feat(labs): add local-OCR text mode for image-blind AI providers

Add an opt-in in-browser OCR path so a user whose provider cannot read
images (ChatGPT-OAuth/Codex, a text-only model) can still scan a lab
report. The capability probe gains a `mode` field: `vision` when the
provider reads the image directly, `text` when local OCR is enabled and
any provider is configured, or null. The extract route grows a text
branch that accepts the in-browser-OCR'd text as JSON and structures it
through the existing schema + review/commit flow; the raw image never
reaches the server in text mode. New `labsLocalOcrEnabled` user column
(migration 0184, default off) gates it, with a dedicated PATCH endpoint.
This commit is contained in:
Marc-André Bombeck committed 2026-06-20 16:50:06 +02:00
1 parent fa37941add
commit 3d039d5220
13 files changed
+634 -77

No files matched your search

+3
View File
@@ -37,4 +37,7 @@ export const labKeys = {
// v1.18.9 — Lab-OCR capability probe (drives whether the "Scan a report"
// affordance shows). Cheap GET; the dialog refetches it on open.
ocrCapability: () => ["lab-ocr", "capability"] as const,
// v1.18.10 — local (in-browser) OCR opt-in flag for text-only providers.
labsLocalOcr: () => ["labs", "local-ocr"] as const,
};