SUPPORTED_EXTS` so the walker's globs cannot drift from what the extractor handles. PDF and legacy binary formats are deliberately out of scope.
- **[glean_code/_indexing_walk.py](glean_code/_indexing_walk.py)** — the `--path
extraction is format-dependent
`src/metadata.py` reads real EPUB `DC` metadata (title/author/subtitle) for `.epub`. For `.pdf`/`.txt` there is no such metadata, so it falls back to "first non-blank line
console kept its own list of formats (`ACCEPT`/`BINARY` constants in
`Ingest.jsx`) so every `.pdf` stayed greyed out while the converter was
installed, enabled and loaded; the Models console kept
only networked script, and not part of the pipeline.** Fetches each paper's source PDF, counts words with `pdftotext`, and caches the result in `source_lengths.json`. Run by hand when papers
structure and content completeness
/wire:kickoff-review [release-folder] — Internal review; on approval, instructs PDF export via headless Chrome
```
Set `engagementType: "Discovery"` automatically when engagement type is discovery — the deck
future for 23 works. Use `observed_from`.
- **Never diff across extraction profiles.** `pdf-lu/1` and `akn-lu/1` mint different anchor
schemes, so pairing them reports parser disagreement
portals.yml` | Query and company config |
| `templates/cv-template.html` | HTML template for CVs |
| `generate-pdf.mjs` | Playwright: HTML to PDF |
| `article-digest.md` | Compact proof points from portfolio (optional) |
| `interview-prep/story-bank.md` | Accumulated STAR+R stories across
auth tokens (`.npmrc`, `.pypirc`, `.netrc`). Never remove this filtering.
3. **WeasyPrint SSRF protection**: The PDF export (`--format pdf`) MUST use a custom `url_fetcher` that blocks all URL fetching. Never
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.