Add judge_language config plumbing (settings + scenario + ScoreRequest)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

rag_eval/config/loader.py

@@ -64,6 +64,7 @@ def load_scenario(path: str | Path) -> Scenario:
         optimization_advisor=model.optimization_advisor,
         metric_weights=dict(model.metric_weights),
         doc_weights=dict(model.doc_weights),
+        judge_language=model.judge_language,
     )
     # Run cross-field checks after all relative paths have been resolved.
     validate_scenario(scenario)

rag_eval/config/schema.py

@@ -57,6 +57,7 @@ class ScenarioModel(BaseModel):
     optimization_advisor: bool = False
     metric_weights: dict[str, float] = Field(default_factory=dict)
     doc_weights: dict[str, float] = Field(default_factory=dict)
+    judge_language: Literal["en", "zh"] | None = None
 
     @field_validator("metrics")
     @classmethod

rag_eval/settings.py

@@ -22,6 +22,7 @@ class EvaluationSettings(BaseSettings):
     openai_api_key: str | None = Field(default=None, alias="OPENAI_API_KEY")
     openai_base_url: str = Field(default="http://6.86.80.4:30080/v1", alias="OPENAI_BASE_URL")
     ragas_judge_model: str = Field(default="gpt-5", alias="RAGAS_JUDGE_MODEL")
+    ragas_judge_language: str = Field(default="en", alias="RAGAS_JUDGE_LANGUAGE")
     ragas_embedding_model: str = Field(
         default="text-embedding-3-small",
         alias="RAGAS_EMBEDDING_MODEL",

rag_eval/shared/models.py

@@ -79,6 +79,9 @@ class Scenario:
     optimization_advisor: bool = False
     metric_weights: dict[str, float] = field(default_factory=dict)
     doc_weights: dict[str, float] = field(default_factory=dict)
+    # Language used for judge prompts: 'en' (default, English) or 'zh' (Chinese).
+    # None means "use the global settings default".
+    judge_language: str | None = None
 
     def snapshot(self) -> dict[str, Any]:
         """Serialize the scenario into a reporting-friendly dictionary snapshot."""