mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-11 05:38:38 +00:00
feat(tests): make inference_recorder into api_recorder (include tool_invoke) (#3403)
Renames `inference_recorder.py` to `api_recorder.py` and extends it to support recording/replaying tool invocations in addition to inference calls. This allows us to record web-search, etc. tool calls and thereafter apply recordings for `tests/integration/responses` ## Test Plan ``` export OPENAI_API_KEY=... export TAVILY_SEARCH_API_KEY=... ./scripts/integration-tests.sh --stack-config ci-tests \ --suite responses --inference-mode record-if-missing ```
This commit is contained in:
parent
26fd5dbd34
commit
f50ce11a3b
284 changed files with 296191 additions and 631 deletions
|
@ -30,7 +30,7 @@ Options:
|
|||
--stack-config STRING Stack configuration to use (required)
|
||||
--suite STRING Test suite to run (default: 'base')
|
||||
--setup STRING Test setup (models, env) to use (e.g., 'ollama', 'ollama-vision', 'gpt', 'vllm')
|
||||
--inference-mode STRING Inference mode: record or replay (default: replay)
|
||||
--inference-mode STRING Inference mode: replay, record-if-missing or record (default: replay)
|
||||
--subdirs STRING Comma-separated list of test subdirectories to run (overrides suite)
|
||||
--pattern STRING Regex pattern to pass to pytest -k
|
||||
--collect-only Collect tests only without running them (skips server startup)
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue