Add Phase 5: ReAct-style agent loop with tool execution

Implement the core autonomy layer — AgentLoop streams LLM responses,
parses tool calls, executes them with permission checks, feeds results
back, and repeats until the task completes or finish is called.

- Add FinishTool for explicit loop termination
- Add tools parameter to LLMClient.stream_chat() for function calling
- Add compact tool result display (status line, not full output)
- Refactor REPL to delegate to AgentLoop.run_turn()
- Fix Ollama null content rejection (always send content as string)
- Add finish to auto_approve permissions
- 9 unit tests for agent loop (34 total, zero regressions)

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

tests/unit/test_tools.py

@@ -96,12 +96,12 @@ class TestToolRegistry:
     def test_create_default_registry(self, workspace: Path, config: AppConfig) -> None:
         registry = create_default_registry(workspace, config)
         names = set(registry.get_all().keys())
-        assert names == {"read_file", "list_dir", "grep_files", "find_files"}
+        assert names == {"read_file", "list_dir", "grep_files", "find_files", "finish"}
 
     def test_schema_export(self, workspace: Path, config: AppConfig) -> None:
         registry = create_default_registry(workspace, config)
         schemas = registry.get_openai_tools_schema()
-        assert len(schemas) == 4
+        assert len(schemas) == 5
         assert all(s["type"] == "function" for s in schemas)