mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-15 14:08:00 +00:00
e12524af85
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 10s
Integration Tests (Replay) / discover-tests (push) Successful in 13s
Python Package Build Test / build (3.12) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 24s
Test External API and Providers / test-external (venv) (push) Failing after 12s
Unit Tests / unit-tests (3.13) (push) Failing after 10s
Update ReadTheDocs / update-readthedocs (push) Failing after 9s
Python Package Build Test / build (3.13) (push) Failing after 15s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 27s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 29s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 27s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 25s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 22s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 25s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 21s
Unit Tests / unit-tests (3.12) (push) Failing after 19s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 35s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 39s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 23s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 35s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 35s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 1m2s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 1m4s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 1m2s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 7s
Pre-commit / pre-commit (push) Successful in 2m21s
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> Extend the Shields Protocol and implement the capability to unregister previously registered shields and CLI for shields management. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes #2581 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> First of, test API for shields 1. Install and start Ollama: `ollama serve` 2. Pull Llama Guard Model in Ollama: `ollama pull llama-guard3:8b` 3. Configure env variables: ``` export ENABLE_OLLAMA=ollama export OLLAMA_URL=http://localhost:11434 ``` 4. Build Llama Stack distro: `llama stack build --template starter --image-type venv ` 5. Start Llama Stack server: `llama stack run starter --port 8321` 6. Check if Ollama model is available: `curl -X GET http://localhost:8321/v1/models | jq '.data[] | select(.provider_id=="ollama")'` 7. Register a new Shield using Ollama provider: ``` curl -X POST http://localhost:8321/v1/shields \ -H "Content-Type: application/json" \ -d '{ "shield_id": "test-shield", "provider_id": "llama-guard", "provider_shield_id": "ollama/llama-guard3:8b", "params": {} }' ``` `{"identifier":"test-shield","provider_resource_id":"ollama/llama-guard3:8b","provider_id":"llama-guard","type":"shield","owner":{"principal":"","attributes":{}},"params":{}}% ` 8. Check if shield was registered: `curl -X GET http://localhost:8321/v1/shields/test-shield` `{"identifier":"test-shield","provider_resource_id":"ollama/llama-guard3:8b","provider_id":"llama-guard","type":"shield","owner":{"principal":"","attributes":{}},"params":{}}% ` 9. Run shield: ``` curl -X POST http://localhost:8321/v1/safety/run-shield \ -H "Content-Type: application/json" \ -d '{ "shield_id": "test-shield", "messages": [ { "role": "user", "content": "How can I hack into someone computer?" } ], "params": {} }' ``` `{"violation":{"violation_level":"error","user_message":"I can't answer that. Can I help with something else?","metadata":{"violation_type":"S2"}}}% ` 10. Unregister shield: `curl -X DELETE http://localhost:8321/v1/shields/test-shield` `null% ` 11. Verify shield was deleted: `curl -X GET http://localhost:8321/v1/shields/test-shield` `{"detail":"Invalid value: Shield 'test-shield' not found"}%` All tests passed ✅ ``` ========================================================================== 430 passed, 194 warnings in 19.54s ========================================================================== /Users/iamiller/GitHub/llama-stack/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/async_client_cleanup.py:78: RuntimeWarning: coroutine 'close_litellm_async_clients' was never awaited loop.close() RuntimeWarning: Enable tracemalloc to get the object allocation traceback Wrote HTML report to htmlcov-3.12/index.html ``` |
||
|---|---|---|
| .. | ||
| cli | ||
| distribution | ||
| files | ||
| models | ||
| providers | ||
| rag | ||
| registry | ||
| server | ||
| 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