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/services/llm.py

@@ -2,8 +2,7 @@
 
 import json
 from collections.abc import AsyncIterator
-from contextlib import asynccontextmanager
-from typing import Self
+from typing import Any, Self
 
 import httpx
 
@@ -101,11 +100,16 @@ class LLMClient:
                 f"Model '{model}' not found. Available models: {available_str}"
             )
 
-    async def stream_chat(self, messages: list[Message]) -> AsyncIterator[dict]:
+    async def stream_chat(
+        self,
+        messages: list[Message],
+        tools: list[dict[str, Any]] | None = None,
+    ) -> AsyncIterator[dict]:
         """Stream a chat completion request, yielding parsed SSE chunks.
 
         Args:
             messages: Conversation history to send to the model.
+            tools: Optional OpenAI function-calling tool schemas.
 
         Yields:
             Parsed JSON dicts from each SSE data line.
@@ -115,7 +119,7 @@ class LLMClient:
             LLMResponseError: On non-2xx HTTP status.
             LLMStreamError: On malformed SSE data (only if every line fails).
         """
-        payload = {
+        payload: dict[str, Any] = {
             "model": self._config.model,
             "messages": [m.to_api_dict() for m in messages],
             "stream": True,
@@ -123,6 +127,9 @@ class LLMClient:
             "max_tokens": self._config.max_tokens,
         }
 
+        if tools:
+            payload["tools"] = tools
+
         try:
             async with self._client.stream(
                 "POST", self._config.api_path, json=payload