• There are 53 files with units, with 5,629 lines of code.
• 0 very complex files (McCabe index sum 251+; 0 lines of code)
• 0 complex files (McCabe index sum 126-250; 0 lines of code)
• 3 medium complex files (McCabe index sum 51-125; 1,230 lines of code)
• 4 slightly complex files (McCabe index sum 26-50; 666 lines of code)
• 46 simple files (McCabe index sum 1-25; 3,733 lines of code)
• 35 main files have no units (e.g. languages without unit analysis, or files without functions) and are not classified.

The McCabe index of a file grows with its size: per 100 lines tells a large but plain file from a dense one, and most complex unit whether the complexity sits in one unit or is spread over many.

File	# lines	# units	McCabe index (sum)	per 100 lines	most complex unit
openai_file_search.py in stores	321	9	90	28	60
pipeline.py in ingestion	332	9	62	19	39
main.py in app/backend/app	577	20	56	10	23
auto_pipeline.py in evals/generator	160	2	38	24	26
runner.py in evals/graders	150	5	37	25	15
config.py in cli	296	7	28	9	9
utils.py in ingestion/chunkers	60	5	26	43	8
useStableOptions.ts in app/frontend/src/chatkit-react	106	2	23	22	19
local_judge.py in evals/runners	144	5	22	15	12
custom_qdrant.py in stores	114	6	22	19	7
harness.py in evals	112	2	21	19	20
pipeline.py in retrieval	234	9	21	9	5
reranker.py in retrieval	134	8	20	15	8
qgen.py in evals/generator	257	5	19	7	11
KnowledgeDocumentsPanel.tsx in app/frontend/src/components	236	5	19	8	7
env_utils.py in cli	48	3	19	40	7
retrieval.py in evals/metrics	48	6	18	38	5
main.py in cli	203	7	18	9	8
assistant_agent.py in app/backend/app	97	7	17	18	8
candidates.py in evals/generator	104	3	16	15	10
html.py in evals/reporters	51	1	14	27	14
openai_evals.py in evals/runners	195	5	13	7	4
recursive.py in ingestion/chunkers	41	2	13	32	12
schema.py in evals/datasets	52	2	11	21	8
base.py in stores	48	5	11	23	7
qa.py in evals/metrics	22	4	9	41	4
DocumentPreviewModal.tsx in app/frontend/src/components	64	2	9	14	6
useColorScheme.ts in app/frontend/src/hooks	37	2	9	24	5
my_chunker.py in extensions	59	3	9	15	7
useThreadCitations.ts in app/frontend/src/hooks	72	1	7	10	7
documents.py in app/backend/app	23	4	7	30	3
xml_aware.py in ingestion/chunkers	65	3	6	9	4
canonicalize.py in evals/generator	36	2	5	14	3
useChatKit.ts in app/frontend/src/chatkit-react	83	1	5	6	5
useKnowledgeDocuments.ts in app/frontend/src/hooks	40	1	4	10	4
custom_chunker_runner.py in ingestion	19	3	3	16	1
ChatKitPanel.tsx in app/frontend/src/components	65	1	3	5	3
memory_store.py in app/backend/app	145	2	3	2	2
synthesis.py in models	291	3	3	1	1
expansion.py in retrieval	84	3	3	4	1
judge_prompts.py in evals/graders	22	2	2	9	1
schema.py in evals/graders	19	1	2	11	2
corpus_iter.py in evals/generator	92	1	1	1	1
sampler.py in evals/generator	53	1	1	2	1
md.py in evals/reporters	30	1	1	3	1
rubrics.py in evals	32	1	1	3	1
hybrid.py in ingestion/chunkers	28	1	1	4	1
heading.py in ingestion/chunkers	44	1	1	2	1
vite.config.ts in app/frontend	20	1	1	5	1
citations.py in retrieval	21	1	1	5	1

• File complexity is the sum of the McCabe indexes (conditional complexity) of the units (methods, functions...) in a file.
• Files are classified in five categories based on that sum: 1-25 (simple files), 26-50 (slightly complex files), 51-125 (medium complex files), 126-250 (complex files), 251+ (very complex files). The default bands are five times the unit complexity bands, as a file is a group of units.
• Only main code files with units are classified. Files without units (languages without unit analysis, or files without functions) have no complexity to measure and are left out rather than counted as simple.
• A very complex file holds many decisions, which often means it has too many responsibilities: a candidate to split, and a place where changes need more testing.