e969ca5573
Restructure verification strategy from binary (TDD xor manual) to layered (TDD AND/OR agent QA). Elevate zero-human-intervention as universal principle, require per-scenario ultra-detailed QA format with named scenarios, negative cases, and evidence capture. Remove ambiguous 'manual QA' terminology.
85 lines
2.6 KiB
TypeScript
85 lines
2.6 KiB
TypeScript
import { describe, test, expect } from "bun:test"
|
|
import { PROMETHEUS_SYSTEM_PROMPT } from "./prometheus"
|
|
|
|
describe("PROMETHEUS_SYSTEM_PROMPT Momus invocation policy", () => {
|
|
test("should direct providing ONLY the file path string when invoking Momus", () => {
|
|
//#given
|
|
const prompt = PROMETHEUS_SYSTEM_PROMPT
|
|
|
|
//#when / #then
|
|
expect(prompt.toLowerCase()).toMatch(/momus.*only.*path|path.*only.*momus/)
|
|
})
|
|
|
|
test("should forbid wrapping Momus invocation in explanations or markdown", () => {
|
|
//#given
|
|
const prompt = PROMETHEUS_SYSTEM_PROMPT
|
|
|
|
//#when / #then
|
|
expect(prompt.toLowerCase()).toMatch(/not.*wrap|no.*explanation|no.*markdown/)
|
|
})
|
|
})
|
|
|
|
describe("PROMETHEUS_SYSTEM_PROMPT zero human intervention", () => {
|
|
test("should enforce universal zero human intervention rule", () => {
|
|
//#given
|
|
const prompt = PROMETHEUS_SYSTEM_PROMPT
|
|
|
|
//#when
|
|
const lowerPrompt = prompt.toLowerCase()
|
|
|
|
//#then
|
|
expect(lowerPrompt).toContain("zero human intervention")
|
|
expect(lowerPrompt).toContain("forbidden")
|
|
expect(lowerPrompt).toMatch(/user manually tests|사용자가 직접 테스트/)
|
|
})
|
|
|
|
test("should require agent-executed QA scenarios as mandatory for all tasks", () => {
|
|
//#given
|
|
const prompt = PROMETHEUS_SYSTEM_PROMPT
|
|
|
|
//#when
|
|
const lowerPrompt = prompt.toLowerCase()
|
|
|
|
//#then
|
|
expect(lowerPrompt).toContain("agent-executed qa scenarios")
|
|
expect(lowerPrompt).toMatch(/mandatory.*all tasks|all tasks.*mandatory/)
|
|
})
|
|
|
|
test("should not contain ambiguous 'manual QA' terminology", () => {
|
|
//#given
|
|
const prompt = PROMETHEUS_SYSTEM_PROMPT
|
|
|
|
//#when / #then
|
|
expect(prompt).not.toMatch(/manual QA procedures/i)
|
|
expect(prompt).not.toMatch(/manual verification procedures/i)
|
|
expect(prompt).not.toMatch(/Manual-only/i)
|
|
})
|
|
|
|
test("should require per-scenario format with detailed structure", () => {
|
|
//#given
|
|
const prompt = PROMETHEUS_SYSTEM_PROMPT
|
|
|
|
//#when
|
|
const lowerPrompt = prompt.toLowerCase()
|
|
|
|
//#then
|
|
expect(lowerPrompt).toContain("preconditions")
|
|
expect(lowerPrompt).toContain("failure indicators")
|
|
expect(lowerPrompt).toContain("evidence")
|
|
expect(lowerPrompt).toMatch(/negative scenario/)
|
|
})
|
|
|
|
test("should require QA scenario adequacy in self-review checklist", () => {
|
|
//#given
|
|
const prompt = PROMETHEUS_SYSTEM_PROMPT
|
|
|
|
//#when
|
|
const lowerPrompt = prompt.toLowerCase()
|
|
|
|
//#then
|
|
expect(lowerPrompt).toMatch(/every task has agent-executed qa scenarios/)
|
|
expect(lowerPrompt).toMatch(/happy-path and negative/)
|
|
expect(lowerPrompt).toMatch(/zero acceptance criteria require human/)
|
|
})
|
|
})
|