ehhuang 386c806c70 test: introduce recordable mocks for Agent tests (#1268) ... Summary: Agent tests shouldn't need to run inference and tools calls repeatedly. This PR introduces a way to record inference/tool calls and reuse them in subsequent test runs, which makes the tests more reliable and saves costs. Test Plan: Run when there's no recorded calls created (fails): ``` LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B ``` Run when `--record-responses` to record calls: ``` LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --record-responses ``` Run without `--record-responses` again (succeeds): ``` LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B ```		2025-03-03 14:48:32 -08:00
..
client-sdk	test: introduce recordable mocks for Agent tests (#1268)	2025-03-03 14:48:32 -08:00
test_logcat.py	feat: add a configurable category-based logger (#1352)	2025-03-02 18:51:14 -08:00
test_replace_env_vars.py	feat: allow conditionally enabling providers in run.yaml (#1321)	2025-03-01 11:19:14 -08:00