2026-10-26T15:05:13.042Z Diffinery runner: job e2e (End-to-end (agent reviews, tasks, Today)) for codician/diffinery@3dc94d14c81f 2026-10-26T15:05:13.058Z Runner: image diffinery-runner:bca05d12d6c57337029615de, in lax10, WNAM, container 552fa6fd98201af75e9a798c9a145c83023954f753d56f33cd8a11b0289971cf 2026-10-26T15:05:13.058Z 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 2026-10-26T15:05:13.058Z Host: AMD EPYC (family 25, model 17), 4 vCPUs, 2550 MHz 2026-10-26T15:05:13.058Z Workspace: /workspace/diffinery 2026-10-26T15:05:13.322Z ##[group]Run actions/checkout@v4 2026-10-26T15:05:13.322Z ##[endgroup] 2026-10-26T15:05:13.326Z Syncing repository: codician/diffinery 2026-10-26T15:05:13.422Z Fetching the repository (depth 1) 2026-10-26T15:05:14.863Z remote: Enumerating objects: 919, done. 2026-10-26T15:05:16.273Z Receiving objects: 0% (1/919) Receiving objects: 1% (10/919) Receiving objects: 2% (19/919) Receiving objects: 3% (28/919) Receiving objects: 4% (37/919) Receiving objects: 5% (46/919) Receiving objects: 6% (56/919) Receiving objects: 7% (65/919) Receiving objects: 8% (74/919) Receiving objects: 9% (83/919) Receiving objects: 10% (92/919) Receiving objects: 11% (102/919) Receiving objects: 12% (111/919) Receiving objects: 13% (120/919) Receiving objects: 14% (129/919) Receiving objects: 15% (138/919) Receiving objects: 16% (148/919) Receiving objects: 17% (157/919) Receiving objects: 18% (166/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 19% (175/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 20% (184/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 21% (193/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 22% (203/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 23% (212/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 24% (221/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 25% (230/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 26% (239/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 27% (249/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 28% (258/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 29% (267/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 30% (276/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 31% (285/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 32% (295/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 33% (304/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 34% (313/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 35% (322/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 36% (331/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 37% (341/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 38% (350/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 39% (359/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 40% (368/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 41% (377/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 42% (386/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 43% (396/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 44% (405/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 45% (414/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 46% (423/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 47% (432/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 48% (442/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 49% (451/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 50% (460/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 51% (469/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 52% (478/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 53% (488/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 54% (497/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 55% (506/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 56% (515/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 57% (524/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 58% (534/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 59% (543/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 60% (552/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 61% (561/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 62% (570/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 63% (579/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 64% (589/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 65% (598/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 66% (607/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 67% (616/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 68% (625/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 69% (635/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 70% (644/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 71% (653/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 72% (662/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 73% (671/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 74% (681/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 75% (690/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 76% (699/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 77% (708/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 78% (717/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 79% (727/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 80% (736/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 81% (745/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 82% (754/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 83% (763/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 84% (772/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 85% (782/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 86% (791/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 86% (796/919), 835.73 KiB | 1.60 MiB/s Receiving objects: 87% (800/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 88% (809/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 89% (818/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 90% (828/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 91% (837/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 92% (846/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 93% (855/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 94% (864/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 95% (874/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 96% (883/919), 5.25 MiB | 5.15 MiB/s remote: Total 919 (delta 0), reused 919 (delta 0) 2026-10-26T15:05:16.275Z Receiving objects: 97% (892/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 98% (901/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 99% (910/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 100% (919/919), 5.25 MiB | 5.15 MiB/s Receiving objects: 100% (919/919), 5.83 MiB | 5.61 MiB/s, done. 2026-10-26T15:05:16.294Z From https://diffinery.com/codician/diffinery 2026-10-26T15:05:16.294Z * [new ref] 3dc94d14c81ff03a14269521b86b8616288cad29 -> origin/diffinery-checkout 2026-10-26T15:05:16.433Z Note: switching to '3dc94d14c81ff03a14269521b86b8616288cad29'. 2026-10-26T15:05:16.433Z 2026-10-26T15:05:16.433Z You are in 'detached HEAD' state. You can look around, make experimental 2026-10-26T15:05:16.433Z changes and commit them, and you can discard any commits you make in this 2026-10-26T15:05:16.433Z state without impacting any branches by switching back to a branch. 2026-10-26T15:05:16.433Z 2026-10-26T15:05:16.433Z If you want to create a new branch to retain commits you create, you may 2026-10-26T15:05:16.433Z do so (now or later) by using -c with the switch command. Example: 2026-10-26T15:05:16.433Z 2026-10-26T15:05:16.433Z git switch -c 2026-10-26T15:05:16.433Z 2026-10-26T15:05:16.433Z Or undo this operation with: 2026-10-26T15:05:16.433Z 2026-10-26T15:05:16.433Z git switch - 2026-10-26T15:05:16.433Z 2026-10-26T15:05:16.433Z Turn off this advice by setting config variable advice.detachedHead to false 2026-10-26T15:05:16.433Z 2026-10-26T15:05:16.433Z HEAD is now at 3dc94d1 Merge 062b4c3e2dbe44921a3ce763031743a03b2d49ac into bc4d1baf43da951271a59361559d2c71c78de642 2026-10-26T15:05:16.439Z HEAD is now at 3dc94d14c81ff03a14269521b86b8616288cad29 2026-10-26T15:05:16.841Z Download action repository 'pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1' 2026-10-26T15:05:17.210Z ##[group]Run pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1 2026-10-26T15:05:17.211Z with: 2026-10-26T15:05:17.211Z dest: ~/setup-pnpm 2026-10-26T15:05:17.211Z run_install: null 2026-10-26T15:05:17.211Z cache: false 2026-10-26T15:05:17.211Z cache_dependency_path: pnpm-lock.yaml 2026-10-26T15:05:17.211Z package_json_file: package.json 2026-10-26T15:05:17.211Z standalone: false 2026-10-26T15:05:17.211Z ##[endgroup] 2026-10-26T15:05:17.424Z ##[group]Running self-installer... 2026-10-26T15:05:18.244Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-26T15:05:18.255Z Packages: +1 2026-10-26T15:05:18.255Z + 2026-10-26T15:05:18.907Z Progress: resolved 1, reused 0, downloaded 1, added 1, done 2026-10-26T15:05:18.962Z 2026-10-26T15:05:18.962Z dependencies: 2026-10-26T15:05:18.962Z + pnpm 10.28.0 (12.15.0 is available) 2026-10-26T15:05:18.962Z 2026-10-26T15:05:18.973Z Done in 1.2s 2026-10-26T15:05:19.008Z ##[endgroup] 2026-10-26T15:05:19.008Z Installation Completed! 2026-10-26T15:05:19.403Z ##[group]Run actions/setup-node@v4 2026-10-26T15:05:19.403Z with: 2026-10-26T15:05:19.403Z node-version: 22 2026-10-26T15:05:19.403Z cache: pnpm 2026-10-26T15:05:19.403Z ##[endgroup] 2026-10-26T15:05:19.413Z Found in cache @ 22.22.0 (pre-installed node satisfies '22') 2026-10-26T15:05:20.678Z Cache Size: ~216 MB (226934503 B) 2026-10-26T15:05:27.158Z Cache restored from key: node-cache-Linux-x64-pnpm-42d02c0263a3b5f911ed6ae8e9210922b97166ca02e60b2c70c55dfa1f00371b 2026-10-26T15:05:27.552Z ##[group]Run pnpm install --frozen-lockfile 2026-10-26T15:05:27.552Z ##[endgroup] 2026-10-26T15:05:28.100Z Scope: all 8 workspace projects 2026-10-26T15:05:28.196Z Lockfile is up to date, resolution step is skipped 2026-10-26T15:05:28.277Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-26T15:05:28.322Z Packages: +251 2026-10-26T15:05:28.322Z ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2026-10-26T15:05:29.285Z Progress: resolved 251, reused 245, downloaded 0, added 143 2026-10-26T15:05:30.281Z Progress: resolved 251, reused 245, downloaded 0, added 250 2026-10-26T15:05:30.292Z Progress: resolved 251, reused 245, downloaded 0, added 251, done 2026-10-26T15:05:30.531Z .../esbuild@0.25.11/node_modules/esbuild postinstall$ node install.js 2026-10-26T15:05:30.532Z .../esbuild@0.28.1/node_modules/esbuild postinstall$ node install.js 2026-10-26T15:05:30.533Z .../node_modules/workerd postinstall$ node install.js 2026-10-26T15:05:30.534Z .../node_modules/workerd postinstall$ node install.js 2026-10-26T15:05:30.535Z .../esbuild@0.25.12/node_modules/esbuild postinstall$ node install.js 2026-10-26T15:05:30.682Z .../esbuild@0.25.11/node_modules/esbuild postinstall: Done 2026-10-26T15:05:30.751Z .../esbuild@0.28.1/node_modules/esbuild postinstall: Done 2026-10-26T15:05:30.759Z .../esbuild@0.28.2/node_modules/esbuild postinstall$ node install.js 2026-10-26T15:05:31.209Z .../node_modules/workerd postinstall: Done 2026-10-26T15:05:31.422Z .../node_modules/workerd postinstall: Done 2026-10-26T15:05:31.449Z .../esbuild@0.25.12/node_modules/esbuild postinstall: Done 2026-10-26T15:05:31.497Z .../esbuild@0.28.2/node_modules/esbuild postinstall: Done 2026-10-26T15:05:32.046Z 2026-10-26T15:05:32.046Z devDependencies: 2026-10-26T15:05:32.046Z + turbo 2.11.7 2026-10-26T15:05:32.046Z + typescript 5.9.3 2026-10-26T15:05:32.046Z 2026-10-26T15:05:32.640Z Done in 4.9s using pnpm v10.28.0 2026-10-26T15:05:33.046Z ##[group]Run pnpm -r --if-present build 2026-10-26T15:05:33.046Z ##[endgroup] 2026-10-26T15:05:33.458Z Scope: 7 of 8 workspace projects 2026-10-26T15:05:33.462Z apps/cli build$ esbuild src/bin.ts --bundle --platform=node --target=node22 --format=esm --outfile=dist/diffinery.mjs "--banner:js=#!/usr/bin/env node 2026-10-26T15:05:33.462Z import { createRequire as __diffineryCreateRequire } from 'node:module'; const require = __diffineryCreateRequire(import.meta.url);" 2026-10-26T15:05:33.465Z apps/diffinery build$ node islands/build.mjs && node scripts/build-docs.mjs 2026-10-26T15:05:33.465Z 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);" 2026-10-26T15:05:33.622Z apps/cli build: dist/diffinery.mjs 473.3kb 2026-10-26T15:05:33.625Z apps/cli build: ⚡ Done in 123ms 2026-10-26T15:05:33.628Z apps/cli build: Done 2026-10-26T15:05:33.652Z containers/runner build: dist/agent.mjs 684.1kb 2026-10-26T15:05:33.653Z containers/runner build: ⚡ Done in 149ms 2026-10-26T15:05:33.668Z containers/runner build: Done 2026-10-26T15:05:35.911Z apps/diffinery build: islands: kumo.js 466 KB, kumo.css 149 KB, terminal.js 286 KB 2026-10-26T15:05:36.371Z apps/diffinery build: docs: 86 pages (+2 generated at runtime), 20 site pages, 15 images, CLI 0.1.0 (254 KiB), editor extension 0.1.2 (26 KiB), JetBrains plugin 0.1.1 (70 KiB), Claude Code plugins diffinery 0.1.4, diffinery-ci 0.2.4 2026-10-26T15:05:36.394Z apps/diffinery build: Done 2026-10-26T15:05:36.955Z ##[group]Run as_root() { if [ "$(id -u)" = 0 ]; then "$@"; else sudo "$@"; fi; } 2026-10-26T15:05:36.956Z if ! command -v bwrap >/dev/null; then 2026-10-26T15:05:36.956Z as_root apt-get install -y --no-install-recommends bubblewrap || { as_root apt-get update -qq && as_root apt-get install -y --no-install-recommends bubblewrap; } 2026-10-26T15:05:36.956Z fi 2026-10-26T15:05:36.956Z as_root sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 2>/dev/null || true 2026-10-26T15:05:36.956Z bwrap --unshare-all --ro-bind / / --dev /dev --proc /proc -- true 2026-10-26T15:05:36.956Z ##[endgroup] 2026-10-26T15:05:37.374Z ##[group]Run # Shards of similar length; a new test file runs in "rest" unless it's added to another. 2026-10-26T15:05:37.374Z core='/e2e\.test\.mjs$' 2026-10-26T15:05:37.374Z agents='/(agentic|review|tasks)\.test\.mjs$' 2026-10-26T15:05:37.374Z # security.test.mjs, security-*.test.mjs (security-txt's too) and status.test.mjs. 2026-10-26T15:05:37.374Z security='/(security(-[a-z-]+)?|status)\.test\.mjs$' 2026-10-26T15:05:37.374Z # The core file's real histories and large pushes take minutes each (jquery's alone 2 to 3 on 2026-10-26T15:05:37.374Z # Diffinery's runners): two shards of their own, so no part of the file runs into node's 2026-10-26T15:05:37.374Z # per-file timeout, which is the --test-timeout here. 2026-10-26T15:05:37.374Z histories='^real histories:' 2026-10-26T15:05:37.374Z large='^(large files|large pushes):' 2026-10-26T15:05:37.374Z opts=(--test-timeout=600000) 2026-10-26T15:05:37.374Z case "agents" in 2026-10-26T15:05:37.374Z core) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-skip-pattern="$histories" --test-skip-pattern="$large") ;; 2026-10-26T15:05:37.374Z histories) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts=(--test-timeout=900000 --test-name-pattern="$histories") ;; 2026-10-26T15:05:37.374Z large) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-name-pattern="$large") ;; 2026-10-26T15:05:37.374Z agents) files=$(ls test/e2e/*.test.mjs | grep -E "$agents") ;; 2026-10-26T15:05:37.374Z security) files=$(ls test/e2e/*.test.mjs | grep -E "$security") ;; 2026-10-26T15:05:37.374Z *) files=$(ls test/e2e/*.test.mjs | grep -vE "$core|$agents|$security") ;; 2026-10-26T15:05:37.374Z esac 2026-10-26T15:05:37.374Z echo "$files" 2026-10-26T15:05:37.374Z # Two files at a time: each starts its own local server on its own port, database and 2026-10-26T15:05:37.374Z # directory, so they don't share state, and a file's server mostly keeps one core busy. 2026-10-26T15:05:37.374Z node --test --test-concurrency=2 "${opts[@]}" $files 2026-10-26T15:05:37.374Z ##[endgroup] 2026-10-26T15:05:37.396Z test/e2e/agentic.test.mjs 2026-10-26T15:05:37.396Z test/e2e/review.test.mjs 2026-10-26T15:05:37.396Z test/e2e/tasks.test.mjs 2026-10-26T15:05:37.448Z TAP version 13 2026-10-26T15:06:09.834Z # Subtest: Today: what needs you, your agents' work and what landed 2026-10-26T15:06:09.835Z ok 1 - Today: what needs you, your agents' work and what landed 2026-10-26T15:06:09.835Z --- 2026-10-26T15:06:09.835Z duration_ms: 32238.700849 2026-10-26T15:06:09.835Z type: 'test' 2026-10-26T15:06:09.835Z ... 2026-10-26T15:06:59.245Z # Subtest: agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-26T15:06:59.246Z ok 2 - agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-26T15:06:59.246Z --- 2026-10-26T15:06:59.246Z duration_ms: 81660.048073 2026-10-26T15:06:59.246Z type: 'test' 2026-10-26T15:06:59.246Z ... 2026-10-26T15:07:14.989Z # Subtest: agent review: Fix it, asking for a review, and who may 2026-10-26T15:07:14.989Z ok 3 - agent review: Fix it, asking for a review, and who may 2026-10-26T15:07:14.989Z --- 2026-10-26T15:07:14.989Z duration_ms: 15733.864652 2026-10-26T15:07:14.989Z type: 'test' 2026-10-26T15:07:14.990Z ... 2026-10-26T15:08:08.309Z # Subtest: agent review: spend limits per review (requests, tokens) and per repository 2026-10-26T15:08:08.309Z ok 4 - agent review: spend limits per review (requests, tokens) and per repository 2026-10-26T15:08:08.309Z --- 2026-10-26T15:08:08.309Z duration_ms: 53235.646407 2026-10-26T15:08:08.309Z type: 'test' 2026-10-26T15:08:08.309Z ... 2026-10-26T15:08:25.629Z # Subtest: model keys: write-only, browser session only, with an opt-in 2026-10-26T15:08:25.629Z ok 5 - model keys: write-only, browser session only, with an opt-in 2026-10-26T15:08:25.629Z --- 2026-10-26T15:08:25.629Z duration_ms: 8623.321806 2026-10-26T15:08:25.629Z type: 'test' 2026-10-26T15:08:25.629Z ... 2026-10-26T15:08:25.630Z # Subtest: an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-26T15:08:25.630Z ok 6 - an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-26T15:08:25.630Z --- 2026-10-26T15:08:25.630Z duration_ms: 10168.287354 2026-10-26T15:08:25.630Z type: 'test' 2026-10-26T15:08:25.630Z ... 2026-10-26T15:08:25.634Z # Subtest: task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-26T15:08:25.634Z ok 7 - task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-26T15:08:25.634Z --- 2026-10-26T15:08:25.634Z duration_ms: 4405.699147 2026-10-26T15:08:25.634Z type: 'test' 2026-10-26T15:08:25.634Z ... 2026-10-26T15:08:25.634Z # Subtest: a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-26T15:08:25.634Z ok 8 - a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-26T15:08:25.634Z --- 2026-10-26T15:08:25.635Z duration_ms: 17370.956855 2026-10-26T15:08:25.635Z type: 'test' 2026-10-26T15:08:25.635Z ... 2026-10-26T15:08:25.635Z # Subtest: a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-26T15:08:25.635Z ok 9 - a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-26T15:08:25.635Z --- 2026-10-26T15:08:25.635Z duration_ms: 27673.20764 2026-10-26T15:08:25.635Z type: 'test' 2026-10-26T15:08:25.635Z ... 2026-10-26T15:08:25.635Z # Subtest: plan first: a read-only plan run, then approve, change or split the plan 2026-10-26T15:08:25.635Z ok 10 - plan first: a read-only plan run, then approve, change or split the plan 2026-10-26T15:08:25.635Z --- 2026-10-26T15:08:25.635Z duration_ms: 25104.410034 2026-10-26T15:08:25.635Z type: 'test' 2026-10-26T15:08:25.635Z ... 2026-10-26T15:08:25.635Z # Subtest: best of N: attempts run side by side on their own branches, then one is picked 2026-10-26T15:08:25.635Z ok 11 - best of N: attempts run side by side on their own branches, then one is picked 2026-10-26T15:08:25.635Z --- 2026-10-26T15:08:25.635Z duration_ms: 10433.583148 2026-10-26T15:08:25.635Z type: 'test' 2026-10-26T15:08:25.635Z ... 2026-10-26T15:08:25.635Z # Subtest: verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-26T15:08:25.635Z ok 12 - verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-26T15:08:25.635Z --- 2026-10-26T15:08:25.635Z duration_ms: 13058.325022 2026-10-26T15:08:25.635Z type: 'test' 2026-10-26T15:08:25.635Z ... 2026-10-26T15:08:25.635Z # Subtest: organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-26T15:08:25.635Z ok 13 - organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-26T15:08:25.635Z --- 2026-10-26T15:08:25.635Z duration_ms: 18701.900555 2026-10-26T15:08:25.635Z type: 'test' 2026-10-26T15:08:25.635Z ... 2026-10-26T15:08:27.570Z # Subtest: losing access to the agent stops the task 2026-10-26T15:08:27.570Z ok 14 - losing access to the agent stops the task 2026-10-26T15:08:27.570Z --- 2026-10-26T15:08:27.570Z duration_ms: 1715.565978 2026-10-26T15:08:27.570Z type: 'test' 2026-10-26T15:08:27.570Z ... 2026-10-26T15:08:27.590Z 1..14 2026-10-26T15:08:27.590Z # tests 14 2026-10-26T15:08:27.590Z # suites 0 2026-10-26T15:08:27.590Z # pass 14 2026-10-26T15:08:27.590Z # fail 0 2026-10-26T15:08:27.590Z # cancelled 0 2026-10-26T15:08:27.591Z # skipped 0 2026-10-26T15:08:27.591Z # todo 0 2026-10-26T15:08:27.591Z # duration_ms 170158.983558 2026-10-26T15:08:28.003Z Cache hit occurred on the primary key node-cache-Linux-x64-pnpm-42d02c0263a3b5f911ed6ae8e9210922b97166ca02e60b2c70c55dfa1f00371b, not saving cache. 2026-10-26T15:08:28.643Z Pruning is unnecessary. 2026-10-26T15:08:29.029Z Removing persisted credentials 2026-10-26T15:08:29.276Z Host: 7% of the vCPUs' time went to other work on the host (steal) 2026-10-26T15:08:29.276Z Job completed with conclusion: success 2026-10-26T15:08:29.278Z Resources: 1.0 of 4 vCPUs busy on average (2.4 at the 95th percentile), peak memory 3.8 GiB of 11.9 GiB, peak disk 2.2 GB of 19.2 GB