openai/openai-agents-python

27.8

Adjusted Score

27.8

Raw Score

100%

Time Factor

2026-07-14

Last Push

27.9K

Stars

Python

Language

331.6K

Lines of Code

1.3K

Files

8.6K

Pattern Hits

2026-07-14

Scan Date

0.15

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 1HIGH 198MEDIUM 474LOW 7894

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 8567 distinct pattern matches across 23 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers5600 hits · 4796 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_run_error_details.py	12	async def test_run_error_includes_data():	CODE
LOW	tests/test_run_error_details.py	31	async def test_streamed_run_error_includes_data():	CODE
LOW	tests/test_tool_use_tracker.py	20	def test_tool_use_tracker_as_serializable_uses_agent_map_or_runtime_snapshot() -> None:	CODE
LOW	tests/test_tool_use_tracker.py	31	def test_tool_use_tracker_from_and_serialize_snapshots() -> None:	CODE
LOW	tests/test_tool_use_tracker.py	42	def test_serialize_and_hydrate_tool_use_tracker_preserves_duplicate_agent_identity() -> None:	CODE
LOW	tests/test_tool_use_tracker.py	54	def get_tool_use_tracker_snapshot(self) -> dict[str, list[str]]:	CODE
LOW	tests/test_tool_use_tracker.py	67	def test_tool_use_tracker_handles_literal_suffix_names_without_collision() -> None:	CODE
LOW	tests/test_tool_use_tracker.py	82	def get_tool_use_tracker_snapshot(self) -> dict[str, list[str]]:	CODE
LOW	tests/test_tool_use_tracker.py	95	def test_record_used_tools_uses_trace_names_for_namespaced_and_deferred_functions() -> None:	CODE
LOW	tests/test_tool_use_tracker.py	133	def test_record_processed_response_ignores_hosted_tool_search_for_resets():	CODE
LOW	tests/test_tool_use_tracker.py	161	def test_record_processed_response_keeps_function_named_tool_search():	CODE
LOW	tests/test_tool_use_tracker.py	189	def test_record_processed_response_counts_output_only_tools_without_shifting_names() -> None:	CODE
LOW	tests/test_tool_use_tracker.py	224	def test_hydrate_tool_use_tracker_skips_unknown_agents() -> None:	CODE
LOW	tests/test_tool_use_tracker.py	226	def get_tool_use_tracker_snapshot(self) -> dict[str, list[str]]:	CODE
LOW	tests/test_handoff_prompt.py	7	def test_prompt_with_handoff_instructions_includes_prefix() -> None:	CODE
LOW	tests/test_tool_metadata.py	36	def test_tool_name_properties() -> None:	CODE
LOW	tests/test_tool_metadata.py	56	def test_shell_command_output_status_property() -> None:	CODE
LOW	tests/test_tool_metadata.py	61	def test_tool_context_from_agent_context() -> None:	CODE
LOW	tests/test_asyncio_progress.py	12	async def test_function_tool_task_progress_deadline_detects_timer_backed_sleep() -> None:	CODE
LOW	tests/test_asyncio_progress.py	37	async def test_function_tool_task_progress_deadline_returns_none_for_external_wait() -> None:	CODE
LOW	tests/test_asyncio_progress.py	61	async def test_function_tool_task_progress_deadline_can_follow_tracked_invoke_task() -> None:	CODE
LOW	tests/test_asyncio_progress.py	95	async def test_function_tool_task_progress_deadline_can_follow_awaited_child_task() -> None:	CODE
LOW	tests/test_asyncio_progress.py	121	async def test_function_tool_task_progress_deadline_can_follow_shielded_child_task() -> None:	CODE
LOW	tests/test_asyncio_progress.py	147	async def test_function_tool_task_progress_deadline_can_follow_gathered_child_tasks() -> None:	CODE
LOW	tests/test_asyncio_progress.py	172	async def test_function_tool_task_progress_deadline_can_follow_timer_backed_future() -> None:	CODE
LOW	tests/test_asyncio_progress.py	177	async def _timer_backed_future_task() -> None:	CODE
LOW	tests/test_run_config.py	28	async def test_model_provider_on_run_config_is_used_for_agent_model_name() -> None:	CODE
LOW	tests/test_run_config.py	45	async def test_run_config_model_name_override_takes_precedence() -> None:	CODE
LOW	tests/test_run_config.py	65	async def test_run_config_model_name_override_uses_model_specific_default_settings(	CODE
LOW	tests/test_run_config.py	88	async def test_run_config_model_settings_override_implicit_model_specific_defaults(	CODE
LOW	tests/test_run_config.py	113	async def test_run_config_model_override_object_takes_precedence() -> None:	CODE
LOW	tests/test_run_config.py	127	async def test_agent_model_object_is_used_when_present() -> None:	CODE
LOW	tests/test_run_config.py	144	def test_trace_include_sensitive_data_defaults_to_true_when_env_not_set(monkeypatch):	CODE
LOW	tests/test_run_config.py	178	def test_trace_include_sensitive_data_follows_env_value(env_value, expected, monkeypatch):	CODE
LOW	tests/test_run_config.py	185	def test_trace_include_sensitive_data_explicit_override_takes_precedence(monkeypatch):	CODE
LOW⚡	tests/test_run_config.py	196	def test_tool_execution_config_rejects_invalid_function_tool_concurrency() -> None:	CODE
LOW⚡	tests/test_run_config.py	204	def test_tool_execution_config_is_public_from_agents_package() -> None:	CODE
LOW⚡	tests/test_run_config.py	211	def test_tool_not_found_behavior_defaults_to_raise_error() -> None:	CODE
LOW⚡	tests/test_run_config.py	217	def test_tool_not_found_behavior_is_public_from_agents_package() -> None:	CODE
LOW	tests/test_oaiconv_resume_response_id.py	18	def test_hydrate_from_state_uses_latest_non_none_response_id() -> None:	CODE
LOW	tests/test_shell_call_serialization.py	13	def test_coerce_shell_call_reads_max_output_length() -> None:	CODE
LOW⚡	tests/test_shell_call_serialization.py	26	def test_coerce_shell_call_requires_commands() -> None:	CODE
LOW⚡	tests/test_shell_call_serialization.py	33	def test_coerce_shell_call_rejects_string_like_commands(commands: object) -> None:	CODE
LOW⚡	tests/test_shell_call_serialization.py	42	def test_normalize_shell_output_handles_timeout() -> None:	CODE
LOW	tests/test_shell_call_serialization.py	54	def test_normalize_shell_output_converts_string_outcome() -> None:	CODE
LOW	tests/test_shell_call_serialization.py	67	def test_serialize_shell_output_emits_canonical_outcome() -> None:	CODE
LOW	tests/test_shell_call_serialization.py	79	def test_shell_rejection_payload_preserves_missing_exit_code() -> None:	CODE
LOW	tests/test_shell_call_serialization.py	105	def test_shell_output_preserves_zero_exit_code() -> None:	CODE
LOW	tests/test_tracing_errors.py	34	async def test_single_turn_model_error():	CODE
LOW	tests/test_tracing_errors.py	75	async def test_multi_turn_no_handoffs():	CODE
LOW	tests/test_tracing_errors.py	208	async def test_multiple_handoff_doesnt_error():	CODE
LOW	tests/test_tracing_errors.py	298	async def test_multiple_final_output_doesnt_error():	CODE
LOW	tests/test_tracing_errors.py	334	async def test_handoffs_lead_to_correct_agent_spans():	CODE
LOW	tests/test_agent_instructions_signature.py	17	async def test_valid_async_signature_passes(self, mock_run_context):	CODE
LOW	tests/test_agent_instructions_signature.py	28	async def test_valid_sync_signature_passes(self, mock_run_context):	CODE
LOW	tests/test_agent_instructions_signature.py	39	async def test_one_parameter_raises_error(self, mock_run_context):	CODE
LOW	tests/test_agent_instructions_signature.py	54	async def test_three_parameters_raises_error(self, mock_run_context):	CODE
LOW	tests/test_agent_instructions_signature.py	69	async def test_zero_parameters_raises_error(self, mock_run_context):	CODE
LOW	tests/test_agent_instructions_signature.py	84	async def test_function_with_args_kwargs_fails(self, mock_run_context):	CODE
LOW⚡	tests/test_agent_instructions_signature.py	99	async def test_string_instructions_still_work(self, mock_run_context):	CODE
5540 more matches not shown…

Unused Imports1318 hits · 1050 pts

Severity	File	Line	Context
LOW	tests/test_tool_use_tracker.py	1	CODE
LOW	tests/test_tool_metadata.py	1	CODE
LOW	tests/test_asyncio_progress.py	1	CODE
LOW	tests/test_run_config.py	1	CODE
LOW	tests/test_shell_call_serialization.py	1	CODE
LOW	tests/test_tracing_errors.py	1	CODE
LOW	tests/testing_processor.py	1	CODE
LOW	tests/conftest.py	1	CODE
LOW	tests/test_tool_use_behavior.py	3	CODE
LOW	tests/test_usaspending_setup_db.py	1	CODE
LOW	tests/test_agent_tool_state.py	1	CODE
LOW	tests/test_tool_origin.py	1	CODE
LOW	tests/test_prompt_cache_key.py	1	CODE
LOW	tests/test_tracing.py	1	CODE
LOW	tests/test_agent_memory_leak.py	1	CODE
LOW	tests/test_call_model_input_filter.py	1	CODE
LOW	tests/test_source_compat_constructors.py	1	CODE
LOW	tests/test_output_guardrail_cancellation.py	1	CODE
LOW	tests/test_guardrails.py	1	CODE
LOW	tests/test_hitl_session_scenario.py	1	CODE
LOW	tests/test_tracing_errors_streamed.py	1	CODE
LOW	tests/test_run.py	1	CODE
LOW	tests/test_items_helpers.py	1	CODE
LOW	tests/test_agent_runner_streamed.py	1	CODE
LOW	tests/test_streaming_logging.py	1	CODE
LOW	tests/test_agent_prompt.py	1	CODE
LOW	tests/test_agent_tracing.py	1	CODE
LOW	tests/test_hitl_error_scenarios.py	3	CODE
LOW	tests/test_run_step_processing.py	1	CODE
LOW	tests/test_apply_diff.py	3	CODE
LOW	tests/test_usage.py	1	CODE
LOW	tests/test_agent_tool_input.py	1	CODE
LOW	tests/test_shell_tool.py	1	CODE
LOW	tests/test_agents_logging.py	1	CODE
LOW	tests/test_run_internal_error_handlers.py	1	CODE
LOW	tests/test_agent_runner.py	1	CODE
LOW	tests/test_agent_as_tool.py	1	CODE
LOW	tests/test_call_model_input_filter_unit.py	1	CODE
LOW	tests/test_computer_tool_lifecycle.py	1	CODE
LOW	tests/test_invalid_final_output_handler.py	1	CODE
LOW	tests/test_apply_diff_helpers.py	3	CODE
LOW	tests/test_run_state.py	3	CODE
LOW	tests/test_extension_filters.py	1	CODE
LOW	tests/test_tool_guardrails.py	1	CODE
LOW	tests/test_tool_output_conversion.py	1	CODE
LOW	tests/test_tracing_provider_safe_debug.py	1	CODE
LOW	tests/test_responses.py	1	CODE
LOW	tests/test_daytona_usaspending_example.py	1	CODE
LOW	tests/test_max_turns.py	1	CODE
LOW	tests/test_result_cast.py	1	CODE
LOW	tests/test_global_hooks.py	1	CODE
LOW	tests/test_apply_patch_tool.py	1	CODE
LOW	tests/test_run_examples_script.py	1	CODE
LOW	tests/test_tool_identity.py	9	CODE
LOW	tests/test_tool_custom_data.py	1	CODE
LOW	tests/test_run_step_execution.py	1	CODE
LOW	tests/test_example_workflows.py	1	CODE
LOW	tests/test_streamed_terminal_output_backfill.py	1	CODE
LOW	tests/fake_model.py	1	CODE
LOW	tests/test_run_internal_approvals.py	1	CODE
1258 more matches not shown…

Decorative Section Separators236 hits · 784 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/memory/test_session.py	665	# ============================================================================	COMMENT
MEDIUM⚡	tests/memory/test_session.py	667	# ============================================================================	COMMENT
MEDIUM⚡	tests/memory/test_openai_conversations_session.py	528	# ============================================================================	COMMENT
MEDIUM⚡	tests/memory/test_openai_conversations_session.py	530	# ============================================================================	COMMENT
MEDIUM⚡	tests/extensions/test_tool_output_trimmer.py	82	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/test_tool_output_trimmer.py	84	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/test_tool_output_trimmer.py	113	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/test_tool_output_trimmer.py	115	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/test_tool_output_trimmer.py	160	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/test_tool_output_trimmer.py	162	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/test_tool_output_trimmer.py	571	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/test_tool_output_trimmer.py	573	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/test_tool_output_trimmer.py	17	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/test_tool_output_trimmer.py	19	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/test_tool_output_trimmer.py	52	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/test_tool_output_trimmer.py	54	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/test_tool_output_trimmer.py	513	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/test_tool_output_trimmer.py	515	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_encrypt_session.py	432	# ============================================================================	COMMENT
MEDIUM⚡	tests/extensions/memory/test_encrypt_session.py	434	# ============================================================================	COMMENT
MEDIUM⚡	tests/extensions/memory/test_dapr_session.py	878	# ============================================================================	COMMENT
MEDIUM⚡	tests/extensions/memory/test_dapr_session.py	880	# ============================================================================	COMMENT
MEDIUM⚡	tests/extensions/memory/test_advanced_sqlite_session.py	1604	# ============================================================================	COMMENT
MEDIUM⚡	tests/extensions/memory/test_advanced_sqlite_session.py	1606	# ============================================================================	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	226	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	228	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	372	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	374	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	433	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	435	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	468	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	470	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	587	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	589	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	771	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_mongodb_session.py	773	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	28	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	30	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	256	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	258	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	283	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	285	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	649	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	651	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	697	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/memory/test_mongodb_session.py	699	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/memory/test_redis_session.py	824	# ============================================================================	COMMENT
MEDIUM⚡	tests/extensions/memory/test_redis_session.py	826	# ============================================================================	COMMENT
MEDIUM	tests/extensions/sandbox/test_daytona.py	1620	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/extensions/sandbox/test_daytona.py	1622	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	34	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	36	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	48	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	50	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	752	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	754	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	850	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	852	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	1014	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/extensions/sandbox/test_blaxel.py	1016	# ---------------------------------------------------------------------------	COMMENT
176 more matches not shown…

Cross-File Repetition126 hits · 630 pts

Severity	File	Line	Snippet	Context
HIGH	tests/test_function_tool_decorator.py	0	get the temperature for a given city. args: city: the city to get temperature for. returns: temperature information for	STRING
HIGH	examples/agent_patterns/human_in_the_loop.py	0	get the temperature for a given city. args: city: the city to get temperature for. returns: temperature information for	STRING
HIGH	examples/agent_patterns/human_in_the_loop_stream.py	0	get the temperature for a given city. args: city: the city to get temperature for. returns: temperature information for	STRING
HIGH	tests/memory/test_session.py	0	pop_item skips corrupt newest rows and returns the next valid item.	STRING
HIGH	tests/extensions/memory/test_async_sqlite_session.py	0	pop_item skips corrupt newest rows and returns the next valid item.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	pop_item skips corrupt newest rows and returns the next valid item.	STRING
HIGH	tests/memory/test_session.py	0	pop_item removes corrupt rows and returns none when no valid items remain.	STRING
HIGH	tests/extensions/memory/test_async_sqlite_session.py	0	pop_item removes corrupt rows and returns none when no valid items remain.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	pop_item removes corrupt rows and returns none when no valid items remain.	STRING
HIGH	tests/memory/test_session.py	0	test that session correctly stores and retrieves unicode/non-ascii content.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test that session correctly stores and retrieves unicode/non-ascii content.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test that session correctly stores and retrieves unicode/non-ascii content.	STRING
HIGH	tests/memory/test_session.py	0	test concurrent access to the same session to verify data integrity.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test concurrent access to the same session to verify data integrity.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test concurrent access to the same session to verify data integrity.	STRING
HIGH	tests/memory/test_session.py	0	test that session_settings defaults to empty sessionsettings.	STRING
HIGH	tests/memory/test_openai_conversations_session.py	0	test that session_settings defaults to empty sessionsettings.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test that session_settings defaults to empty sessionsettings.	STRING
HIGH	tests/extensions/memory/test_async_sqlite_session.py	0	test that session_settings defaults to empty sessionsettings.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	test that session_settings defaults to empty sessionsettings.	STRING
HIGH	tests/extensions/memory/test_advanced_sqlite_session.py	0	test that session_settings defaults to empty sessionsettings.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test that session_settings defaults to empty sessionsettings.	STRING
HIGH	tests/memory/test_session.py	0	test that get_items uses session_settings.limit as default.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test that get_items uses session_settings.limit as default.	STRING
HIGH	tests/extensions/memory/test_async_sqlite_session.py	0	test that get_items uses session_settings.limit as default.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	test that get_items uses session_settings.limit as default.	STRING
HIGH	tests/extensions/memory/test_advanced_sqlite_session.py	0	test that get_items uses session_settings.limit as default.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test that get_items uses session_settings.limit as default.	STRING
HIGH	tests/memory/test_session.py	0	test that explicit limit parameter overrides session_settings.	STRING
HIGH	tests/extensions/memory/test_encrypt_session.py	0	test that explicit limit parameter overrides session_settings.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test that explicit limit parameter overrides session_settings.	STRING
HIGH	tests/extensions/memory/test_async_sqlite_session.py	0	test that explicit limit parameter overrides session_settings.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	test that explicit limit parameter overrides session_settings.	STRING
HIGH	tests/extensions/memory/test_advanced_sqlite_session.py	0	test that explicit limit parameter overrides session_settings.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test that explicit limit parameter overrides session_settings.	STRING
HIGH	tests/memory/test_session.py	0	test that runconfig can override session's default settings.	STRING
HIGH	tests/extensions/memory/test_encrypt_session.py	0	test that runconfig can override session's default settings.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test that runconfig can override session's default settings.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	test that runconfig can override session's default settings.	STRING
HIGH	tests/extensions/memory/test_advanced_sqlite_session.py	0	test that runconfig can override session's default settings.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test that runconfig can override session's default settings.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test that different session ids result in isolated conversation histories.	STRING
HIGH	tests/extensions/memory/test_async_sqlite_session.py	0	test that different session ids result in isolated conversation histories.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	test that different session ids result in isolated conversation histories.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test that different session ids result in isolated conversation histories.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test that pop_item returns none on an empty session.	STRING
HIGH	tests/extensions/memory/test_async_sqlite_session.py	0	test that pop_item returns none on an empty session.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	test that pop_item returns none on an empty session.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test that pop_item returns none on an empty session.	STRING
HIGH	tests/extensions/memory/test_dapr_session.py	0	test that adding an empty list of items is a no-op.	STRING
HIGH	tests/extensions/memory/test_async_sqlite_session.py	0	test that adding an empty list of items is a no-op.	STRING
HIGH	tests/extensions/memory/test_sqlalchemy_session.py	0	test that adding an empty list of items is a no-op.	STRING
HIGH	tests/extensions/memory/test_redis_session.py	0	test that adding an empty list of items is a no-op.	STRING
HIGH	docs/context.md	0	fetch the age of the user. call this function to get user's age information.	STRING
HIGH	docs/ja/context.md	0	fetch the age of the user. call this function to get user's age information.	STRING
HIGH	docs/zh/context.md	0	fetch the age of the user. call this function to get user's age information.	STRING
HIGH	docs/ko/context.md	0	fetch the age of the user. call this function to get user's age information.	STRING
HIGH	docs/handoffs.md	0	{recommended_prompt_prefix} <fill in the rest of your prompt here>.	STRING
HIGH	docs/ja/handoffs.md	0	{recommended_prompt_prefix} <fill in the rest of your prompt here>.	STRING
HIGH	docs/zh/handoffs.md	0	{recommended_prompt_prefix} <fill in the rest of your prompt here>.	STRING
66 more matches not shown…

Excessive Try-Catch Wrapping581 hits · 579 pts

Severity	File	Line	Snippet	Context
LOW	tests/memory/test_session.py	44	except Exception:	CODE
LOW	tests/mcp/test_mcp_util.py	911	except Exception:	CODE
LOW⚡	tests/extensions/memory/test_dapr_session.py	678	except Exception:	CODE
LOW	tests/extensions/memory/test_dapr_session.py	296	except Exception:	CODE
LOW	tests/extensions/memory/test_dapr_session.py	613	except Exception:	CODE
LOW	tests/extensions/memory/test_dapr_redis_integration.py	86	except Exception:	CODE
LOW	tests/extensions/memory/test_dapr_redis_integration.py	109	except Exception:	CODE
LOW	tests/extensions/memory/test_sqlalchemy_session.py	458	except Exception as exc:	CODE
LOW	tests/extensions/memory/test_sqlalchemy_session.py	506	except Exception as exc:	CODE
LOW	tests/extensions/memory/test_advanced_sqlite_session.py	1210	except Exception:	CODE
LOW⚡	tests/extensions/memory/test_redis_session.py	467	except Exception:	CODE
LOW⚡	tests/extensions/memory/test_redis_session.py	591	except Exception:	CODE
LOW	tests/extensions/memory/test_redis_session.py	187	except Exception:	CODE
LOW	tests/extensions/memory/test_redis_session.py	414	except Exception:	CODE
LOW	tests/extensions/memory/test_redis_session.py	513	except Exception:	CODE
LOW	tests/extensions/memory/test_redis_session.py	640	except Exception:	CODE
LOW⚡	tests/extensions/sandbox/test_blaxel.py	1558	except Exception:	CODE
MEDIUM	tests/realtime/test_openai_realtime.py	2001	def handler(websocket):	CODE
LOW	tests/realtime/test_openai_realtime.py	2030	except Exception:	CODE
LOW	tests/realtime/test_session.py	665	except Exception: # noqa: S110	CODE
MEDIUM	docs/ja/realtime/quickstart.md	96	print(f"Error: {event.error}")	CODE
MEDIUM	docs/realtime/quickstart.md	92	print(f"Error: {event.error}")	CODE
MEDIUM	docs/zh/realtime/quickstart.md	96	print(f"Error: {event.error}")	CODE
LOW	docs/scripts/translate_docs.py	389	except Exception:	STRING
MEDIUM	docs/scripts/translate_docs.py	498	print("Error: No valid files found to translate")	STRING
MEDIUM	docs/ko/realtime/quickstart.md	96	print(f"Error: {event.error}")	CODE
LOW⚡	examples/memory/dapr_session_example.py	223	except Exception as e:	CODE
MEDIUM⚡	examples/memory/dapr_session_example.py	224	print(f"Error: {e}")	CODE
LOW	examples/memory/dapr_session_example.py	295	except Exception as e:	CODE
LOW⚡	examples/memory/dapr_session_example.py	426	except Exception as e:	CODE
LOW	examples/memory/dapr_session_example.py	458	except Exception:	CODE
LOW	examples/memory/file_hitl_example.py	83	except Exception as exc: # noqa: BLE001	CODE
LOW	examples/memory/file_hitl_example.py	143	except Exception:	CODE
LOW⚡	examples/memory/redis_session_example.py	148	except Exception as e:	CODE
MEDIUM⚡	examples/memory/redis_session_example.py	149	print(f"Error: {e}")	CODE
LOW	examples/memory/redis_session_example.py	175	except Exception as e:	CODE
LOW	examples/memory/mongodb_session_example.py	31	except Exception:	CODE
LOW	examples/financial_research_agent/manager.py	176	except Exception:	CODE
LOW	examples/basic/tool_guardrails.py	140	except Exception as e:	CODE
MEDIUM	examples/basic/tool_guardrails.py	141	print(f"Error: {e}\n")	CODE
LOW	examples/basic/tool_guardrails.py	157	except Exception as e:	CODE
MEDIUM	examples/basic/tool_guardrails.py	158	print(f"Error: {e}\n")	CODE
LOW	examples/basic/non_strict_output_type.py	64	except Exception as e:	CODE
MEDIUM	examples/basic/non_strict_output_type.py	65	print(f"Error (expected): {e}")	CODE
LOW	examples/research_bot/manager.py	102	except Exception:	CODE
LOW	…mples/mcp/streamablehttp_custom_client_example/main.py	129	except Exception as e:	CODE
MEDIUM	…mples/mcp/streamablehttp_custom_client_example/main.py	130	print(f"Error starting Streamable HTTP server: {e}")	CODE
LOW	examples/mcp/streamablehttp_example/server.py	36	except Exception:	CODE
LOW	examples/mcp/streamablehttp_example/main.py	96	except Exception as e:	CODE
MEDIUM	examples/mcp/streamablehttp_example/main.py	97	print(f"Error starting Streamable HTTP server: {e}")	CODE
LOW	examples/mcp/prompt_server/main.py	44	except Exception as e:	CODE
LOW	examples/mcp/prompt_server/main.py	122	except Exception as e:	CODE
MEDIUM	examples/mcp/prompt_server/main.py	123	print(f"Error starting server: {e}")	CODE
LOW	examples/mcp/sse_example/main.py	96	except Exception as e:	CODE
MEDIUM	examples/mcp/sse_example/main.py	97	print(f"Error starting SSE server: {e}")	CODE
LOW	examples/realtime/app/server.py	147	except Exception as e:	CODE
LOW	examples/realtime/app/server.py	385	except Exception:	CODE
LOW	examples/realtime/cli/demo.py	135	except Exception:	CODE
LOW	examples/realtime/cli/demo.py	200	except Exception:	CODE
LOW	examples/realtime/cli/demo.py	316	except Exception as e:	CODE
521 more matches not shown…

Self-Referential Comments132 hits · 414 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_responses_tracing.py	232	# Create an instance of the model	COMMENT
MEDIUM⚡	tests/test_responses_tracing.py	235	# Define a dummy fetch function that returns an async stream with a dummy response	COMMENT
MEDIUM⚡	tests/test_responses_tracing.py	374	# Create an instance of the model	COMMENT
MEDIUM⚡	tests/test_responses_tracing.py	377	# Define a dummy fetch function that returns an async stream with a dummy response	COMMENT
MEDIUM⚡	tests/test_responses_tracing.py	450	# Create an instance of the model	COMMENT
MEDIUM⚡	tests/test_responses_tracing.py	453	# Define a dummy fetch function that returns an async stream with a dummy response	COMMENT
MEDIUM	tests/test_responses_tracing.py	61	# Create an instance of the model	COMMENT
MEDIUM	tests/test_responses_tracing.py	125	# Create an instance of the model	COMMENT
MEDIUM	tests/test_responses_tracing.py	191	# Create an instance of the model	COMMENT
MEDIUM⚡	tests/test_items_helpers.py	201	# Create a non-message run item of a different type, e.g., a reasoning trace.	COMMENT
MEDIUM	tests/test_agent_runner_streamed.py	1696	# Create a tool that requires approval	COMMENT
MEDIUM	tests/test_hitl_error_scenarios.py	575	# Create the tool with needs_approval directly	COMMENT
MEDIUM	tests/test_usage.py	254	# Create a usage with request_usage_entries	COMMENT
MEDIUM	tests/test_agent_runner.py	4595	# Define a tool that will be called by the orchestrator agent	COMMENT
MEDIUM	tests/test_agent_runner.py	4683	# Create a computer tool (not a FunctionTool)	COMMENT
MEDIUM	tests/test_agent_runner.py	4725	# Create an approved tool call for the computer tool	COMMENT
MEDIUM	tests/test_agent_runner.py	4757	# Create a rejected tool call	COMMENT
MEDIUM	tests/test_agent_runner.py	4901	# Create a tool call with unclear status (neither approved nor rejected)	COMMENT
MEDIUM	tests/test_agent_runner.py	4924	# Create an approved tool call for a tool that doesn't exist	COMMENT
MEDIUM	tests/test_agent_as_tool.py	61	# Create a simple agent	COMMENT
MEDIUM	tests/test_agent_as_tool.py	109	# Create a simple agent	COMMENT
MEDIUM	tests/test_agent_as_tool.py	157	# Create a simple agent	COMMENT
MEDIUM	tests/test_agent_as_tool.py	220	# Create a simple agent	COMMENT
MEDIUM	tests/test_computer_action.py	542	# Create a dummy click action to trigger a click and screenshot.	COMMENT
MEDIUM⚡	tests/test_run_state.py	3374	# Create a tool call item	COMMENT
MEDIUM⚡	tests/test_run_state.py	3384	# Create a ProcessedResponse with the tool call item in new_items	COMMENT
MEDIUM⚡	tests/test_run_state.py	3467	# Create a tool call item	COMMENT
MEDIUM⚡	tests/test_run_state.py	3477	# Create a ProcessedResponse with the tool call item	COMMENT
MEDIUM⚡	tests/test_run_state.py	5100	# Create a tool call item	COMMENT
MEDIUM⚡	tests/test_run_state.py	5110	# Create a ProcessedResponse	COMMENT
MEDIUM⚡	tests/test_run_state.py	5130	# Create a tool call item	COMMENT
MEDIUM⚡	tests/test_run_state.py	5140	# Create a ProcessedResponse	COMMENT
MEDIUM⚡	tests/test_run_state.py	5229	# Create a mock MCP tool that will be recognized as HostedMCPTool	COMMENT
MEDIUM⚡	tests/test_run_state.py	5234	# Create a minimal Mcp config	COMMENT
MEDIUM	tests/test_run_state.py	1472	# Create a mock item that has id and type directly on the item (not in raw_item)	COMMENT
MEDIUM	tests/test_run_state.py	1698	# Create a cycle A -> B -> A	COMMENT
MEDIUM	tests/test_run_state.py	2551	# Create a handoff output item	COMMENT
MEDIUM	tests/test_run_state.py	3294	# Create a RunState with context	COMMENT
MEDIUM	tests/test_run_state.py	3314	# Create a RunState with context	COMMENT
MEDIUM	tests/test_run_state.py	3338	# Create a run that will have interruptions	COMMENT
MEDIUM	tests/test_run_state.py	3406	# Create a message with nested content	COMMENT
MEDIUM	tests/test_run_state.py	3683	# Create a handoff with a name attribute but no tool_name	COMMENT
MEDIUM	tests/test_run_state.py	3828	# Create a shell tool with description	COMMENT
MEDIUM	tests/test_run_state.py	3866	# Create an apply patch tool with description	COMMENT
MEDIUM	tests/test_run_state.py	3912	# Create a mock MCP tool - HostedMCPTool doesn't have a simple constructor	COMMENT
MEDIUM	tests/test_run_state.py	3951	# Create a message item	COMMENT
MEDIUM	tests/test_run_state.py	4184	# Create a mock item with a raw_item that is neither dict nor has model_dump	COMMENT
MEDIUM	tests/test_run_state.py	4204	# Create an agent without get_all_tools method	COMMENT
MEDIUM	tests/test_run_state.py	4233	# Create a handoff with tool_name	COMMENT
MEDIUM	tests/test_run_state.py	4845	# Create a mock MCP tool	COMMENT
MEDIUM	tests/test_run_state.py	5190	# Create a handoff with name attribute but no tool_name	COMMENT
MEDIUM	tests/test_run_state.py	5280	# Create an agent without get_all_tools method	COMMENT
MEDIUM	tests/test_run_state.py	5343	# Create an item with missing type field to trigger the union adapter fallback	COMMENT
MEDIUM⚡	tests/test_extension_filters.py	729	# Create a nested summary that will be parsed	COMMENT
MEDIUM⚡	tests/test_extension_filters.py	737	# Create a second nested summary that includes the first	COMMENT
MEDIUM⚡	tests/test_extension_filters.py	836	# Create an item with a circular reference or other unserializable content	COMMENT
MEDIUM⚡	tests/test_extension_filters.py	841	# Create an item that will trigger TypeError in json.dumps	COMMENT
MEDIUM	tests/test_extension_filters.py	571	# Create an item that doesn't have a role (e.g., a function call)	COMMENT
MEDIUM	tests/test_extension_filters.py	708	# Create a summary message with non-string content (array)	COMMENT
MEDIUM	tests/test_extension_filters.py	756	# Create a summary that includes a role with name	COMMENT
72 more matches not shown…

Cross-Language Confusion55 hits · 312 pts

Severity	File	Line	Snippet	Context
HIGH	tests/test_agent_tool_input.py	93	assert "- count (integer \| null, optional) - Optional count." in info.summary	CODE
HIGH	tests/extensions/sandbox/test_modal.py	2149	"modal-snapshot-directory-ephemeral.tar -T - 2>/dev/null && test -f "	CODE
HIGH	tests/extensions/sandbox/test_modal.py	2375	"cd -- /workspace && (tar cf - -- tmp.txt 2>/dev/null \|\| true)",	CODE
HIGH	tests/extensions/sandbox/test_modal.py	2406	["sh", "-lc", "cd -- /workspace && (tar cf - -- tmp.txt 2>/dev/null \|\| true)"],	CODE
HIGH	tests/extensions/sandbox/test_modal.py	2458	"cd -- /workspace && (tar cf - -- tmp.txt 2>/dev/null \|\| true)",	CODE
HIGH	tests/extensions/sandbox/test_modal.py	2486	["sh", "-lc", "cd -- /workspace && (tar cf - -- tmp.txt 2>/dev/null \|\| true)"],	CODE
HIGH	tests/extensions/sandbox/test_e2b.py	131	"sh -lc test -c /dev/fuse && grep -qw fuse /proc/filesystems && "	CODE
HIGH	tests/extensions/sandbox/test_e2b.py	132	"(command -v fusermount3 >/dev/null 2>&1 \|\| command -v fusermount >/dev/null 2>&1)"	CODE
HIGH	tests/extensions/sandbox/test_e2b.py	159	"sh -lc command -v rclone >/dev/null 2>&1 \|\| test -x /usr/local/bin/rclone",	CODE
HIGH	tests/extensions/sandbox/test_e2b.py	176	"sh -lc command -v rclone >/dev/null 2>&1 \|\| test -x /usr/local/bin/rclone"	CODE
HIGH	tests/extensions/sandbox/test_runloop_mounts.py	153	"sh -lc command -v rclone >/dev/null 2>&1 \|\| test -x /usr/local/bin/rclone",	CODE
HIGH	tests/extensions/sandbox/test_runloop_mounts.py	170	"sh -lc command -v rclone >/dev/null 2>&1 \|\| test -x /usr/local/bin/rclone"	CODE
HIGH	tests/extensions/sandbox/test_runloop_mounts.py	196	"sh -lc command -v fusermount3 >/dev/null 2>&1 \|\| command -v fusermount >/dev/null 2>&1",	CODE
HIGH	tests/extensions/sandbox/test_runloop_mounts.py	206	"sh -lc command -v fusermount3 >/dev/null 2>&1 \|\| command -v fusermount >/dev/null 2>&1",	CODE
HIGH	tests/extensions/sandbox/test_runloop.py	2280	await session.exec("pwd && echo hello", shell=True)	CODE
HIGH	tests/extensions/sandbox/test_runloop.py	2496	await session.exec("pwd && echo hello", shell=True)	CODE
HIGH	tests/realtime/test_session.py	3165	complex_args = '{"nested": {"data": [1, 2, 3]}, "bool": true, "null": null}'	CODE
HIGH	tests/sandbox/test_session_sinks.py	495	slow_result = await session.exec("sleep 1 && echo slow span")	CODE
HIGH	tests/sandbox/test_runtime.py	3751	result = await session.exec("echo hi > note.txt && cat note.txt")	CODE
HIGH⚡	tests/sandbox/test_session_utils.py	189	await session.exec("echo hello && echo goodbye", shell=True)	CODE
HIGH⚡	tests/sandbox/test_session_utils.py	191	assert session.last_command == ("sh", "-lc", "echo hello && echo goodbye")	CODE
HIGH	tests/sandbox/test_mounts.py	1149	["sh", "-lc", "command -v rclone >/dev/null 2>&1 \|\| test -x /usr/local/bin/rclone"],	CODE
HIGH⚡	tests/sandbox/test_docker.py	2471	'pid="$(cat "$1" 2>/dev/null \|\| true)"; '	CODE
HIGH⚡	tests/sandbox/test_docker.py	2472	'if [ -n "$pid" ]; then kill -KILL "$pid" >/dev/null 2>&1 \|\| true; fi; '	CODE
HIGH⚡	tests/sandbox/test_docker.py	2514	"cmd": ["sh", "-lc", "pkill -f -- 'sleep 10' >/dev/null 2>&1 \|\| true"],	CODE
HIGH⚡	tests/sandbox/test_docker.py	2519	"cmd": ["sh", "-lc", "pkill -f -- 'sleep 20' >/dev/null 2>&1 \|\| true"],	CODE
HIGH	tests/sandbox/test_docker.py	2456	'mkdir -p "$1" && printf "%s" "$$" > "$2" && shift 2 && exec "$@"',	CODE
HIGH⚡	tests/sandbox/capabilities/test_shell_capability.py	503	("cd /workspace/src/project && pwd", 10.0, ["/bin/bash", "-c"])	CODE
HIGH⚡	tests/sandbox/capabilities/test_shell_capability.py	510	"stdout: cd /workspace/src/project && pwd\n"	CODE
HIGH⚡	tests/sandbox/capabilities/test_shell_capability.py	511	"stderr: cd /workspace/src/project && pwd"	CODE
HIGH⚡	tests/sandbox/capabilities/test_shell_capability.py	545	assert session.exec_calls == [("cd /tmp && pwd", 10.0, ["/bin/bash", "-c"])]	CODE
HIGH⚡	tests/sandbox/capabilities/test_shell_capability.py	551	"stdout: cd /tmp && pwd\n"	CODE
HIGH⚡	tests/sandbox/capabilities/test_shell_capability.py	552	"stderr: cd /tmp && pwd"	CODE
HIGH	examples/sandbox/extensions/blaxel_runner.py	307	f"cat {mount_path}/{marker}.txt && ls {mount_path}"	CODE
HIGH	…ples/sandbox/tutorials/dataroom_metric_extract/main.py	61	Optional field: `segment` (segment/geography if explicitly stated, else null).	STRING
HIGH	src/agents/extensions/sandbox/_rclone.py	8	_RCLONE_CHECK = "command -v rclone >/dev/null 2>&1 \|\| test -x /usr/local/bin/rclone"	CODE
HIGH	src/agents/extensions/sandbox/runloop/mounts.py	49	"command -v fusermount3 >/dev/null 2>&1 \|\| command -v fusermount >/dev/null 2>&1",	CODE
HIGH	src/agents/extensions/sandbox/runloop/mounts.py	77	"command -v fusermount3 >/dev/null 2>&1 \|\| command -v fusermount >/dev/null 2>&1",	CODE
HIGH	src/agents/extensions/sandbox/blaxel/mounts.py	222	"cd /tmp && ar x gcsfuse.deb && "	CODE
HIGH	src/agents/extensions/sandbox/blaxel/mounts.py	246	detect = await _exec(session, "which apk >/dev/null 2>&1 && echo apk \|\| echo apt")	CODE
HIGH	src/agents/extensions/sandbox/blaxel/mounts.py	246	detect = await _exec(session, "which apk >/dev/null 2>&1 && echo apk \|\| echo apt")	CODE
HIGH⚡	src/agents/extensions/sandbox/daytona/mounts.py	37	f"command -v {cmd} >/dev/null 2>&1 \|\| test -x /usr/local/bin/{cmd}",	CODE
HIGH	src/agents/extensions/sandbox/daytona/mounts.py	57	f"apt-get update -qq && DEBIAN_FRONTEND=noninteractive apt-get install -y -qq {package}"	CODE
HIGH	src/agents/extensions/sandbox/modal/sandbox.py	1318	f"(tar cf - -- {rel_args} 2>/dev/null \|\| true)"	CODE
HIGH	src/agents/extensions/sandbox/e2b/mounts.py	30	"test -c /dev/fuse && grep -qw fuse /proc/filesystems && "	CODE
HIGH	src/agents/extensions/sandbox/e2b/mounts.py	31	"(command -v fusermount3 >/dev/null 2>&1 \|\| command -v fusermount >/dev/null 2>&1)",	CODE
HIGH⚡	src/agents/sandbox/sandboxes/docker.py	525	f"pkill -f -- '{pattern}' >/dev/null 2>&1 \|\| true",	CODE
HIGH⚡	src/agents/sandbox/sandboxes/docker.py	1281	'pid="$(cat "$1" 2>/dev/null \|\| true)"; '	CODE
HIGH⚡	src/agents/sandbox/sandboxes/docker.py	1283	'kill -KILL "$pid" >/dev/null 2>&1 \|\| true; '	CODE
HIGH	src/agents/sandbox/sandboxes/docker.py	151	'n=$1; shift; [ "$(printf ab \| head -c 1 2>/dev/null)" = a ] \|\| exit 98; head -c "$n" \| "$@"'	CODE
HIGH	src/agents/sandbox/sandboxes/docker.py	942	'mkdir -p "$1" && printf "%s" "$$" > "$2" && shift 2 && exec "$@"',	CODE
HIGH	src/agents/sandbox/entries/mounts/patterns.py	881	"command -v rclone >/dev/null 2>&1 \|\| test -x /usr/local/bin/rclone",	CODE
HIGH	src/agents/sandbox/entries/mounts/patterns.py	964	f"umount {shlex.quote(sandbox_path_str(path))} >/dev/null 2>&1 \|\| true",	CODE
HIGH	src/agents/sandbox/entries/mounts/patterns.py	973	f"'rclone (mount\|serve nfs) {rclone_config.remote_name}:' >/dev/null 2>&1 \|\| true"	CODE
HIGH	src/agents/sandbox/session/runtime_helpers.py	288	if [ -x "$dest" ] && command -v cmp >/dev/null 2>&1 && cmp -s "$dest" "$tmp"; then	CODE

Deep Nesting213 hits · 174 pts

Severity	File	Line	Context
LOW	tests/test_tracing.py	288	CODE
LOW	tests/test_agent_llm_hooks.py	104	CODE
LOW	tests/test_hitl_session_scenario.py	361	CODE
LOW	tests/test_hitl_session_scenario.py	382	CODE
LOW	tests/test_run_hooks.py	126	CODE
LOW	tests/fake_model.py	147	CODE
LOW	tests/memory/test_session.py	26	CODE
LOW	…xtensions/experimental/hosted_multi_agent/test_live.py	37	CODE
LOW	tests/extensions/memory/test_dapr_redis_integration.py	65	CODE
LOW	tests/extensions/memory/test_dapr_redis_integration.py	95	CODE
LOW	tests/extensions/sandbox/test_e2b.py	306	CODE
LOW	tests/extensions/sandbox/test_vercel.py	244	CODE
LOW	tests/extensions/sandbox/test_runloop.py	266	CODE
LOW	tests/realtime/test_session.py	1000	CODE
LOW	tests/sandbox/test_runtime.py	4464	CODE
LOW	tests/sandbox/test_runtime.py	4487	CODE
LOW	docs/scripts/translate_docs.py	459	CODE
LOW	examples/web_search_utils.py	20	CODE
LOW	examples/run_examples.py	612	CODE
LOW	examples/run_examples.py	666	CODE
LOW	examples/tools/tool_search.py	121	CODE
LOW	examples/tools/code_interpreter.py	14	CODE
LOW	examples/tools/container_shell_inline_skill.py	18	CODE
LOW	examples/tools/shell_human_in_the_loop.py	104	CODE
LOW	examples/customer_service/main.py	151	CODE
LOW	examples/memory/file_hitl_example.py	22	CODE
LOW	examples/memory/memory_session_hitl_example.py	56	CODE
LOW	examples/memory/openai_session_hitl_example.py	56	CODE
LOW	examples/basic/stream_function_call_args.py	25	CODE
LOW	examples/basic/stream_ws.py	90	CODE
LOW	examples/basic/stream_items.py	13	CODE
LOW	examples/realtime/app/server.py	417	CODE
LOW	examples/realtime/app/server.py	151	CODE
LOW	examples/realtime/app/server.py	334	CODE
LOW	examples/realtime/app/server.py	351	CODE
LOW	examples/realtime/cli/demo.py	84	CODE
LOW	examples/realtime/cli/demo.py	272	CODE
LOW	examples/realtime/cli/demo.py	324	CODE
LOW	examples/realtime/twilio_sip/server.py	99	CODE
LOW	examples/realtime/twilio/twilio_handler.py	149	CODE
LOW	examples/realtime/twilio/twilio_handler.py	194	CODE
LOW	examples/reasoning_content/runner_example.py	23	CODE
LOW	examples/reasoning_content/main.py	70	CODE
LOW	examples/agent_patterns/agents_as_tools_conditional.py	87	CODE
LOW	examples/agent_patterns/agents_as_tools.py	59	CODE
LOW	examples/agent_patterns/routing.py	37	CODE
LOW	examples/agent_patterns/llm_as_a_judge.py	42	CODE
LOW	examples/voice/static/util.py	9	CODE
LOW	examples/sandbox/memory.py	138	CODE
LOW	examples/sandbox/memory_s3.py	233	CODE
LOW	examples/sandbox/memory_multi_agent_multiturn.py	145	CODE
LOW	examples/sandbox/unix_local_pty.py	83	CODE
LOW	examples/sandbox/sandbox_agent_capabilities.py	287	CODE
LOW	examples/sandbox/docker/docker_runner.py	65	CODE
LOW	examples/sandbox/extensions/blaxel_runner.py	138	CODE
LOW	examples/sandbox/extensions/cloudflare_runner.py	216	CODE
LOW	…/sandbox/extensions/temporal/temporal_sandbox_agent.py	241	CODE
LOW	…/sandbox/extensions/temporal/temporal_sandbox_agent.py	284	CODE
LOW	…es/sandbox/extensions/temporal/temporal_sandbox_tui.py	809	CODE
LOW	…es/sandbox/extensions/temporal/temporal_sandbox_tui.py	992	CODE
153 more matches not shown…

Modern Structural Boilerplate141 hits · 154 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_agent_runner_sync.py	14	def set_event_loop(self, loop: asyncio.AbstractEventLoop \| None) -> None: ...	CODE
LOW⚡	tests/test_trace_processor.py	336	def set_processors(self, processors: list[TracingProcessor]) -> None:	CODE
LOW⚡	tests/test_trace_processor.py	345	def set_disabled(self, disabled: bool) -> None:	CODE
LOW	tests/extensions/memory/test_encrypt_session.py	46	def _set_time(value: int) -> None:	CODE
LOW	tests/extensions/sandbox/test_modal.py	58	def _set_aio_attr(obj: object, name: str, fn: Callable[..., object]) -> None:	CODE
LOW	tests/realtime/test_session_exceptions.py	30	def set_next_events(self, events: list[RealtimeModelEvent]) -> None:	CODE
LOW	tests/sandbox/test_runtime.py	121	def _set_concurrency_limits(self, limits: SandboxConcurrencyLimits) -> None:	CODE
LOW	tests/sandbox/test_runtime.py	125	def _set_archive_limits(self, limits: SandboxArchiveLimits \| None) -> None:	CODE
LOW	examples/realtime/app/server.py	44	logger = logging.getLogger(__name__)	CODE
LOW⚡	examples/realtime/cli/demo.py	369	def _update_playback_rms(self, samples: np.ndarray[Any, np.dtype[Any]]) -> None:	CODE
LOW	…andbox/extensions/temporal/temporal_session_manager.py	395	async def update_snapshot_id(self, request: RenameRequest) -> None:	CODE
LOW⚡	…es/sandbox/extensions/temporal/temporal_sandbox_tui.py	328	def _set_activity(self, text: str \| Text = "") -> None:	CODE
LOW	…es/sandbox/extensions/temporal/temporal_sandbox_tui.py	722	def _set_session_title(self, title: str) -> None:	CODE
LOW⚡	…es/sandbox/extensions/temporal/temporal_sandbox_tui.py	324	def _set_liveness(self, text: str \| Text) -> None:	STRING
LOW	src/agents/run.py	131	__all__ = [	CODE
LOW	src/agents/run.py	152	def set_default_agent_runner(runner: AgentRunner \| None) -> None:	CODE
LOW⚡	src/agents/run_state.py	994	def set_trace(self, trace: Trace \| None) -> None:	CODE
LOW⚡	src/agents/run_state.py	1003	def set_tool_use_tracker_snapshot(self, snapshot: Mapping[str, Sequence[str]] \| None) -> None:	CODE
LOW⚡	src/agents/run_state.py	1016	def set_reasoning_item_id_policy(self, policy: Literal["preserve", "omit"] \| None) -> None:	CODE
LOW	src/agents/run_error_handlers.py	58	__all__ = [	CODE
LOW	src/agents/responses_websocket_session.py	133	__all__ = ["ResponsesWebSocketSession", "responses_websocket_session"]	CODE
LOW⚡	src/agents/__init__.py	298	def set_default_openai_api(api: Literal["chat_completions", "responses"]) -> None:	CODE
LOW⚡	src/agents/__init__.py	305	def set_default_openai_responses_transport(transport: Literal["http", "websocket"]) -> None:	CODE
LOW⚡	src/agents/__init__.py	325	def set_default_openai_harness(harness_id: str \| None) -> None:	CODE
LOW⚡	src/agents/__init__.py	340	__all__ = [	CODE
LOW	src/agents/__init__.py	270	def set_default_openai_key(key: str, use_for_tracing: bool = True) -> None:	CODE
LOW	src/agents/__init__.py	285	def set_default_openai_client(client: AsyncOpenAI, use_for_tracing: bool = True) -> None:	CODE
LOW	src/agents/apply_diff.py	347	__all__ = ["apply_diff"]	CODE
LOW⚡	src/agents/_config.py	13	def set_default_openai_key(key: str, use_for_tracing: bool) -> None:	CODE
LOW⚡	src/agents/_config.py	20	def set_default_openai_client(client: AsyncOpenAI, use_for_tracing: bool) -> None:	CODE
LOW⚡	src/agents/_config.py	27	def set_default_openai_api(api: Literal["chat_completions", "responses"]) -> None:	CODE
LOW⚡	src/agents/_config.py	34	def set_default_openai_responses_transport(transport: Literal["http", "websocket"]) -> None:	CODE
LOW⚡	src/agents/_config.py	48	def set_default_openai_harness(harness_id: str \| None) -> None:	CODE
LOW	src/agents/run_config.py	372	__all__ = [	CODE
LOW⚡	src/agents/agent_tool_state.py	36	def set_agent_tool_state_scope(context: Any, scope_id: str \| None) -> None:	CODE
LOW	src/agents/tracing/provider.py	182	def set_processors(self, processors: list[TracingProcessor]) -> None:	CODE
LOW	src/agents/tracing/provider.py	194	def set_disabled(self, disabled: bool) -> None:	CODE
LOW	src/agents/tracing/provider.py	284	def set_disabled(self, disabled: bool) -> None:	CODE
LOW⚡	src/agents/tracing/__init__.py	101	def set_trace_processors(processors: list[TracingProcessor]) -> None:	CODE
LOW⚡	src/agents/tracing/__init__.py	108	def set_tracing_disabled(disabled: bool) -> None:	CODE
LOW⚡	src/agents/tracing/__init__.py	115	def set_tracing_export_api_key(api_key: str) -> None:	CODE
LOW	src/agents/tracing/__init__.py	45	__all__ = [	CODE
LOW	src/agents/tracing/spans.py	139	def set_error(self, error: SpanError) -> None:	CODE
LOW	src/agents/tracing/spans.py	240	def set_error(self, error: SpanError) -> None:	CODE
LOW	src/agents/tracing/spans.py	349	def set_error(self, error: SpanError) -> None:	CODE
LOW	src/agents/tracing/setup.py	27	def set_trace_provider(provider: TraceProvider) -> None:	CODE
LOW	src/agents/memory/__init__.py	20	__all__ = [	CODE
LOW	src/agents/mcp/__init__.py	44	__all__ = [	CODE
LOW	src/agents/models/reasoning_content_replay.py	54	__all__ = [	CODE
LOW	src/agents/models/__init__.py	9	__all__ = [	CODE
LOW⚡	src/agents/models/_openai_shared.py	18	def set_default_openai_key(key: str) -> None:	CODE
LOW⚡	src/agents/models/_openai_shared.py	27	def set_default_openai_client(client: AsyncOpenAI) -> None:	CODE
LOW⚡	src/agents/models/_openai_shared.py	36	def set_use_responses_by_default(use_responses: bool) -> None:	CODE
LOW⚡	src/agents/models/_openai_shared.py	45	def set_use_responses_websocket_by_default(use_responses_websocket: bool) -> None:	CODE
LOW⚡	src/agents/models/_openai_shared.py	53	def set_default_openai_responses_transport(transport: OpenAIResponsesTransport) -> None:	CODE
LOW	src/agents/extensions/tool_output_trimmer.py	41	logger = logging.getLogger(__name__)	CODE
LOW	src/agents/extensions/__init__.py	3	__all__ = ["ToolOutputTrimmer"]	CODE
LOW	src/agents/extensions/handoff_filters.py	26	__all__ = [	CODE
LOW	src/agents/extensions/experimental/__init__.py	4	__all__ = [	CODE
LOW	src/agents/extensions/experimental/codex/__init__.py	48	__all__ = [	CODE
81 more matches not shown…

Modern AI Meta-Vocabulary43 hits · 118 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	12	1. [Agents](https://openai.github.io/openai-agents-python/agents): LLMs configured with instructions, tools, guardra	CODE
MEDIUM	README.md	16	1. [Guardrails](https://openai.github.io/openai-agents-python/guardrails/): Configurable safety checks for input and	CODE
MEDIUM⚡	tests/test_items_helpers.py	201	# Create a non-message run item of a different type, e.g., a reasoning trace.	COMMENT
MEDIUM	tests/realtime/test_session.py	3536	# Neither should trigger guardrails yet	COMMENT
MEDIUM	tests/realtime/test_session.py	3679	# Use a minimal agent (guardrails from run_config)	COMMENT
MEDIUM⚡	docs/llms.txt	8	- [Overview](https://openai.github.io/openai-agents-python/): Learn the core primitives—agents, handoffs, guardrails, se	CODE
MEDIUM⚡	docs/llms.txt	10	- [Example Gallery](https://openai.github.io/openai-agents-python/examples/): Task-oriented examples that demonstrate ag	CODE
MEDIUM⚡	docs/llms.txt	13	- [Agents](https://openai.github.io/openai-agents-python/agents/): Configure agent instructions, tools, guardrails, memo	CODE
MEDIUM	docs/llms.txt	24	- [Guardrails](https://openai.github.io/openai-agents-python/guardrails/): Define validators that run alongside the agen	CODE
MEDIUM	docs/guardrails.md	20	## Input guardrails	COMMENT
MEDIUM	docs/guardrails.md	40	## Output guardrails	COMMENT
MEDIUM	docs/guardrails.md	54	## Tool guardrails	COMMENT
MEDIUM	docs/quickstart.md	180	## Run the agent orchestration	COMMENT
MEDIUM	docs/llms-full.txt	10	- [Example Gallery](https://openai.github.io/openai-agents-python/examples/): Realistic Python samples that demonstrate	CODE
MEDIUM	docs/llms-full.txt	28	- [Guardrails](https://openai.github.io/openai-agents-python/guardrails/): Create synchronous or asynchronous checks, sh	CODE
MEDIUM	docs/llms-full.txt	59	- [guardrail APIs](https://openai.github.io/openai-agents-python/ref/guardrail/): Build custom guardrails, interpret val	CODE
MEDIUM	docs/index.md	3	The [OpenAI Agents SDK](https://github.com/openai/openai-agents-python) enables you to build agentic AI apps in a lightw	CODE
MEDIUM	docs/multi_agent.md	1	# Agent orchestration	COMMENT
MEDIUM	docs/multi_agent.md	57	- [Tools](tools.md#agents-as-tools) for `Agent.as_tool()` and manager-style orchestration.	CODE
MEDIUM	docs/ja/models/index.md	20	\| OpenAIがホストするサブエージェントを使用する \| 試験的なホスト型マルチエージェントモデルを使用する \| [ホスト型マルチエージェント](#hosted-multi-agent-experimental) \|	CODE
MEDIUM	docs/models/index.md	16	\| Use OpenAI-hosted subagents \| Use the experimental hosted multi-agent model \| [Hosted multi-agent](#hosted-multi-agent	CODE
MEDIUM	docs/models/index.md	235	### Hosted multi-agent (experimental)	COMMENT
MEDIUM	docs/models/index.md	287	#### Relationship to SDK orchestration	COMMENT
MEDIUM	docs/realtime/guide.md	182	## Tools, approvals, handoffs, and guardrails	COMMENT
MEDIUM	docs/zh/models/index.md	20	\| 使用OpenAI托管的子智能体 \| 使用实验性的托管式多智能体模型 \| [托管式多智能体](#hosted-multi-agent-experimental) \|	CODE
MEDIUM	docs/ko/models/index.md	20	\| OpenAI에서 호스팅되는 서브에이전트 사용 \| 실험적 호스티드 멀티 에이전트 모델 사용 \| [호스티드 멀티 에이전트](#hosted-multi-agent-experimental) \|	CODE
MEDIUM	examples/basic/tool_guardrails.py	103	# Apply guardrails to tools	COMMENT
MEDIUM	examples/realtime/twilio_sip/server.py	44	# Build the multi-agent graph (triage + specialist agents) from agents.py.	COMMENT
MEDIUM	examples/agent_patterns/input_guardrails.py	32	### 1. An agent-based guardrail that is triggered if the user is asking to do math homework	COMMENT
MEDIUM	examples/agent_patterns/agents_as_tools.py	65	# Run the entire orchestration in a single trace	COMMENT
MEDIUM	examples/agent_patterns/README.md	1	# Common agentic patterns	COMMENT
MEDIUM	examples/agent_patterns/README.md	5	## Hosted multi-agent (experimental)	COMMENT
MEDIUM	examples/agent_patterns/streaming_guardrails.py	70	# alternate implementation is to have N guardrails running, or cancel the previous	COMMENT
MEDIUM	examples/sandbox/README.md	27	## Tutorial scaffold	COMMENT
MEDIUM	…dbox/extensions/daytona/usaspending_text2sql/README.md	65	### SQL guardrails (defense in depth)	COMMENT
MEDIUM	src/agents/run.py	782	# Blocking first-turn guardrails must run before sandbox prep so a tripwire	COMMENT
MEDIUM	src/agents/result.py	736	# Await input guardrails if they are still running, so late	COMMENT
MEDIUM	src/agents/tool.py	419	# Tool-specific guardrails.	COMMENT
MEDIUM	src/agents/run_internal/guardrails.py	94	# Early first-turn streamed guardrails can run before the agent span exists.	COMMENT
MEDIUM	src/agents/realtime/session.py	421	# Check if we should run guardrails based on debounce threshold	COMMENT
MEDIUM	src/agents/realtime/session.py	1362	# Runs the guardrails in a separate task to avoid blocking the main loop	COMMENT
MEDIUM	src/agents/sandbox/entries/mounts/patterns.py	678	# host process that is orchestrating the session.	COMMENT
MEDIUM	src/agents/sandbox/memory/phase_one.py	69	# context window once model metadata is available in the SDK.	COMMENT

Magic Placeholder Names12 hits · 60 pts

Severity	File	Line	Snippet	Context
HIGH	docs/tracing.md	161	api_key="your-api-key",	CODE
HIGH	docs/ja/tracing.md	165	api_key="your-api-key",	CODE
HIGH	docs/ja/realtime/quickstart.md	134	export OPENAI_API_KEY="your-api-key-here"	CODE
HIGH	docs/ja/realtime/quickstart.md	140	session = await runner.run(model_config={"api_key": "your-api-key"})	CODE
HIGH	docs/realtime/quickstart.md	130	export OPENAI_API_KEY="your-api-key-here"	CODE
HIGH	docs/realtime/quickstart.md	136	session = await runner.run(model_config={"api_key": "your-api-key"})	CODE
HIGH	docs/zh/tracing.md	165	api_key="your-api-key",	CODE
HIGH	docs/zh/realtime/quickstart.md	134	export OPENAI_API_KEY="your-api-key-here"	CODE
HIGH	docs/zh/realtime/quickstart.md	140	session = await runner.run(model_config={"api_key": "your-api-key"})	CODE
HIGH	docs/ko/tracing.md	165	api_key="your-api-key",	CODE
HIGH	docs/ko/realtime/quickstart.md	134	export OPENAI_API_KEY="your-api-key-here"	CODE
HIGH	docs/ko/realtime/quickstart.md	140	session = await runner.run(model_config={"api_key": "your-api-key"})	CODE

AI Structural Patterns40 hits · 28 pts

Severity	File	Line	Context
LOW	tests/test_run_state.py	195	CODE
LOW	tests/test_run_step_execution.py	2908	CODE
LOW	tests/extensions/sandbox/test_e2b.py	306	CODE
LOW	tests/extensions/sandbox/test_e2b.py	1034	CODE
LOW	tests/extensions/sandbox/test_e2b.py	1101	CODE
LOW	tests/extensions/sandbox/test_e2b.py	1153	CODE
LOW	tests/extensions/sandbox/test_e2b.py	1367	CODE
LOW	tests/sandbox/capabilities/test_apply_patch_tool.py	241	CODE
LOW	…ndbox/extensions/daytona/usaspending_text2sql/agent.py	203	CODE
LOW	src/agents/run.py	200	CODE
LOW	src/agents/run.py	284	CODE
LOW	src/agents/run.py	366	CODE
LOW	src/agents/responses_websocket_session.py	81	CODE
LOW	src/agents/tool_context.py	60	CODE
LOW	src/agents/retry.py	62	CODE
LOW	src/agents/agent.py	508	CODE
LOW	src/agents/tool.py	599	CODE
LOW	src/agents/tool.py	1851	CODE
LOW	src/agents/tool.py	1876	CODE
LOW	src/agents/tool.py	1899	CODE
LOW	src/agents/tracing/create.py	188	CODE
LOW	src/agents/tracing/create.py	353	CODE
LOW	src/agents/tracing/create.py	397	CODE
LOW	src/agents/mcp/server.py	541	CODE
LOW	src/agents/mcp/server.py	1116	CODE
LOW	src/agents/mcp/server.py	1241	CODE
LOW	src/agents/mcp/server.py	1381	CODE
LOW	src/agents/models/multi_provider.py	75	CODE
LOW	src/agents/models/openai_provider.py	45	CODE
LOW	src/agents/extensions/experimental/codex/codex_tool.py	236	CODE
LOW	src/agents/extensions/sandbox/vercel/sandbox.py	199	CODE
LOW	src/agents/extensions/sandbox/runloop/sandbox.py	479	CODE
LOW	src/agents/extensions/sandbox/blaxel/mounts.py	206	CODE
LOW	src/agents/extensions/sandbox/blaxel/sandbox.py	1187	CODE
LOW	src/agents/extensions/sandbox/daytona/sandbox.py	327	CODE
LOW	src/agents/extensions/sandbox/modal/sandbox.py	289	CODE
LOW	src/agents/extensions/sandbox/e2b/sandbox.py	443	CODE
LOW	src/agents/extensions/sandbox/e2b/sandbox.py	210	CODE
LOW	src/agents/extensions/sandbox/e2b/sandbox.py	271	CODE
LOW	src/agents/extensions/sandbox/e2b/sandbox.py	625	CODE

Docstring Block Structure5 hits · 25 pts

Severity	File	Line	Snippet	Context
HIGH	src/agents/run_state.py	667	Serializes the run state to a JSON-compatible dictionary. This method is used to serialize the run state to a d	STRING
HIGH	src/agents/run_state.py	1036	Deserializes a run state from a JSON string. This method is used to deserialize a run state from a string that	STRING
HIGH	src/agents/run_state.py	1077	Deserializes a run state from a JSON dictionary. This method is used to deserialize a run state from a dict tha	STRING
HIGH	src/agents/extensions/memory/advanced_sqlite_session.py	808	Create a new branch starting from a specific user message turn. Args: turn_number: The branch turn	STRING
HIGH	src/agents/extensions/memory/advanced_sqlite_session.py	885	Create branch from the first user turn matching the search term. Args: search_term: Text to search	STRING

Redundant / Tautological Comments12 hits · 18 pts

Severity	File	Line	Snippet	Context
LOW	tests/realtime/test_session_exceptions.py	121	# Set events to send	COMMENT
LOW	tests/voice/test_input.py	130	# Add audio to the queue	COMMENT
LOW	examples/memory/memory_session_hitl_example.py	36	# Check if any city name is in the provided location string	COMMENT
LOW	examples/memory/openai_session_hitl_example.py	36	# Check if any city name is in the provided location string	COMMENT
LOW	examples/realtime/cli/demo.py	282	# Check if there's enough data to read	COMMENT
LOW	examples/agent_patterns/agents_as_tools_structured.py	41	# Set include_input_schema to true to include the full JSON Schema:	COMMENT
LOW	examples/agent_patterns/streaming_guardrails.py	68	# Check if it's time to run the guardrail check	COMMENT
LOW	src/agents/models/chatcmpl_converter.py	134	# Check if message is agents.extensions.models.litellm_model.InternalChatCompletionMessage	COMMENT
LOW	src/agents/extensions/memory/advanced_sqlite_session.py	964	# Check if trying to delete current branch	COMMENT
LOW	src/agents/extensions/models/litellm_model.py	640	# Check if this is an assistant message with tool calls	COMMENT
LOW	src/agents/realtime/session.py	276	# Check if there's a stored exception to raise	COMMENT
LOW	src/agents/realtime/session.py	421	# Check if we should run guardrails based on debounce threshold	COMMENT

Dead Code8 hits · 16 pts

Severity	File	Line	Context
MEDIUM	tests/test_cancel_streaming.py	259	CODE
MEDIUM	tests/test_run_step_execution.py	2599	CODE
MEDIUM	tests/models/test_model_retry.py	1566	CODE
MEDIUM	tests/models/test_model_retry.py	1696	CODE
MEDIUM	tests/models/test_model_retry.py	1740	CODE
MEDIUM	tests/models/test_model_retry.py	2062	CODE
MEDIUM	tests/models/test_model_retry.py	2106	CODE
MEDIUM	src/agents/voice/workflow.py	41	CODE

Fake / Example Data14 hits · 12 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_responses_tracing.py	45	self.id = "dummy-id"	CODE
LOW	tests/test_responses_tracing.py	101	"response_id": "dummy-id",	CODE
LOW	tests/test_responses_tracing.py	252	response=fake_model.get_response_obj([], "dummy-id-123"),	CODE
LOW	tests/test_responses_tracing.py	281	"response_id": "dummy-id-123",	CODE
LOW	tests/test_responses_tracing.py	325	self.response = fake_model.get_response_obj([], "dummy-id-terminal")	CODE
LOW	tests/test_responses_tracing.py	394	response=fake_model.get_response_obj([], "dummy-id-123"),	CODE
LOW	tests/test_responses_tracing.py	470	response=fake_model.get_response_obj([], "dummy-id-123"),	CODE
LOW	tests/test_run_state.py	2210	state = make_state(agent, context=context, original_input="placeholder", max_turns=5)	CODE
LOW	tests/models/test_model_payload_iterators.py	87	id="dummy-id",	CODE
LOW	tests/extensions/sandbox/test_blaxel.py	157	def __init__(self, value: str = "fake-token-abc123") -> None:	CODE
LOW	examples/basic/tool_guardrails.py	29	"name": "John Doe",	CODE
LOW	examples/basic/tool_guardrails.py	32	"phone": "555-1234",	CODE
LOW	examples/basic/tool_guardrails.py	43	"phone": "555-1234",	CODE
LOW	examples/basic/tool_guardrails.py	95	if "555-1234" in output_str:	CODE

Hallucination Indicators1 hit · 10 pts

Severity	File	Line	Snippet	Context
CRITICAL	src/agents/voice/models/openai_tts.py	42	response = self._client.audio.speech.with_streaming_response.create(	CODE

Verbosity Indicators6 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	tests/models/test_anthropic_thinking_blocks.py	144	# Step 1: Convert message to output items	COMMENT
LOW	tests/models/test_anthropic_thinking_blocks.py	177	# Step 2: Convert output items back to messages	COMMENT
LOW	tests/models/test_anthropic_thinking_blocks.py	330	# Step 1: Convert message to output items	COMMENT
LOW	tests/models/test_anthropic_thinking_blocks.py	366	# Step 2: Convert output items back to messages with preserve_thinking_blocks=True	COMMENT
LOW	tests/models/test_gemini_thought_signatures.py	38	# Step 1: Convert to items	COMMENT
LOW	tests/models/test_gemini_thought_signatures.py	53	# Step 2: Convert back to messages	COMMENT

Structural Annotation Overuse6 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	tests/models/test_anthropic_thinking_blocks.py	144	# Step 1: Convert message to output items	COMMENT
LOW	tests/models/test_anthropic_thinking_blocks.py	177	# Step 2: Convert output items back to messages	COMMENT
LOW	tests/models/test_anthropic_thinking_blocks.py	330	# Step 1: Convert message to output items	COMMENT
LOW	tests/models/test_anthropic_thinking_blocks.py	366	# Step 2: Convert output items back to messages with preserve_thinking_blocks=True	COMMENT
LOW	tests/models/test_gemini_thought_signatures.py	38	# Step 1: Convert to items	COMMENT
LOW	tests/models/test_gemini_thought_signatures.py	53	# Step 2: Convert back to messages	COMMENT

AI Slop Vocabulary5 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_run_state.py	5296	# This should not raise an error, just return empty tools	COMMENT
MEDIUM	tests/mcp/test_tool_filtering.py	206	# Role-based filter for comprehensive testing	COMMENT
LOW	examples/customer_service/main.py	158	# Here, we'll just use a random UUID for the conversation ID	COMMENT
MEDIUM	examples/mcp/prompt_server/server.py	20	return f"""You are a senior {language} code review specialist. Your role is to provide comprehensive code analysis w	CODE
LOW	src/agents/result.py	691	# Soft cancel - just set the flag	COMMENT

Slop Phrases4 hits · 8 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/basic/tool_guardrails.py	173	❌ Guardrail rejected function tool call: I'm unable to send the email as mentioning ACME Corp. is restricted.	STRING
MEDIUM	examples/basic/tool_guardrails.py	180	❌ Guardrail rejected function tool output: I'm unable to retrieve the contact info for user456 because it contains restr	STRING
MEDIUM	examples/handoffs/message_filter_streaming.py	37	# or, you can use the HandoffInputData.clone(kwargs) method	COMMENT
MEDIUM	examples/handoffs/message_filter.py	37	# or, you can use the HandoffInputData.clone(kwargs) method	COMMENT

Over-Commented Block8 hits · 8 pts

Severity	File	Line	Snippet	Context
LOW	examples/__init__.py	1	# Make the examples directory into a package to avoid top-level module name collisions.	COMMENT
LOW	examples/basic/lifecycle_example.py	181	### 11: LLM ended. Usage: 3 requests, 472 input tokens, 45 output tokens, 517 total tokens	COMMENT
LOW	examples/basic/stream_items.py	61	# 3. Why did the scarecrow win an award?	COMMENT
LOW	examples/sandbox/memory.py	81	),	COMMENT
LOW	examples/sandbox/memory.py	101	#	COMMENT
LOW	src/agents/models/chatcmpl_stream_handler.py	961	# Content-filter refusal with no emitted output: synthesize a refusal so	COMMENT
LOW	src/agents/extensions/memory/mongodb_session.py	81	atomically incrementing a counter on the session metadata document. This	COMMENT
LOW	src/agents/sandbox/sandboxes/docker.py	641	# Frame the payload by length so the in-container reader terminates on a	COMMENT

Overly Generic Function Names1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	tests/realtime/test_realtime_model_settings.py	65	def helper() -> str:	CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings