2026-10-25T17:26:18.144Z Diffinery runner: job e2e (End-to-end (agent reviews, tasks, Today)) for codician/diffinery@36263e52cb30 2026-10-25T17:26:18.160Z Runner: image diffinery-runner:4d3bf17f06575e64ab4155b3, in sin20, APAC, container 8cd52aca2c4bb4daacecb9995bc6fe9cd2bb9060ec6bc58cabc33d8e3fe5369d 2026-10-25T17:26:18.160Z Runner size: large (4 vCPU, 12 GiB of memory, 20 GB of disk), this job uses what a smaller runner doesn't have; runs-on: diffinery-large (or -medium, -small, -tiny) sets a size 2026-10-25T17:26:18.160Z Host: AMD EPYC (family 25, model 17), 4 vCPUs, 2546 MHz 2026-10-25T17:26:18.161Z Workspace: /workspace/diffinery 2026-10-25T17:26:18.392Z ##[group]Run actions/checkout@v4 2026-10-25T17:26:18.392Z ##[endgroup] 2026-10-25T17:26:18.394Z Syncing repository: codician/diffinery 2026-10-25T17:26:18.475Z Fetching the repository (depth 1) 2026-10-25T17:26:19.988Z remote: Enumerating objects: 875, done. 2026-10-25T17:26:20.955Z Receiving objects: 0% (1/875) Receiving objects: 1% (9/875) Receiving objects: 2% (18/875) Receiving objects: 3% (27/875) Receiving objects: 4% (35/875) Receiving objects: 5% (44/875) Receiving objects: 6% (53/875) Receiving objects: 7% (62/875) Receiving objects: 8% (70/875) Receiving objects: 9% (79/875) Receiving objects: 10% (88/875) Receiving objects: 11% (97/875) Receiving objects: 12% (105/875) Receiving objects: 13% (114/875) Receiving objects: 14% (123/875) Receiving objects: 15% (132/875) Receiving objects: 16% (140/875) Receiving objects: 17% (149/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 18% (158/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 19% (167/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 20% (175/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 21% (184/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 22% (193/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 23% (202/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 24% (210/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 25% (219/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 26% (228/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 27% (237/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 28% (245/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 29% (254/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 30% (263/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 31% (272/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 32% (280/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 33% (289/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 34% (298/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 35% (307/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 36% (315/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 37% (324/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 38% (333/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 39% (342/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 40% (350/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 41% (359/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 42% (368/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 43% (377/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 44% (385/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 45% (394/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 46% (403/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 47% (412/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 48% (420/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 49% (429/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 50% (438/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 51% (447/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 52% (455/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 53% (464/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 54% (473/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 55% (482/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 56% (490/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 57% (499/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 58% (508/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 59% (517/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 60% (525/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 61% (534/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 62% (543/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 63% (552/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 64% (560/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 65% (569/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 66% (578/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 67% (587/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 68% (595/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 69% (604/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 70% (613/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 71% (622/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 72% (630/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 73% (639/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 74% (648/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 75% (657/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 76% (665/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 77% (674/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 78% (683/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 79% (692/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 80% (700/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 81% (709/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 82% (718/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 83% (727/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 84% (735/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 85% (744/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 86% (753/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 87% (762/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 88% (770/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 89% (779/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 90% (788/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 91% (797/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 92% (805/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 93% (814/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 94% (823/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 95% (832/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 96% (840/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 97% (849/875), 579.82 KiB | 1.12 MiB/s remote: Total 875 (delta 0), reused 875 (delta 0) 2026-10-25T17:26:20.958Z Receiving objects: 98% (858/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 99% (867/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 100% (875/875), 579.82 KiB | 1.12 MiB/s Receiving objects: 100% (875/875), 3.80 MiB | 4.15 MiB/s, done. 2026-10-25T17:26:20.969Z From https://diffinery.com/codician/diffinery 2026-10-25T17:26:20.969Z * [new ref] 36263e52cb3006fee980a92ad3ee3e6fcae6688d -> origin/diffinery-checkout 2026-10-25T17:26:21.084Z Note: switching to '36263e52cb3006fee980a92ad3ee3e6fcae6688d'. 2026-10-25T17:26:21.084Z 2026-10-25T17:26:21.084Z You are in 'detached HEAD' state. You can look around, make experimental 2026-10-25T17:26:21.084Z changes and commit them, and you can discard any commits you make in this 2026-10-25T17:26:21.084Z state without impacting any branches by switching back to a branch. 2026-10-25T17:26:21.084Z 2026-10-25T17:26:21.084Z If you want to create a new branch to retain commits you create, you may 2026-10-25T17:26:21.084Z do so (now or later) by using -c with the switch command. Example: 2026-10-25T17:26:21.084Z 2026-10-25T17:26:21.084Z git switch -c 2026-10-25T17:26:21.084Z 2026-10-25T17:26:21.084Z Or undo this operation with: 2026-10-25T17:26:21.084Z 2026-10-25T17:26:21.084Z git switch - 2026-10-25T17:26:21.084Z 2026-10-25T17:26:21.084Z Turn off this advice by setting config variable advice.detachedHead to false 2026-10-25T17:26:21.084Z 2026-10-25T17:26:21.084Z HEAD is now at 36263e5 Merge 503bdef8da45623fa39b484f2ad2446747d67634 into db0badff555154599b606f2bbd04b6f811dca3e9 2026-10-25T17:26:21.090Z HEAD is now at 36263e52cb3006fee980a92ad3ee3e6fcae6688d 2026-10-25T17:26:21.551Z Download action repository 'pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1' 2026-10-25T17:26:23.686Z ##[group]Run pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1 2026-10-25T17:26:23.686Z with: 2026-10-25T17:26:23.686Z dest: ~/setup-pnpm 2026-10-25T17:26:23.686Z run_install: null 2026-10-25T17:26:23.686Z cache: false 2026-10-25T17:26:23.686Z cache_dependency_path: pnpm-lock.yaml 2026-10-25T17:26:23.686Z package_json_file: package.json 2026-10-25T17:26:23.686Z standalone: false 2026-10-25T17:26:23.686Z ##[endgroup] 2026-10-25T17:26:23.932Z ##[group]Running self-installer... 2026-10-25T17:26:24.974Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-25T17:26:24.984Z Packages: +1 2026-10-25T17:26:24.984Z + 2026-10-25T17:26:25.648Z Progress: resolved 1, reused 0, downloaded 1, added 1, done 2026-10-25T17:26:25.697Z 2026-10-25T17:26:25.697Z dependencies: 2026-10-25T17:26:25.697Z + pnpm 10.28.0 (12.15.0 is available) 2026-10-25T17:26:25.697Z 2026-10-25T17:26:25.705Z Done in 1.4s 2026-10-25T17:26:25.735Z ##[endgroup] 2026-10-25T17:26:25.735Z Installation Completed! 2026-10-25T17:26:26.193Z ##[group]Run actions/setup-node@v4 2026-10-25T17:26:26.193Z with: 2026-10-25T17:26:26.193Z node-version: 22 2026-10-25T17:26:26.193Z cache: pnpm 2026-10-25T17:26:26.193Z ##[endgroup] 2026-10-25T17:26:26.204Z Found in cache @ 22.22.0 (pre-installed node satisfies '22') 2026-10-25T17:26:28.389Z Cache Size: ~216 MB (226934503 B) 2026-10-25T17:26:34.147Z Cache restored from key: node-cache-Linux-x64-pnpm-42d02c0263a3b5f911ed6ae8e9210922b97166ca02e60b2c70c55dfa1f00371b 2026-10-25T17:26:34.559Z ##[group]Run pnpm install --frozen-lockfile 2026-10-25T17:26:34.559Z ##[endgroup] 2026-10-25T17:26:35.046Z Scope: all 8 workspace projects 2026-10-25T17:26:35.131Z Lockfile is up to date, resolution step is skipped 2026-10-25T17:26:35.193Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-25T17:26:35.251Z Packages: +251 2026-10-25T17:26:35.251Z ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2026-10-25T17:26:36.195Z Progress: resolved 251, reused 245, downloaded 0, added 165 2026-10-25T17:26:37.195Z Progress: resolved 251, reused 245, downloaded 0, added 243 2026-10-25T17:26:37.372Z Progress: resolved 251, reused 245, downloaded 0, added 251, done 2026-10-25T17:26:37.579Z .../node_modules/workerd postinstall$ node install.js 2026-10-25T17:26:37.581Z .../esbuild@0.25.11/node_modules/esbuild postinstall$ node install.js 2026-10-25T17:26:37.595Z .../esbuild@0.28.1/node_modules/esbuild postinstall$ node install.js 2026-10-25T17:26:37.608Z .../esbuild@0.25.12/node_modules/esbuild postinstall$ node install.js 2026-10-25T17:26:37.609Z .../node_modules/workerd postinstall$ node install.js 2026-10-25T17:26:37.847Z .../esbuild@0.28.1/node_modules/esbuild postinstall: Done 2026-10-25T17:26:37.852Z .../esbuild@0.28.2/node_modules/esbuild postinstall$ node install.js 2026-10-25T17:26:37.855Z .../esbuild@0.25.11/node_modules/esbuild postinstall: Done 2026-10-25T17:26:37.863Z .../node_modules/workerd postinstall: Done 2026-10-25T17:26:38.030Z .../node_modules/workerd postinstall: Done 2026-10-25T17:26:38.041Z .../esbuild@0.25.12/node_modules/esbuild postinstall: Done 2026-10-25T17:26:38.059Z .../esbuild@0.28.2/node_modules/esbuild postinstall: Done 2026-10-25T17:26:38.650Z 2026-10-25T17:26:38.650Z devDependencies: 2026-10-25T17:26:38.650Z + turbo 2.11.7 2026-10-25T17:26:38.650Z + typescript 5.9.3 2026-10-25T17:26:38.650Z 2026-10-25T17:26:39.221Z Done in 4.5s using pnpm v10.28.0 2026-10-25T17:26:39.671Z ##[group]Run pnpm -r --if-present build 2026-10-25T17:26:39.671Z ##[endgroup] 2026-10-25T17:26:40.069Z Scope: 7 of 8 workspace projects 2026-10-25T17:26:40.074Z apps/cli build$ esbuild src/bin.ts --bundle --platform=node --target=node22 --format=esm --outfile=dist/diffinery.mjs "--banner:js=#!/usr/bin/env node 2026-10-25T17:26:40.074Z import { createRequire as __diffineryCreateRequire } from 'node:module'; const require = __diffineryCreateRequire(import.meta.url);" 2026-10-25T17:26:40.076Z apps/diffinery build$ node islands/build.mjs && node scripts/build-docs.mjs 2026-10-25T17:26:40.076Z containers/runner build$ esbuild src/main.ts --bundle --platform=node --target=node22 --format=esm --outfile=dist/agent.mjs --external:bufferutil --external:utf-8-validate "--banner:js=import { createRequire as __diffineryCreateRequire } from 'node:module'; const require = __diffineryCreateRequire(import.meta.url);" 2026-10-25T17:26:40.187Z apps/cli build: dist/diffinery.mjs 468.9kb 2026-10-25T17:26:40.189Z apps/cli build: ⚡ Done in 82ms 2026-10-25T17:26:40.201Z apps/cli build: Done 2026-10-25T17:26:40.228Z containers/runner build: dist/agent.mjs 684.1kb 2026-10-25T17:26:40.229Z containers/runner build: ⚡ Done in 113ms 2026-10-25T17:26:40.233Z containers/runner build: Done 2026-10-25T17:26:42.562Z apps/diffinery build: islands: kumo.js 466 KB, kumo.css 149 KB, terminal.js 286 KB 2026-10-25T17:26:42.968Z apps/diffinery build: docs: 84 pages (+2 generated at runtime), 19 site pages, 11 images, CLI 0.1.0 (250 KiB), editor extension 0.1.1 (20 KiB), JetBrains plugin 0.1.0 (64 KiB), Claude Code plugins diffinery 0.1.3, diffinery-ci 0.2.3 2026-10-25T17:26:42.983Z apps/diffinery build: Done 2026-10-25T17:26:43.607Z ##[group]Run as_root() { if [ "$(id -u)" = 0 ]; then "$@"; else sudo "$@"; fi; } 2026-10-25T17:26:43.607Z if ! command -v bwrap >/dev/null; then 2026-10-25T17:26:43.607Z as_root apt-get install -y --no-install-recommends bubblewrap || { as_root apt-get update -qq && as_root apt-get install -y --no-install-recommends bubblewrap; } 2026-10-25T17:26:43.607Z fi 2026-10-25T17:26:43.607Z as_root sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 2>/dev/null || true 2026-10-25T17:26:43.607Z bwrap --unshare-all --ro-bind / / --dev /dev --proc /proc -- true 2026-10-25T17:26:43.607Z ##[endgroup] 2026-10-25T17:26:44.096Z ##[group]Run # Shards of similar length; a new test file runs in "rest" unless it's added to another. 2026-10-25T17:26:44.096Z core='/e2e\.test\.mjs$' 2026-10-25T17:26:44.096Z agents='/(agentic|review|tasks)\.test\.mjs$' 2026-10-25T17:26:44.096Z # security.test.mjs, security-*.test.mjs (security-txt's too) and status.test.mjs. 2026-10-25T17:26:44.096Z security='/(security(-[a-z-]+)?|status)\.test\.mjs$' 2026-10-25T17:26:44.096Z # The core file's real histories and large pushes take minutes each (jquery's alone 2 to 3 on 2026-10-25T17:26:44.096Z # Diffinery's runners): two shards of their own, so no part of the file runs into node's 2026-10-25T17:26:44.096Z # per-file timeout, which is the --test-timeout here. 2026-10-25T17:26:44.096Z histories='^real histories:' 2026-10-25T17:26:44.096Z large='^(large files|large pushes):' 2026-10-25T17:26:44.096Z opts=(--test-timeout=600000) 2026-10-25T17:26:44.096Z case "agents" in 2026-10-25T17:26:44.096Z core) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-skip-pattern="$histories" --test-skip-pattern="$large") ;; 2026-10-25T17:26:44.096Z histories) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts=(--test-timeout=900000 --test-name-pattern="$histories") ;; 2026-10-25T17:26:44.096Z large) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-name-pattern="$large") ;; 2026-10-25T17:26:44.097Z agents) files=$(ls test/e2e/*.test.mjs | grep -E "$agents") ;; 2026-10-25T17:26:44.097Z security) files=$(ls test/e2e/*.test.mjs | grep -E "$security") ;; 2026-10-25T17:26:44.097Z *) files=$(ls test/e2e/*.test.mjs | grep -vE "$core|$agents|$security") ;; 2026-10-25T17:26:44.097Z esac 2026-10-25T17:26:44.097Z echo "$files" 2026-10-25T17:26:44.097Z # Two files at a time: each starts its own local server on its own port, database and 2026-10-25T17:26:44.097Z # directory, so they don't share state, and a file's server mostly keeps one core busy. 2026-10-25T17:26:44.097Z node --test --test-concurrency=2 "${opts[@]}" $files 2026-10-25T17:26:44.097Z ##[endgroup] 2026-10-25T17:26:44.120Z test/e2e/agentic.test.mjs 2026-10-25T17:26:44.120Z test/e2e/review.test.mjs 2026-10-25T17:26:44.120Z test/e2e/tasks.test.mjs 2026-10-25T17:26:44.184Z TAP version 13 2026-10-25T17:27:13.898Z # Subtest: Today: what needs you, your agents' work and what landed 2026-10-25T17:27:13.898Z ok 1 - Today: what needs you, your agents' work and what landed 2026-10-25T17:27:13.898Z --- 2026-10-25T17:27:13.898Z duration_ms: 29528.727979 2026-10-25T17:27:13.898Z type: 'test' 2026-10-25T17:27:13.898Z ... 2026-10-25T17:28:03.959Z # Subtest: agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-25T17:28:03.959Z ok 2 - agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-25T17:28:03.959Z --- 2026-10-25T17:28:03.959Z duration_ms: 79599.277623 2026-10-25T17:28:03.959Z type: 'test' 2026-10-25T17:28:03.959Z ... 2026-10-25T17:28:19.550Z # Subtest: agent review: Fix it, asking for a review, and who may 2026-10-25T17:28:19.551Z ok 3 - agent review: Fix it, asking for a review, and who may 2026-10-25T17:28:19.551Z --- 2026-10-25T17:28:19.551Z duration_ms: 15590.653586 2026-10-25T17:28:19.551Z type: 'test' 2026-10-25T17:28:19.551Z ... 2026-10-25T17:29:10.733Z # Subtest: agent review: spend limits per review (requests, tokens) and per repository 2026-10-25T17:29:10.733Z ok 4 - agent review: spend limits per review (requests, tokens) and per repository 2026-10-25T17:29:10.733Z --- 2026-10-25T17:29:10.733Z duration_ms: 51124.835853 2026-10-25T17:29:10.733Z type: 'test' 2026-10-25T17:29:10.733Z ... 2026-10-25T17:29:22.320Z # Subtest: model keys: write-only, browser session only, with an opt-in 2026-10-25T17:29:22.320Z ok 5 - model keys: write-only, browser session only, with an opt-in 2026-10-25T17:29:22.320Z --- 2026-10-25T17:29:22.320Z duration_ms: 6967.179547 2026-10-25T17:29:22.321Z type: 'test' 2026-10-25T17:29:22.321Z ... 2026-10-25T17:29:22.321Z # Subtest: an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-25T17:29:22.321Z ok 6 - an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-25T17:29:22.321Z --- 2026-10-25T17:29:22.321Z duration_ms: 9438.037067 2026-10-25T17:29:22.321Z type: 'test' 2026-10-25T17:29:22.321Z ... 2026-10-25T17:29:22.321Z # Subtest: task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-25T17:29:22.321Z ok 7 - task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-25T17:29:22.322Z --- 2026-10-25T17:29:22.322Z duration_ms: 3998.042337 2026-10-25T17:29:22.322Z type: 'test' 2026-10-25T17:29:22.322Z ... 2026-10-25T17:29:22.322Z # Subtest: a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-25T17:29:22.322Z ok 8 - a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-25T17:29:22.322Z --- 2026-10-25T17:29:22.322Z duration_ms: 17300.617155 2026-10-25T17:29:22.322Z type: 'test' 2026-10-25T17:29:22.322Z ... 2026-10-25T17:29:22.322Z # Subtest: a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-25T17:29:22.322Z ok 9 - a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-25T17:29:22.322Z --- 2026-10-25T17:29:22.322Z duration_ms: 26353.479011 2026-10-25T17:29:22.322Z type: 'test' 2026-10-25T17:29:22.322Z ... 2026-10-25T17:29:22.323Z # Subtest: plan first: a read-only plan run, then approve, change or split the plan 2026-10-25T17:29:22.323Z ok 10 - plan first: a read-only plan run, then approve, change or split the plan 2026-10-25T17:29:22.323Z --- 2026-10-25T17:29:22.323Z duration_ms: 24012.360151 2026-10-25T17:29:22.323Z type: 'test' 2026-10-25T17:29:22.323Z ... 2026-10-25T17:29:22.323Z # Subtest: best of N: attempts run side by side on their own branches, then one is picked 2026-10-25T17:29:22.323Z ok 11 - best of N: attempts run side by side on their own branches, then one is picked 2026-10-25T17:29:22.323Z --- 2026-10-25T17:29:22.323Z duration_ms: 9425.639407 2026-10-25T17:29:22.323Z type: 'test' 2026-10-25T17:29:22.323Z ... 2026-10-25T17:29:22.323Z # Subtest: verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-25T17:29:22.323Z ok 12 - verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-25T17:29:22.323Z --- 2026-10-25T17:29:22.323Z duration_ms: 12662.835055 2026-10-25T17:29:22.323Z type: 'test' 2026-10-25T17:29:22.323Z ... 2026-10-25T17:29:22.325Z # Subtest: organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-25T17:29:22.325Z ok 13 - organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-25T17:29:22.325Z --- 2026-10-25T17:29:22.325Z duration_ms: 18050.853008 2026-10-25T17:29:22.325Z type: 'test' 2026-10-25T17:29:22.325Z ... 2026-10-25T17:29:24.206Z # Subtest: losing access to the agent stops the task 2026-10-25T17:29:24.206Z ok 14 - losing access to the agent stops the task 2026-10-25T17:29:24.206Z --- 2026-10-25T17:29:24.206Z duration_ms: 1659.594749 2026-10-25T17:29:24.206Z type: 'test' 2026-10-25T17:29:24.206Z ... 2026-10-25T17:29:24.224Z 1..14 2026-10-25T17:29:24.224Z # tests 14 2026-10-25T17:29:24.224Z # suites 0 2026-10-25T17:29:24.225Z # pass 14 2026-10-25T17:29:24.225Z # fail 0 2026-10-25T17:29:24.225Z # cancelled 0 2026-10-25T17:29:24.225Z # skipped 0 2026-10-25T17:29:24.225Z # todo 0 2026-10-25T17:29:24.225Z # duration_ms 160061.761514 2026-10-25T17:29:24.645Z Cache hit occurred on the primary key node-cache-Linux-x64-pnpm-42d02c0263a3b5f911ed6ae8e9210922b97166ca02e60b2c70c55dfa1f00371b, not saving cache. 2026-10-25T17:29:25.360Z Pruning is unnecessary. 2026-10-25T17:29:25.787Z Removing persisted credentials 2026-10-25T17:29:26.000Z Host: 3% of the vCPUs' time went to other work on the host (steal) 2026-10-25T17:29:26.000Z Job completed with conclusion: success 2026-10-25T17:29:26.001Z Resources: 1.0 of 4 vCPUs busy on average (2.4 at the 95th percentile), peak memory 4.0 GiB of 11.9 GiB, peak disk 2.2 GB of 19.2 GB