567-labs/instructor

25.8

Adjusted Score

25.8

Raw Score

100%

Time Factor

2026-07-29

Last Push

13.7K

Stars

Python

Language

133.3K

Lines of Code

834

Files

2.2K

Pattern Hits

2026-08-02

Scan Date

0.21

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 19HIGH 156MEDIUM 183LOW 1871

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 2229 distinct pattern matches across 25 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 Identifiers992 hits · 986 pts

Severity	File	Line	Snippet	Context
LOW	github_issue.md	42	def generate_anthropic_schema(model: Type[BaseModel]) -> dict[str, Any]:	CODE
LOW	tests/test_lazy_imports.py	34	def test_top_level_exports_load_lazily():	STRING
LOW	tests/test_lazy_imports.py	58	def test_mode_export_stays_lightweight():	STRING
LOW⚡	tests/test_utils.py	200	def test_combine_system_messages_string_string():	CODE
LOW⚡	tests/test_utils.py	207	def test_combine_system_messages_list_list():	CODE
LOW⚡	tests/test_utils.py	217	def test_combine_system_messages_string_list():	CODE
LOW⚡	tests/test_utils.py	227	def test_combine_system_messages_list_string():	CODE
LOW⚡	tests/test_utils.py	237	def test_update_total_usage_preserves_openai_usage_subclass():	CODE
LOW⚡	tests/test_utils.py	267	def test_combine_system_messages_none_string():	CODE
LOW⚡	tests/test_utils.py	274	def test_combine_system_messages_none_list():	CODE
LOW⚡	tests/test_utils.py	281	def test_combine_system_messages_invalid_type():	CODE
LOW⚡	tests/test_utils.py	286	def test_extract_system_messages():	CODE
LOW	tests/test_utils.py	22	def test_extract_json_from_codeblock():	CODE
LOW	tests/test_utils.py	300	def test_extract_system_messages_no_system():	CODE
LOW	tests/test_utils.py	309	def test_combine_system_messages_with_cache_control():	CODE
LOW	tests/test_utils.py	338	def test_combine_system_messages_string_to_cache_control():	CODE
LOW	tests/test_utils.py	361	def test_extract_system_messages_with_cache_control():	CODE
LOW	tests/test_utils.py	390	def test_combine_system_messages_preserve_cache_control():	CODE
LOW	tests/test_utils.py	429	def test_provider_enum_covers_supported_providers():	CODE
LOW	tests/test_utils.py	437	def test_get_provider_matches_supported_providers():	CODE
LOW	tests/test_utils.py	36	def test_extract_json_from_codeblock_no_end():	STRING
LOW	tests/test_utils.py	53	def test_extract_json_from_codeblock_no_start():	STRING
LOW	tests/test_utils.py	142	def test_merge_consecutive_messages():	STRING
LOW	tests/test_utils.py	162	def test_merge_consecutive_messages_empty():	STRING
LOW	tests/test_utils.py	168	def test_merge_consecutive_messages_single():	STRING
LOW	tests/test_genai_reask.py	16	def test_reask_genai_tools_preserves_thought_signature():	CODE
LOW	tests/test_genai_reask.py	39	def test_reask_genai_tools_finds_function_call_part_when_not_first():	CODE
LOW	tests/test_genai_reask.py	61	def test_reask_genai_tools_handles_none_response():	CODE
LOW	tests/test_genai_reask.py	71	def test_reask_genai_tools_falls_back_when_no_function_call():	CODE
LOW	tests/test_xai_optional_dependency.py	5	def test_from_provider_xai_requires_optional_extra(monkeypatch):	CODE
LOW	tests/test_xai_optional_dependency.py	25	def test_direct_from_xai_has_clear_error_when_sdk_missing(monkeypatch):	CODE
LOW	tests/test_batch_in_memory.py	24	def test_save_to_bytesio_openai(self):	CODE
LOW	tests/test_batch_in_memory.py	52	def test_save_to_bytesio_anthropic(self):	CODE
LOW	tests/test_batch_in_memory.py	78	def test_save_to_file_still_works(self):	CODE
LOW	tests/test_batch_in_memory.py	111	def test_multiple_requests_in_buffer(self):	CODE
LOW	tests/test_batch_in_memory.py	137	def test_invalid_buffer_type_raises_error(self):	CODE
LOW	tests/test_batch_in_memory.py	158	def test_openai_provider_accepts_bytesio(self):	CODE
LOW⚡	tests/test_batch_in_memory.py	187	def test_anthropic_provider_accepts_bytesio(self):	CODE
LOW	tests/test_batch_in_memory.py	214	def test_provider_invalid_type_raises_error(self):	CODE
LOW	tests/test_openai_responses_tools.py	28	def test_responses_tools_preserves_function_description() -> None:	CODE
LOW	tests/test_openai_responses_tools.py	38	def test_responses_tools_sets_text_format() -> None:	CODE
LOW	tests/test_openai_responses_tools.py	49	def test_responses_tools_overrides_conflicting_text_format() -> None:	CODE
LOW	tests/test_openai_responses_tools.py	72	def test_responses_tools_preserves_matching_text_format() -> None:	CODE
LOW	tests/test_openai_responses_tools.py	90	def test_responses_tools_none_model_no_text() -> None:	CODE
LOW	tests/test_openai_responses_tools.py	108	def test_reask_responses_tools_empty_args_message() -> None:	CODE
LOW	tests/test_openai_responses_tools.py	122	def test_reask_responses_tools_nonempty_args_message() -> None:	CODE
LOW⚡	tests/test_openai_responses_tools.py	135	def test_reask_responses_tools_none_arguments() -> None:	CODE
LOW⚡	tests/test_openai_responses_tools.py	144	def test_responses_tools_overrides_text_type_format() -> None:	CODE
LOW⚡	tests/test_openai_responses_tools.py	154	def test_parse_response_warns_on_empty_args(caplog) -> None:	CODE
LOW	tests/test_incomplete_output_exception.py	38	def test_incomplete_output_exception_is_catchable_sync():	CODE
LOW	tests/test_incomplete_output_exception.py	56	def test_incomplete_output_not_wrapped_in_instructor_retry_exception_sync():	CODE
LOW	tests/test_incomplete_output_exception.py	74	def test_incomplete_output_exception_with_max_retries_zero():	CODE
LOW	tests/test_incomplete_output_exception.py	78	def _raise_incomplete_and_count(_args, *_kwargs):	CODE
LOW	tests/test_incomplete_output_exception.py	102	async def test_incomplete_output_exception_is_catchable_async():	CODE
LOW	tests/test_update_total_usage.py	31	def test_update_total_usage_preserves_openai_usage_subclass() -> None:	CODE
LOW⚡	tests/test_genai_config_merging.py	24	def test_update_genai_kwargs_thinking_config_from_config_object():	CODE
LOW⚡	tests/test_genai_config_merging.py	402	def test_update_genai_kwargs_config_dict_labels():	CODE
LOW⚡	tests/test_genai_config_merging.py	412	def test_update_genai_kwargs_config_dict_cached_content():	CODE
LOW⚡	tests/test_genai_config_merging.py	422	def test_update_genai_kwargs_config_dict_thinking_config():	CODE
LOW	tests/test_genai_config_merging.py	57	def test_update_genai_kwargs_thinking_config_kwarg_priority():	CODE
932 more matches not shown…

Cross-File Repetition79 hits · 395 pts

Severity	File	Line	Snippet	Context
HIGH	tests/llm/test_new_client.py	0	\ given the following text, create a group object for 'the beatles' band text: the beatles were an english rock band for	STRING
HIGH	docs/integrations/cohere.md	0	\ given the following text, create a group object for 'the beatles' band text: the beatles were an english rock band for	STRING
HIGH	examples/cohere/cohere.py	0	\ given the following text, create a group object for 'the beatles' band text: the beatles were an english rock band for	STRING
HIGH	tests/llm/test_writer/evals/test_entities.py	0	sample legal contract agreement contract this agreement is made and entered into on 2020-01-01 by and between company a	STRING
HIGH	docs/examples/entity_resolution.md	0	sample legal contract agreement contract this agreement is made and entered into on 2020-01-01 by and between company a	STRING
HIGH	examples/resolving-complex-entities/run.py	0	sample legal contract agreement contract this agreement is made and entered into on 2020-01-01 by and between company a	STRING
HIGH	tests/v2/test_xai_handlers.py	0	test prepare_request returns unchanged kwargs when response_model is none.	STRING
HIGH	tests/v2/test_mistral_handlers.py	0	test prepare_request returns unchanged kwargs when response_model is none.	STRING
HIGH	tests/v2/test_cohere_handlers.py	0	test prepare_request returns unchanged kwargs when response_model is none.	STRING
HIGH	tests/v2/test_xai_handlers.py	0	test prepare_request doesn't modify original kwargs.	STRING
HIGH	tests/v2/test_mistral_handlers.py	0	test prepare_request doesn't modify original kwargs.	STRING
HIGH	tests/v2/test_cohere_handlers.py	0	test prepare_request doesn't modify original kwargs.	STRING
HIGH	docs/blog/posts/writer-support.md	0	in our recent online meeting, participants from various backgrounds joined to discuss the upcoming tech conference. the	STRING
HIGH	docs/examples/partial_streaming.md	0	in our recent online meeting, participants from various backgrounds joined to discuss the upcoming tech conference. the	STRING
HIGH	docs/concepts/partial.md	0	in our recent online meeting, participants from various backgrounds joined to discuss the upcoming tech conference. the	STRING
HIGH	docs/blog/posts/introducing-structured-outputs.md	0	in our recent online meeting, participants from various backgrounds joined to discuss the upcoming tech conference. the	STRING
HIGH	docs/blog/posts/matching-language.md	0	լեզվական մոդելները վերջին տարիներին դարձել են ավելի հարուստ և կատարյալ, հնարավորություն ընձեռելով ստեղծել սահուն և բնակա	STRING
HIGH	examples/match_language/run_v2.py	0	լեզվական մոդելները վերջին տարիներին դարձել են ավելի հարուստ և կատարյալ, հնարավորություն ընձեռելով ստեղծել սահուն և բնակա	STRING
HIGH	examples/match_language/run_v1.py	0	լեզվական մոդելները վերջին տարիներին դարձել են ավելի հարուստ և կատարյալ, հնարավորություն ընձեռելով ստեղծել սահուն և բնակա	STRING
HIGH	docs/blog/posts/logfire.md	0	perform single-label classification on the input text.	STRING
HIGH	docs/examples/single_classification.md	0	perform single-label classification on the input text.	STRING
HIGH	docs/examples/classification.md	0	perform single-label classification on the input text.	STRING
HIGH	examples/logfire/classify.py	0	perform single-label classification on the input text.	STRING
HIGH	docs/blog/posts/langsmith.md	0	predict the type of question that is being asked. here are some tips on how to predict the question type: contact: searc	STRING
HIGH	docs/examples/batch_classification_langsmith.md	0	predict the type of question that is being asked. here are some tips on how to predict the question type: contact: searc	STRING
HIGH	examples/batch-classification/run-cache.py	0	predict the type of question that is being asked. here are some tips on how to predict the question type: contact: searc	STRING
HIGH	examples/batch-classification/run.py	0	predict the type of question that is being asked. here are some tips on how to predict the question type: contact: searc	STRING
HIGH	examples/batch-classification/run_langsmith.py	0	predict the type of question that is being asked. here are some tips on how to predict the question type: contact: searc	STRING
HIGH	docs/integrations/deepseek.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/fireworks.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/writer.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/xai.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/groq.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/openai.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/bedrock.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/mistral.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/cortex.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/cerebras.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/google.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/perplexity.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/openrouter.md	0	extract: jason is 25 years old. he lives at 123 main st, new york, usa and has a summer house at 456 beach rd, miami, us	STRING
HIGH	docs/integrations/deepseek.md	0	extract users: 1. jason is 25 years old 2. sarah is 30 years old 3. mike is 28 years old	STRING
HIGH	docs/integrations/fireworks.md	0	extract users: 1. jason is 25 years old 2. sarah is 30 years old 3. mike is 28 years old	STRING
HIGH	docs/integrations/anthropic.md	0	extract users: 1. jason is 25 years old 2. sarah is 30 years old 3. mike is 28 years old	STRING
HIGH	docs/integrations/openai.md	0	extract users: 1. jason is 25 years old 2. sarah is 30 years old 3. mike is 28 years old	STRING
HIGH	docs/integrations/google.md	0	extract users: 1. jason is 25 years old 2. sarah is 30 years old 3. mike is 28 years old	STRING
HIGH	docs/integrations/azure.md	0	extract users: 1. jason is 25 years old 2. sarah is 30 years old 3. mike is 28 years old	STRING
HIGH	docs/integrations/ollama.md	0	{ "name": "harry james potter", "age": 37, "fact": [ "he is the chosen one.", "he has a lightning-shaped scar on his for	STRING
HIGH	docs/examples/ollama.md	0	{ "name": "harry james potter", "age": 37, "fact": [ "he is the chosen one.", "he has a lightning-shaped scar on his for	STRING
HIGH	examples/proscons/run.py	0	{ "name": "harry james potter", "age": 37, "fact": [ "he is the chosen one.", "he has a lightning-shaped scar on his for	STRING
HIGH	docs/examples/pandas_df.md	0	the markdown representation of the table, each one should be tidy, do not try to join tables that should be separate	STRING
HIGH	docs/examples/tables_from_vision.md	0	the markdown representation of the table, each one should be tidy, do not try to join tables that should be separate	STRING
HIGH	docs/concepts/types.md	0	the markdown representation of the table, each one should be tidy, do not try to join tables that should be separate	STRING
HIGH	examples/extract-table/run_vision_org_table.py	0	the markdown representation of the table, each one should be tidy, do not try to join tables that should be separate	STRING
HIGH	examples/extract-table/run_vision_langsmith.py	0	the markdown representation of the table, each one should be tidy, do not try to join tables that should be separate	STRING
HIGH	examples/extract-table/run_vision.py	0	the markdown representation of the table, each one should be tidy, do not try to join tables that should be separate	STRING
HIGH	examples/vision/run_table.py	0	the markdown representation of the table, each one should be tidy, do not try to join tables that should be separate	STRING
HIGH	instructor/v2/providers/gemini/utils.py	0	as a genius expert, your task is to understand the content and provide the parsed objects in json that match the followi	STRING
HIGH	instructor/v2/providers/writer/handlers.py	0	as a genius expert, your task is to understand the content and provide the parsed objects in json that match the followi	STRING
HIGH	instructor/v2/providers/mistral/handlers.py	0	as a genius expert, your task is to understand the content and provide the parsed objects in json that match the followi	STRING
19 more matches not shown…

Unused Imports385 hits · 362 pts

Severity	File	Line	Context
LOW	tests/test_streaming_reasoning_events.py	10	CODE
LOW	tests/test_import_lazy_openai.py	3	CODE
LOW	tests/test_batch_processor_coverage.py	3	CODE
LOW	tests/llm/test_vertexai/conftest.py	11	CODE
LOW	tests/llm/test_gemini/conftest.py	14	CODE
LOW	tests/llm/test_core_providers/conftest.py	5	CODE
LOW	tests/llm/test_core_providers/conftest.py	5	CODE
LOW	tests/llm/test_bedrock/test_openai_image_conversion.py	1	CODE
LOW	tests/llm/test_bedrock/conftest.py	1	CODE
LOW	…ts/llm/test_bedrock/test_bedrock_native_passthrough.py	1	CODE
LOW	tests/llm/test_bedrock/test_prepare_kwargs.py	1	CODE
LOW	tests/llm/test_bedrock/test_normalize.py	1	CODE
LOW	tests/llm/test_writer/conftest.py	8	CODE
LOW	tests/processing/test_list_response_wrapper.py	1	CODE
LOW	tests/providers/test_auto_client.py	1	CODE
LOW	tests/docs/conftest.py	1	CODE
LOW	tests/docs/_example_groups.py	1	CODE
LOW	tests/docs/_concept_groups.py	1	CODE
LOW	tests/typing/test_public_surface.py	1	CODE
LOW	tests/typing/test_installed_package.py	1	CODE
LOW	tests/v2/test_issue_2374.py	1	CODE
LOW	tests/v2/test_xai_client.py	7	CODE
LOW	tests/v2/test_auto_client_deterministic.py	1	CODE
LOW	tests/v2/test_gemini_utils_deterministic.py	1	CODE
LOW	tests/v2/test_handler_registration_unified.py	7	CODE
LOW	tests/v2/test_anthropic_handlers.py	7	CODE
LOW	tests/v2/test_genai_integration.py	1	CODE
LOW	tests/v2/test_openai_streaming.py	1	CODE
LOW	tests/v2/test_xai_handlers.py	6	CODE
LOW	tests/v2/test_handlers_parametrized.py	7	CODE
LOW	tests/v2/_fake_genai.py	3	CODE
LOW	tests/v2/test_citation.py	8	CODE
LOW	tests/v2/test_vertexai_runtime.py	1	CODE
LOW	tests/v2/test_mode_normalization.py	1	CODE
LOW	tests/v2/test_genai_multimodal_runtime.py	1	CODE
LOW	tests/v2/test_client_unified.py	7	CODE
LOW	tests/v2/test_legacy_provider_compat.py	1	CODE
LOW	tests/v2/test_genai_handlers_deterministic.py	1	CODE
LOW	tests/v2/test_core_multimodal_runtime.py	1	CODE
LOW	tests/v2/test_core_provider_dispatch.py	3	CODE
LOW	tests/v2/test_openai_compat_handlers.py	3	CODE
LOW	tests/v2/test_provider_modes.py	7	CODE
LOW	tests/v2/test_optional_dependency_imports.py	1	CODE
LOW	tests/v2/provider_matrix.py	3	CODE
LOW	tests/v2/test_response_schema_compat.py	3	CODE
LOW	tests/v2/test_gemini_json_messages.py	1	CODE
LOW	tests/v2/test_writer_client.py	3	CODE
LOW	tests/v2/test_messages_not_mutated.py	29	CODE
LOW	tests/v2/test_bedrock_client.py	3	CODE
LOW	tests/v2/test_bedrock_handlers.py	3	CODE
LOW	tests/v2/test_writer_handlers.py	3	CODE
LOW	tests/v2/test_json_helpers.py	1	CODE
LOW	tests/v2/test_iterable_streaming.py	1	CODE
LOW	tests/v2/test_provider_specs.py	3	CODE
LOW	tests/v2/test_mistral_handlers.py	7	CODE
LOW	tests/v2/test_retry_runtime.py	1	CODE
LOW	tests/v2/test_cohere_handlers.py	7	CODE
LOW	examples/parallel/run.py	1	CODE
LOW	examples/codegen-from-schema/models.py	5	CODE
LOW	examples/fizzbuzz/run.py	1	CODE
325 more matches not shown…

Decorative Section Separators88 hits · 321 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_streaming_reasoning_events.py	21	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_streaming_reasoning_events.py	23	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_streaming_reasoning_events.py	53	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_streaming_reasoning_events.py	56	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_streaming_reasoning_events.py	81	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_streaming_reasoning_events.py	83	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_streaming_reasoning_events.py	160	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_streaming_reasoning_events.py	162	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/v2/test_xai_client.py	21	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_xai_client.py	23	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_xai_client.py	187	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_xai_client.py	189	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_xai_client.py	195	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_xai_client.py	197	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_handler_registration_unified.py	39	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_handler_registration_unified.py	41	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_handler_registration_unified.py	95	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_handler_registration_unified.py	97	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_handler_registration_unified.py	170	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_handler_registration_unified.py	172	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_xai_handlers.py	366	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_xai_handlers.py	368	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_xai_handlers.py	373	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_xai_handlers.py	375	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_xai_handlers.py	51	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_xai_handlers.py	53	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_xai_handlers.py	179	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_xai_handlers.py	181	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_xai_handlers.py	263	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_xai_handlers.py	265	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	150	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	152	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	203	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	205	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	229	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	231	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	266	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	268	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	304	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_client_unified.py	306	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_client_unified.py	348	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_client_unified.py	350	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_mistral_handlers.py	340	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_mistral_handlers.py	342	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_mistral_handlers.py	439	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_mistral_handlers.py	441	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_mistral_handlers.py	446	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_mistral_handlers.py	448	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_mistral_handlers.py	487	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_mistral_handlers.py	489	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_mistral_handlers.py	101	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_mistral_handlers.py	103	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_mistral_handlers.py	278	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_mistral_handlers.py	280	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_mistral_handlers.py	563	# ============================================================================	COMMENT
MEDIUM	tests/v2/test_mistral_handlers.py	565	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_cohere_handlers.py	451	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_cohere_handlers.py	453	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_cohere_handlers.py	458	# ============================================================================	COMMENT
MEDIUM⚡	tests/v2/test_cohere_handlers.py	460	# ============================================================================	COMMENT
28 more matches not shown…

Hallucination Indicators19 hits · 225 pts

Severity	File	Line	Snippet	Context
CRITICAL	tests/test_xai_optional_dependency.py	8	from instructor.core.exceptions import ConfigurationError	CODE
CRITICAL	tests/llm/test_vertexai/test_deprecated_async.py	5	from instructor.core.exceptions import ConfigurationError	CODE
CRITICAL⚡	tests/providers/test_auto_client.py	230	from instructor.core.exceptions import ConfigurationError	CODE
CRITICAL⚡	tests/providers/test_auto_client.py	239	from instructor.core.exceptions import ConfigurationError	CODE
CRITICAL	tests/providers/test_auto_client.py	453	from instructor.core.exceptions import ConfigurationError	CODE
CRITICAL	tests/providers/test_auto_client.py	474	from instructor.core.exceptions import ConfigurationError	CODE
CRITICAL⚡	tests/v2/test_xai_client.py	210	from instructor.core.exceptions import ClientError	CODE
CRITICAL	tests/v2/test_client_unified.py	332	from instructor.core.exceptions import ClientError	CODE
CRITICAL⚡	tests/v2/test_bedrock_client.py	31	from instructor.core.exceptions import ClientError	CODE
CRITICAL⚡	tests/v2/test_bedrock_client.py	44	from instructor.core.exceptions import ClientError	CODE
CRITICAL⚡	tests/v2/test_bedrock_client.py	58	from instructor.core.exceptions import ModeError	CODE
CRITICAL⚡	tests/v2/test_cohere_handlers.py	644	from instructor.core.exceptions import ResponseParsingError	CODE
CRITICAL	docs/concepts/error_handling.md	92	from instructor.core.exceptions import ValidationError	CODE
CRITICAL	docs/concepts/error_handling.md	123	from instructor.core.exceptions import ConfigurationError, ModeError	CODE
CRITICAL	docs/concepts/error_handling.md	190	from instructor.core.exceptions import InstructorError	CODE
CRITICAL	docs/concepts/error_handling.md	214	from instructor.core.exceptions import ValidationError, InstructorRetryException	CODE
CRITICAL	docs/concepts/error_handling.md	258	from instructor.core.exceptions import ResponseParsingError	CODE
CRITICAL	docs/concepts/error_handling.md	293	from instructor.core.exceptions import ValidationError	CODE
CRITICAL	docs/concepts/from_provider.md	221	from instructor.core.exceptions import ConfigurationError	CODE

Excessive Try-Catch Wrapping194 hits · 224 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_batch_in_memory.py	183	except Exception as exc_info:	CODE
LOW	tests/test_batch_in_memory.py	210	except Exception as exc_info:	CODE
LOW⚡	tests/test_openai_responses_tools.py	163	except Exception:	CODE
LOW	tests/llm/test_vertexai/conftest.py	38	except Exception:	CODE
LOW	tests/llm/test_anthropic/test_reasoning.py	29	except Exception as e:	CODE
LOW	tests/processing/test_function_calls.py	295	except Exception as e:	CODE
LOW⚡	tests/providers/test_auto_client.py	184	except Exception as e:	CODE
LOW⚡	tests/providers/test_auto_client.py	195	except Exception as e:	CODE
LOW⚡	tests/providers/test_auto_client.py	211	except Exception as e:	CODE
LOW⚡	tests/providers/test_auto_client.py	222	except Exception as e:	CODE
LOW	tests/v2/test_issue_2374.py	49	except Exception:	CODE
LOW	tests/v2/test_issue_2374.py	67	except Exception:	CODE
MEDIUM	docs/index.md	316	client.on("completion:error", lambda e: print(f"Error: {e}"))	CODE
LOW	docs/debugging.md	127	except Exception as err:	CODE
LOW	docs/learning/validation/retry_mechanisms.md	190	except Exception as e:	CODE
LOW	docs/blog/posts/caching.md	845	except Exception as e:	CODE
LOW	docs/blog/posts/caching.md	854	except Exception as e:	CODE
MEDIUM	docs/blog/posts/caching.md	840	def wrapper(args, *kwargs):	CODE
LOW	docs/blog/posts/youtube-transcripts.md	82	except Exception as e:	CODE
MEDIUM	docs/blog/posts/youtube-transcripts.md	83	print(f"Error fetching transcript: {e}")	CODE
LOW	docs/blog/posts/youtube-transcripts.md	120	except Exception as e:	CODE
MEDIUM	docs/blog/posts/youtube-transcripts.md	121	print(f"Error fetching transcript: {e}")	CODE
LOW	…s/blog/posts/semantic-validation-structured-outputs.md	242	except Exception as e:	STRING
LOW	docs/blog/posts/introducing-structured-outputs.md	76	except Exception as e:	CODE
MEDIUM	docs/blog/posts/string-based-init.md	137	print("Error: Install the anthropic package first")	CODE
LOW	docs/integrations/xai.md	206	except Exception as e:	STRING
MEDIUM	docs/integrations/xai.md	207	print(f"Error: {e}")	STRING
LOW	docs/integrations/anthropic.md	97	except Exception as e:	CODE
LOW	docs/integrations/anthropic.md	387	except Exception as e:	CODE
MEDIUM	docs/integrations/anthropic.md	388	print(f"Error during streaming: {e}")	CODE
LOW	docs/integrations/anthropic.md	448	except Exception as e:	STRING
MEDIUM	docs/integrations/anthropic.md	449	print(f"Error during iteration: {e}")	STRING
LOW	docs/integrations/anthropic.md	549	except Exception as e:	CODE
MEDIUM	docs/integrations/anthropic.md	550	print(f"Error: {e}")	CODE
LOW	docs/integrations/anthropic.md	623	except Exception as e:	CODE
MEDIUM	docs/integrations/anthropic.md	624	print(f"Error during image analysis: {e}")	CODE
LOW	docs/examples/batch_in_memory.md	269	except Exception as e:	CODE
MEDIUM	docs/examples/batch_in_memory.md	270	print(f"Error during batch processing: {e}")	CODE
LOW	docs/examples/self_critique.md	95	except Exception as e:	CODE
LOW	docs/examples/extract_contact_info.md	91	except Exception as e:	CODE
LOW	docs/examples/sqlmodel.md	470	except Exception as e:	CODE
LOW	docs/examples/sqlmodel.md	556	except Exception as e:	CODE
LOW	docs/examples/moderation.md	39	except Exception as e:	CODE
LOW	docs/examples/moderation.md	50	except Exception as e:	CODE
MEDIUM	docs/concepts/unions.md	240	print(f"Error: {result.message}")	CODE
MEDIUM	docs/concepts/unions.md	327	print(f"Error: {response.message}")	CODE
MEDIUM	docs/concepts/error_handling.md	275	print(f"Error: {e}")	CODE
LOW	docs/concepts/semantic_validation.md	153	except Exception as e:	CODE
LOW	docs/concepts/retrying.md	41	except Exception as e:	CODE
MEDIUM	docs/concepts/hooks.md	101	print(f"Error #{self.count}: {type(error).__name__}: {error}")	CODE
LOW	docs/concepts/hooks.md	122	except Exception as e:	CODE
MEDIUM	docs/concepts/batch.md	182	print(f"Error: {result.error_message}")	CODE
LOW	docs/templates/provider_template.md	74	except Exception as e:	CODE
MEDIUM	docs/templates/provider_template.md	75	print(f"Error: {e}")	CODE
LOW	docs/templates/provider_template.md	130	except Exception as e:	CODE
MEDIUM	docs/templates/provider_template.md	131	print(f"Error during extraction: {e}")	CODE
LOW	examples/classification/classifiy_with_validation.py	169	except Exception as e:	CODE
MEDIUM	examples/open_source_examples/openrouter.py	60	print(f"Error: {user.error}")	CODE
MEDIUM	examples/open_source_examples/perplexity.py	73	print(f"Error: {user.error}")	CODE
LOW	examples/open_source_examples/runpod.py	60	except Exception as e:	CODE
134 more matches not shown…

Magic Placeholder Names35 hits · 182 pts

Severity	File	Line	Snippet	Context
HIGH	docs/cli/index.md	51	export OPENAI_API_KEY="your-api-key-here"	CODE
HIGH	docs/blog/posts/google-openai-client.md	37	base_url="https://generativelanguage.googleapis.com/v1beta/", api_key="YOUR_API_KEY"	CODE
HIGH	…roducing-structured-outputs-with-cerebras-inference.md	59	export CEREBRAS_API_KEY=<your-api-key>	CODE
HIGH	docs/blog/posts/open_source.md	144	export GROQ_API_KEY="your-api-key"	CODE
HIGH	docs/blog/posts/open_source.md	190	export TOGETHER_API_KEY="your-api-key"	CODE
HIGH	docs/blog/posts/langsmith.md	30	export LANGCHAIN_API_KEY=<your-api-key>	CODE
HIGH	docs/integrations/deepseek.md	25	export DEEPSEEK_API_KEY='your-api-key-here'	CODE
HIGH	docs/integrations/writer.md	13	export WRITER_API_KEY=<your-api-key-here>	CODE
HIGH	docs/integrations/xai.md	29	export XAI_API_KEY='your-api-key-here'	CODE
HIGH	docs/integrations/xai.md	181	export XAI_API_KEY="your-api-key-here"	STRING
HIGH	docs/integrations/anthropic.md	40	# os.environ["ANTHROPIC_API_KEY"] = "your-api-key" # Uncomment and replace with your API key if not set	COMMENT
HIGH	docs/integrations/anthropic.md	356	# os.environ["ANTHROPIC_API_KEY"] = "your-api-key" # Uncomment and replace with your API key if not set	COMMENT
HIGH	docs/integrations/anthropic.md	405	# os.environ["ANTHROPIC_API_KEY"] = "your-api-key" # Uncomment and replace with your API key if not set	COMMENT
HIGH	docs/integrations/anthropic.md	493	# os.environ["ANTHROPIC_API_KEY"] = "your-api-key" # Uncomment and replace with your API key if not set	STRING
HIGH	docs/integrations/anthropic.md	567	# os.environ["ANTHROPIC_API_KEY"] = "your-api-key" # Uncomment and replace with your API key if not set	COMMENT
HIGH	docs/integrations/groq.md	13	export GROQ_API_KEY=<your-api-key-here>	CODE
HIGH	docs/integrations/openai.md	23	export OPENAI_API_KEY='your-api-key-here'	CODE
HIGH	docs/integrations/openai.md	33	api_key='your-api-key-here',	CODE
HIGH	docs/integrations/mistral.md	33	client = Mistral(api_key='your-api-key-here')	CODE
HIGH	docs/integrations/perplexity.md	15	export PERPLEXITY_API_KEY=<your-api-key-here>	CODE
HIGH	docs/integrations/azure.md	63	os.environ["AZURE_OPENAI_API_KEY"] = "your-api-key"	CODE
HIGH	docs/integrations/azure.md	80	api_key="your-api-key",	CODE
HIGH	docs/examples/groq.md	22	export GROQ_API_KEY=<your-api-key>	CODE
HIGH	docs/examples/mistral.md	23	export MISTRAL_API_KEY=<your-api-key>	CODE
HIGH	docs/examples/batch_classification_langsmith.md	21	export LANGCHAIN_API_KEY=<your-api-key>	CODE
HIGH	docs/templates/provider_template.md	40	# os.environ["PROVIDER_API_KEY"] = "your-api-key" # Uncomment and replace with your API key if not set	COMMENT
HIGH	docs/templates/provider_template.md	94	# os.environ["PROVIDER_API_KEY"] = "your-api-key" # Uncomment and replace with your API key if not set	COMMENT
HIGH	examples/batch_api/run_batch_test.py	102	f"Please set your API key: export {required_key}='your-api-key-here'",	CODE
HIGH	examples/openai/run.py	8	export OPENAI_API_KEY=your-api-key	STRING
HIGH	instructor/v2/auto_client.py	303	"Set it with `export AZURE_OPENAI_API_KEY=<your-api-key>` or pass it as kwarg api_key=<your-api-key>"	CODE
HIGH	instructor/v2/auto_client.py	380	f"Set it with `export {env_var}=<your-api-key>` or pass it as kwarg api_key=<your-api-key>"	CODE
HIGH	instructor/v2/auto_client.py	750	"Set it with `export MISTRAL_API_KEY=<your-api-key>`."	CODE
HIGH	instructor/v2/auto_client.py	850	"Set it with `export PERPLEXITY_API_KEY=<your-api-key>` or pass it as a kwarg api_key=<your-api-key>"	CODE
HIGH	instructor/v2/auto_client.py	1376	"Set it with `export DEEPSEEK_API_KEY=<your-api-key>` or pass it as kwarg api_key=<your-api-key>"	CODE
HIGH	instructor/v2/auto_client.py	1499	"Set it with `export OPENROUTER_API_KEY=<your-api-key>` or pass it as kwarg api_key=<your-api-key>"	CODE

Docstring Block Structure31 hits · 155 pts

Severity	File	Line	Snippet	Context
HIGH	scripts/make_sitemap.py	110	Analyze the content of a file to extract summary, keywords, topics, and references. Args: client (Asyn	STRING
HIGH	instructor/v2/auto_client.py	67	Create an Instructor client from a model string. Args: model: String in format "provider/model-name"	STRING
HIGH	instructor/v2/core/patch.py	85	Patch a function to use v2 registry for structured outputs. Args: func: Function to patch (e.g., client.mes	STRING
HIGH	instructor/v2/core/hooks.py	117	Convert a string hook name to its corresponding enum value. Args: hook_name: Either a Hook	STRING
HIGH	instructor/v2/core/handler.py	76	Parse API response into validated Pydantic model. Args: response: Raw API response resp	STRING
HIGH	instructor/v2/core/templating.py	94	Handle templating for messages using the provided context. This function processes messages, applying Jinja2 t	STRING
HIGH	instructor/v2/core/protocols.py	83	Parse and validate response into model. Args: response: Raw API response response_model	STRING
HIGH	instructor/v2/core/registry.py	160	Get all handlers for a mode. This is the preferred method for retrieving handlers. It performs a single	STRING
HIGH	instructor/v2/core/registry.py	227	Get a specific handler for a mode. This is a convenience method that internally calls get_handlers(). F	STRING
HIGH	instructor/v2/core/multimodal.py	448	Attempt to autodetect a PDF from a source string or Path. Args: source (Union[str,path]): The source	STRING
HIGH	instructor/v2/core/response.py	128	Asynchronously process and transform LLM responses into structured models. This function is the async entry point f	STRING
HIGH	instructor/v2/core/response.py	257	Process and transform LLM responses into structured models (synchronous). This is the main entry point for converti	STRING
HIGH	instructor/v2/core/response.py	463	Compatibility dispatcher for provider-specific reask formatting. The retry loop itself lives in :mod:`instructor.v2	STRING
HIGH	instructor/v2/core/retry.py	125	Sync retry logic using v2 registry handlers. Args: func: API function to call response_model: Pydan	STRING
HIGH	instructor/v2/core/retry.py	370	Async retry logic using v2 registry handlers. Args: func: Async API function to call response_model	STRING
HIGH	instructor/v2/core/exceptions.py	62	Validate and merge context parameters. Args: context: New-style context parameter valid	STRING
HIGH	instructor/v2/core/errors.py	189	Exception raised when all retry attempts have been exhausted. This exception is raised after the maximum number of	STRING
HIGH	instructor/v2/providers/cohere/client.py	67	Create an Instructor instance from a Cohere client using v2 registry. Args: client: A Cohere client instanc	STRING
HIGH	instructor/v2/providers/fireworks/client.py	54	Create an Instructor instance from a Fireworks client using v2 registry. Fireworks uses an OpenAI-compatible API, s	STRING
HIGH	instructor/v2/providers/groq/client.py	53	Create an Instructor instance from a Groq client using v2 registry. Groq uses an OpenAI-compatible API, so this fac	STRING
HIGH	instructor/v2/providers/xai/client.py	193	Create an Instructor instance from an xAI client using v2 registry. Args: client: An instance of xAI client	STRING
HIGH	instructor/v2/providers/bedrock/client.py	51	Create an Instructor instance from a Bedrock client using v2 registry. Bedrock uses the Converse API through a boto	STRING
HIGH	instructor/v2/providers/writer/client.py	53	Create an Instructor instance from a Writer client using v2 registry. Writer uses the writerai SDK and supports TOO	STRING
HIGH	instructor/v2/providers/anthropic/client.py	68	Create an Instructor instance from an Anthropic client using v2 registry. Args: client: An instance of Anth	STRING
HIGH	instructor/v2/providers/cerebras/client.py	54	Create an Instructor instance from a Cerebras client using v2 registry. Cerebras uses an OpenAI-compatible API, so	STRING
HIGH	instructor/v2/providers/mistral/client.py	70	Create an Instructor instance from a Mistral client using v2 registry. Mistral uses a single client class with both	STRING
HIGH	instructor/v2/providers/openai/client.py	125	Create an Instructor instance from an OpenAI client using v2 registry. Args: client: An instance of OpenAI	STRING
HIGH	instructor/v2/providers/openai/client.py	205	Create an Instructor instance for Anyscale. Supports two usage patterns: 1. String-based (recommended): Pass a	STRING
HIGH	instructor/v2/providers/openai/client.py	298	Create an Instructor instance for Together AI. Supports two usage patterns: 1. String-based (recommended): Pas	STRING
HIGH	instructor/v2/providers/openai/client.py	391	Create an Instructor instance for Databricks. Supports two usage patterns: 1. String-based (recommended): Pass	STRING
HIGH	instructor/v2/providers/openai/client.py	484	Create an Instructor instance for DeepSeek. Supports two usage patterns: 1. String-based (recommended): Pass a	STRING

Self-Referential Comments34 hits · 108 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_batch_in_memory.py	163	# Create a valid OpenAI batch request	COMMENT
MEDIUM⚡	tests/test_batch_in_memory.py	192	# Create a valid Anthropic batch request	COMMENT
MEDIUM⚡	tests/test_genai_config_merging.py	31	# Create a mock config object with thinking_config	COMMENT
MEDIUM⚡	tests/test_genai_config_merging.py	38	# Create a config object with thinking_config attribute	COMMENT
MEDIUM	tests/test_genai_config_merging.py	60	# Create a mock config object with thinking_config	COMMENT
MEDIUM	tests/test_genai_config_merging.py	299	# Create a config with cached_content	COMMENT
MEDIUM	tests/test_genai_config_merging.py	356	# Create a config with cached_content	COMMENT
MEDIUM	tests/llm/test_genai/test_utils.py	278	# Create a mock ThinkingConfig-like object	COMMENT
MEDIUM	tests/llm/test_genai/test_schema_conversion.py	160	# Create a schema with a true union (not just Optional)	COMMENT
MEDIUM	tests/llm/test_genai/test_schema_conversion.py	208	# Create a model with a true union type (not Optional or Decimal)	COMMENT
MEDIUM	tests/providers/test_auto_client.py	575	# Create a mock google module	COMMENT
MEDIUM	tests/providers/test_auto_client.py	653	# Create a mock google module with genai attribute	COMMENT
MEDIUM	tests/v2/test_handlers_parametrized.py	356	# Create a mock that works with dump_message	COMMENT
MEDIUM	tests/v2/test_client_unified.py	509	# Create a mock OpenAI client	COMMENT
MEDIUM⚡	tests/v2/test_cohere_handlers.py	646	# Create a response that has neither .text nor valid .message.content	COMMENT
MEDIUM	examples/extracting-pii/run.py	50	# Define the PII Scrubbing Model	STRING
MEDIUM	examples/learn-async/run.py	96	# Create a semaphore that will only allow 2 concurrent requests	COMMENT
MEDIUM	examples/tenacity-benchmarks/run.py	91	# Create a simple mock response for RateLimitError	COMMENT
MEDIUM	examples/tenacity-benchmarks/run.py	101	# Create a simple mock request for APIError	COMMENT
MEDIUM	examples/tenacity-benchmarks/run.py	461	# Create a simple mock response for RateLimitError	COMMENT
MEDIUM	examples/tenacity-benchmarks/run.py	471	# Create a simple mock request for APIError	COMMENT
MEDIUM	examples/hooks/run.py	53	# Create a statistics collector	COMMENT
MEDIUM	examples/sqlmodel/test_basic.py	75	# Create a team	COMMENT
MEDIUM	instructor/cli/batch.py	130	# Create a dummy model string for the provider	COMMENT
MEDIUM	instructor/cli/batch.py	140	# Create a dummy response model (not used for listing)	COMMENT
MEDIUM	instructor/cli/batch.py	258	# Create a dummy response model (not used for direct file submission)	COMMENT
MEDIUM	instructor/cli/batch.py	312	# Create a dummy response model (not used for cancellation)	COMMENT
MEDIUM	instructor/cli/batch.py	318	# Create a dummy model string for the provider	COMMENT
MEDIUM	instructor/cli/batch.py	359	# Create a dummy response model (not used for deletion)	COMMENT
MEDIUM	instructor/cli/batch.py	365	# Create a dummy model string for the provider	COMMENT
MEDIUM	instructor/cli/usage.py	52	# Define the cost per unit for each model	COMMENT
MEDIUM	instructor/v2/core/response.py	559	# Create a shallow copy of kwargs to avoid modifying the original	COMMENT
MEDIUM	instructor/v2/core/function_calls.py	600	# Create the wrapped model	COMMENT
MEDIUM⚡	instructor/v2/dsl/partial.py	2	# The following code is adapted from a comment on GitHub in the pydantic/pydantic repository by silviumarcu.	COMMENT

Deep Nesting102 hits · 98 pts

Severity	File	Line	Context
LOW	tests/providers/test_auto_client.py	451	CODE
LOW	tests/providers/test_auto_client.py	472	CODE
LOW	tests/providers/test_auto_client.py	596	CODE
LOW	tests/providers/test_auto_client.py	634	CODE
LOW	tests/v2/test_handlers_parametrized.py	499	CODE
LOW	tests/v2/test_handlers_parametrized.py	536	CODE
LOW	tests/multimodal/test_multimodal.py	349	CODE
LOW	examples/batch_api/in_memory_batch_example.py	20	CODE
LOW	examples/batch_api/run_batch_test.py	179	CODE
LOW	examples/batch_api/run_batch_test.py	284	CODE
LOW	examples/batch_api/run_batch_test.py	354	CODE
LOW	examples/batch_api/run_batch_test.py	469	CODE
LOW	examples/tenacity-benchmarks/run.py	433	CODE
LOW	examples/tenacity-benchmarks/run.py	81	CODE
LOW	examples/sqlmodel/test_basic.py	68	CODE
LOW	scripts/audit_patterns.py	62	CODE
LOW	scripts/audit_patterns.py	109	CODE
LOW	scripts/validate_meta_tags.py	53	CODE
LOW	scripts/validate_meta_tags.py	101	CODE
LOW	scripts/check_links.py	91	CODE
LOW	scripts/check_links.py	124	CODE
LOW	scripts/make_clean.py	48	CODE
LOW	scripts/make_sitemap.py	18	CODE
LOW	scripts/make_sitemap.py	43	CODE
LOW	scripts/make_sitemap.py	107	CODE
LOW	scripts/validate_headings.py	86	CODE
LOW	scripts/make_desc.py	75	CODE
LOW	instructor/cli/batch.py	18	CODE
LOW	instructor/cli/batch.py	397	CODE
LOW	instructor/cli/batch.py	449	CODE
LOW	instructor/cli/batch.py	511	CODE
LOW	instructor/cli/jobs.py	146	CODE
LOW	instructor/v2/auto_client.py	966	CODE
LOW	instructor/v2/core/hooks.py	136	CODE
LOW	instructor/v2/core/multimodal.py	712	CODE
LOW	instructor/v2/core/multimodal.py	801	CODE
LOW	instructor/v2/core/multimodal.py	167	CODE
LOW	instructor/v2/core/multimodal.py	623	CODE
LOW	instructor/v2/core/retry.py	113	CODE
LOW	instructor/v2/core/retry.py	358	CODE
LOW	instructor/v2/core/messages.py	51	CODE
LOW	instructor/v2/core/messages.py	72	CODE
LOW	instructor/v2/core/json.py	9	CODE
LOW	instructor/v2/core/json.py	76	CODE
LOW	instructor/v2/core/json.py	174	CODE
LOW	instructor/v2/providers/cohere/handlers.py	93	CODE
LOW	instructor/v2/providers/gemini/handlers.py	161	CODE
LOW	instructor/v2/providers/gemini/utils.py	77	CODE
LOW	instructor/v2/providers/gemini/utils.py	128	CODE
LOW	instructor/v2/providers/gemini/utils.py	229	CODE
LOW	instructor/v2/providers/gemini/utils.py	321	CODE
LOW	instructor/v2/providers/gemini/utils.py	353	CODE
LOW	instructor/v2/providers/gemini/utils.py	383	CODE
LOW	instructor/v2/providers/gemini/utils.py	152	CODE
LOW	instructor/v2/providers/xai/client.py	68	CODE
LOW	instructor/v2/providers/xai/client.py	120	CODE
LOW	instructor/v2/providers/xai/client.py	188	CODE
LOW	instructor/v2/providers/xai/client.py	260	CODE
LOW	instructor/v2/providers/xai/client.py	420	CODE
LOW	instructor/v2/providers/xai/handlers.py	58	CODE
42 more matches not shown…

Modern Structural Boilerplate70 hits · 69 pts

Severity	File	Line	Snippet	Context
LOW	examples/citation_with_extraction/main.py	17	logger = logging.getLogger(__name__)	CODE
LOW	examples/tenacity-benchmarks/run.py	39	logger = logging.getLogger(__name__)	CODE
LOW	examples/asyncio-benchmarks/run.py	26	logger = logging.getLogger(__name__)	CODE
LOW	examples/sqlmodel/test_basic.py	15	logger = logging.getLogger(__name__)	CODE
LOW	examples/sqlmodel/run.py	32	logger = logging.getLogger(__name__)	CODE
LOW	examples/caching/run.py	31	logger = logging.getLogger(__name__)	CODE
LOW	instructor/__init__.py	71	__all__ = [	CODE
LOW	instructor/exceptions.py	35	__all__ = [	CODE
LOW	instructor/core/__init__.py	22	__all__ = [	CODE
LOW	instructor/cache/__init__.py	35	__all__ = [	CODE
LOW	instructor/processing/__init__.py	18	__all__ = [	CODE
LOW	instructor/processing/schema.py	9	__all__ = [	CODE
LOW	instructor/providers/cohere/client.py	5	__all__ = ["from_cohere"]	CODE
LOW	instructor/providers/gemini/client.py	5	__all__ = ["from_gemini"]	CODE
LOW	instructor/providers/fireworks/client.py	5	__all__ = ["from_fireworks"]	CODE
LOW	instructor/providers/groq/client.py	5	__all__ = ["from_groq"]	CODE
LOW	instructor/providers/xai/client.py	5	__all__ = ["from_xai"]	CODE
LOW	instructor/providers/bedrock/client.py	5	__all__ = ["from_bedrock"]	CODE
LOW	instructor/providers/writer/client.py	5	__all__ = ["from_writer"]	CODE
LOW	instructor/providers/vertexai/client.py	5	__all__ = ["from_vertexai"]	CODE
LOW	instructor/providers/perplexity/client.py	5	__all__ = ["from_perplexity"]	CODE
LOW	instructor/providers/anthropic/client.py	5	__all__ = ["from_anthropic"]	CODE
LOW	instructor/providers/cerebras/client.py	5	__all__ = ["from_cerebras"]	CODE
LOW	instructor/providers/genai/client.py	5	__all__ = ["from_genai"]	CODE
LOW	instructor/providers/mistral/client.py	5	__all__ = ["from_mistral"]	CODE
LOW	instructor/utils/__init__.py	27	__all__ = [	CODE
LOW	instructor/utils/core.py	26	__all__ = [	CODE
LOW	instructor/v2/__init__.py	9	__all__ = [	CODE
LOW	instructor/v2/core/__init__.py	8	__all__ = [	CODE
LOW	instructor/v2/core/schema.py	19	__all__ = [	CODE
LOW	instructor/v2/providers/cohere/handlers.py	475	__all__ = [	STRING
LOW	instructor/v2/providers/cohere/__init__.py	8	__all__ = ["from_cohere"]	CODE
LOW	instructor/v2/providers/gemini/client.py	100	__all__ = ["from_gemini"]	CODE
LOW	instructor/v2/providers/gemini/handlers.py	324	__all__ = ["GeminiToolsHandler", "GeminiJSONHandler"]	CODE
LOW	instructor/v2/providers/gemini/__init__.py	9	__all__ = ["GeminiJSONHandler", "GeminiToolsHandler", "from_gemini"]	CODE
LOW	instructor/v2/providers/openrouter/client.py	51	__all__ = ["from_openrouter"]	CODE
LOW	instructor/v2/providers/openrouter/handlers.py	48	__all__ = ["OpenRouterJSONSchemaHandler"]	CODE
LOW	instructor/v2/providers/openrouter/__init__.py	6	__all__ = ["OpenRouterJSONSchemaHandler", "from_openrouter"]	CODE
LOW	instructor/v2/providers/fireworks/__init__.py	12	__all__ = ["from_fireworks"]	CODE
LOW	instructor/v2/providers/groq/__init__.py	8	__all__ = ["from_groq"]	CODE
LOW	instructor/v2/providers/xai/handlers.py	800	__all__ = [	CODE
LOW	instructor/v2/providers/xai/__init__.py	11	__all__ = ["from_xai"]	CODE
LOW	instructor/v2/providers/bedrock/client.py	138	__all__ = ["from_bedrock"]	CODE
LOW	instructor/v2/providers/bedrock/handlers.py	558	__all__ = [	CODE
LOW	instructor/v2/providers/bedrock/__init__.py	8	__all__ = ["from_bedrock"]	CODE
LOW	instructor/v2/providers/writer/handlers.py	370	__all__ = [	CODE
LOW	instructor/v2/providers/writer/__init__.py	8	__all__ = ["from_writer"]	CODE
LOW	instructor/v2/providers/vertexai/client.py	97	__all__ = ["from_vertexai"]	CODE
LOW	instructor/v2/providers/vertexai/handlers.py	492	__all__ = [	CODE
LOW	instructor/v2/providers/vertexai/__init__.py	8	__all__ = [	CODE
LOW	instructor/v2/providers/perplexity/client.py	51	__all__ = ["from_perplexity"]	CODE
LOW	instructor/v2/providers/perplexity/handlers.py	74	__all__ = ["PerplexityMDJSONHandler"]	CODE
LOW	instructor/v2/providers/perplexity/__init__.py	6	__all__ = ["PerplexityMDJSONHandler", "from_perplexity"]	CODE
LOW	instructor/v2/providers/anthropic/handlers.py	937	__all__ = [	STRING
LOW	instructor/v2/providers/anthropic/__init__.py	8	__all__ = ["from_anthropic"]	CODE
LOW	instructor/v2/providers/cerebras/__init__.py	8	__all__ = ["from_cerebras"]	CODE
LOW	instructor/v2/providers/genai/__init__.py	10	__all__ = ["from_genai"]	CODE
LOW	instructor/v2/providers/litellm/__init__.py	5	__all__ = ["from_litellm"]	CODE
LOW	instructor/v2/providers/mistral/handlers.py	626	__all__ = [	CODE
LOW	instructor/v2/providers/mistral/__init__.py	12	__all__ = ["from_mistral"]	CODE
10 more matches not shown…

Redundant / Tautological Comments39 hits · 60 pts

Severity	File	Line	Snippet	Context
LOW	tests/llm/shared_config.py	94	# Check if API key is set	COMMENT
LOW	tests/llm/shared_config.py	98	# Check if package is installed	COMMENT
LOW	tests/llm/test_openai/test_attr.py	21	# Check if the 'embeddings' attribute can be accessed through the client	COMMENT
LOW	examples/batch_api/run_batch_test.py	304	# Check if batch ID file exists	COMMENT
LOW	examples/batch_api/run_batch_test.py	365	# Check if batch ID file exists	COMMENT
LOW	examples/asyncio-benchmarks/run.py	277	# Check if OpenAI API key is set	COMMENT
LOW	examples/citations/run.py	30	# Check if the substring_quote is in the text_chunk	COMMENT
LOW	examples/sqlmodel/run.py	226	# Check if team already exists	COMMENT
LOW	examples/sqlmodel/run.py	360	if isinstance(hero, Hero): # Check if not an exception	CODE
LOW	examples/caching/example_redis.py	22	# Check if the result is already cached	COMMENT
LOW	examples/caching/run.py	150	# Check if we'll get a cache hit by calling cache_info	COMMENT
LOW	examples/caching/run.py	211	# Check if the result is already cached	COMMENT
LOW	examples/caching/run.py	288	# Check if the result is already cached	COMMENT
LOW	examples/caching/example_diskcache.py	32	# Check if the result is already cached	COMMENT
LOW	examples/caching/example_diskcache.py	48	# Check if the result is already cached	COMMENT
LOW	examples/logging/run.py	8	# Set logging to DEBUG	COMMENT
LOW⚡	scripts/check_blog_excerpts.py	49	# Read the file content	COMMENT
LOW⚡	scripts/check_blog_excerpts.py	53	# Check if the file contains the <!-- more --> tag	COMMENT
LOW	scripts/audit_patterns.py	66	# Check if from_provider is used	COMMENT
LOW	scripts/audit_patterns.py	84	# Check if the import is actually used	COMMENT
LOW	scripts/check_links.py	63	# Check if file exists	COMMENT
LOW	scripts/make_clean.py	88	# Check if content was modified	COMMENT
LOW	scripts/make_sitemap.py	215	# Check if we can reuse existing data	COMMENT
LOW	instructor/cache/__init__.py	214	# Check if this looks like a Pydantic-serialized object (has proper structure)	COMMENT
LOW	instructor/cli/batch.py	194	# Check if required API key is available for the provider	COMMENT
LOW	instructor/v2/auto_client.py	1317	# Check if model supports tools by looking at model name	COMMENT
LOW	instructor/v2/core/registry.py	187	# Check if already loaded	COMMENT
LOW	instructor/v2/core/registry.py	348	# Check if handlers are registered	COMMENT
LOW	instructor/v2/core/client.py	778	# Check if the response model is an iterable type	COMMENT
LOW	instructor/v2/core/multimodal.py	544	# Check if it's a valid PDF by looking for the PDF header	COMMENT
LOW	instructor/v2/providers/fireworks/client.py	85	# Check if fireworks is installed	COMMENT
LOW	instructor/v2/providers/groq/client.py	84	# Check if groq is installed	COMMENT
LOW	instructor/v2/providers/writer/client.py	84	# Check if writerai SDK is installed	COMMENT
LOW	instructor/v2/providers/cerebras/client.py	85	# Check if cerebras SDK is installed	COMMENT
LOW	instructor/v2/providers/mistral/client.py	105	# Check if mistralai is installed	COMMENT
LOW	instructor/v2/dsl/simple_type.py	96	# Check if inner type is a BaseModel - if so, not a simple type	COMMENT
LOW	instructor/v2/dsl/partial.py	122	# Check if root is complete AND has actual data (not just empty {})	COMMENT
LOW	instructor/batch/processor.py	209	# Check if this is a provider error response	COMMENT
LOW	instructor/batch/processor.py	263	# Check if result is an error	COMMENT

Fake / Example Data51 hits · 59 pts

Severity	File	Line	Snippet	Context
LOW	sitemap.yaml	557	blog/posts/fake-data.md:	CODE
LOW	tests/llm/test_core_providers/test_validation.py	52	assert user.name == "John Doe"	CODE
LOW⚡	tests/llm/test_core_providers/test_basic_extraction.py	88	assert user.name == "John Doe"	CODE
LOW⚡	tests/llm/test_core_providers/test_basic_extraction.py	91	assert user.address.street == "123 Main St"	CODE
LOW	tests/llm/test_writer/test_format_difficult_models.py	101	assert {book.author for book in response.books} == {"Jane Doe", "John Smith"}	STRING
LOW	tests/llm/test_genai/test_invalid_schema.py	125	assert response.name == "John Doe"	CODE
LOW	tests/llm/test_genai/test_invalid_schema.py	193	assert response.name == "John Doe"	CODE
LOW	tests/core/test_schema.py	145	name: str = "John Doe"	CODE
LOW	tests/processing/test_json_extraction.py	102	"street": "123 Main St",	CODE
LOW	docs/llms.txt	89	print(user.name) # "John Doe"	CODE
LOW	docs/index.md	428	#> User(name='John Doe', age=30)	COMMENT
LOW	docs/contributing.md	427	print(person.name) # "John Doe"	CODE
LOW	docs/prompting/zero_shot/style_prompting.md	53	sender="Jane Doe",	STRING
LOW	docs/learning/getting_started/structured_outputs.md	72	print(customer) # Customer(name='John Doe', age=35, email='john@example.com')	CODE
LOW	docs/blog/posts/structured-output-anthropic.md	75	"name": "John Doe",	STRING
LOW	docs/blog/posts/fake-data.md	92	#> name='John Doe' age=25	COMMENT
LOW⚡	docs/blog/posts/version-1.md	206	#> name='John Doe' age=None	COMMENT
LOW⚡	docs/blog/posts/version-1.md	207	#> name='John Doe' age=None	COMMENT
LOW⚡	docs/blog/posts/version-1.md	208	#> name='John Doe' age=None	COMMENT
LOW⚡	docs/blog/posts/version-1.md	209	#> name='John Doe' age=None	COMMENT
LOW⚡	docs/blog/posts/version-1.md	210	#> name='John Doe' age=30	COMMENT
LOW⚡	docs/blog/posts/version-1.md	211	#> name='John Doe' age=30	COMMENT
LOW⚡	docs/blog/posts/version-1.md	215	# name='John Doe' age=None	COMMENT
LOW⚡	docs/blog/posts/version-1.md	216	# name='John Doe' age=30	COMMENT
LOW⚡	docs/blog/posts/version-1.md	250	#> name='John Doe' age=30	COMMENT
LOW⚡	docs/blog/posts/version-1.md	251	#> name='Jane Doe' age=28	COMMENT
LOW⚡	docs/blog/posts/version-1.md	252	# User(name='John Doe', age=30)	COMMENT
LOW	docs/blog/posts/using_json.md	77	# "name": "John Doe",	COMMENT
LOW	docs/integrations/deepseek.md	156	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/fireworks.md	135	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/writer.md	127	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/xai.md	126	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/anthropic.md	82	# "name": "John Doe",	COMMENT
LOW	docs/integrations/groq.md	144	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/openai.md	174	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/bedrock.md	273	#> Address(street='123 Main St', city='New York', country='USA'),	STRING
LOW	docs/integrations/mistral.md	173	# Address(street='123 Main St', city='New York', country='USA'),	STRING
LOW	docs/integrations/cortex.md	143	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/cerebras.md	123	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/google.md	235	#> 'street': '123 Main St',	STRING
LOW	docs/integrations/perplexity.md	142	#> Address(street='123 Main St', city='New York', country='USA'),	STRING
LOW	docs/integrations/openrouter.md	135	#> name='Jason' age=25 addresses=[Address(street='123 Main St', city='New York', country='USA'), Address(street='456 Bea	STRING
LOW	docs/integrations/azure.md	206	# 'street': '123 Main St',	STRING
LOW	docs/examples/pii.md	109	{"private_data":[{"index":1,"data_type":"Name","pii_value":"John Doe"},{"index":2,"data_type":"Email","pii_value":"john.	CODE
LOW	docs/examples/extracting_receipts.md	175	items=[Item(name='Lorem ipsum', price=9.2, quantity=1), Item(name='Lorem ipsum dolor sit', price=19.2, quantity=1), Item	STRING
LOW	docs/examples/extracting_receipts.md	175	items=[Item(name='Lorem ipsum', price=9.2, quantity=1), Item(name='Lorem ipsum dolor sit', price=19.2, quantity=1), Item	STRING
LOW	docs/concepts/partial.md	131	"name": "John Doe",	CODE
LOW	docs/concepts/templating.md	52	#> name='John Doe' age=30	COMMENT
LOW	docs/concepts/fields.md	17	name: str = Field(default='John Doe')	CODE
LOW	docs/concepts/fields.md	22	#> name='John Doe'	COMMENT
LOW	examples/simple-extraction/user.py	56	"name": "John Doe",	STRING

Modern AI Meta-Vocabulary17 hits · 45 pts

Severity	File	Line	Snippet	Context
MEDIUM	sitemap.yaml	2435	- concepts/prompting.md#chain-of-thought]	CODE
MEDIUM	cross_link_mapping.yaml	201	# RAG AND SEARCH CLUSTER	COMMENT
MEDIUM	docs/prompting/index.md	14	[:octicons-arrow-right-16: Zero-Shot](#zero-shot) · [:octicons-arrow-right-16: Few-Shot](#few-shot)	CODE
MEDIUM	docs/prompting/index.md	106	## Zero-Shot {#zero-shot}	COMMENT
MEDIUM	docs/prompting/index.md	121	## Few-Shot {#few-shot}	COMMENT
MEDIUM	docs/blog/posts/rag-and-beyond.md	19	# RAG is more than just embedding search	COMMENT
MEDIUM	docs/blog/posts/rag-and-beyond.md	36	## The 'Dumb' RAG Model	COMMENT
MEDIUM	docs/blog/posts/rag-and-beyond.md	51	## Improving the RAG Model with Query Understanding	COMMENT
MEDIUM	docs/blog/posts/situate-context.md	30	## Background: The Context Problem in RAG	COMMENT
MEDIUM	docs/blog/posts/llm-as-reranker.md	19	# Building an LLM-based Reranker for your RAG pipeline	COMMENT
MEDIUM	docs/blog/posts/rag-timelines.md	20	# Enhancing RAG with Time Filters Using Instructor	COMMENT
MEDIUM	docs/integrations/truefoundry.md	9	TrueFoundry provides an enterprise-ready [AI Gateway](https://www.truefoundry.com/ai-gateway) and integrates seamlessly	CODE
MEDIUM	docs/examples/classification.md	32	Using [Chain of Thought](../concepts/prompting.md#chain-of-thought) has been shown to improve the quality of the pre	CODE
MEDIUM	docs/examples/bulk_classification.md	179	response_model=Tag, # Minimizes the hallucination of tags that are not in the allowed tags.	CODE
MEDIUM	docs/examples/bulk_classification.md	259	response_model=Tag, # Minimizes the hallucination of tags that are not in the allowed tags.	CODE
MEDIUM	docs/concepts/prompting.md	18	## Modular Chain of Thought {#chain-of-thought}	COMMENT
MEDIUM	examples/validated-multiclass/run.py	60	# Minizises the hallucination of tags that are not in the allowed tags.	COMMENT

Structural Annotation Overuse36 hits · 44 pts

Severity	File	Line	Snippet	Context
LOW	NEW_PROVIDER_AGENT_INSTRUCTIONS.md	31	### Step 1: Project Structure Setup	COMMENT
LOW	NEW_PROVIDER_AGENT_INSTRUCTIONS.md	58	### Step 2: Provider Client Implementation	COMMENT
LOW	NEW_PROVIDER_AGENT_INSTRUCTIONS.md	161	### Step 3: Mode Handlers Implementation	COMMENT
LOW	NEW_PROVIDER_AGENT_INSTRUCTIONS.md	285	### Step 4: Package Configuration	COMMENT
LOW	NEW_PROVIDER_AGENT_INSTRUCTIONS.md	347	### Step 3: Testing Implementation	COMMENT
LOW	NEW_PROVIDER_AGENT_INSTRUCTIONS.md	527	### Step 4: Required Infrastructure Updates	COMMENT
LOW	NEW_PROVIDER_AGENT_INSTRUCTIONS.md	573	### Step 5: Documentation	COMMENT
LOW⚡	docs/prompting/few_shot/exemplar_selection/knn.md	120	# Step 1 : Embed the Examples	STRING
LOW⚡	docs/prompting/few_shot/exemplar_selection/knn.md	126	# # Step 3: Find the k closest examples to the query	STRING
LOW⚡	docs/prompting/few_shot/exemplar_selection/knn.md	134	# Step 4: Use these examples as in-context examples	STRING
LOW	docs/prompting/zero_shot/s2a.md	76	# Step 1: Rewrite the prompt	STRING
LOW	docs/prompting/zero_shot/s2a.md	85	# Step 2: Generate the final response	STRING
LOW	docs/prompting/self_criticism/self_verification.md	121	# Step 1: Forward Reasoning	STRING
LOW	docs/prompting/self_criticism/self_verification.md	124	# Step 2: Backwards Verification	STRING
LOW	docs/prompting/ensembling/cosp.md	15	### Step 1 - Selecting Examples	COMMENT
LOW	docs/prompting/ensembling/cosp.md	57	### Step 2 - Self Consistency	COMMENT
LOW	docs/prompting/ensembling/cosp.md	252	# Step 1 : Generate the examples	STRING
LOW	docs/prompting/ensembling/cosp.md	258	# Step 2 : Run Self-Consistency	STRING
LOW	docs/prompting/decomposition/skeleton_of_thought.md	89	# Step 1: Get the skeleton	STRING
LOW	docs/prompting/decomposition/skeleton_of_thought.md	105	# Step 2: Expand on each point in parallel	STRING
LOW	docs/learning/getting_started/first_extraction.md	49	### Step 1: Define Your LLM Output Schema	COMMENT
LOW	docs/learning/getting_started/first_extraction.md	61	### Step 2: Configure Your LLM Client	COMMENT
LOW	docs/learning/getting_started/first_extraction.md	69	### Step 3: Execute LLM Extraction	COMMENT
LOW	docs/learning/getting_started/first_extraction.md	86	### Step 4: Work with Validated LLM Data	COMMENT
LOW	docs/integrations/truefoundry.md	22	### Step 1: Install Dependencies	COMMENT
LOW	docs/integrations/truefoundry.md	28	### Step 2: Configure Instructor with TrueFoundry Gateway	COMMENT
LOW	docs/concepts/reask_validation.md	120	### Step 1: Define the Response Model with Validators	COMMENT
LOW	instructor/v2/README.md	344	#### Step 1: Analyze Your V1 Implementation	COMMENT
LOW	instructor/v2/README.md	401	#### Step 2: Create V2 Provider Directory Structure	COMMENT
LOW	instructor/v2/README.md	412	#### Step 3: Map V1 Modes to V2 Modes	COMMENT
LOW	instructor/v2/README.md	422	#### Step 4: Extract Handler Logic from V1	COMMENT
LOW	instructor/v2/README.md	460	#### Step 5: Implement V2 Handlers	COMMENT
LOW	instructor/v2/README.md	540	#### Step 6: Create V2 Factory Function	COMMENT
LOW	instructor/v2/README.md	631	#### Step 7: Export Provider	COMMENT
LOW	instructor/v2/README.md	658	#### Step 8: Write Comprehensive Tests	COMMENT
LOW	instructor/v2/README.md	695	#### Step 9: Update Integration Points	COMMENT

Cross-Language Confusion7 hits · 32 pts

Severity	File	Line	Snippet	Context
HIGH	tests/test_genai_config_merging.py	190	# Test with Optional type (Union with null)	COMMENT
HIGH	tests/test_anthropic_bedrock_caller.py	5	resulting dict contained "caller": null, which the Anthropic API rejected with	STRING
HIGH	tests/llm/test_genai/test_schema_conversion.py	66	"""Test conversion transforms anyOf[T, null] to nullable fields."""	STRING
HIGH	tests/llm/test_genai/test_schema_conversion.py	223	# Schema with Optional field (Union with null)	COMMENT
HIGH	tests/dsl/test_partial.py	976	chunks = ['{"name": "Al', 'ice", "email"', ": null}"]	CODE
HIGH	tests/dsl/test_partial.py	1015	yield ": null}"	CODE
HIGH	examples/simple-extraction/maybe_user.py	66	"user": null,	STRING

Synthetic Comment Markers4 hits · 30 pts

Severity	File	Line	Snippet	Context
HIGH	docs/examples/sqlmodel.md	93	# AI-generated fields	COMMENT
HIGH	docs/examples/sqlmodel.md	589	# AI-generated fields with database constraints	COMMENT
HIGH	examples/sqlmodel/run.py	86	# AI-generated fields with validation	COMMENT
HIGH	examples/sqlmodel/run.py	119	# AI-generated fields	COMMENT

Over-Commented Block24 hits · 24 pts

Severity	File	Line	Snippet	Context
LOW	requirements.txt	1	# This file was autogenerated by uv via the following command:	COMMENT
LOW	requirements.txt	21	# httpcore	COMMENT
LOW	requirements.txt	41	# via openai	COMMENT
LOW	requirements.txt	61	# via	COMMENT
LOW	requirements.txt	81	# via instructor (pyproject.toml)	COMMENT
LOW	requirements.txt	101	# anyio	COMMENT
LOW	docs/blog/posts/version-1.md	201	print(user)	COMMENT
LOW	docs/blog/posts/generating-pdf-citations.md	101	},	COMMENT
LOW	docs/blog/posts/introducing-structured-outputs.md	121	#> {"	COMMENT
LOW	docs/blog/posts/introducing-structured-outputs.md	141	#> {"	COMMENT
LOW	…cs/blog/posts/announcing-unified-provider-interface.md	41	- Simplified Configuration: Reduces boilerplate code in projects that integrate with multiple LLM providers.	COMMENT
LOW	docs/integrations/fireworks.md	121	He lives at 123 Main St, New York, USA	COMMENT
LOW	docs/integrations/writer.md	121	print(user)	COMMENT
LOW	docs/integrations/xai.md	121	#> {	COMMENT
LOW	docs/integrations/anthropic.md	81	# {	COMMENT
LOW	docs/integrations/anthropic.md	221	# Image.from_path("path/to/local/image.jpg")	COMMENT
LOW	docs/integrations/groq.md	141	#> 'age': 25,	COMMENT
LOW	docs/integrations/openai.md	161	He lives at 123 Main St, New York, USA	COMMENT
LOW	docs/integrations/cortex.md	141	#> 'addresses': [	COMMENT
LOW	docs/integrations/cerebras.md	121	#> 'addresses': [	COMMENT
LOW	docs/integrations/google.md	221	He lives at 123 Main St, New York, USA	COMMENT
LOW	docs/integrations/azure.md	201	# {	COMMENT
LOW	docs/concepts/prompt_caching.md	241	# id='msg_01QcqjktYc1PXL8nk7y5hkMV',	COMMENT
LOW	examples/recursive_filepaths/parse_recursive_paths.py	121	└── file4.txt	COMMENT

Dead Code3 hits · 6 pts

Severity	File	Line	Context
MEDIUM	examples/citation_with_extraction/main.py	132	CODE
MEDIUM	examples/citation_with_extraction/main.py	134	CODE
MEDIUM	examples/citation_with_extraction/main.py	147	CODE

AI Slop Vocabulary5 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/tenacity-benchmarks/run.py	238	"""Extract with comprehensive logging."""	STRING
MEDIUM	examples/caching/run.py	515	"""Run comprehensive caching demonstration"""	STRING
LOW	instructor/v2/core/retry.py	146	# No structured output, just call the API	COMMENT
LOW	instructor/v2/core/retry.py	391	# No structured output, just call the API	COMMENT
MEDIUM	instructor/batch/models.py	96	"""Enhanced unified batch job information with comprehensive provider support"""	STRING

AI Structural Patterns5 hits · 5 pts

Severity	File	Line	Context
LOW	examples/classification/classifiy_with_validation.py	67	CODE
LOW	examples/situate_context/run.py	69	CODE
LOW	examples/caching/run.py	141	CODE
LOW	scripts/make_desc.py	72	CODE
LOW	instructor/cli/jobs.py	146	CODE

Slop Phrases2 hits · 5 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/simple-extraction/maybe_user.py	72	# ! due to the __bool__ method, you can use the MaybeUser object as a boolean	COMMENT
MEDIUM	examples/gpt-engineer/program.json	1	{"files": [{"file_name": "readme.md", "body": "# FastAPI App\n\nThis is a FastAPI app that provides some basic math func	CODE

Example Usage Blocks2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	examples/youtube-clips/run.py	89	# Example usage	COMMENT
LOW	examples/situate_context/run.py	125	# Example usage	STRING

Overly Generic Function Names4 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	instructor/distil.py	48	>>> def my_function(a: int, b: int) -> int:	STRING
LOW	instructor/distil.py	52	"def my_function(a: int, b: int) -> int"	STRING
LOW	instructor/distil.py	174	>>> def my_function() -> MyModel:	STRING
LOW	instructor/distil.py	178	>>> def my_function() -> MyModel:	STRING

Verbosity Indicators1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	instructor/v2/dsl/simple_type.py	68	# ! TypeError, so we need to check if `response_model` is an Iterable	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings