Repository navigation
feat(elos): on-device OCR of scanned PDFs in the MCP server (macOS Vision) - #26
Conversation
…sion) Scanned course PDFs were skipped by the agent server. On macOS it now recognises them with the built-in Vision framework (mcp/ocr-vision.swift, compiled once with swiftc): no download, no upload. OCR runs in the background so a first question never waits, results are cached by file digest outside the shared folder (ELOS_CACHE_DIR), and citations from OCR pages say to verify against the page. `npm run mcp:ocr` prepares the cache ahead of time; ELOS_OCR=off disables it. On a real 226-file library: 14 scanned PDFs / 220 pages recognised in 84 s, readable documents 210 → 224. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
ⓘ Qodo reviews are paused because the subscription is no longer active. Ask your workspace admin to reactivate the subscription to resume reviews. Manage billing |
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars. ⚙️ Run configuration
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Summary
Scanned course PDFs are now read by the agent server on macOS with the built-in Vision framework (
mcp/ocr-vision.swift, compiled once): no download, no upload. Background OCR (first question never waits), cache by file digest outside the shared folder (ELOS_CACHE_DIR), OCR citations flagged.npm run mcp:ocrpre-computes;ELOS_OCR=offdisables.Real library: 14 scanned PDFs / 220 pages in 84 s; readable documents 210 → 224.
Test plan
npm run test:ci, typecheck,eslint .🤖 Generated with Claude Code