fix: handle max_tokens for NVIDIA MiniMax M3 (#9209)

Author: Last-emo-boy

astrbot/core/provider/sources/openai_source.py

@@ -404,10 +404,26 @@ def _ollama_disable_thinking_enabled(self) -> bool:
             return value.strip().lower() in {"1", "true", "yes", "on"}
         return bool(value)
 
-    def _apply_provider_specific_extra_body_overrides(
-        self, extra_body: dict[str, Any]
+    def _apply_provider_specific_request_overrides(
+        self,
+        payloads: dict[str, Any],
+        extra_body: dict[str, Any],
     ) -> None:
-        if self.provider_config.get("provider") != "ollama":
+        provider = self.provider_config.get("provider")
+        model = str(payloads.get("model", "")).lower()
+
+        # NVIDIA's hosted MiniMax M3 endpoint can return empty choices when
+        # max_tokens is omitted (#9206). Scope the compatibility default to
+        # that model; other NVIDIA models have different token limits.
+        if (
+            provider == "nvidia"
+            and model == "minimaxai/minimax-m3"
+            and "max_tokens" not in payloads
+            and "max_tokens" not in extra_body
+        ):
+            payloads["max_tokens"] = 8192
+
+        if provider != "ollama":
             return
         if not self._ollama_disable_thinking_enabled():
             return
@@ -543,7 +559,7 @@ async def _query(
         custom_extra_body = self.provider_config.get("custom_extra_body", {})
         if isinstance(custom_extra_body, dict):
             extra_body.update(custom_extra_body)
-        self._apply_provider_specific_extra_body_overrides(extra_body)
+        self._apply_provider_specific_request_overrides(payloads, extra_body)
 
         model = payloads.get("model", "").lower()
 
@@ -603,7 +619,7 @@ async def _query_stream(
                 to_del.append(key)
         for key in to_del:
             del payloads[key]
-        self._apply_provider_specific_extra_body_overrides(extra_body)
+        self._apply_provider_specific_request_overrides(payloads, extra_body)
 
         self._sanitize_assistant_messages(payloads)
 

tests/test_openai_source.py

@@ -1272,7 +1272,7 @@ async def fake_resolve_media_ref_to_base64_data(
 
 
 @pytest.mark.asyncio
-async def test_apply_provider_specific_extra_body_overrides_disables_ollama_thinking():
+async def test_apply_provider_specific_request_overrides_disables_ollama_thinking():
     provider = _make_provider(
         {
             "provider": "ollama",
@@ -1287,7 +1287,7 @@ async def test_apply_provider_specific_extra_body_overrides_disables_ollama_thin
             "temperature": 0.2,
         }
 
-        provider._apply_provider_specific_extra_body_overrides(extra_body)
+        provider._apply_provider_specific_request_overrides({}, extra_body)
 
         assert extra_body["reasoning_effort"] == "none"
         assert "reasoning" not in extra_body
@@ -1297,6 +1297,69 @@ async def test_apply_provider_specific_extra_body_overrides_disables_ollama_thin
         await provider.terminate()
 
 
+@pytest.mark.asyncio
+async def test_provider_specific_request_overrides_sets_minimax_m3_max_tokens():
+    provider = _make_provider({"provider": "nvidia"})
+    try:
+        payloads = {"model": "minimaxai/minimax-m3"}
+        extra_body = {"temperature": 0.2}
+
+        provider._apply_provider_specific_request_overrides(payloads, extra_body)
+
+        assert payloads["max_tokens"] == 8192
+        assert extra_body == {"temperature": 0.2}
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_minimax_m3_max_tokens_preserves_custom_extra_body_value():
+    provider = _make_provider({"provider": "nvidia"})
+    try:
+        payloads = {"model": "minimaxai/minimax-m3"}
+        extra_body = {"max_tokens": 4096}
+
+        provider._apply_provider_specific_request_overrides(payloads, extra_body)
+
+        assert "max_tokens" not in payloads
+        assert extra_body["max_tokens"] == 4096
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_minimax_m3_max_tokens_preserves_standard_payload_value():
+    provider = _make_provider({"provider": "nvidia"})
+    try:
+        payloads = {
+            "model": "minimaxai/minimax-m3",
+            "max_tokens": 2048,
+        }
+        extra_body = {}
+
+        provider._apply_provider_specific_request_overrides(payloads, extra_body)
+
+        assert payloads["max_tokens"] == 2048
+        assert extra_body == {}
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_nvidia_request_does_not_set_max_tokens_for_other_models():
+    provider = _make_provider({"provider": "nvidia"})
+    try:
+        payloads = {"model": "nvidia/usdcode"}
+        extra_body = {}
+
+        provider._apply_provider_specific_request_overrides(payloads, extra_body)
+
+        assert "max_tokens" not in payloads
+        assert "max_tokens" not in extra_body
+    finally:
+        await provider.terminate()
+
+
 @pytest.mark.asyncio
 async def test_query_injects_reasoning_effort_none_for_ollama(monkeypatch):
     provider = _make_provider(