Files
united-workforce/packages/eval/src/commands/report.ts
T
xiaoju ae81e4b5ac
CI / check (pull_request) Successful in 1m44s
feat: eval report, diff, list commands
Implement the 3 read commands for eval framework:

- report: read eval-run from CAS, render formatted text
  (task, overall, config, judges table, thread ID)
- diff: side-by-side comparison with ▲/▼ delta indicators
  and config change markers
- list: scan @uwf/eval/*/latest variables, sort by timestamp desc,
  --task filter, --limit pagination

Architecture: pure formatting functions (format.ts) + data access
(read.ts) + thin CLI handlers. Types in types.ts.

11 new tests (formatReport, formatDiff, formatList, selectEntries)

Refs #72
2026-06-05 00:19:25 +00:00

33 lines
1.1 KiB
TypeScript

import { createLogger } from "@united-workforce/util";
import type { Command } from "commander";
import { createEvalStore } from "../storage/index.js";
import { formatReport } from "./format.js";
import { readEvalRun } from "./read.js";
const log = createLogger({ sink: { kind: "stderr" } });
const LOG_REPORT = "R7QP2M4K";
export function registerReportCommand(program: Command): void {
program
.command("report <hash>")
.description("Show eval run results")
.action(async (hash: string) => {
try {
const evalStore = await createEvalStore();
const payload = readEvalRun(evalStore, hash);
if (payload === null) {
process.stderr.write(`eval run not found: ${hash}\n`);
process.exitCode = 1;
return;
}
log(LOG_REPORT, `report task=${payload.task} hash=${hash}`);
process.stdout.write(formatReport(payload, hash));
} catch (e) {
const message = e instanceof Error ? e.message : String(e);
process.stderr.write(`${message}\n`);
process.exitCode = 1;
}
});
}