Forward judge_language through score, async, and session endpoints

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

tests/test_score_endpoint_language.py

@@ -0,0 +1,46 @@
+"""Tests that score endpoints forward the resolved judge_language to the scorer."""
+
+from unittest.mock import MagicMock, patch
+
+from fastapi.testclient import TestClient
+
+import webapp.api.score as score_mod
+from webapp.server import create_app
+
+
+def _client():
+    return TestClient(create_app())
+
+
+def test_score_route_forwards_judge_language(monkeypatch):
+    """A request with judge_language='zh' reaches inline_scorer.score."""
+    captured: dict = {}
+
+    def fake_score(**kwargs):
+        captured.update(kwargs)
+        return {"faithfulness": 0.9}
+
+    monkeypatch.setattr(score_mod.inline_scorer, "score", fake_score)
+    resp = _client().post("/api/score", json={
+        "question": "q", "answer": "a", "contexts": "c",
+        "ground_truth": "g", "metrics": ["faithfulness"], "judge_language": "zh",
+    })
+    assert resp.status_code == 200
+    assert captured.get("judge_language") == "zh"
+
+
+def test_score_route_defaults_language_to_en(monkeypatch):
+    """Omitting judge_language falls back to settings default ('en')."""
+    captured: dict = {}
+
+    def fake_score(**kwargs):
+        captured.update(kwargs)
+        return {"faithfulness": 0.9}
+
+    monkeypatch.setattr(score_mod.inline_scorer, "score", fake_score)
+    resp = _client().post("/api/score", json={
+        "question": "q", "answer": "a", "contexts": "c",
+        "ground_truth": "g", "metrics": ["faithfulness"],
+    })
+    assert resp.status_code == 200
+    assert captured.get("judge_language") == "en"

webapp/api/score.py

@@ -116,6 +116,7 @@ def score_sample(
 
     judge_model = request.judge_model or settings.ragas_judge_model
     embedding_model = request.embedding_model or settings.ragas_embedding_model
+    judge_language = request.judge_language or settings.ragas_judge_language
     effective = request.effective_metrics()
     requested = set(request.metrics)
     skipped = sorted(requested - set(effective))
@@ -139,6 +140,7 @@ def score_sample(
             judge_model=judge_model,
             embedding_model=embedding_model,
             settings=settings,
+            judge_language=judge_language,
         )
     except Exception as exc:  # noqa: BLE001
         latency_ms = int((time.monotonic() - t0) * 1000)

webapp/services/score_job_manager.py

@@ -120,6 +120,7 @@ class ScoreJobManager:
         settings = EvaluationSettings()
         judge_model = request.judge_model or settings.ragas_judge_model
         embedding_model = request.embedding_model or settings.ragas_embedding_model
+        judge_language = request.judge_language or settings.ragas_judge_language
         effective = request.effective_metrics()
         requested = set(request.metrics)
         skipped = sorted(requested - set(effective))
@@ -138,6 +139,7 @@ class ScoreJobManager:
                     judge_model=judge_model,
                     embedding_model=embedding_model,
                     settings=settings,
+                    judge_language=judge_language,
                 )
             else:
                 raw_scores = {}

webapp/services/session_score_manager.py

@@ -205,6 +205,7 @@ class SessionScoreJobManager:
         settings = EvaluationSettings()
         judge_model = request.judge_model or settings.ragas_judge_model
         embedding_model = request.embedding_model or settings.ragas_embedding_model
+        judge_language = request.judge_language or settings.ragas_judge_language
         effective = request.effective_metrics()
         requested = set(request.metrics)
         skipped = sorted(requested - set(effective))
@@ -223,6 +224,7 @@ class SessionScoreJobManager:
                     judge_model=judge_model,
                     embedding_model=embedding_model,
                     settings=settings,
+                    judge_language=judge_language,
                 )
             else:
                 raw_scores = {}