2026-10-22T14:02:35.868Z Diffinery runner: job e2e (End-to-end (agent reviews, tasks, Today)) for codician/diffinery@e8b4d094fe38 2026-10-22T14:02:35.877Z Runner: image diffinery-runner:4d3bf17f06575e64ab4155b3, in muc01, WEUR, container ae003983b0a68ed16c0520dbfcbcef5cc2f8f46c24eee003dfbcfc91006f6df9 2026-10-22T14:02:35.877Z 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 2026-10-22T14:02:35.878Z Host: AMD EPYC (family 25, model 1), 4 vCPUs, 2000 MHz 2026-10-22T14:02:35.878Z Workspace: /workspace/diffinery 2026-10-22T14:02:35.948Z ##[group]Run actions/checkout@v4 2026-10-22T14:02:35.948Z ##[endgroup] 2026-10-22T14:02:35.950Z Syncing repository: codician/diffinery 2026-10-22T14:02:36.011Z Fetching the repository (depth 1) 2026-10-22T14:02:37.079Z remote: Enumerating objects: 770, done. 2026-10-22T14:02:38.369Z Receiving objects: 0% (1/770) Receiving objects: 1% (8/770) Receiving objects: 2% (16/770) Receiving objects: 3% (24/770) Receiving objects: 4% (31/770) Receiving objects: 5% (39/770) Receiving objects: 6% (47/770) Receiving objects: 7% (54/770) Receiving objects: 8% (62/770) Receiving objects: 9% (70/770) Receiving objects: 10% (77/770) Receiving objects: 11% (85/770) Receiving objects: 12% (93/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 13% (101/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 14% (108/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 15% (116/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 16% (124/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 17% (131/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 18% (139/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 19% (147/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 20% (154/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 21% (162/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 22% (170/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 23% (178/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 24% (185/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 25% (193/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 26% (201/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 27% (208/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 28% (216/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 29% (224/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 30% (231/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 31% (239/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 32% (247/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 33% (255/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 34% (262/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 35% (270/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 36% (278/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 37% (285/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 38% (293/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 39% (301/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 40% (308/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 41% (316/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 42% (324/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 43% (332/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 44% (339/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 45% (347/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 46% (355/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 47% (362/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 48% (370/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 49% (378/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 50% (385/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 51% (393/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 52% (401/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 53% (409/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 54% (416/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 55% (424/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 56% (432/770), 387.88 KiB | 566.00 KiB/s Receiving objects: 56% (435/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 57% (439/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 58% (447/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 59% (455/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 60% (462/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 61% (470/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 62% (478/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 63% (486/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 64% (493/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 65% (501/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 66% (509/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 67% (516/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 68% (524/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 69% (532/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 70% (539/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 71% (547/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 72% (555/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 73% (563/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 74% (570/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 75% (578/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 76% (586/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 77% (593/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 78% (601/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 79% (609/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 80% (616/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 81% (624/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 82% (632/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 83% (640/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 84% (647/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 85% (655/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 86% (663/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 87% (670/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 88% (678/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 89% (686/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 90% (693/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 91% (701/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 92% (709/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 93% (717/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 94% (724/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 95% (732/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 96% (740/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 97% (747/770), 2.57 MiB | 2.07 MiB/s remote: Total 770 (delta 0), reused 770 (delta 0) 2026-10-22T14:02:38.371Z Receiving objects: 98% (755/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 99% (763/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 100% (770/770), 2.57 MiB | 2.07 MiB/s Receiving objects: 100% (770/770), 3.53 MiB | 2.77 MiB/s, done. 2026-10-22T14:02:38.383Z From https://diffinery.com/codician/diffinery 2026-10-22T14:02:38.383Z * [new ref] e8b4d094fe380ad2b963b9959ef2d336f195bc59 -> origin/diffinery-checkout 2026-10-22T14:02:38.505Z Note: switching to 'e8b4d094fe380ad2b963b9959ef2d336f195bc59'. 2026-10-22T14:02:38.505Z 2026-10-22T14:02:38.505Z You are in 'detached HEAD' state. You can look around, make experimental 2026-10-22T14:02:38.505Z changes and commit them, and you can discard any commits you make in this 2026-10-22T14:02:38.505Z state without impacting any branches by switching back to a branch. 2026-10-22T14:02:38.505Z 2026-10-22T14:02:38.505Z If you want to create a new branch to retain commits you create, you may 2026-10-22T14:02:38.505Z do so (now or later) by using -c with the switch command. Example: 2026-10-22T14:02:38.505Z 2026-10-22T14:02:38.505Z git switch -c 2026-10-22T14:02:38.505Z 2026-10-22T14:02:38.505Z Or undo this operation with: 2026-10-22T14:02:38.505Z 2026-10-22T14:02:38.505Z git switch - 2026-10-22T14:02:38.505Z 2026-10-22T14:02:38.505Z Turn off this advice by setting config variable advice.detachedHead to false 2026-10-22T14:02:38.505Z 2026-10-22T14:02:38.505Z HEAD is now at e8b4d09 Merge 13773b4c0d53b91b65284d76ed0d64f80ac3701d into 7209c91f0667f4c809373e3ee531d893fdfa60c6 2026-10-22T14:02:38.510Z HEAD is now at e8b4d094fe380ad2b963b9959ef2d336f195bc59 2026-10-22T14:02:38.630Z Download action repository 'pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1' 2026-10-22T14:02:39.075Z ##[group]Run pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1 2026-10-22T14:02:39.075Z with: 2026-10-22T14:02:39.075Z dest: ~/setup-pnpm 2026-10-22T14:02:39.075Z run_install: null 2026-10-22T14:02:39.075Z cache: false 2026-10-22T14:02:39.075Z cache_dependency_path: pnpm-lock.yaml 2026-10-22T14:02:39.075Z package_json_file: package.json 2026-10-22T14:02:39.075Z standalone: false 2026-10-22T14:02:39.075Z ##[endgroup] 2026-10-22T14:02:39.313Z ##[group]Running self-installer... 2026-10-22T14:02:40.343Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-22T14:02:40.358Z Packages: +1 2026-10-22T14:02:40.358Z + 2026-10-22T14:02:41.040Z Progress: resolved 1, reused 0, downloaded 1, added 1, done 2026-10-22T14:02:41.092Z 2026-10-22T14:02:41.092Z dependencies: 2026-10-22T14:02:41.092Z + pnpm 10.28.0 (12.15.0 is available) 2026-10-22T14:02:41.092Z 2026-10-22T14:02:41.098Z Done in 1.4s 2026-10-22T14:02:41.127Z ##[endgroup] 2026-10-22T14:02:41.127Z Installation Completed! 2026-10-22T14:02:41.270Z ##[group]Run actions/setup-node@v4 2026-10-22T14:02:41.270Z with: 2026-10-22T14:02:41.270Z node-version: 22 2026-10-22T14:02:41.270Z cache: pnpm 2026-10-22T14:02:41.270Z ##[endgroup] 2026-10-22T14:02:41.278Z Found in cache @ 22.22.0 (pre-installed node satisfies '22') 2026-10-22T14:02:42.264Z Cache Size: ~216 MB (226493609 B) 2026-10-22T14:02:48.347Z Cache restored from key: node-cache-Linux-x64-pnpm-a02ba8dce5cb7329b868883337d1a03f862819a15859861dae22d3a8b1092f41 2026-10-22T14:02:48.511Z ##[group]Run pnpm install --frozen-lockfile 2026-10-22T14:02:48.511Z ##[endgroup] 2026-10-22T14:02:49.096Z Scope: all 8 workspace projects 2026-10-22T14:02:49.176Z Lockfile is up to date, resolution step is skipped 2026-10-22T14:02:49.263Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-22T14:02:49.313Z Packages: +250 2026-10-22T14:02:49.313Z ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2026-10-22T14:02:50.265Z Progress: resolved 250, reused 244, downloaded 0, added 167 2026-10-22T14:02:51.155Z Progress: resolved 250, reused 244, downloaded 0, added 250, done 2026-10-22T14:02:51.404Z .../esbuild@0.25.12/node_modules/esbuild postinstall$ node install.js 2026-10-22T14:02:51.406Z .../esbuild@0.28.1/node_modules/esbuild postinstall$ node install.js 2026-10-22T14:02:51.407Z .../node_modules/workerd postinstall$ node install.js 2026-10-22T14:02:51.420Z .../node_modules/workerd postinstall$ node install.js 2026-10-22T14:02:51.421Z .../esbuild@0.25.11/node_modules/esbuild postinstall$ node install.js 2026-10-22T14:02:51.524Z .../esbuild@0.25.12/node_modules/esbuild postinstall: Done 2026-10-22T14:02:51.530Z .../esbuild@0.28.2/node_modules/esbuild postinstall$ node install.js 2026-10-22T14:02:51.676Z .../node_modules/workerd postinstall: Done 2026-10-22T14:02:51.810Z .../node_modules/workerd postinstall: Done 2026-10-22T14:02:51.818Z .../esbuild@0.25.11/node_modules/esbuild postinstall: Done 2026-10-22T14:02:51.828Z .../esbuild@0.28.1/node_modules/esbuild postinstall: Done 2026-10-22T14:02:51.832Z .../esbuild@0.28.2/node_modules/esbuild postinstall: Done 2026-10-22T14:02:52.496Z 2026-10-22T14:02:52.496Z devDependencies: 2026-10-22T14:02:52.496Z + turbo 2.11.7 2026-10-22T14:02:52.496Z + typescript 5.9.3 2026-10-22T14:02:52.496Z 2026-10-22T14:02:53.215Z Done in 4.6s using pnpm v10.28.0 2026-10-22T14:02:53.354Z ##[group]Run pnpm -r --if-present build 2026-10-22T14:02:53.354Z ##[endgroup] 2026-10-22T14:02:53.953Z Scope: 7 of 8 workspace projects 2026-10-22T14:02:53.959Z apps/cli build$ esbuild src/bin.ts --bundle --platform=node --target=node22 --format=esm --outfile=dist/diffinery.mjs "--banner:js=#!/usr/bin/env node 2026-10-22T14:02:53.959Z import { createRequire as __diffineryCreateRequire } from 'node:module'; const require = __diffineryCreateRequire(import.meta.url);" 2026-10-22T14:02:53.960Z apps/diffinery build$ node islands/build.mjs && node scripts/build-docs.mjs 2026-10-22T14:02:53.961Z 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);" 2026-10-22T14:02:54.060Z apps/cli build: dist/diffinery.mjs 460.5kb 2026-10-22T14:02:54.062Z apps/cli build: ⚡ Done in 75ms 2026-10-22T14:02:54.077Z apps/cli build: Done 2026-10-22T14:02:54.111Z containers/runner build: dist/agent.mjs 684.1kb 2026-10-22T14:02:54.112Z containers/runner build: ⚡ Done in 98ms 2026-10-22T14:02:54.120Z containers/runner build: Done 2026-10-22T14:02:55.279Z apps/diffinery build: islands: kumo.js 466 KB, kumo.css 149 KB, terminal.js 286 KB 2026-10-22T14:02:55.741Z apps/diffinery build: docs: 74 pages (+2 generated at runtime), 10 site pages, 11 images, CLI 0.1.0 (245 KiB), editor extension 0.1.1 (20 KiB), JetBrains plugin 0.1.0 (64 KiB) 2026-10-22T14:02:55.754Z apps/diffinery build: Done 2026-10-22T14:02:55.900Z ##[group]Run as_root() { if [ "$(id -u)" = 0 ]; then "$@"; else sudo "$@"; fi; } 2026-10-22T14:02:55.900Z if ! command -v bwrap >/dev/null; then 2026-10-22T14:02:55.900Z as_root apt-get install -y --no-install-recommends bubblewrap || { as_root apt-get update -qq && as_root apt-get install -y --no-install-recommends bubblewrap; } 2026-10-22T14:02:55.900Z fi 2026-10-22T14:02:55.900Z as_root sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 2>/dev/null || true 2026-10-22T14:02:55.900Z bwrap --unshare-all --ro-bind / / --dev /dev --proc /proc -- true 2026-10-22T14:02:55.900Z ##[endgroup] 2026-10-22T14:02:56.035Z ##[group]Run # Shards of similar length; a new test file runs in "rest" unless it's added to another. 2026-10-22T14:02:56.035Z core='/e2e\.test\.mjs$' 2026-10-22T14:02:56.035Z agents='/(agentic|review|tasks)\.test\.mjs$' 2026-10-22T14:02:56.035Z # security.test.mjs, security-*.test.mjs (security-txt's too) and status.test.mjs. 2026-10-22T14:02:56.035Z security='/(security(-[a-z-]+)?|status)\.test\.mjs$' 2026-10-22T14:02:56.035Z # The core file's real histories and large pushes take minutes each (jquery's alone 2 to 3 on 2026-10-22T14:02:56.035Z # Diffinery's runners): two shards of their own, so no part of the file runs into node's 2026-10-22T14:02:56.035Z # per-file timeout, which is the --test-timeout here. 2026-10-22T14:02:56.035Z histories='^real histories:' 2026-10-22T14:02:56.035Z large='^(large files|large pushes):' 2026-10-22T14:02:56.035Z opts=(--test-timeout=600000) 2026-10-22T14:02:56.035Z case "agents" in 2026-10-22T14:02:56.035Z core) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-skip-pattern="$histories" --test-skip-pattern="$large") ;; 2026-10-22T14:02:56.035Z histories) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts=(--test-timeout=900000 --test-name-pattern="$histories") ;; 2026-10-22T14:02:56.035Z large) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-name-pattern="$large") ;; 2026-10-22T14:02:56.035Z agents) files=$(ls test/e2e/*.test.mjs | grep -E "$agents") ;; 2026-10-22T14:02:56.035Z security) files=$(ls test/e2e/*.test.mjs | grep -E "$security") ;; 2026-10-22T14:02:56.035Z *) files=$(ls test/e2e/*.test.mjs | grep -vE "$core|$agents|$security") ;; 2026-10-22T14:02:56.035Z esac 2026-10-22T14:02:56.035Z echo "$files" 2026-10-22T14:02:56.035Z # Two files at a time: each starts its own local server on its own port, database and 2026-10-22T14:02:56.035Z # directory, so they don't share state, and a file's server mostly keeps one core busy. 2026-10-22T14:02:56.035Z node --test --test-concurrency=2 "${opts[@]}" $files 2026-10-22T14:02:56.035Z ##[endgroup] 2026-10-22T14:02:56.061Z test/e2e/agentic.test.mjs 2026-10-22T14:02:56.061Z test/e2e/review.test.mjs 2026-10-22T14:02:56.061Z test/e2e/tasks.test.mjs 2026-10-22T14:02:56.142Z TAP version 13 2026-10-22T14:03:31.139Z # Subtest: Today: what needs you, your agents' work and what landed 2026-10-22T14:03:31.140Z ok 1 - Today: what needs you, your agents' work and what landed 2026-10-22T14:03:31.140Z --- 2026-10-22T14:03:31.140Z duration_ms: 34897.216051 2026-10-22T14:03:31.140Z type: 'test' 2026-10-22T14:03:31.140Z ... 2026-10-22T14:04:21.701Z # Subtest: agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-22T14:04:21.701Z ok 2 - agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-22T14:04:21.701Z --- 2026-10-22T14:04:21.701Z duration_ms: 85399.241413 2026-10-22T14:04:21.701Z type: 'test' 2026-10-22T14:04:21.701Z ... 2026-10-22T14:04:37.795Z # Subtest: agent review: Fix it, asking for a review, and who may 2026-10-22T14:04:37.795Z ok 3 - agent review: Fix it, asking for a review, and who may 2026-10-22T14:04:37.795Z --- 2026-10-22T14:04:37.795Z duration_ms: 16092.657477 2026-10-22T14:04:37.795Z type: 'test' 2026-10-22T14:04:37.795Z ... 2026-10-22T14:05:31.350Z # Subtest: agent review: spend limits per review (requests, tokens) and per repository 2026-10-22T14:05:31.350Z ok 4 - agent review: spend limits per review (requests, tokens) and per repository 2026-10-22T14:05:31.350Z --- 2026-10-22T14:05:31.350Z duration_ms: 53432.495528 2026-10-22T14:05:31.350Z type: 'test' 2026-10-22T14:05:31.350Z ... 2026-10-22T14:05:43.252Z # Subtest: model keys: write-only, browser session only, with an opt-in 2026-10-22T14:05:43.252Z ok 5 - model keys: write-only, browser session only, with an opt-in 2026-10-22T14:05:43.252Z --- 2026-10-22T14:05:43.252Z duration_ms: 9075.466195 2026-10-22T14:05:43.252Z type: 'test' 2026-10-22T14:05:43.252Z ... 2026-10-22T14:05:43.252Z # Subtest: an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-22T14:05:43.253Z ok 6 - an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-22T14:05:43.253Z --- 2026-10-22T14:05:43.253Z duration_ms: 9843.120377 2026-10-22T14:05:43.253Z type: 'test' 2026-10-22T14:05:43.253Z ... 2026-10-22T14:05:43.253Z # Subtest: task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-22T14:05:43.254Z ok 7 - task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-22T14:05:43.254Z --- 2026-10-22T14:05:43.254Z duration_ms: 4580.646458 2026-10-22T14:05:43.254Z type: 'test' 2026-10-22T14:05:43.254Z ... 2026-10-22T14:05:43.254Z # Subtest: a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-22T14:05:43.254Z ok 8 - a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-22T14:05:43.254Z --- 2026-10-22T14:05:43.254Z duration_ms: 16763.767778 2026-10-22T14:05:43.254Z type: 'test' 2026-10-22T14:05:43.254Z ... 2026-10-22T14:05:43.254Z # Subtest: a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-22T14:05:43.255Z ok 9 - a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-22T14:05:43.255Z --- 2026-10-22T14:05:43.255Z duration_ms: 25992.032338 2026-10-22T14:05:43.255Z type: 'test' 2026-10-22T14:05:43.255Z ... 2026-10-22T14:05:43.255Z # Subtest: plan first: a read-only plan run, then approve, change or split the plan 2026-10-22T14:05:43.255Z ok 10 - plan first: a read-only plan run, then approve, change or split the plan 2026-10-22T14:05:43.255Z --- 2026-10-22T14:05:43.255Z duration_ms: 24722.674487 2026-10-22T14:05:43.255Z type: 'test' 2026-10-22T14:05:43.255Z ... 2026-10-22T14:05:43.255Z # Subtest: best of N: attempts run side by side on their own branches, then one is picked 2026-10-22T14:05:43.255Z ok 11 - best of N: attempts run side by side on their own branches, then one is picked 2026-10-22T14:05:43.256Z --- 2026-10-22T14:05:43.256Z duration_ms: 9532.100301 2026-10-22T14:05:43.256Z type: 'test' 2026-10-22T14:05:43.256Z ... 2026-10-22T14:05:43.256Z # Subtest: verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-22T14:05:43.256Z ok 12 - verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-22T14:05:43.256Z --- 2026-10-22T14:05:43.256Z duration_ms: 12742.460782 2026-10-22T14:05:43.256Z type: 'test' 2026-10-22T14:05:43.256Z ... 2026-10-22T14:05:43.256Z # Subtest: organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-22T14:05:43.257Z ok 13 - organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-22T14:05:43.257Z --- 2026-10-22T14:05:43.257Z duration_ms: 18655.092751 2026-10-22T14:05:43.257Z type: 'test' 2026-10-22T14:05:43.257Z ... 2026-10-22T14:05:45.335Z # Subtest: losing access to the agent stops the task 2026-10-22T14:05:45.336Z ok 14 - losing access to the agent stops the task 2026-10-22T14:05:45.336Z --- 2026-10-22T14:05:45.336Z duration_ms: 1733.850304 2026-10-22T14:05:45.336Z type: 'test' 2026-10-22T14:05:45.336Z ... 2026-10-22T14:05:45.362Z 1..14 2026-10-22T14:05:45.362Z # tests 14 2026-10-22T14:05:45.362Z # suites 0 2026-10-22T14:05:45.362Z # pass 14 2026-10-22T14:05:45.362Z # fail 0 2026-10-22T14:05:45.362Z # cancelled 0 2026-10-22T14:05:45.362Z # skipped 0 2026-10-22T14:05:45.362Z # todo 0 2026-10-22T14:05:45.362Z # duration_ms 169256.770826 2026-10-22T14:05:45.472Z Cache hit occurred on the primary key node-cache-Linux-x64-pnpm-a02ba8dce5cb7329b868883337d1a03f862819a15859861dae22d3a8b1092f41, not saving cache. 2026-10-22T14:05:45.774Z Pruning is unnecessary. 2026-10-22T14:05:45.869Z Removing persisted credentials 2026-10-22T14:05:45.920Z Host: 0% of the vCPUs' time went to other work on the host (steal) 2026-10-22T14:05:45.920Z Job completed with conclusion: success 2026-10-22T14:05:45.921Z Resources: 1.2 of 4 vCPUs busy on average (2.8 at the 95th percentile), peak memory 3.8 GiB of 11.9 GiB, peak disk 2.2 GB of 19.2 GB