phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/tests/unit
History
Sumanth Kamenani 2838d5a20f
fix: AWS Bedrock inference profile ID conversion for region-specific endpoints (#3386) 
Fixes #3370

AWS switched to requiring region-prefixed inference profile IDs instead
of foundation model IDs for on-demand throughput. This was causing
ValidationException errors.

Added auto-detection based on boto3 client region to convert model IDs
like meta.llama3-1-70b-instruct-v1:0 to
us.meta.llama3-1-70b-instruct-v1:0 depending on the detected region.

Also handles edge cases like ARNs, case insensitive regions, and None
regions.

Tested with this request.
```json
{
  "model_id": "meta.llama3-1-8b-instruct-v1:0",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "tell me a riddle"
    }
  ],
  "sampling_params": {
     "strategy": {
        "type": "top_p",
        "temperature": 0.7,
        "top_p": 0.9
      },
      "max_tokens": 512
  }
}
```
<img width="1488" height="878" alt="image"
src="https://github.com/user-attachments/assets/0d61beec-3869-4a31-8f37-9f554c280b88"
/>
2025-09-11 11:41:53 +02:00
..
cli chore(rename): move llama_stack.distribution to llama_stack.core (#2975) 2025-07-30 23:30:53 -07:00
distribution feat!: Migrate Vector DB IDs to Vector Store IDs (breaking change) (#3253) 2025-09-05 15:40:34 +02:00
files chore(files tests): update files integration tests and fix inline::localfs (#3195) 2025-08-20 14:22:40 -04:00
models chore(test): migrate unit tests from unittest to pytest for system prompt (#2789) 2025-07-18 11:54:02 +02:00
prompts/prompts feat: Adding OpenAI Prompts API (#3319) 2025-09-08 11:05:13 -04:00
providers fix: AWS Bedrock inference profile ID conversion for region-specific endpoints (#3386) 2025-09-11 11:41:53 +02:00
rag fix: pre-commit issues: non executable shebang file and removal of @pytest.mark.asyncio decorator (#3397) 2025-09-10 15:27:35 +02:00
registry chore(rename): move llama_stack.distribution to llama_stack.core (#2975) 2025-07-30 23:30:53 -07:00
server feat: Add Kubernetes auth provider to use SelfSubjectReview and kubernetes api server (#2559) 2025-09-08 11:25:10 +02:00
utils chore: introduce write queue for inference_store (#3383) 2025-09-10 11:57:42 -07:00
__init__.py chore: Add fixtures to conftest.py (#2067) 2025-05-06 13:57:48 +02:00
conftest.py chore: block network access from unit tests (#2732) 2025-07-12 16:53:54 -07:00
fixtures.py chore(rename): move llama_stack.distribution to llama_stack.core (#2975) 2025-07-30 23:30:53 -07:00
README.md test: Measure and track code coverage (#2636) 2025-07-18 18:08:36 +02:00

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

  1. Python Environment: Ensure you have Python 3.12+ installed
  2. uv Package Manager: Install uv if 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=auto for 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_VERSION environment 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