feat(ocr): Tesseract.js as default scanner, AI as opt-in per port

The mobile receipt scanner now runs Tesseract.js in-browser by default —
on-device, free, and image bytes never leave the device. AI providers
(OpenAI / Claude) become a per-port opt-in for higher accuracy on
hard-to-read receipts.

- Lazy-load Tesseract WASM in src/lib/ocr/tesseract-client.ts (5 MB
  bundle dynamic-imports on first scan, not in main chunk)
- Heuristic parser src/lib/ocr/parse-receipt-text.ts extracts vendor,
  date, amount, currency, and line items from raw OCR text
- New port-scoped aiEnabled flag on OcrConfig (defaults false). Resolved
  flag never inherits from the global row — each port admin opts in
  independently
- Scan endpoint short-circuits to manual-mode when aiEnabled=false so
  the AI provider is never invoked unless the admin has flipped the
  switch
- Scan UI runs Tesseract first, then asks the server whether AI is
  enabled — uses the AI result only when its confidence beats Tesseract;
  network failures degrade gracefully to the local parse
- Admin OCR-settings form gains the per-port aiEnabled checkbox

Tests: 756/756 vitest (was 747) — +7 parser unit tests, +2 aiEnabled
config tests.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Matt Ciaccio
2026-04-28 19:46:29 +02:00
parent 46937bbcb9
commit 2cf1bd9754
11 changed files with 693 additions and 38 deletions

92
pnpm-lock.yaml generated
View File

@@ -200,6 +200,9 @@ importers:
tailwindcss-animate:
specifier: ^1.0.7
version: 1.0.7(tailwindcss@3.4.19(tsx@4.21.0)(yaml@2.8.2))
tesseract.js:
specifier: ^7.0.0
version: 7.0.0
zod:
specifier: ^3.24.0
version: 3.25.76
@@ -2763,6 +2766,9 @@ packages:
block-stream2@2.1.0:
resolution: {integrity: sha512-suhjmLI57Ewpmq00qaygS8UgEq2ly2PCItenIyhMqVjo4t4pGzqMvfgJuX8iWTeSDdfSSqS6j38fL4ToNL7Pfg==}
bmp-js@0.1.0:
resolution: {integrity: sha512-vHdS19CnY3hwiNdkaqk93DvjVLfbEcI8mys4UjuWrlX1haDmroo8o4xCzh4wD6DGV6HxRCyauwhHRqMTfERtjw==}
brace-expansion@1.1.12:
resolution: {integrity: sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==}
@@ -3708,6 +3714,9 @@ packages:
resolution: {integrity: sha512-im9DjEDQ55s9fL4EYzOAv0yMqmMBSZp6G0VvFyTMPKWxiSBHUj9NW/qqLmXUwXrrM7AvqSlTCfvqRb0cM8yYqw==}
engines: {node: '>=0.10.0'}
idb-keyval@6.2.2:
resolution: {integrity: sha512-yjD9nARJ/jb1g+CvD0tlhUHOrJ9Sy0P8T9MF3YaLlHnSRpwPfpTX0XIvpmw3gAJUmEu3FiICLBDPXVwyEvrleg==}
ieee754@1.2.1:
resolution: {integrity: sha512-dcyqhDvX1C46lXZcVqCpK+FtMRQVdIMN6/Df5js2zouUsqG7I6sFxitIC+7KYK29KdXOLHdu9zL4sFnoVQnqaA==}
@@ -3877,6 +3886,9 @@ packages:
resolution: {integrity: sha512-p3EcsicXjit7SaskXHs1hA91QxgTw46Fv6EFKKGS5DRFLD8yKnohjF3hxoju94b/OcMZoQukzpPpBE9uLVKzgQ==}
engines: {node: '>= 0.4'}
is-url@1.2.4:
resolution: {integrity: sha512-ITvGim8FhRiYe4IQ5uHSkj7pVaPDrCTkNd3yq3cV7iZAcJdHTUMPMEHcqSOy9xZ9qFenQCvi+2wjH9a1nXqHww==}
is-weakmap@2.0.2:
resolution: {integrity: sha512-K5pXYOm9wqY1RgjpL3YTkF39tni1XajUIkawTLUo9EZEVUFga5gSQJF8nNS7ZwJQ02y+1YCNYcMh+HIf1ZqE+w==}
engines: {node: '>= 0.4'}
@@ -4289,6 +4301,15 @@ packages:
resolution: {integrity: sha512-pyFS63ptit/P5WqUkt+UUfe+4oevH+bFeIiPPdfb0pFeYEu/1ELnJu5l+5EcTKYL5M7zaAa7S8ddywgXypqKCw==}
engines: {node: '>= 0.4'}
node-fetch@2.7.0:
resolution: {integrity: sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==}
engines: {node: 4.x || >=6.0.0}
peerDependencies:
encoding: ^0.1.0
peerDependenciesMeta:
encoding:
optional: true
node-gyp-build-optional-packages@5.2.2:
resolution: {integrity: sha512-s+w+rBWnpTMwSFbaE0UXsRlg7hU4FjekKU4eyAih5T8nJuNZT1nNsskXpxmeqSK9UzkBl6UgRlnKc8hz8IEqOw==}
hasBin: true
@@ -4384,6 +4405,10 @@ packages:
zod:
optional: true
opencollective-postinstall@2.0.3:
resolution: {integrity: sha512-8AV/sCtuzUeTo8gQK5qDZzARrulB3egtLzFgteqB2tcT4Mw7B8Kt7JcDHmltjz6FOAHsvTevk70gZEbhM4ZS9Q==}
hasBin: true
optionator@0.9.4:
resolution: {integrity: sha512-6IpQ7mKUxRcZNLIObR0hz7lxsapSSIYNZJwXPGeF0mTVqGKFIXj1DQcMoT22S3ROcLyY/rz0PWaWZ9ayWmad9g==}
engines: {node: '>= 0.8.0'}
@@ -4970,6 +4995,9 @@ packages:
regenerator-runtime@0.11.1:
resolution: {integrity: sha512-MguG95oij0fC3QV3URf4V2SDYGJhJnJGqvIIgdECeODCT98wSWDAJ94SSuVpYQUoTcGUIL6L4yNB7j1DFFHSBg==}
regenerator-runtime@0.13.11:
resolution: {integrity: sha512-kY1AZVr2Ra+t+piVaJ4gxaFaReZVH40AKNo7UCX6W+dEwBo/2oZJzqfuN1qLq1oL45o56cPaTXELwrTh8Fpggg==}
regexp.prototype.flags@1.5.4:
resolution: {integrity: sha512-dYqgNSZbDwkaJ2ceRd9ojCGjBq+mOm9LmtXnAnEGyHhN/5R7iDW2TRw3h+o/jCFxus3P2LfWIIiwowAjANm7IA==}
engines: {node: '>= 0.4'}
@@ -5327,6 +5355,12 @@ packages:
engines: {node: '>=14.0.0'}
hasBin: true
tesseract.js-core@7.0.0:
resolution: {integrity: sha512-WnNH518NzmbSq9zgTPeoF8c+xmilS8rFIl1YKbk/ptuuc7p6cLNELNuPAzcmsYw450ca6bLa8j3t0VAtq435Vw==}
tesseract.js@7.0.0:
resolution: {integrity: sha512-exPBkd+z+wM1BuMkx/Bjv43OeLBxhL5kKWsz/9JY+DXcXdiBjiAch0V49QR3oAJqCaL5qURE0vx9Eo+G5YE7mA==}
thenify-all@1.6.0:
resolution: {integrity: sha512-RNxQH/qI8/t3thXJDwcstUO4zeqo64+Uy/+sNVRBx4Xn2OX+OZ9oP+iJnNFqplFra2ZUVeKCSa2oVWi3T4uVmA==}
engines: {node: '>=0.8'}
@@ -5383,6 +5417,9 @@ packages:
toggle-selection@1.0.6:
resolution: {integrity: sha512-BiZS+C1OS8g/q2RRbJmy59xpyghNBqrr6k5L/uKBGRsTfxmu3ffiRnd8mlGPUVayg8pvfi5urfnu8TU7DVOkLQ==}
tr46@0.0.3:
resolution: {integrity: sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==}
tr46@5.1.1:
resolution: {integrity: sha512-hdF5ZgjTqgAntKkklYw0R03MG2x/bSzTtkxmIRw/sTNV8YXsCJ1tfLAX23lhxhHJlEf3CRCOCGGWw3vI3GaSPw==}
engines: {node: '>=18'}
@@ -5591,6 +5628,12 @@ packages:
jsdom:
optional: true
wasm-feature-detect@1.8.0:
resolution: {integrity: sha512-zksaLKM2fVlnB5jQQDqKXXwYHLQUVH9es+5TOOHwGOVJOCeRBCiPjwSg+3tN2AdTCzjgli4jijCH290kXb/zWQ==}
webidl-conversions@3.0.1:
resolution: {integrity: sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ==}
webidl-conversions@7.0.0:
resolution: {integrity: sha512-VwddBukDzu71offAQR975unBIGqfKZpM+8ZX6ySk8nYhVoo5CYaZyzt3YBvYtRtO+aoGlqxPg/B87NGVZ/fu6g==}
engines: {node: '>=12'}
@@ -5599,6 +5642,9 @@ packages:
resolution: {integrity: sha512-De72GdQZzNTUBBChsXueQUnPKDkg/5A5zp7pFDuQAj5UFoENpiACU0wlCvzpAGnTkj++ihpKwKyYewn/XNUbKw==}
engines: {node: '>=18'}
whatwg-url@5.0.0:
resolution: {integrity: sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==}
which-boxed-primitive@1.1.1:
resolution: {integrity: sha512-TbX3mj8n0odCBFVlY8AxkqcHASw3L60jIuF8jFP78az3C2YhmGvqbHBpAjTRH2/xqYunrJ9g1jSyjCjpoWzIAA==}
engines: {node: '>= 0.4'}
@@ -5674,6 +5720,9 @@ packages:
resolution: {integrity: sha512-rVksvsnNCdJ/ohGc6xgPwyN8eheCxsiLM8mxuE/t/mOVqJewPuO1miLpTHQiRgTKCLexL4MeAFVagts7HmNZ2Q==}
engines: {node: '>=10'}
zlibjs@0.3.1:
resolution: {integrity: sha512-+J9RrgTKOmlxFSDHo0pI1xM6BLVUv+o0ZT9ANtCxGkjIVCCUdx9alUF8Gm+dGLKbkkkidWIHFDZHDMpfITt4+w==}
zod@3.25.76:
resolution: {integrity: sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==}
@@ -7869,6 +7918,8 @@ snapshots:
dependencies:
readable-stream: 3.6.2
bmp-js@0.1.0: {}
brace-expansion@1.1.12:
dependencies:
balanced-match: 1.0.2
@@ -8987,6 +9038,8 @@ snapshots:
dependencies:
safer-buffer: 2.1.2
idb-keyval@6.2.2: {}
ieee754@1.2.1: {}
ignore@5.3.2: {}
@@ -9175,6 +9228,8 @@ snapshots:
dependencies:
which-typed-array: 1.1.20
is-url@1.2.4: {}
is-weakmap@2.0.2: {}
is-weakref@1.1.1:
@@ -9563,6 +9618,10 @@ snapshots:
object.entries: 1.1.9
semver: 6.3.1
node-fetch@2.7.0:
dependencies:
whatwg-url: 5.0.0
node-gyp-build-optional-packages@5.2.2:
dependencies:
detect-libc: 2.1.2
@@ -9651,6 +9710,8 @@ snapshots:
ws: 8.18.3
zod: 3.25.76
opencollective-postinstall@2.0.3: {}
optionator@0.9.4:
dependencies:
deep-is: 0.1.4
@@ -10365,6 +10426,8 @@ snapshots:
regenerator-runtime@0.11.1: {}
regenerator-runtime@0.13.11: {}
regexp.prototype.flags@1.5.4:
dependencies:
call-bind: 1.0.8
@@ -10819,6 +10882,22 @@ snapshots:
- tsx
- yaml
tesseract.js-core@7.0.0: {}
tesseract.js@7.0.0:
dependencies:
bmp-js: 0.1.0
idb-keyval: 6.2.2
is-url: 1.2.4
node-fetch: 2.7.0
opencollective-postinstall: 2.0.3
regenerator-runtime: 0.13.11
tesseract.js-core: 7.0.0
wasm-feature-detect: 1.8.0
zlibjs: 0.3.1
transitivePeerDependencies:
- encoding
thenify-all@1.6.0:
dependencies:
thenify: 3.3.1
@@ -10866,6 +10945,8 @@ snapshots:
toggle-selection@1.0.6: {}
tr46@0.0.3: {}
tr46@5.1.1:
dependencies:
punycode: 2.3.1
@@ -11081,6 +11162,10 @@ snapshots:
transitivePeerDependencies:
- msw
wasm-feature-detect@1.8.0: {}
webidl-conversions@3.0.1: {}
webidl-conversions@7.0.0: {}
whatwg-url@14.2.0:
@@ -11088,6 +11173,11 @@ snapshots:
tr46: 5.1.1
webidl-conversions: 7.0.0
whatwg-url@5.0.0:
dependencies:
tr46: 0.0.3
webidl-conversions: 3.0.1
which-boxed-primitive@1.1.1:
dependencies:
is-bigint: 1.1.0
@@ -11167,6 +11257,8 @@ snapshots:
yocto-queue@0.1.0: {}
zlibjs@0.3.1: {}
zod@3.25.76: {}
zod@4.3.6: {}