Kathy WuandCopybara-Service 7478bdaa98 fix: Parallelize tool resolution in LlmAgent.canonical_tools() ...

Previously we resolved tools sequentially by awaiting _convert_tool_union_to_tools() in a loop -- reduce the latency by resolving tools concurrently.

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 872979105

2026-02-20 10:45:18 -08:00

..

__init__.py

…

test_agent_clone.py

…

test_agent_config.py

…

test_base_agent.py

…

test_callback_context.py

…

test_context_cache_config.py

…

test_context.py

…

test_gemini_context_cache_manager.py

…

test_invocation_context.py

…

test_langgraph_agent.py

…

test_live_request_queue.py

…

test_llm_agent_callbacks.py

…

test_llm_agent_error_messages.py

…

test_llm_agent_fields.py

…

test_llm_agent_include_contents.py

…

test_llm_agent_output_save.py

…

test_loop_agent.py

…

test_mcp_instruction_provider.py

…

test_model_callback_chain.py

…

test_parallel_agent.py

…

test_readonly_context.py

…

test_remote_a2a_agent.py

…

test_resumable_llm_agent.py

…

test_run_config.py

…

test_sequential_agent.py

…