Skip to content

tests

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History
 
 

tests

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
extensions
extensions
 
 
fastapi
fastapi
 
 
mcp
mcp
 
 
memory
memory
 
 
model_settings
model_settings
 
 
models
models
 
 
realtime
realtime
 
 
sandbox
sandbox
 
 
tracing
tracing
 
 
utils
utils
 
 
voice
voice
 
 
README.md
README.md
 
 
__init__.py
__init__.py
 
 
conftest.py
conftest.py
 
 
fake_model.py
fake_model.py
 
 
test_agent_as_tool.py
test_agent_as_tool.py
 
 
test_agent_clone_shallow_copy.py
test_agent_clone_shallow_copy.py
 
 
test_agent_config.py
test_agent_config.py
 
 
test_agent_hooks.py
test_agent_hooks.py
 
 
test_agent_instructions_signature.py
test_agent_instructions_signature.py
 
 
test_agent_llm_hooks.py
test_agent_llm_hooks.py
 
 
test_agent_memory_leak.py
test_agent_memory_leak.py
 
 
test_agent_prompt.py
test_agent_prompt.py
 
 
test_agent_runner.py
test_agent_runner.py
 
 
test_agent_runner_streamed.py
test_agent_runner_streamed.py
 
 
test_agent_runner_sync.py
test_agent_runner_sync.py
 
 
test_agent_tool_input.py
test_agent_tool_input.py
 
 
test_agent_tool_state.py
test_agent_tool_state.py
 
 
test_agent_tracing.py
test_agent_tracing.py
 
 
test_agents_logging.py
test_agents_logging.py
 
 
test_anthropic_thinking_blocks.py
test_anthropic_thinking_blocks.py
 
 
test_apply_diff.py
test_apply_diff.py
 
 
test_apply_diff_helpers.py
test_apply_diff_helpers.py
 
 
test_apply_patch_tool.py
test_apply_patch_tool.py
 
 
test_asyncio_progress.py
test_asyncio_progress.py
 
 
test_call_model_input_filter.py
test_call_model_input_filter.py
 
 
test_call_model_input_filter_unit.py
test_call_model_input_filter_unit.py
 
 
test_cancel_streaming.py
test_cancel_streaming.py
 
 
test_computer_action.py
test_computer_action.py
 
 
test_computer_tool_lifecycle.py
test_computer_tool_lifecycle.py
 
 
test_config.py
test_config.py
 
 
test_custom_tool.py
test_custom_tool.py
 
 
test_debug.py
test_debug.py
 
 
test_doc_parsing.py
test_doc_parsing.py
 
 
test_example_workflows.py
test_example_workflows.py
 
 
test_extended_thinking_message_order.py
test_extended_thinking_message_order.py
 
 
test_extension_filters.py
test_extension_filters.py
 
 
test_extra_headers.py
test_extra_headers.py
 
 
test_function_schema.py
test_function_schema.py
 
 
test_function_tool.py
test_function_tool.py
 
 
test_function_tool_decorator.py
test_function_tool_decorator.py
 
 
test_gemini_thought_signatures.py
test_gemini_thought_signatures.py
 
 
test_gemini_thought_signatures_stream.py
test_gemini_thought_signatures_stream.py
 
 
test_global_hooks.py
test_global_hooks.py
 
 
test_guardrails.py
test_guardrails.py
 
 
test_handoff_history_duplication.py
test_handoff_history_duplication.py
 
 
test_handoff_prompt.py
test_handoff_prompt.py
 
 
test_handoff_tool.py
test_handoff_tool.py
 
 
test_hitl_error_scenarios.py
test_hitl_error_scenarios.py
 
 
test_hitl_session_scenario.py
test_hitl_session_scenario.py
 
 
test_hitl_utils.py
test_hitl_utils.py
 
 
test_items_helpers.py
test_items_helpers.py
 
 
test_local_shell_tool.py
test_local_shell_tool.py
 
 
test_logprobs.py
test_logprobs.py
 
 
test_max_turns.py
test_max_turns.py
 
 
test_model_payload_iterators.py
test_model_payload_iterators.py
 
 
test_model_retry.py
test_model_retry.py
 
 
test_openai_chatcompletions.py
test_openai_chatcompletions.py
 
 
test_openai_chatcompletions_converter.py
test_openai_chatcompletions_converter.py
 
 
test_openai_chatcompletions_stream.py
test_openai_chatcompletions_stream.py
 
 
test_openai_client_utils.py
test_openai_client_utils.py
 
 
test_openai_conversations_session.py
test_openai_conversations_session.py
 
 
test_openai_responses.py
test_openai_responses.py
 
 
test_openai_responses_converter.py
test_openai_responses_converter.py
 
 
test_output_tool.py
test_output_tool.py
 
 
test_pr_labels.py
test_pr_labels.py
 
 
test_pretty_print.py
test_pretty_print.py
 
 
test_process_model_response.py
test_process_model_response.py
 
 
test_prompt_cache_key.py
test_prompt_cache_key.py
 
 
test_reasoning_content.py
test_reasoning_content.py
 
 
test_remove_openai_responses_api_incompatible_fields.py
test_remove_openai_responses_api_incompatible_fields.py
 
 
test_repl.py
test_repl.py
 
 
test_responses.py
test_responses.py
 
 
test_responses_tracing.py
test_responses_tracing.py
 
 
test_responses_websocket_session.py
test_responses_websocket_session.py
 
 
test_result_cast.py
test_result_cast.py
 
 
test_run.py
test_run.py
 
 
test_run_config.py
test_run_config.py
 
 
test_run_context_approvals.py
test_run_context_approvals.py
 
 
test_run_context_wrapper.py
test_run_context_wrapper.py
 
 
test_run_error_details.py
test_run_error_details.py
 
 
test_run_hooks.py
test_run_hooks.py
 
 
test_run_impl_resume_paths.py
test_run_impl_resume_paths.py
 
 
test_run_internal_error_handlers.py
test_run_internal_error_handlers.py
 
 
test_run_internal_items.py
test_run_internal_items.py
 
 
test_run_state.py
test_run_state.py
 
 
test_run_step_execution.py
test_run_step_execution.py
 
 
test_run_step_processing.py
test_run_step_processing.py
 
 
test_runner_guardrail_resume.py
test_runner_guardrail_resume.py
 
 
test_sandbox_memory.py
test_sandbox_memory.py
 
 

README.md

Tests

Before running any tests, make sure you have uv installed (and ideally run make sync after).

Running tests

make tests

make tests runs the shard-safe suite in parallel and then runs tests marked serial in a separate serial pass.

Snapshots

We use inline-snapshots for some tests. If your code adds new snapshot tests or breaks existing ones, you can fix/create them. After fixing/creating snapshots, run make tests again to verify the tests pass.

Fixing snapshots

make snapshots-fix

Creating snapshots

make snapshots-create