Files
OmniRoute/tests/unit/ocr-handler-dispatch.test.ts
Diego Rodrigues de Sa e Souza c62ace5a49 feat(ocr): multi-provider /v1/ocr with transformation layer (Azure Document Intelligence) (#10283)
* 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>
2026-08-14 13:47:35 -03:00

134 lines
4.9 KiB
TypeScript

import { test } from "node:test";
import assert from "node:assert/strict";
import { handleOcr } from "../../open-sse/handlers/ocr.ts";
function fetchStub(
script: Array<{ status: number; headers?: Record<string, string>; json?: unknown }>
) {
const calls: Array<{ url: string; init: RequestInit }> = [];
const impl = async (url: string, init: RequestInit) => {
calls.push({ url, init });
const step = script.shift()!;
return new Response(step.json !== undefined ? JSON.stringify(step.json) : null, {
status: step.status,
headers: { "Content-Type": "application/json", ...(step.headers ?? {}) },
});
};
return { impl, calls };
}
const noSleep = async () => {};
test("mistral path posts once and returns the upstream body", async () => {
const { impl, calls } = fetchStub([
{ status: 200, json: { pages: [{ index: 0, markdown: "ok" }], model: "mistral-ocr-latest" } },
]);
const res = await handleOcr({
body: {
model: "mistral/mistral-ocr-latest",
document: { type: "image_url", image_url: "https://x/y.png" },
},
credentials: { apiKey: "sk" },
fetchImpl: impl,
sleepImpl: noSleep,
});
assert.equal(res.status, 200);
assert.equal(calls.length, 1);
const data = await res.json();
assert.equal(data.pages[0].markdown, "ok");
});
test("azure DI path polls Operation-Location until succeeded", async () => {
const { impl, calls } = fetchStub([
{ status: 202, headers: { "Operation-Location": "https://poll/op/1" } },
{ status: 200, json: { status: "running" } },
{ status: 200, json: { status: "succeeded", analyzeResult: { content: "# md", pages: [{}] } } },
]);
const res = await handleOcr({
body: {
model: "azure-document-intelligence/prebuilt-read",
document: { type: "document_url", document_url: "https://x/d.pdf" },
},
credentials: { apiKey: "azkey", baseUrl: "https://r.cognitiveservices.azure.com" },
fetchImpl: impl,
sleepImpl: noSleep,
});
assert.equal(res.status, 200);
assert.ok(calls.length >= 3);
const data = await res.json();
assert.equal(data.pages[0].markdown, "# md");
});
test("unknown model lists available providers dynamically and errors do not leak internals", async () => {
const res = await handleOcr({
body: { model: "nope/none", document: { type: "image_url", image_url: "https://x" } },
credentials: { apiKey: "k" },
fetchImpl: async () => new Response("{}", { status: 200 }),
sleepImpl: noSleep,
});
assert.equal(res.status, 400);
const body = await res.json();
assert.ok(body.error.message.includes("azure-document-intelligence"));
assert.ok(!body.error.message.includes("at /"));
});
test("azure DI poll returns failed status maps to 502", async () => {
const { impl } = fetchStub([
{ status: 202, headers: { "Operation-Location": "https://poll/op/1" } },
{ status: 200, json: { status: "failed" } },
]);
const res = await handleOcr({
body: {
model: "azure-document-intelligence/prebuilt-read",
document: { type: "document_url", document_url: "https://x/d.pdf" },
},
credentials: { apiKey: "azkey", baseUrl: "https://r.cognitiveservices.azure.com" },
fetchImpl: impl,
sleepImpl: noSleep,
});
assert.equal(res.status, 502);
const body = await res.json();
assert.ok(!body.error.message.includes("at /"));
});
test("azure DI poll returns a non-ok response (401) and fails fast without exhausting the loop", async () => {
const { impl, calls } = fetchStub([
{ status: 202, headers: { "Operation-Location": "https://poll/op/1" } },
{ status: 401, json: { error: "unauthorized" } },
]);
const res = await handleOcr({
body: {
model: "azure-document-intelligence/prebuilt-read",
document: { type: "document_url", document_url: "https://x/d.pdf" },
},
credentials: { apiKey: "azkey", baseUrl: "https://r.cognitiveservices.azure.com" },
fetchImpl: impl,
sleepImpl: noSleep,
});
assert.equal(res.status, 502);
// 1 initial POST + 1 poll: the loop stopped immediately, it did not run all 30 attempts.
assert.equal(calls.length, 2);
const body = await res.json();
assert.ok(!body.error.message.includes("at /"));
});
test("azure DI poll never resolves and times out after 30 attempts with a 504", async () => {
const script = [{ status: 202, headers: { "Operation-Location": "https://poll/op/1" } }];
for (let i = 0; i < 30; i++) {
script.push({ status: 200, json: { status: "running" } });
}
const { impl, calls } = fetchStub(script);
const res = await handleOcr({
body: {
model: "azure-document-intelligence/prebuilt-read",
document: { type: "document_url", document_url: "https://x/d.pdf" },
},
credentials: { apiKey: "azkey", baseUrl: "https://r.cognitiveservices.azure.com" },
fetchImpl: impl,
sleepImpl: noSleep,
});
assert.equal(res.status, 504);
// 1 initial POST + 30 poll attempts (the max cap), no more.
assert.equal(calls.length, 31);
});