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/finish.py

@@ -0,0 +1,35 @@
+"""FinishTool — signals agent loop termination."""
+
+from typing import Any, ClassVar
+
+from pydantic import BaseModel, Field
+
+from app.models.config import AppConfig
+from app.models.tool_call import ToolResult, ToolResultStatus
+from app.tools.base import BaseTool
+
+
+class FinishParams(BaseModel):
+    """Parameters for the finish tool."""
+
+    message: str = Field(default="Task complete.", description="Final message to the user")
+
+
+class FinishTool(BaseTool):
+    """Signal that the agent has completed its task."""
+
+    name: ClassVar[str] = "finish"
+    description: ClassVar[str] = (
+        "Call this tool when you have completed the user's task. "
+        "Provide a brief summary message."
+    )
+    params_model: ClassVar[type[BaseModel]] = FinishParams
+
+    def execute(self, *, tool_call_id: str, **kwargs: Any) -> ToolResult:
+        message = kwargs.get("message", "Task complete.")
+        return ToolResult(
+            tool_call_id=tool_call_id,
+            tool_name=self.name,
+            status=ToolResultStatus.SUCCESS,
+            output=message,
+        )