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

fixtures/sample-project/src/components/Button.tsx

@@ -0,0 +1,27 @@
+import React from "react";
+
+export interface ButtonProps {
+  label: string;
+  variant?: "primary" | "secondary" | "danger";
+  onClick?: () => void;
+  disabled?: boolean;
+}
+
+export function Button({
+  label,
+  variant = "primary",
+  onClick,
+  disabled = false,
+}: ButtonProps): JSX.Element {
+  return (
+    <button
+      className={`btn btn--${variant}`}
+      onClick={onClick}
+      disabled={disabled}
+    >
+      {label}
+    </button>
+  );
+}
+
+export default Button;