feat(hub): switch capability provider to Aliyun Doc Mind (ADR-0027) (#6)

Co-authored-by: Hong Jiarong <me@jrhim.com>
Co-committed-by: Hong Jiarong <me@jrhim.com>
This commit is contained in:
2026-07-18 16:42:42 +08:00
committed by 洪佳荣
parent b673dd1fe9
commit 64b3d1fc64
8 changed files with 593 additions and 113 deletions
@@ -4,11 +4,11 @@ import { join } from "node:path";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { prisma, resetDb, seedTestOrganization, testSecretEnvelope, DEFAULT_ORG_ID } from "./helpers.js";
import { createPdfToMdBundleAdapter, CapabilityPathEscape } from "../../src/capability/pdfToMdBundle.js";
import { MineruClientError, type MineruClient, type MineruParseResult } from "../../src/capability/mineruClient.js";
import { DocmindClientError, type CapabilityProviderClient, type DocmindParseResult } from "../../src/capability/docmindClient.js";
import type { CapabilitySecretPayload } from "../../src/capability/types.js";
const CAPABILITY_ID = "pdf_to_md_bundle";
const PROVIDER_ID = "mineru";
const PROVIDER_ID = "aliyun_docmind";
/**
* ADR-0027: pdf_to_md_bundle adapter contract tests. Proves:
@@ -16,8 +16,8 @@ const PROVIDER_ID = "mineru";
* - fail-closed credential resolution (no ACTIVE connection → error)
* - UsageFact attribution with non-token meter (pages), costSource rules
* - outputs (md + images) written into workspace
* - MinerU client errors propagate
* The MineruClient is mocked; the prisma + envelope + filesystem are real.
* - docmind client errors propagate
* The client is mocked; the prisma + envelope + filesystem are real.
*/
describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
let workspaceRoot: string;
@@ -58,9 +58,9 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
async function seedActiveCapabilityConnection(): Promise<void> {
const payload: CapabilitySecretPayload = {
schemaVersion: 1,
baseUrl: "https://mineru.test/api",
apiToken: "mineru-secret-token",
projectId: null,
accessKeyId: "LTAI-test-key-id",
accessKeySecret: "test-secret-never-log",
endpoint: "docmind-api.cn-hangzhou.aliyuncs.com",
};
const connection = await prisma.organizationCapabilityConnection.create({
data: {
@@ -95,23 +95,23 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
});
}
function mockMineruClient(result: Partial<MineruParseResult> = {}): MineruClient {
const full: MineruParseResult = {
markdown: "# Parsed Document\n\nHello world.\n\n![fig](page_1_fig_0.jpg)\n",
function mockDocmindClient(result: Partial<DocmindParseResult> = {}): CapabilityProviderClient {
const full: DocmindParseResult = {
markdown: "# Parsed Document\n\nHello world.\n\n![fig](page_1.jpg)\n",
images: [
{ filename: "page_1_fig_0.jpg", data: new Uint8Array([0xff, 0xd8, 0xff, 0xe0]) },
{ filename: "page_1.jpg", data: new Uint8Array([0xff, 0xd8, 0xff, 0xe0]) },
],
pageCount: 3,
costUsd: 0.015,
requestId: "mineru-task-abc",
costUsd: 0.0168,
requestId: "docmind-job-abc",
...result,
};
return {
parse: vi.fn(async (): Promise<MineruParseResult> => full),
parse: vi.fn(async (): Promise<DocmindParseResult> => full),
};
}
function makeAdapter(client: MineruClient) {
function makeAdapter(client: CapabilityProviderClient) {
return createPdfToMdBundleAdapter({
secrets: testSecretEnvelope,
client,
@@ -130,7 +130,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
it("writes md + images into the workspace and records a UsageFact", async () => {
await seedActiveCapabilityConnection();
const inputPath = await seedInputPdf();
const client = mockMineruClient();
const client = mockDocmindClient();
const adapter = makeAdapter(client);
const result = await adapter.invoke({
@@ -147,12 +147,12 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
const md = await readFile(join(workspaceRoot, "output", "document.md"), "utf8");
expect(md).toContain("# Parsed Document");
expect(result.artifacts.some((a) => a.kind === "markdown" && a.path === "output/document.md")).toBe(true);
expect(result.artifacts.some((a) => a.kind === "image" && a.path === "output/page_1_fig_0.jpg")).toBe(true);
expect(result.artifacts.some((a) => a.kind === "image" && a.path === "output/page_1.jpg")).toBe(true);
// Client received the decrypted credential, not the env.
const call = (client.parse as ReturnType<typeof vi.fn>).mock.calls[0]?.[0] as CapabilitySecretPayload;
expect(call.apiToken).toBe("mineru-secret-token");
expect(call.baseUrl).toBe("https://mineru.test/api");
expect(call.accessKeyId).toBe("LTAI-test-key-id");
expect(call.endpoint).toBe("docmind-api.cn-hangzhou.aliyuncs.com");
// UsageFact written with non-token meter and provider_reported cost.
const facts = await prisma.usageFact.findMany({ where: { runId } });
@@ -163,15 +163,15 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
expect(fact.capabilityId).toBe(CAPABILITY_ID);
expect(Number(fact.quantity)).toBe(3);
expect(fact.unit).toBe("pages");
expect(Number(fact.costUsd!)).toBeCloseTo(0.015, 8);
expect(Number(fact.costUsd!)).toBeCloseTo(0.0168, 8);
expect(fact.costSource).toBe("provider_reported");
expect(fact.correlationId).toBe("mineru-task-abc");
expect(fact.correlationId).toBe("docmind-job-abc");
});
it("writes UsageFact with costSource=unknown when MinerU reports no cost", async () => {
it("writes UsageFact with costSource=unknown when docmind reports no cost", async () => {
await seedActiveCapabilityConnection();
const inputPath = await seedInputPdf();
const client = mockMineruClient({ costUsd: null, requestId: null });
const client = mockDocmindClient({ costUsd: null, requestId: null });
const adapter = makeAdapter(client);
await adapter.invoke({
@@ -194,7 +194,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
it("fails closed when the org has no ACTIVE capability connection", async () => {
// No connection seeded.
const inputPath = await seedInputPdf();
const adapter = makeAdapter(mockMineruClient());
const adapter = makeAdapter(mockDocmindClient());
await expect(adapter.invoke({
runId,
@@ -213,7 +213,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
it("rejects an input path that escapes the workspace", async () => {
await seedActiveCapabilityConnection();
const adapter = makeAdapter(mockMineruClient());
const adapter = makeAdapter(mockDocmindClient());
await expect(adapter.invoke({
runId,
@@ -229,7 +229,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
it("rejects an output path that escapes the workspace", async () => {
await seedActiveCapabilityConnection();
const inputPath = await seedInputPdf();
const adapter = makeAdapter(mockMineruClient());
const adapter = makeAdapter(mockDocmindClient());
await expect(adapter.invoke({
runId,
@@ -242,12 +242,12 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
})).rejects.toBeInstanceOf(CapabilityPathEscape);
});
it("propagates MinerU client errors without writing a UsageFact", async () => {
it("propagates docmind client errors without writing a UsageFact", async () => {
await seedActiveCapabilityConnection();
const inputPath = await seedInputPdf();
const client: MineruClient = {
parse: vi.fn(async (): Promise<MineruParseResult> => {
throw new MineruClientError("upstream 502", "mineru_rejected", 502);
const client: CapabilityProviderClient = {
parse: vi.fn(async (): Promise<DocmindParseResult> => {
throw new DocmindClientError("upstream 502", "docmind_rejected", 502);
}),
};
const adapter = makeAdapter(client);
@@ -269,7 +269,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
it("rejects empty markdown output as a parse failure", async () => {
await seedActiveCapabilityConnection();
const inputPath = await seedInputPdf();
const client = mockMineruClient({ markdown: "" });
const client = mockDocmindClient({ markdown: "" });
const adapter = makeAdapter(client);
await expect(adapter.invoke({