Convert gitgram/ and aitimemachine/ from embedded git repos (which showed as opaque submodule gitlinks on GitHub) into fully-tracked first-party content. AITM now merges its 7 vendored repos as first-party engines: - memory: beads (Go task DAG) + context7 (docs SDK), unified into saved_contexts - git: vendored C git (bundled binary) + gitnexus (in-process code intelligence) - agentic: a2a (@a2a-js/sdk) + pal (AITM-managed Python subprocess) Includes the full session's product build: Gitgram web/mobile/backend features, AITM website/CLI/MCP, the unified memory layer, engine build tooling (scripts/build-engines.sh, Dockerfile, CI), docs (README, ENGINES.md, ARCHITECTURE.md), and extensive test suites. Build artifacts, node_modules, external/, and gemini-cli are gitignored. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
52 lines
1.8 KiB
TypeScript
52 lines
1.8 KiB
TypeScript
import * as fs from "fs";
|
|
import * as os from "os";
|
|
import * as path from "path";
|
|
import { afterEach, beforeEach, describe, expect, it } from "vitest";
|
|
import { runRedactionBenchmark } from "../src/export/redaction-benchmark.js";
|
|
import { saveConsent } from "../src/auth/consent-policy.js";
|
|
import { TrainingExporter } from "../src/export/training-exporter.js";
|
|
|
|
describe("redaction benchmark metrics", () => {
|
|
let projectDir: string;
|
|
|
|
beforeEach(() => {
|
|
projectDir = fs.mkdtempSync(path.join(os.tmpdir(), "aitm-redaction-bench-"));
|
|
});
|
|
|
|
afterEach(() => {
|
|
fs.rmSync(projectDir, { recursive: true, force: true });
|
|
});
|
|
|
|
it("computes precision/recall/f1 from default benchmark", () => {
|
|
const report = runRedactionBenchmark();
|
|
|
|
expect(report.sampleCount).toBeGreaterThan(0);
|
|
expect(report.metrics.precision).toBeGreaterThanOrEqual(0);
|
|
expect(report.metrics.recall).toBeGreaterThanOrEqual(0);
|
|
expect(report.metrics.f1).toBeGreaterThanOrEqual(0);
|
|
});
|
|
|
|
it("includes redaction quality metrics in training export stats when redaction is enabled", async () => {
|
|
saveConsent(projectDir, {
|
|
policy: {
|
|
operational_capture: true,
|
|
training_export: true,
|
|
},
|
|
});
|
|
|
|
const exporter = new TrainingExporter();
|
|
const result = await exporter.exportTrainingData({
|
|
projectPath: projectDir,
|
|
outputPath: path.join(projectDir, "training.jsonl"),
|
|
redact: true,
|
|
});
|
|
|
|
expect(result.success).toBe(true);
|
|
expect(result.stats.redactionQuality).toBeDefined();
|
|
expect((result.stats.redactionQuality?.f1 ?? 0) >= 0).toBe(true);
|
|
const reportPath = result.stats.redactionQuality?.reportPath;
|
|
expect(typeof reportPath).toBe("string");
|
|
expect(fs.existsSync(reportPath as string)).toBe(true);
|
|
});
|
|
});
|