426e9eeabd
Voice Workbench / headless workbench (mocked backends) (push) Has been cancelled
Voice Workbench / real acoustic lane (nightly, provisioned only) (push) Has been cancelled
ci / test (push) Has been cancelled
ci / lint-and-format (push) Has been cancelled
ci / build (push) Has been cancelled
ci / dev-startup (push) Has been cancelled
gitleaks / gitleaks (push) Has been cancelled
Markdown Links / Relative Markdown Links (push) Has been cancelled
Quality (Extended) / Homepage Build (PR smoke) (push) Has been cancelled
Quality (Extended) / Comment-only diff guard (push) Has been cancelled
Quality (Extended) / Format + Type Safety Ratchet (push) Has been cancelled
Quality (Extended) / Develop Gate (secret scan + UI determinism) (push) Has been cancelled
Quality (Extended) / Develop Gate (lint) (push) Has been cancelled
Chat shell gestures / Chat shell gesture + parity e2e (push) Has been cancelled
Cloud Gateway Discord / Test (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx @biomejs/biome check packages/lifeops-bench/src, benchmark-lint) (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx vitest run --config packages/lifeops-bench/vitest.config.ts --root packages/lifeops-bench --passWithNoTests, benchmark-tests) (push) Has been cancelled
Build Agent Image / build-and-push (push) Has been cancelled
Dev Smoke / bun run dev onboarding chat (push) Has been cancelled
Dev Smoke / Vite HMR dependency-level smoke (push) Has been cancelled
Electrobun Submodule Guard / electrobun gitlink is fetchable (push) Has been cancelled
Publish @elizaos/example-code / check_npm (push) Has been cancelled
Publish @elizaos/example-code / publish_npm (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / verify_version (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / publish_npm (push) Has been cancelled
Sandbox Live Smoke / Sandbox live smoke (push) Has been cancelled
Snap Build & Test / Build Snap (amd64) (push) Has been cancelled
Snap Build & Test / Build Snap (arm64) (push) Has been cancelled
Test Packaging / elizaos CLI global-install smoke (node + bun) (push) Has been cancelled
Cloud Gateway Webhook / Test (push) Has been cancelled
Cloud Tests / lint-and-types (push) Has been cancelled
Cloud Tests / unit-tests (push) Has been cancelled
Cloud Tests / integration-tests (push) Has been cancelled
Cloud Tests / e2e-tests (push) Has been cancelled
CodeQL Advanced / Analyze (javascript-typescript) (push) Has been cancelled
Deploy Apps Worker (Product 2) / Determine environment (push) Has been cancelled
Deploy Apps Worker (Product 2) / Deploy apps worker to apps-control host (${{ needs.determine-env.outputs.environment }}) (push) Has been cancelled
Deploy Eliza Provisioning Worker / Determine environment (push) Has been cancelled
Deploy Eliza Provisioning Worker / Deploy worker to Hetzner host (${{ needs.determine-env.outputs.environment }} @ ${{ needs.determine-env.outputs.deployment_sha }}) (push) Has been cancelled
Dev Smoke / Classify changed paths (push) Has been cancelled
supply-chain / sbom (push) Has been cancelled
supply-chain / vulnerability-scan (push) Has been cancelled
Build, Push & Deploy to Phala Cloud / build-and-push (push) Has been cancelled
Test Packaging / Validate Packaging Configs (push) Has been cancelled
Test Packaging / Build & Test PyPI Package (push) Has been cancelled
Test Packaging / PyPI on Python ${{ matrix.python }} (push) Has been cancelled
Test Packaging / Pack & Test JS Tarballs (push) Has been cancelled
UI Fixture E2E / ui-fixture-e2e (push) Has been cancelled
UI Fixture E2E / fixture-e2e (push) Has been cancelled
UI Story Gate / story-gate (push) Has been cancelled
vault-ci / test (macos-latest) (push) Has been cancelled
vault-ci / test (ubuntu-latest) (push) Has been cancelled
vault-ci / test (windows-latest) (push) Has been cancelled
vault-ci / app-core wiring tests (push) Has been cancelled
verify-patches / verify patches/CHECKSUMS.sha256 (push) Has been cancelled
Voice Benchmark Smoke / voice-emotion fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voiceagentbench fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench-quality unit smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench TypeScript unit (no audio) (push) Has been cancelled
Voice Benchmark Smoke / voice bench smoke summary (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/app-core test bun run --cwd packages/elizaos test bun run --cwd packages/cloud/shared test], app-and-cli) (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/scenario-runner test bun run --cwd packages/vault test bun run --cwd packages/security test bun run --cwd plugins/plugin-coding-tools test], framework-packages) (push) Has been cancelled
Windows CI / windows ([bun run --cwd plugins/plugin-elizacloud test bun run --cwd plugins/plugin-discord test bun run --cwd plugins/plugin-anthropic test bun run --cwd plugins/plugin-openai test bun run --cwd plugins/plugin-app-control test bun run --cwd plugins/pl… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run build --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/agent --concurrency=4 node packages/scripts/run-bash-linux-only.mjs scripts/verify-riscv64-buildpaths.sh node packages/scripts/run… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run typecheck --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/cloud-shared --concurrency=4 bun run --cwd packages/core test bun run --cwd packages/shared test], core-runtime, 75) (push) Has been cancelled
189 lines
4.8 KiB
TypeScript
189 lines
4.8 KiB
TypeScript
// Exercises launch qa check model data.test automation behavior with deterministic script fixtures.
|
|
import fs from "node:fs/promises";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
import { afterEach, describe, expect, it } from "vitest";
|
|
import { checkModelData } from "./check-model-data.mjs";
|
|
|
|
const tempRoots: string[] = [];
|
|
|
|
async function makeRepo() {
|
|
const repoRoot = await fs.mkdtemp(path.join(os.tmpdir(), "model-data-gate-"));
|
|
tempRoots.push(repoRoot);
|
|
await fs.mkdir(path.join(repoRoot, "plugins", "app-training", "datasets"), {
|
|
recursive: true,
|
|
});
|
|
return repoRoot;
|
|
}
|
|
|
|
async function writeDataset(repoRoot: string, name: string, rows: unknown[]) {
|
|
const datasetPath = path.join(
|
|
repoRoot,
|
|
"plugins",
|
|
"app-training",
|
|
"datasets",
|
|
`${name}.jsonl`,
|
|
);
|
|
await fs.writeFile(
|
|
datasetPath,
|
|
`${rows.map((row) => JSON.stringify(row)).join("\n")}\n`,
|
|
);
|
|
return datasetPath;
|
|
}
|
|
|
|
afterEach(async () => {
|
|
await Promise.all(
|
|
tempRoots
|
|
.splice(0)
|
|
.map((root) => fs.rm(root, { recursive: true, force: true })),
|
|
);
|
|
});
|
|
|
|
describe("model/data gate", () => {
|
|
it("passes a valid app-training JSONL dataset with matching metadata", async () => {
|
|
const repoRoot = await makeRepo();
|
|
await writeDataset(repoRoot, "valid", [
|
|
{
|
|
messages: [
|
|
{ role: "system", content: "Be brief." },
|
|
{ role: "user", content: "hello" },
|
|
{ role: "model", content: "hi" },
|
|
],
|
|
reward: 1,
|
|
metadata: { caseId: "c-1" },
|
|
},
|
|
]);
|
|
await fs.writeFile(
|
|
path.join(
|
|
repoRoot,
|
|
"plugins",
|
|
"app-training",
|
|
"datasets",
|
|
"valid.meta.json",
|
|
),
|
|
JSON.stringify({
|
|
rowCount: 1,
|
|
caseCount: 1,
|
|
passCount: 1,
|
|
failCount: 0,
|
|
rejectedCount: 0,
|
|
}),
|
|
);
|
|
|
|
const result = checkModelData({ repoRoot });
|
|
|
|
expect(result.ok).toBe(true);
|
|
expect(result.totals.rows).toBe(1);
|
|
expect(result.files[0]?.metadataFile).toBe(
|
|
"plugins/app-training/datasets/valid.meta.json",
|
|
);
|
|
});
|
|
|
|
it("fails invalid JSONL rows", async () => {
|
|
const repoRoot = await makeRepo();
|
|
await fs.writeFile(
|
|
path.join(
|
|
repoRoot,
|
|
"plugins",
|
|
"app-training",
|
|
"datasets",
|
|
"invalid.jsonl",
|
|
),
|
|
'{"messages": [}\n',
|
|
);
|
|
|
|
const result = checkModelData({ repoRoot });
|
|
|
|
expect(result.ok).toBe(false);
|
|
expect(result.errors).toContainEqual(
|
|
expect.objectContaining({
|
|
type: "invalid-jsonl",
|
|
file: "plugins/app-training/datasets/invalid.jsonl",
|
|
line: 1,
|
|
}),
|
|
);
|
|
});
|
|
|
|
it("fails rows missing required messages fields", async () => {
|
|
const repoRoot = await makeRepo();
|
|
await writeDataset(repoRoot, "missing-fields", [
|
|
{
|
|
messages: [{ role: "system", content: "No user or answer." }],
|
|
},
|
|
]);
|
|
|
|
const result = checkModelData({ repoRoot });
|
|
|
|
expect(result.ok).toBe(false);
|
|
expect(result.errors).toEqual(
|
|
expect.arrayContaining([
|
|
expect.objectContaining({
|
|
type: "invalid-row-schema",
|
|
message: expect.stringContaining("user message"),
|
|
}),
|
|
expect.objectContaining({
|
|
type: "invalid-row-schema",
|
|
message: expect.stringContaining("model or assistant message"),
|
|
}),
|
|
]),
|
|
);
|
|
});
|
|
|
|
it("fails secret-like strings in dataset rows", async () => {
|
|
const repoRoot = await makeRepo();
|
|
await writeDataset(repoRoot, "secret", [
|
|
{
|
|
messages: [
|
|
{ role: "user", content: "use api_key=abcdefghijklmnop1234567890" },
|
|
{ role: "assistant", content: "I will not store that." },
|
|
],
|
|
},
|
|
]);
|
|
|
|
const result = checkModelData({ repoRoot });
|
|
|
|
expect(result.ok).toBe(false);
|
|
expect(result.totals.secretHits).toBeGreaterThan(0);
|
|
expect(result.errors).toContainEqual(
|
|
expect.objectContaining({
|
|
type: "secret-like-string",
|
|
label: "credential-assignment",
|
|
}),
|
|
);
|
|
});
|
|
|
|
it("fails metadata row-count mismatches", async () => {
|
|
const repoRoot = await makeRepo();
|
|
await writeDataset(repoRoot, "mismatch", [
|
|
{
|
|
messages: [
|
|
{ role: "user", content: "one" },
|
|
{ role: "model", content: "two" },
|
|
],
|
|
},
|
|
]);
|
|
await fs.writeFile(
|
|
path.join(
|
|
repoRoot,
|
|
"plugins",
|
|
"app-training",
|
|
"datasets",
|
|
"mismatch.meta.json",
|
|
),
|
|
JSON.stringify({ rowCount: 2 }),
|
|
);
|
|
|
|
const result = checkModelData({ repoRoot });
|
|
|
|
expect(result.ok).toBe(false);
|
|
expect(result.errors).toContainEqual(
|
|
expect.objectContaining({
|
|
type: "metadata-row-count-mismatch",
|
|
field: "rowCount",
|
|
expected: 1,
|
|
actual: 2,
|
|
}),
|
|
);
|
|
});
|
|
});
|