Private
Public Access
0
0
Files
manual_slop/tests
ed f4a782d99f 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).
2026-06-15 10:56:24 -04:00
..
2026-03-05 17:13:59 -05:00
2026-05-10 15:14:54 -04:00
2026-05-20 07:51:58 -04:00
2026-03-05 16:37:30 -05:00
2026-03-05 17:13:59 -05:00
2026-03-05 16:37:30 -05:00
2026-03-07 20:32:59 -05:00
2026-03-06 22:03:59 -05:00
2026-03-05 17:13:59 -05:00
2026-03-12 19:08:51 -04:00
2026-03-05 15:10:53 -05:00
2026-03-12 19:08:51 -04:00
2026-03-12 19:08:51 -04:00
2026-05-20 07:51:58 -04:00
2026-05-20 07:51:58 -04:00
ok
2026-03-07 21:40:40 -05:00