template-app/modules/knowledge/__tests__/platform-knowledge.test.ts

import { createMemoryDataSource } from "@conusai-kit/data"
import { DEFAULT_FILES_POLICY, type FilesDeps, files } from "@conusai-kit/files"
import type { Knowledge, KnowledgeSearchHit } from "@conusai-kit/platform"
import { fakeObjectStore } from "@conusai-kit/testing"
import { describe, expect, it } from "vitest"
import { platformKnowledgeSearch } from "../adapters/platform-knowledge.js"
import type { KnowledgeScope } from "../core/ports.js"

const scope: KnowledgeScope = {
  level: "project",
  actor: { userId: "01900000-0000-7000-0000-000000000009" },
  orgId: "01900000-0000-7000-0000-000000000001",
  workspaceId: "01900000-0000-7000-0000-000000000002",
  projectId: "01900000-0000-7000-0000-000000000003",
}
const otherScope: KnowledgeScope = {
  ...scope,
  projectId: "01900000-0000-7000-0000-000000000004",
}
const storageKey = `files/${scope.workspaceId}/${scope.projectId}/01900000-0000-7000-0000-000000000100`
const otherStorageKey = `files/${otherScope.workspaceId}/${otherScope.projectId}/01900000-0000-7000-0000-000000000101`
const pathname = `org/${scope.orgId}/${storageKey}`

interface ClientStub {
  indexed: string[]
  removed: string[]
  searches: Array<Parameters<Knowledge["search"]>[0]>
  results: readonly KnowledgeSearchHit[]
}

function knowledgeClient(stub: ClientStub): Knowledge {
  return {
    readiness: async () => ({ state: "ready", reasons: [], checkedAt: new Date().toISOString() }),
    createCollection: async (input) => input,
    search: async (input) => {
      stub.searches.push(input)
      return stub.results
    },
    index: async (input) => {
      stub.indexed.push(input.documentRef)
      return { jobId: "job-1" }
    },
    job: async (jobId) => ({ jobId, status: "succeeded", progress: 1, generation: 1, error: null }),
    cancel: async () => undefined,
    remove: async (documentRef) => {
      stub.removed.push(documentRef)
    },
  }
}

function stub(results: readonly KnowledgeSearchHit[] = []): ClientStub {
  return { indexed: [], removed: [], searches: [], results }
}

function makeFiles() {
  const data = createMemoryDataSource({ entities: [files] })
  const deps: FilesDeps = { data, store: fakeObjectStore(), policy: DEFAULT_FILES_POLICY }
  return { data, deps }
}

async function seedFile(
  data: ReturnType<typeof createMemoryDataSource>,
  atScope: KnowledgeScope,
  key: string,
  filename = "contract.txt",
): Promise<string> {
  const row = await data.forScope(atScope).of(files).insert({
    status: "stored",
    storageKey: key,
    filename,
    contentType: "text/plain",
    size: 17,
    sha256: "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
    uploadedBy: atScope.actor.userId,
    storedAt: "2026-10-24T00:00:00.000Z",
    uploadId: null,
    declaredSize: null,
    partSize: null,
    deletingAt: null,
  })
  return row.id
}

describe("the managed knowledge Blob reference", () => {
  it("indexes and removes by Blob pathname rather than opaque file id", async () => {
    const { data, deps } = makeFiles()
    const fileId = await seedFile(data, scope, storageKey)
    const client = stub()
    const service = platformKnowledgeSearch(knowledgeClient(client), deps)

    await service.index(scope, {
      collectionName: "contracts",
      fileId,
      filename: "contract.txt",
      bytes: new TextEncoder().encode("managed knowledge"),
    })
    await service.remove(scope, { collectionName: "contracts", fileId })

    expect(client.indexed).toEqual([pathname])
    expect(client.removed).toEqual([pathname])
  })

  it("maps citations through scoped file rows and drops foreign or stale references", async () => {
    const { data, deps } = makeFiles()
    const fileId = await seedFile(data, scope, storageKey)
    await seedFile(data, otherScope, otherStorageKey, "other-project.txt")
    const client = stub([
      { documentRef: pathname, snippet: "own snippet", score: 0.9, citations: [{ page: 1 }] },
      {
        documentRef: `org/${scope.orgId}/${otherStorageKey}`,
        snippet: "other project snippet",
        score: 0.8,
        citations: [],
      },
      {
        documentRef: `org/01900000-0000-7000-0000-000000000777/${storageKey}`,
        snippet: "other organization snippet",
        score: 0.7,
        citations: [],
      },
      {
        documentRef: `org/${scope.orgId}/files/${scope.workspaceId}/${scope.projectId}/01900000-0000-7000-0000-000000000200`,
        snippet: "stale snippet",
        score: 0.6,
        citations: [],
      },
    ])
    const service = platformKnowledgeSearch(knowledgeClient(client), deps)

    const hits = await service.search(scope, {
      collectionName: "contracts",
      query: "contract",
      limit: 10,
      actorId: scope.actor.userId,
    })

    expect(hits).toEqual([
      {
        fileId,
        filename: "contract.txt",
        collectionName: "contracts",
        score: 0.9,
        chunk: 1,
        snippet: "own snippet",
      },
    ])
    expect(client.searches).toHaveLength(1)
    expect(client.searches[0]).toMatchObject({ collection: "contracts", query: "contract", limit: 10 })
    expect(client.searches[0]).not.toHaveProperty("tenant")
    expect(client.searches[0]).not.toHaveProperty("ownerRef")
  })

  it("refuses a foreign file id before any managed index call", async () => {
    const { data, deps } = makeFiles()
    const foreignFileId = await seedFile(data, otherScope, otherStorageKey)
    const client = stub()
    const service = platformKnowledgeSearch(knowledgeClient(client), deps)

    await expect(
      service.index(scope, {
        collectionName: "contracts",
        fileId: foreignFileId,
        filename: "other-project.txt",
        bytes: new TextEncoder().encode("foreign content"),
      }),
    ).rejects.toThrow()
    expect(client.indexed).toEqual([])
  })
})