AI payload generation added to task testing suite
Testing background tasks just got easier with a new AI-powered payload generator that reads your schemas and source code to instantly mock valid test data.
Developers can now for background tasks directly from the UI, removing the friction of manually constructing complex test data.
The Test page now features a dedicated sidebar with AI and Schema tabs. Instead of guessing required fields, users can prompt an AI to generate test data that perfectly matches the task's expectations. The system even if an explicit payload shape isn't defined.
Under the hood, the backend streams responses from OpenAI directly to the browser. If a task lacks a strict JSON Schema, the AI uses a fallback tool to . It analyzes the task's function signature and internal variable usage to mathematically determine the correct payload shape before generating the mock data.
View Original GitHub Description
Add a tabbed sidebar to the Test page for standard tasks, reusing the ClientTabs pattern from the Query page.
- Options tab: existing sidebar content (machine, version, queue, etc.)
- AI tab: AI-powered payload generation with streaming, supports JSON Schema, inferred schema from recent runs, and task source code lookup via tool calling for tasks without schemas
- Schema tab: displays payload JSON Schema (from schemaTask), inferred schema (from recent runs via @jsonhero/schema-infer), or empty state with schemaTask docs and example code
Data layer changes:
- Surface payloadSchema and inferredPayloadSchema from TestTaskPresenter
- Add payloadSchema and fileId to WorkerDeploymentWithWorkerTasks type
- Decompress zlib-deflated source files for AI context