extraction with relevance scoring
- [pdfService.ts](zotero-mcp-plugin/src/modules/pdfService.ts) / [pdfProcessor.ts](zotero-mcp-plugin/src/modules/pdfProcessor.ts) - PDF text extraction
### Configuration
- [serverPreferences.ts](zotero-mcp-plugin/src/modules/serverPreferences.ts) - Server port and enabled state preferences
- [mcpSettingsService.ts
4228d agoReviewMountCreate a free account to mount
directly**, don't ask to paste the text into the chat. Formats: `.txt`, `.md`, `.pdf`, `.docx`.
**`.docx` files:** the Read tool cannot open them (binary). Do not tell
412mo agoReviewMountCreate a free account to mount
down first, then write new data at row 0.
- **JXA export format strings**: Use `"PDF"` not `"Numbers PDF"`/`"Pages PDF"`/`"Keynote PDF"`. The app-prefixed strings cause
419mo agoReviewMountCreate a free account to mount
/files` to the Express server (:3012).
**Build chunking**: `vite.config.ts` splits vendor libs into `vendor-pdf`, `vendor-charts`, `vendor-icons`, and `vendor`. Feature-specific code splits into `feature-investigation`, `feature-media
402mo agoReviewMountCreate a free account to mount
study facts (`config.toml`) + an institution pack (`profile.toml` + `forms.py`) →
that institution's official DOCX forms → PDF → layout gate. KFSYSCC is the bundled
reference pack (`irb_in_hurry/institutions/kfsyscc/`).
Method: `docs/METHODOLOGY.md` · Fork guide
3924d agoReviewMountCreate a free account to mount
Search the vault first to find the exact filename if unsure.
- Image embeds: `![[filename.png]]`
- PDF embeds: `![[filename.pdf]]`
- Anki anchor: `[ ](#anki-card)` — marks content for Anki export
## Directory structure
```
notes
397mo agoReviewMountCreate a free account to mount
tests use, so those imports are not dead
## Testing changes
Test with a small PDF to verify the full pipeline:
```bash
python3 scripts/convert.py /path/to/small.pdf --olang zh
# then run translation
3824d agoReviewMountCreate a free account to mount
enabled by default) allows PNG images to be stored as WebP instead of losslessly. PDF streams are not scanned (pdf_parse was removed).
### Code constraints
- **No unsafe code** — enforced
deflate_stream`, assert bitwise identical output.
- **Container round-trip**: compress a ZIP / PNG / DOCX / PDF through
`PreflateContainerProcessor`, decompress with `RecreateContainerProcessor`,
assert the output matches the original file byte-for-byte
their resume as LaTeX, for example an Overleaf export (optional; default: you convert
the PDF into Jake's Resume template); for each bullet with no number, a real number
3711d agoReviewMountCreate a free account to mount
status` is
`success`/`failure`/`timedout`/`error`/... — but note **LaTeX recovers and still emits a PDF
on most errors, so `status` is `success` even when the document has errors**; the errors
3713d agoReviewMountCreate a free account to mount
eForm pages must not receive a global stylesheet: the renderers (`efmshowform_data.jsp`,
`efmformadd_data.jsp`) and the PDF render surface (`EFormRenderPdfHtmlComposer`) never add the
plain `bootstrap.min.css`, whose reboot moves legacy eForm fields
3519d agoReviewMountCreate a free account to mount
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.