feat: M7 proper LLM integration with dual providers, caching, and parallel batching

- Add LLM client abstraction (src/llm-client.ts) with factory pattern
- Add OpenAI-compatible external client (src/external-llm-client.ts)
- Add Kimi.com client using Anthropic-based API (src/kimi-llm-client.ts)
- Add Pi native LLM stub (src/pi-llm-client.ts) for future ExtensionAPI wiring
- Add SHA-256 disk cache at ~/.cache/pi-project-map/ (src/llm-cache.ts)
- Add parallel batching with p-limit, retry + exponential backoff (src/llm-batch.ts)
- Rewrite llm-extract.ts to use real LLM calls with structured prompts
  - File-level: PURPOSE, DEPS, CONCEPTS
  - Package-level: ROLE, ARCH
  - Context truncation, 50KB skip, cache before LLM call
- Wire CLI with --llm-provider, --llm-model, --llm-base-url flags
- Update config.ts with llmProvider, llmBaseUrl fields
- Update init.ts and patch.ts to accept optional LLMClient
- Add sample project fixture for manual testing
- Add tests: llm-cache (3), llm-batch (5), llm-integration (8 with real Kimi API),
  pi-extension (14 mocked)
- All 56 tests pass

tests/llm-extract.test.ts

@@ -1,8 +1,9 @@
 import { describe, it, expect } from "vitest";
-import { extractFileLLM } from "../src/llm-extract.js";
+import { extractFileLLM, extractFileHeuristic } from "../src/llm-extract.js";
 import { writeFileSync, mkdtempSync } from "fs";
 import { join } from "path";
 import { tmpdir } from "os";
+import type { LLMClient } from "../src/llm-client.js";
 
 describe("llm-extract heuristics", () => {
 	it("extracts TypeScript exports", async () => {
@@ -61,3 +62,61 @@ const x = require("legacy");
 		expect(result.exports).toEqual([]);
 	});
 });
+
+describe("llm-extract with mock client", () => {
+	it("uses LLM client when provided", async () => {
+		const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
+		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 result = await extractFileLLM(file, mockClient);
+		expect(result.purpose).toBe("Test file");
+		expect(result.deps).toEqual([]);
+		expect(result.concepts).toContain("testing");
+	});
+
+	it("skips large files", async () => {
+		const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
+		const file = join(dir, "big.ts");
+		writeFileSync(file, "x".repeat(60 * 1024));
+
+		const mockClient: LLMClient = {
+			async complete() {
+				return "PURPOSE: Should not call\nDEPS: none\nCONCEPTS: none";
+			},
+		};
+
+		const result = await extractFileLLM(file, mockClient);
+		expect(result.purpose).toBe("Large/generated file");
+	});
+
+	it("falls back to heuristics without client", async () => {
+		const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
+		const file = join(dir, "utils.ts");
+		writeFileSync(file, `export function helper() {}`);
+
+		const result = await extractFileLLM(file);
+		expect(result.purpose).toBe("Utility functions");
+		expect(result.exports).toContain("helper");
+	});
+});
+
+describe("extractFileHeuristic", () => {
+	it("returns structured data", async () => {
+		const dir = mkdtempSync(join(tmpdir(), "pi-map-"));
+		const file = join(dir, "test.ts");
+		writeFileSync(file, `export 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);
+	});
+});