• There are 60 files with 15,071 lines of code.
• 2 very long files (3,732 lines of code)
• 5 long files (3,551 lines of code)
• 12 medium size files (3,767 lines of code)
• 21 small files (3,039 lines of code)
• 20 very small files (982 lines of code)

File	# lines	≈ tokens to read	# changes (1y)	≈ lines edited per change	lines read per line changed
trace.tpl.html in genai_processors/dev	2451	~15k–50k	15	~300	~10
content_api.py in genai_processors	686	~3k–10k	32	~50	~15
processor.py in genai_processors	899	~5k–15k	16	~70	~10
function_calling.py in genai_processors/core	458	~3k–7k	30	~70	~7
content_api_intro.ipynb in notebooks	719	~5k–15k	5	~150	~5
trace_file.py in genai_processors/dev	238	~1.5k–5k	15	~30	~7
transformers_model.py in genai_processors/core	318	~2k–5k	9	~70	~5
processor_intro.ipynb in notebooks	1281	~7k–20k	2	~200	~7
text.py in genai_processors/core	324	~2k–5k	7	~50	~7
realtime.py in genai_processors/core	217	~1.5k–5k	10	~50	~5
create_your_own_processor.ipynb in notebooks	693	~3k–10k	3	~100	~7
constrained_decoding.ipynb in notebooks	554	~3k–10k	3	~150	~3
genai_model.py in genai_processors/core	155	~1k–3k	9	~30	~5
function_calling_with_gemma.ipynb in notebooks	420	~2k–7k	3	~150	~3
ollama_model.py in genai_processors/core	169	~1k–3k	6	~30	~5
live_processor_intro.ipynb in notebooks	335	~2k–5k	3	~30	~7
mime_types.py in genai_processors	167	~1k–3k	6	~30	~5
sql_cache.py in genai_processors	166	~1k–3k	6	~50	~3
speech_to_text.py in genai_processors/core	280	~1.5k–5k	3	~100	~2
live_model.py in genai_processors/core	185	~1k–3k	4	~50	~3

Tokens are lines × 7 to 14 (analysis.fileReadsForChanges). Lines edited per change are the file's lines added and deleted divided by its commits over the whole history. Agents read about 2,000 lines at a time: when a 17,000-line file was split into modules, the tokens an agent read for the same change fell by 83% (The Economic Benefit of Refactoring, 2026).

There are 10 files with lines longer than 120 characters. In total, there are 52 long lines.

File	# lines	# units	# long lines
trace.tpl.html in genai_processors/dev	2451	-	22
drive_processors.ipynb in notebooks	337	-	4
live_processor_intro.ipynb in notebooks	335	-	4
constrained_decoding.ipynb in notebooks	554	-	4
content_api_intro.ipynb in notebooks	719	-	4
processor_intro.ipynb in notebooks	1281	-	3
function_calling_with_gemma.ipynb in notebooks	420	-	3
research_example.ipynb in notebooks	327	-	3
create_your_own_processor.ipynb in notebooks	693	-	3
function_calling.ipynb in notebooks	265	-	2

• File size measurements show the distribution of size of files.
• Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
• It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.