letta-ai/letta

Pattern Findings

6450 matches across 19 categories. Click a row to expand file-level details.

Hyper-Verbose Identifiers2976 hits · 2505 pts

Severity	File	Line	Snippet
LOW	tests/test_modal_sandbox_v2.py	18	def test_execute_tool_dynamic_success(self):
LOW	tests/test_modal_sandbox_v2.py	42	def test_execute_tool_dynamic_with_error(self):
LOW	tests/test_modal_sandbox_v2.py	92	def test_execute_with_stdout_capture(self):
LOW	tests/test_modal_sandbox_v2.py	124	async def test_register_and_get_deployment(self):
LOW	tests/test_modal_sandbox_v2.py	374	def test_version_hash_calculation(self, mock_tool, mock_user, mock_sandbox_config):
LOW	tests/test_modal_sandbox_v2.py	450	async def test_run_with_mocked_modal(self, mock_tool, mock_user, mock_sandbox_config):
LOW	tests/test_modal_sandbox_v2.py	537	def test_detect_async_function(self, mock_user):
LOW	tests/test_context_window_calculator.py	16	def test_returns_none_for_missing_tag(self):
LOW	tests/test_context_window_calculator.py	21	def test_returns_none_for_missing_opening_tag(self):
LOW	tests/test_context_window_calculator.py	26	def test_returns_none_for_unclosed_tag(self):
LOW	tests/test_context_window_calculator.py	31	def test_handles_multiline_content(self):
LOW	tests/test_context_window_calculator.py	36	def test_handles_nested_content(self):
LOW	tests/test_context_window_calculator.py	41	def test_handles_empty_content(self):
LOW	tests/test_context_window_calculator.py	46	def test_extracts_first_occurrence_with_duplicate_tags(self):
LOW	tests/test_context_window_calculator.py	56	def test_extracts_standard_agent_sections(self):
LOW	tests/test_context_window_calculator.py	106	def test_extracts_tool_usage_rules(self):
LOW	tests/test_context_window_calculator.py	181	def test_returns_correct_dict_keys(self):
LOW	tests/test_context_window_calculator.py	194	def test_no_base_instructions_tag_extracts_preamble(self):
LOW	tests/test_context_window_calculator.py	216	def test_nested_memory_filesystem_not_extracted_as_top_level(self):
LOW	tests/test_context_window_calculator.py	244	def test_top_level_memory_filesystem_outside_memory_blocks(self):
LOW	tests/test_context_window_calculator.py	266	def test_letta_code_agent_real_format(self):
LOW	tests/test_context_window_calculator.py	320	def test_git_enabled_agent_bare_file_blocks_captured_as_core_memory(self):
LOW	tests/test_context_window_calculator.py	354	def test_git_enabled_agent_no_bare_blocks(self):
LOW	tests/test_context_window_calculator.py	367	def test_extract_top_level_tag_dual_occurrence_nested_first(self):
LOW	tests/test_context_window_calculator.py	380	def test_extract_system_prompt_pure_text_no_tags(self):
LOW	tests/test_context_window_calculator.py	388	def test_git_backed_memory_without_memory_blocks_wrapper(self):
LOW	tests/test_context_window_calculator.py	478	async def test_calculate_context_window_standard_agent(self):
LOW	tests/test_context_window_calculator.py	519	async def test_calculate_context_window_skips_empty_sections(self):
LOW	tests/test_context_window_calculator.py	546	async def test_calculate_context_window_all_sections(self):
LOW	tests/test_context_window_calculator.py	598	async def test_calculate_context_window_git_enabled_agent(self):
LOW	tests/test_context_window_calculator.py	88	def test_extracts_git_enabled_agent_sections(self):
LOW	tests/test_context_window_calculator.py	121	def test_extracts_directories(self):
LOW	tests/test_context_window_calculator.py	141	def test_handles_react_agent_no_memory_blocks(self):
LOW	tests/test_context_window_calculator.py	157	def test_handles_all_sections_present(self):
LOW	tests/test_context_window_calculator.py	176	def test_handles_empty_string(self):
LOW	tests/test_context_window_calculator.py	423	def test_legacy_memory_blocks_wrapper(self):
LOW	tests/test_openai_ws_session.py	56	async def test_iteration_without_context_manager(self):
LOW	tests/test_openai_ws_session.py	77	async def test_aclose_is_idempotent(self):
LOW	tests/test_openai_ws_session.py	84	async def test_stream_after_close_raises(self):
LOW	tests/test_openai_ws_session.py	100	async def test_stream_responses_yields_events_and_stops_on_terminal(self):
LOW	tests/test_openai_ws_session.py	162	def test_letta_llm_stream_adapter_stores_flag(self):
LOW	tests/test_openai_ws_session.py	178	def test_default_flag_is_false(self):
LOW	tests/test_openai_ws_session.py	193	async def test_aclose_default_is_noop(self):
LOW	tests/integration_test_turbopuffer.py	163	def test_should_use_tpuf_with_settings():
LOW	tests/integration_test_turbopuffer.py	356	async def test_native_only_operations(server, default_user, sarah_agent, disable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	1899	async def test_archive_namespace_tracking(server, default_user, enable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	190	async def test_archive_creation_with_tpuf_enabled(server, default_user, enable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	200	async def test_archive_creation_with_tpuf_disabled(server, default_user, disable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	211	async def test_dual_write_and_query_with_real_tpuf(server, default_user, sarah_agent, enable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	287	async def test_turbopuffer_metadata_attributes(default_user, enable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	390	async def test_hybrid_search_with_real_tpuf(default_user, enable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	496	async def test_tag_filtering_with_real_tpuf(default_user, enable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	623	async def test_temporal_filtering_with_real_tpuf(default_user, enable_turbopuffer):
LOW	tests/integration_test_turbopuffer.py	761	def test_should_use_tpuf_for_messages_settings():
LOW	tests/integration_test_turbopuffer.py	803	def test_message_text_extraction(server, default_user):
LOW	tests/integration_test_turbopuffer.py	946	async def test_message_embedding_without_config(server, default_user, sarah_agent, enable_message_embedding):
LOW	tests/integration_test_turbopuffer.py	984	async def test_generic_reciprocal_rank_fusion():
LOW	tests/integration_test_turbopuffer.py	1085	async def test_message_dual_write_with_real_tpuf(enable_message_embedding, default_user):
LOW	tests/integration_test_turbopuffer.py	1147	async def test_message_vector_search_with_real_tpuf(enable_message_embedding, default_user):
LOW	tests/integration_test_turbopuffer.py	1208	async def test_message_hybrid_search_with_real_tpuf(enable_message_embedding, default_user):
2916 more matches not shown…

Decorative Section Separators504 hits · 1745 pts

Severity	File	Line	Snippet
MEDIUM	conf.yaml	56	# =============================================================================
MEDIUM	conf.yaml	58	# =============================================================================
MEDIUM	conf.yaml	63	# =============================================================================
MEDIUM	conf.yaml	65	# =============================================================================
MEDIUM	conf.yaml	71	# =============================================================================
MEDIUM	conf.yaml	73	# =============================================================================
MEDIUM	conf.yaml	106	# =============================================================================
MEDIUM	conf.yaml	108	# =============================================================================
MEDIUM	conf.yaml	112	# =============================================================================
MEDIUM	conf.yaml	114	# =============================================================================
MEDIUM	conf.yaml	117	# =============================================================================
MEDIUM	conf.yaml	119	# =============================================================================
MEDIUM	conf.yaml	126	# =============================================================================
MEDIUM	conf.yaml	128	# =============================================================================
MEDIUM	conf.yaml	133	# =============================================================================
MEDIUM	conf.yaml	135	# =============================================================================
MEDIUM	conf.yaml	143	# =============================================================================
MEDIUM	conf.yaml	145	# =============================================================================
MEDIUM	conf.yaml	153	# =============================================================================
MEDIUM	conf.yaml	155	# =============================================================================
MEDIUM	conf.yaml	160	# =============================================================================
MEDIUM	conf.yaml	162	# =============================================================================
MEDIUM	conf.yaml	166	# =============================================================================
MEDIUM	conf.yaml	168	# =============================================================================
MEDIUM	conf.yaml	172	# =============================================================================
MEDIUM	conf.yaml	174	# =============================================================================
MEDIUM	conf.yaml	178	# =============================================================================
MEDIUM	conf.yaml	180	# =============================================================================
MEDIUM	conf.yaml	183	# =============================================================================
MEDIUM	conf.yaml	185	# =============================================================================
MEDIUM	conf.yaml	200	# =============================================================================
MEDIUM	conf.yaml	202	# =============================================================================
MEDIUM	conf.yaml	209	# =============================================================================
MEDIUM	conf.yaml	211	# =============================================================================
MEDIUM	conf.yaml	12	# =============================================================================
MEDIUM	conf.yaml	14	# =============================================================================
MEDIUM	conf.yaml	27	# =============================================================================
MEDIUM	conf.yaml	29	# =============================================================================
MEDIUM	conf.yaml	92	# =============================================================================
MEDIUM	conf.yaml	94	# =============================================================================
MEDIUM	conf.yaml	231	# =============================================================================
MEDIUM	conf.yaml	233	# =============================================================================
MEDIUM	conf.yaml	334	# =============================================================================
MEDIUM	conf.yaml	336	# =============================================================================
MEDIUM	conf.yaml	370	# =============================================================================
MEDIUM	conf.yaml	372	# =============================================================================
MEDIUM	tests/integration_test_client_side_tools.py	16	# ------------------------------
MEDIUM	tests/integration_test_client_side_tools.py	18	# ------------------------------
MEDIUM	tests/integration_test_client_side_tools.py	47	# ------------------------------
MEDIUM	tests/integration_test_client_side_tools.py	49	# ------------------------------
MEDIUM	tests/integration_test_client_side_tools.py	58	# ------------------------------
MEDIUM	tests/integration_test_client_side_tools.py	60	# ------------------------------
MEDIUM	tests/test_utils.py	70	# -----------------------------------------------------------------------
MEDIUM	tests/test_utils.py	77	# -----------------------------------------------------------------------
MEDIUM	tests/integration_test_send_message.py	1089	# ------------------------------
MEDIUM	tests/integration_test_send_message.py	1091	# ------------------------------
MEDIUM	tests/integration_test_send_message.py	2579	# ============================
MEDIUM	tests/integration_test_send_message.py	2581	# ============================
MEDIUM	tests/integration_test_send_message.py	37	# ------------------------------
MEDIUM	tests/integration_test_send_message.py	39	# ------------------------------
444 more matches not shown…

Cross-File Repetition273 hits · 1365 pts

Severity	File	Line	Snippet
HIGH	tests/test_multi_agent.py	0	fixture to create and return the default organization.
HIGH	tests/conftest.py	0	fixture to create and return the default organization.
HIGH	tests/integration_test_tool_execution_sandbox.py	0	fixture to create and return the default organization.
HIGH	tests/integration_test_async_tool_sandbox.py	0	fixture to create and return the default organization.
HIGH	…/integration_test_typescript_tool_execution_sandbox.py	0	fixture to create and return the default organization.
HIGH	tests/test_embeddings.py	0	fixture to create and return the default organization.
HIGH	tests/test_agent_serialization_v2.py	0	fixture to create and return the default organization.
HIGH	tests/test_letta_agent_batch.py	0	fixture to create and return the default organization.
HIGH	tests/integration_test_token_counters.py	0	fixture to create and return the default organization.
HIGH	tests/integration_test_modal.py	0	fixture to create and return the default organization.
HIGH	tests/test_managers.py	0	fixture to create and return the default organization.
HIGH	tests/test_managers.py	0	fixture to create and return the default organization.
HIGH	tests/test_agent_serialization.py	0	fixture to create and return the default organization.
HIGH	tests/test_agent_serialization.py	0	fixture to create and return the default organization.
HIGH	tests/test_server_providers.py	0	fixture to create and return the default organization.
HIGH	tests/managers/test_provider_manager.py	0	fixture to create and return the default organization.
HIGH	.github/scripts/model-sweep/conftest.py	0	fixture to create and return the default organization.
HIGH	tests/test_multi_agent.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/conftest.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/integration_test_tool_execution_sandbox.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/integration_test_async_tool_sandbox.py	0	fixture to create and return the default user within the default organization.
HIGH	…/integration_test_typescript_tool_execution_sandbox.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_embeddings.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_agent_serialization_v2.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_letta_agent_batch.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/integration_test_token_counters.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/integration_test_modal.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_managers.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_managers.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_managers.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_agent_serialization.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_agent_serialization.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/test_server_providers.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/managers/test_provider_manager.py	0	fixture to create and return the default user within the default organization.
HIGH	.github/scripts/model-sweep/conftest.py	0	fixture to create and return the default user within the default organization.
HIGH	tests/conftest.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/integration_test_cancellation.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/integration_test_async_tool_sandbox.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/integration_test_send_message.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/integration_test_override_model.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/integration_test_multi_agent.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/test_long_running_agents.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/integration_test_sleeptime_agent.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/integration_test_send_message_v2.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/integration_test_mcp.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/sdk/conftest.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/sdk/mcp_servers_test.py	0	provides the url for the letta server. if letta_server_url is not set, starts the server in a background thread and poll
HIGH	tests/conftest.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/integration_test_async_tool_sandbox.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/integration_test_send_message.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/integration_test_override_model.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/integration_test_system_prompt_prefix_caching.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/integration_test_multi_agent.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/test_long_running_agents.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/integration_test_sleeptime_agent.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/integration_test_builtin_tools.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/integration_test_mcp.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/sdk/conftest.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	tests/sdk/mcp_servers_test.py	0	creates and returns a synchronous letta rest client for testing.
HIGH	.github/scripts/model-sweep/conftest.py	0	creates and returns a synchronous letta rest client for testing.
213 more matches not shown…

Self-Referential Comments436 hits · 1209 pts

Severity	File	Line	Snippet
MEDIUM	tests/locust_test.py	21	# Create a user and get the token
MEDIUM	tests/test_modal_sandbox_v2.py	140	# Create a mock actor
MEDIUM	tests/test_modal_sandbox_v2.py	182	# Create a mock actor
MEDIUM	tests/test_modal_sandbox_v2.py	242	# Create a mock actor
MEDIUM	tests/test_modal_sandbox_v2.py	287	# Create a mock actor
MEDIUM	tests/test_modal_sandbox_v2.py	463	# Create a mock that has a remote attribute
MEDIUM	tests/test_openai_ws_session.py	200	# Create a concrete subclass just for testing
MEDIUM	tests/integration_test_turbopuffer.py	1901	# Create an archive
MEDIUM	tests/integration_test_turbopuffer.py	214	# Create a TPUF-enabled archive
MEDIUM	tests/integration_test_turbopuffer.py	634	# Create a unique archive ID for this test
MEDIUM	tests/integration_test_turbopuffer.py	2172	# Create a conversation
MEDIUM	tests/integration_test_client_side_tools.py	222	# Create the server-side tool
MEDIUM	tests/test_utils.py	708	# Create a dict that when serialized will exceed limit
MEDIUM	tests/test_secret.py	198	# Create a Secret from encrypted value
MEDIUM	tests/integration_test_tool_execution_sandbox.py	251	# Create the SandboxConfigManager
MEDIUM	tests/integration_test_tool_execution_sandbox.py	261	# Create the sandbox configuration
MEDIUM	tests/integration_test_tool_execution_sandbox.py	409	# Create a tool that uses the injected client and agent_id to actually clear a memory block
MEDIUM	tests/integration_test_tool_execution_sandbox.py	456	# Create the tool
MEDIUM	tests/integration_test_tool_execution_sandbox.py	479	# Create the tool in the system
MEDIUM	tests/integration_test_tool_execution_sandbox.py	482	# Create an agent with a memory block
MEDIUM	tests/integration_test_tool_execution_sandbox.py	500	# Create the sandbox for the tool
MEDIUM	tests/integration_test_async_tool_sandbox.py	321	# Create the SandboxConfigManager
MEDIUM	tests/integration_test_async_tool_sandbox.py	331	# Create the sandbox configuration
MEDIUM	tests/integration_test_async_tool_sandbox.py	1246	# Create the tool with proper schema
MEDIUM	tests/integration_test_async_tool_sandbox.py	1282	# Create the sandbox and verify client injection is detected
MEDIUM	tests/integration_test_async_tool_sandbox.py	1343	# Create the sandbox and verify client injection is detected
MEDIUM	tests/integration_test_send_message.py	2385	# # Create a streaming request
MEDIUM	tests/integration_test_override_model.py	373	# Create a conversation
MEDIUM	tests/integration_test_summarizer.py	111	# Create a realistic-looking tool return with repeated data
MEDIUM	tests/integration_test_summarizer.py	1451	# # Create an input message to trigger the agent
MEDIUM	tests/integration_test_summarizer.py	1457	# # Create a proper run record in the database
MEDIUM	tests/integration_test_summarizer.py	1466	# # Create the agent loop using LettaAgentV3
MEDIUM	tests/integration_test_summarizer.py	1485	# # Create a mock response with the required structure
MEDIUM	tests/integration_test_summarizer.py	1634	# # Create an input message to trigger the agent
MEDIUM	tests/integration_test_summarizer.py	1640	# # Create a proper run record in the database
MEDIUM	tests/integration_test_summarizer.py	1649	# # Create the agent loop using LettaAgentV3
MEDIUM	tests/integration_test_summarizer.py	1666	# # Create a mock response with the required structure
MEDIUM	tests/integration_test_summarizer.py	333	# Create a small conversation with ~5 messages
MEDIUM	tests/integration_test_summarizer.py	396	# Create a large tool return
MEDIUM	tests/integration_test_summarizer.py	589	# # Create an extremely large tool return (100k chars)
MEDIUM	tests/integration_test_summarizer.py	694	# Create a conversation with enough messages to trigger summarization
MEDIUM	tests/integration_test_summarizer.py	792	# Create a conversation with enough messages to summarize
MEDIUM	tests/integration_test_summarizer.py	868	# Create a conversation with enough messages to summarize
MEDIUM	tests/integration_test_summarizer.py	1048	# Create the V3 agent loop
MEDIUM	tests/integration_test_summarizer.py	1127	# Create a real summarizer config using the default factory
MEDIUM	tests/integration_test_summarizer.py	1229	# Create a real summarizer config using the default factory
MEDIUM	tests/integration_test_summarizer.py	1343	# # Create a run for the agent using RunManager
MEDIUM	tests/integration_test_summarizer.py	1347	# # Create the agent loop using LettaAgentV3
MEDIUM	tests/integration_test_summarizer.py	1387	# # Create a new run for the repaired agent
MEDIUM	tests/integration_test_summarizer.py	1391	# # Create a new agent loop with the repaired agent state
MEDIUM	tests/integration_test_summarizer.py	1789	# Create a summarizer config with "all" mode
MEDIUM	tests/integration_test_summarizer.py	1862	# Create a summarizer config with "self" mode
MEDIUM	tests/integration_test_summarizer.py	2232	# Create a conversation with enough messages to summarize
MEDIUM	tests/test_sonnet_nonnative_reasoning_buffering.py	153	# Create the stream
MEDIUM	…/integration_test_typescript_tool_execution_sandbox.py	292	# Create a TypeScript tool that has 'agent_state' in its parameters
MEDIUM	…/integration_test_typescript_tool_execution_sandbox.py	435	# Create a tool that checks if the client variable exists
MEDIUM	…/integration_test_typescript_tool_execution_sandbox.py	480	# Create a tool that uses the 'lodash' npm package
MEDIUM	tests/test_agent_serialization_v2.py	337	# Create a mock MCP tool
MEDIUM	tests/test_internal_agents_count.py	46	# Create a simple AgentState-like object for tracking
MEDIUM	tests/test_letta_agent_batch.py	432	# Create the mock for results
376 more matches not shown…

Excessive Try-Catch Wrapping805 hits · 824 pts

Severity	File	Line	Snippet
LOW	test_watchdog_hang.py	88	except Exception as e:
LOW	tests/integration_test_turbopuffer.py	154	except Exception:
LOW	tests/integration_test_turbopuffer.py	346	except Exception as e:
LOW	tests/integration_test_turbopuffer.py	350	except Exception:
LOW	tests/integration_test_turbopuffer.py	1894	except Exception:
LOW	tests/integration_test_turbopuffer.py	48	except Exception:
LOW	tests/integration_test_turbopuffer.py	490	except Exception:
LOW	tests/integration_test_turbopuffer.py	618	except Exception:
LOW	tests/integration_test_turbopuffer.py	757	except Exception:
LOW	tests/integration_test_turbopuffer.py	1141	except Exception:
LOW	tests/integration_test_turbopuffer.py	1202	except Exception:
LOW	tests/integration_test_turbopuffer.py	1265	except Exception:
LOW	tests/integration_test_turbopuffer.py	1337	except Exception:
LOW	tests/integration_test_turbopuffer.py	2398	except Exception:
LOW	tests/integration_test_turbopuffer.py	2480	except Exception:
LOW	tests/integration_test_turbopuffer.py	2536	except Exception:
LOW	tests/test_crypto_utils.py	92	except Exception as e:
LOW	tests/conftest.py	79	except Exception:
LOW	tests/conftest.py	85	except Exception:
LOW	tests/integration_test_tool_execution_sandbox.py	452	except Exception as e:
LOW	tests/integration_test_cancellation.py	124	except Exception:
LOW	tests/integration_test_async_tool_sandbox.py	360	except Exception as e:
LOW	tests/integration_test_async_tool_sandbox.py	1242	except Exception as e:
LOW	tests/integration_test_send_message.py	373	except Exception:
LOW	tests/integration_test_send_message.py	511	except Exception:
LOW	tests/integration_test_send_message.py	667	except Exception:
LOW	tests/integration_test_send_message.py	703	except Exception:
LOW	tests/integration_test_send_message.py	859	except Exception:
LOW	tests/integration_test_send_message.py	1200	except Exception as e:
LOW	tests/integration_test_send_message.py	2026	except Exception as e:
LOW	tests/integration_test_send_message.py	2202	except Exception as e:
LOW	tests/mcp_test.py	216	except Exception as e:
LOW	tests/mcp_test.py	257	except Exception as e:
LOW	tests/mcp_test.py	277	except Exception as e:
LOW	tests/integration_test_override_model.py	117	except Exception as e:
LOW	tests/integration_test_override_model.py	141	except Exception as e:
LOW	tests/test_sonnet_nonnative_reasoning_buffering.py	87	except Exception:
LOW	tests/test_sonnet_nonnative_reasoning_buffering.py	213	except Exception as e:
LOW	tests/integration_test_system_prompt_prefix_caching.py	33	except Exception:
LOW	tests/test_provider_trace_agents.py	94	except Exception:
LOW	tests/test_provider_trace_agents.py	160	except Exception:
LOW	tests/test_internal_agents_count.py	59	except Exception:
LOW	tests/integration_test_usage_tracking.py	126	except Exception as e:
LOW	tests/integration_test_human_in_the_loop.py	381	except Exception:
LOW	tests/integration_test_human_in_the_loop.py	368	except Exception:
LOW	tests/integration_test_human_in_the_loop.py	508	except Exception as e:
LOW	tests/integration_test_human_in_the_loop.py	770	except Exception as e:
LOW	tests/integration_test_human_in_the_loop.py	1035	except Exception as e:
LOW	tests/test_temporal_metrics_local.py	115	except Exception:
LOW	tests/integration_test_send_message_v2.py	138	except Exception:
LOW	tests/integration_test_send_message_v2.py	209	except Exception:
LOW	tests/integration_test_send_message_v2.py	262	except Exception:
LOW	tests/integration_test_chat_completions.py	183	except Exception as e:
LOW	tests/integration_test_modal.py	428	except Exception as e:
LOW	tests/test_managers.py	11220	except Exception:
LOW	tests/test_sources.py	1599	except Exception as e:
LOW	tests/test_tool_schema_parsing.py	121	except Exception as e:
LOW	tests/test_tool_schema_parsing.py	194	except Exception as e:
LOW	tests/test_tool_schema_parsing.py	315	except Exception as e:
LOW	tests/test_tool_schema_parsing.py	676	except Exception as e:
745 more matches not shown…

Docstring Block Structure82 hits · 410 pts

Severity	File	Line	Snippet
HIGH	tests/conftest.py	242	Fetches the current weather for a given location. Args: location (str): The location to ge
HIGH	tests/test_letta_agent_batch.py	56	Fetches the current weather for a given location. Args: location: The location to get the
HIGH	tests/integration_test_chat_completions.py	71	Fetches the current weather for a given location. Args: location (str): The location to ge
HIGH	tests/performance_tests/test_agent_mass_update.py	97	Fetches the current weather for a given location. Parameters: location (str): The location
HIGH	.github/scripts/model-sweep/conftest.py	68	Fetches the current weather for a given location. Parameters: location (str): The location
HIGH	letta/local_llm/grammars/gbnf_grammar_generator.py	518	Generate GBNF Grammar from Pydantic Models. This method takes a list of Pydantic models and uses them to gener
HIGH	letta/server/rest_api/streaming_response.py	161	Wraps a stream generator to provide real-time run cancellation checking. This wrapper periodically checks for
HIGH	letta/schemas/message.py	943	Parse tool response JSON and extract message and status. Args: response_text: Raw JSON response tex
HIGH	letta/schemas/providers/chatgpt_oauth.py	197	Perform OAuth token refresh with OpenAI's token endpoint. Args: creds: Current credentials containi
HIGH	letta/functions/functions.py	328	Dynamically imports a function from a specified module. Args: module_name (str): The name of the modul
HIGH	letta/functions/functions.py	354	Dynamically loads a specific function from a module and generates its JSON schema. Args: module_name (
HIGH	letta/functions/typescript_parser.py	10	Derives the OpenAI JSON schema for a given TypeScript function source code. This parser extracts the function signa
HIGH	letta/functions/async_composio_toolset.py	44	Execute an action asynchronously using the Composio API Args: action (str): The name of th
HIGH	letta/functions/schema_generator.py	527	Extracts the 'Examples:' section from a Google-style docstring. Args: docstring (Optional[str]): The full d
HIGH	letta/functions/ast_parsers.py	56	Resolve a type annotation string into a Python type. Previously, primitive support for int, float, str, dict, l
HIGH	letta/functions/ast_parsers.py	91	Parse the source code to extract annotations for a given function name. Args: source_code (str): The P
HIGH	letta/functions/function_sets/files.py	11	Open one or more files and load their contents into files section in core memory. Maximum of 5 files can be opened simul
HIGH	letta/functions/function_sets/builtin.py	43	Search the web using Exa's AI-powered search engine and retrieve relevant content. Examples: web_search("T
HIGH	letta/functions/function_sets/base.py	23	Memory management tool with various sub-commands for memory block operations. Args: command (str): The
HIGH	letta/functions/function_sets/base.py	95	Search prior conversation history using hybrid search (text + semantic similarity). Args: query (Optio
HIGH	letta/functions/function_sets/base.py	165	Add information to long-term archival memory for later retrieval. Use this tool to store facts, knowledge, or
HIGH	letta/functions/function_sets/base.py	203	Search archival memory using semantic similarity to find relevant information. This tool searches your long-te
HIGH	letta/functions/function_sets/base.py	312	The memory_replace command allows you to replace a specific string in a memory block with a new string. This is use
HIGH	letta/functions/function_sets/base.py	392	The memory_insert command allows you to insert text at a specific location in a memory block. Args: la
HIGH	letta/orm/sqlite_functions.py	75	Validates and transforms embeddings to ensure correct dimensionality. Args: embedding: Input embedding
HIGH	letta/orm/sqlalchemy_base.py	441	The primary accessor for an ORM record. Async version of read method. Args: db_session: the database
HIGH	letta/orm/sqlalchemy_base.py	844	Get the count of rows that match the provided filters. Args: db_session: SQLAlchemy session
HIGH	letta/llm_api/llm_client.py	19	Create an LLM client based on the model endpoint type. Args: provider: The model endpoint
HIGH	letta/llm_api/chatgpt_oauth_client.py	106	Get the ChatGPT OAuth provider and credentials with automatic refresh if needed. Args: llm_config:
HIGH	letta/llm_api/anthropic_client.py	382	Sends a batch request to the Anthropic API using the provided agent messages and tools mappings. Args:
HIGH	letta/helpers/tpuf_client.py	803	Generic query execution for Turbopuffer. Args: namespace_name: Turbopuffer namespace to query
HIGH	letta/helpers/message_helper.py	16	Async helper to fetch image from URL without blocking the event loop. Retries once on timeout to handle transie
HIGH	letta/helpers/crypto_utils.py	105	Encrypt a string using AES-256-GCM (synchronous version). WARNING: This performs CPU-intensive PBKDF2
HIGH	letta/helpers/crypto_utils.py	154	Encrypt a string using AES-256-GCM (async version). Runs the CPU-intensive PBKDF2 key derivation in a
HIGH	letta/helpers/crypto_utils.py	203	Decrypt a string that was encrypted using AES-256-GCM (synchronous version). WARNING: This performs CP
HIGH	letta/helpers/crypto_utils.py	254	Decrypt a string that was encrypted using AES-256-GCM (async version). Runs the CPU-intensive PBKDF2 k
HIGH	letta/services/provider_manager.py	970	Get an LLMConfig from a model handle. Args: handle: The model handle to look up actor:
HIGH	letta/services/provider_manager.py	1097	Get an EmbeddingConfig from a model handle. Args: handle: The model handle to look up a
HIGH	letta/services/agent_generate_completion_manager.py	77	Generate a completion directly from the LLM provider using the agent's configuration. This method make
HIGH	letta/services/tool_manager.py	472	Bulk create or update multiple tools in a single database transaction. Uses optimized PostgreSQL bulk
HIGH	letta/services/tool_manager.py	1397	Search tools using Turbopuffer semantic search. Args: actor: User performing the search
HIGH	letta/services/block_manager.py	800	Bulk-update the `value` field for multiple blocks in one transaction. Args: updates: mappi
HIGH	letta/services/archive_manager.py	293	Create a passage in an archive. Args: archive_id: ID of the archive to add the passage to
HIGH	letta/services/archive_manager.py	383	Create multiple passages in an archive. Args: archive_id: ID of the archive to add the passages to
HIGH	letta/services/job_manager.py	329	Get messages associated with a job using cursor-based pagination. This is a wrapper around get_job_mess
HIGH	letta/services/job_manager.py	387	Get steps associated with a job using cursor-based pagination. This is a wrapper around get_job_message
HIGH	letta/services/job_manager.py	434	Verify that a job exists and the user has the required access. Args: session: The database
HIGH	letta/services/job_manager.py	553	Get all steps associated with a job. Args: job_id: The ID of the job to get steps for
HIGH	letta/services/agent_serialization_manager.py	383	Export agents and their related entities to AgentFileSchema format. Args: agent_ids: List
HIGH	letta/services/agent_serialization_manager.py	509	Import AgentFileSchema into the database. Args: schema: The agent file schema to import
HIGH	letta/services/agent_manager.py	1975	Lists all sources attached to an agent with pagination. Args: agent_id: ID of the agent to
HIGH	letta/services/agent_manager.py	2758	Attaches a tool to an agent. Args: agent_id: ID of the agent to attach the tool to.
HIGH	letta/services/agent_manager.py	2901	Attaches missing core file tools to an agent. Args: agent_state: The current agent state w
HIGH	letta/services/agent_manager.py	2962	Detach all core file tools from an agent. Args: agent_state: The current agent state with
HIGH	letta/services/message_manager.py	910	Most performant query to list messages by directly querying the Message table. This function filters b
HIGH	letta/services/message_manager.py	1276	Search messages across entire organization using Turbopuffer. Args: actor: User performing
HIGH	letta/services/step_manager.py	286	Update the transaction ID for a step. Args: actor: The user making the request step_id:
HIGH	letta/services/step_manager.py	340	Update the stop reason for a step. Args: actor: The user making the request step_id: Th
HIGH	letta/services/step_manager.py	378	Update a step with error information. Args: actor: The user making the request step_id:
HIGH	letta/services/step_manager.py	426	Update a step with success status and final usage statistics. Args: actor: The user making the requ
22 more matches not shown…

Deep Nesting449 hits · 365 pts

Severity	File	Line
LOW	tests/test_modal_sandbox_v2.py	450
LOW	tests/conftest.py	24
LOW	tests/conftest.py	70
LOW	tests/integration_test_cancellation.py	91
LOW	tests/integration_test_async_tool_sandbox.py	68
LOW	tests/integration_test_send_message.py	215
LOW	tests/integration_test_send_message.py	786
LOW	tests/integration_test_send_message.py	895
LOW	tests/integration_test_send_message.py	983
LOW	tests/integration_test_send_message.py	1009
LOW	tests/integration_test_send_message.py	984
LOW	tests/mcp_test.py	240
LOW	tests/mcp_test.py	260
LOW	tests/mcp_test.py	280
LOW	tests/integration_test_override_model.py	43
LOW	tests/test_sonnet_nonnative_reasoning_buffering.py	134
LOW	tests/integration_test_agent_tool_graph.py	501
LOW	tests/test_letta_agent_batch.py	362
LOW	tests/test_letta_agent_batch.py	448
LOW	tests/test_letta_agent_batch.py	615
LOW	tests/test_letta_agent_batch.py	781
LOW	tests/integration_test_multi_agent.py	18
LOW	tests/integration_test_multi_agent.py	135
LOW	tests/integration_test_multi_agent.py	210
LOW	tests/integration_test_multi_agent.py	325
LOW	tests/test_sdk_client.py	1069
LOW	tests/test_sdk_client.py	1154
LOW	tests/test_sdk_client.py	1899
LOW	tests/test_sdk_client.py	2164
LOW	tests/test_long_running_agents.py	18
LOW	tests/integration_test_human_in_the_loop.py	1175
LOW	tests/test_file_processor.py	226
LOW	tests/integration_test_sleeptime_agent.py	16
LOW	tests/integration_test_send_message_v2.py	283
LOW	tests/integration_test_send_message_v2.py	528
LOW	tests/test_managers.py	5081
LOW	tests/test_tool_schema_parsing.py	202
LOW	tests/test_agent_serialization.py	39
LOW	tests/test_agent_serialization.py	268
LOW	tests/test_agent_serialization.py	486
LOW	tests/integration_test_modal_sandbox_v2.py	632
LOW	tests/integration_test_builtin_tools.py	24
LOW	tests/integration_test_builtin_tools.py	161
LOW	tests/integration_test_clickhouse_llm_traces.py	180
LOW	tests/integration_test_mcp.py	27
LOW	tests/test_prompt_caching.py	605
LOW	tests/test_prompt_caching.py	697
LOW	tests/test_prompt_caching.py	974
LOW	tests/performance_tests/test_agent_mass_creation.py	253
LOW	tests/managers/test_cancellation.py	1143
LOW	tests/managers/test_agent_manager.py	1876
LOW	tests/managers/test_agent_manager.py	1990
LOW	tests/managers/test_mcp_manager.py	238
LOW	tests/managers/test_tool_manager.py	1207
LOW	tests/sdk/conftest.py	13
LOW	tests/sdk/conftest.py	64
LOW	tests/sdk/conftest.py	111
LOW	tests/sdk/conftest.py	151
LOW	tests/sdk/mcp_servers_test.py	31
LOW	tests/sdk/search_test.py	294
389 more matches not shown…

Redundant / Tautological Comments205 hits · 310 pts

Severity	File	Line	Snippet
LOW	tests/integration_test_turbopuffer.py	150	# Check if our message ID is in the results
LOW	tests/integration_test_turbopuffer.py	64	# Set environment to DEV for testing
LOW	tests/conftest.py	187	# Set environment to DEV for testing
LOW	tests/integration_test_send_message.py	378	# Check if next message is LettaStopReason to detect this case
LOW	tests/integration_test_send_message.py	831	# Check if there are tool calls in the response
LOW	tests/integration_test_send_message.py	905	# Check if chunks are raw SSE strings (from background streaming)
LOW	tests/integration_test_summarizer.py	1567	# # Check if content has system_alert type with the summary message (object form)
LOW	tests/integration_test_summarizer.py	1745	# # Check if content has system_alert type with the summary message (object form)
LOW	tests/test_sonnet_nonnative_reasoning_buffering.py	200	# Check if this is inner thoughts
LOW	tests/test_sonnet_nonnative_reasoning_buffering.py	251	# Check if we detected large bursts
LOW	tests/test_sdk_client.py	631	# Check if modify method exists
LOW	tests/test_temporal_metrics_local.py	109	# Check if DogStatsD is listening
LOW	tests/integration_test_send_message_v2.py	752	# Check if tool calls are grouped in a single message (parallel) or separate messages (sequential)
LOW	tests/integration_test_send_message_v2.py	777	# Check if we have true parallel tool calling
LOW	tests/integration_test_send_message_v2.py	780	# Check if the single message contains multiple tool calls
LOW	tests/test_tool_schema_parsing.py	150	# Check if we expect the conversion to fail
LOW	tests/integration_test_multi_modal_tool_returns.py	398	# Check if this is a tool return message that might contain our image
LOW	tests/test_server_providers.py	2383	# Check if provider already exists
LOW	tests/test_server_providers.py	2633	# Set last_synced to indicate models are already synced
LOW	tests/test_prompt_caching.py	827	# Check if ANY of the follow-up messages had a cache hit
LOW	tests/test_prompt_caching.py	961	# Check if ANY of the follow-up messages had a cache hit
LOW	tests/managers/test_cancellation.py	1280	# Check if message has tool_returns (new format) or tool_return (old format)
LOW	tests/managers/test_agent_manager.py	2008	# Check if expected type is in the union
LOW	otel/start-otel-collector.sh	92	# Check if update is needed
LOW	sandbox/node_server.py	66	# Check if there was an error
LOW	.github/scripts/model-sweep/conftest.py	166	# Check if already running
LOW	…d06594144ef3_add_and_migrate_encrypted_columns_for_.py	37	# Check if encryption key is available
LOW	…rsions/8149a781ac1b_backfill_encrypted_columns_for_.py	27	# Check if encryption key is available
LOW	…c/versions/74e860718e0d_add_archival_memory_sharing.py	57	# Check if archives table already exists
LOW	…/versions/eff256d296cb_mcp_encrypted_data_migration.py	30	# Check if encryption key is available
LOW	letta/streaming_utils.py	287	# Check if this same chunk also contains the terminating quote (and optional delimiter)
LOW	letta/utils.py	1167	# Check if coro is an async generator instead of a coroutine
LOW	letta/agent.py	553	# Check if inner thoughts is in the function call arguments (possible apparently if you are using Azure)
LOW	letta/agent.py	1217	# Check if there's a summary message in the message queue
LOW	letta/agent.py	1350	# Check if there's a summary message in the message queue
LOW	letta/agent.py	1488	# Check if there's a summary message in the message queue
LOW	letta/local_llm/function_parser.py	46	# Check if it's a user message or system message
LOW	letta/local_llm/utils.py	50	# Check if the file exists
LOW	letta/local_llm/settings/settings.py	29	# Check if settings_dir folder exists (if not, create it)
LOW	letta/local_llm/grammars/gbnf_grammar_generator.py	473	# Check if the field is optional (not required)
LOW	letta/local_llm/grammars/gbnf_grammar_generator.py	85	if not parts: # Check if the list is empty
LOW	letta/agents/letta_agent_v3.py	289	# Check if we should use SGLang native adapter for multi-turn RL training.
LOW	letta/agents/letta_agent_v3.py	358	# Check if step was cancelled - break out of the step loop
LOW	letta/agents/letta_agent_v3.py	424	# Set context_tokens to expose actual context window usage (vs accumulated prompt_tokens)
LOW	letta/agents/letta_agent_v3.py	502	# Check if we should use SGLang native adapter for multi-turn RL training
LOW	letta/agents/letta_agent_v3.py	615	# Check if step was cancelled - break out of the step loop
LOW	letta/agents/letta_agent_v3.py	696	# Set context_tokens to expose actual context window usage (vs accumulated prompt_tokens)
LOW	letta/agents/letta_agent_v3.py	1184	# Check if there's a fallback route for the current model
LOW	letta/agents/letta_agent_v3.py	1625	# Check if there are required-before-exit tools that haven't been called
LOW	letta/agents/letta_agent_v3.py	1999	# Check if the LLM hit max_tokens (finish_reason == "length")
LOW	letta/server/server.py	1812	# Check if the server name is already in the config
LOW	letta/server/server.py	1883	# Check if the server name is already in the config
LOW	letta/server/startup.sh	23	# Check if we're configured for external Redis
LOW	letta/server/startup.sh	38	# Check if we're configured for external Postgres
LOW	letta/server/ws_api/server.py	110	# Check if a port argument is provided
LOW	letta/server/ws_api/interface.py	37	if self.clients: # Check if there are any clients connected
LOW	letta/server/rest_api/streaming_response.py	132	# Check if there's anything left
LOW	letta/server/rest_api/proxy_helpers.py	319	# Set max_tokens to budget_tokens + reasonable buffer for response
LOW	letta/server/rest_api/proxy_helpers.py	28	# Check if entire message is a policy spec (starts with tag)
LOW	letta/server/rest_api/proxy_helpers.py	33	# Check if policy spec is appended (with prefix)
145 more matches not shown…

Unused Imports320 hits · 292 pts

Severity	File	Line
LOW	tests/test_openai_ws_session.py	5
LOW	tests/integration_test_tool_execution_sandbox.py	13
LOW	tests/integration_test_async_tool_sandbox.py	18
LOW	tests/integration_test_async_tool_sandbox.py	383
LOW	tests/integration_test_send_message.py	32
LOW	tests/integration_test_modal.py	14
LOW	…sions/b888f21b151f_add_vector_db_provider_to_source.py	26
LOW	…sions/b888f21b151f_add_vector_db_provider_to_source.py	26
LOW	letta/__init__.py	25
LOW	letta/__init__.py	26
LOW	letta/__init__.py	27
LOW	letta/__init__.py	28
LOW	letta/__init__.py	29
LOW	letta/__init__.py	30
LOW	letta/__init__.py	31
LOW	letta/__init__.py	31
LOW	letta/__init__.py	31
LOW	letta/__init__.py	32
LOW	letta/__init__.py	33
LOW	letta/__init__.py	34
LOW	letta/__init__.py	34
LOW	letta/__init__.py	34
LOW	letta/__init__.py	34
LOW	letta/__init__.py	34
LOW	letta/__init__.py	41
LOW	letta/__init__.py	42
LOW	letta/__init__.py	43
LOW	letta/__init__.py	44
LOW	letta/__init__.py	45
LOW	letta/__init__.py	46
LOW	letta/__init__.py	47
LOW	letta/__init__.py	19
LOW	letta/errors.py	7
LOW	letta/errors.py	8
LOW	letta/serialize_schemas/__init__.py	1
LOW	letta/agents/base_agent.py	18
LOW	letta/agents/agent_loop.py	12
LOW	letta/agents/letta_agent.py	9
LOW	letta/agents/letta_agent.py	51
LOW	letta/agents/base_agent_v2.py	14
LOW	letta/agents/base_agent_v2.py	14
LOW	letta/agents/base_agent_v2.py	15
LOW	letta/agents/voice_sleeptime_agent.py	4
LOW	letta/agents/letta_agent_v3.py	73
LOW	letta/server/rest_api/dependencies.py	13
LOW	letta/server/rest_api/routers/v1/tags.py	8
LOW	letta/server/rest_api/routers/v1/internal_agents.py	5
LOW	letta/server/rest_api/routers/v1/users.py	11
LOW	letta/server/rest_api/routers/v1/git_http.py	20
LOW	letta/server/rest_api/routers/v1/internal_runs.py	10
LOW	letta/server/rest_api/routers/v1/archives.py	12
LOW	letta/server/rest_api/routers/v1/identities.py	20
LOW	letta/server/rest_api/routers/v1/agents.py	52
LOW	letta/server/rest_api/routers/v1/voice.py	9
LOW	letta/server/rest_api/routers/v1/jobs.py	9
LOW	letta/server/rest_api/routers/v1/providers.py	12
LOW	letta/server/rest_api/routers/v1/organizations.py	9
LOW	letta/server/rest_api/routers/v1/llms.py	10
LOW	letta/server/rest_api/routers/v1/internal_templates.py	10
LOW	letta/server/rest_api/routers/v1/runs.py	24
260 more matches not shown…

Verbosity Indicators128 hits · 188 pts

Severity	File	Line	Snippet
LOW	tests/integration_test_client_side_tools.py	92	# Step 1: User asks for the secret code - agent should call the tool
LOW	tests/integration_test_client_side_tools.py	109	# Step 2: Provide the tool return (simulating client-side execution)
LOW	tests/integration_test_client_side_tools.py	152	# Step 3: Ask the agent what the secret code was (testing memory/context)
LOW	tests/integration_test_client_side_tools.py	173	# Step 4: Validate the full conversation history makes sense
LOW	tests/integration_test_client_side_tools.py	242	# Step 1: Call the tool WITH client_tools specified - should pause for approval
LOW	tests/integration_test_client_side_tools.py	261	# Step 2: Provide client-side tool return
LOW	tests/integration_test_client_side_tools.py	286	# Step 3: Verify the client value was used, not the server value
LOW	tests/integration_test_client_side_tools.py	306	# Step 4: Test that WITHOUT client_tools, server tool executes directly
LOW	tests/integration_test_client_side_tools.py	354	# Step 1: Trigger the client-side tool call
LOW	tests/integration_test_client_side_tools.py	366	# Step 2: Provide an error response
LOW	tests/test_mcp_encryption.py	251	# Step 1: Create OAuth session (without tokens initially)
LOW	tests/test_mcp_encryption.py	264	# Step 2: Update session with tokens (simulating OAuth callback)
LOW	tests/integration_test_system_prompt_prefix_caching.py	156	# Step 1: Get initial context window
LOW	tests/integration_test_system_prompt_prefix_caching.py	161	# Step 2: Get the human block
LOW	tests/integration_test_system_prompt_prefix_caching.py	170	# Step 3: Update block via agent-specific endpoint (triggers recompilation)
LOW	tests/integration_test_system_prompt_prefix_caching.py	179	# Step 4: Verify the block was updated
LOW	tests/integration_test_system_prompt_prefix_caching.py	183	# Step 5: Get context window and verify core memory was recompiled
LOW	tests/integration_test_system_prompt_prefix_caching.py	192	# Step 6: System prompt template should NOT change (only memory content changes)
LOW	tests/integration_test_system_prompt_prefix_caching.py	205	# Step 1: Get initial system prompt
LOW	tests/integration_test_system_prompt_prefix_caching.py	209	# Step 2: Manually update a block via the API
LOW	tests/integration_test_system_prompt_prefix_caching.py	58	# Step 1: Get initial context window, system prompt, and human block value
LOW	tests/integration_test_system_prompt_prefix_caching.py	72	# Step 2: Tell the agent to update its memory using the memory tool
LOW	tests/integration_test_system_prompt_prefix_caching.py	84	# Step 3: Verify block was modified but system prompt hasn't changed
LOW	tests/integration_test_system_prompt_prefix_caching.py	97	# Step 4: Send another message to the agent
LOW	tests/integration_test_system_prompt_prefix_caching.py	109	# Step 5: Verify system prompt still hasn't changed
LOW	tests/integration_test_system_prompt_prefix_caching.py	114	# Step 6: Manually update a block via the API
LOW	tests/integration_test_system_prompt_prefix_caching.py	129	# Step 7: Send another message and verify system prompt still hasn't changed
LOW	tests/integration_test_system_prompt_prefix_caching.py	224	# Step 3: Reset messages (this should trigger system prompt rebuild)
LOW	tests/integration_test_system_prompt_prefix_caching.py	227	# Step 4: Verify system prompt HAS changed and includes the new memory
LOW	tests/test_sdk_client.py	380	# Step 1: Add multiple tags to the agent
LOW	tests/test_sdk_client.py	386	# Step 2: Retrieve tags for the agent and verify they match the added tags
LOW	tests/test_sdk_client.py	392	# Step 3: Retrieve agents by each tag to ensure the agent is associated correctly
LOW	tests/test_sdk_client.py	397	# Step 4: Delete a specific tag from the agent and verify its removal
LOW	tests/test_sdk_client.py	406	# Step 5: Delete all remaining tags from the agent
LOW	tests/test_sdk_client.py	367	# Step 0: create an agent with no tags
LOW	tests/integration_test_human_in_the_loop.py	1395	# Step 4: Accumulate remaining chunks (already collected above)
LOW	tests/integration_test_human_in_the_loop.py	1397	# Step 5: Verify we got chunks AND a cancelled stop reason
LOW	tests/integration_test_human_in_the_loop.py	1405	# Step 6: Verify run status is cancelled
LOW	tests/integration_test_human_in_the_loop.py	1412	# Step 7: Verify that approval response message is persisted
LOW	tests/integration_test_human_in_the_loop.py	1418	# Step 8: Attempt retry with same response
LOW	tests/integration_test_human_in_the_loop.py	1438	# Step 9: Accumulate chunks
LOW	tests/integration_test_human_in_the_loop.py	1441	# Step 10: Verify we got chunks AND an end_turn stop reason
LOW	tests/integration_test_human_in_the_loop.py	1449	# Step 11: Verify keep-alive message was sent
LOW	tests/integration_test_human_in_the_loop.py	1515	# Step 4: Verify we got cancelled
LOW	tests/integration_test_human_in_the_loop.py	1520	# Step 6: Verify tool return message is persisted
LOW	tests/integration_test_human_in_the_loop.py	1525	# Step 7: Call compact with mode='all' to evict all messages from context
LOW	tests/integration_test_human_in_the_loop.py	1531	# Step 8: Verify only system and summary messages remain in context (should be 2)
LOW	tests/integration_test_human_in_the_loop.py	1538	# Step 9: Retry the original approval response - should succeed via idempotency check
LOW	tests/integration_test_human_in_the_loop.py	1351	# Step 1: Send message that triggers approval request
LOW	tests/integration_test_human_in_the_loop.py	1358	# Step 2: Start approval stream and wait for first chunk (sentinel approach)
LOW	tests/integration_test_human_in_the_loop.py	1379	# Step 3: Wait for first chunk before triggering cancellation
LOW	tests/integration_test_human_in_the_loop.py	1471	# Step 1: Send message that triggers approval request
LOW	tests/integration_test_human_in_the_loop.py	1478	# Step 2: Start approval stream and wait for first chunk (sentinel approach)
LOW	tests/integration_test_human_in_the_loop.py	1499	# Step 3: Wait for first chunk before triggering cancellation
LOW	tests/integration_test_human_in_the_loop.py	1558	# Step 10: Accumulate chunks
LOW	tests/integration_test_human_in_the_loop.py	1561	# Step 11: Verify we got chunks AND an end_turn stop reason (not an error)
LOW	tests/test_managers.py	6569	# Step 1: Create block
LOW	tests/test_managers.py	6575	# Step 2: Update to v2, checkpoint => seq=2
LOW	tests/test_managers.py	6581	# Step 3: Update to v3, checkpoint => seq=3
LOW	tests/test_managers.py	6732	# Step 1: create initial block => seq=1
68 more matches not shown…

Over-Commented Block161 hits · 108 pts

Severity	File	Line	Snippet
LOW	conf.yaml	1	# Letta Configuration File
LOW	conf.yaml	161	# Letta Client (LETTA_DEFAULT_*)
LOW	conf.yaml	281	# api_key: ""
LOW	conf.yaml	301
LOW	conf.yaml	321	# sglang:
LOW	conf.yaml	341	# sandbox_template_id: ""
LOW	conf.yaml	361
LOW	conf.yaml	381	# health_metrics_enabled: false
LOW	conf.yaml	401	#
LOW	alembic.ini	1	# A generic, single database configuration.
LOW	alembic.ini	21	# Any required deps can installed by adding `alembic[tz]` to the pip requirements
LOW	alembic.ini	41	# The path separator used here should be the separator specified by "version_path_separator" below.
LOW	alembic.ini	61	# output_encoding = utf-8
LOW	tests/locust_test.py	81	# response = requests.post(f"{self.base_url}/api/agents/{agent_id}/messages", json=request.model_dump(), head
LOW	tests/locust_test.py	101	# try:
LOW	tests/test_crypto_utils.py	421	This simulates the real-world scenario of existing encrypted values
LOW	tests/integration_test_async_tool_sandbox.py	41
LOW	tests/integration_test_send_message.py	1901	assert_greeting_with_assistant_message_response(messages_from_db, model_handle, model_settings, from_db=True)
LOW	tests/integration_test_send_message.py	1921	# client.agents.update(agent_id=agent_state.id, model=model_handle, model_settings=model_settings)
LOW	tests/integration_test_send_message.py	2281	# # ids=[c.model for c in TESTED_LLM_CONFIGS],
LOW	tests/integration_test_send_message.py	2301	# # Verify the job was created
LOW	tests/integration_test_send_message.py	2321	# def test_job_cancellation_endpoint_validation(
LOW	tests/integration_test_send_message.py	2341	# disable_e2b_api_key: Any,
LOW	tests/integration_test_send_message.py	2361	# # Try to cancel the completed job - should fail
LOW	tests/integration_test_send_message.py	2381	# This verifies that jobs continue even if the client "disconnects" (simulated by not consuming the stream).
LOW	tests/integration_test_send_message.py	2401	# )
LOW	tests/integration_test_send_message.py	2561
LOW	tests/integration_test_summarizer.py	41
LOW	tests/integration_test_summarizer.py	581	# TESTED_LLM_CONFIGS,
LOW	tests/integration_test_summarizer.py	601	# content=[
LOW	tests/integration_test_summarizer.py	621	# ],
LOW	tests/integration_test_summarizer.py	641	# # Find tool return messages in the result and verify truncation occurred
LOW	tests/integration_test_summarizer.py	1301	)
LOW	tests/integration_test_summarizer.py	1321	# """
LOW	tests/integration_test_summarizer.py	1341	# agent_state = await server.agent_manager.create_agent_async(agent_create, actor=actor)
LOW	tests/integration_test_summarizer.py	1361	# )
LOW	tests/integration_test_summarizer.py	1381	# # Reload agent state after repairs
LOW	tests/integration_test_summarizer.py	1401	# # Verify we got a valid response after repair
LOW	tests/integration_test_summarizer.py	1421	# from unittest.mock import patch
LOW	tests/integration_test_summarizer.py	1441	# messages.append(
LOW	tests/integration_test_summarizer.py	1461	# id=test_run_id,
LOW	tests/integration_test_summarizer.py	1481	# from unittest.mock import MagicMock
LOW	tests/integration_test_summarizer.py	1501	# response=mock_response,
LOW	tests/integration_test_summarizer.py	1521	# stream_tokens=True,
LOW	tests/integration_test_summarizer.py	1541	# # Verify a summary message exists with the correct format
LOW	tests/integration_test_summarizer.py	1561	# if "prior messages" in text_to_check and "hidden" in text_to_check and "summary of the previous" in
LOW	tests/integration_test_summarizer.py	1581	# # Verify we attempted multiple invocations (the failing one + retry after summarization)
LOW	tests/integration_test_summarizer.py	1601	# Note: This test only runs with OpenAI since it uses OpenAI-specific error handling.
LOW	tests/integration_test_summarizer.py	1621	# content=[TextContent(type="text", text=f"User message {i}: This is test message number {i}.")],
LOW	tests/integration_test_summarizer.py	1641	# run_manager = RunManager()
LOW	tests/integration_test_summarizer.py	1661	# if call_count == 1:
LOW	tests/integration_test_summarizer.py	1681	# message="This model's maximum context length is 8000 tokens. However, your messages resulted in 12000 t
LOW	tests/integration_test_summarizer.py	1701	# run_id=test_run_id,
LOW	tests/integration_test_summarizer.py	1721	# # "prior messages ... have been hidden" and "summary of the previous"
LOW	tests/integration_test_summarizer.py	1741	# summary_message_text = parsed.get("message")
LOW	tests/test_providers.py	261	assert len(embedding_models) == 0 # embedding models currently not supported by SGLang
LOW	tests/integration_test_agent_tool_graph.py	861	# Check order
LOW	tests/integration_test_agent_tool_graph.py	881	# -- flip_coin
LOW	tests/integration_test_agent_tool_graph.py	901	# child_output_mapping={
LOW	tests/integration_test_agent_tool_graph.py	921	# found_secret_word = False
101 more matches not shown…

AI Slop Vocabulary48 hits · 108 pts

Severity	File	Line	Snippet
MEDIUM	tests/integration_test_summarizer.py	1307	### in order to leverage caching (for self compaction)
MEDIUM	tests/test_agent_serialization_v2.py	772	"""Test file export functionality with comprehensive validation"""
MEDIUM	tests/integration_test_usage_tracking.py	449	# Use Anthropic Sonnet 4.5 for this test as it has the most comprehensive caching
MEDIUM	tests/test_managers.py	1279	# Create an agent using the comprehensive fixture.
MEDIUM	tests/test_managers.py	1297	# Create an agent using the comprehensive fixture.
MEDIUM	tests/test_managers.py	3612	"""Test comprehensive tag functionality for passages."""
MEDIUM	tests/managers/conftest.py	364	"""Create a comprehensive test agent with all features."""
MEDIUM	tests/managers/test_passage_manager.py	815	"""Test comprehensive tag functionality for passages."""
MEDIUM	tests/managers/test_agent_manager.py	1210	# Create an agent using the comprehensive fixture.
MEDIUM	tests/managers/test_agent_manager.py	1228	# Create an agent using the comprehensive fixture.
MEDIUM	…empty_archival/agent_state/2024-01-11_12_44_32_PM.json	1	{"model": "gpt-4", "system": "You are Letta, the latest version of Limnal Corporation's digital companion, developed in
MEDIUM	…empty_archival/agent_state/2024-01-11_12_44_33_PM.json	1	{"model": "gpt-4", "system": "You are Letta, the latest version of Limnal Corporation's digital companion, developed in
MEDIUM	…nt_test_attach/agent_state/2024-01-11_12_42_19_PM.json	1	{"model": "gpt-4", "system": "You are Letta, the latest version of Limnal Corporation's digital companion, developed in
MEDIUM	…nt_test_attach/agent_state/2024-01-11_12_42_17_PM.json	1	{"model": "gpt-4", "system": "You are Letta, the latest version of Limnal Corporation's digital companion, developed in
MEDIUM	…nts/agent_test/agent_state/2024-01-11_12_43_59_PM.json	1	{"model": "gpt-4", "system": "You are Letta, the latest version of Limnal Corporation's digital companion, developed in
MEDIUM	…nts/agent_test/agent_state/2024-01-11_12_43_57_PM.json	1	{"model": "gpt-4", "system": "You are Letta, the latest version of Limnal Corporation's digital companion, developed in
MEDIUM	letta/streaming_utils.py	268	# Not in message yet: accumulate until we see '<json_key>': (robust to split fragments)
MEDIUM	letta/agent.py	1740	# If it exists in the input message, elevate it to the 'message' level
LOW	letta/agent.py	950	# Fallback if for some reason context_window is missing, just set to the default
LOW	letta/agent.py	1134	# Fallback if for some reason context_window is missing, just set to the default
MEDIUM	letta/agent.py	314	"""Get response from LLM API with robust retry mechanism."""
LOW	letta/serialize_schemas/marshmallow_agent.py	117	# no user messages, just return system message
LOW	letta/serialize_schemas/marshmallow_agent.py	152	# no user messages, just return system message
MEDIUM	letta/agents/letta_agent_v3.py	1238	# NOTE: we no longer refresh the system prompt before compaction so we can leverage cach
MEDIUM	letta/agents/letta_agent_v3.py	1461	# NOTE: we no longer refresh the system prompt before compaction so we can leverage cache for self m
MEDIUM	letta/server/rest_api/interface.py	307	# To make streamed arguments robust, we add a JSON-aware incremental
LOW	letta/server/rest_api/interface.py	1120	# Example where we just pass through the raw stream from the underlying OpenAI SSE stream
LOW	letta/server/rest_api/auth_token.py	15	# user is admin so we just return the default uuid
LOW	letta/server/rest_api/routers/v1/tools.py	557	# TODO: don't do this in the future (just return MCPServer)
LOW	letta/server/rest_api/routers/v1/tools.py	612	# TODO: don't do this in the future (just return MCPServer)
LOW	letta/schemas/sandbox_config.py	45	# If `data` is not a dict (e.g., it's another Pydantic model), just return it
LOW	letta/schemas/sandbox_config.py	73	# If `data` is not a dict (e.g., it's another Pydantic model), just return it
LOW	letta/schemas/message.py	641	# TODO remove the cast and just return the native type
LOW	letta/schemas/message.py	728	# If assistant mode is off, just create one ToolCallMessage with all tool calls
LOW	letta/schemas/providers/anthropic.py	138	# just use a cheap model to count some tokens - as of 5/7/2025 this is faster than fetching the list of mode
LOW	letta/schemas/providers/base.py	96	# Simplified asyncio handling - just use asyncio.run()
LOW	letta/schemas/providers/base.py	120	# Simplified asyncio handling - just use asyncio.run()
LOW	letta/functions/typescript_parser.py	180	# Handle union types (simplified - just use string)
LOW	letta/functions/mcp_client/types.py	94	# If the result still contains unreplaced templates, just return original value
MEDIUM	letta/orm/sqlalchemy_base.py	278	# TODO (cliandy): can make this more robust down the line
MEDIUM	letta/llm_api/openai_client.py	574	# don't raise error since this isn't robust against edge cases
LOW	letta/llm_api/openai_client.py	646	# For text or json_object, just pass the type
MEDIUM	letta/services/mcp_manager.py	1130	# TODO: @jnjpng make this check more robust and remove direct os.getenv
MEDIUM	letta/services/mcp_server_manager.py	1326	# TODO: @jnjpng make this check more robust and remove direct os.getenv
MEDIUM	letta/services/tool_sandbox/modal_sandbox_v2.py	418	# Start with a more robust base image with development tools
LOW	letta/interfaces/anthropic_streaming_interface.py	150	# This interface doesn't track cache tokens, so we just use the raw values
LOW	letta/interfaces/anthropic_streaming_interface.py	702	# This interface doesn't track cache tokens, so we just use the raw values
MEDIUM	letta/interfaces/openai_streaming_interface.py	476	# Minimal, robust extraction: only emit the value of "message".

Cross-Language Confusion18 hits · 105 pts

Severity	File	Line	Snippet
HIGH	…/integration_test_typescript_tool_execution_sandbox.py	595	assert "let client: any = null;" in script
HIGH	…/integration_test_typescript_tool_execution_sandbox.py	615	result, agent_state = parse_typescript_result('{"results": 42, "agent_state": null}')
HIGH	tests/managers/test_message_manager.py	1087	arguments='{"message": {"status": "success", "data": {"count": 42, "items": ["a", "b"]}, "meta": null}}'
HIGH	letta/streaming_utils.py	106	# numbers, null, or a nested object/array) streamed in next, the stream
HIGH	letta/local_llm/json_parser.py	63	- if (function call is not send_message && prev message['role'] == user): insert heartbeat
HIGH	letta/server/rest_api/routers/v1/groups.py	168	include_return_message_types: Optional[List[MessageType]] = Query(None, description="Message types to include in res
HIGH	letta/server/rest_api/routers/v1/agents.py	1601	include_return_message_types: Optional[List[MessageType]] = Query(None, description="Message types to include in res
HIGH	letta/server/rest_api/routers/v1/messages.py	46	None, description="Message types to include in response. When null, all message types are returned."
HIGH	letta/server/rest_api/routers/v1/conversations.py	214	include_return_message_types: Optional[List[MessageType]] = Query(None, description="Message types to include in res
HIGH	letta/schemas/providers.py	283	# "param": null,
HIGH	letta/schemas/providers/openai.py	184	# "param": null,
HIGH	letta/functions/schema_validator.py	173	# They represent union types (e.g., string \| null)
HIGH	letta/functions/helpers.py	288	# If we have exactly one type and null, make it Optional
HIGH	letta/llm_api/helpers.py	39	# If it's simple primitives only (string, null, integer, boolean, etc), flatten to type array
HIGH	letta/services/mcp_server_manager.py	9	from sqlalchemy import delete, desc, null, select
HIGH	letta/services/tool_sandbox/typescript_generator.py	140	"let client: any = null;",
HIGH	letta/services/tool_sandbox/typescript_generator.py	209	lines.append("const _output = { results: _result, agent_state: null };")
HIGH	letta/services/provider_trace_backends/clickhouse.py	96	# OpenAI Responses API returns {"error": null} on success

Hallucination Indicators4 hits · 40 pts

Severity	File	Line	Snippet
CRITICAL	letta/orm/sqlalchemy_base.py	270	query = query.join(cls.identities).filter(cls.identities.property.mapper.class_.identifier_key.in_(identifie
CRITICAL	letta/jobs/llm_batch_job_polling.py	55	response = await server.anthropic_async_client.beta.messages.batches.retrieve(batch_id_str)
CRITICAL	letta/jobs/llm_batch_job_polling.py	80	results = await server.anthropic_async_client.beta.messages.batches.results(batch_resp_id)
CRITICAL	letta/services/block_manager.py	404	BlockModel.identities.property.mapper.class_.identifier_key.in_(identifier_keys)

Synthetic Comment Markers4 hits · 25 pts

Severity	File	Line	Snippet
HIGH	letta/services/tool_sandbox/local_sandbox.py	149	print(f"Auto-generated code for debugging:\n\n{code}")
HIGH	letta/services/tool_executor/tool_execution_sandbox.py	49	# This is the variable name in the auto-generated code that contains the function results
HIGH	letta/services/tool_executor/tool_execution_sandbox.py	167	logger.error(f"Logging out tool {self.tool_name} auto-generated code for debugging: \n\n{code}")
HIGH	letta/services/tool_executor/tool_execution_sandbox.py	233	logger.debug(f"Tool {self.tool_name} auto-generated code for debugging: \n\n{code}")

Overly Generic Function Names20 hits · 12 pts

Severity	File	Line	Snippet
LOW	tests/test_modal_sandbox_v2.py	338	def test_function(x: int, y: int) -> int:
LOW	tests/test_modal_sandbox_v2.py	395	mock_tool.source_code = "def test_function(x, y): return x * y"
LOW	tests/test_modal_sandbox_v2.py	408	mock_tool.source_code = "def test_function(x, y): return x + y" # Reset
LOW	tests/test_utils.py	92	def my_function(a: int, b: float, c: str, d: list, e: dict, f: CustomClass = None):
LOW	tests/conftest.py	111	def test_function(e2b_sandbox_mode, ...):
LOW	tests/conftest.py	177	def test_function(turbopuffer_mode, ...):
LOW	tests/test_sdk_client.py	1722	# def main_function(x: int, y: int) -> int:
LOW	tests/test_sdk_client.py	1752	# def process_data(data: str, count: int) -> str:
LOW	tests/test_sdk_client.py	1639	def main_function(x: int, y: int) -> int:
LOW	tests/managers/test_tool_manager.py	1805	def test_function(arg1: str) -> str:
LOW	tests/managers/test_tool_manager.py	1834	def test_function(arg1: str, arg2: int) -> str:
LOW	tests/managers/test_tool_manager.py	1870	def test_function(arg1: str, arg2: int = 5) -> str:
LOW	tests/managers/test_tool_manager.py	1903	def test_function(old_arg: str) -> str:
LOW	tests/managers/test_tool_manager.py	1938	def test_function():
LOW	tests/managers/test_tool_manager.py	1957	def test_function(arg1: str) -> str:
LOW	tests/managers/test_tool_manager.py	1986	def test_function() -> str:
LOW	tests/managers/test_tool_manager.py	2019	def test_function() -> str:
LOW	tests/managers/test_tool_manager.py	2034	def test_function(new_arg: str) -> str:
LOW	tests/managers/test_tool_manager.py	2067	source_code="def test_function(): pass",
LOW	letta/validators.py	136	def my_function(agent_id: str, folder_id: str):

Dead Code5 hits · 10 pts

Severity	File	Line
MEDIUM	tests/managers/test_cancellation.py	1504
MEDIUM	tests/managers/test_cancellation.py	1576
MEDIUM	tests/managers/test_cancellation.py	1629
MEDIUM	tests/managers/test_cancellation.py	1681
MEDIUM	tests/managers/test_cancellation.py	1733

Slop Phrases5 hits · 9 pts

Severity	File	Line	Snippet
LOW	letta/local_llm/llm_chat_completion_wrappers/chatml.py	24	# Don't forget to use send_message, otherwise the user won't see your message"""
LOW	letta/local_llm/llm_chat_completion_wrappers/llama3.py	23	# Don't forget to use send_message, otherwise the user won't see your message"""
LOW	letta/server/server.py	1847	# Write out the file, and make sure to in include the top-level mcpConfig (wrapped to avoid blocking event loop)
LOW	letta/server/server.py	1891	# Write out the file, and make sure to in include the top-level mcpConfig (wrapped to avoid blocking event loop)
LOW	letta/llm_api/anthropic_client.py	973	# make sure to check for overflow errors, regardless of error type

Fake / Example Data7 hits · 6 pts

Severity	File	Line	Snippet
LOW	…/integration_test_typescript_tool_execution_sandbox.py	425	assert result.func_return == "John Doe"
LOW	tests/sdk/mcp_servers_test.py	1072	"content": 'Use the create_person tool to create a person named "John Doe", age 30, '
LOW	tests/sdk/mcp_servers_test.py	1073	'email "john@example.com", with address at "123 Main St", city "New York", zip "10001".',
LOW	tests/sdk/mcp_servers_test.py	1089	assert "John Doe" in person_return.tool_return, "Expected person name in response"
LOW	tests/data/api_server.go	360	userService.CreateUser("John Doe", "john@example.com")
LOW	tests/data/test.md	78	1. Lorem ipsum dolor sit amet
LOW	tests/data/test.md	78	1. Lorem ipsum dolor sit amet

Score History

Severity Breakdown

Pattern Findings