2026-10-22T12:37:23.795Z Diffinery runner: job e2e (End-to-end (agent reviews, tasks, Today)) for codician/diffinery@dd72e88c1f08 2026-10-22T12:37:23.806Z Runner: image diffinery-runner:fe3c3f94009aac30d494e6db, in bom06, APAC, container 16ace26b974b2be6a596e5ca340e9d555601d9e1d6c1191b561e17e1a1ae350b 2026-10-22T12:37:23.806Z 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 2026-10-22T12:37:23.806Z Host: AMD EPYC (family 25, model 17), 4 vCPUs, 2550 MHz 2026-10-22T12:37:23.806Z Workspace: /workspace/diffinery 2026-10-22T12:37:24.117Z ##[group]Run actions/checkout@v4 2026-10-22T12:37:24.117Z ##[endgroup] 2026-10-22T12:37:24.119Z Syncing repository: codician/diffinery 2026-10-22T12:37:24.167Z Fetching the repository (depth 1) 2026-10-22T12:37:25.995Z remote: Enumerating objects: 763, done. 2026-10-22T12:37:27.458Z Receiving objects: 0% (1/763) Receiving objects: 1% (8/763) Receiving objects: 2% (16/763) Receiving objects: 3% (23/763) Receiving objects: 4% (31/763) Receiving objects: 5% (39/763) Receiving objects: 6% (46/763) Receiving objects: 7% (54/763) Receiving objects: 8% (62/763) Receiving objects: 9% (69/763) Receiving objects: 10% (77/763) Receiving objects: 11% (84/763) Receiving objects: 12% (92/763) Receiving objects: 13% (100/763) Receiving objects: 14% (107/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 15% (115/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 16% (123/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 17% (130/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 18% (138/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 19% (145/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 20% (153/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 21% (161/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 22% (168/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 23% (176/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 24% (184/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 25% (191/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 26% (199/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 27% (207/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 28% (214/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 29% (222/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 30% (229/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 31% (237/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 32% (245/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 33% (252/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 34% (260/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 35% (268/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 36% (275/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 37% (283/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 38% (290/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 39% (298/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 40% (306/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 41% (313/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 42% (321/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 43% (329/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 44% (336/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 45% (344/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 46% (351/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 46% (356/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 47% (359/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 48% (367/763), 451.86 KiB | 836.00 KiB/s Receiving objects: 49% (374/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 50% (382/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 51% (390/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 52% (397/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 53% (405/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 54% (413/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 55% (420/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 56% (428/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 57% (435/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 58% (443/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 59% (451/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 60% (458/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 61% (466/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 62% (474/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 63% (481/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 64% (489/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 65% (496/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 66% (504/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 67% (512/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 68% (519/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 69% (527/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 70% (535/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 71% (542/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 72% (550/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 73% (557/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 74% (565/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 75% (573/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 76% (580/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 77% (588/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 78% (596/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 79% (603/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 80% (611/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 81% (619/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 82% (626/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 83% (634/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 84% (641/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 85% (649/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 86% (657/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 87% (664/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 88% (672/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 89% (680/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 90% (687/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 91% (695/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 92% (702/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 93% (710/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 94% (718/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 95% (725/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 96% (733/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 97% (741/763), 2.07 MiB | 1.99 MiB/s remote: Total 763 (delta 0), reused 763 (delta 0) 2026-10-22T12:37:27.459Z Receiving objects: 98% (748/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 99% (756/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 100% (763/763), 2.07 MiB | 1.99 MiB/s Receiving objects: 100% (763/763), 3.49 MiB | 2.83 MiB/s, done. 2026-10-22T12:37:27.467Z From https://diffinery.com/codician/diffinery 2026-10-22T12:37:27.467Z * [new ref] dd72e88c1f08643b85001863a40a07d0d6c38590 -> origin/diffinery-checkout 2026-10-22T12:37:27.557Z Note: switching to 'dd72e88c1f08643b85001863a40a07d0d6c38590'. 2026-10-22T12:37:27.557Z 2026-10-22T12:37:27.557Z You are in 'detached HEAD' state. You can look around, make experimental 2026-10-22T12:37:27.557Z changes and commit them, and you can discard any commits you make in this 2026-10-22T12:37:27.557Z state without impacting any branches by switching back to a branch. 2026-10-22T12:37:27.557Z 2026-10-22T12:37:27.557Z If you want to create a new branch to retain commits you create, you may 2026-10-22T12:37:27.557Z do so (now or later) by using -c with the switch command. Example: 2026-10-22T12:37:27.557Z 2026-10-22T12:37:27.557Z git switch -c 2026-10-22T12:37:27.557Z 2026-10-22T12:37:27.557Z Or undo this operation with: 2026-10-22T12:37:27.557Z 2026-10-22T12:37:27.557Z git switch - 2026-10-22T12:37:27.557Z 2026-10-22T12:37:27.557Z Turn off this advice by setting config variable advice.detachedHead to false 2026-10-22T12:37:27.557Z 2026-10-22T12:37:27.557Z HEAD is now at dd72e88 Merge ce508b5e8713318af3ff650a7aa1a23d4e3d1e78 into 7bde4a51b5fa2d01cc57d1e3ba47f961d956d2b4 2026-10-22T12:37:27.561Z HEAD is now at dd72e88c1f08643b85001863a40a07d0d6c38590 2026-10-22T12:37:29.234Z Download action repository 'pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1' 2026-10-22T12:37:29.655Z ##[group]Run pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1 2026-10-22T12:37:29.655Z with: 2026-10-22T12:37:29.655Z dest: ~/setup-pnpm 2026-10-22T12:37:29.655Z run_install: null 2026-10-22T12:37:29.655Z cache: false 2026-10-22T12:37:29.655Z cache_dependency_path: pnpm-lock.yaml 2026-10-22T12:37:29.655Z package_json_file: package.json 2026-10-22T12:37:29.655Z standalone: false 2026-10-22T12:37:29.655Z ##[endgroup] 2026-10-22T12:37:29.844Z ##[group]Running self-installer... 2026-10-22T12:37:30.771Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-22T12:37:30.781Z Packages: +1 2026-10-22T12:37:30.781Z + 2026-10-22T12:37:31.449Z Progress: resolved 1, reused 0, downloaded 1, added 1, done 2026-10-22T12:37:31.484Z 2026-10-22T12:37:31.484Z dependencies: 2026-10-22T12:37:31.484Z + pnpm 10.28.0 (12.15.0 is available) 2026-10-22T12:37:31.484Z 2026-10-22T12:37:31.488Z Done in 1.4s 2026-10-22T12:37:31.514Z ##[endgroup] 2026-10-22T12:37:31.515Z Installation Completed! 2026-10-22T12:37:32.049Z ##[group]Run actions/setup-node@v4 2026-10-22T12:37:32.049Z with: 2026-10-22T12:37:32.049Z node-version: 22 2026-10-22T12:37:32.049Z cache: pnpm 2026-10-22T12:37:32.049Z ##[endgroup] 2026-10-22T12:37:32.060Z Found in cache @ 22.22.0 (pre-installed node satisfies '22') 2026-10-22T12:37:34.614Z Cache Size: ~216 MB (226493609 B) 2026-10-22T12:37:42.234Z Cache restored from key: node-cache-Linux-x64-pnpm-a02ba8dce5cb7329b868883337d1a03f862819a15859861dae22d3a8b1092f41 2026-10-22T12:37:42.805Z ##[group]Run pnpm install --frozen-lockfile 2026-10-22T12:37:42.805Z ##[endgroup] 2026-10-22T12:37:43.170Z Scope: all 8 workspace projects 2026-10-22T12:37:43.226Z Lockfile is up to date, resolution step is skipped 2026-10-22T12:37:43.269Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-22T12:37:43.322Z Packages: +250 2026-10-22T12:37:43.322Z ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2026-10-22T12:37:44.271Z Progress: resolved 250, reused 244, downloaded 0, added 238 2026-10-22T12:37:44.386Z Progress: resolved 250, reused 244, downloaded 0, added 250, done 2026-10-22T12:37:44.506Z .../esbuild@0.28.1/node_modules/esbuild postinstall$ node install.js 2026-10-22T12:37:44.507Z .../node_modules/workerd postinstall$ node install.js 2026-10-22T12:37:44.508Z .../esbuild@0.25.12/node_modules/esbuild postinstall$ node install.js 2026-10-22T12:37:44.508Z .../node_modules/workerd postinstall$ node install.js 2026-10-22T12:37:44.516Z .../esbuild@0.25.11/node_modules/esbuild postinstall$ node install.js 2026-10-22T12:37:44.696Z .../node_modules/workerd postinstall: Done 2026-10-22T12:37:44.700Z .../esbuild@0.28.2/node_modules/esbuild postinstall$ node install.js 2026-10-22T12:37:44.818Z .../node_modules/workerd postinstall: Done 2026-10-22T12:37:44.823Z .../esbuild@0.25.11/node_modules/esbuild postinstall: Done 2026-10-22T12:37:44.824Z .../esbuild@0.28.1/node_modules/esbuild postinstall: Done 2026-10-22T12:37:44.841Z .../esbuild@0.25.12/node_modules/esbuild postinstall: Done 2026-10-22T12:37:44.844Z .../esbuild@0.28.2/node_modules/esbuild postinstall: Done 2026-10-22T12:37:45.283Z 2026-10-22T12:37:45.283Z devDependencies: 2026-10-22T12:37:45.283Z + turbo 2.11.7 2026-10-22T12:37:45.283Z + typescript 5.9.3 2026-10-22T12:37:45.283Z 2026-10-22T12:37:45.692Z Done in 2.8s using pnpm v10.28.0 2026-10-22T12:37:46.230Z ##[group]Run pnpm -r --if-present build 2026-10-22T12:37:46.230Z ##[endgroup] 2026-10-22T12:37:46.530Z Scope: 7 of 8 workspace projects 2026-10-22T12:37:46.534Z apps/cli build$ esbuild src/bin.ts --bundle --platform=node --target=node22 --format=esm --outfile=dist/diffinery.mjs "--banner:js=#!/usr/bin/env node 2026-10-22T12:37:46.534Z import { createRequire as __diffineryCreateRequire } from 'node:module'; const require = __diffineryCreateRequire(import.meta.url);" 2026-10-22T12:37:46.534Z apps/diffinery build$ node islands/build.mjs && node scripts/build-docs.mjs 2026-10-22T12:37:46.534Z 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);" 2026-10-22T12:37:46.607Z apps/cli build: dist/diffinery.mjs 448.1kb 2026-10-22T12:37:46.607Z apps/cli build: ⚡ Done in 53ms 2026-10-22T12:37:46.609Z containers/runner build: dist/agent.mjs 684.1kb 2026-10-22T12:37:46.609Z containers/runner build: ⚡ Done in 53ms 2026-10-22T12:37:46.611Z apps/cli build: Done 2026-10-22T12:37:46.616Z containers/runner build: Done 2026-10-22T12:37:47.351Z apps/diffinery build: islands: kumo.js 466 KB, kumo.css 149 KB, terminal.js 286 KB 2026-10-22T12:37:47.663Z apps/diffinery build: docs: 73 pages (+2 generated at runtime), 10 site pages, 11 images, CLI 0.1.0 (236 KiB), editor extension 0.1.1 (20 KiB), JetBrains plugin 0.1.0 (64 KiB) 2026-10-22T12:37:47.673Z apps/diffinery build: Done 2026-10-22T12:37:48.491Z ##[group]Run as_root() { if [ "$(id -u)" = 0 ]; then "$@"; else sudo "$@"; fi; } 2026-10-22T12:37:48.491Z if ! command -v bwrap >/dev/null; then 2026-10-22T12:37:48.491Z as_root apt-get install -y --no-install-recommends bubblewrap || { as_root apt-get update -qq && as_root apt-get install -y --no-install-recommends bubblewrap; } 2026-10-22T12:37:48.491Z fi 2026-10-22T12:37:48.491Z as_root sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 2>/dev/null || true 2026-10-22T12:37:48.491Z bwrap --unshare-all --ro-bind / / --dev /dev --proc /proc -- true 2026-10-22T12:37:48.491Z ##[endgroup] 2026-10-22T12:37:49.034Z ##[group]Run # Shards of similar length; a new test file runs in "rest" unless it's added to another. 2026-10-22T12:37:49.034Z core='/e2e\.test\.mjs$' 2026-10-22T12:37:49.034Z agents='/(agentic|review|tasks)\.test\.mjs$' 2026-10-22T12:37:49.034Z # security.test.mjs, security-*.test.mjs (security-txt's too) and status.test.mjs. 2026-10-22T12:37:49.034Z security='/(security(-[a-z-]+)?|status)\.test\.mjs$' 2026-10-22T12:37:49.034Z # The core file's real histories and large pushes take minutes each (jquery's alone 2 to 3 on 2026-10-22T12:37:49.034Z # Diffinery's runners): two shards of their own, so no part of the file runs into node's 2026-10-22T12:37:49.034Z # per-file timeout, which is the --test-timeout here. 2026-10-22T12:37:49.034Z histories='^real histories:' 2026-10-22T12:37:49.034Z large='^(large files|large pushes):' 2026-10-22T12:37:49.034Z opts=(--test-timeout=600000) 2026-10-22T12:37:49.034Z case "agents" in 2026-10-22T12:37:49.034Z core) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-skip-pattern="$histories" --test-skip-pattern="$large") ;; 2026-10-22T12:37:49.034Z histories) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts=(--test-timeout=900000 --test-name-pattern="$histories") ;; 2026-10-22T12:37:49.034Z large) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-name-pattern="$large") ;; 2026-10-22T12:37:49.034Z agents) files=$(ls test/e2e/*.test.mjs | grep -E "$agents") ;; 2026-10-22T12:37:49.034Z security) files=$(ls test/e2e/*.test.mjs | grep -E "$security") ;; 2026-10-22T12:37:49.034Z *) files=$(ls test/e2e/*.test.mjs | grep -vE "$core|$agents|$security") ;; 2026-10-22T12:37:49.034Z esac 2026-10-22T12:37:49.034Z echo "$files" 2026-10-22T12:37:49.034Z # Two files at a time: each starts its own local server on its own port, database and 2026-10-22T12:37:49.034Z # directory, so they don't share state, and a file's server mostly keeps one core busy. 2026-10-22T12:37:49.034Z node --test --test-concurrency=2 "${opts[@]}" $files 2026-10-22T12:37:49.034Z ##[endgroup] 2026-10-22T12:37:49.046Z test/e2e/agentic.test.mjs 2026-10-22T12:37:49.046Z test/e2e/review.test.mjs 2026-10-22T12:37:49.046Z test/e2e/tasks.test.mjs 2026-10-22T12:37:49.089Z TAP version 13 2026-10-22T12:38:07.742Z # Subtest: Today: what needs you, your agents' work and what landed 2026-10-22T12:38:07.742Z ok 1 - Today: what needs you, your agents' work and what landed 2026-10-22T12:38:07.742Z --- 2026-10-22T12:38:07.742Z duration_ms: 18603.305297 2026-10-22T12:38:07.742Z type: 'test' 2026-10-22T12:38:07.742Z ... 2026-10-22T12:38:58.548Z # Subtest: agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-22T12:38:58.548Z ok 2 - agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-22T12:38:58.548Z --- 2026-10-22T12:38:58.548Z duration_ms: 69402.115794 2026-10-22T12:38:58.548Z type: 'test' 2026-10-22T12:38:58.548Z ... 2026-10-22T12:39:14.144Z # Subtest: agent review: Fix it, asking for a review, and who may 2026-10-22T12:39:14.145Z ok 3 - agent review: Fix it, asking for a review, and who may 2026-10-22T12:39:14.145Z --- 2026-10-22T12:39:14.145Z duration_ms: 15595.672823 2026-10-22T12:39:14.145Z type: 'test' 2026-10-22T12:39:14.145Z ... 2026-10-22T12:40:01.906Z # Subtest: agent review: spend limits per review (requests, tokens) and per repository 2026-10-22T12:40:01.906Z ok 4 - agent review: spend limits per review (requests, tokens) and per repository 2026-10-22T12:40:01.906Z --- 2026-10-22T12:40:01.906Z duration_ms: 47704.21021 2026-10-22T12:40:01.906Z type: 'test' 2026-10-22T12:40:01.906Z ... 2026-10-22T12:40:08.720Z # Subtest: model keys: write-only, browser session only, with an opt-in 2026-10-22T12:40:08.720Z ok 5 - model keys: write-only, browser session only, with an opt-in 2026-10-22T12:40:08.720Z --- 2026-10-22T12:40:08.720Z duration_ms: 5458.961433 2026-10-22T12:40:08.720Z type: 'test' 2026-10-22T12:40:08.720Z ... 2026-10-22T12:40:08.720Z # Subtest: an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-22T12:40:08.720Z ok 6 - an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-22T12:40:08.720Z --- 2026-10-22T12:40:08.720Z duration_ms: 9426.417444 2026-10-22T12:40:08.720Z type: 'test' 2026-10-22T12:40:08.720Z ... 2026-10-22T12:40:08.721Z # Subtest: task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-22T12:40:08.721Z ok 7 - task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-22T12:40:08.721Z --- 2026-10-22T12:40:08.721Z duration_ms: 3254.308874 2026-10-22T12:40:08.721Z type: 'test' 2026-10-22T12:40:08.721Z ... 2026-10-22T12:40:08.721Z # Subtest: a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-22T12:40:08.721Z ok 8 - a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-22T12:40:08.722Z --- 2026-10-22T12:40:08.722Z duration_ms: 15634.683036 2026-10-22T12:40:08.722Z type: 'test' 2026-10-22T12:40:08.722Z ... 2026-10-22T12:40:08.722Z # Subtest: a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-22T12:40:08.722Z ok 9 - a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-22T12:40:08.722Z --- 2026-10-22T12:40:08.722Z duration_ms: 25345.045203 2026-10-22T12:40:08.722Z type: 'test' 2026-10-22T12:40:08.722Z ... 2026-10-22T12:40:08.722Z # Subtest: plan first: a read-only plan run, then approve, change or split the plan 2026-10-22T12:40:08.722Z ok 10 - plan first: a read-only plan run, then approve, change or split the plan 2026-10-22T12:40:08.722Z --- 2026-10-22T12:40:08.722Z duration_ms: 23750.606174 2026-10-22T12:40:08.722Z type: 'test' 2026-10-22T12:40:08.722Z ... 2026-10-22T12:40:08.722Z # Subtest: best of N: attempts run side by side on their own branches, then one is picked 2026-10-22T12:40:08.722Z ok 11 - best of N: attempts run side by side on their own branches, then one is picked 2026-10-22T12:40:08.722Z --- 2026-10-22T12:40:08.722Z duration_ms: 8741.21936 2026-10-22T12:40:08.722Z type: 'test' 2026-10-22T12:40:08.722Z ... 2026-10-22T12:40:08.722Z # Subtest: verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-22T12:40:08.722Z ok 12 - verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-22T12:40:08.722Z --- 2026-10-22T12:40:08.722Z duration_ms: 12185.287206 2026-10-22T12:40:08.722Z type: 'test' 2026-10-22T12:40:08.722Z ... 2026-10-22T12:40:08.722Z # Subtest: organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-22T12:40:08.723Z ok 13 - organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-22T12:40:08.723Z --- 2026-10-22T12:40:08.723Z duration_ms: 17043.837167 2026-10-22T12:40:08.723Z type: 'test' 2026-10-22T12:40:08.723Z ... 2026-10-22T12:40:10.486Z # Subtest: losing access to the agent stops the task 2026-10-22T12:40:10.486Z ok 14 - losing access to the agent stops the task 2026-10-22T12:40:10.486Z --- 2026-10-22T12:40:10.486Z duration_ms: 1597.141001 2026-10-22T12:40:10.486Z type: 'test' 2026-10-22T12:40:10.486Z ... 2026-10-22T12:40:10.501Z 1..14 2026-10-22T12:40:10.501Z # tests 14 2026-10-22T12:40:10.501Z # suites 0 2026-10-22T12:40:10.501Z # pass 14 2026-10-22T12:40:10.501Z # fail 0 2026-10-22T12:40:10.501Z # cancelled 0 2026-10-22T12:40:10.501Z # skipped 0 2026-10-22T12:40:10.501Z # todo 0 2026-10-22T12:40:10.501Z # duration_ms 141427.727546 2026-10-22T12:40:11.044Z Cache hit occurred on the primary key node-cache-Linux-x64-pnpm-a02ba8dce5cb7329b868883337d1a03f862819a15859861dae22d3a8b1092f41, not saving cache. 2026-10-22T12:40:11.711Z Pruning is unnecessary. 2026-10-22T12:40:12.231Z Removing persisted credentials 2026-10-22T12:40:12.497Z Host: 0% of the vCPUs' time went to other work on the host (steal) 2026-10-22T12:40:12.497Z Job completed with conclusion: success 2026-10-22T12:40:12.498Z Resources: 0.8 of 4 vCPUs busy on average (2.5 at the 95th percentile), peak memory 3.9 GiB of 11.9 GiB, peak disk 2.2 GB of 19.2 GB