2026-10-24T14:23:44.827Z Diffinery runner: job e2e (End-to-end (agent reviews, tasks, Today)) for codician/diffinery@6ee38762ef46 2026-10-24T14:23:44.880Z Runner: image diffinery-runner:4d3bf17f06575e64ab4155b3, in sea06, WNAM, container e4a5f5fefa4edd1e2781b17c82dbef2d004e9770050442669c4ae717b1037ecc 2026-10-24T14:23:44.880Z 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 2026-10-24T14:23:44.880Z Host: AMD EPYC (family 25, model 17), 4 vCPUs, 2546 MHz 2026-10-24T14:23:44.880Z Workspace: /workspace/diffinery 2026-10-24T14:23:45.074Z ##[group]Run actions/checkout@v4 2026-10-24T14:23:45.074Z ##[endgroup] 2026-10-24T14:23:45.076Z Syncing repository: codician/diffinery 2026-10-24T14:23:45.154Z Fetching the repository (depth 1) 2026-10-24T14:23:46.341Z remote: Enumerating objects: 808, done. 2026-10-24T14:23:47.263Z Receiving objects: 0% (1/808) Receiving objects: 1% (9/808) Receiving objects: 2% (17/808) Receiving objects: 3% (25/808) Receiving objects: 4% (33/808) Receiving objects: 5% (41/808) Receiving objects: 6% (49/808) Receiving objects: 7% (57/808) Receiving objects: 8% (65/808) Receiving objects: 9% (73/808) Receiving objects: 10% (81/808) Receiving objects: 11% (89/808) Receiving objects: 12% (97/808) Receiving objects: 13% (106/808) Receiving objects: 14% (114/808) Receiving objects: 15% (122/808) Receiving objects: 16% (130/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 17% (138/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 18% (146/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 19% (154/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 20% (162/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 21% (170/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 22% (178/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 23% (186/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 24% (194/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 25% (202/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 26% (211/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 27% (219/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 28% (227/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 29% (235/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 30% (243/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 31% (251/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 32% (259/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 33% (267/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 34% (275/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 35% (283/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 36% (291/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 37% (299/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 38% (308/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 39% (316/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 40% (324/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 41% (332/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 42% (340/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 43% (348/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 44% (356/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 45% (364/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 46% (372/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 47% (380/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 48% (388/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 49% (396/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 50% (404/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 51% (413/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 52% (421/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 53% (429/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 54% (437/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 55% (445/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 56% (453/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 57% (461/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 58% (469/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 59% (477/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 60% (485/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 61% (493/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 62% (501/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 63% (510/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 64% (518/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 65% (526/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 66% (534/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 67% (542/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 68% (550/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 69% (558/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 70% (566/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 71% (574/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 72% (582/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 73% (590/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 74% (598/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 75% (606/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 76% (615/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 77% (623/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 78% (631/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 79% (639/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 80% (647/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 81% (655/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 82% (663/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 83% (671/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 84% (679/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 85% (687/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 86% (695/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 87% (703/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 88% (712/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 89% (720/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 90% (728/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 91% (736/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 92% (744/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 93% (752/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 94% (760/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 95% (768/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 96% (776/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 97% (784/808), 643.79 KiB | 1.23 MiB/s remote: Total 808 (delta 0), reused 808 (delta 0) 2026-10-24T14:23:47.265Z Receiving objects: 98% (792/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 99% (800/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 100% (808/808), 643.79 KiB | 1.23 MiB/s Receiving objects: 100% (808/808), 3.69 MiB | 4.22 MiB/s, done. 2026-10-24T14:23:47.277Z From https://diffinery.com/codician/diffinery 2026-10-24T14:23:47.277Z * [new ref] 6ee38762ef468ce7a88a3f5347bc5360203bf0fa -> origin/diffinery-checkout 2026-10-24T14:23:47.383Z Note: switching to '6ee38762ef468ce7a88a3f5347bc5360203bf0fa'. 2026-10-24T14:23:47.383Z 2026-10-24T14:23:47.383Z You are in 'detached HEAD' state. You can look around, make experimental 2026-10-24T14:23:47.383Z changes and commit them, and you can discard any commits you make in this 2026-10-24T14:23:47.383Z state without impacting any branches by switching back to a branch. 2026-10-24T14:23:47.383Z 2026-10-24T14:23:47.383Z If you want to create a new branch to retain commits you create, you may 2026-10-24T14:23:47.383Z do so (now or later) by using -c with the switch command. Example: 2026-10-24T14:23:47.383Z 2026-10-24T14:23:47.383Z git switch -c 2026-10-24T14:23:47.383Z 2026-10-24T14:23:47.383Z Or undo this operation with: 2026-10-24T14:23:47.383Z 2026-10-24T14:23:47.383Z git switch - 2026-10-24T14:23:47.383Z 2026-10-24T14:23:47.383Z Turn off this advice by setting config variable advice.detachedHead to false 2026-10-24T14:23:47.383Z 2026-10-24T14:23:47.383Z HEAD is now at 6ee3876 Merge b39b4a9af6627b5d1e638d45bf519a4e0740d9e0 into 9f8a300c458b776547582959bea3eac7a6758de6 2026-10-24T14:23:47.390Z HEAD is now at 6ee38762ef468ce7a88a3f5347bc5360203bf0fa 2026-10-24T14:23:47.777Z Download action repository 'pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1' 2026-10-24T14:23:48.039Z ##[group]Run pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1 2026-10-24T14:23:48.039Z with: 2026-10-24T14:23:48.039Z dest: ~/setup-pnpm 2026-10-24T14:23:48.039Z run_install: null 2026-10-24T14:23:48.039Z cache: false 2026-10-24T14:23:48.039Z cache_dependency_path: pnpm-lock.yaml 2026-10-24T14:23:48.039Z package_json_file: package.json 2026-10-24T14:23:48.039Z standalone: false 2026-10-24T14:23:48.039Z ##[endgroup] 2026-10-24T14:23:48.248Z ##[group]Running self-installer... 2026-10-24T14:23:49.117Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-24T14:23:49.127Z Packages: +1 2026-10-24T14:23:49.127Z + 2026-10-24T14:23:49.738Z Progress: resolved 1, reused 0, downloaded 1, added 1, done 2026-10-24T14:23:49.771Z 2026-10-24T14:23:49.771Z dependencies: 2026-10-24T14:23:49.771Z + pnpm 10.28.0 (12.15.0 is available) 2026-10-24T14:23:49.771Z 2026-10-24T14:23:49.774Z Done in 1.2s 2026-10-24T14:23:49.796Z ##[endgroup] 2026-10-24T14:23:49.796Z Installation Completed! 2026-10-24T14:23:50.405Z ##[group]Run actions/setup-node@v4 2026-10-24T14:23:50.405Z with: 2026-10-24T14:23:50.405Z node-version: 22 2026-10-24T14:23:50.405Z cache: pnpm 2026-10-24T14:23:50.405Z ##[endgroup] 2026-10-24T14:23:50.413Z Found in cache @ 22.22.0 (pre-installed node satisfies '22') 2026-10-24T14:23:51.579Z Cache Size: ~216 MB (226934503 B) 2026-10-24T14:23:55.972Z Cache restored from key: node-cache-Linux-x64-pnpm-42d02c0263a3b5f911ed6ae8e9210922b97166ca02e60b2c70c55dfa1f00371b 2026-10-24T14:23:56.445Z ##[group]Run pnpm install --frozen-lockfile 2026-10-24T14:23:56.445Z ##[endgroup] 2026-10-24T14:23:56.849Z Scope: all 8 workspace projects 2026-10-24T14:23:56.909Z Lockfile is up to date, resolution step is skipped 2026-10-24T14:23:56.960Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-24T14:23:57.012Z Packages: +251 2026-10-24T14:23:57.012Z ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2026-10-24T14:23:57.961Z Progress: resolved 251, reused 245, downloaded 0, added 189 2026-10-24T14:23:58.525Z Progress: resolved 251, reused 245, downloaded 0, added 251, done 2026-10-24T14:23:58.654Z .../esbuild@0.25.12/node_modules/esbuild postinstall$ node install.js 2026-10-24T14:23:58.655Z .../node_modules/workerd postinstall$ node install.js 2026-10-24T14:23:58.655Z .../node_modules/workerd postinstall$ node install.js 2026-10-24T14:23:58.657Z .../esbuild@0.25.11/node_modules/esbuild postinstall$ node install.js 2026-10-24T14:23:58.657Z .../esbuild@0.28.1/node_modules/esbuild postinstall$ node install.js 2026-10-24T14:23:58.754Z .../esbuild@0.25.11/node_modules/esbuild postinstall: Done 2026-10-24T14:23:58.759Z .../esbuild@0.28.2/node_modules/esbuild postinstall$ node install.js 2026-10-24T14:23:58.870Z .../esbuild@0.25.12/node_modules/esbuild postinstall: Done 2026-10-24T14:23:58.879Z .../node_modules/workerd postinstall: Done 2026-10-24T14:23:59.004Z .../node_modules/workerd postinstall: Done 2026-10-24T14:23:59.009Z .../esbuild@0.28.1/node_modules/esbuild postinstall: Done 2026-10-24T14:23:59.013Z .../esbuild@0.28.2/node_modules/esbuild postinstall: Done 2026-10-24T14:23:59.553Z 2026-10-24T14:23:59.553Z devDependencies: 2026-10-24T14:23:59.553Z + turbo 2.11.7 2026-10-24T14:23:59.553Z + typescript 5.9.3 2026-10-24T14:23:59.553Z 2026-10-24T14:24:00.059Z Done in 3.5s using pnpm v10.28.0 2026-10-24T14:24:00.483Z ##[group]Run pnpm -r --if-present build 2026-10-24T14:24:00.483Z ##[endgroup] 2026-10-24T14:24:00.850Z Scope: 7 of 8 workspace projects 2026-10-24T14:24:00.855Z apps/cli build$ esbuild src/bin.ts --bundle --platform=node --target=node22 --format=esm --outfile=dist/diffinery.mjs "--banner:js=#!/usr/bin/env node 2026-10-24T14:24:00.855Z import { createRequire as __diffineryCreateRequire } from 'node:module'; const require = __diffineryCreateRequire(import.meta.url);" 2026-10-24T14:24:00.855Z apps/diffinery build$ node islands/build.mjs && node scripts/build-docs.mjs 2026-10-24T14:24:00.856Z 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);" 2026-10-24T14:24:00.938Z apps/cli build: dist/diffinery.mjs 468.9kb 2026-10-24T14:24:00.939Z apps/cli build: ⚡ Done in 63ms 2026-10-24T14:24:00.943Z apps/cli build: Done 2026-10-24T14:24:00.960Z containers/runner build: dist/agent.mjs 684.1kb 2026-10-24T14:24:00.960Z containers/runner build: ⚡ Done in 84ms 2026-10-24T14:24:00.964Z containers/runner build: Done 2026-10-24T14:24:03.001Z apps/diffinery build: islands: kumo.js 466 KB, kumo.css 149 KB, terminal.js 286 KB 2026-10-24T14:24:03.322Z apps/diffinery build: docs: 78 pages (+2 generated at runtime), 10 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 0.1.1, diffinery-ci 0.2.1 2026-10-24T14:24:03.334Z apps/diffinery build: Done 2026-10-24T14:24:03.894Z ##[group]Run as_root() { if [ "$(id -u)" = 0 ]; then "$@"; else sudo "$@"; fi; } 2026-10-24T14:24:03.894Z if ! command -v bwrap >/dev/null; then 2026-10-24T14:24:03.894Z as_root apt-get install -y --no-install-recommends bubblewrap || { as_root apt-get update -qq && as_root apt-get install -y --no-install-recommends bubblewrap; } 2026-10-24T14:24:03.894Z fi 2026-10-24T14:24:03.894Z as_root sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 2>/dev/null || true 2026-10-24T14:24:03.894Z bwrap --unshare-all --ro-bind / / --dev /dev --proc /proc -- true 2026-10-24T14:24:03.894Z ##[endgroup] 2026-10-24T14:24:04.417Z ##[group]Run # Shards of similar length; a new test file runs in "rest" unless it's added to another. 2026-10-24T14:24:04.417Z core='/e2e\.test\.mjs$' 2026-10-24T14:24:04.417Z agents='/(agentic|review|tasks)\.test\.mjs$' 2026-10-24T14:24:04.417Z # security.test.mjs, security-*.test.mjs (security-txt's too) and status.test.mjs. 2026-10-24T14:24:04.417Z security='/(security(-[a-z-]+)?|status)\.test\.mjs$' 2026-10-24T14:24:04.417Z # The core file's real histories and large pushes take minutes each (jquery's alone 2 to 3 on 2026-10-24T14:24:04.417Z # Diffinery's runners): two shards of their own, so no part of the file runs into node's 2026-10-24T14:24:04.417Z # per-file timeout, which is the --test-timeout here. 2026-10-24T14:24:04.417Z histories='^real histories:' 2026-10-24T14:24:04.417Z large='^(large files|large pushes):' 2026-10-24T14:24:04.417Z opts=(--test-timeout=600000) 2026-10-24T14:24:04.417Z case "agents" in 2026-10-24T14:24:04.417Z core) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-skip-pattern="$histories" --test-skip-pattern="$large") ;; 2026-10-24T14:24:04.417Z histories) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts=(--test-timeout=900000 --test-name-pattern="$histories") ;; 2026-10-24T14:24:04.417Z large) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-name-pattern="$large") ;; 2026-10-24T14:24:04.417Z agents) files=$(ls test/e2e/*.test.mjs | grep -E "$agents") ;; 2026-10-24T14:24:04.417Z security) files=$(ls test/e2e/*.test.mjs | grep -E "$security") ;; 2026-10-24T14:24:04.417Z *) files=$(ls test/e2e/*.test.mjs | grep -vE "$core|$agents|$security") ;; 2026-10-24T14:24:04.417Z esac 2026-10-24T14:24:04.417Z echo "$files" 2026-10-24T14:24:04.417Z # Two files at a time: each starts its own local server on its own port, database and 2026-10-24T14:24:04.417Z # directory, so they don't share state, and a file's server mostly keeps one core busy. 2026-10-24T14:24:04.417Z node --test --test-concurrency=2 "${opts[@]}" $files 2026-10-24T14:24:04.417Z ##[endgroup] 2026-10-24T14:24:04.586Z test/e2e/agentic.test.mjs 2026-10-24T14:24:04.586Z test/e2e/review.test.mjs 2026-10-24T14:24:04.586Z test/e2e/tasks.test.mjs 2026-10-24T14:24:04.637Z TAP version 13 2026-10-24T14:24:31.062Z # Subtest: Today: what needs you, your agents' work and what landed 2026-10-24T14:24:31.068Z ok 1 - Today: what needs you, your agents' work and what landed 2026-10-24T14:24:31.068Z --- 2026-10-24T14:24:31.068Z duration_ms: 26293.640223 2026-10-24T14:24:31.068Z type: 'test' 2026-10-24T14:24:31.068Z ... 2026-10-24T14:25:20.428Z # Subtest: agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-24T14:25:20.428Z ok 2 - agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-24T14:25:20.429Z --- 2026-10-24T14:25:20.429Z duration_ms: 75668.128822 2026-10-24T14:25:20.429Z type: 'test' 2026-10-24T14:25:20.429Z ... 2026-10-24T14:25:36.221Z # Subtest: agent review: Fix it, asking for a review, and who may 2026-10-24T14:25:36.222Z ok 3 - agent review: Fix it, asking for a review, and who may 2026-10-24T14:25:36.222Z --- 2026-10-24T14:25:36.222Z duration_ms: 15793.457172 2026-10-24T14:25:36.222Z type: 'test' 2026-10-24T14:25:36.222Z ... 2026-10-24T14:26:26.013Z # Subtest: agent review: spend limits per review (requests, tokens) and per repository 2026-10-24T14:26:26.013Z ok 4 - agent review: spend limits per review (requests, tokens) and per repository 2026-10-24T14:26:26.013Z --- 2026-10-24T14:26:26.013Z duration_ms: 49719.308337 2026-10-24T14:26:26.013Z type: 'test' 2026-10-24T14:26:26.013Z ... 2026-10-24T14:26:37.391Z # Subtest: model keys: write-only, browser session only, with an opt-in 2026-10-24T14:26:37.391Z ok 5 - model keys: write-only, browser session only, with an opt-in 2026-10-24T14:26:37.391Z --- 2026-10-24T14:26:37.391Z duration_ms: 6624.817649 2026-10-24T14:26:37.391Z type: 'test' 2026-10-24T14:26:37.391Z ... 2026-10-24T14:26:37.391Z # Subtest: an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-24T14:26:37.392Z ok 6 - an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-24T14:26:37.392Z --- 2026-10-24T14:26:37.392Z duration_ms: 9194.892254 2026-10-24T14:26:37.392Z type: 'test' 2026-10-24T14:26:37.392Z ... 2026-10-24T14:26:37.392Z # Subtest: task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-24T14:26:37.392Z ok 7 - task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-24T14:26:37.392Z --- 2026-10-24T14:26:37.392Z duration_ms: 3693.760605 2026-10-24T14:26:37.392Z type: 'test' 2026-10-24T14:26:37.392Z ... 2026-10-24T14:26:37.392Z # Subtest: a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-24T14:26:37.392Z ok 8 - a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-24T14:26:37.392Z --- 2026-10-24T14:26:37.392Z duration_ms: 16947.26468 2026-10-24T14:26:37.393Z type: 'test' 2026-10-24T14:26:37.393Z ... 2026-10-24T14:26:37.393Z # Subtest: a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-24T14:26:37.393Z ok 9 - a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-24T14:26:37.393Z --- 2026-10-24T14:26:37.393Z duration_ms: 26146.690284 2026-10-24T14:26:37.393Z type: 'test' 2026-10-24T14:26:37.393Z ... 2026-10-24T14:26:37.393Z # Subtest: plan first: a read-only plan run, then approve, change or split the plan 2026-10-24T14:26:37.393Z ok 10 - plan first: a read-only plan run, then approve, change or split the plan 2026-10-24T14:26:37.393Z --- 2026-10-24T14:26:37.393Z duration_ms: 24310.754714 2026-10-24T14:26:37.393Z type: 'test' 2026-10-24T14:26:37.393Z ... 2026-10-24T14:26:37.393Z # Subtest: best of N: attempts run side by side on their own branches, then one is picked 2026-10-24T14:26:37.394Z ok 11 - best of N: attempts run side by side on their own branches, then one is picked 2026-10-24T14:26:37.394Z --- 2026-10-24T14:26:37.394Z duration_ms: 9062.68077 2026-10-24T14:26:37.394Z type: 'test' 2026-10-24T14:26:37.394Z ... 2026-10-24T14:26:37.394Z # Subtest: verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-24T14:26:37.394Z ok 12 - verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-24T14:26:37.394Z --- 2026-10-24T14:26:37.394Z duration_ms: 12464.82798 2026-10-24T14:26:37.394Z type: 'test' 2026-10-24T14:26:37.394Z ... 2026-10-24T14:26:37.395Z # Subtest: organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-24T14:26:37.395Z ok 13 - organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-24T14:26:37.395Z --- 2026-10-24T14:26:37.395Z duration_ms: 17685.115762 2026-10-24T14:26:37.395Z type: 'test' 2026-10-24T14:26:37.395Z ... 2026-10-24T14:26:39.246Z # Subtest: losing access to the agent stops the task 2026-10-24T14:26:39.246Z ok 14 - losing access to the agent stops the task 2026-10-24T14:26:39.246Z --- 2026-10-24T14:26:39.246Z duration_ms: 1642.052904 2026-10-24T14:26:39.246Z type: 'test' 2026-10-24T14:26:39.246Z ... 2026-10-24T14:26:39.262Z 1..14 2026-10-24T14:26:39.262Z # tests 14 2026-10-24T14:26:39.262Z # suites 0 2026-10-24T14:26:39.263Z # pass 14 2026-10-24T14:26:39.263Z # fail 0 2026-10-24T14:26:39.263Z # cancelled 0 2026-10-24T14:26:39.263Z # skipped 0 2026-10-24T14:26:39.263Z # todo 0 2026-10-24T14:26:39.263Z # duration_ms 154644.291363 2026-10-24T14:26:39.626Z Cache hit occurred on the primary key node-cache-Linux-x64-pnpm-42d02c0263a3b5f911ed6ae8e9210922b97166ca02e60b2c70c55dfa1f00371b, not saving cache. 2026-10-24T14:26:40.199Z Pruning is unnecessary. 2026-10-24T14:26:40.594Z Removing persisted credentials 2026-10-24T14:26:40.780Z Host: 1% of the vCPUs' time went to other work on the host (steal) 2026-10-24T14:26:40.780Z Job completed with conclusion: success 2026-10-24T14:26:40.782Z Resources: 1.0 of 4 vCPUs busy on average (2.5 at the 95th percentile), peak memory 3.7 GiB of 11.9 GiB, peak disk 2.2 GB of 19.2 GB