I feel the baseline comparison should be relative to the intuitive and simple "line-numbers only" schema.

It's less token heavy than the proposed hash approach, and I don't think frontier LLMs hallucinate line numbers if each line in the context is prefixed with them.

The issue is when the file changed between when the LLM read the file and when it wrote to the file. Just using line numbers will clobber a file if that happens. The hashes prevent that from being an issue.

it starts writing to the wrong part of the file after multiple edits.