research-memory

1# Research Memory
2 
3Keep `<vault>/DeepPaperNote/research-memory.md` true to the user's research by **interviewing** them. The user never writes the memory alone: you propose, with evidence from what they have read; they confirm, correct, or add. Only confirmed answers reach the file, and only through `scripts/write_research_memory.py`. This skill writes that one file and never touches paper notes.
4 
5`references/file-contract.md` defines the file format and the JSON both scripts read and write. Read it before step 4.
6 
7## 1. Read the vault
8 
9Run `python3 scripts/aggregate_reading.py --output <tmp>/aggregate.json`. It finds the vault through DeepPaperNote's configuration. On `needs_vault` or `not_a_vault`, ask the user once for their Obsidian vault folder and rerun with `--vault <path>`.
10 
11Keep `memory.sha256` from this run; step 4 passes it to the writer.
12 
13**Done when** the aggregate reports `status: ok`.
14 
15## 2. Plan the interview
16 
17`memory.exists` picks the mode. Build the list of open **candidates**, each a statement you will ask the user to confirm, with its evidence: counts and up to five notes by title from the aggregate.
18 
19**Building** (no memory file yet):
20- With `enough_reading` true, propose candidate directions from clusters across `aggregates.methods`, `datasets`, `tasks`, `domains`, and the recent window. The user's own words weigh most: `papers[].my_notes` and `papers[].judgments`.
21…