ehhuang 07a992ef90 feat: deterministic tools ordering (#1380) ... Summary: 1. The `tools` parameter we construct to pass the inference API is non-deterministic. As a result, our recordable mocks is flaky as the ordering change sometimes. This PR makes it so that `tools` ordering is deterministic and aligned with the order user specified. 2. In recordable mock key generation, client tool's parameter type was 'str' and now is 'string' for some reason. I didn't dig into exactly why, but just regenerated the fixtures. Test Plan: Regenerate mocks: ``` LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --record-responses ``` Rerun tests without --record-responses: ``` 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 20:38:07 -08:00
..
tests	chore: move all Llama Stack types from llama-models to llama-stack (#1098)	2025-02-14 09:10:59 -08:00
__init__.py	Fix precommit check after moving to ruff (#927)	2025-02-02 06:46:45 -08:00
agent_instance.py	feat: deterministic tools ordering (#1380)	2025-03-03 20:38:07 -08:00
agents.py	feat: ability to retrieve agents session, turn, step by ids (#1286)	2025-02-27 09:45:14 -08:00
config.py	Auto-generate distro yamls + docs (#468)	2024-11-18 14:57:06 -08:00
persistence.py	feat: unify max_infer_iters in client/server agent loop (#1309)	2025-03-03 10:08:36 -08:00
safety.py	build: configure ruff from pyproject.toml (#1100)	2025-02-14 09:01:57 -08:00