feat(llm): add LLM integration module with OpenRouter and Claude Code adapters

Implements markitect/llm/ package with concrete LLMAdapter implementations:
- OpenRouterAdapter: HTTP via urllib with retry/backoff on 429/5xx
- ClaudeCodeAdapter: subprocess-based Claude CLI with stdin piping
- Factory pattern: create_adapter("openrouter") or create_adapter("claude-code")
- API key resolution chain: constructor > env var > project-root key file
- 42 unit tests, 2 integration tests (gated on API key / CLI availability)

Also adds the infospace-with-history example with Wealth of Nations VSM
analysis pipeline, templates, schemas, source chapters, and processed
output for chapters 1-2. process_chapters.py now supports --provider
and --model flags for automatic LLM-driven processing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

tests/integration/llm/test_claude_code_live.py

@@ -0,0 +1,28 @@
+"""Live integration test for ClaudeCodeAdapter.
+
+Skipped unless the ``claude`` CLI is available on PATH.
+"""
+
+import shutil
+
+import pytest
+
+from markitect.llm.claude_code import ClaudeCodeAdapter
+from markitect.prompts.execution.models import RunConfig, LLMResponse
+
+
+pytestmark = pytest.mark.skipif(
+    shutil.which("claude") is None,
+    reason="claude CLI not found on PATH",
+)
+
+
+class TestClaudeCodeLive:
+    def test_simple_completion(self):
+        adapter = ClaudeCodeAdapter()
+        config = RunConfig(timeout_seconds=60, max_tokens=50)
+        resp = adapter.execute_prompt("Reply with exactly: PONG", config)
+
+        assert isinstance(resp, LLMResponse)
+        assert len(resp.content.strip()) > 0
+        assert resp.metadata["provider"] == "claude-code"