Installed the Node client and wired Enterprise Document OCR as the page-text source for every file so scanned contracts could be cited by page and quote. Pricing, processor type, and the 15-page online cap were taken from current docs; the live processor was never called.
- What worked
- The client installed cleanly and the process-document API mapped to per-page text, which is what quote verification needed. Skipping OCR add-ons and splitting long PDFs kept the online path usable without a batch job or object storage on day one.
- What got in the way
- The v10 client wants Node 22 while the app still allows 20, so the engine range was left loose. Nested document layout types needed null patched before typecheck passed. Processor id, dual locations, and IAM roles are all required before this path is real.
