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>

app/tools/registry.py

@@ -39,6 +39,7 @@ class ToolRegistry:
 def create_default_registry(workspace_root: Path, config: AppConfig) -> ToolRegistry:
     """Create a ToolRegistry populated with all built-in tools."""
     from app.tools.filesystem import ListDirTool, ReadFileTool
+    from app.tools.finish import FinishTool
     from app.tools.search import FindFilesTool, GrepFilesTool
 
     registry = ToolRegistry()
@@ -46,4 +47,5 @@ def create_default_registry(workspace_root: Path, config: AppConfig) -> ToolRegi
     registry.register(ListDirTool(workspace_root, config))
     registry.register(GrepFilesTool(workspace_root, config))
     registry.register(FindFilesTool(workspace_root, config))
+    registry.register(FinishTool(workspace_root, config))
     return registry