fix(providers): inject OpenRouter reasoning.effort for thinking models

Follow-up to #3851: that PR added `extra_body.thinking={type: disabled}`
for MiMo via OpenRouter, but OR doesn't forward provider-specific
thinking shapes to upstream — it strips unknown extra_body fields and
uses its own unified `reasoning` parameter. So MiMo via OR kept
thinking despite the injection (reproduced by @ClearPlume on #3851
with identical kwargs but provider switched from openrouter → xiaomi_mimo).

For known thinking-capable models (Kimi, MiMo) routed via the
openrouter spec, also inject `extra_body.reasoning = {effort: <effort>}`
in OR's documented enum ("none"|"minimal"|"low"|"medium"|"high"|"xhigh").
OR translates this to the upstream model's native shape.

Existing tests updated to expect both fields on the OR path. The direct
xiaomi_mimo and moonshot paths are unchanged (the new branch is gated
on spec.name == "openrouter"). Flash and non-MiMo models on OR continue
to receive no injection.

nanobot/providers/openai_compat_provider.py

@@ -615,6 +615,27 @@ class OpenAICompatProvider(LLMProvider):
                 {"thinking": {"type": "enabled" if thinking_enabled else "disabled"}}
             )
 
+        # OpenRouter uses its own unified `reasoning` field and does not
+        # forward provider-specific thinking shapes (the Kimi/MiMo
+        # extra_body.thinking above) to upstream. Reported as the follow-up
+        # to #3845/#3851: MiMo via OR kept thinking despite our injection.
+        # For known thinking-capable models routed via OR, mirror the
+        # effort signal into reasoning.effort (OR's documented enum:
+        # "none"|"minimal"|"low"|"medium"|"high"|"xhigh"), which OR
+        # translates to the upstream model's native shape.
+        if (
+            spec
+            and spec.name == "openrouter"
+            and reasoning_effort is not None
+            and (
+                _is_kimi_thinking_model(model_name)
+                or _is_mimo_thinking_model(model_name)
+            )
+        ):
+            kwargs.setdefault("extra_body", {}).update(
+                {"reasoning": {"effort": semantic_effort}}
+            )
+
         if tools:
             kwargs["tools"] = tools
             kwargs["tool_choice"] = tool_choice or "auto"

tests/providers/test_litellm_kwargs.py

@@ -1391,9 +1391,16 @@ def test_kimi_k25_no_extra_body_when_reasoning_effort_none() -> None:
 
 
 def test_kimi_k25_thinking_enabled_with_openrouter_prefix() -> None:
-    """OpenRouter-style model names like moonshotai/kimi-k2.5 must trigger thinking."""
+    """OpenRouter-style model names like moonshotai/kimi-k2.5 must trigger thinking.
+
+    OR drops upstream-provider `thinking` fields, so the same intent also has
+    to go through OR's `reasoning.effort` shape (#3851 follow-up).
+    """
     kw = _build_kwargs_for("openrouter", "moonshotai/kimi-k2.5", reasoning_effort="medium")
-    assert kw.get("extra_body") == {"thinking": {"type": "enabled"}}
+    assert kw.get("extra_body") == {
+        "thinking": {"type": "enabled"},
+        "reasoning": {"effort": "medium"},
+    }
 
 
 def test_kimi_k26_thinking_enabled() -> None:
@@ -1403,9 +1410,13 @@ def test_kimi_k26_thinking_enabled() -> None:
 
 
 def test_kimi_k26_thinking_enabled_with_openrouter_prefix() -> None:
-    """OpenRouter-style names like moonshotai/kimi-k2.6 must trigger thinking."""
+    """OpenRouter-style names like moonshotai/kimi-k2.6 must trigger thinking
+    via both upstream `thinking` and OR's `reasoning.effort`."""
     kw = _build_kwargs_for("openrouter", "moonshotai/kimi-k2.6", reasoning_effort="medium")
-    assert kw.get("extra_body") == {"thinking": {"type": "enabled"}}
+    assert kw.get("extra_body") == {
+        "thinking": {"type": "enabled"},
+        "reasoning": {"effort": "medium"},
+    }
 
 
 def test_moonshot_kimi_k26_temperature_override() -> None:

tests/providers/test_xiaomi_mimo_thinking.py

@@ -142,9 +142,11 @@ def test_mimo_reasoning_effort_unset_preserves_provider_default():
 
 
 def test_mimo_via_openrouter_reasoning_effort_none_disables_thinking():
-    """OpenRouter routes MiMo as "xiaomi/mimo-v2.5-pro"; the openrouter spec
+    """OpenRouter routes MiMo as "xiaomi/mimo-v2.5-pro" and does NOT forward
-    has no thinking_style, so the disable signal must come from the
+    extra_body.thinking to upstream, so a disable signal must also reach OR
-    model-name path (#3845)."""
+    in its own `reasoning.effort` shape. Verifies both the upstream-MiMo
+    payload (#3845) and the OR-native payload (#3851 follow-up) are sent.
+    """
     provider = _openrouter_provider("xiaomi/mimo-v2.5-pro")
     kwargs = provider._build_kwargs(
         messages=_simple_messages(),
@@ -152,11 +154,15 @@ def test_mimo_via_openrouter_reasoning_effort_none_disables_thinking():
         temperature=0.7, reasoning_effort="none", tool_choice=None,
     )
     assert "reasoning_effort" not in kwargs
-    assert kwargs["extra_body"] == {"thinking": {"type": "disabled"}}
+    assert kwargs["extra_body"] == {
+        "thinking": {"type": "disabled"},
+        "reasoning": {"effort": "none"},
+    }
 
 
 def test_mimo_via_openrouter_reasoning_effort_medium_enables_thinking():
-    """Same as the direct path: any non-none/minimal effort enables thinking."""
+    """Non-none/minimal effort enables thinking and the OR `reasoning.effort`
+    field mirrors the requested effort level."""
     provider = _openrouter_provider("xiaomi/mimo-v2.5-pro")
     kwargs = provider._build_kwargs(
         messages=_simple_messages(),
@@ -164,7 +170,10 @@ def test_mimo_via_openrouter_reasoning_effort_medium_enables_thinking():
         temperature=0.7, reasoning_effort="medium", tool_choice=None,
     )
     assert kwargs.get("reasoning_effort") == "medium"
-    assert kwargs["extra_body"] == {"thinking": {"type": "enabled"}}
+    assert kwargs["extra_body"] == {
+        "thinking": {"type": "enabled"},
+        "reasoning": {"effort": "medium"},
+    }
 
 
 def test_mimo_via_openrouter_bare_slug_also_matches():
@@ -176,12 +185,16 @@ def test_mimo_via_openrouter_bare_slug_also_matches():
         tools=None, model=None, max_tokens=100,
         temperature=0.7, reasoning_effort="none", tool_choice=None,
     )
-    assert kwargs["extra_body"] == {"thinking": {"type": "disabled"}}
+    assert kwargs["extra_body"] == {
+        "thinking": {"type": "disabled"},
+        "reasoning": {"effort": "none"},
+    }
 
 
 def test_mimo_flash_via_openrouter_does_not_inject_thinking():
     """mimo-v2-flash has no thinking mode per Xiaomi docs; the allowlist
-    excludes it, so no thinking field should be injected on the gateway path."""
+    excludes it, so neither the upstream `thinking` field nor OR's
+    `reasoning.effort` should be injected on the gateway path."""
     provider = _openrouter_provider("xiaomi/mimo-v2-flash")
     kwargs = provider._build_kwargs(
         messages=_simple_messages(),
@@ -200,3 +213,18 @@ def test_non_mimo_model_via_openrouter_unaffected():
         temperature=0.7, reasoning_effort="none", tool_choice=None,
     )
     assert "extra_body" not in kwargs
+
+
+def test_kimi_via_openrouter_also_injects_reasoning_effort():
+    """Kimi has the same gateway problem as MiMo: OR drops the upstream
+    `thinking` field. The same OR-reasoning injection should fire."""
+    provider = _openrouter_provider("moonshotai/kimi-k2.5")
+    kwargs = provider._build_kwargs(
+        messages=_simple_messages(),
+        tools=None, model=None, max_tokens=100,
+        temperature=0.7, reasoning_effort="none", tool_choice=None,
+    )
+    assert kwargs["extra_body"] == {
+        "thinking": {"type": "disabled"},
+        "reasoning": {"effort": "none"},
+    }