ThothII/backend/test/workspace-preprocessing-state.test.ts

import { existsSync, mkdtempSync, readFileSync, rmSync, statSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { afterEach, expect, test } from "vitest";
import { PreprocessingStateStore } from "../src/workspaces/preprocessing-state.js";

const roots: string[] = [];

afterEach(() => {
  roots.splice(0).forEach((root) => rmSync(root, { recursive: true, force: true }));
});

function fixture() {
  const dataRoot = mkdtempSync(join(tmpdir(), "tht-preprocessing-state-"));
  roots.push(dataRoot);
  return {
    dataRoot,
    store: new PreprocessingStateStore({ dataRoot, workspaceId: "psd-clinical" }),
  };
}

test("job state creates durable 0600 JSON and enforces same-revision resume", async () => {
  const { store } = fixture();
  const job = await store.beginJob({
    operation: "preprocess dwh",
    workspaceRevision: "a".repeat(40),
    descriptorBlob: "b".repeat(40),
    catalogBlob: "c".repeat(40),
    configDigest: "sha256:config",
    bindingDigest: "sha256:bindings",
    embeddingId: "ollama/qwen3-embedding:0.6b",
    embeddingDimensions: 1024,
  });

  const path = store.jobPath(job.runId);
  expect(existsSync(path)).toBe(true);
  expect(statSync(path).mode & 0o777).toBe(0o600);
  expect(JSON.parse(readFileSync(path, "utf8"))).toMatchObject({
    schemaVersion: 2,
    operation: "preprocess dwh",
    workspaceId: "psd-clinical",
    workspaceRevision: "a".repeat(40),
    descriptorBlob: "b".repeat(40),
    catalogBlob: "c".repeat(40),
    configDigest: "sha256:config",
    bindingDigest: "sha256:bindings",
    embeddingId: "ollama/qwen3-embedding:0.6b",
    embeddingDimensions: 1024,
  });

  await expect(store.beginJob({
    operation: "preprocess dwh",
    runId: job.runId,
    workspaceRevision: "d".repeat(40),
    descriptorBlob: "b".repeat(40),
    catalogBlob: "c".repeat(40),
    configDigest: "sha256:config",
    bindingDigest: "sha256:bindings",
    embeddingId: "ollama/qwen3-embedding:0.6b",
    embeddingDimensions: 1024,
  })).rejects.toMatchObject({ code: "preprocessing_resume_mismatch" });

  await expect(store.beginJob({
    operation: "preprocess dwh",
    runId: job.runId,
    workspaceRevision: "a".repeat(40),
    descriptorBlob: "b".repeat(40),
    catalogBlob: "c".repeat(40),
    configDigest: "sha256:config",
    bindingDigest: "sha256:bindings",
    embeddingId: "ollama/replacement-embedding",
    embeddingDimensions: 1024,
  })).rejects.toMatchObject({ code: "preprocessing_resume_mismatch" });

  const resumed = await store.beginJob({
    operation: "preprocess dwh",
    runId: job.runId,
    workspaceRevision: "a".repeat(40),
    descriptorBlob: "b".repeat(40),
    catalogBlob: "c".repeat(40),
    configDigest: "sha256:config",
    bindingDigest: "sha256:bindings",
    embeddingId: "ollama/qwen3-embedding:0.6b",
    embeddingDimensions: 1024,
  });
  expect(resumed.runId).toBe(job.runId);
});

test("writer lock rejects a concurrent contender and the kernel releases it after holder death", async () => {
  const f = fixture();
  const other = new PreprocessingStateStore({ dataRoot: f.dataRoot, workspaceId: "psd-clinical" });
  const first = await f.store.acquireWriterLock();
  await expect(other.acquireWriterLock()).rejects.toMatchObject({ code: "preprocessing_conflict" });

  process.kill(first.holderPid, "SIGKILL");
  const deadline = Date.now() + 5_000;
  while (Date.now() < deadline) {
    try {
      const recovered = await other.acquireWriterLock();
      await recovered.release();
      return;
    } catch (error) {
      if ((error as { code?: string }).code !== "preprocessing_conflict") throw error;
      await new Promise((resolve) => setTimeout(resolve, 50));
    }
  }
  throw new Error("writer lock was not released after holder death");
});

test("session inventory guard blocks resumable sessions pinned to a different revision", async () => {
  const { store } = fixture();

  await expect(store.assertSessionInventoryCompatible("a".repeat(40), [
    { id: "open-other", status: "closed", archived: false, workspaceRevision: "b".repeat(40) },
  ])).rejects.toMatchObject({ code: "preprocessing_conflict" });

  await expect(store.assertSessionInventoryCompatible("a".repeat(40), [
    { id: "current", status: "open", archived: false, workspaceRevision: "a".repeat(40) },
    { id: "finalized", status: "finalized", archived: false, workspaceRevision: "b".repeat(40) },
    { id: "archived", status: "closed", archived: true, workspaceRevision: "c".repeat(40) },
  ])).resolves.toBeUndefined();
});

test("candidate and review artifacts are digest-bound durable files", async () => {
  const { store } = fixture();
  const runId = "1".repeat(32);
  const candidate = await store.writeFkCandidates(runId, `tables: []
`);
  const review = await store.writeFkReview(runId, {
    reviewedCandidatesDigest: candidate.digest,
    annotationsDigest: "sha256:annotations",
    workspaceRevision: "a".repeat(40),
  });

  expect(candidate.digest).toMatch(/^sha256:[0-9a-f]{64}$/);
  expect(review.digest).toMatch(/^sha256:[0-9a-f]{64}$/);
  expect(store.readFkCandidates(runId)?.digest).toBe(candidate.digest);
  expect(store.readFkReview(runId)?.reviewedCandidatesDigest).toBe(candidate.digest);
});