nature-reader

1# Full-Paper Markdown Reader — Router
2 
3## Routing protocol
4 
5First distinguish creating a reader from answering a question or translating an excerpt.
6For a source-linked question, read `references/grounding-rules.md` and inspect only the relevant
7source material; reuse existing source-map IDs when available. Do not regenerate the reader or
8require a full source map before answering. For an explicit excerpt request, apply extraction,
9translation, and grounding rules to that excerpt. The full-artifact workflow below applies when
10the user requests a reader or full-paper translation.
11 
12For a new task, load the core and matching resources below. Reuse already loaded guidance on follow-ups; load more only when the task needs it.
13 
14### 1. Load the manifest and the core layer
15 
16Read [manifest.yaml](manifest.yaml). It declares the `source_format` axis, the allowed values, and the file paths each value maps to.
17 
18Also read every file listed under `always_load`. These hold the core principles, the reading workflow, and the output contract that apply to every reading job, plus the shared Terminology Ledger used to build the recurring-term table.
19 
20### 2. Detect the source format
21 
22Decide the `source_format` value using the manifest's `detect:` hint and the user's input:
23 
24- `pdf-text` — selectable-text PDF. Default.
25- `scanned-pdf` — image-only or OCR-required PDF.
26- `html` — publisher or preprint HTML page.
27- `doi-arxiv` — a bare DOI or arXiv link that must be resolved first.
28…