simonw/llm

14.2

Adjusted Score

14.2

Raw Score

100%

Time Factor

2026-08-22

Last Push

12.4K

Stars

Python

Language

51.0K

Lines of Code

109

Files

799

Pattern Hits

2026-08-29

Scan Date

0.08

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 0HIGH 9MEDIUM 10LOW 780

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 799 distinct pattern matches across 13 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

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

Hyper-Verbose Identifiers674 hits · 553 pts

Severity	File	Line	Snippet	Context
LOW⚡	llm/hookspecs.py	18	def register_embedding_models(register):	CODE
LOW⚡	llm/hookspecs.py	23	def register_template_loaders(register):	CODE
LOW⚡	llm/hookspecs.py	28	def register_fragment_loaders(register):	CODE
LOW	llm/models.py	260	def _get_arguments_input_schema(function, name):	CODE
LOW	llm/models.py	289	def _implementation_arguments(tool: "Tool", tool_call: "ToolCall") -> dict:	CODE
LOW	llm/models.py	2707	def _append_tool_results_to_chain(chain, tool_results, attachments) -> list[Any]:	CODE
LOW	llm/models.py	2760	def _trailing_pending_tool_calls(messages) -> list[ToolCall]:	CODE
LOW	llm/models.py	3216	def supported_server_side_tools(self) -> tuple[type[ServerSideTool], ...]:	CODE
LOW	llm/models.py	3651	def _remove_titles_recursively(obj):	CODE
LOW	llm/__init__.py	237	def get_embedding_models_with_aliases() -> list["EmbeddingModelWithAliases"]:	CODE
LOW	llm/__init__.py	279	def get_embedding_model_aliases() -> dict[str, EmbeddingModel]:	CODE
LOW	llm/__init__.py	501	def get_default_embedding_model():	CODE
LOW	llm/__init__.py	505	def set_default_embedding_model(model):	CODE
LOW	llm/embeddings.py	183	def embed_multi_with_metadata(	CODE
LOW	llm/cli.py	122	async def display_async_stream_events(events, *, show_reasoning=True):	CODE
LOW	llm/cli.py	299	def process_fragments_in_chat(	CODE
LOW	llm/cli.py	388	def resolve_attachment_with_type(value: str, mimetype: str) -> Attachment:	CODE
LOW	llm/cli.py	404	def attachment_types_callback(ctx, param, values) -> list[Attachment]:	CODE
LOW	llm/cli.py	439	def _merge_template_attachments(template, attachments, attachment_types):	CODE
LOW	llm/cli.py	1764	def logs_json_for_response_ids(db, ids):	STRING
LOW	llm/cli.py	2066	def _format_tool_call_arguments(arguments):	STRING
LOW	llm/cli.py	2380	def model_matches_id_or_alias(model_with_aliases, model_ids):	STRING
LOW	llm/cli.py	2387	def render_model_with_aliases(	STRING
LOW	llm/cli.py	2455	def render_model_with_options(model_id, *, async_=False):	STRING
LOW	llm/utils.py	181	def extract_fenced_code_block(text: str, last: bool = False) -> str \| None:	CODE
LOW	llm/logs.py	1581	def _instances_by_tool_call_id(	CODE
LOW	llm/default_plugins/openai_models.py	427	def register_embedding_models(register):	CODE
LOW	llm/default_plugins/openai_models.py	1833	def supported_server_side_tools(self):	CODE
LOW	llm/default_plugins/openai_models.py	2116	def _finalize_responses_kwargs(self, prompt, stream, instructions=None):	CODE
LOW	llm/default_plugins/openai_models.py	2149	def _reasoning_text_from_item(self, item):	CODE
LOW	llm/default_plugins/openai_models.py	2194	def _reasoning_refresh_events(self, response_json, done_events):	CODE
LOW	llm/default_plugins/openai_models.py	2325	def _refresh_server_tool_events(self, output, done_events):	CODE
LOW	llm/default_plugins/openai_models.py	2350	def _non_streaming_output_events(self, output, response):	CODE
LOW	tests/test_cli_openai_models.py	49	def test_openai_options_min_max():	CODE
LOW	tests/test_cli_openai_models.py	108	def test_deprecated_models_are_not_registered(model_id):	CODE
LOW	tests/test_cli_openai_models.py	217	def test_code_interpreter_cli_tool_is_resolved_from_model(httpx_mock):	CODE
LOW	tests/test_cli_openai_models.py	274	def test_code_interpreter_cli_tool_is_reused_on_continue(httpx_mock, user_path):	CODE
LOW	tests/test_cli_openai_models.py	395	def test_web_search_cli_tool_is_resolved_from_model(httpx_mock):	CODE
LOW	tests/test_cli_openai_models.py	453	def test_tools_list_for_model_includes_server_side_tools():	CODE
LOW	tests/test_cli_openai_models.py	485	def test_tools_list_for_model_with_no_server_side_tools():	CODE
LOW	tests/test_cli_openai_models.py	496	def test_tools_list_rejects_unknown_model():	CODE
LOW	tests/test_cli_openai_models.py	520	def test_openai_image_detail_option_description(model_id, expected_description):	CODE
LOW	tests/test_cli_openai_models.py	525	def test_openai_image_detail_option_is_sent_on_image_attachments(httpx_mock):	CODE
LOW	tests/test_cli_openai_models.py	672	def test_openai_image_detail_original_is_rejected_for_other_models():	CODE
LOW	tests/test_async_parity.py	17	def test_echo_registered_for_both():	CODE
LOW	tests/test_async_parity.py	26	async def test_async_to_dict_captures_chain_and_output():	CODE
LOW	tests/test_async_parity.py	40	async def test_async_to_dict_raises_before_awaited():	CODE
LOW	tests/test_async_parity.py	48	async def test_async_from_dict_rehydrates():	CODE
LOW	tests/test_async_parity.py	66	async def test_async_from_dict_then_reply_continues():	CODE
LOW	tests/test_async_parity.py	90	async def test_async_from_row_response_messages_synthesized(tmp_path):	CODE
LOW	tests/test_async_parity.py	136	async def test_async_load_conversation_follow_up_preserves_chain(tmp_path):	CODE
LOW	tests/test_async_parity.py	188	async def test_sync_and_async_produce_identical_chain():	CODE
LOW	tests/test_async_parity.py	207	async def test_async_chain_tool_result_turn_has_full_chain():	CODE
LOW	tests/test_async_parity.py	246	async def test_astream_events_matches_stream_events_for_text_only():	CODE
LOW	tests/test_async_parity.py	276	async def test_async_from_dict_model_override():	CODE
LOW	tests/test_async_parity.py	288	def test_sync_from_dict_model_override():	CODE
LOW	tests/test_async_parity.py	300	async def test_async_to_dict_preserves_datetime():	CODE
LOW	tests/test_async_parity.py	310	async def test_async_to_dict_preserves_usage_when_set(async_mock_model):	CODE
LOW	tests/test_async_parity.py	328	async def test_async_reply_messages_kwarg_appends():	CODE
LOW	tests/test_async_parity.py	341	async def test_async_full_chain_to_dict_round_trip_three_turns():	CODE
614 more matches not shown…

Cross-Language Confusion7 hits · 40 pts

Severity	File	Line	Snippet	Context
HIGH	llm/utils.py	699	if re.match(r'\s*(["\[\d\-]\|true\|false\|null)', arg_body, re.IGNORECASE):	CODE
HIGH	llm/logs.py	1082	where json_extract(je.value, '$.literal') is not null)	CODE
HIGH	llm/migrations.py	676	and p2.tool_name is not null) as tools	CODE
HIGH	tests/test_llm_logs.py	1387	"""When reasoning is empty/null, no heading appears (existing	STRING
HIGH⚡	tests/test_plugins.py	479	'[{"id": ID, "tool_id": 1, "name": "upper", "output": "ONE", "tool_call_id": "tc_TCID", "exception": nul	CODE
HIGH⚡	tests/test_plugins.py	484	'[{"id": ID, "tool_id": 1, "name": "upper", "output": "TWO", "tool_call_id": "tc_TCID", "exception": nul	CODE
HIGH⚡	tests/test_plugins.py	492	'[{"id": ID, "tool_id": 1, "name": "upper", "output": "THREE", "tool_call_id": "tc_TCID", "exception": n	CODE

Deep Nesting39 hits · 34 pts

Severity	File	Line	Context
LOW	llm/plugins.py	23	CODE
LOW	llm/models.py	604	CODE
LOW	llm/models.py	104	CODE
LOW	llm/models.py	1311	CODE
LOW	llm/models.py	1879	CODE
LOW	llm/models.py	2226	CODE
LOW	llm/models.py	3009	CODE
LOW	llm/cli.py	136	CODE
LOW	llm/cli.py	228	CODE
LOW	llm/cli.py	685	CODE
LOW	llm/cli.py	1412	CODE
LOW	llm/cli.py	1683	CODE
LOW	llm/cli.py	1878	CODE
LOW	llm/cli.py	2802	CODE
LOW	llm/cli.py	3358	CODE
LOW	llm/cli.py	3501	CODE
LOW	llm/cli.py	3699	CODE
LOW	llm/cli.py	2087	CODE
LOW	llm/cli.py	3595	CODE
LOW	llm/utils.py	76	CODE
LOW	llm/utils.py	311	CODE
LOW	llm/utils.py	585	CODE
LOW	llm/logs.py	85	CODE
LOW	llm/logs.py	878	CODE
LOW	llm/parts.py	253	CODE
LOW	llm/default_plugins/openai_models.py	489	CODE
LOW	llm/default_plugins/openai_models.py	3037	CODE
LOW	llm/default_plugins/openai_models.py	580	CODE
LOW	llm/default_plugins/openai_models.py	1215	CODE
LOW	llm/default_plugins/openai_models.py	1385	CODE
LOW	llm/default_plugins/openai_models.py	1503	CODE
LOW	llm/default_plugins/openai_models.py	1746	CODE
LOW	llm/default_plugins/openai_models.py	1927	CODE
LOW	llm/default_plugins/openai_models.py	2037	CODE
LOW	llm/default_plugins/openai_models.py	2233	CODE
LOW	llm/default_plugins/openai_models.py	2350	CODE
LOW	llm/default_plugins/openai_models.py	2480	CODE
LOW	llm/default_plugins/openai_models.py	2724	CODE
LOW	tests/test_templates.py	510	CODE

Unused Imports26 hits · 20 pts

Severity	File	Line	Context
LOW	llm/__init__.py	11	CODE
LOW	llm/__init__.py	12	CODE
LOW	llm/__init__.py	12	CODE
LOW	llm/__init__.py	16	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	17	CODE
LOW	llm/__init__.py	42	CODE
LOW	llm/__init__.py	42	CODE
LOW	llm/__init__.py	42	CODE
LOW	llm/__init__.py	42	CODE
LOW	llm/__init__.py	42	CODE
LOW	llm/__init__.py	51	CODE
LOW	tests/test_options_parameter.py	89	CODE

Excessive Try-Catch Wrapping15 hits · 14 pts

Severity	File	Line	Snippet	Context
LOW	llm/models.py	1980	except Exception as ex: # noqa: BLE001	CODE
LOW	llm/models.py	2300	except Exception as ex: # noqa: BLE001	CODE
LOW	llm/models.py	2355	except Exception as ex: # noqa: BLE001	CODE
LOW	llm/models.py	2399	except Exception as ex: # noqa: BLE001	CODE
LOW	llm/models.py	2423	except Exception as ex: # noqa: BLE001	CODE
LOW	llm/models.py	2441	except Exception as ex: # noqa: BLE001	CODE
MEDIUM	llm/cli.py	381	def convert(self, value, param, ctx):	CODE
LOW	llm/cli.py	282	except Exception as ex: # noqa: BLE001	CODE
LOW	llm/cli.py	1142	except Exception as ex:	CODE
LOW	llm/cli.py	1663	except Exception as ex: # noqa: BLE001	STRING
LOW	llm/cli.py	4227	except Exception as ex: # noqa: BLE001	STRING
LOW	llm/default_plugins/openai_models.py	829	except Exception as ex:	CODE
LOW	llm/default_plugins/openai_models.py	2185	except Exception: # noqa: BLE001	CODE
LOW	docs/plugins/plugin-hooks.md	221	except Exception as e:	CODE
LOW	docs/plugins/plugin-hooks.md	271	except Exception as ex:	CODE

Modern AI Meta-Vocabulary5 hits · 14 pts

Severity	File	Line	Snippet	Context
MEDIUM	llm/__init__.py	442	# Try to resolve it to an embedding model	COMMENT
MEDIUM	tests/test_embed_cli.py	180	# --key should be passed through to the embedding model	COMMENT
MEDIUM	tests/test_embed_cli.py	201	# --key should be passed through to the embedding model for embed-multi too	COMMENT
MEDIUM	tests/test_openai_responses.py	1242	# item, otherwise the model loses its chain of thought.	COMMENT
MEDIUM	docs/embeddings/python-api.md	50	To work with embeddings in this way you will need an instance of a [sqlite-utils Database](https://sqlite-utils.datasett	CODE

AI Structural Patterns15 hits · 12 pts

Severity	File	Line	Context
LOW	llm/models.py	493	CODE
LOW	llm/models.py	823	CODE
LOW	llm/models.py	877	CODE
LOW	llm/models.py	956	CODE
LOW	llm/models.py	1010	CODE
LOW	llm/models.py	3263	CODE
LOW	llm/models.py	3310	CODE
LOW	llm/models.py	3389	CODE
LOW	llm/models.py	3435	CODE
LOW	llm/logs.py	1307	CODE
LOW	llm/logs.py	1650	CODE
LOW	llm/default_plugins/openai_models.py	1148	CODE
LOW	llm/default_plugins/openai_models.py	1651	CODE
LOW	llm/default_plugins/openai_models.py	2422	CODE
LOW	llm/default_plugins/openai_models.py	2668	CODE

Magic Placeholder Names2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	README.md	84	Add `--key your-api-key` if the endpoint requires authentication. See [Run against an endpoint without configuring it](h	CODE
HIGH	docs/index.md	52	Add `--key your-api-key` if the endpoint requires authentication. See {ref}`Run against an endpoint without configuring	CODE

Self-Referential Comments4 hits · 10 pts

Severity	File	Line	Snippet	Context
MEDIUM	llm/cli.py	3977	# Create a test Options object to validate	STRING
MEDIUM	tests/test_templates.py	160	# Create a file to test attachment	COMMENT
MEDIUM	tests/test_chat_templates.py	38	# Create a system fragment file	COMMENT
MEDIUM	docs/conf.py	3	# This file is execfile()d with the current directory set to its	COMMENT

Redundant / Tautological Comments4 hits · 6 pts

Severity	File	Line	Snippet	Context
LOW	llm/cli.py	3636	# Read the file twice - first time is to get a count	COMMENT
LOW	llm/utils.py	376	# Check if the schema is newline-separated or comma-separated	COMMENT
LOW	tests/test_utils.py	434	# Check if the correct number of backticks is used	COMMENT
LOW	.github/workflows/stable-docs.yml	52	# Check if the list of files is non-empty	COMMENT

Modern Structural Boilerplate4 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	llm/__init__.py	53	__all__ = [	CODE
LOW	llm/cli.py	4130	def set_model_option(model_id: str, key: str, value: Any) -> None:	STRING
LOW	llm/logs.py	45	__all__ = [	CODE
LOW	llm/serialization.py	41	__all__ = [	CODE

Over-Commented Block3 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	llm/migrations.py	721	# only while sorted by path.	COMMENT
LOW	docs/conf.py	1	from subprocess import PIPE, Popen	COMMENT
LOW	docs/conf.py	121	# The paper size ('letterpaper' or 'a4paper').	COMMENT

Overly Generic Function Names1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	llm/utils.py	107	def handle_request(self, request: httpx2.Request) -> httpx2.Response:	CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings