Run a project's configured build and test commands, including type checks that detect inconsistent data types. Save pass or fail results, failure details, and logs so an automated editing loop can decide whether verification is complete.
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
Review the instructions the agent will receive before you install.
Spec §20.2 / §22.4: the "subjective critique-theater panel" is
not enough on its own — a code-migration / tune-collab run must
prove the build still passes. This atom shells out to the
project's declared test commands and emits structured signals the
devloop's until evaluator reads.
code/index.json +
plan.md's targetStack block).od plugin run --input testCommand='pnpm test').| framework | typecheck | test |
|---|---|---|
| next | pnpm typecheck | pnpm test |
| vite | pnpm typecheck | pnpm test |
| remix | pnpm typecheck | pnpm test |
| custom | (read from package.json.scripts) | (read from package.json.scripts) |
project-cwd/
└── critique/
├── build-test.json # { build: 'passing' | 'failing', tests: 'passing' | 'failing' | 'skipped', durationMs, commandsRun: [...], failures: [...] }
└── build-test.log # raw stdout / stderr (truncated to the runner's logBudgetBytes limit, default 1 MiB)
The atom emits two signals the devloop reads:
build.passing: boolean — the typecheck command exited 0.tests.passing: boolean — the test command exited 0.Plus the legacy critique.score so existing pipelines that read
the score keep working: 5 when both pass, 3 when only build
passes, 1 when both fail.
Pipelines wire the atom into a devloop:
{
"id": "verify",
"atoms": ["patch-edit", "build-test"],
"repeat": true,
"until": "(build.passing && tests.passing) || iterations >= 8"
}
patch-edit, and only when plan.steps's
current step is in completed state).tests: 'skipped' without a non-empty reason field.Implemented by the daemon runner in
apps/daemon/src/plugins/atoms/build-test.ts. It executes the configured
build and test commands, bounds runtime and captured logs, and persists the
report and log outputs above.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create a three-scene video composition in a retro pixel style using a Hyperframes HTML template. Customize titles, labels, and colors while preserving scene transitions, short scene durations, and repeatable animation timing.
Create and revise headlines, descriptions, and main text for paid social and search ads. Use it to develop ad copy options and refine wording through repeated rounds of revision.
Create a three-page editorial motion sequence with dark backgrounds, serif typography, staged text reveals, and chapter transitions. The result is a single HTML file suited to fashion-inspired storytelling and short visual presentations.
Inspect and test web pages through a browser automation command-line tool. Navigate, click, enter text, capture screenshots, and extract page details, with a focus on checking local OpenDesign previews and reviewing web app quality.
Plan an AI music album from its concept through lyric drafts, track order, and export. Intended for independent album experiments and brand soundtracks, with the full production workflow provided through a separately installed upstream bundle.
Create generative art, or images made with programmed rules, using p5.js. Fixed random seeds make each rendering reproducible, supporting procedural posters, still images that suggest motion, and studies of artistic frame composition.