mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
# What does this PR do? PR fixes couple of issues with telemetry: 1) The REST refactor changed the method from get_span_tree to query_span_tree, which is causing the server side to return empty spans 2) Library client has introduced a new event loop, which required changing the location of where start and end trace are called ## Test Plan LLAMA_STACK_CONFIG="/Users/dineshyv/.llama/distributions/llamastack-fireworks/fireworks-run.yaml" pytest -v tests/client-sdk/agents/test_agents.py -k "test_builtin_tool_web_search" And querying for spans from the agent run using the library client. |
||
|---|---|---|
| .. | ||
| routers | ||
| server | ||
| store | ||
| ui | ||
| utils | ||
| __init__.py | ||
| build.py | ||
| build_conda_env.sh | ||
| build_container.sh | ||
| build_venv.sh | ||
| client.py | ||
| common.sh | ||
| configure.py | ||
| configure_container.sh | ||
| datatypes.py | ||
| distribution.py | ||
| inspect.py | ||
| library_client.py | ||
| request_headers.py | ||
| resolver.py | ||
| stack.py | ||
| start_conda_env.sh | ||
| start_container.sh | ||