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

src/pi-llm-client.ts

@@ -0,0 +1,21 @@
+import { LLMError } from "./llm-error.js";
+import type { LLMClient } from "./llm-client.js";
+
+/**
+ * Pi LLM Client — calls Pi's built-in LLM via ExtensionAPI.
+ *
+ * TODO: This is a stub. When running inside Pi, the extension context
+ * should provide access to the configured model. The exact API shape
+ * depends on the Pi runtime version. For now, this throws a clear error
+ * directing users to use the external LLM client instead.
+ */
+export class PiLLMClient implements LLMClient {
+	constructor(private _extensionContext?: unknown) {}
+
+	async complete(_prompt: string): Promise<string> {
+		throw new LLMError(
+			"Pi native LLM client is not yet implemented. " +
+				"Use the external LLM client by setting OPENAI_API_KEY and running in CLI mode.",
+		);
+	}
+}