langroid/langroid

22.3

Adjusted Score

22.3

Raw Score

100%

Time Factor

2026-07-12

Last Push

4.1K

Stars

Python

Language

120.8K

Lines of Code

626

Files

1.7K

Pattern Hits

2026-07-14

Scan Date

0.27

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

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

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 0HIGH 171MEDIUM 205LOW 1351

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 1727 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.

Cross-File Repetition138 hits · 690 pts

Severity	File	Line	Snippet	Context
HIGH	README.md	0	you will be given a number n. if it is odd, return (n*3+1), say nothing else. if it is even, say -10	STRING
HIGH	tests/main/test_recipient_tool_async.py	0	you will be given a number n. if it is odd, return (n*3+1), say nothing else. if it is even, say -10	STRING
HIGH	examples/quick-start/three-agent-chat-num-router.py	0	you will be given a number n. if it is odd, return (n*3+1), say nothing else. if it is even, say -10	STRING
HIGH	README.md	0	to find how many numbers in my list are less than or equal to the <number> you specify.	STRING
HIGH	examples/langdb/langdb_chat_agent_tool.py	0	to find how many numbers in my list are less than or equal to the <number> you specify.	STRING
HIGH	examples/quick-start/chat-agent-tool.py	0	to find how many numbers in my list are less than or equal to the <number> you specify.	STRING
HIGH	README.md	0	done! successfully extracted lease info: {message.terms}	STRING
HIGH	examples/chainlit/multi-extract.py	0	done! successfully extracted lease info: {message.terms}	STRING
HIGH	examples/docqa/chat_multi_extract.py	0	done! successfully extracted lease info: {message.terms}	STRING
HIGH	tests/main/test_doc_chat_relevance.py	0	test window retrieval of relevant doc-chunks. check that we are retrieving 2 neighbors around each match.	STRING
HIGH	tests/main/test_doc_chat_agent.py	0	test window retrieval of relevant doc-chunks. check that we are retrieving 2 neighbors around each match.	STRING
HIGH	tests/extras/test_doc_chat_agent_llamacpp.py	0	test window retrieval of relevant doc-chunks. check that we are retrieving 2 neighbors around each match.	STRING
HIGH	tests/main/test_multi_agent_complex_async.py	0	you are a calculator. you will be given a multiplication problem. you simply reply with the answer, say nothing else.	STRING
HIGH	tests/main/test_multi_agent.py	0	you are a calculator. you will be given a multiplication problem. you simply reply with the answer, say nothing else.	STRING
HIGH	tests/main/test_multi_agent_complex.py	0	you are a calculator. you will be given a multiplication problem. you simply reply with the answer, say nothing else.	STRING
HIGH	tests/main/test_doc_chat_agent.py	0	in the year 2050, gpt10 was released. in 2057, paperclips were seen all over the world. global warming was solved in 206	STRING
HIGH	tests/extras/test_doc_chat_agent_llamacpp.py	0	in the year 2050, gpt10 was released. in 2057, paperclips were seen all over the world. global warming was solved in 206	STRING
HIGH	docs/notes/weaviate.md	0	in the year 2050, gpt10 was released. in 2057, paperclips were seen all over the world. global warming was solved in 206	STRING
HIGH	docs/notes/pgvector.md	0	in the year 2050, gpt10 was released. in 2057, paperclips were seen all over the world. global warming was solved in 206	STRING
HIGH	docs/quick-start/chat-agent-docs.md	0	in the year 2050, gpt10 was released. in 2057, paperclips were seen all over the world. global warming was solved in 206	STRING
HIGH	examples/langdb/langdb_chat_agent_docs.py	0	in the year 2050, gpt10 was released. in 2057, paperclips were seen all over the world. global warming was solved in 206	STRING
HIGH	examples/quick-start/chat-agent-docs.py	0	in the year 2050, gpt10 was released. in 2057, paperclips were seen all over the world. global warming was solved in 206	STRING
HIGH	tests/main/test_doc_chat_agent.py	0	check we can ingest from a dataframe and run queries.	STRING
HIGH	tests/main/test_retriever_agent.py	0	check we can ingest from a dataframe and run queries.	STRING
HIGH	tests/extras/test_doc_chat_agent_llamacpp.py	0	check we can ingest from a dataframe and run queries.	STRING
HIGH	tests/main/test_tool_messages_async.py	0	test whether llm is able to generate message (tool) in required format, and the agent handles the message correctly. arg	STRING
HIGH	tests/main/test_stateless_tool_messages.py	0	test whether llm is able to generate message (tool) in required format, and the agent handles the message correctly. arg	STRING
HIGH	tests/main/test_tool_messages.py	0	test whether llm is able to generate message (tool) in required format, and the agent handles the message correctly. arg	STRING
HIGH	tests/main/test_tool_messages_azure.py	0	test whether llm is able to generate message (tool) in required format, and the agent handles the message correctly. arg	STRING
HIGH	docs/FAQ.md	0	important: you must include an actual query in the `query` field,	STRING
HIGH	examples/chainlit/chat-search-rag.py	0	important: you must include an actual query in the `query` field,	STRING
HIGH	examples/docqa/chat_search.py	0	important: you must include an actual query in the `query` field,	STRING
HIGH	examples/docqa/chat-search-filter.py	0	important: you must include an actual query in the `query` field,	STRING
HIGH	docs/FAQ.md	0	------------------------------ ask me questions one by one, to fill in the fields of the `lease_info` function/tool. fir	STRING
HIGH	examples/chainlit/multi-extract-3.py	0	------------------------------ ask me questions one by one, to fill in the fields of the `lease_info` function/tool. fir	STRING
HIGH	examples/docqa/chat-multi-extract-3.py	0	------------------------------ ask me questions one by one, to fill in the fields of the `lease_info` function/tool. fir	STRING
HIGH	docs/notes/weaviate.md	0	we are living in an alternate universe where germany has occupied the usa, and the capital of usa is berlin. charlie cha	STRING
HIGH	docs/notes/pgvector.md	0	we are living in an alternate universe where germany has occupied the usa, and the capital of usa is berlin. charlie cha	STRING
HIGH	docs/quick-start/chat-agent-docs.md	0	we are living in an alternate universe where germany has occupied the usa, and the capital of usa is berlin. charlie cha	STRING
HIGH	examples/langdb/langdb_chat_agent_docs.py	0	we are living in an alternate universe where germany has occupied the usa, and the capital of usa is berlin. charlie cha	STRING
HIGH	examples/quick-start/chat-agent-docs.py	0	we are living in an alternate universe where germany has occupied the usa, and the capital of usa is berlin. charlie cha	STRING
HIGH	docs/examples/agent-tree.md	0	this is a stateless tool (i.e. does not use any agent member vars), so we can define the handler right here, instead of	STRING
HIGH	examples/basic/chat-tree-structured.py	0	this is a stateless tool (i.e. does not use any agent member vars), so we can define the handler right here, instead of	STRING
HIGH	examples/basic/chat-tree.py	0	this is a stateless tool (i.e. does not use any agent member vars), so we can define the handler right here, instead of	STRING
HIGH	examples/chainlit/chat-tree-chainlit.py	0	this is a stateless tool (i.e. does not use any agent member vars), so we can define the handler right here, instead of	STRING
HIGH	docs/quick-start/chat-agent-tool.md	0	i have a list of numbers between 1 and 20. your job is to find the smallest of them. to help with this, you can give me	STRING
HIGH	examples/langdb/langdb_chat_agent_tool.py	0	i have a list of numbers between 1 and 20. your job is to find the smallest of them. to help with this, you can give me	STRING
HIGH	examples/quick-start/chat-agent-tool.py	0	i have a list of numbers between 1 and 20. your job is to find the smallest of them. to help with this, you can give me	STRING
HIGH	examples/portkey/portkey_multi_provider.py	0	check if environment variable is set and return its value.	STRING
HIGH	examples/portkey/portkey_advanced_features.py	0	check if environment variable is set and return its value.	STRING
HIGH	examples/portkey/portkey_basic_chat.py	0	check if environment variable is set and return its value.	STRING
HIGH	examples/chainlit/chat-search-rag.py	0	get docs/extracts relevant to the query, from vecdb	STRING
HIGH	examples/docqa/chat_search.py	0	get docs/extracts relevant to the query, from vecdb	STRING
HIGH	examples/docqa/chat-search-filter.py	0	get docs/extracts relevant to the query, from vecdb	STRING
HIGH	examples/chainlit/chat-search-rag.py	0	no extracts found! you can try doing a web search with the `relevant_search_extracts` tool/function-call.	STRING
HIGH	examples/docqa/chat_search.py	0	no extracts found! you can try doing a web search with the `relevant_search_extracts` tool/function-call.	STRING
HIGH	examples/docqa/chat-search-filter.py	0	no extracts found! you can try doing a web search with the `relevant_search_extracts` tool/function-call.	STRING
HIGH	examples/chainlit/chat-search-rag.py	0	get docs/extracts relevant to the query, from a web search	STRING
HIGH	examples/docqa/chat_search.py	0	get docs/extracts relevant to the query, from a web search	STRING
HIGH	examples/docqa/chat-search-filter.py	0	get docs/extracts relevant to the query, from a web search	STRING
78 more matches not shown…

Hyper-Verbose Identifiers598 hits · 554 pts

Severity	File	Line	Snippet	Context
LOW	…ugins/langroid/skills/patterns/mcp-tool-integration.md	32	async def setup_agent_with_all_tools():	CODE
LOW	tests/conftest.py	83	def pytest_runtest_makereport(item, call):	STRING
LOW	tests/conftest.py	147	def pytest_collection_modifyitems(config, items):	STRING
LOW	tests/main/test_qdrant_lock_release.py	13	def test_qdrant_explicit_close():	CODE
LOW	tests/main/test_qdrant_lock_release.py	43	def test_qdrant_context_manager():	CODE
LOW	tests/main/test_qdrant_lock_release.py	67	def test_qdrant_context_manager_with_exception():	CODE
LOW	tests/main/test_qdrant_lock_release.py	94	def test_qdrant_multiple_sequential_operations():	CODE
LOW	tests/main/test_qdrant_lock_release.py	115	def test_qdrant_no_close_creates_new_directory():	CODE
LOW	tests/main/test_docx_parser.py	40	def test_markitdown_docx_parser():	CODE
LOW	tests/main/test_string_search.py	46	def test_return_correct_number_of_matches(	STRING
LOW	tests/main/test_string_search.py	65	def test_find_match_with_surrounding_words(	STRING
LOW⚡	tests/main/test_string_search.py	93	def test_preprocess_lowercase():	STRING
LOW⚡	tests/main/test_string_search.py	98	def test_preprocess_remove_punctuation():	STRING
LOW⚡	tests/main/test_string_search.py	104	def test_preprocess_remove_stopwords():	STRING
LOW⚡	tests/main/test_string_search.py	113	def test_preprocess_lemmatization():	STRING
LOW	tests/main/test_doc_chat_relevance.py	175	def test_doc_chat_rerank_diversity(test_settings: Settings, vecdb):	CODE
LOW	tests/main/test_doc_chat_relevance.py	213	def test_doc_chat_rerank_periphery(test_settings: Settings, vecdb):	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	56	def test_to_chatdocument_user_string_is_tainted():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	62	def test_agent_authored_string_not_tainted():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	68	def test_agent_response_not_tainted():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	73	def test_create_user_response_is_tainted():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	78	def test_interactive_user_response_is_tainted():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	86	def test_system_user_response_not_tainted():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	95	def test_task_init_user_string_is_tainted():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	104	def test_root_task_user_chatdocument_input_is_tainted():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	124	def test_deepcopy_propagates_taint():	CODE
LOW⚡	tests/main/test_tool_origin_taint.py	132	def test_donepass_repackage_propagates_taint():	CODE
LOW	tests/main/test_tool_origin_taint.py	146	def test_donepass_repackage_of_llm_message_not_tainted():	CODE
LOW	tests/main/test_tool_origin_taint.py	177	def test_filter_vetoes_tainted_handoff():	CODE
LOW	tests/main/test_tool_origin_taint.py	187	def test_tainted_handoff_does_not_dispatch_handle_only_tool():	CODE
LOW	tests/main/test_multi_agent_complex_async.py	40	async def test_agents_with_recipient(	CODE
LOW	tests/main/test_md_parser.py	74	def test_parse_markdown_headings(sample_markdown, markdown_sections):	CODE
LOW	tests/main/test_md_parser.py	141	def test_no_headers_only_paragraphs():	CODE
LOW	tests/main/test_md_parser.py	152	def test_headers_with_no_content():	STRING
LOW	tests/main/test_md_parser.py	167	def test_header_with_inline_formatting():	STRING
LOW	tests/main/test_md_parser.py	176	def test_lists_and_code_blocks():	STRING
LOW	tests/main/test_md_parser.py	201	def test_multiple_same_level_headers():	STRING
LOW	tests/main/test_md_parser.py	216	def test_header_skipping_levels():	STRING
LOW⚡	tests/main/test_md_parser.py	385	def test_chunking_word_set_consistency(rollup: bool):	STRING
LOW	tests/main/test_md_parser.py	470	def test_degenerate_markdown_parsing_and_chunking(	STRING
LOW	tests/main/test_md_parser.py	625	def test_recursive_chunk_enhanced():	STRING
LOW⚡	tests/main/test_tool_handler.py	304	def test_agent_response_with_chat_document(self):	CODE
LOW⚡	tests/main/test_tool_handler.py	340	def test_agent_response_agent_only(self):	CODE
LOW⚡	tests/main/test_tool_handler.py	355	def test_agent_response_chat_doc_only(self):	CODE
LOW⚡	tests/main/test_tool_handler.py	370	def test_agent_response_class_annotations(self):	CODE
LOW	tests/main/test_tool_handler.py	208	def test_handle_agent_chat_doc(self):	CODE
LOW	tests/main/test_tool_handler.py	220	def test_handle_chat_doc_agent(self):	CODE
LOW	tests/main/test_tool_handler.py	230	def test_handle_no_annotations(self):	CODE
LOW	tests/main/test_tool_handler.py	242	def test_handle_no_annotations_agent(self):	CODE
LOW	tests/main/test_tool_handler.py	253	def test_handle_no_annotations_both(self):	CODE
LOW	tests/main/test_tool_handler.py	265	def test_handle_no_annotations_both_reversed(self):	CODE
LOW	tests/main/test_tool_handler.py	275	def test_backward_compatibility(self):	CODE
LOW	tests/main/test_tool_handler.py	287	def test_agent_response_with_tool_message(self):	CODE
LOW	tests/main/test_tool_handler.py	323	def test_agent_response_no_annotations(self):	CODE
LOW	tests/main/test_tool_handler.py	390	def test_agent_response_class_annotations_reversed(self):	CODE
LOW	tests/main/test_concurrent_doc_chat_qdrant.py	26	def test_doc_chat_concurrent_local_qdrant(local_qdrant_config):	CODE
LOW	tests/main/test_task_inf_loop.py	119	def test_task_alternating_no_answer():	CODE
LOW	tests/main/test_quiet_mode.py	28	def test_quiet_mode_with_exception():	CODE
LOW	tests/main/test_parsing_citations.py	19	def test_invalid_markdown_citations(input_str: str, expected: list[str]) -> None:	CODE
LOW	tests/main/test_multi_agent.py	185	def test_multi_agent_directed(test_settings: Settings):	STRING
538 more matches not shown…

Self-Referential Comments113 hits · 309 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/main/test_md_parser.py	325	# Create a long text consisting of 200 repeated tokens ("word")	STRING
MEDIUM⚡	tests/main/test_md_parser.py	391	# Define a header and content.	STRING
MEDIUM⚡	tests/main/test_md_parser.py	397	# Create a sample Markdown document with a header and content.	STRING
MEDIUM⚡	tests/main/test_tool_handler.py	309	# Create a tool message	COMMENT
MEDIUM⚡	tests/main/test_tool_handler.py	312	# Create a ChatDocument with the tool message	COMMENT
MEDIUM⚡	tests/main/test_tool_handler.py	345	# Create a tool message	COMMENT
MEDIUM⚡	tests/main/test_tool_handler.py	360	# Create a tool message	COMMENT
MEDIUM⚡	tests/main/test_tool_handler.py	378	# Create a tool message	COMMENT
MEDIUM	tests/main/test_tool_handler.py	292	# Create a tool message	COMMENT
MEDIUM	tests/main/test_tool_handler.py	328	# Create a tool message	COMMENT
MEDIUM	tests/main/test_tool_handler.py	398	# Create a tool message	COMMENT
MEDIUM	tests/main/test_task.py	1009	# Create a mock LLM that always responds with a tool in JSON format	COMMENT
MEDIUM	tests/main/test_task.py	1079	# Create an agent	COMMENT
MEDIUM	tests/main/test_llm.py	631	# Create a FileAttachment from the PDF file	COMMENT
MEDIUM⚡	tests/main/test_llm.py	677	# Create a FileAttachment from the PDF file	COMMENT
MEDIUM⚡	tests/main/test_llm.py	683	# Create a FileAttachment from the PDF file	COMMENT
MEDIUM	tests/main/test_chat_agent.py	224	# Create a FileAttachment from the PDF file	STRING
MEDIUM	tests/main/test_mcp_tools.py	947	# Create a mock server that returns image content	COMMENT
MEDIUM	tests/main/test_mcp_tools.py	966	# Create a mock agent	COMMENT
MEDIUM	tests/main/test_mcp_tools.py	995	# Create a mock CallToolResult with text and text resource	COMMENT
MEDIUM	tests/main/test_mcp_tools.py	1041	# Create a mock CallToolResult with text and blob resource	COMMENT
MEDIUM	tests/main/test_mcp_tools.py	1169	# Create a real MCP server	COMMENT
MEDIUM	tests/main/test_mcp_tools.py	1181	# Create a Tool with the problematic schema	COMMENT
MEDIUM	tests/main/test_mcp_tools.py	1238	# Create a real MCP server	COMMENT
MEDIUM	tests/main/test_openai_params_subclass.py	39	# Create an instance - note we can't pass custom fields to constructor	COMMENT
MEDIUM	tests/main/test_openai_params_subclass.py	68	# Create an instance with custom fields	COMMENT
MEDIUM	tests/main/test_tool_messages_async.py	108	# Define the range of values each variable can have	COMMENT
MEDIUM	tests/main/test_table_chat_agent.py	36	# Create a list of states	STRING
MEDIUM⚡	tests/main/test_table_chat_agent.py	166	# Create a simple dataframe with data that needs cleaning	STRING
MEDIUM	tests/main/test_prep_llm_message.py	31	# Create a mock parser that counts tokens as characters for simplicity	COMMENT
MEDIUM	tests/main/test_prep_llm_message.py	44	# Create a mock LLM that returns a fixed context length	COMMENT
MEDIUM	tests/main/test_prep_llm_message.py	135	# Create a mock parser that counts tokens as characters for simplicity	COMMENT
MEDIUM	tests/main/test_prep_llm_message.py	148	# Create a mock LLM that returns a fixed context length	COMMENT
MEDIUM	tests/main/test_retriever_agent.py	23	# Create a list of states	COMMENT
MEDIUM	tests/main/test_stateless_tool_messages.py	53	# Define the range of values each variable can have	STRING
MEDIUM	tests/main/test_llm_async.py	184	# Create a FileAttachment from the PDF file	COMMENT
MEDIUM⚡	tests/main/test_llm_async.py	232	# Create a FileAttachment from the PDF file	COMMENT
MEDIUM⚡	tests/main/test_llm_async.py	238	# Create a FileAttachment from the PDF file	COMMENT
MEDIUM	tests/main/test_llm_async.py	283	# Create the LLM instance	STRING
MEDIUM	tests/main/test_task_optional_logger.py	14	# Create a simple mock agent	COMMENT
MEDIUM	tests/main/test_task_optional_logger.py	46	# Create a simple mock agent	COMMENT
MEDIUM⚡	tests/main/test_task_optional_logger.py	65	# Create a simple mock agent	COMMENT
MEDIUM	tests/main/test_task_optional_logger.py	77	# Create a test message	COMMENT
MEDIUM	tests/main/test_task_tool.py	56	# Create main task that stops after handling the task_tool	STRING
MEDIUM	tests/main/test_task_tool.py	186	# Create a main agent with multiple tools available	STRING
MEDIUM	tests/main/test_task_tool.py	276	# Create a main agent that delegates with no tools	STRING
MEDIUM⚡	tests/main/test_pydantic_utils.py	21	# Create an instance of TestModel with nested DetailsModel	COMMENT
MEDIUM	tests/main/test_html_logger.py	40	# Create a user message	COMMENT
MEDIUM	tests/main/test_tool_messages.py	157	# Define the range of values each variable can have	STRING
MEDIUM	tests/main/test_tool_messages.py	2155	# Create a ChatDocument containing ToolB (which only AgentB knows about)	COMMENT
MEDIUM	tests/main/test_file_tools.py	164	# Create a test file	STRING
MEDIUM	tests/main/test_global_settings.py	127	# Define a temporary override that forces quiet=True.	COMMENT
MEDIUM	tests/main/test_token_usage.py	35	# Define the configurations	COMMENT
MEDIUM	tests/main/sql_chat/test_sql_chat_agent.py	56	# Create an in-memory SQLite database	COMMENT
MEDIUM	tests/extras/test_csv_kg_chat.py	14	# Create a dummy DataFrame	COMMENT
MEDIUM	tests/extras/test_csv_kg_chat.py	43	# Create a mock PandasToKGTool object	COMMENT
MEDIUM	examples/langdb/langdb_chat_agent_tool.py	72	# Create a LangDB model configuration	STRING
MEDIUM	examples/langdb/langdb_custom_headers.py	23	# Create a LangDB model configuration	COMMENT
MEDIUM	examples/langdb/langdb_custom_headers.py	34	# Create the model	COMMENT
MEDIUM	examples/langdb/langdb_chat_agent_docs.py	77	# Create a LangDB model configuration	STRING
53 more matches not shown…

Unused Imports236 hits · 224 pts

Severity	File	Line	Context
LOW	tests/main/test_openai_http_client.py	16	CODE
LOW	tests/main/test_rich_file_logger.py	1	CODE
LOW	examples/multi-agent-debate/chainlit_utils.py	6	CODE
LOW	examples/basic/fn-call-local-simple.py	28	CODE
LOW	examples/basic/planner-workflow-spawn.py	31	CODE
LOW	examples/mcp/claude-code-mcp-single.py	23	CODE
LOW	langroid/__init__.py	5	CODE
LOW	langroid/__init__.py	6	CODE
LOW	langroid/__init__.py	8	CODE
LOW	langroid/__init__.py	9	CODE
LOW	langroid/__init__.py	10	CODE
LOW	langroid/__init__.py	12	CODE
LOW	langroid/__init__.py	13	CODE
LOW	langroid/__init__.py	15	CODE
LOW	langroid/__init__.py	16	CODE
LOW	langroid/__init__.py	18	CODE
LOW	langroid/__init__.py	18	CODE
LOW	langroid/__init__.py	23	CODE
LOW	langroid/__init__.py	23	CODE
LOW	langroid/__init__.py	23	CODE
LOW	langroid/__init__.py	29	CODE
LOW	langroid/__init__.py	29	CODE
LOW	langroid/__init__.py	29	CODE
LOW	langroid/__init__.py	35	CODE
LOW	langroid/__init__.py	39	CODE
LOW	langroid/__init__.py	39	CODE
LOW	langroid/__init__.py	44	CODE
LOW	langroid/__init__.py	44	CODE
LOW	langroid/__init__.py	47	CODE
LOW	langroid/__init__.py	47	CODE
LOW	langroid/__init__.py	47	CODE
LOW	langroid/__init__.py	53	CODE
LOW	langroid/__init__.py	54	CODE
LOW	langroid/embedding_models/__init__.py	1	CODE
LOW	langroid/embedding_models/__init__.py	2	CODE
LOW	langroid/embedding_models/__init__.py	3	CODE
LOW	langroid/embedding_models/__init__.py	5	CODE
LOW	langroid/embedding_models/__init__.py	5	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	9	CODE
LOW	langroid/embedding_models/__init__.py	20	CODE
LOW	langroid/embedding_models/__init__.py	20	CODE
LOW	langroid/language_models/__init__.py	1	CODE
LOW	langroid/language_models/__init__.py	2	CODE
LOW	langroid/language_models/__init__.py	3	CODE
LOW	langroid/language_models/__init__.py	4	CODE
LOW	langroid/language_models/__init__.py	5	CODE
LOW	langroid/language_models/__init__.py	6	CODE
LOW	langroid/language_models/__init__.py	8	CODE
LOW	langroid/language_models/__init__.py	8	CODE
LOW	langroid/language_models/__init__.py	8	CODE
LOW	langroid/language_models/__init__.py	8	CODE
LOW	langroid/language_models/__init__.py	8	CODE
176 more matches not shown…

Excessive Try-Catch Wrapping152 hits · 143 pts

Severity	File	Line	Snippet	Context
LOW	plugins/langroid/skills/patterns/run-batch-tasks.md	160	except Exception as e:	CODE
LOW	…groid/skills/patterns/agent-tool-handler-with-state.md	67	except Exception as e:	CODE
LOW	…groid/skills/patterns/agent-tool-handler-with-state.md	127	except Exception as e:	CODE
LOW	tests/conftest.py	190	except Exception:	CODE
LOW	tests/main/test_quiet_mode.py	35	except Exception:	CODE
LOW	tests/main/test_concurrent_rag_simple.py	281	except Exception as e:	CODE
LOW	tests/main/test_concurrent_rag_simple.py	289	except Exception as e:	CODE
LOW	tests/main/test_arangodb_chat_agent.py	30	except Exception:	CODE
LOW	tests/main/test_arangodb_chat_agent.py	150	except Exception as e:	CODE
MEDIUM	tests/main/test_arangodb_chat_agent.py	151	print(f"Error inserting data: {e}")	CODE
LOW	tests/main/test_openai_http_client.py	265	except Exception as e:	CODE
LOW	tests/main/test_openai_http_client.py	306	except Exception as e:	CODE
LOW	tests/main/test_openai_http_client.py	333	except Exception as e:	CODE
LOW	tests/main/test_openai_http_client.py	354	except Exception:	CODE
LOW	tests/main/test_mcp_tools.py	1122	except Exception:	CODE
LOW	tests/main/test_mcp_tools.py	838	except Exception as e:	STRING
LOW	tests/main/test_web_search_tools.py	78	except Exception as e:	CODE
LOW	tests/main/test_vector_stores.py	491	except Exception as exc:	CODE
LOW	tests/main/test_openai_gpt_client_cache.py	284	except Exception as e:	CODE
LOW	tests/main/test_task_tool.py	261	except Exception:	STRING
LOW	tests/main/test_neo4j_chat_agent.py	28	except Exception:	CODE
LOW	tests/main/test_neo4j_chat_agent.py	64	except Exception as e:	CODE
LOW	tests/main/test_neo4j_chat_agent.py	91	except Exception as e:	CODE
LOW	tests/main/test_global_settings.py	35	except Exception as e:	CODE
LOW	tests/main/mcp/weather-server-python/weather.py	22	except Exception:	CODE
LOW	tests/main/mcp/weather-server-python/weather.py	44	except Exception:	CODE
LOW	docs/notes/portkey.md	277	except Exception:	CODE
LOW	examples/portkey/portkey_multi_provider.py	81	except Exception as e:	CODE
LOW	examples/portkey/portkey_multi_provider.py	144	except Exception as e:	CODE
LOW⚡	examples/portkey/portkey_multi_provider.py	174	except Exception as e:	CODE
LOW⚡	examples/portkey/portkey_multi_provider.py	184	except Exception as e:	CODE
LOW⚡	examples/portkey/portkey_multi_provider.py	194	except Exception as e:	CODE
LOW	examples/portkey/portkey_advanced_features.py	166	except Exception as e:	CODE
LOW	examples/portkey/portkey_advanced_features.py	203	except Exception as e:	CODE
LOW	examples/portkey/portkey_basic_chat.py	58	except Exception as e:	CODE
LOW	examples/portkey/portkey_basic_chat.py	105	except Exception as e:	CODE
LOW	examples/chainlit/dependency_chatbot.py	194	except Exception as e:	STRING
MEDIUM⚡	examples/docqa/crawl4ai_examples.py	95	print("Error: Failed to parse the extracted content as JSON.")	CODE
MEDIUM	examples/docqa/crawl4ai_examples.py	281	print(f"Error parsing LLM output JSON: {e}")	CODE
LOW	examples/multi-agent-debate/models.py	65	except Exception as e:	CODE
LOW	examples/multi-agent-debate/chainlit_utils.py	173	except Exception as e:	CODE
LOW⚡	examples/basic/done_sequences_example.py	47	except Exception as e:	CODE
MEDIUM	examples/basic/done_sequences_example.py	43	def handle(self) -> str:	CODE
LOW	examples/basic/python-code-exec-tool.py	47	except Exception as e:	CODE
MEDIUM	examples/basic/python-code-exec-tool.py	48	print(f"Error: {str(e)}")	CODE
LOW	examples/basic/chat-persist.py	103	except Exception:	CODE
LOW	examples/mcp/claude-code-mcp-single.py	102	except Exception:	CODE
LOW	examples/kg-chat/dependency_chatbot.py	202	except Exception as e:	STRING
LOW	langroid/embedding_models/base.py	35	except Exception:	CODE
LOW	langroid/language_models/utils.py	96	except Exception as e:	CODE
LOW	langroid/language_models/utils.py	178	except Exception as e:	CODE
LOW	langroid/language_models/client_cache.py	376	except Exception:	CODE
LOW	langroid/language_models/openai_gpt.py	408	except Exception:	CODE
LOW	langroid/language_models/openai_gpt.py	1352	except Exception as e:	CODE
LOW	langroid/language_models/openai_gpt.py	1431	except Exception as e:	CODE
LOW⚡	langroid/language_models/openai_gpt.py	2104	except Exception as e:	STRING
LOW	langroid/language_models/openai_gpt.py	138	except Exception as e:	STRING
LOW	langroid/language_models/openai_gpt.py	1712	except Exception as e:	STRING
LOW	langroid/language_models/openai_gpt.py	1732	except Exception as e:	STRING
LOW	langroid/language_models/openai_gpt.py	1795	except Exception as e:	STRING
92 more matches not shown…

Decorative Section Separators31 hits · 112 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/main/test_tool_origin_taint.py	47	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_tool_origin_taint.py	49	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_tool_origin_taint.py	119	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_tool_origin_taint.py	121	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/main/test_tool_origin_taint.py	160	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/main/test_tool_origin_taint.py	163	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/main/test_md_parser.py	548	# ----------------------------------------------------------------	STRING
MEDIUM	tests/main/test_md_parser.py	550	# ----------------------------------------------------------------	STRING
MEDIUM⚡	tests/main/test_handle_message_security.py	54	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_handle_message_security.py	56	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_handle_message_security.py	89	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_handle_message_security.py	91	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_handle_message_security.py	120	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_handle_message_security.py	122	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/main/test_pandas_utils.py	87	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/main/test_pandas_utils.py	97	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/test_minimax_provider.py	25	# ──────────────────────── Unit Tests ────────────────────────	COMMENT
MEDIUM	tests/main/test_minimax_provider.py	269	# ──────────────────────── Integration Tests ────────────────────────	COMMENT
MEDIUM⚡	tests/main/sql_chat/test_sql_chat_security.py	56	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/sql_chat/test_sql_chat_security.py	58	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/sql_chat/test_sql_chat_security.py	201	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/main/sql_chat/test_sql_chat_security.py	203	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/main/sql_chat/test_sql_chat_security.py	235	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/main/sql_chat/test_sql_chat_security.py	238	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	langroid/agent/batch.py	337	# ----------------------------------------	COMMENT
MEDIUM	langroid/agent/tools/mcp/fastmcp_client.py	926	# ==============================================================================	COMMENT
MEDIUM	langroid/agent/tools/mcp/fastmcp_client.py	930	# ==============================================================================	COMMENT
MEDIUM	langroid/parsing/md_parser.py	210	# -------------------------------------------------	COMMENT
MEDIUM	langroid/parsing/md_parser.py	212	# -------------------------------------------------	COMMENT
MEDIUM	langroid/parsing/md_parser.py	282	# -------------------------------------------------	COMMENT
MEDIUM	langroid/parsing/md_parser.py	284	# -------------------------------------------------	COMMENT

Docstring Block Structure21 hits · 105 pts

Severity	File	Line	Snippet	Context
HIGH	examples/multi-agent-debate/config.py	51	Creates an LLM (Language Learning Model) configuration based on the selected model. This function uses the use	STRING
HIGH	examples/multi-agent-debate/models.py	35	Load and validate system messages from a JSON file. Reads the JSON file containing system messages, maps each entry	STRING
HIGH	examples/multi-agent-debate/utils.py	141	Prompt the user to select a debate topic and sets up the respective side. This function handles the user interactio	STRING
HIGH	examples/multi-agent-debate/chainlit_utils.py	254	Prompt the user to select a debate topic and sets up the respective side. Args: system_messages (System	STRING
HIGH	examples/basic/drug-outcomes.py	59	Extracts an integer from a string that contains a number. Args: x (str): The input string containing t	STRING
HIGH	examples/data-qa/sql-chat/sql_chat.py	55	Create an empty descriptions JSON file for SQLAlchemy tables. This function inspects the database, generates a	STRING
HIGH	issues/issue-919-llamacpp-embeddings.md	131	Extract embedding vector from llama.cpp response. Handles multiple response formats: 1. Native /embedding:	STRING
HIGH	langroid/embedding_models/models.py	486	Extract embedding vector from llama.cpp response. Handles multiple response formats: 1. Native	STRING
HIGH	langroid/utils/system.py	191	Resolve ``user_path`` relative to ``base_dir`` and ensure the result stays within ``base_dir`` (a path-traversa	STRING
HIGH	langroid/utils/system.py	263	Read the contents of a file. Args: path (str): The path to the file to be read. line_numbers (	STRING
HIGH	langroid/agent/xml_tool_message.py	63	Extracts field values from an XML-formatted string. Args: formatted_string (str): The XML-	STRING
HIGH	langroid/agent/done_sequence_parser.py	22	Parse a string pattern or return existing DoneSequence unchanged. Args: sequence: Either a DoneSequence obj	STRING
HIGH	langroid/agent/done_sequence_parser.py	48	Parse a string pattern into a list of AgentEvent objects. Pattern format: - Single letter codes: T, A, L, U	STRING
HIGH	langroid/agent/done_sequence_parser.py	88	Parse a single event token into an AgentEvent. Args: token: Single event token (e.g., "T", "T[calc]", "C[qu	STRING
HIGH	langroid/agent/special/neo4j/neo4j_chat_agent.py	389	Retrieves the schema of a Neo4j graph database. Args: msg (GraphSchemaTool): An instance o	STRING
HIGH	langroid/vector_store/lancedb.py	144	NOTE: NOT USED, but leaving it here as it may be useful. Create a subclass of LanceModel with fields:	STRING
HIGH	langroid/parsing/repo_loader.py	212	Get the file type of a file name. Args: name: name of file, can be "a", "a.b", or ".b"	STRING
HIGH	langroid/parsing/url_loader.py	182	Create a crawler instance based on configuration type. Args: config: Configuration for the crawler	STRING
HIGH	langroid/parsing/url_loader.py	396	Crawl the given URLs using Exa SDK. Args: urls: List of URLs to crawl Returns:	STRING
HIGH	langroid/parsing/table_loader.py	8	Reads tabular data from a file or URL and returns a pandas DataFrame. The separator is auto-detected if not spe	STRING
HIGH	langroid/parsing/urls.py	20	Fetch content from the given URL and save it to a temporary local file. Args: url (str): The URL of th	STRING

Modern Structural Boilerplate106 hits · 103 pts

Severity	File	Line	Snippet	Context
LOW	tests/conftest.py	11	logger = logging.getLogger(__name__)	CODE
LOW	tests/extras/test_doc_chat_agent_llamacpp.py	129	logger = logging.getLogger(__name__)	STRING
LOW	examples/chainlit/chat-search-rag.py	46	logger = logging.getLogger(__name__)	CODE
LOW	examples/chainlit/chat-search.py	35	logger = logging.getLogger(__name__)	CODE
LOW	examples/docqa/chat_search.py	54	logger = logging.getLogger(__name__)	CODE
LOW	examples/multi-agent-debate/chainlit_utils.py	12	logger = logging.getLogger(__name__)	CODE
LOW	examples/basic/multi-agent-medical.py	41	logger = logging.getLogger(__name__)	CODE
LOW	examples/basic/chat-persist.py	42	logger = logging.getLogger(__name__)	CODE
LOW	examples/basic/planner-workflow-spawn.py	34	logger = logging.getLogger(__name__)	CODE
LOW	examples/basic/planner-workflow.py	28	logger = logging.getLogger(__name__)	CODE
LOW	examples/basic/planner-workflow-simple.py	37	logger = logging.getLogger(__name__)	CODE
LOW	examples/kg-chat/chat-arangodb.py	52	logger = logging.getLogger(__name__)	CODE
LOW	examples/kg-chat/chat-arangodb-igvf.py	46	logger = logging.getLogger(__name__)	CODE
LOW	examples/extract/pdf-json.py	39	logger = logging.getLogger(__name__)	CODE
LOW	examples/extract/pdf-json-flex.py	37	logger = logging.getLogger(__name__)	CODE
LOW	examples/extract/pdf-json-no-parse.py	44	logger = logging.getLogger(__name__)	CODE
LOW	examples/data-qa/sql-chat/utils.py	9	logger = logging.getLogger(__name__)	CODE
LOW	examples/data-qa/sql-chat/sql_chat.py	48	logger = logging.getLogger(__name__)	CODE
LOW	langroid/__init__.py	56	__all__ = [	CODE
LOW	langroid/embedding_models/__init__.py	26	__all__ = [	CODE
LOW	langroid/language_models/__init__.py	30	__all__ = [	CODE
LOW	langroid/language_models/azure_openai.py	21	logger = logging.getLogger(__name__)	CODE
LOW	langroid/language_models/utils.py	12	logger = logging.getLogger(__name__)	CODE
LOW	langroid/language_models/model_info.py	7	logger = logging.getLogger(__name__)	CODE
LOW	langroid/language_models/base.py	33	logger = logging.getLogger(__name__)	CODE
LOW	langroid/language_models/prompt_formatter/__init__.py	9	__all__ = [	CODE
LOW	…d/language_models/prompt_formatter/llama2_formatter.py	8	logger = logging.getLogger(__name__)	CODE
LOW	…groid/language_models/prompt_formatter/hf_formatter.py	18	logger = logging.getLogger(__name__)	CODE
LOW	langroid/language_models/prompt_formatter/base.py	8	logger = logging.getLogger(__name__)	CODE
LOW	langroid/utils/configuration.py	70	def update_global_settings(cfg: BaseSettings, keys: List[str]) -> None:	CODE
LOW	langroid/utils/configuration.py	85	def set_global(key_vals: Settings) -> None:	CODE
LOW	langroid/utils/configuration.py	131	def set_env(settings_instance: BaseSettings) -> None:	CODE
LOW	langroid/utils/system.py	15	logger = logging.getLogger(__name__)	CODE
LOW	langroid/utils/globals.py	42	def set_values(cls: Type[T], **kwargs: Dict[str, Any]) -> None:	CODE
LOW	langroid/utils/pydantic_utils.py	22	logger = logging.getLogger(__name__)	CODE
LOW	langroid/utils/__init__.py	10	__all__ = [	CODE
LOW	langroid/utils/types.py	8	logger = logging.getLogger(__name__)	CODE
LOW	langroid/utils/git_utils.py	12	logger = logging.getLogger(__name__)	CODE
LOW	langroid/utils/algorithms/__init__.py	3	__all__ = ["graph"]	CODE
LOW	langroid/utils/output/citations.py	6	logger = logging.getLogger(__name__)	CODE
LOW	langroid/utils/output/__init__.py	12	__all__ = [	CODE
LOW	langroid/utils/output/status.py	11	logger = logging.getLogger(__name__)	CODE
LOW	langroid/agent/task.py	64	logger = logging.getLogger(__name__)	CODE
LOW	langroid/agent/task.py	534	def _set_alive(self) -> None:	CODE
LOW	langroid/agent/task.py	2267	def set_color_log(self, enable: bool = True) -> None:	CODE
LOW	langroid/agent/task.py	1407	def _update_no_answer_vars(self, result: ChatDocument) -> None:	STRING
LOW	langroid/agent/__init__.py	22	__all__ = [	CODE
LOW	langroid/agent/openai_assistant.py	33	logger = logging.getLogger(__name__)	CODE
LOW	langroid/agent/openai_assistant.py	302	def _update_messages_hash(self, msg: Message \| LLMMessage) -> None:	CODE
LOW	langroid/agent/openai_assistant.py	574	def set_system_message(self, msg: str) -> None:	CODE
LOW	langroid/agent/base.py	73	logger = logging.getLogger(__name__)	CODE
LOW	langroid/agent/base.py	255	def update_dialog(self, prompt: str, output: str) -> None:	CODE
LOW	langroid/agent/chat_agent.py	63	logger = logging.getLogger(__name__)	CODE
LOW	langroid/agent/chat_agent.py	149	def _set_fn_or_tools(self) -> None:	CODE
LOW	langroid/agent/chat_agent.py	381	def set_system_message(self, msg: str) -> None:	CODE
LOW	langroid/agent/chat_agent.py	387	def set_user_message(self, msg: str) -> None:	CODE
LOW	langroid/agent/chat_agent.py	445	def update_history(self, message: str, response: str) -> None:	CODE
LOW	langroid/agent/chat_agent.py	593	def update_last_message(self, message: str, role: str = Role.USER) -> None:	CODE
LOW⚡	langroid/agent/chat_agent.py	850	def _update_tool_instructions(self) -> None:	STRING
LOW	langroid/agent/tools/__init__.py	20	__all__ = [	CODE
46 more matches not shown…

Deep Nesting101 hits · 94 pts

Severity	File	Line	Context
LOW	tests/main/test_task_tool.py	182	CODE
LOW	tests/main/test_tool_messages.py	857	CODE
LOW	examples/docqa/crawl4ai_examples.py	405	CODE
LOW	examples/docqa/chat_search.py	107	CODE
LOW	examples/docqa/rag-concurrent.py	132	CODE
LOW	…amples/basic/multi-agent-search-critic-no-orch/main.py	56	CODE
LOW	…amples/basic/multi-agent-search-critic-no-orch/main.py	93	CODE
LOW	examples/kg-chat/csv-chat.py	48	CODE
LOW	langroid/embedding_models/remote_embeds.py	71	CODE
LOW	langroid/embedding_models/remote_embeds.py	84	CODE
LOW	langroid/embedding_models/models.py	607	CODE
LOW	langroid/embedding_models/models.py	118	CODE
LOW	langroid/embedding_models/models.py	483	CODE
LOW	langroid/embedding_models/base.py	40	CODE
LOW	langroid/language_models/client_cache.py	360	CODE
LOW	langroid/language_models/base.py	294	CODE
LOW	langroid/language_models/base.py	419	CODE
LOW	langroid/language_models/openai_gpt.py	421	CODE
LOW	langroid/language_models/openai_gpt.py	974	CODE
LOW	langroid/language_models/openai_gpt.py	1139	CODE
LOW	langroid/language_models/openai_gpt.py	1293	CODE
LOW	langroid/language_models/openai_gpt.py	2121	CODE
LOW	langroid/utils/logging.py	200	CODE
LOW	langroid/utils/system.py	218	CODE
LOW	langroid/utils/pydantic_utils.py	104	CODE
LOW	langroid/utils/pydantic_utils.py	165	CODE
LOW	langroid/utils/types.py	13	CODE
LOW	langroid/utils/types.py	75	CODE
LOW	langroid/utils/html_logger.py	516	CODE
LOW	langroid/utils/git_utils.py	42	CODE
LOW	langroid/utils/algorithms/graph.py	11	CODE
LOW	langroid/utils/algorithms/graph.py	53	CODE
LOW	langroid/utils/output/citations.py	49	CODE
LOW	langroid/agent/task.py	610	CODE
LOW	langroid/agent/task.py	692	CODE
LOW	langroid/agent/task.py	789	CODE
LOW	langroid/agent/task.py	957	CODE
LOW	langroid/agent/task.py	1754	CODE
LOW	langroid/agent/task.py	2339	CODE
LOW	langroid/agent/task.py	2386	CODE
LOW	langroid/agent/xml_tool_message.py	62	CODE
LOW	langroid/agent/xml_tool_message.py	190	CODE
LOW	langroid/agent/xml_tool_message.py	342	CODE
LOW	langroid/agent/xml_tool_message.py	390	CODE
LOW	langroid/agent/xml_tool_message.py	91	CODE
LOW	langroid/agent/xml_tool_message.py	203	CODE
LOW	langroid/agent/xml_tool_message.py	353	CODE
LOW	langroid/agent/batch.py	71	CODE
LOW	langroid/agent/batch.py	184	CODE
LOW	langroid/agent/batch.py	214	CODE
LOW	langroid/agent/chat_document.py	253	CODE
LOW	langroid/agent/chat_document.py	441	CODE
LOW	langroid/agent/tool_message.py	35	CODE
LOW	langroid/agent/tool_message.py	298	CODE
LOW	langroid/agent/done_sequence_parser.py	85	CODE
LOW	langroid/agent/base.py	264	CODE
LOW	langroid/agent/base.py	325	CODE
LOW	langroid/agent/base.py	766	CODE
LOW	langroid/agent/base.py	1975	CODE
LOW	langroid/agent/base.py	2034	CODE
41 more matches not shown…

Modern AI Meta-Vocabulary41 hits · 82 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/main/test_vector_stores.py	432	# Test context window retrieval	COMMENT
MEDIUM	tests/main/test_vector_stores.py	570	# Test context window retrieval	COMMENT
MEDIUM	tests/main/test_vector_stores.py	575	# single window. The third Giraffe-match context window will not overlap with	COMMENT
MEDIUM	docs/FAQ.md	309	## How can I improve `DocChatAgent` (RAG) latency?	STRING
MEDIUM	docs/blog/posts/langroid-lancedb.md	134	## Retrieval Augmented Generation (RAG) and Vector Databases	STRING
MEDIUM	docs/blog/posts/multi-agent-debate.md	60	#### RAG Q&A Agent:	COMMENT
MEDIUM	docs/notes/chunking.md	113	# Configure context window	COMMENT
MEDIUM	docs/notes/llama-cpp-embeddings.md	44	dims=768, # Match the dimensions of your embedding model	CODE
MEDIUM	docs/examples/guide.md	55	### Document-chat examples, or RAG (Retrieval Augmented Generation)	COMMENT
MEDIUM	docs/quick-start/two-agent-chat-num.md	114	## Logs of multi-agent interactions	STRING
MEDIUM	docs/quick-start/chat-agent-tool.md	83	# Compiled to few-shot examples sent along with the tool instructions.	STRING
MEDIUM	docs/tutorials/langroid-tour.md	125	## Chat with a document (RAG)	STRING
MEDIUM	examples/langdb/README.md	16	### 1. LangDB Chat Agent with Document RAG (`langdb_chat_agent_docs.py`)	COMMENT
MEDIUM	examples/chainlit/.chainlit/config.toml	65	# Hide the chain of thought details from the user in the UI.	COMMENT
MEDIUM	examples/docqa/rag-local-simple.py	60	# using SentenceTransformers/BAAI/bge-large-en-v1.5 embedding model	COMMENT
MEDIUM	examples/docqa/chat.py	128	dims=768, # Change this to match the dimensions of your embedding model	CODE
MEDIUM	examples/docqa/chat-multi-extract-local.py	245	# (2) RAG AGENT: try to answer a given question based on documents	STRING
MEDIUM	examples/docqa/chat-multi-extract-local.py	277	# from the RAG agent	STRING
MEDIUM	examples/docqa/chat-multi-extract-local.py	329	# Questions -> Answers using RAG	STRING
MEDIUM	examples/basic/fn-call-local-numerical.py	83	# Used to provide few-shot examples in the system prompt	COMMENT
MEDIUM	examples/basic/fn-call-local-numerical.py	207	# and few-shot examples into the system message	STRING
MEDIUM	examples/basic/fn-call-local-simple.py	73	# Used to provide few-shot examples in the system prompt	COMMENT
MEDIUM	examples/basic/fn-call-local-simple.py	138	# and few-shot examples (specified in the tool defn above) into the system message	STRING
MEDIUM	examples/basic/1-agent-3-tools.py	27	# Examples that will be compiled into few-shot examples for the LLM.	COMMENT
MEDIUM	examples/basic/text-to-structured.py	85	# Used to provide few-shot examples in the system prompt	STRING
MEDIUM	examples/basic/text-to-structured.py	133	# and few-shot examples (specified in the tool defn above) into the system message	STRING
MEDIUM	examples/basic/1-agent-3-tools-address-user.py	30	# Examples that will be compiled into few-shot examples for the LLM.	COMMENT
MEDIUM	.chainlit/config.toml	65	# Hide the chain of thought details from the user in the UI.	COMMENT
MEDIUM	issues/issue-919-llamacpp-embeddings.md	223	dims=768, # Match your embedding model dimensions	CODE
MEDIUM	issues/issue-919-llamacpp-embeddings.md	238	# For dedicated embedding model (RECOMMENDED)	COMMENT
MEDIUM	issues/20251010-concurrent-rag-status.md	1	# Concurrent DocChat RAG – Current Status (2025-10-10)	COMMENT
MEDIUM	langroid/mytypes.py	52	window_ids: List[str] = [] # for RAG: ids of chunks around this one	CODE
MEDIUM	langroid/language_models/model_info.py	163	max_cot_tokens: int = 0 # max chain of thought (thinking) tokens where applicable	CODE
MEDIUM	langroid/agent/chat_document.py	61	# multi-agent handoff (a Task then relabels sender -> USER). Lets handle-only	COMMENT
MEDIUM	langroid/agent/base.py	1364	# across a multi-agent handoff), not raw user input -- safe to	STRING
MEDIUM	langroid/agent/base.py	1651	# check whether there are multiple orchestration-tools (e.g. DoneTool etc),	STRING
MEDIUM	langroid/agent/base.py	1706	# Cannot support multi-tool results containing orchestration strings!	STRING
MEDIUM	langroid/agent/base.py	1752	# agent's or, in multi-agent setups, another agent's), not by raw user	STRING
MEDIUM	langroid/agent/special/doc_chat_agent.py	230	rerank_after_adding_context: bool = True # rerank after adding context window?	STRING
MEDIUM	langroid/agent/special/doc_chat_agent.py	1301	# Do not add context window when there are other fields besides just	STRING
MEDIUM	langroid/agent/special/lance_rag/query_planner_agent.py	195	# since this Agent seeks feedback only after receiving RAG answer.	COMMENT

Redundant / Tautological Comments45 hits · 54 pts

Severity	File	Line	Snippet	Context
LOW	tests/main/test_task.py	1118	# Set caller to simulate subtask scenario	COMMENT
LOW	tests/main/test_openai_http_client.py	14	# Check if httpx is available	COMMENT
LOW	tests/main/test_git_utils.py	92	# Check if the file was actually committed	COMMENT
LOW	tests/main/test_task_optional_logger.py	26	# Check if loggers were created	COMMENT
LOW⚡	tests/main/test_task_optional_logger.py	58	# Check if loggers were NOT created	COMMENT
LOW	tests/main/test_task_tool.py	248	# Check if current message is from TaskTool	STRING
LOW	tests/main/test_pdf_utils.py	9	# Check if the pages are split correctly	COMMENT
LOW⚡	tests/main/test_file_tools.py	71	# Check if the file was created	STRING
LOW⚡	tests/main/test_file_tools.py	75	# Check if the content was written correctly	STRING
LOW⚡	tests/main/test_file_tools.py	79	# Check if the file was committed to the git repo	STRING
LOW	tests/main/test_file_tools.py	118	# Check if all files are in the repo	STRING
LOW	tests/main/test_file_tools.py	213	# Check if each line of content is in the result, ignoring line numbers	STRING
LOW	examples/chainlit/dependency_chatbot.py	133	# Check if node has been added before	STRING
LOW	examples/docqa/rag-concurrent.py	377	# Display results	COMMENT
LOW	examples/kg-chat/dependency_chatbot.py	141	# Check if node has been added before	STRING
LOW	langroid/embedding_models/models.py	187	# Check if using LangDB	COMMENT
LOW	langroid/embedding_models/models.py	510	# Check if it's [floats]	COMMENT
LOW	langroid/embedding_models/models.py	534	# Check if it's [floats]	COMMENT
LOW	langroid/embedding_models/models.py	538	# Check if it's [[floats]]	COMMENT
LOW	langroid/language_models/utils.py	75	# Increment retries	COMMENT
LOW	langroid/language_models/utils.py	78	# Check if max retries has been reached	COMMENT
LOW	langroid/language_models/utils.py	158	# Increment retries	COMMENT
LOW	langroid/language_models/utils.py	161	# Check if max retries has been reached	COMMENT
LOW	langroid/language_models/client_cache.py	368	# Check if close is a coroutine function (async)	COMMENT
LOW	langroid/utils/pydantic_utils.py	461	# Check if metadata_cols is empty	COMMENT
LOW	langroid/utils/git_utils.py	103	# Check if we're on the master branch	COMMENT
LOW	langroid/agent/task.py	2009	# Check if task should be done if message contains a tool	COMMENT
LOW	langroid/agent/xml_tool_message.py	128	# Check if this corresponds to a nested Pydantic model	COMMENT
LOW	langroid/agent/batch.py	464	# Check if the method is async	COMMENT
LOW	langroid/agent/chat_agent.py	1184	# Check if tool class was attached to the exception	STRING
LOW	langroid/agent/chat_agent.py	2124	# Check if callback accepts 'reasoning' param or **kwargs	STRING
LOW	langroid/agent/special/doc_chat_agent.py	158	# Check if module exists in sys.path	STRING
LOW	langroid/agent/special/table_chat_agent.py	262	# Return the result	STRING
LOW	langroid/agent/special/neo4j/neo4j_chat_agent.py	259	# Check if query contains database/collection creation patterns	STRING
LOW	langroid/agent/special/arangodb/arangodb_agent.py	231	# Check if any non-system collection has data	STRING
LOW	langroid/vector_store/weaviatedb.py	292	# Check if the name now meets the criteria	STRING
LOW	langroid/parsing/md_parser.py	75	# Check if we're toggling in/out of a fenced code block	COMMENT
LOW	langroid/parsing/md_parser.py	95	# Check if the line is a heading	COMMENT
LOW	langroid/parsing/md_parser.py	369	# Check if this is a header-only node.	COMMENT
LOW	langroid/parsing/md_parser.py	437	# Check if this is a header node (content matches last item in path)	COMMENT
LOW	langroid/parsing/md_parser.py	471	# Check if the node is "heading-only" and has children	COMMENT
LOW	langroid/parsing/md_parser.py	494	# Check if we can roll up everything (node + children) in a single chunk	COMMENT
LOW	langroid/parsing/urls.py	77	# Check if the user wants to exit the loop.	COMMENT
LOW	langroid/parsing/document_parser.py	89	# Check if the MIME type is not a text type	COMMENT
LOW	langroid/parsing/file_attachment.py	112	# Check if it's a URL	COMMENT

Cross-Language Confusion8 hits · 45 pts

Severity	File	Line	Snippet	Context
HIGH	tests/main/test_mcp_tools.py	1831	# Optional[int] (anyOf including null) -> Union[int, None]	COMMENT
HIGH	tests/main/test_json.py	101	('{"key": null}', {"key": None}),	CODE
HIGH	tests/main/test_json.py	120	"null": null,	STRING
HIGH⚡	tests/main/test_json.py	184	'{"key": undefined}', # JavaScript-style undefined (gets repaired)	CODE
HIGH⚡	tests/main/test_json.py	188	'{"key": null, "key2": }', # Trailing comma with no value	CODE
HIGH	tests/extras/test_csv_kg_chat.py	64	assert nodes_query_df.equals(df)	CODE
HIGH	langroid/utils/html_logger.py	434	if (savedState !== null) {{	CODE
HIGH	langroid/utils/html_logger.py	453	if (contentElement && toggleElement) {{	CODE

Over-Commented Block33 hits · 33 pts

Severity	File	Line	Snippet	Context
LOW	tests/main/test_md_parser.py	681		COMMENT
LOW	tests/main/test_task_lineage_rewind.py	161		COMMENT
LOW	tests/main/test_task_lineage_rewind.py	321	)	COMMENT
LOW	tests/main/test_tool_messages.py	1481	# Strict fallback disables the default arguments, but the LLM	COMMENT
LOW	tests/main/test_pandas_utils.py	81	def test_block(expr, msg):	COMMENT
LOW	examples/portkey/requirements.txt	1	# Requirements for Portkey examples	COMMENT
LOW	examples/chainlit/.chainlit/config.toml	61		COMMENT
LOW	examples/chainlit/.chainlit/config.toml	81		COMMENT
LOW	examples/docqa/rag-local-simple.py	41	)	COMMENT
LOW	examples/summarize/summ.py	41	# Create the llm config object.	COMMENT
LOW	examples/basic/chat-local.py	21	# Notes:	COMMENT
LOW	examples/basic/fn-call-local-simple.py	101	timeout=45,	COMMENT
LOW	examples/kg-chat/chat-arangodb.py	181		COMMENT
LOW	examples/kg-chat/chat-arangodb-igvf.py	141	# You can have this in a loop with the user, like so:	COMMENT
LOW	scripts/fix-pydantic-imports.sh	1	#!/bin/bash	COMMENT
LOW	.github/workflows/pytest.yml	141	# - name: Restore uv cache	COMMENT
LOW	.github/workflows/pytest-subset.yml	1	name: Pytest subset (manual)	COMMENT
LOW	.chainlit/config.toml	61		COMMENT
LOW	.chainlit/config.toml	81		COMMENT
LOW	langroid/language_models/openai_gpt.py	481	# set the actual model name by stripping the "litellm/" prefix	COMMENT
LOW	langroid/language_models/openai_gpt.py	2081	result = completion_call(**kwargs)	COMMENT
LOW	langroid/agent/task.py	1161		COMMENT
LOW	langroid/agent/chat_document.py	61	# multi-agent handoff (a Task then relabels sender -> USER). Lets handle-only	COMMENT
LOW	langroid/agent/chat_document.py	81	cached: bool = False	COMMENT
LOW	langroid/agent/tool_message.py	101	id: str = "" # placeholder for OpenAI-API tool_call_id	COMMENT
LOW	langroid/agent/base.py	821	)	COMMENT
LOW	langroid/agent/base.py	901	source=e,	COMMENT
LOW	langroid/agent/base.py	1741	return str(xe)	COMMENT
LOW	langroid/agent/base.py	1881	try:	COMMENT
LOW	langroid/agent/special/doc_chat_agent.py	201	# and those will already be in stand-alone form, so in this mode	COMMENT
LOW	langroid/agent/special/doc_chat_agent.py	1441		COMMENT
LOW	langroid/agent/special/sql/sql_chat_agent.py	121	# query text (case-insensitive) as a defense-in-depth layer in addition to the	COMMENT
LOW	langroid/agent/special/sql/sql_chat_agent.py	241		COMMENT

Fake / Example Data26 hits · 30 pts

Severity	File	Line	Snippet	Context
LOW	tests/main/test_mcp_tools.py	411	recipient__="John Doe",	CODE
LOW	tests/main/test_mcp_tools.py	418	assert msg.recipient__ == "John Doe"	CODE
LOW⚡	tests/main/test_neo4j_chat_agent.py	170	CREATE (p:Person {name: 'John Doe', age: 30})	CODE
LOW⚡	tests/main/test_neo4j_chat_agent.py	176	MATCH (p:Person {name: 'John Doe'})	CODE
LOW⚡	tests/main/test_neo4j_chat_agent.py	183	MATCH (p:Person {name: 'John Doe'})	CODE
LOW⚡	tests/main/test_pydantic_utils.py	23	name="John Doe", age=30, details=DetailsModel(height=180.5, weight=75.0)	CODE
LOW⚡	tests/main/test_pydantic_utils.py	28	assert result == {"name": "John Doe"}	CODE
LOW⚡	tests/main/test_pydantic_utils.py	32	assert result == {"name": "John Doe", "age": 30, "weight": 75.0}	CODE
LOW⚡	tests/main/test_object_registry.py	102	ObjectRegistry.registry["dummy_id"] = None	CODE
LOW⚡	tests/main/test_object_registry.py	103	# Ensure "dummy_id" is in the registry before cleanup	COMMENT
LOW⚡	tests/main/test_object_registry.py	104	assert "dummy_id" in ObjectRegistry.registry	CODE
LOW⚡	tests/main/test_object_registry.py	107	# "dummy_id" should be removed post cleanup	COMMENT
LOW⚡	tests/main/test_object_registry.py	108	assert "dummy_id" not in ObjectRegistry.registry	CODE
LOW⚡	tests/main/test_xml_tool_message.py	361	name="John Doe",	STRING
LOW⚡	tests/main/test_xml_tool_message.py	364	street="123 Main St", city="Anytown", country="USA"	STRING
LOW⚡	tests/main/test_xml_tool_message.py	371	name="Jane Doe",	STRING
LOW⚡	tests/main/test_xml_tool_message.py	402	name="Jane Doe",	STRING
LOW⚡	tests/main/test_xml_tool_message.py	410	name="John Doe",	STRING
LOW⚡	tests/main/test_xml_tool_message.py	412	address=Address(street="123 Main St", city="Anytown", country="USA"),	STRING
LOW⚡	tests/main/test_xml_tool_message.py	491	assert parsed.person.name == "John Doe"	STRING
LOW⚡	tests/main/test_xml_tool_message.py	494	assert parsed.person.address.street == "123 Main St"	STRING
LOW	tests/main/test_xml_tool_message.py	562	name="Jane Doe",	STRING
LOW	examples/chainlit/.chainlit/translations/pt-BR.json	53	"placeholder": "Digite sua mensagem aqui..."	CODE
LOW	examples/chainlit/.chainlit/translations/en-US.json	53	"placeholder": "Ask, respond, give feedback, or just 'c' for continue..."	CODE
LOW	.chainlit/translations/pt-BR.json	53	"placeholder": "Digite sua mensagem aqui..."	CODE
LOW	.chainlit/translations/en-US.json	53	"placeholder": "Ask, respond, give feedback, or just 'c' for continue..."	CODE

AI Structural Patterns32 hits · 30 pts

Severity	File	Line	Context
LOW	tests/main/test_table_chat_agent.py	60	CODE
LOW	tests/main/test_seltz_search.py	30	CODE
LOW	examples/chainlit/multi-agent-nested-tool.py	47	CODE
LOW	…mples/chainlit/non-callback/chat-search-no-callback.py	31	CODE
LOW	…mples/chainlit/non-callback/chat-search-no-callback.py	38	CODE
LOW	examples/chainlit/non-callback/chat-tool-no-callback.py	38	CODE
LOW	examples/docqa/chat.py	53	CODE
LOW	examples/docqa/rag-concurrent.py	132	CODE
LOW	examples/docqa/doc-chunk-enrich.py	263	CODE
LOW	examples/basic/fn-call-local-numerical.py	106	CODE
LOW	…amples/basic/multi-agent-search-critic/search_agent.py	130	CODE
LOW	…asic/multi-agent-search-critic-no-orch/search_agent.py	130	CODE
LOW	langroid/embedding_models/protoc/embeddings_pb2_grpc.py	53	CODE
LOW	langroid/language_models/openai_gpt.py	974	CODE
LOW	langroid/language_models/openai_gpt.py	1139	CODE
LOW	langroid/language_models/openai_gpt.py	1582	CODE
LOW	langroid/agent/task.py	209	CODE
LOW	langroid/agent/task.py	789	CODE
LOW	langroid/agent/task.py	957	CODE
LOW	langroid/agent/task.py	1539	CODE
LOW	langroid/agent/batch.py	268	CODE
LOW	langroid/agent/batch.py	367	CODE
LOW	langroid/agent/batch.py	484	CODE
LOW	langroid/agent/base.py	618	CODE
LOW	langroid/agent/base.py	876	CODE
LOW	langroid/agent/base.py	929	CODE
LOW	langroid/agent/base.py	1122	CODE
LOW	langroid/agent/tools/task_tool.py	218	CODE
LOW	langroid/agent/tools/task_tool.py	255	CODE
LOW	langroid/agent/tools/mcp/fastmcp_client.py	85	CODE
LOW	langroid/agent/special/relevance_extractor_agent.py	87	CODE
LOW	langroid/agent/special/relevance_extractor_agent.py	118	CODE

Structural Annotation Overuse11 hits · 23 pts

Severity	File	Line	Snippet	Context
LOW	docs/blog/posts/malade.md	111	### Step 2: Identifying Drug-Outcome Associations (`DrugOutcomeInfoAgent`)	COMMENT
LOW	docs/blog/posts/malade.md	129	### Step 3: Labeling Drug Category-Outcome Associations (`CategoryOutcomeRiskAgent`)	COMMENT
LOW⚡	docs/notes/portkey.md	433	# Step 1: Basic Portkey	COMMENT
LOW⚡	docs/notes/portkey.md	438	# Step 2: Add caching	COMMENT
LOW⚡	docs/notes/portkey.md	446	# Step 3: Add observability	COMMENT
LOW⚡	issues/html-logger-implementation.md	43	#### Step 1: Create HTML Logger Foundation	COMMENT
LOW⚡	issues/html-logger-implementation.md	48	#### Step 2: Integrate with Task System	COMMENT
LOW⚡	issues/html-logger-implementation.md	53	#### Step 3: Implement HTML Generation	COMMENT
LOW⚡	issues/html-logger-implementation.md	58	#### Step 4: Add JavaScript Functionality	COMMENT
LOW⚡	langroid/parsing/url_loader.py	490	# Step 1: Separate URLs into documents and web pages	COMMENT
LOW⚡	langroid/parsing/url_loader.py	498	# Step 2: Process web page URLs asynchronously	COMMENT

AI Slop Vocabulary17 hits · 19 pts

Severity	File	Line	Snippet	Context
LOW	tests/main/test_doc_chat_agent.py	277	# to just use ChatAgent's LLM response - this ensures that the system msg	STRING
MEDIUM	tests/main/test_mcp_tools.py	736	# Add timeout and robust skipping similar to npx test	STRING
LOW⚡	tests/main/test_json.py	179	# Test cases that should not crash, just return ""	COMMENT
LOW⚡	tests/main/test_json.py	193	# Should never crash, just return empty string or found value	COMMENT
LOW	tests/extras/test_doc_chat_agent_llamacpp.py	335	# to just use ChatAgent's LLM response - this ensures that the system msg	STRING
MEDIUM	examples/docqa/rag-concurrent.py	34	# Use Langroid's built-in run_batch_tasks harness instead of the custom one	STRING
LOW	examples/basic/schedule-extract.py	112	# from the input text. For this example, we'll just return a placeholder.	STRING
LOW	langroid/mytypes.py	96	# If parsing fails, just use the original date	COMMENT
LOW	langroid/language_models/openai_gpt.py	495	# so we can just use `openai.*` methods directly,	STRING
LOW	langroid/agent/chat_agent.py	691	# Otherwise just return `no_tool_option` as is:	COMMENT
LOW	langroid/agent/tools/mcp/fastmcp_client.py	660	# Otherwise, just return the text content	COMMENT
LOW	langroid/agent/special/doc_chat_agent.py	728	# no filter, so just use the docs passed in	STRING
LOW	langroid/agent/special/doc_chat_agent.py	1642	# no relevance extraction: simply return passages	STRING
LOW	langroid/parsing/utils.py	189	# just add them to the last sentence and break	COMMENT
LOW	langroid/parsing/md_parser.py	316	# we just add it anyway to avoid creating a tiny final chunk.	COMMENT
LOW	langroid/parsing/md_parser.py	546	# Pure text, no hierarchy, so just use recursive_chunk	COMMENT
LOW	langroid/parsing/urls.py	156	# no need to crawl, just return the original list	STRING

Slop Phrases9 hits · 17 pts

Severity	File	Line	Snippet	Context
LOW	examples/chainlit/dependency_chatbot.py	232	DON'T forget to include the package name in your questions.	CODE
MEDIUM	examples/docqa/rag-local-simple.py	44	# Once this works, then you can try the DocChatAgent	COMMENT
MEDIUM	examples/summarize/summ-batch.py	56	# Once this works, then you can try the DocChatAgent	COMMENT
MEDIUM	examples/summarize/summ.py	54	# Once this works, then you can try the DocChatAgent	COMMENT
MEDIUM	examples/basic/fn-call-local-numerical.py	152	# Once this works, then you can try the rest of the example.	STRING
MEDIUM	examples/basic/fn-call-local-simple.py	105	# Once this works, then you can try the rest of the example.	COMMENT
LOW	examples/kg-chat/dependency_chatbot.py	255	DON'T forget to include the package name in your questions.	CODE
LOW	langroid/agent/xml_tool_message.py	336	Make sure to replace the placeholders with actual values	CODE
MEDIUM	langroid/parsing/md_parser.py	566	# (you can adjust chunk_size, overlap_tokens, variation_percent)	STRING

Magic Placeholder Names3 hits · 15 pts

Severity	File	Line	Snippet	Context
HIGH	docs/notes/weaviate.md	28	WEAVIATE_API_KEY=<your_api_key>	CODE
HIGH	docs/notes/tavily_search.md	22	TAVILY_API_KEY=<your_api_key>	CODE
HIGH	docs/notes/seltz_search.md	22	SELTZ_API_KEY=<your_api_key>	CODE

Synthetic Comment Markers1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	langroid/language_models/base.py	168	Represents a single tool call in a list of tool calls generated by OpenAI LLM API.	CODE

Verbosity Indicators2 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW⚡	langroid/parsing/url_loader.py	490	# Step 1: Separate URLs into documents and web pages	COMMENT
LOW⚡	langroid/parsing/url_loader.py	498	# Step 2: Process web page URLs asynchronously	COMMENT

Example Usage Blocks2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	langroid/parsing/md_parser.py	557	# Example usage:	COMMENT
LOW	langroid/parsing/urls.py	277	# Example usage	STRING

TODO Padding1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	langroid/embedding_models/models.py	43	# TODO: Add auth support for Azure OpenAI via AzureADTokenProvider	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings