github-featured/openai--openai-agents-python
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
efa88f79e759b17e65572919239cf9593ac2f686
openai--openai-agents-python/tests
T
History
Rohan Mehta efa88f79e7 Wait for input guardrails in streaming runs (#1730)
2025-09-12 18:29:39 -04:00
..
extensions/memory
Add SQLAlchemy session backend for conversation history management (#1357)
2025-08-21 23:10:30 +09:00
fastapi
Start and finish streaming trace in impl metod (#540)
2025-04-21 13:08:38 -04:00
mcp
feat: add retry logic to MCP server operations (#1554)
2025-08-21 17:02:55 -04:00
model_settings
Fix #1407 Add reasoning.effort="minimal" and "verbosity" params to ModelSettings (#1439)
2025-08-13 10:00:13 -04:00
models
Fix #1564 Add conversations API support (#1587)
2025-08-29 10:06:36 -04:00
realtime
feat: #1614 gpt-realtime migration (Realtime API GA) (#1646)
2025-09-11 13:56:20 -04:00
tracing
Fix set_api_key breaking cached property mechanism (#1339)
2025-08-01 20:08:22 +09:00
utils
Fix a bug where debug logging fails with Iterable objects (#1683)
2025-09-11 13:57:57 -04:00
voice
feat: #1614 gpt-realtime migration (Realtime API GA) (#1646)
2025-09-11 13:56:20 -04:00
__init__.py
Initial commit
2025-03-11 09:42:28 -07:00
conftest.py
feat: #1614 gpt-realtime migration (Realtime API GA) (#1646)
2025-09-11 13:56:20 -04:00
fake_model.py
Fix #1564 Add conversations API support (#1587)
2025-08-29 10:06:36 -04:00
README.md
Pretty print result classes
2025-03-17 11:11:39 -04:00
test_agent_as_tool.py
Add conditional tool enabling feature to agent as tool. (#1193)
2025-08-15 19:44:17 -04:00
test_agent_clone_shallow_copy.py
Fix: Emit tool_called events immediately in streaming runs (#1300)
2025-08-25 10:48:32 +09:00
test_agent_config.py
Added runtime validation for Agent constructor arguments (#998)
2025-08-11 17:05:30 -04:00
test_agent_hooks.py
Fix typos and misspellings (#486)
2025-04-14 10:37:13 -04:00
test_agent_instructions_signature.py
Wait for input guardrails in streaming runs (#1730)
2025-09-12 18:29:39 -04:00
test_agent_llm_hooks.py
feat(agents): Add on_llm_start and on_llm_end Lifecycle Hooks (#987)
2025-08-16 06:01:42 +00:00
test_agent_prompt.py
Fix #1564 Add conversations API support (#1587)
2025-08-29 10:06:36 -04:00
test_agent_runner_streamed.py
Wait for input guardrails in streaming runs (#1730)
2025-09-12 18:29:39 -04:00
test_agent_runner.py
Prevent preamble messages from being treated as final output when tool calls are pending (#1689)
2025-09-09 16:00:38 +09:00
test_agent_tracing.py
More fetch_normalized_spans
2025-03-21 18:31:06 +02:00
test_anthropic_thinking_blocks.py
fix: #1704 Preserve thinking blocks in Anthropic conversations with tool calls (#1706)
2025-09-12 14:45:32 +09:00
test_call_model_input_filter_unit.py
Allow modifying the input sent to the model (#1483)
2025-08-14 20:06:29 -04:00
test_call_model_input_filter.py
Allow modifying the input sent to the model (#1483)
2025-08-14 20:06:29 -04:00
test_cancel_streaming.py
More tests for cancelling streamed run (#590)
2025-04-24 14:45:03 -04:00
test_computer_action.py
Add safety check handling for ComputerTool (#923)
2025-06-27 14:32:34 -04:00
test_config.py
make format
2025-03-11 14:54:10 -07:00
test_debug.py
Fix a bug where the default behavior of loading the debug flag differs from the documentation (#1682)
2025-09-08 10:05:25 -04:00
test_doc_parsing.py
Initial commit
2025-03-11 09:42:28 -07:00
test_extension_filters.py
Fix #1238 by enhancing HandoffInputData and enable passing async functions (#1302)
2025-07-30 13:17:15 -04:00
test_extra_headers.py
Fix #1564 Add conversations API support (#1587)
2025-08-29 10:06:36 -04:00
test_function_schema.py
feat(function_schema): Add support for pydantic Field annotations in tool arguments (for tools decorated with @function_schema) (#1124)
2025-07-15 11:35:54 -04:00
test_function_tool_decorator.py
Retry: Add tool_name to ToolContext for generic tool handlers (#1110)
2025-07-15 11:37:38 -04:00
test_function_tool.py
Retry: Add tool_name to ToolContext for generic tool handlers (#1110)
2025-07-15 11:37:38 -04:00
test_global_hooks.py
fix typos in tests
2025-03-20 11:24:15 +01:00
test_guardrails.py
Initial commit
2025-03-11 09:42:28 -07:00
test_handoff_tool.py
Fix #1238 by enhancing HandoffInputData and enable passing async functions (#1302)
2025-07-30 13:17:15 -04:00
test_items_helpers.py
Make shallow copies of lists instead of deep copies (#1490)
2025-08-15 11:22:13 -04:00
test_logprobs.py
Add logprobs to ModelSettings (#971)
2025-08-11 13:59:44 +09:00
test_max_turns.py
Initial commit
2025-03-11 09:42:28 -07:00
test_model_payload_iterators.py
Fix a bug where debug logging fails with Iterable objects (#1683)
2025-09-11 13:57:57 -04:00
test_openai_chatcompletions_converter.py
chore(deps): Bump "openai>=1.99.6,<2" (#1415)
2025-08-11 10:57:04 -04:00
test_openai_chatcompletions_stream.py
Fix #1564 Add conversations API support (#1587)
2025-08-29 10:06:36 -04:00
test_openai_chatcompletions.py
Fix #1564 Add conversations API support (#1587)
2025-08-29 10:06:36 -04:00
test_openai_responses_converter.py
Fix #1592 Web search tool updates (#1601)
2025-08-28 23:20:00 +00:00
test_output_tool.py
Allow replacing AgentRunner and TraceProvider (#720)
2025-06-17 17:41:10 -07:00
test_pretty_print.py
Pretty print result classes
2025-03-17 11:11:39 -04:00
test_reasoning_content.py
Fix #1564 Add conversations API support (#1587)
2025-08-29 10:06:36 -04:00
test_repl.py
Add REPL run_demo_loop helper (#811)
2025-06-04 11:53:17 -04:00
test_responses_tracing.py
Fix #1564 Add conversations API support (#1587)
2025-08-29 10:06:36 -04:00
test_responses.py
Added support for passing tool_call_id via the RunContextWrapper (#766)
2025-06-09 11:08:50 -04:00
test_result_cast.py
Add usage to context in streaming (#595)
2025-04-24 18:20:35 -04:00
test_run_config.py
Feature: Make trace_include_sensitive_data configurable via environment variable (#1192)
2025-08-26 21:27:49 +09:00
test_run_error_details.py
Don't cache agent tools during a run (#803)
2025-06-02 14:49:16 -04:00
test_run_hooks.py
fix(run): fire on_llm_start / on_llm_end in Runner.run() for streaming & non-streaming (aligns with docs) (#1619)
2025-09-02 12:32:17 +09:00
test_run_step_execution.py
Add is_enabled to handoffs (#925)
2025-06-24 10:53:33 -04:00
test_run_step_processing.py
Fix #968 by upgrading openai package to the latest (#1034)
2025-07-12 10:59:47 +09:00
test_run.py
Allow replacing AgentRunner and TraceProvider (#720)
2025-06-17 17:41:10 -07:00
test_session_exceptions.py
Realtime: only update model settings from session (#1169)
2025-07-17 13:04:02 -04:00
test_session.py
Wait for input guardrails in streaming runs (#1730)
2025-09-12 18:29:39 -04:00
test_stream_events.py
fix(streaming): #1712 push processed_response.new_items (including HandoffCallItem) to event_queue (#1703)
2025-09-12 14:28:53 +09:00
test_streaming_tool_call_arguments.py
Fix #1629 Empty tool call arguments in streaming events (#1636)
2025-09-03 06:43:37 +09:00
test_strict_schema.py
Initial commit
2025-03-11 09:42:28 -07:00
test_tool_choice_reset.py
Make the reset behavior on tool use configurable
2025-03-25 13:29:32 -04:00
test_tool_converter.py
Extract chat completions conversion code into helper (#522)
2025-04-15 18:31:17 -04:00
test_tool_use_behavior.py
Introduce tool_use_behavior on agents
2025-03-18 21:55:12 -04:00
test_trace_processor.py
Initial commit
2025-03-11 09:42:28 -07:00
test_tracing_errors_streamed.py
Added RunErrorDetails object for MaxTurnsExceeded exception (#743)
2025-05-29 16:11:33 -04:00
test_tracing_errors.py
Convert MCP schemas to strict where possible (#414)
2025-04-01 16:50:13 -04:00
test_tracing.py
More fetch_normalized_spans
2025-03-21 18:31:06 +02:00
test_usage.py
Dev/add usage details to Usage class (#726)
2025-05-20 18:23:56 +01:00
test_visualization.py
feat(viz): draw MCP servers (#1368)
2025-08-04 22:35:07 +00:00
testing_processor.py
More fetch_normalized_spans
2025-03-21 18:31:06 +02:00

README.md

Tests

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

Running tests

make tests

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-update
Reference in New Issue View Git Blame Copy Permalink