mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-26 01:12:59 +00:00
8265d4efc8
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (push) Failing after 6s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 14s
UI Tests / ui-tests (22) (push) Successful in 43s
Pre-commit / pre-commit (push) Successful in 1m35s
# What does this PR do? Clean up telemetry code since the telemetry API has been remove. - moved telemetry files out of providers to core - removed from Api ## Test Plan ❯ OTEL_SERVICE_NAME=llama_stack OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 uv run llama stack run starter ❯ curl http://localhost:8321/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "openai/gpt-4o-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }' -> verify traces in Grafana CI |
||
|---|---|---|
| .. | ||
| cli | ||
| conversations | ||
| core | ||
| distribution | ||
| files | ||
| models | ||
| prompts/prompts | ||
| providers | ||
| rag | ||
| registry | ||
| server | ||
| tools | ||
| utils | ||
| __init__.py | ||
| conftest.py | ||
| fixtures.py | ||
| README.md | ||
Llama Stack Unit Tests
Unit Tests
Unit tests verify individual components and functions in isolation. They are fast, reliable, and don't require external services.
Prerequisites
- Python Environment: Ensure you have Python 3.12+ installed
- uv Package Manager: Install
uvif not already installed
You can run the unit tests by running:
./scripts/unit-tests.sh [PYTEST_ARGS]
Any additional arguments are passed to pytest. For example, you can specify a test directory, a specific test file, or any pytest flags (e.g., -vvv for verbosity). If no test directory is specified, it defaults to "tests/unit", e.g:
./scripts/unit-tests.sh tests/unit/registry/test_registry.py -vvv
If you'd like to run for a non-default version of Python (currently 3.12), pass PYTHON_VERSION variable as follows:
source .venv/bin/activate
PYTHON_VERSION=3.13 ./scripts/unit-tests.sh
Test Configuration
- Test Discovery: Tests are automatically discovered in the
tests/unit/directory - Async Support: Tests use
--asyncio-mode=autofor automatic async test handling - Coverage: Tests generate coverage reports in
htmlcov/directory - Python Version: Defaults to Python 3.12, but can be overridden with
PYTHON_VERSIONenvironment variable
Coverage Reports
After running tests, you can view coverage reports:
# Open HTML coverage report in browser
open htmlcov/index.html # macOS
xdg-open htmlcov/index.html # Linux
start htmlcov/index.html # Windows