Files
chatgpt-mcp/test/prompts/debug-issue.test.js
T

410 lines
18 KiB
JavaScript

import { describe, it, expect } from "vitest";
import { buildDebugIssuePrompt } from "../../src/prompts/debug-issue.js";
describe("buildDebugIssuePrompt", () => {
// --- Basic output contract ---
it("returns a non-empty string given question-only input", () => {
const result = buildDebugIssuePrompt({ question: "Why is the API returning 500?" });
expect(typeof result).toBe("string");
expect(result.length).toBeGreaterThan(0);
});
it("is deterministic — same input always produces the same output", () => {
const a = buildDebugIssuePrompt({ question: "Why is the API returning 500?" });
const b = buildDebugIssuePrompt({ question: "Why is the API returning 500?" });
expect(a).toBe(b);
});
// --- Composition with base prompt ---
it("includes the base system prompt content", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("second-opinion assistant");
expect(result).toContain("Claude Code");
expect(result).toContain("not responsible for editing files");
});
it("contains a '---' separator between base and tool-specific sections", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
const parts = result.split("\n---\n");
expect(parts.length).toBe(2);
});
// --- debug_issue-specific role instructions ---
it("contains debugger/advisor role instruction", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("debugger/advisor");
});
it("instructs Claude Code as the implementation agent", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("Claude Code will implement your suggestions");
});
it("instructs ChatGPT that you do not implement anything yourself", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("you do not implement anything yourself");
});
// --- Claude Code / debugger guard rails ---
it("states Claude Code remains the implementation agent", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("Claude Code remains the implementation agent");
});
it("states ChatGPT is acting only as a debugger/advisor", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("acting only as a debugger/advisor");
});
it("instructs to use only supplied code, logs, and context", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("use only the code, logs, and context provided");
});
it("states ChatGPT does not have repository-wide visibility", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("does not have repository-wide visibility");
});
// --- Investigation dimensions ---
it("contains instruction to diagnose using only supplied evidence", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result.toLowerCase()).toContain("diagnose the reported issue using only");
});
it("contains instruction to identify likely root causes with confidence levels", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("most likely root causes");
expect(result.toLowerCase()).toContain("confidence levels");
});
it("contains instruction to distinguish evidence from assumptions", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result.toLowerCase()).toContain("distinguish evidence from assumptions");
});
it("contains instruction to highlight missing information", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toMatch(/highlight\s+missing\s+information/i);
});
it("contains instruction to suggest focused debugging steps", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result.toLowerCase()).toContain("suggest focused debugging steps");
});
it("contains instruction to suggest fixes only when supported by evidence", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toMatch(/fixes?\s+only\s+when.*supported\s+by.*evidence/i);
});
// --- Response structure (TASKS.md §7) ---
it("requests Summary section in response structure", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toMatch(/summary/i);
});
it("requests Likely Causes section with confidence levels in response structure", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("Likely Causes");
expect(result.toLowerCase()).toContain("confidence");
});
it("requests Fast Checks section in response structure", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("Fast Checks");
});
it("requests Minimal Safe Experiments section in response structure", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("Minimal Safe Experiments");
});
it("requests What Not To Do Yet section in response structure", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).toContain("What Not To Do Yet");
});
// --- Question field ---
it("appends the input question verbatim in the task section", () => {
const result = buildDebugIssuePrompt({ question: "Why does the API return 500?" });
expect(result).toContain("Question: Why does the API return 500?");
});
// --- Optional fields appended correctly (with question) ---
it("appends Context when context is provided", () => {
const result = buildDebugIssuePrompt({
question: "Why is the API returning 500?",
context: "The issue appeared after deploying v2.3.",
});
expect(result).toContain("Context: The issue appeared after deploying v2.3.");
});
it("does NOT append Context section when context is empty", () => {
const result = buildDebugIssuePrompt({ question: "Test", context: "" });
expect(result).not.toContain("Context:");
});
it("appends Constraints list when constraints are provided", () => {
const result = buildDebugIssuePrompt({
question: "Why is the API returning 500?",
constraints: ["Do not change the database schema", "Must be safe to deploy"],
});
expect(result).toContain("Constraints:");
expect(result).toContain("- Do not change the database schema");
expect(result).toContain("- Must be safe to deploy");
});
it("does NOT append Constraints section when constraints array is empty", () => {
const result = buildDebugIssuePrompt({ question: "Test", constraints: [] });
expect(result).not.toContain("Constraints:");
});
it("appends Expected output when expectedOutput is provided", () => {
const result = buildDebugIssuePrompt({
question: "Why is the API returning 500?",
expectedOutput: "A root-cause analysis with confidence levels.",
});
expect(result).toContain(
"Expected output: A root-cause analysis with confidence levels."
);
});
it("does NOT append Expected output section when expectedOutput is omitted", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).not.toContain("Expected output:");
});
it("does NOT append Expected output section when expectedOutput is empty", () => {
const result = buildDebugIssuePrompt({ question: "Test", expectedOutput: "" });
expect(result).not.toContain("Expected output:");
});
it("appends all optional fields alongside each other", () => {
const result = buildDebugIssuePrompt({
question: "Why is the API returning 500?",
context: "The issue appeared after deploying v2.3.",
constraints: ["Do not change the database schema", "Must be safe to deploy"],
expectedOutput: "A root-cause analysis with confidence levels.",
projectSummary: "E-commerce platform using Express + PostgreSQL.",
taskSummary: "Stripe webhook handler processes recurring payment events.",
});
expect(result).toContain("Question: Why is the API returning 500?");
expect(result).toContain("Context: The issue appeared after deploying v2.3.");
expect(result).toContain("Constraints:");
expect(result).toContain("- Do not change the database schema");
expect(result).toContain("- Must be safe to deploy");
expect(result).toContain("Expected output: A root-cause analysis with confidence levels.");
expect(result).toContain("Project summary: E-commerce platform using Express + PostgreSQL.");
expect(result).toContain(
"Task summary: Stripe webhook handler processes recurring payment events."
);
});
it("does NOT append Project summary when projectSummary is omitted", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).not.toContain("Project summary:");
});
it("does NOT append Task summary when taskSummary is omitted", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).not.toContain("Task summary:");
});
// --- relevantFiles (present) ---
it("includes file section header when relevantFiles is provided", () => {
const result = buildDebugIssuePrompt({
question: "Why does the API return 500?",
relevantFiles: [{ path: "src/webhooks/stripe.js", content: "app.post('/webhook', handler);" }],
});
expect(result).toContain("Relevant files:");
});
it("includes file path, language, and content when relevantFiles has language", () => {
const result = buildDebugIssuePrompt({
question: "Why does the API return 500?",
relevantFiles: [
{ path: "src/webhooks/stripe.js", language: "javascript", content: "app.post('/webhook', handler);" },
],
});
expect(result).toContain("File: src/webhooks/stripe.js");
expect(result).toContain("Language: javascript");
expect(result).toContain("app.post('/webhook', handler);");
});
it("includes file content without language header when language is omitted", () => {
const result = buildDebugIssuePrompt({
question: "Why does the API return 500?",
relevantFiles: [{ path: "src/webhooks/stripe.js", content: "app.post('/webhook', handler);" }],
});
expect(result).toContain("File: src/webhooks/stripe.js");
expect(result).not.toContain("Language:");
expect(result).toContain("app.post('/webhook', handler);");
});
it("includes multiple files when relevantFiles has multiple entries", () => {
const result = buildDebugIssuePrompt({
question: "Why does the API return 500?",
relevantFiles: [
{ path: "src/webhooks/stripe.js", language: "javascript", content: "app.post('/webhook', handler);" },
{ path: "src/utils/notifications.js", language: "javascript", content: "// no tests" },
],
});
expect(result).toContain("File: src/webhooks/stripe.js");
expect(result).toContain("File: src/utils/notifications.js");
expect(result).toContain("app.post('/webhook', handler);");
expect(result).toContain("// no tests");
});
// --- relevantFiles (absent/empty) ---
it("does NOT include Relevant files section when relevantFiles is omitted", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).not.toContain("Relevant files:");
});
it("does NOT include Relevant files section when relevantFiles is empty array", () => {
const result = buildDebugIssuePrompt({ question: "Test", relevantFiles: [] });
expect(result).not.toContain("Relevant files:");
});
// --- logs (present) ---
it("includes Logs section with content when logs is provided", () => {
const result = buildDebugIssuePrompt({
question: "Why does the API return 500?",
logs: "ERROR TypeError: Cannot read properties of undefined",
});
expect(result).toContain("Logs:");
expect(result).toContain("ERROR TypeError: Cannot read properties of undefined");
});
it("does NOT include Logs section when logs is absent", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).not.toContain("Logs:");
});
it("does NOT include Logs section when logs is empty string", () => {
const result = buildDebugIssuePrompt({ question: "Test", logs: "" });
expect(result).not.toContain("Logs:");
});
// --- Tool-specific guard ---
it("does NOT contain review_code specific content", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result.toLowerCase()).not.toContain("issues by severity");
expect(result.toLowerCase()).not.toContain("suggested fixes");
});
it("does NOT contain review_plan specific content", () => {
const result = buildDebugIssuePrompt({ question: "Test" });
expect(result).not.toContain("missing steps");
expect(result).not.toContain("scope creep");
});
// --- Input validation ---
it("throws TypeError when input is missing, null, or undefined", () => {
expect(() => buildDebugIssuePrompt()).toThrow(TypeError);
expect(() => buildDebugIssuePrompt(null)).toThrow(TypeError);
expect(() => buildDebugIssuePrompt(undefined)).toThrow(TypeError);
});
it("throws TypeError when question is missing", () => {
expect(() => buildDebugIssuePrompt({ context: "something" })).toThrow(TypeError);
});
it("throws TypeError when question is empty", () => {
expect(() => buildDebugIssuePrompt({ question: "" })).toThrow(TypeError);
});
// --- Full integration test ---
it("returns a well-formed two-part prompt with all fields, relevantFiles, and logs", () => {
const result = buildDebugIssuePrompt({
question: "Why does the payment endpoint return 500 for recurring invoices?",
context: "The issue appeared after deploying v2.3. Only affects Stripe webhooks with retry logic.",
constraints: ["Do not change the database schema", "Must be safe to deploy during business hours"],
expectedOutput: "A root-cause analysis with confidence levels and minimal debugging steps.",
projectSummary: "E-commerce platform using Express + PostgreSQL, deployed on EC2.",
taskSummary: "Stripe webhook handler processes recurring payment events.",
relevantFiles: [
{
path: "src/webhooks/stripe.js",
language: "javascript",
content: `app.post('/webhook/stripe', async (req, res) => {\n const sig = req.headers['stripe-signature'];\n const event = stripe.webhooks.constructEvent(req.body, sig);\n if (event.type === 'invoice.payment_failed') {\n await handlePaymentFailed(event.data.object);\n }\n res.sendStatus(200);\n});`,
},
],
logs: `2024-01-15T10:23:01Z ERROR StripeWebhookHandler: Failed to process event inv_1abc
at handlePaymentFailed (src/webhooks/stripe.js:14:9)
at IncomingMessage.<anonymous> (src/server.js:87:5)
TypeError: Cannot read properties of undefined (reading 'customer_email')
at formatRetryNotification (src/utils/notifications.js:23:35)`,
});
// Base section present
expect(result).toContain("second-opinion assistant");
expect(result).toContain("Rules:");
// Separator
expect(result).toMatch(/\n---\n/);
// Tool-specific section present
expect(result).toContain("debugger/advisor");
expect(result).toContain("Claude Code remains the implementation agent");
expect(result).toContain("repository-wide visibility");
// Investigation dimensions present
expect(result.toLowerCase()).toContain("diagnose the reported issue using only");
expect(result).toContain("most likely root causes");
expect(result.toLowerCase()).toContain("distinguish evidence from assumptions");
expect(result).toMatch(/highlight\s+missing\s+information/i);
expect(result.toLowerCase()).toContain("suggest focused debugging steps");
expect(result).toMatch(/fixes?\s+only\s+when.*supported\s+by.*evidence/i);
// Response structure present (TASKS.md §7)
expect(result).toMatch(/summary/i);
expect(result).toContain("Likely Causes");
expect(result.toLowerCase()).toContain("confidence");
expect(result).toContain("Fast Checks");
expect(result).toContain("Minimal Safe Experiments");
expect(result).toContain("What Not To Do Yet");
// All fields present verbatim
expect(result).toContain("Question: Why does the payment endpoint return 500 for recurring invoices?");
expect(result).toContain("Context: The issue appeared after deploying v2.3.");
expect(result).toContain("Constraints:");
expect(result).toContain("- Do not change the database schema");
expect(result).toContain("- Must be safe to deploy during business hours");
expect(result).toContain("Expected output: A root-cause analysis with confidence levels and minimal debugging steps.");
expect(result).toContain("Project summary: E-commerce platform using Express + PostgreSQL, deployed on EC2.");
expect(result).toContain("Task summary: Stripe webhook handler processes recurring payment events.");
// Relevant files present
expect(result).toContain("Relevant files:");
expect(result).toContain("File: src/webhooks/stripe.js");
expect(result).toContain("Language: javascript");
expect(result).toContain("app.post('/webhook/stripe', async (req, res) => {");
// Logs present
expect(result).toContain("Logs:");
expect(result).toContain("ERROR StripeWebhookHandler: Failed to process event inv_1abc");
expect(result).toContain("TypeError: Cannot read properties of undefined");
// Does not contain other tool content
expect(result.toLowerCase()).not.toContain("issues by severity");
expect(result).not.toContain("missing steps");
expect(result).not.toContain("scope creep");
});
});