2026-10-23T15:11:50.091Z Diffinery runner: job e2e (End-to-end (agent reviews, tasks, Today)) for codician/diffinery@274d35077218 2026-10-23T15:11:50.106Z Runner: image diffinery-runner:4d3bf17f06575e64ab4155b3, in lax08, WNAM, container 8aac3dad68899cc078dedccbeacf4ac99ca9e4a9cfa1522e544db6f8e9355c03 2026-10-23T15:11:50.106Z Runner size: large (4 vCPU, 12 GiB of memory, 20 GB of disk), an earlier run of this job wasn't measured; runs-on: diffinery-large (or -medium, -small, -tiny) sets a size 2026-10-23T15:11:50.106Z Host: AMD EPYC (family 25, model 17), 4 vCPUs, 2550 MHz 2026-10-23T15:11:50.107Z Workspace: /workspace/diffinery 2026-10-23T15:11:50.299Z ##[group]Run actions/checkout@v4 2026-10-23T15:11:50.299Z ##[endgroup] 2026-10-23T15:11:50.301Z Syncing repository: codician/diffinery 2026-10-23T15:11:50.368Z Fetching the repository (depth 1) 2026-10-23T15:11:51.589Z remote: Enumerating objects: 781, done. 2026-10-23T15:11:52.529Z Receiving objects: 0% (1/781) Receiving objects: 1% (8/781) Receiving objects: 2% (16/781) Receiving objects: 3% (24/781) Receiving objects: 4% (32/781) Receiving objects: 5% (40/781) Receiving objects: 6% (47/781) Receiving objects: 7% (55/781) Receiving objects: 8% (63/781) Receiving objects: 9% (71/781) Receiving objects: 10% (79/781) Receiving objects: 11% (86/781) Receiving objects: 12% (94/781) Receiving objects: 13% (102/781) Receiving objects: 14% (110/781) Receiving objects: 15% (118/781) Receiving objects: 16% (125/781) Receiving objects: 17% (133/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 18% (141/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 19% (149/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 20% (157/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 21% (165/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 22% (172/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 23% (180/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 24% (188/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 25% (196/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 26% (204/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 27% (211/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 28% (219/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 29% (227/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 30% (235/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 31% (243/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 32% (250/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 33% (258/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 34% (266/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 35% (274/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 36% (282/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 37% (289/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 38% (297/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 39% (305/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 40% (313/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 41% (321/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 42% (329/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 43% (336/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 44% (344/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 45% (352/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 46% (360/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 47% (368/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 48% (375/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 49% (383/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 50% (391/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 51% (399/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 52% (407/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 53% (414/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 54% (422/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 55% (430/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 56% (438/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 57% (446/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 58% (453/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 59% (461/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 60% (469/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 61% (477/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 62% (485/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 63% (493/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 64% (500/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 65% (508/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 66% (516/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 67% (524/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 68% (532/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 69% (539/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 70% (547/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 71% (555/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 72% (563/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 73% (571/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 74% (578/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 75% (586/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 76% (594/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 77% (602/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 78% (610/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 79% (617/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 80% (625/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 81% (633/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 82% (641/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 83% (649/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 84% (657/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 85% (664/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 86% (672/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 87% (680/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 88% (688/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 89% (696/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 90% (703/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 91% (711/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 92% (719/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 93% (727/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 94% (735/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 95% (742/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 96% (750/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 97% (758/781), 899.71 KiB | 1.73 MiB/s remote: Total 781 (delta 0), reused 781 (delta 0) 2026-10-23T15:11:52.531Z Receiving objects: 98% (766/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 99% (774/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 100% (781/781), 899.71 KiB | 1.73 MiB/s Receiving objects: 100% (781/781), 3.57 MiB | 4.11 MiB/s, done. 2026-10-23T15:11:52.599Z From https://diffinery.com/codician/diffinery 2026-10-23T15:11:52.599Z * [new ref] 274d35077218e914c8aba0ad6f2e3567dffdf605 -> origin/diffinery-checkout 2026-10-23T15:11:52.696Z Note: switching to '274d35077218e914c8aba0ad6f2e3567dffdf605'. 2026-10-23T15:11:52.696Z 2026-10-23T15:11:52.696Z You are in 'detached HEAD' state. You can look around, make experimental 2026-10-23T15:11:52.696Z changes and commit them, and you can discard any commits you make in this 2026-10-23T15:11:52.696Z state without impacting any branches by switching back to a branch. 2026-10-23T15:11:52.696Z 2026-10-23T15:11:52.696Z If you want to create a new branch to retain commits you create, you may 2026-10-23T15:11:52.696Z do so (now or later) by using -c with the switch command. Example: 2026-10-23T15:11:52.696Z 2026-10-23T15:11:52.696Z git switch -c 2026-10-23T15:11:52.696Z 2026-10-23T15:11:52.696Z Or undo this operation with: 2026-10-23T15:11:52.696Z 2026-10-23T15:11:52.696Z git switch - 2026-10-23T15:11:52.696Z 2026-10-23T15:11:52.696Z Turn off this advice by setting config variable advice.detachedHead to false 2026-10-23T15:11:52.696Z 2026-10-23T15:11:52.696Z HEAD is now at 274d350 Merge db64d539821489de9c55c19b92898f70e8bc02db into 294f5fa63e01248d04a89f599af9d874033dcc94 2026-10-23T15:11:52.703Z HEAD is now at 274d35077218e914c8aba0ad6f2e3567dffdf605 2026-10-23T15:11:53.161Z Download action repository 'pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1' 2026-10-23T15:11:53.481Z ##[group]Run pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1 2026-10-23T15:11:53.481Z with: 2026-10-23T15:11:53.481Z dest: ~/setup-pnpm 2026-10-23T15:11:53.481Z run_install: null 2026-10-23T15:11:53.481Z cache: false 2026-10-23T15:11:53.481Z cache_dependency_path: pnpm-lock.yaml 2026-10-23T15:11:53.481Z package_json_file: package.json 2026-10-23T15:11:53.481Z standalone: false 2026-10-23T15:11:53.481Z ##[endgroup] 2026-10-23T15:11:53.685Z ##[group]Running self-installer... 2026-10-23T15:11:54.535Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-23T15:11:54.546Z Packages: +1 2026-10-23T15:11:54.546Z + 2026-10-23T15:11:55.161Z Progress: resolved 1, reused 0, downloaded 1, added 1, done 2026-10-23T15:11:55.195Z 2026-10-23T15:11:55.195Z dependencies: 2026-10-23T15:11:55.195Z + pnpm 10.28.0 (12.15.0 is available) 2026-10-23T15:11:55.195Z 2026-10-23T15:11:55.199Z Done in 1.2s 2026-10-23T15:11:55.224Z ##[endgroup] 2026-10-23T15:11:55.224Z Installation Completed! 2026-10-23T15:11:55.594Z ##[group]Run actions/setup-node@v4 2026-10-23T15:11:55.594Z with: 2026-10-23T15:11:55.594Z node-version: 22 2026-10-23T15:11:55.594Z cache: pnpm 2026-10-23T15:11:55.594Z ##[endgroup] 2026-10-23T15:11:55.603Z Found in cache @ 22.22.0 (pre-installed node satisfies '22') 2026-10-23T15:11:56.810Z Cache Size: ~216 MB (226493609 B) 2026-10-23T15:12:02.105Z Cache restored from key: node-cache-Linux-x64-pnpm-a02ba8dce5cb7329b868883337d1a03f862819a15859861dae22d3a8b1092f41 2026-10-23T15:12:02.467Z ##[group]Run pnpm install --frozen-lockfile 2026-10-23T15:12:02.467Z ##[endgroup] 2026-10-23T15:12:02.917Z Scope: all 8 workspace projects 2026-10-23T15:12:02.982Z Lockfile is up to date, resolution step is skipped 2026-10-23T15:12:03.046Z Progress: resolved 1, reused 0, downloaded 0, added 0 2026-10-23T15:12:03.099Z Packages: +250 2026-10-23T15:12:03.099Z ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2026-10-23T15:12:04.051Z Progress: resolved 250, reused 244, downloaded 0, added 166 2026-10-23T15:12:04.688Z Progress: resolved 250, reused 244, downloaded 0, added 250, done 2026-10-23T15:12:04.836Z .../esbuild@0.28.1/node_modules/esbuild postinstall$ node install.js 2026-10-23T15:12:04.837Z .../esbuild@0.25.12/node_modules/esbuild postinstall$ node install.js 2026-10-23T15:12:04.838Z .../esbuild@0.25.11/node_modules/esbuild postinstall$ node install.js 2026-10-23T15:12:04.850Z .../node_modules/workerd postinstall$ node install.js 2026-10-23T15:12:04.890Z .../node_modules/workerd postinstall$ node install.js 2026-10-23T15:12:04.939Z .../esbuild@0.25.11/node_modules/esbuild postinstall: Done 2026-10-23T15:12:04.947Z .../esbuild@0.28.2/node_modules/esbuild postinstall$ node install.js 2026-10-23T15:12:04.962Z .../esbuild@0.25.12/node_modules/esbuild postinstall: Done 2026-10-23T15:12:05.112Z .../esbuild@0.28.1/node_modules/esbuild postinstall: Done 2026-10-23T15:12:05.140Z .../node_modules/workerd postinstall: Done 2026-10-23T15:12:05.342Z .../node_modules/workerd postinstall: Done 2026-10-23T15:12:05.349Z .../esbuild@0.28.2/node_modules/esbuild postinstall: Done 2026-10-23T15:12:05.926Z 2026-10-23T15:12:05.926Z devDependencies: 2026-10-23T15:12:05.926Z + turbo 2.11.7 2026-10-23T15:12:05.926Z + typescript 5.9.3 2026-10-23T15:12:05.926Z 2026-10-23T15:12:06.466Z Done in 3.9s using pnpm v10.28.0 2026-10-23T15:12:06.860Z ##[group]Run pnpm -r --if-present build 2026-10-23T15:12:06.860Z ##[endgroup] 2026-10-23T15:12:07.220Z Scope: 7 of 8 workspace projects 2026-10-23T15:12:07.225Z apps/cli build$ esbuild src/bin.ts --bundle --platform=node --target=node22 --format=esm --outfile=dist/diffinery.mjs "--banner:js=#!/usr/bin/env node 2026-10-23T15:12:07.225Z import { createRequire as __diffineryCreateRequire } from 'node:module'; const require = __diffineryCreateRequire(import.meta.url);" 2026-10-23T15:12:07.225Z apps/diffinery build$ node islands/build.mjs && node scripts/build-docs.mjs 2026-10-23T15:12:07.226Z 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);" 2026-10-23T15:12:07.324Z containers/runner build: dist/agent.mjs 684.1kb 2026-10-23T15:12:07.326Z containers/runner build: ⚡ Done in 76ms 2026-10-23T15:12:07.327Z apps/cli build: dist/diffinery.mjs 465.9kb 2026-10-23T15:12:07.327Z apps/cli build: ⚡ Done in 82ms 2026-10-23T15:12:07.330Z containers/runner build: Done 2026-10-23T15:12:07.331Z apps/cli build: Done 2026-10-23T15:12:08.199Z apps/diffinery build: islands: kumo.js 466 KB, kumo.css 149 KB, terminal.js 286 KB 2026-10-23T15:12:08.572Z apps/diffinery build: docs: 75 pages (+2 generated at runtime), 10 site pages, 11 images, CLI 0.1.0 (248 KiB), editor extension 0.1.1 (20 KiB), JetBrains plugin 0.1.0 (64 KiB), Claude Code plugins diffinery 0.1.1, diffinery-ci 0.2.0 2026-10-23T15:12:08.582Z apps/diffinery build: Done 2026-10-23T15:12:09.150Z ##[group]Run as_root() { if [ "$(id -u)" = 0 ]; then "$@"; else sudo "$@"; fi; } 2026-10-23T15:12:09.150Z if ! command -v bwrap >/dev/null; then 2026-10-23T15:12:09.150Z as_root apt-get install -y --no-install-recommends bubblewrap || { as_root apt-get update -qq && as_root apt-get install -y --no-install-recommends bubblewrap; } 2026-10-23T15:12:09.150Z fi 2026-10-23T15:12:09.150Z as_root sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 2>/dev/null || true 2026-10-23T15:12:09.150Z bwrap --unshare-all --ro-bind / / --dev /dev --proc /proc -- true 2026-10-23T15:12:09.150Z ##[endgroup] 2026-10-23T15:12:09.550Z ##[group]Run # Shards of similar length; a new test file runs in "rest" unless it's added to another. 2026-10-23T15:12:09.550Z core='/e2e\.test\.mjs$' 2026-10-23T15:12:09.550Z agents='/(agentic|review|tasks)\.test\.mjs$' 2026-10-23T15:12:09.550Z # security.test.mjs, security-*.test.mjs (security-txt's too) and status.test.mjs. 2026-10-23T15:12:09.550Z security='/(security(-[a-z-]+)?|status)\.test\.mjs$' 2026-10-23T15:12:09.550Z # The core file's real histories and large pushes take minutes each (jquery's alone 2 to 3 on 2026-10-23T15:12:09.550Z # Diffinery's runners): two shards of their own, so no part of the file runs into node's 2026-10-23T15:12:09.550Z # per-file timeout, which is the --test-timeout here. 2026-10-23T15:12:09.550Z histories='^real histories:' 2026-10-23T15:12:09.550Z large='^(large files|large pushes):' 2026-10-23T15:12:09.550Z opts=(--test-timeout=600000) 2026-10-23T15:12:09.550Z case "agents" in 2026-10-23T15:12:09.550Z core) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-skip-pattern="$histories" --test-skip-pattern="$large") ;; 2026-10-23T15:12:09.550Z histories) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts=(--test-timeout=900000 --test-name-pattern="$histories") ;; 2026-10-23T15:12:09.550Z large) files=$(ls test/e2e/*.test.mjs | grep -E "$core"); opts+=(--test-name-pattern="$large") ;; 2026-10-23T15:12:09.550Z agents) files=$(ls test/e2e/*.test.mjs | grep -E "$agents") ;; 2026-10-23T15:12:09.550Z security) files=$(ls test/e2e/*.test.mjs | grep -E "$security") ;; 2026-10-23T15:12:09.550Z *) files=$(ls test/e2e/*.test.mjs | grep -vE "$core|$agents|$security") ;; 2026-10-23T15:12:09.550Z esac 2026-10-23T15:12:09.550Z echo "$files" 2026-10-23T15:12:09.550Z # Two files at a time: each starts its own local server on its own port, database and 2026-10-23T15:12:09.550Z # directory, so they don't share state, and a file's server mostly keeps one core busy. 2026-10-23T15:12:09.550Z node --test --test-concurrency=2 "${opts[@]}" $files 2026-10-23T15:12:09.550Z ##[endgroup] 2026-10-23T15:12:09.572Z test/e2e/agentic.test.mjs 2026-10-23T15:12:09.572Z test/e2e/review.test.mjs 2026-10-23T15:12:09.572Z test/e2e/tasks.test.mjs 2026-10-23T15:12:09.627Z TAP version 13 2026-10-23T15:12:36.867Z # Subtest: Today: what needs you, your agents' work and what landed 2026-10-23T15:12:36.868Z ok 1 - Today: what needs you, your agents' work and what landed 2026-10-23T15:12:36.868Z --- 2026-10-23T15:12:36.868Z duration_ms: 27166.392515 2026-10-23T15:12:36.868Z type: 'test' 2026-10-23T15:12:36.868Z ... 2026-10-23T15:13:26.940Z # Subtest: agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-23T15:13:26.940Z ok 2 - agent review: on open, inline findings and a failing check; autofix; the re-review marks it fixed 2026-10-23T15:13:26.940Z --- 2026-10-23T15:13:26.940Z duration_ms: 77238.408244 2026-10-23T15:13:26.940Z type: 'test' 2026-10-23T15:13:26.940Z ... 2026-10-23T15:13:42.674Z # Subtest: agent review: Fix it, asking for a review, and who may 2026-10-23T15:13:42.675Z ok 3 - agent review: Fix it, asking for a review, and who may 2026-10-23T15:13:42.675Z --- 2026-10-23T15:13:42.675Z duration_ms: 15735.106701 2026-10-23T15:13:42.675Z type: 'test' 2026-10-23T15:13:42.675Z ... 2026-10-23T15:14:32.955Z # Subtest: agent review: spend limits per review (requests, tokens) and per repository 2026-10-23T15:14:32.955Z ok 4 - agent review: spend limits per review (requests, tokens) and per repository 2026-10-23T15:14:32.955Z --- 2026-10-23T15:14:32.955Z duration_ms: 50220.829205 2026-10-23T15:14:32.955Z type: 'test' 2026-10-23T15:14:32.955Z ... 2026-10-23T15:14:42.091Z # Subtest: model keys: write-only, browser session only, with an opt-in 2026-10-23T15:14:42.091Z ok 5 - model keys: write-only, browser session only, with an opt-in 2026-10-23T15:14:42.091Z --- 2026-10-23T15:14:42.091Z duration_ms: 7065.158592 2026-10-23T15:14:42.091Z type: 'test' 2026-10-23T15:14:42.091Z ... 2026-10-23T15:14:42.091Z # Subtest: an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-23T15:14:42.091Z ok 6 - an agent task runs in a sandbox as the agent, through the model proxy, and opens a pull request 2026-10-23T15:14:42.091Z --- 2026-10-23T15:14:42.091Z duration_ms: 9236.601312 2026-10-23T15:14:42.091Z type: 'test' 2026-10-23T15:14:42.091Z ... 2026-10-23T15:14:42.092Z # Subtest: task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-23T15:14:42.092Z ok 7 - task sandboxes are closed to the sandbox API, and stopping ends the run's access 2026-10-23T15:14:42.092Z --- 2026-10-23T15:14:42.092Z duration_ms: 3961.986577 2026-10-23T15:14:42.092Z type: 'test' 2026-10-23T15:14:42.092Z ... 2026-10-23T15:14:42.092Z # Subtest: a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-23T15:14:42.093Z ok 8 - a repository is a project: settings, memory, conversation, and a queue of tasks 2026-10-23T15:14:42.093Z --- 2026-10-23T15:14:42.093Z duration_ms: 16001.899619 2026-10-23T15:14:42.093Z type: 'test' 2026-10-23T15:14:42.093Z ... 2026-10-23T15:14:42.093Z # Subtest: a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-23T15:14:42.093Z ok 9 - a coordinator turns posts into tasks, within its caps, and acts only through a validated block 2026-10-23T15:14:42.093Z --- 2026-10-23T15:14:42.093Z duration_ms: 25696.855432 2026-10-23T15:14:42.093Z type: 'test' 2026-10-23T15:14:42.093Z ... 2026-10-23T15:14:42.093Z # Subtest: plan first: a read-only plan run, then approve, change or split the plan 2026-10-23T15:14:42.093Z ok 10 - plan first: a read-only plan run, then approve, change or split the plan 2026-10-23T15:14:42.093Z --- 2026-10-23T15:14:42.093Z duration_ms: 24155.120579 2026-10-23T15:14:42.093Z type: 'test' 2026-10-23T15:14:42.093Z ... 2026-10-23T15:14:42.093Z # Subtest: best of N: attempts run side by side on their own branches, then one is picked 2026-10-23T15:14:42.093Z ok 11 - best of N: attempts run side by side on their own branches, then one is picked 2026-10-23T15:14:42.093Z --- 2026-10-23T15:14:42.093Z duration_ms: 9060.945273 2026-10-23T15:14:42.093Z type: 'test' 2026-10-23T15:14:42.093Z ... 2026-10-23T15:14:42.093Z # Subtest: verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-23T15:14:42.093Z ok 12 - verify and land: failing checks start a fix run, and an approved pull request lands 2026-10-23T15:14:42.093Z --- 2026-10-23T15:14:42.093Z duration_ms: 12396.799117 2026-10-23T15:14:42.093Z type: 'test' 2026-10-23T15:14:42.093Z ... 2026-10-23T15:14:42.093Z # Subtest: organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-23T15:14:42.093Z ok 13 - organizations: an agent policy, model keys only owners hold, and whose key pays (phase 5b) 2026-10-23T15:14:42.093Z --- 2026-10-23T15:14:42.093Z duration_ms: 17493.28848 2026-10-23T15:14:42.093Z type: 'test' 2026-10-23T15:14:42.093Z ... 2026-10-23T15:14:43.925Z # Subtest: losing access to the agent stops the task 2026-10-23T15:14:43.925Z ok 14 - losing access to the agent stops the task 2026-10-23T15:14:43.925Z --- 2026-10-23T15:14:43.925Z duration_ms: 1627.978248 2026-10-23T15:14:43.925Z type: 'test' 2026-10-23T15:14:43.925Z ... 2026-10-23T15:14:43.945Z 1..14 2026-10-23T15:14:43.945Z # tests 14 2026-10-23T15:14:43.945Z # suites 0 2026-10-23T15:14:43.945Z # pass 14 2026-10-23T15:14:43.945Z # fail 0 2026-10-23T15:14:43.945Z # cancelled 0 2026-10-23T15:14:43.945Z # skipped 0 2026-10-23T15:14:43.945Z # todo 0 2026-10-23T15:14:43.945Z # duration_ms 154336.874908 2026-10-23T15:14:44.326Z Cache hit occurred on the primary key node-cache-Linux-x64-pnpm-a02ba8dce5cb7329b868883337d1a03f862819a15859861dae22d3a8b1092f41, not saving cache. 2026-10-23T15:14:44.849Z Pruning is unnecessary. 2026-10-23T15:14:45.201Z Removing persisted credentials 2026-10-23T15:14:45.373Z Host: 2% of the vCPUs' time went to other work on the host (steal) 2026-10-23T15:14:45.373Z Job completed with conclusion: success 2026-10-23T15:14:45.374Z 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