feat: remove heuristics, go LLM-only with mocks + restructure
BREAKING: Heuristic fallback removed — LLM client now required Changes: - Remove extractFileHeuristic, extractPackageHeuristic, all helpers - extractFileLLM / extractPackageLLM now throw LLMError when client missing - Add hybrid binary detection: extension blacklist + content sniffing - Increase file size limit: 50KB → 500KB (text files only) - Restructure src/ into subdirectories: - src/llm/ — all LLM clients, extract, batch, cache, error - src/ast/ — AST extraction - src/cli/ — CLI entry point - Update all imports across codebase and tests - Add tests/mock-llm.ts helper for deterministic mock clients - Update all tests to use mock LLM clients (no heuristics dependency) - All 52 tests passing (including 8 real LLM integration tests)
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
import { describe, it, expect } from "vitest";
|
||||
import { extractFileAST } from "../src/ast-extract.js";
|
||||
import { extractFileAST } from "../src/ast/ast-extract.js";
|
||||
import { mkdtempSync, writeFileSync } from "fs";
|
||||
import { join } from "path";
|
||||
import { tmpdir } from "os";
|
||||
|
||||
@@ -11,6 +11,7 @@ import { tmpdir } from "os";
|
||||
import { initProject } from "../src/init.js";
|
||||
import { patchFile } from "../src/patch.js";
|
||||
import { validateMaps } from "../src/validate.js";
|
||||
import { createMockFileClient, createMockPackageClient } from "./mock-llm.js";
|
||||
|
||||
describe("integration", () => {
|
||||
let dir: string;
|
||||
@@ -26,25 +27,26 @@ describe("integration", () => {
|
||||
it("init creates .pi-map.md files", async () => {
|
||||
mkdirSync(join(dir, "src"));
|
||||
writeFileSync(join(dir, "src", "index.ts"), `export function foo() {}\n`);
|
||||
await initProject(dir);
|
||||
const client = createMockFileClient();
|
||||
await initProject(dir, { llmClient: client, verbose: false });
|
||||
|
||||
const map = readFileSync(join(dir, "src", ".pi-map.md"), "utf8");
|
||||
expect(map).toContain("# src");
|
||||
expect(map).toContain("foo");
|
||||
});
|
||||
|
||||
it("patch updates a file entry", async () => {
|
||||
mkdirSync(join(dir, "src"));
|
||||
writeFileSync(join(dir, "src", "index.ts"), `export function foo() {}\n`);
|
||||
writeFileSync(join(dir, "src", "utils.ts"), `export const bar = 1;\n`);
|
||||
await initProject(dir);
|
||||
const client = createMockFileClient();
|
||||
await initProject(dir, { llmClient: client, verbose: false });
|
||||
|
||||
// Modify a file
|
||||
writeFileSync(
|
||||
join(dir, "src", "index.ts"),
|
||||
`export function foo() {}\nexport function baz() {}\n`,
|
||||
);
|
||||
await patchFile(join(dir, "src", "index.ts"));
|
||||
await patchFile(join(dir, "src", "index.ts"), client, dir);
|
||||
|
||||
const map = readFileSync(join(dir, "src", ".pi-map.md"), "utf8");
|
||||
expect(map).toContain("baz");
|
||||
@@ -59,14 +61,15 @@ describe("integration", () => {
|
||||
`export const x${i} = ${i};\n`,
|
||||
);
|
||||
}
|
||||
await initProject(dir);
|
||||
const client = createMockFileClient();
|
||||
await initProject(dir, { llmClient: client, verbose: false });
|
||||
|
||||
// Modify a file
|
||||
writeFileSync(
|
||||
join(dir, "src", "file0.ts"),
|
||||
`export const x0 = 0;\nexport const y = 99;\n`,
|
||||
);
|
||||
await patchFile(join(dir, "src", "file0.ts"));
|
||||
await patchFile(join(dir, "src", "file0.ts"), client, dir);
|
||||
|
||||
const map = readFileSync(join(dir, "src", ".pi-map.md"), "utf8");
|
||||
expect(map).toContain("y");
|
||||
@@ -77,7 +80,8 @@ describe("integration", () => {
|
||||
it("validate detects new files", async () => {
|
||||
mkdirSync(join(dir, "src"));
|
||||
writeFileSync(join(dir, "src", "a.ts"), `export const a = 1;\n`);
|
||||
await initProject(dir);
|
||||
const client = createMockFileClient();
|
||||
await initProject(dir, { llmClient: client, verbose: false });
|
||||
|
||||
// Add new file
|
||||
writeFileSync(join(dir, "src", "b.ts"), `export const b = 2;\n`);
|
||||
@@ -91,7 +95,8 @@ describe("integration", () => {
|
||||
mkdirSync(join(dir, "src"));
|
||||
writeFileSync(join(dir, "src", "a.ts"), `export const a = 1;\n`);
|
||||
writeFileSync(join(dir, "src", "b.ts"), `export const b = 2;\n`);
|
||||
await initProject(dir);
|
||||
const client = createMockFileClient();
|
||||
await initProject(dir, { llmClient: client, verbose: false });
|
||||
|
||||
// Delete a file
|
||||
rmSync(join(dir, "src", "b.ts"));
|
||||
@@ -104,7 +109,8 @@ describe("integration", () => {
|
||||
it("validate detects changed signatures", async () => {
|
||||
mkdirSync(join(dir, "src"));
|
||||
writeFileSync(join(dir, "src", "a.ts"), `export const a = 1;\n`);
|
||||
await initProject(dir);
|
||||
const client = createMockFileClient();
|
||||
await initProject(dir, { llmClient: client, verbose: false });
|
||||
|
||||
// Change exports
|
||||
writeFileSync(
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { describe, it, expect } from "vitest";
|
||||
import { withRetry, processFiles } from "../src/llm-batch.js";
|
||||
import { withRetry, processFiles } from "../src/llm/llm-batch.js";
|
||||
import { LLMError } from "../src/llm-error.js";
|
||||
|
||||
describe("withRetry", () => {
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { describe, it, expect, beforeEach, afterEach } from "vitest";
|
||||
import { getCached, setCached } from "../src/llm-cache.js";
|
||||
import { getCached, setCached } from "../src/llm/llm-cache.js";
|
||||
import { existsSync, unlinkSync } from "fs";
|
||||
import { join } from "path";
|
||||
import { tmpdir } from "os";
|
||||
|
||||
+46
-86
@@ -1,67 +1,17 @@
|
||||
import { describe, it, expect } from "vitest";
|
||||
import { extractFileLLM, extractFileHeuristic } from "../src/llm-extract.js";
|
||||
import { extractFileLLM } from "../src/llm/llm-extract.js";
|
||||
import { writeFileSync, mkdtempSync } from "fs";
|
||||
import { join } from "path";
|
||||
import { tmpdir } from "os";
|
||||
import type { LLMClient } from "../src/llm-client.js";
|
||||
import type { LLMClient } from "../src/llm/llm-client.js";
|
||||
|
||||
describe("llm-extract heuristics", () => {
|
||||
it("extracts TypeScript exports", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
|
||||
const file = join(dir, "test.ts");
|
||||
writeFileSync(
|
||||
file,
|
||||
`export function foo() {}
|
||||
export class Bar {}
|
||||
export const baz = 1;
|
||||
export type Qux = string;
|
||||
export { a, b as c };
|
||||
`,
|
||||
);
|
||||
const result = await extractFileLLM(file);
|
||||
expect(result.exports).toContain("foo");
|
||||
expect(result.exports).toContain("Bar");
|
||||
expect(result.exports).toContain("baz");
|
||||
expect(result.exports).toContain("Qux");
|
||||
expect(result.exports).toContain("a");
|
||||
expect(result.exports).toContain("b");
|
||||
});
|
||||
|
||||
it("extracts TypeScript imports", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
|
||||
const file = join(dir, "test.ts");
|
||||
writeFileSync(
|
||||
file,
|
||||
`import { foo } from "./bar";
|
||||
import * as baz from "baz-lib";
|
||||
import type { Qux } from "qux";
|
||||
const x = require("legacy");
|
||||
`,
|
||||
);
|
||||
const result = await extractFileLLM(file);
|
||||
expect(result.deps).toContain("./bar");
|
||||
expect(result.deps).toContain("baz-lib");
|
||||
expect(result.deps).toContain("qux");
|
||||
expect(result.deps).toContain("legacy");
|
||||
});
|
||||
|
||||
it("infers purpose from filename patterns", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
|
||||
const file = join(dir, "userController.ts");
|
||||
writeFileSync(file, `export class UserController {}`);
|
||||
const result = await extractFileLLM(file);
|
||||
expect(result.purpose).toMatch(/Controller|Exports/);
|
||||
});
|
||||
|
||||
it("handles non-code files", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
|
||||
const file = join(dir, "Dockerfile");
|
||||
writeFileSync(file, `FROM node:20\nWORKDIR /app`);
|
||||
const result = await extractFileLLM(file);
|
||||
expect(result.purpose).toBe("Container definition");
|
||||
expect(result.exports).toEqual([]);
|
||||
});
|
||||
});
|
||||
function createMockClient(response: string): LLMClient {
|
||||
return {
|
||||
async complete() {
|
||||
return response;
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
describe("llm-extract with mock client", () => {
|
||||
it("uses LLM client when provided", async () => {
|
||||
@@ -69,11 +19,9 @@ describe("llm-extract with mock client", () => {
|
||||
const file = join(dir, "test.ts");
|
||||
writeFileSync(file, `export const foo = 1;`);
|
||||
|
||||
const mockClient: LLMClient = {
|
||||
async complete() {
|
||||
return "PURPOSE: Test file\nDEPS: none\nCONCEPTS: testing";
|
||||
},
|
||||
};
|
||||
const mockClient = createMockClient(
|
||||
"PURPOSE: Test file\nDEPS: none\nCONCEPTS: testing",
|
||||
);
|
||||
|
||||
const result = await extractFileLLM(file, mockClient, tmpdir());
|
||||
expect(result.purpose).toBe("Test file");
|
||||
@@ -81,42 +29,54 @@ describe("llm-extract with mock client", () => {
|
||||
expect(result.concepts).toContain("testing");
|
||||
});
|
||||
|
||||
it("throws without LLM client", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
|
||||
const file = join(dir, "test.ts");
|
||||
writeFileSync(file, `export const foo = 1;`);
|
||||
|
||||
await expect(extractFileLLM(file)).rejects.toThrow("No LLM client configured");
|
||||
});
|
||||
|
||||
it("skips large files", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
|
||||
const file = join(dir, "big.ts");
|
||||
writeFileSync(file, "x".repeat(60 * 1024));
|
||||
writeFileSync(file, "x".repeat(600 * 1024));
|
||||
|
||||
const mockClient: LLMClient = {
|
||||
async complete() {
|
||||
return "PURPOSE: Should not call\nDEPS: none\nCONCEPTS: none";
|
||||
},
|
||||
};
|
||||
const mockClient = createMockClient(
|
||||
"PURPOSE: Should not call\nDEPS: none\nCONCEPTS: none",
|
||||
);
|
||||
|
||||
const result = await extractFileLLM(file, mockClient);
|
||||
expect(result.purpose).toBe("Large/generated file");
|
||||
expect(result.purpose).toBe("Large file");
|
||||
});
|
||||
|
||||
it("falls back to heuristics without client", async () => {
|
||||
it("skips binary files", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
|
||||
const file = join(dir, "utils.ts");
|
||||
writeFileSync(file, `export function helper() {}`);
|
||||
const file = join(dir, "image.png");
|
||||
// Write some binary-looking content with null bytes
|
||||
const buf = Buffer.from([0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a]);
|
||||
writeFileSync(file, buf);
|
||||
|
||||
const result = await extractFileLLM(file);
|
||||
expect(result.purpose).toBe("Utility functions");
|
||||
expect(result.exports).toContain("helper");
|
||||
const mockClient = createMockClient(
|
||||
"PURPOSE: Should not call\nDEPS: none\nCONCEPTS: none",
|
||||
);
|
||||
|
||||
const result = await extractFileLLM(file, mockClient);
|
||||
expect(result.purpose).toBe("Binary file");
|
||||
});
|
||||
});
|
||||
|
||||
describe("extractFileHeuristic", () => {
|
||||
it("returns structured data", async () => {
|
||||
it("parses response with deps and concepts", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
|
||||
const file = join(dir, "test.ts");
|
||||
writeFileSync(file, `export const x = 1;`);
|
||||
writeFileSync(file, `import { foo } from "bar";\nexport const x = 1;`);
|
||||
|
||||
const result = await extractFileHeuristic(file);
|
||||
expect(result.purpose).toBeDefined();
|
||||
expect(Array.isArray(result.exports)).toBe(true);
|
||||
expect(Array.isArray(result.deps)).toBe(true);
|
||||
expect(Array.isArray(result.concepts)).toBe(true);
|
||||
const mockClient = createMockClient(
|
||||
"PURPOSE: Config module\nDEPS: bar, baz\nCONCEPTS: constants, config",
|
||||
);
|
||||
|
||||
const result = await extractFileLLM(file, mockClient, tmpdir());
|
||||
expect(result.purpose).toBe("Config module");
|
||||
expect(result.deps).toEqual(["bar", "baz"]);
|
||||
expect(result.concepts).toEqual(["constants", "config"]);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -2,9 +2,9 @@ import { describe, it, expect } from "vitest";
|
||||
import { writeFileSync, mkdtempSync, readFileSync } from "fs";
|
||||
import { join } from "path";
|
||||
import { tmpdir } from "os";
|
||||
import { createLLMClient } from "../src/llm-client.js";
|
||||
import { extractFileLLM, extractPackageLLM } from "../src/llm-extract.js";
|
||||
import { processFiles } from "../src/llm-batch.js";
|
||||
import { createLLMClient } from "../src/llm/llm-client.js";
|
||||
import { extractFileLLM, extractPackageLLM } from "../src/llm/llm-extract.js";
|
||||
import { processFiles } from "../src/llm/llm-batch.js";
|
||||
|
||||
// Load .env file manually (no dotenv dependency needed)
|
||||
function loadEnv(): Record<string, string> {
|
||||
@@ -135,7 +135,7 @@ describe.skipIf(!hasKimiKey)("LLM integration with Kimi", () => {
|
||||
it("skips large files without calling LLM", async () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "pi-map-llm-"));
|
||||
const file = join(dir, "big.ts");
|
||||
writeFileSync(file, "x".repeat(60 * 1024));
|
||||
writeFileSync(file, "x".repeat(600 * 1024));
|
||||
|
||||
let calls = 0;
|
||||
const trackingClient = createLLMClient("kimi", { model: kimiModel });
|
||||
@@ -146,7 +146,7 @@ describe.skipIf(!hasKimiKey)("LLM integration with Kimi", () => {
|
||||
};
|
||||
|
||||
const result = await extractFileLLM(file, trackingClient, dir);
|
||||
expect(result.purpose).toBe("Large/generated file");
|
||||
expect(result.purpose).toBe("Large file");
|
||||
expect(calls).toBe(0); // Should never call LLM for large files
|
||||
});
|
||||
});
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
import type { LLMClient } from "../src/llm/llm-client.js";
|
||||
|
||||
export function createMockFileClient(purpose = "Test file"): LLMClient {
|
||||
return {
|
||||
async complete() {
|
||||
return `PURPOSE: ${purpose}\nDEPS: none\nCONCEPTS: testing`;
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
export function createMockPackageClient(): LLMClient {
|
||||
return {
|
||||
async complete() {
|
||||
return "ROLE: Test package\nARCH: Test architecture";
|
||||
},
|
||||
};
|
||||
}
|
||||
Reference in New Issue
Block a user