> ## Documentation Index > Fetch the complete documentation index at: https://cstreams.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Diagnostic > Settings for diagnosing and troubleshooting issues ## Overview As you experiment, you will likely find edges cases specific to your PDF collection. You can use the following settings to dig deeper into each run. ### Ignoring Files and Directories at Runtime Within the `[project-root]/data` directory tree, any directory named `.runtime-ignore` and its entire subtree will be skipped during processing. This is useful for troubleshooting and moving nested directories around without breaking the hierarchy. A leading `.` to hide the directory from the file system has no effect on processing. You must set a value, but you don't need to create the folder until you need it. [See a sample](/analysis-and-iteration/evaluation#use-runtime-ignore-folders-to-selectively-run-sets-of-files) directory listing with nested `.runtime-ignore` directories ### Diagnostic Folder The directory name for storing log data and diagnostic files. Relative to the project root directory. Example directory listing described on the [Evaluation](/analysis-and-iteration/evaluation#log-file-page-images-and-extracted-text) page. ### Save Diagnostic Files OCR is a complex process that can sometimes produce unexpected results. Enable saving diagnostic files to help troubleshoot:
Comparison of original and enhanced images, demonstrating the effect of binarisation
From Tesseract docs: [Improving the quality of the output](https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html)
For each page in the document, diagnostic files can be saved: **Images:** * the original image, as found in the source PDF * the enhanced image, after processing, to make it easier for OCR to read **Text files:** * the unstructured OCR results, as a plain text file * the structured OCR results, as a markdown file * vision analysis results (when local VLM is enabled) Default leaves both off so routine runs stay light on disk usage. Toggle them on when you need per-page artifacts for troubleshooting OCR quality or layout detection. Whether to save diagnostic images (original and enhanced) for each page. Whether to save diagnostic text files (OCR results, structured markdown, vision analysis) for each page. For saved diagnostic images. PNG preferred for maintaining sharp detail. ### AI Request and Response Logging Controls how AI prompts and responses are handled in logs. These are never shown in the terminal output, only in log files. Applies to both: * OpenAI filename and metadata generation * Ollama vision analysis Whether to include raw AI requests (prompts) in log files. Whether to include raw AI responses in log files. ### Terminal Colors Running the pipeline with `VERBOSE-TERM` gives rich output in the terminal. This gives fine grained view into the progress and potential failures. These [standard ANSI color codes](https://en.wikipedia.org/wiki/ANSI_escape_code#Colors) are used to make the output more readable. Modify these to change the color scheme.