huggingface/smolagents

26.0

Adjusted Score

26.0

Raw Score

100%

Time Factor

2026-07-11

Last Push

28.3K

Stars

Python

Language

46.1K

Lines of Code

176

Files

787

Pattern Hits

2026-07-14

Scan Date

0.45

HC Hit Rate

What These Metrics Mean

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

Score History

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

Severity Breakdown

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

CRITICAL 1HIGH 79MEDIUM 83LOW 624

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 787 distinct pattern matches across 19 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 Repetition57 hits · 285 pts

Severity	File	Snippet	Context
HIGH	tests/test_models.py	get weather in the next days at given location. secretly this tool does not care about the location, it hates the weathe	STRING
HIGH	tests/test_tools.py	get weather in the next days at given location. secretly this tool does not care about the location, it hates the weathe	STRING
HIGH	examples/agent_from_any_llm.py	get weather in the next days at given location. secretly this tool does not care about the location, it hates the weathe	STRING
HIGH	tests/test_tools.py	this is a tool that returns the most downloaded model of a given task on the hugging face hub. it returns the name of th	STRING
HIGH	docs/source/zh/tutorials/tools.md	this is a tool that returns the most downloaded model of a given task on the hugging face hub. it returns the name of th	STRING
HIGH	docs/source/hi/tutorials/tools.md	this is a tool that returns the most downloaded model of a given task on the hugging face hub. it returns the name of th	STRING
HIGH	docs/source/en/tutorials/tools.md	this is a tool that returns the most downloaded model of a given task on the hugging face hub. it returns the name of th	STRING
HIGH	docs/source/zh/guided_tour.md	this is a tool that returns the most downloaded model of a given task on the hugging face hub. it returns the name of th	STRING
HIGH	docs/source/hi/guided_tour.md	this is a tool that returns the most downloaded model of a given task on the hugging face hub. it returns the name of th	STRING
HIGH	docs/source/ko/guided_tour.md	this is a tool that returns the most downloaded model of a given task on the hugging face hub. it returns the name of th	STRING
HIGH	docs/source/en/guided_tour.md	this is a tool that returns the most downloaded model of a given task on the hugging face hub. it returns the name of th	STRING
HIGH	docs/source/zh/_config.py	# installation ! pip install smolagents # to install from source instead of the last release, comment the command above	STRING
HIGH	docs/source/hi/_config.py	# installation ! pip install smolagents # to install from source instead of the last release, comment the command above	STRING
HIGH	docs/source/ko/_config.py	# installation ! pip install smolagents # to install from source instead of the last release, comment the command above	STRING
HIGH	docs/source/es/_config.py	# installation ! pip install smolagents # to install from source instead of the last release, comment the command above	STRING
HIGH	docs/source/en/_config.py	# installation ! pip install smolagents # to install from source instead of the last release, comment the command above	STRING
HIGH	docs/source/zh/examples/web_browser.md	searches for text on the current page via ctrl + f and jumps to the nth occurrence. args: text: the text to search for n	STRING
HIGH	docs/source/en/examples/web_browser.md	searches for text on the current page via ctrl + f and jumps to the nth occurrence. args: text: the text to search for n	STRING
HIGH	src/smolagents/vision_web_browser.py	searches for text on the current page via ctrl + f and jumps to the nth occurrence. args: text: the text to search for n	STRING
HIGH	docs/source/zh/examples/web_browser.md	closes any visible modal or pop-up on the page. use this to dismiss pop-up windows! this does not work on cookie consent	STRING
HIGH	docs/source/ko/examples/web_browser.md	closes any visible modal or pop-up on the page. use this to dismiss pop-up windows! this does not work on cookie consent	STRING
HIGH	docs/source/en/examples/web_browser.md	closes any visible modal or pop-up on the page. use this to dismiss pop-up windows! this does not work on cookie consent	STRING
HIGH	src/smolagents/vision_web_browser.py	closes any visible modal or pop-up on the page. use this to dismiss pop-up windows! this does not work on cookie consent	STRING
HIGH	docs/source/zh/examples/web_browser.md	you can use helium to access websites. don't bother about the helium driver, it's already managed. we've already ran "fr	STRING
HIGH	docs/source/ko/examples/web_browser.md	you can use helium to access websites. don't bother about the helium driver, it's already managed. we've already ran "fr	STRING
HIGH	docs/source/en/examples/web_browser.md	you can use helium to access websites. don't bother about the helium driver, it's already managed. we've already ran "fr	STRING
HIGH	docs/source/zh/examples/web_browser.md	please navigate to https://en.wikipedia.org/wiki/chicago and give me a sentence containing the word "1992" that mentions	STRING
HIGH	docs/source/ko/examples/web_browser.md	please navigate to https://en.wikipedia.org/wiki/chicago and give me a sentence containing the word "1992" that mentions	STRING
HIGH	docs/source/en/examples/web_browser.md	please navigate to https://en.wikipedia.org/wiki/chicago and give me a sentence containing the word "1992" that mentions	STRING
HIGH	src/smolagents/vision_web_browser.py	please navigate to https://en.wikipedia.org/wiki/chicago and give me a sentence containing the word "1992" that mentions	STRING
HIGH	docs/source/zh/examples/web_browser.md	i'm trying to find how hard i have to work to get a repo in github.com/trending. can you navigate to the profile for the	STRING
HIGH	docs/source/ko/examples/web_browser.md	i'm trying to find how hard i have to work to get a repo in github.com/trending. can you navigate to the profile for the	STRING
HIGH	docs/source/en/examples/web_browser.md	i'm trying to find how hard i have to work to get a repo in github.com/trending. can you navigate to the profile for the	STRING
HIGH	src/smolagents/vision_web_browser.py	i'm trying to find how hard i have to work to get a repo in github.com/trending. can you navigate to the profile for the	STRING
HIGH	docs/source/zh/examples/multiagents.md	visits a webpage at the given url and returns its content as a markdown string. args: url: the url of the webpage to vis	STRING
HIGH	docs/source/hi/examples/multiagents.md	visits a webpage at the given url and returns its content as a markdown string. args: url: the url of the webpage to vis	STRING
HIGH	docs/source/en/examples/multiagents.md	visits a webpage at the given url and returns its content as a markdown string. args: url: the url of the webpage to vis	STRING
HIGH	docs/source/zh/examples/text_to_sql.md	allows you to perform sql queries on the table. returns a string representation of the result. the table is named 'recei	STRING
HIGH	docs/source/hi/examples/text_to_sql.md	allows you to perform sql queries on the table. returns a string representation of the result. the table is named 'recei	STRING
HIGH	docs/source/en/examples/text_to_sql.md	allows you to perform sql queries on the table. returns a string representation of the result. the table is named 'recei	STRING
HIGH	examples/text_to_sql.py	allows you to perform sql queries on the table. returns a string representation of the result. the table is named 'recei	STRING
HIGH	docs/source/zh/examples/text_to_sql.md	allows you to perform sql queries on the table. beware that this tool's output is a string representation of the executi	STRING
HIGH	docs/source/hi/examples/text_to_sql.md	allows you to perform sql queries on the table. beware that this tool's output is a string representation of the executi	STRING
HIGH	docs/source/ko/examples/text_to_sql.md	allows you to perform sql queries on the table. beware that this tool's output is a string representation of the executi	STRING
HIGH	docs/source/en/examples/text_to_sql.md	allows you to perform sql queries on the table. beware that this tool's output is a string representation of the executi	STRING
HIGH	docs/source/zh/tutorials/building_good_agents.md	returns the weather report. args: location: the name of the place that you want the weather for. date_time: the date and	STRING
HIGH	docs/source/hi/tutorials/building_good_agents.md	returns the weather report. args: location: the name of the place that you want the weather for. date_time: the date and	STRING
HIGH	docs/source/ko/tutorials/building_good_agents.md	returns the weather report. args: location: the name of the place that you want the weather for. date_time: the date and	STRING
HIGH	docs/source/en/tutorials/building_good_agents.md	returns the weather report. args: location: the name of the place that you want the weather for. date_time: the date and	STRING
HIGH	docs/source/zh/tutorials/building_good_agents.md	returns the weather report. args: location: the name of the place that you want the weather for. should be a place name,	STRING
HIGH	docs/source/hi/tutorials/building_good_agents.md	returns the weather report. args: location: the name of the place that you want the weather for. should be a place name,	STRING
HIGH	docs/source/ko/tutorials/building_good_agents.md	returns the weather report. args: location: the name of the place that you want the weather for. should be a place name,	STRING
HIGH	docs/source/en/tutorials/building_good_agents.md	returns the weather report. args: location: the name of the place that you want the weather for. should be a place name,	STRING
HIGH	docs/source/ko/tutorials/building_good_agents.md	{{ agent.description }} args: task: long detailed description of the task. additional_args: dictionary of extra inputs t	STRING
HIGH	docs/source/en/tutorials/building_good_agents.md	{{ agent.description }} args: task: long detailed description of the task. additional_args: dictionary of extra inputs t	STRING
HIGH	src/smolagents/prompts/code_agent.yaml	{{ agent.description }} args: task: long detailed description of the task. additional_args: dictionary of extra inputs t	STRING
HIGH	src/smolagents/prompts/structured_code_agent.yaml	{{ agent.description }} args: task: long detailed description of the task. additional_args: dictionary of extra inputs t	STRING

Hyper-Verbose Identifiers373 hits · 281 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_remote_executors.py	28	def test_send_tools_empty_tools(self):	CODE
LOW⚡	tests/test_remote_executors.py	36	def test_send_variables_with_empty_dict_is_noop(self):	CODE
LOW⚡	tests/test_remote_executors.py	42	def test_send_variables_non_empty_generates_executable_deserializer_code(self):	CODE
LOW	tests/test_remote_executors.py	61	def test_send_variables_allow_pickle_handles_prefixed_payload(self):	CODE
LOW	tests/test_remote_executors.py	75	def test_deserialize_final_answer_rejects_unprefixed_payload(self):	CODE
LOW	tests/test_remote_executors.py	80	def test_send_tools_with_default_wikipedia_search_tool(self):	CODE
LOW	tests/test_remote_executors.py	190	def test_final_answer_patterns(self, code_action, expected_result):	STRING
LOW	tests/test_remote_executors.py	209	def test_custom_final_answer_with_custom_inputs(self):	STRING
LOW	tests/test_remote_executors.py	285	def test_execute_multiline_output(self):	STRING
LOW	tests/test_remote_executors.py	292	def test_execute_image_output(self):	STRING
LOW	tests/test_remote_executors.py	305	def test_syntax_error_handling(self):	STRING
LOW	tests/test_remote_executors.py	344	def test_final_answer_patterns(self, code_action, expected_result):	STRING
LOW	tests/test_remote_executors.py	363	def test_custom_final_answer_with_custom_inputs(self):	STRING
LOW	tests/test_remote_executors.py	478	def test_blaxel_executor_instantiation_without_blaxel_sdk(self):	STRING
LOW	tests/test_remote_executors.py	489	def test_blaxel_executor_instantiation_with_blaxel_sdk(	STRING
LOW	tests/test_remote_executors.py	531	def test_blaxel_executor_custom_parameters(	STRING
LOW	tests/test_remote_executors.py	578	def test_blaxel_executor_cleanup(self, mock_settings, mock_sandbox_instance, mock_create_kernel):	STRING
LOW⚡	tests/test_utils.py	168	def test_get_source_standard_class():	CODE
LOW⚡	tests/test_utils.py	176	def test_get_source_standard_function():	CODE
LOW⚡	tests/test_utils.py	184	def test_get_source_ipython_errors_empty_cells(ipython_shell):	CODE
LOW⚡	tests/test_utils.py	192	def test_get_source_ipython_errors_definition_not_found(ipython_shell):	CODE
LOW⚡	tests/test_utils.py	200	def test_get_source_ipython_errors_type_error():	CODE
LOW	tests/test_utils.py	467	def test_parse_json_blob_with_valid_json(raw_json, expected_data, expected_blob):	CODE
LOW	tests/test_utils.py	484	def test_parse_json_blob_with_invalid_json(raw_json):	CODE
LOW	tests/test_utils.py	520	def test_agent_gradio_app_template_excludes_class_keyword():	CODE
LOW	tests/conftest.py	16	def patch_multi_step_agent_with_suppressed_logging():	CODE
LOW	tests/conftest.py	19	def init_with_suppressed_logging(self, args, verbosity_level=LogLevel.OFF, *kwargs):	CODE
LOW	tests/test_function_type_hints_utils.py	207	def complex_docstring_types_func():	CODE
LOW	tests/test_function_type_hints_utils.py	224	def keywords_in_description_func():	CODE
LOW	tests/test_function_type_hints_utils.py	241	def test_get_json_schema_example(self):	CODE
LOW	tests/test_function_type_hints_utils.py	298	def test_get_json_schema_raises(self, request, fixture_name, should_fail):	CODE
LOW	tests/test_function_type_hints_utils.py	319	def test_schema_basic_structure(self, valid_func):	CODE
LOW	tests/test_function_type_hints_utils.py	395	def test_typed_docstring_parsing(self, typed_docstring_func):	CODE
LOW	tests/test_function_type_hints_utils.py	414	def test_mismatched_docstring_types(self, mismatched_types_func):	CODE
LOW	tests/test_function_type_hints_utils.py	422	def test_complex_docstring_types(self, complex_docstring_types_func):	CODE
LOW	tests/test_function_type_hints_utils.py	442	def test_type_in_description_handling(self, request, fixture_name, expected_description):	CODE
LOW	tests/test_function_type_hints_utils.py	450	def test_with_special_words_in_description_func(self, keywords_in_description_func):	CODE
LOW	tests/test_mcp_client.py	29	def structured_output_server_script():	CODE
LOW	tests/test_mcp_client.py	55	def test_mcp_client_with_syntax(echo_server_script: str):	CODE
LOW	tests/test_mcp_client.py	64	def test_mcp_client_with_structured_output(structured_output_server_script: str):	CODE
LOW	tests/test_mcp_client.py	87	def test_mcp_client_without_structured_output(structured_output_server_script: str):	CODE
LOW	tests/test_mcp_client.py	105	def test_mcp_client_try_finally_syntax(echo_server_script: str):	CODE
LOW	tests/test_import.py	6	def test_import_smolagents_without_extras(monkeypatch):	CODE
LOW	tests/test_monitoring.py	66	def test_code_agent_metrics_max_steps(self):	CODE
LOW	tests/test_monitoring.py	86	def test_code_agent_metrics_generation_error(self):	CODE
LOW	tests/test_monitoring.py	100	def test_streaming_agent_text_output(self):	CODE
LOW	tests/test_monitoring.py	119	def test_streaming_agent_image_output(self):	CODE
LOW	tests/test_monitoring.py	156	def test_streaming_with_agent_error(self):	CODE
LOW	tests/test_monitoring.py	190	def test_replay_with_chatmessage(self):	CODE
LOW	tests/test_monitoring.py	205	def test_logger_log_task_does_not_crash_on_stray_markup_or_control_chars(self):	CODE
LOW	tests/test_monitoring.py	228	def test_logger_log_task_accepts_non_string_payloads(self):	CODE
LOW	tests/test_gradio_ui.py	43	def test_upload_file_default_types(self):	CODE
LOW	tests/test_gradio_ui.py	57	def test_upload_file_default_types_disallowed(self):	CODE
LOW	tests/test_gradio_ui.py	90	def test_upload_file_invalid_type(self):	CODE
LOW	tests/test_gradio_ui.py	101	def test_upload_file_special_chars(self):	CODE
LOW	tests/test_gradio_ui.py	122	def test_upload_file_custom_types(self):	CODE
LOW	tests/test_gradio_ui.py	138	def test_stream_to_gradio_memory_step(self, mock_pull_messages):	CODE
LOW	tests/test_gradio_ui.py	153	def test_stream_to_gradio_stream_delta(self):	CODE
LOW	tests/test_gradio_ui.py	165	def test_stream_to_gradio_multiple_deltas(self):	CODE
LOW	tests/test_gradio_ui.py	188	def test_stream_to_gradio_parameters(self, task, task_images, reset_memory, additional_args):	CODE
313 more matches not shown…

Modern AI Meta-Vocabulary37 hits · 130 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	README.md	256	## How strong are open models for agentic workflows?	COMMENT
MEDIUM⚡	README.md	260	[Find the benchmarking code here](https://github.com/huggingface/smolagents/blob/main/examples/smolagents_benchmark/run.	CODE
MEDIUM⚡	README.md	263	<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolagents/benchmark_code_ag	CODE
MEDIUM	docs/source/zh/examples/rag.md	1	# Agentic RAG	COMMENT
MEDIUM	docs/source/zh/examples/multiagents.md	1	# 编排 multi-agent 系统 🤖🤝🤖	COMMENT
MEDIUM	docs/source/zh/examples/multiagents.md	103	## 构建我们的 multi-agent 系统 🤖🤝🤖	COMMENT
MEDIUM	docs/source/hi/guided_tour.md	76	model_id="ollama_chat/llama3.2", # This model is a bit weak for agentic behaviours though	CODE
MEDIUM	docs/source/hi/examples/rag.md	1	# एजेंटिक RAG	COMMENT
MEDIUM	docs/source/ko/guided_tour.md	185	model_id="ollama_chat/llama3.2", # This model is a bit weak for agentic behaviours though	CODE
MEDIUM⚡	docs/source/ko/examples/rag.md	1	# Agentic RAG[[agentic-rag]]	COMMENT
MEDIUM⚡	docs/source/ko/examples/rag.md	1	# Agentic RAG[[agentic-rag]]	COMMENT
MEDIUM⚡	docs/source/ko/examples/rag.md	5	## RAG(검색 증강 생성) 소개[[introduction-to-retrieval-augmented-generation-rag]]	COMMENT
MEDIUM⚡	docs/source/ko/examples/rag.md	28	## Agentic RAG: 더 강력한 접근 방식[[agentic-rag-a-more-powerful-approach]]	COMMENT
MEDIUM⚡	docs/source/ko/examples/rag.md	28	## Agentic RAG: 더 강력한 접근 방식[[agentic-rag-a-more-powerful-approach]]	COMMENT
MEDIUM⚡	docs/source/ko/examples/rag.md	32	### Agentic RAG의 주요 장점[[key-benefits-of-agentic-rag]]	COMMENT
MEDIUM	docs/source/ko/examples/rag.md	45	## Agentic RAG 시스템 구축하기[[building-an-agentic-rag-system]]	COMMENT
MEDIUM	docs/source/ko/examples/rag.md	45	## Agentic RAG 시스템 구축하기[[building-an-agentic-rag-system]]	COMMENT
MEDIUM	docs/source/ko/examples/rag.md	187	## Agentic RAG의 실제 적용 사례[[practical-applications-of-agentic-rag]]	COMMENT
MEDIUM	docs/source/ko/tutorials/building_good_agents.md	12	### 최고의 에이전트 시스템은 가장 단순합니다: 워크플로우를 최대한 단순하게 만드세요[[the-best-agentic-systems-are-the-simplest:-simplify-the-workflow-as-mu	COMMENT
MEDIUM⚡	docs/source/es/_toctree.yml	32	# title: Master your knowledge base with agentic RAG	COMMENT
MEDIUM⚡	docs/source/es/_toctree.yml	32	# title: Master your knowledge base with agentic RAG	COMMENT
MEDIUM⚡	docs/source/es/_toctree.yml	34	# title: Orchestrate a multi-agent system	COMMENT
MEDIUM	docs/source/en/guided_tour.md	198	model_id="ollama_chat/llama3.2", # This model is a bit weak for agentic behaviours though	CODE
MEDIUM	docs/source/en/conceptual_guides/intro_agents.md	3	## An introduction to agentic systems.	COMMENT
MEDIUM⚡	docs/source/en/examples/rag.md	1	# Agentic RAG	COMMENT
MEDIUM⚡	docs/source/en/examples/rag.md	5	## Introduction to Retrieval-Augmented Generation (RAG)	COMMENT
MEDIUM⚡	docs/source/en/examples/rag.md	9	### Why Use RAG?	COMMENT
MEDIUM⚡	docs/source/en/examples/rag.md	19	### Limitations of Traditional RAG	COMMENT
MEDIUM⚡	docs/source/en/examples/rag.md	28	## Agentic RAG: A More Powerful Approach	COMMENT
MEDIUM⚡	docs/source/en/examples/rag.md	32	### Key Benefits of Agentic RAG	COMMENT
MEDIUM	docs/source/en/examples/rag.md	45	## Building an Agentic RAG System	COMMENT
MEDIUM	docs/source/en/examples/rag.md	187	## Practical Applications of Agentic RAG	COMMENT
MEDIUM	docs/source/en/examples/multiagents.md	1	# Orchestrate a multi-agent system 🤖🤝🤖	COMMENT
MEDIUM	docs/source/en/examples/multiagents.md	100	## Build our multi-agent system 🤖🤝🤖	COMMENT
MEDIUM	docs/source/en/tutorials/secure_code_execution.md	472	### Approach 2: Running the entire agentic system in a sandbox	STRING
MEDIUM	docs/source/en/tutorials/building_good_agents.md	12	### The best agentic systems are the simplest: simplify the workflow as much as you can	COMMENT
MEDIUM	examples/inspect_multiagent_run.py	18	# Then we run the agentic part!	COMMENT

Self-Referential Comments38 hits · 125 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_import.py	9	# Create a virtual environment	COMMENT
MEDIUM	tests/test_gradio_ui.py	104	# Create a new temporary file with special characters	COMMENT
MEDIUM	tests/test_local_python_executor.py	588	# Create a generator expression that filters an infinite sequence	STRING
MEDIUM	tests/test_models.py	445	# Create a mock response for successful call	COMMENT
MEDIUM	tests/test_models.py	455	# Create a 429 rate limit error	COMMENT
MEDIUM	tests/test_models.py	570	# Create a mock response that contains a stop sequence in the middle	COMMENT
MEDIUM⚡	tests/test_memory.py	238	# Create a mock ChatCompletion-like object (this is what was causing the error)	COMMENT
MEDIUM⚡	tests/test_memory.py	244	# Create a ChatMessage with raw field containing the non-serializable object	COMMENT
MEDIUM⚡	tests/test_serialization.py	799	# Create an object that needs pickle	COMMENT
MEDIUM	tests/test_serialization.py	666	# Create a simple test image	COMMENT
MEDIUM⚡	tests/test_tools.py	616	# Define a test function with type hints and docstring	COMMENT
MEDIUM	tests/test_tools.py	102	# Define a tool class with the test type value	COMMENT
MEDIUM	tests/test_tools.py	631	# Create a tool from the function	COMMENT
MEDIUM	tests/test_tools.py	1038	# Create a tool with the appropriate signature	COMMENT
MEDIUM	tests/test_all_docs.py	171	# Initialize the class if needed	COMMENT
MEDIUM⚡	tests/test_agents.py	1006	# Create a simple agent with mocked model	COMMENT
MEDIUM⚡	tests/test_agents.py	1548	# Create a managed agent	COMMENT
MEDIUM⚡	tests/test_agents.py	1553	# Create a main agent with the managed agent	COMMENT
MEDIUM	tests/test_agents.py	1092	# Create a dummy agent	COMMENT
MEDIUM	tests/test_agents.py	1117	# Create a test agent with a list of callbacks	COMMENT
MEDIUM	tests/test_agents.py	1497	# Create a test agent dictionary	COMMENT
MEDIUM	tests/test_agents.py	1616	# Create a valid agent first	COMMENT
MEDIUM	tests/test_agents.py	2066	# Create a ToolCallingAgent instance with the test tool	COMMENT
MEDIUM	tests/test_agents.py	2070	# Create a memory step for process_tool_calls	COMMENT
MEDIUM	tests/test_agents.py	2285	# Create a test agent dictionary	COMMENT
MEDIUM	examples/open_deep_research/scripts/cookies.py	710	# Create a RequestsCookieJar instance	COMMENT
MEDIUM	examples/open_deep_research/scripts/mdconvert.py	644	# Create the extraction directory if it doesn't exist	COMMENT
MEDIUM⚡	examples/server/main.py	9	# Create an MCP client to connect to the MCP server	COMMENT
MEDIUM⚡	examples/server/main.py	16	# Create a CodeAgent with a specific model and the tools from the MCP client	COMMENT
MEDIUM⚡	examples/server/main.py	23	# Define the shutdown handler to disconnect the MCP client	COMMENT
MEDIUM	examples/plan_customization/plan_customization.py	115	# Define a task that will benefit from planning	COMMENT
MEDIUM	examples/async_agent/main.py	17	# Create a simple agent instance (customize as needed)	COMMENT
MEDIUM	src/smolagents/vision_web_browser.py	77	memory_step.observations_images = [image.copy()] # Create a copy to ensure it persists, important!	STRING
MEDIUM	src/smolagents/gradio_ui.py	119	# Create the tool call message	COMMENT
MEDIUM	src/smolagents/local_python_executor.py	307	# Create a new ThreadPoolExecutor for each call to avoid threading issues	COMMENT
MEDIUM	src/smolagents/local_python_executor.py	1638	# Define the actual execution logic	COMMENT
MEDIUM	src/smolagents/remote_executors.py	158	# Create a new class that inherits from the original FinalAnswerTool	COMMENT
MEDIUM	src/smolagents/remote_executors.py	926	# Create the sandbox	COMMENT

Excessive Try-Catch Wrapping70 hits · 72 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_local_python_executor.py	2228	def run_in_thread():	CODE
LOW⚡	tests/test_local_python_executor.py	1415	except Exception as e:	STRING
LOW	tests/test_local_python_executor.py	2245	except Exception as e:	STRING
LOW	tests/test_local_python_executor.py	2788	except Exception as e:	STRING
MEDIUM	tests/test_serialization.py	907	def serialize_data(data, index):	CODE
LOW	tests/test_serialization.py	912	except Exception as e:	CODE
LOW	tests/test_all_docs.py	153	except Exception:	CODE
LOW	docs/source/zh/examples/multiagents.md	93	except Exception as e:	CODE
LOW	docs/source/zh/tutorials/building_good_agents.md	95	except Exception as e:	CODE
LOW	docs/source/hi/examples/multiagents.md	92	except Exception as e:	CODE
LOW	docs/source/hi/tutorials/building_good_agents.md	96	except Exception as e:	CODE
LOW	docs/source/ko/examples/multiagents.md	90	except Exception as e:	CODE
LOW	docs/source/ko/tutorials/building_good_agents.md	95	except Exception as e:	CODE
LOW	docs/source/en/examples/multiagents.md	90	except Exception as e:	CODE
LOW	docs/source/en/tutorials/secure_code_execution.md	73	except Exception as e:	CODE
LOW	docs/source/en/tutorials/secure_code_execution.md	402	except Exception as e:	STRING
MEDIUM	docs/source/en/tutorials/secure_code_execution.md	403	print(f"Error during cleanup: {e}")	STRING
LOW	docs/source/en/tutorials/building_good_agents.md	95	except Exception as e:	CODE
LOW	examples/smolagents_benchmark/run.py	166	except Exception as e:	CODE
MEDIUM	examples/smolagents_benchmark/run.py	167	print("Error on ", augmented_question, e)	CODE
LOW	examples/open_deep_research/run_gaia.py	244	except Exception as e:	STRING
MEDIUM	examples/open_deep_research/run_gaia.py	245	print("Error on ", augmented_question, e)	STRING
LOW	examples/open_deep_research/run_gaia.py	280	except Exception as e:	STRING
MEDIUM	examples/open_deep_research/run_gaia.py	281	print("Error when loading records: ", e)	STRING
LOW	examples/open_deep_research/scripts/reformulator.py	37	except Exception:	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	274	except Exception:	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	318	except Exception:	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	443	except Exception:	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	514	except Exception:	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	553	except Exception:	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	618	except Exception:	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	864	except Exception:	CODE
LOW⚡	examples/open_deep_research/scripts/mdconvert.py	914	except Exception as e:	CODE
MEDIUM⚡	examples/open_deep_research/scripts/mdconvert.py	915	print(f"Error in converting: {e}")	CODE
LOW⚡	examples/open_deep_research/scripts/mdconvert.py	921	except Exception:	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	950	except Exception:	CODE
LOW	examples/open_deep_research/scripts/visual_qa.py	127	except Exception as e:	CODE
LOW	examples/open_deep_research/scripts/visual_qa.py	183	except Exception:	CODE
LOW	examples/plan_customization/plan_customization.py	132	except Exception as e:	CODE
LOW	examples/plan_customization/plan_customization.py	159	except Exception as resume_error:	CODE
LOW	examples/async_agent/main.py	41	except Exception as e:	CODE
LOW	src/smolagents/models.py	199	except Exception:	CODE
LOW	src/smolagents/models.py	404	except Exception as e:	CODE
LOW	src/smolagents/models.py	974	except Exception as e:	CODE
LOW	src/smolagents/local_python_executor.py	1169	except Exception as e:	CODE
LOW	src/smolagents/local_python_executor.py	1254	except Exception as e:	CODE
LOW	src/smolagents/local_python_executor.py	1262	except Exception as exit_exc:	CODE
LOW	src/smolagents/local_python_executor.py	1655	except Exception as e:	CODE
LOW	src/smolagents/agents.py	106	except Exception as e:	CODE
LOW	src/smolagents/agents.py	617	except Exception as e:	CODE
LOW	src/smolagents/agents.py	803	except Exception:	CODE
LOW	src/smolagents/agents.py	849	except Exception as e:	CODE
LOW	src/smolagents/agents.py	1324	except Exception as e:	CODE
LOW	src/smolagents/agents.py	1330	except Exception as e:	CODE
LOW	src/smolagents/agents.py	1479	except Exception as e:	CODE
LOW	src/smolagents/agents.py	1490	except Exception as e:	CODE
LOW	src/smolagents/agents.py	1699	except Exception as e:	CODE
LOW	src/smolagents/agents.py	1711	except Exception as e:	CODE
LOW	src/smolagents/agents.py	1734	except Exception as e:	CODE
LOW	src/smolagents/cli.py	140	except Exception:	CODE
10 more matches not shown…

Docstring Block Structure14 hits · 70 pts

Severity	File	Line	Snippet	Context
HIGH	examples/multiple_tools.py	53	Converts a specified amount from one currency to another using the ExchangeRate-API. Args: amount: The	STRING
HIGH	examples/multiple_tools.py	149	Fetches the current time for a given location using the World Time API. Args: location: The location fo	STRING
HIGH	examples/multiple_tools.py	196	Fetches a summary of a Wikipedia page for a given query. Args: query: The search term to look up on Wik	STRING
HIGH	src/smolagents/models.py	561	Process the input messages and return the model's response. Parameters: messages (`list[dict[str, s	STRING
HIGH	src/smolagents/models.py	861	A class that uses Hugging Face's Transformers library for language model interaction. This model allows you to load	STRING
HIGH	src/smolagents/models.py	1457	A class to interact with Hugging Face's Inference Providers for language model interaction. This model allows you t	STRING
HIGH	src/smolagents/models.py	1860	A model class for interacting with Amazon Bedrock Server models through the Bedrock API. This class provides a	STRING
HIGH	src/smolagents/tools.py	607	Creates a [`Tool`] from a Space given its id on the Hub. Args: space_id (`str`):	STRING
HIGH	src/smolagents/utils.py	199	Extract code blocs from the LLM's output. If a valid code block is passed, it returns it directly. Args:	STRING
HIGH	src/smolagents/remote_executors.py	308	Deserialize final answer with format detection. Accepts explicit prefix-based formats only: - "safe:" f	STRING
HIGH	src/smolagents/serialization.py	77	Convert Python objects to JSON-serializable format with type markers. Args: obj: Object to convert.	STRING
HIGH	src/smolagents/serialization.py	253	Serialize object to string. Args: obj: Object to serialize allow_pickle: If Fa	STRING
HIGH	src/smolagents/serialization.py	296	Deserialize string with format detection. Args: data: Serialized string (with "safe:" or "	STRING
HIGH	src/smolagents/_function_type_hints_utils.py	98	This function generates a JSON schema for a given function, based on its docstring and type hints. This is most	STRING

Deep Nesting68 hits · 55 pts

Severity	File	Line	Context
LOW	tests/test_tools.py	64	CODE
LOW	tests/test_tools.py	65	CODE
LOW	tests/test_agents.py	1387	CODE
LOW	examples/smolagents_benchmark/run.py	188	CODE
LOW	examples/open_deep_research/scripts/gaia_scorer.py	34	CODE
LOW	examples/open_deep_research/scripts/text_web_browser.py	55	CODE
LOW	examples/open_deep_research/scripts/text_web_browser.py	263	CODE
LOW	examples/open_deep_research/scripts/run_agents.py	72	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	237	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	337	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	420	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	927	CODE
LOW	examples/plan_customization/plan_customization.py	62	CODE
LOW	examples/plan_customization/plan_customization.py	100	CODE
LOW	src/smolagents/gradio_ui.py	378	CODE
LOW	src/smolagents/models.py	220	CODE
LOW	src/smolagents/models.py	288	CODE
LOW	src/smolagents/models.py	332	CODE
LOW	src/smolagents/models.py	1309	CODE
LOW	src/smolagents/models.py	1591	CODE
LOW	src/smolagents/models.py	1707	CODE
LOW	src/smolagents/memory.py	248	CODE
LOW	src/smolagents/local_python_executor.py	156	CODE
LOW	src/smolagents/local_python_executor.py	396	CODE
LOW	src/smolagents/local_python_executor.py	540	CODE
LOW	src/smolagents/local_python_executor.py	638	CODE
LOW	src/smolagents/local_python_executor.py	730	CODE
LOW	src/smolagents/local_python_executor.py	794	CODE
LOW	src/smolagents/local_python_executor.py	825	CODE
LOW	src/smolagents/local_python_executor.py	941	CODE
LOW	src/smolagents/local_python_executor.py	962	CODE
LOW	src/smolagents/local_python_executor.py	1026	CODE
LOW	src/smolagents/local_python_executor.py	1159	CODE
LOW	src/smolagents/local_python_executor.py	1236	CODE
LOW	src/smolagents/local_python_executor.py	1309	CODE
LOW	src/smolagents/local_python_executor.py	1380	CODE
LOW	src/smolagents/local_python_executor.py	1417	CODE
LOW	src/smolagents/local_python_executor.py	645	CODE
LOW	src/smolagents/tools.py	1361	CODE
LOW	src/smolagents/tools.py	144	CODE
LOW	src/smolagents/tool_validation.py	157	CODE
LOW	src/smolagents/tool_validation.py	49	CODE
LOW	src/smolagents/tool_validation.py	80	CODE
LOW	src/smolagents/tool_validation.py	90	CODE
LOW	src/smolagents/tool_validation.py	190	CODE
LOW	src/smolagents/agents.py	294	CODE
LOW	src/smolagents/agents.py	416	CODE
LOW	src/smolagents/agents.py	436	CODE
LOW	src/smolagents/agents.py	540	CODE
LOW	src/smolagents/agents.py	639	CODE
LOW	src/smolagents/agents.py	1276	CODE
LOW	src/smolagents/agents.py	1638	CODE
LOW	src/smolagents/cli.py	188	CODE
LOW	src/smolagents/utils.py	140	CODE
LOW	src/smolagents/utils.py	551	CODE
LOW	src/smolagents/default_tools.py	387	CODE
LOW	src/smolagents/default_tools.py	408	CODE
LOW	src/smolagents/agent_types.py	79	CODE
LOW	src/smolagents/agent_types.py	181	CODE
LOW	src/smolagents/remote_executors.py	481	CODE
8 more matches not shown…

Magic Placeholder Names8 hits · 40 pts

Severity	File	Line	Snippet	Context
HIGH	docs/source/zh/guided_tour.md	89	api_key="YOUR_API_KEY" # 如果需要可以替换为 API key	CODE
HIGH	docs/source/hi/guided_tour.md	78	api_key="YOUR_API_KEY" # replace with API key if necessary	CODE
HIGH	docs/source/ko/guided_tour.md	187	api_key="YOUR_API_KEY", # replace with API key if necessary	CODE
HIGH	docs/source/en/guided_tour.md	200	api_key="YOUR_API_KEY", # replace with API key if necessary	CODE
HIGH	examples/agent_from_any_llm.py	29	api_key="your-api-key", # replace with API key if necessary	CODE
HIGH	examples/multiple_tools.py	27	api_key = "your_api_key" # Replace with your API key from https://weatherstack.com/	CODE
HIGH	examples/multiple_tools.py	67	api_key = "your_api_key" # Replace with your actual API key from https://www.exchangerate-api.com/	CODE
HIGH	examples/multiple_tools.py	98	api_key = "your_api_key" # Replace with your actual API key from https://newsapi.org/	CODE

Over-Commented Block39 hits · 37 pts

Severity	File	Line	Snippet	Context
LOW	e2b.toml	1	# This is a config for E2B sandbox template.	COMMENT
LOW	tests/test_utils.py	1	# coding=utf-8	COMMENT
LOW	tests/test_function_type_hints_utils.py	1	# coding=utf-8	COMMENT
LOW	tests/test_search.py	1	# coding=utf-8	COMMENT
LOW	tests/test_monitoring.py	1	# coding=utf-8	COMMENT
LOW	tests/test_gradio_ui.py	1	# coding=utf-8	COMMENT
LOW	tests/test_local_python_executor.py	1	# coding=utf-8	COMMENT
LOW	tests/test_default_tools.py	1	# coding=utf-8	COMMENT
LOW	tests/test_final_answer.py	1	# coding=utf-8	COMMENT
LOW	tests/test_models.py	1	# coding=utf-8	COMMENT
LOW	tests/test_serialization.py	1	#!/usr/bin/env python	COMMENT
LOW	tests/test_tools.py	1	# coding=utf-8	COMMENT
LOW	tests/test_telemetry.py	1	# coding=utf-8	COMMENT
LOW	tests/test_all_docs.py	1	# coding=utf-8	COMMENT
LOW	tests/test_agents.py	1	# coding=utf-8	COMMENT
LOW	tests/test_types.py	1	# coding=utf-8	COMMENT
LOW	tests/utils/markers.py	1	# coding=utf-8	COMMENT
LOW	docs/source/es/_toctree.yml	1	- title: Primeros Pasos	COMMENT
LOW	docs/source/es/_toctree.yml	21	# - title: Conceptual guides	COMMENT
LOW	docs/source/es/_toctree.yml	41	# - local: examples/async_agent	COMMENT
LOW	examples/rag_using_chromadb.py	21	knowledge_base = datasets.load_dataset("m-ric/huggingface_doc", split="train")	COMMENT
LOW	examples/structured_output_tool.py	1	# How to run with uv:	COMMENT
LOW	examples/multiple_tools.py	221	# If you want to use the ToolCallingAgent instead, uncomment the following lines as they both will work	COMMENT
LOW	examples/open_deep_research/scripts/reformulator.py	81	# """.strip()}]})	COMMENT
LOW	src/smolagents/gradio_ui.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/models.py	1	# Copyright 2024 The HuggingFace Inc. team. All rights reserved.	COMMENT
LOW	src/smolagents/local_python_executor.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/monitoring.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/tools.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/__init__.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/agents.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/cli.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/utils.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/default_tools.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/mcp_client.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/agent_types.py	1	# coding=utf-8	COMMENT
LOW	src/smolagents/remote_executors.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/serialization.py	1	#!/usr/bin/env python	COMMENT
LOW	src/smolagents/_function_type_hints_utils.py	1	#!/usr/bin/env python	COMMENT

Unused Imports25 hits · 24 pts

Severity	File	Line	Context
LOW	tests/test_utils.py	333	CODE
LOW	tests/test_utils.py	226	CODE
LOW	examples/structured_output_tool.py	19	CODE
LOW	src/smolagents/memory.py	12	CODE
LOW	src/smolagents/tools.py	17	CODE
LOW	src/smolagents/tools.py	64	CODE
LOW	src/smolagents/__init__.py	19	CODE
LOW	src/smolagents/__init__.py	20	CODE
LOW	src/smolagents/__init__.py	21	CODE
LOW	src/smolagents/__init__.py	22	CODE
LOW	src/smolagents/__init__.py	23	CODE
LOW	src/smolagents/__init__.py	24	CODE
LOW	src/smolagents/__init__.py	25	CODE
LOW	src/smolagents/__init__.py	26	CODE
LOW	src/smolagents/__init__.py	27	CODE
LOW	src/smolagents/__init__.py	28	CODE
LOW	src/smolagents/__init__.py	29	CODE
LOW	src/smolagents/__init__.py	30	CODE
LOW	src/smolagents/__init__.py	31	CODE
LOW	src/smolagents/__init__.py	32	CODE
LOW	src/smolagents/agents.py	45	CODE
LOW	src/smolagents/utils.py	38	CODE
LOW	src/smolagents/mcp_client.py	18	CODE
LOW	src/smolagents/mcp_client.py	30	CODE
LOW	src/smolagents/remote_executors.py	896	CODE

Redundant / Tautological Comments13 hits · 19 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_import.py	25	# Check if the import was successful	COMMENT
LOW	tests/test_tools.py	115	# Check if we expect this to raise an exception	COMMENT
LOW	examples/multiple_tools.py	38	if data.get("error"): # Check if there's an error in the response	CODE
LOW	examples/open_deep_research/scripts/mdconvert.py	624	# Return the result	COMMENT
LOW	src/smolagents/local_python_executor.py	611	# Check if it is a docstring: first statement in class body which is a string literal expression	COMMENT
LOW	src/smolagents/tools.py	182	# Check if all elements are strings	COMMENT
LOW	src/smolagents/tool_validation.py	198	# Check if the assignment is more complex than simple literals	COMMENT
LOW	src/smolagents/agents.py	1463	# Check if the tool exists	COMMENT
LOW	src/smolagents/cli.py	265	# Check if we should run in interactive mode	COMMENT
LOW	src/smolagents/utils.py	572	# Check if we should retry	COMMENT
LOW	src/smolagents/remote_executors.py	183	# Check if all keys are strings (JSON-compatible)	COMMENT
LOW	src/smolagents/remote_executors.py	389	# Check if the error is a FinalAnswerException	COMMENT
LOW	src/smolagents/remote_executors.py	614	# Check if image exists, unless forced to rebuild	COMMENT

Modern Structural Boilerplate19 hits · 18 pts

Severity	File	Line	Snippet	Context
LOW	examples/open_deep_research/scripts/text_web_browser.py	55	def set_address(self, uri_or_path: str, filter_year: int \| None = None) -> None:	CODE
LOW	examples/open_deep_research/scripts/text_web_browser.py	92	def _set_page_content(self, content: str) -> None:	CODE
LOW	src/smolagents/gradio_ui.py	464	__all__ = ["stream_to_gradio", "GradioUI"]	CODE
LOW	src/smolagents/models.py	36	logger = logging.getLogger(__name__)	CODE
LOW	src/smolagents/models.py	2082	__all__ = [	CODE
LOW	src/smolagents/memory.py	18	__all__ = ["AgentMemory"]	CODE
LOW	src/smolagents/local_python_executor.py	39	logger = logging.getLogger(__name__)	CODE
LOW	src/smolagents/local_python_executor.py	1768	__all__ = ["evaluate_python_code", "LocalPythonExecutor"]	CODE
LOW	src/smolagents/monitoring.py	33	__all__ = ["AgentLogger", "LogLevel", "Monitor", "TokenUsage", "Timing"]	CODE
LOW	src/smolagents/tools.py	67	logger = logging.getLogger(__name__)	CODE
LOW	src/smolagents/tools.py	1415	__all__ = [	STRING
LOW	src/smolagents/agents.py	369	def _setup_managed_agents(self, managed_agents: list \| None = None) -> None:	CODE
LOW	src/smolagents/utils.py	41	__all__ = ["AgentError"]	CODE
LOW	src/smolagents/default_tools.py	687	__all__ = [	CODE
LOW	src/smolagents/mcp_client.py	27	__all__ = ["MCPClient"]	CODE
LOW	src/smolagents/agent_types.py	29	logger = logging.getLogger(__name__)	CODE
LOW	src/smolagents/agent_types.py	284	__all__ = ["AgentType", "AgentImage", "AgentText", "AgentAudio"]	CODE
LOW	src/smolagents/remote_executors.py	42	__all__ = ["BlaxelExecutor", "E2BExecutor", "ModalExecutor", "DockerExecutor"]	CODE
LOW	src/smolagents/serialization.py	36	__all__ = ["SerializationError", "SafeSerializer"]	CODE

Structural Annotation Overuse10 hits · 15 pts

Severity	File	Line	Snippet	Context
LOW	docs/source/en/examples/rag.md	51	### Step 1: Install Required Dependencies	COMMENT
LOW	docs/source/en/examples/rag.md	67	### Step 2: Prepare the Knowledge Base	COMMENT
LOW	docs/source/en/examples/rag.md	102	### Step 3: Create a Retriever Tool	COMMENT
LOW	docs/source/en/examples/rag.md	149	### Step 4: Create an Advanced Retrieval Agent	COMMENT
LOW	docs/source/en/examples/rag.md	171	### Step 5: Run the Agent to Answer Questions	COMMENT
LOW	docs/source/en/tutorials/inspect_runs.md	124	### Step 1: Install Dependencies	COMMENT
LOW	docs/source/en/tutorials/inspect_runs.md	130	### Step 2: Set Up Environment Variables	COMMENT
LOW	docs/source/en/tutorials/inspect_runs.md	162	### Step 3: Initialize the `SmolagentsInstrumentor`	COMMENT
LOW	docs/source/en/tutorials/inspect_runs.md	173	### Step 4: Run your smolagent	COMMENT
LOW	docs/source/en/tutorials/inspect_runs.md	205	### Step 5: View Traces in Langfuse	COMMENT

Hallucination Indicators1 hit · 10 pts

Severity	File	Line	Snippet	Context
CRITICAL	examples/open_deep_research/scripts/mdconvert.py	442	alt_text = shape._element._nvXxPr.cNvPr.attrib.get("descr", "")	CODE

AI Structural Patterns6 hits · 5 pts

Severity	File	Line	Context
LOW	examples/async_agent/main.py	30	CODE
LOW	src/smolagents/models.py	906	CODE
LOW	src/smolagents/models.py	1514	CODE
LOW	src/smolagents/agents.py	294	CODE
LOW	src/smolagents/agents.py	1527	CODE
LOW	src/smolagents/utils.py	531	CODE

Slop Phrases2 hits · 4 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/rag_using_chromadb.py	27	## For your own PDFs, you can use the following code to load them into source_docs	COMMENT
LOW	examples/open_deep_research/run_gaia.py	147	# WARNING: this dataset is gated: make sure you visit the repo to require access.	COMMENT

Overly Generic Function Names3 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_function_type_hints_utils.py	85	def process_data(items: list[str], config: dict[str, float], point: tuple[int, int]) -> dict:	CODE
LOW⚡	tests/test_serialization.py	453	def my_function():	CODE
LOW⚡	tests/test_tools.py	617	def test_function(items: list[str]) -> str:	CODE

AI Slop Vocabulary2 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	src/smolagents/local_python_executor.py	634	# For declarations without values (x: int), just return None	COMMENT
LOW	src/smolagents/local_python_executor.py	1462	# Constant -> just return the value	COMMENT

Fake / Example Data2 hits · 1 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_serialization.py	742	person = Person(name="Bob", address=Address(street="123 Main St", city="NYC"))	CODE
LOW	tests/test_serialization.py	747	assert result["address"]["street"] == "123 Main St"	CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings