From 813af97b3ee2add76363def03bd4a93ae9eab5e9 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Tue, 26 May 2026 21:50:36 +0000 Subject: [PATCH] Append results to job summary --- packages/agent-eval/src/cli.ts | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/packages/agent-eval/src/cli.ts b/packages/agent-eval/src/cli.ts index af568a1..07ce106 100644 --- a/packages/agent-eval/src/cli.ts +++ b/packages/agent-eval/src/cli.ts @@ -10,6 +10,7 @@ import type {Treatment, TreatmentResult} from './treatment' import {run} from './run' const COPILOT_GITHUB_TOKEN = process.env.COPILOT_GITHUB_TOKEN +const GITHUB_STEP_SUMMARY = process.env.GITHUB_STEP_SUMMARY if (!COPILOT_GITHUB_TOKEN) { throw new Error('COPILOT_GITHUB_TOKEN environment variable is required to run the experiments') @@ -335,6 +336,14 @@ function formatResultSummaries(results: Array): string { return formatTable(rows, columns) } +async function appendResultsToJobSummary(resultSummaries: string) { + if (!GITHUB_STEP_SUMMARY) { + return + } + + await fs.appendFile(GITHUB_STEP_SUMMARY, `## Experiment results\n\n\`\`\`\n${resultSummaries}\n\`\`\`\n`) +} + function formatSummaryRow(summary: ResultSummary, level: 'treatment' | 'eval' | 'model'): TableRow { return { Experiment: level === 'treatment' ? summary.experiment : '', @@ -392,6 +401,8 @@ for (const config of experimentConfigs) { } const sortedResults = results.toSorted(compareResults) -console.log(formatResultSummaries(sortedResults)) +const resultSummaries = formatResultSummaries(sortedResults) +console.log(resultSummaries) +await appendResultsToJobSummary(resultSummaries) await fs.writeFile('results.json', JSON.stringify(sortedResults, null, 2))