Review-ready crewwork/fix-checkout-total into main
Hand off software work. Review the result.
CrewWork helps small engineering teams turn feature requests and production errors into review-ready changes. It plans, implements, and validates on infrastructure you control, so you can focus on the decisions that need you.
TypeError: Cannot read properties of undefined (reading 'amount')at orderTotal (src/checkout/total.ts:43)
export function orderTotal(cart: Cart): number { return cart.lines.reduce((sum, line) => {removed: const discount = line.discount.amount;added: // Lines without a promotion carry no discount.added: const discount = line.discount?.amount ?? 0; return sum + line.price * line.quantity - discount; }, 0);}Checks
- “All tests pass.” model-reported, not counted
- Tests passed · platform-run
- Coverage passed · platform-run
- Security scan passed · platform-run
- Code health passed · platform-run
- Live preview passed · platform-run
Review-ready. A person decides what merges.
From request or error to review-ready change.
Signal
Choose a request or production error. CrewWork keeps the project and available context with the work.
Plan
Choose whether to start work now or review the proposed plan before execution.
Implement
The change is written in an isolated worktree, with project context from the indexed codebase.
Validate and repair
Required checks run on the platform. Failures go back for repair, bounded by your configured limits.
Review-ready
You decide from the diff, the executed checks, and remaining risk. Publication follows your project settings and permissions; the change can remain on a local branch.
Give work a system that can carry it through.
CrewWork keeps track of the work around the coding agent: project context, execution limits, recovery, validation, and the evidence you need to review.
How CrewWork comparesWhat counts as done
- Checks carry their source
- CrewWork records which checks it ran. A model’s own claim that a test passed does not count as completion evidence.
- Missing evidence is a failure
- Required checks must run and pass. If the validator is degraded or absent, the run fails rather than resting on the model’s verdict.
- Results are checked against evidence
- CrewWork compares the model’s report with the checks it ran and records a failed result when required validation fails.
Passing checks establish what was verified. They do not guarantee that every possible defect has been found.
Read how verification worksCrewWork builds CrewWork.
CrewWork can apply a governed delivery process to its own codebase. Platform Self-Repair is off by default and produces changes for human review.
Explore Platform Self-Repair- plan a change to CrewWork’s own codebase
- isolate the candidate runs in an isolated worktree
- attest a promotion test matrix, attested by the trusted incumbent build
- publish a draft pull request
- decide a person reviews; the lane never merges its own changes
Your hardware, your models
What self-hosting involves- application
- One Docker Compose host runs the workspace, workers, and data services.
- generation
- The reference setup uses the open-weight Qwen3.8 27B for planning, coding, review, extraction, and chat. You can choose your own configured endpoints.
- code search
- A separate embedding model supports semantic search.
- other models
- Each lane’s model and endpoint can be configured separately; public endpoints require explicit opt-in.
See whether CrewWork fits your work.
CrewWork is built and running, and not yet generally available.
- worth discussing
- The errors and backlog you would hand off
- Where your source has to stay
- The evidence you would need to trust a change