fix(ai_loop): wrap MiniMax reasoning in <thinking> tags for parse_thinking_trace (FR3, Bug #3)

Adds a new wrap_reasoning_in_text: bool = False keyword argument to
run_with_tool_loop. When True and reasoning_content is non-empty, the
returned text is prepended with <thinking>...</thinking> tags so
thinking_parser.parse_thinking_trace can extract a ThinkingSegment
for the discussion entry.

The wrap is conditional (default False) so it doesn't break providers
that already wrap inline (e.g. DeepSeek, which wraps at line 2117-2118
before run_with_tool_loop sees the response).

_send_minimax now passes wrap_reasoning_in_text=bool(caps.reasoning).
When caps.reasoning is True (M2.5/M2.7), the reasoning is wrapped in
<thinking> tags. When False (M2/M2.1), the parameter is False and
no wrap happens (avoids useless getattr on non-reasoning models).

Also fixes a bug in the test_fr3_minimax_thinking_in_returned_text
test mock: it was returning a raw MagicMock instead of a Result
object, which caused the test to see auto-created MagicMock attributes
instead of the expected text. Now wraps in Result(data=MagicMock(...))
and sets ai_client._model to ensure get_capabilities('minimax', _model)
resolves to the M2.7 capabilities (reasoning=True).

tests/test_ai_loop_regressions_20260614.py

@@ -204,7 +204,7 @@ def test_fr3_minimax_thinking_in_returned_text() -> None:
 
  def _fake_send_openai_compatible(client, request, *, capabilities):
   captured_text.append("send_openai_compatible was called")
-  return MagicMock(
+  return Result(data=MagicMock(
    text="The final answer is 42",
    tool_calls=[],
    usage_input_tokens=0,
@@ -212,11 +212,12 @@ def test_fr3_minimax_thinking_in_returned_text() -> None:
    usage_cache_read_tokens=0,
    usage_cache_creation_tokens=0,
    raw_response=fake_raw,
-  )
+  ))
 
  from src import openai_compatible as oc
  from src.vendor_capabilities import register, VendorCapabilities
  register(VendorCapabilities(vendor="minimax", model="MiniMax-M2.7", reasoning=True))
+ ai_client._model = "MiniMax-M2.7"
 
  with patch.object(oc, "send_openai_compatible", side_effect=_fake_send_openai_compatible), \
       patch("src.ai_client._ensure_minimax_client", return_value=MagicMock()), \