ehhuang 6cf79437b3 feat: support ClientTool output metadata (#1426) ... # Summary: Client side change in https://github.com/meta-llama/llama-stack-client-python/pull/180 Changes the resume_turn API to accept `ToolResponse` instead of `ToolResponseMessage`: 1. `ToolResponse` contains `metadata` 2. `ToolResponseMessage` is a concept for model inputs. Here we are just submitting the outputs of tool execution. # Test Plan: Ran integration tests with newly added test using client tool with metadata LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/integration/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --record-responses		2025-03-05 14:30:27 -08:00
..
agents	feat: support ClientTool output metadata (#1426)	2025-03-05 14:30:27 -08:00
datasetio	build: format codebase imports using ruff linter (#1028)	2025-02-13 10:06:21 -08:00
eval	chore: rename task_config to benchmark_config (#1397)	2025-03-04 12:44:04 -08:00
inference	refactor: move generation.py to llama3	2025-03-03 13:50:19 -08:00
ios/inference	chore: removed executorch submodule (#1265)	2025-02-25 21:57:21 -08:00
post_training	fix: replace eval with json decoding for format_adapter (#1328)	2025-02-28 11:25:23 -08:00
safety	chore: move all Llama Stack types from llama-models to llama-stack (#1098)	2025-02-14 09:10:59 -08:00
scoring	fix: regex parser to support more answer formats (#1425)	2025-03-05 11:52:07 -08:00
telemetry	feat: record token usage for inference API (#1300)	2025-03-05 12:41:45 -08:00
tool_runtime	chore: remove dependency on llama_models completely (#1344)	2025-03-01 12:48:08 -08:00
vector_io	refactor(test): unify vector_io tests and make them configurable (#1398)	2025-03-04 13:37:45 -08:00
__init__.py	impls -> inline, adapters -> remote (#381)	2024-11-06 14:54:05 -08:00