mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-15 19:52:50 +03:00
c62ace5a49
* feat(ocr): transformation layer on ocrRegistry (Mistral shape canonical)
* feat(ocr): Azure Document Intelligence provider (prebuilt-read, analyze+poll)
* feat(ocr): generic dispatch with per-provider transformation and DI poll loop
* test(ocr): align sanitized-500 assert with HR#12 error sanitization
The test's own title ("returns a sanitized 500") describes the new
behavior mandated by HR#12 (never leak err.message in a response body).
The old regex asserted the pre-sanitization leak (`OCR request failed:
socket closed`) as expected output, which contradicted its own title
and the sanitization this task intentionally introduced in
open-sse/handlers/ocr.ts. Scoped to this single assertion only.
* fix(ocr): fail fast on non-ok poll responses instead of misleading 504
pollOcrOperation now checks pollRes.ok and returns a sanitized 502
immediately (logging the upstream status via console.error) instead of
looping until the 30-attempt cap and surfacing a misleading timeout for
what was actually an auth/upstream error during polling.
* feat(ocr): route/docs for multi-provider /v1/ocr
- Route: map the connection's providerSpecificData.baseUrl onto
credentials.baseUrl (resolveOcrCredentials) so azure-document-intelligence
connections resolve their endpoint the same way every other custom-endpoint
provider does (src/lib/providers/validation/*); previously handleOcr only
saw a baseUrl when a caller set it directly, so the DB-backed Azure
connection endpoint was never forwarded.
- v1OcrSchema.model is already a free-form string, no schema change needed.
- Docs: add the /v1/ocr provider table + example + Azure poll-flow note to
API_REFERENCE.md, and describe the provider/model prefix + async poll
behavior in openapi.yaml.
- Test: tests/unit/ocr-route-contract.test.ts covers getAllOcrModels/
parseOcrModel for both providers and resolveOcrCredentials's mapping.
* chore(quality): rebaseline deadExports for the OCR/image-to-text series
* docs(skills): regenerate omni-inference skill for the multi-provider /v1/ocr
The generated agent skill mirrors docs/reference/API_REFERENCE.md; updating the
/v1/ocr section left it stale and tripped the merge-integrity gate.
---------
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
75 lines
3.0 KiB
TypeScript
75 lines
3.0 KiB
TypeScript
import { test } from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import {
|
|
OCR_PROVIDERS,
|
|
getOcrTransformation,
|
|
MISTRAL_PASSTHROUGH,
|
|
} from "../../open-sse/config/ocrRegistry.ts";
|
|
|
|
test("mistral resolves the passthrough transformation by default", () => {
|
|
const t = getOcrTransformation("mistral");
|
|
assert.equal(t, MISTRAL_PASSTHROUGH);
|
|
const { url, init } = t.buildRequest({
|
|
baseUrl: OCR_PROVIDERS.mistral.baseUrl,
|
|
token: "sk-test",
|
|
body: { document: { type: "image_url", image_url: "https://x/y.png" } },
|
|
modelId: "mistral-ocr-latest",
|
|
});
|
|
assert.equal(url, "https://api.mistral.ai/v1/ocr");
|
|
assert.equal(init.method, "POST");
|
|
assert.equal((init.headers as Record<string, string>).Authorization, "Bearer sk-test");
|
|
const sent = JSON.parse(String(init.body));
|
|
assert.equal(sent.model, "mistral-ocr-latest");
|
|
});
|
|
|
|
test("passthrough parseResponse returns the body unchanged (Mistral is the canonical shape)", () => {
|
|
const raw = { pages: [{ index: 0, markdown: "hello" }], model: "mistral-ocr-latest" };
|
|
assert.deepEqual(MISTRAL_PASSTHROUGH.parseResponse(raw), raw);
|
|
});
|
|
|
|
test("azure-document-intelligence builds the prebuilt-read:analyze request", () => {
|
|
const t = getOcrTransformation("azure-document-intelligence");
|
|
const { url, init } = t.buildRequest({
|
|
baseUrl: "https://myres.cognitiveservices.azure.com",
|
|
token: "azkey",
|
|
body: { document: { type: "document_url", document_url: "https://x/d.pdf" } },
|
|
modelId: "prebuilt-read",
|
|
});
|
|
assert.equal(
|
|
url,
|
|
"https://myres.cognitiveservices.azure.com/documentintelligence/documentModels/prebuilt-read:analyze?api-version=2024-11-30&outputContentFormat=markdown"
|
|
);
|
|
assert.equal((init.headers as Record<string, string>)["Ocp-Apim-Subscription-Key"], "azkey");
|
|
const sent = JSON.parse(String(init.body));
|
|
assert.equal(sent.urlSource, "https://x/d.pdf");
|
|
});
|
|
|
|
test("azure-document-intelligence extracts poll URL and parses analyzeResult into Mistral shape", () => {
|
|
const t = getOcrTransformation("azure-document-intelligence");
|
|
const res = new Response(null, {
|
|
status: 202,
|
|
headers: { "Operation-Location": "https://poll/op/1" },
|
|
});
|
|
assert.equal(t.pollUrl?.(res), "https://poll/op/1");
|
|
const parsed = t.parseResponse({
|
|
status: "succeeded",
|
|
analyzeResult: { content: "# doc text", pages: [{ pageNumber: 1 }] },
|
|
});
|
|
assert.equal(parsed.pages.length, 1);
|
|
assert.equal(parsed.pages[0].index, 0);
|
|
assert.equal(parsed.pages[0].markdown, "# doc text");
|
|
assert.equal(parsed.model, "prebuilt-read");
|
|
});
|
|
|
|
test("azure DI maps base64/image_url documents to base64Source/urlSource", () => {
|
|
const t = getOcrTransformation("azure-document-intelligence");
|
|
const { init } = t.buildRequest({
|
|
baseUrl: "https://r.example.com",
|
|
token: "k",
|
|
body: { document: { type: "image_url", image_url: "data:image/png;base64,AAAA" } },
|
|
modelId: "prebuilt-read",
|
|
});
|
|
const sent = JSON.parse(String(init.body));
|
|
assert.equal(sent.base64Source, "AAAA");
|
|
});
|