fix(decisions): keep provider fields inside System One answers

Backport of #45214 to stable/1.104.x.
Cherry-picked from 1348de864f (litellm_openai_decisions_provider).

(cherry picked from commit 1348de864f)

litellm/llms/base_llm/decisions/transformation.py

@@ -183,6 +183,7 @@ def _ir_choice_answer(question: DecisionsIRChoiceQuestion, answer: ChoiceAnswer)
             DecisionsIRChoiceProbability(value=typed_values.get(key, key), probability=probability)
             for key, probability in answer.probabilities.items()
         ),
+        extra=MappingProxyType(answer.model_extra or {}),
     )
 
 
@@ -198,13 +199,14 @@ def _ir_score_answer(question: DecisionsIRScoreQuestion, answer: ScoreAnswer) ->
             )
             for index, level in enumerate(question.levels)
         ),
+        extra=MappingProxyType(answer.model_extra or {}),
     )
 
 
 def _ir_answer(question: DecisionsIRQuestion, answer: DecisionAnswer | None) -> DecisionsIRAnswer:
     match question, answer:
         case DecisionsIRPredicateQuestion(), NoulAnswer():
-            return DecisionsIRPredicateAnswer(probability=answer.noul)
+            return DecisionsIRPredicateAnswer(probability=answer.noul, extra=MappingProxyType(answer.model_extra or {}))
         case DecisionsIRChoiceQuestion(), ChoiceAnswer():
             return _ir_choice_answer(question, answer)
         case DecisionsIRScoreQuestion(), ScoreAnswer():
@@ -237,21 +239,29 @@ def parse_systemone_response(payload: object, request: DecisionsIRRequest) -> De
 def _systemone_answer(answer: DecisionsIRAnswer) -> DecisionAnswer | None:
     match answer:
         case DecisionsIRPredicateAnswer():
-            return NoulAnswer(type="noul", noul=answer.probability)
+            return NoulAnswer.model_validate({**answer.extra, "type": "noul", "noul": answer.probability})
         case DecisionsIRChoiceAnswer():
-            return ChoiceAnswer(
-                type="choice",
-                choice=systemone_choice_key(answer.choice),
-                confidence=answer.confidence,
-                probabilities={systemone_choice_key(item.value): item.probability for item in answer.probabilities},
+            return ChoiceAnswer.model_validate(
+                {
+                    **answer.extra,
+                    "type": "choice",
+                    "choice": systemone_choice_key(answer.choice),
+                    "confidence": answer.confidence,
+                    "probabilities": {
+                        systemone_choice_key(item.value): item.probability for item in answer.probabilities
+                    },
+                }
             )
         case DecisionsIRScoreAnswer():
-            return ScoreAnswer(
-                type="score",
-                score=answer.score,
-                confidence=answer.confidence,
-                legend={str(item.value): item.label for item in answer.probabilities},
-                probabilities={str(item.value): item.probability for item in answer.probabilities},
+            return ScoreAnswer.model_validate(
+                {
+                    **answer.extra,
+                    "type": "score",
+                    "score": answer.score,
+                    "confidence": answer.confidence,
+                    "legend": {str(item.value): item.label for item in answer.probabilities},
+                    "probabilities": {str(item.value): item.probability for item in answer.probabilities},
+                }
             )
         case DecisionsIRRefusal():
             return None

litellm/types/decisions.py

@@ -378,6 +378,7 @@ class DecisionsIRRequest:
 @dataclass(frozen=True, slots=True)
 class DecisionsIRPredicateAnswer:
     probability: float
+    extra: Mapping[str, object] = field(default=_NO_EXTRA)
 
 
 @dataclass(frozen=True, slots=True)
@@ -391,6 +392,7 @@ class DecisionsIRChoiceAnswer:
     choice: str | bool
     confidence: float
     probabilities: tuple[DecisionsIRChoiceProbability, ...]
+    extra: Mapping[str, object] = field(default=_NO_EXTRA)
 
 
 @dataclass(frozen=True, slots=True)
@@ -405,6 +407,7 @@ class DecisionsIRScoreAnswer:
     score: float
     confidence: float
     probabilities: tuple[DecisionsIRScoreProbability, ...]
+    extra: Mapping[str, object] = field(default=_NO_EXTRA)
 
 
 @dataclass(frozen=True, slots=True)

tests/unit/llms/base_llm/decisions/test_base_decisions_transformation.py

@@ -136,12 +136,13 @@ def test_a_systemone_response_reaches_the_caller_unchanged_with_provider_extras(
     payload: Final = {
         "model": "jev-latest",
         "answers": {
-            "damaged": {"type": "noul", "noul": 0.95},
+            "damaged": {"type": "noul", "noul": 0.95, "rationale": "crack visible"},
             "action": {
                 "type": "choice",
                 "choice": "refund",
                 "confidence": 0.8,
                 "probabilities": {"refund": 0.9, "escalate": 0.1},
+                "calibrated": True,
             },
             "severity": {
                 "type": "score",
@@ -149,6 +150,7 @@ def test_a_systemone_response_reaches_the_caller_unchanged_with_provider_extras(
                 "confidence": 0.6,
                 "legend": {"0": "minor", "1": {"label": "major"}},
                 "probabilities": {"0": 0.6, "1": 0.4},
+                "raw_logits": [0.1, 0.2],
             },
         },
         "usage": {"input_tokens": 383, "output_tokens": 2, "cost": 0.25},