_collector, llama_stack_client, text_model_id): def test_streaming_chunk_count(mock_otlp_collector, llama_stack_client, text_model_id):
"""Verify streaming adds chunk_count and __type__=async_generator.""" """Verify streaming adds chunk_count and __type__=async_generator."""
pytest.skip("Disabled: See https://github.com/llamastack/llama-stack/issues/4089")
stream = llama_stack_client.chat.completions.create( stream = llama_stack_client.chat.completions.create(
model=text_model_id, model=text_model_id,
messages=[{"role": "user", "content": "Test trace openai 1"}], messages=[{"role": "user", "content": "Test trace openai 1"}],
@ -50,6 +54,7 @@ def test_streaming_chunk_count(mock_otlp_collector, llama_stack_client, text_mod
def test_telemetry_format_completeness(mock_otlp_collector, llama_stack_client, text_model_id): def test_telemetry_format_completeness(mock_otlp_collector, llama_stack_client, text_model_id):
"""Comprehensive validation of telemetry data format including spans and metrics.""" """Comprehensive validation of telemetry data format including spans and metrics."""
pytest.skip("Disabled: See https://github.com/llamastack/llama-stack/issues/4089")
response = llama_stack_client.chat.completions.create( response = llama_stack_client.chat.completions.create(
model=text_model_id, model=text_model_id,
messages=[{"role": "user", "content": "Test trace openai with temperature 0.7"}], messages=[{"role": "user", "content": "Test trace openai with temperature 0.7"}],