From 6892a88e8144eaa95dc0fb4a1cffb76a63776866 Mon Sep 17 00:00:00 2001 From: Dotta Date: Sun, 8 Nov 2026 03:41:40 -0600 Subject: [PATCH] test(evals): keep the trace screencast out of failure evidence A failed agent-chat.track-delegated-work attempt (15 min, live run indicator on screen) produced two ~127 MB trace zips; the 256 MB private allowance refused the whole bundle and no evidence survived. Thirteen launch-1474 cells failed the same way. The bulk was the trace's own JPEG screencast, which does not compress. Keep DOM snapshots, network and sources in the trace and rely on the retained failure video for the visual timeline. Co-Authored-By: Claude Opus 5.5 --- tests/runner-e2e/playwright.config.ts | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tests/runner-e2e/playwright.config.ts b/tests/runner-e2e/playwright.config.ts index 13365db287e..6a89e8f60ef 100644 --- a/tests/runner-e2e/playwright.config.ts +++ b/tests/runner-e2e/playwright.config.ts @@ -62,7 +62,12 @@ export default defineConfig({ actionTimeout: 30_000, navigationTimeout: 30_000, screenshot: process.env.PAPERCLIP_RUNNER_E2E_PUBLIC_MCP === "1" ? "off" : "only-on-failure", - trace: process.env.PAPERCLIP_RUNNER_E2E_PUBLIC_MCP === "1" ? "off" : "retain-on-failure", + // Keep DOM snapshots and network, but not the trace's own screencast: a + // long chat attempt with a live run indicator streamed thousands of JPEG + // frames (incompressible), pushing failure evidence past the 256 MB private + // allowance so no evidence survived. The retained failure video still + // records the visual timeline. + trace: process.env.PAPERCLIP_RUNNER_E2E_PUBLIC_MCP === "1" ? "off" : { mode: "retain-on-failure", screenshots: false }, // A developer-supplied system Chromium keeps the local smoke loop // installation-free; CI's managed browser retains failure video as usual. video: chromiumExecutable || process.env.PAPERCLIP_RUNNER_E2E_PUBLIC_MCP === "1" ? "off" : "retain-on-failure",