fix: AddresseeDecision.confidence as Literal[high|medium|low] (T77)

chat/services/addressee.py

@@ -22,6 +22,8 @@ from a fallback.
 
 from __future__ import annotations
 
+from typing import Literal
+
 from pydantic import BaseModel
 
 from chat.llm.classify import classify
@@ -39,7 +41,7 @@ class AddresseeDecision(BaseModel):
     """
 
     addressee_id: str
-    confidence: str = "medium"  # "high" | "medium" | "low"
+    confidence: Literal["high", "medium", "low"] = "medium"
     reason: str = ""
 
 

tests/test_addressee.py

@@ -97,3 +97,38 @@ async def test_classifier_failure_falls_back_to_host():
     assert result.addressee_id == "bot_a"
     assert result.reason == "fallback"
     assert result.confidence == "low"
+
+
+@pytest.mark.asyncio
+async def test_invalid_confidence_value_falls_back_to_default():
+    """Pydantic rejects ``confidence`` values outside the literal set
+    (``high`` / ``medium`` / ``low``). After the retry budget is
+    exhausted, classify returns the configured fallback default —
+    here that's ``confidence="low"`` with ``reason="fallback"``.
+    """
+    canned = [
+        json.dumps(
+            {
+                "addressee_id": "bot_a",
+                "confidence": "VERY_HIGH",
+                "reason": "out-of-range value",
+            }
+        ),
+        "still_bad",
+        "still_bad",
+    ]
+    client = MockLLMClient(canned=canned)
+
+    result = await detect_addressee(
+        client,
+        classifier_model="test-model",
+        user_prose="anything",
+        host_id="bot_a",
+        host_name="BotA",
+        guest_id="bot_b",
+        guest_name="BotB",
+    )
+
+    assert result.addressee_id == "bot_a"
+    assert result.confidence == "low"
+    assert result.reason == "fallback"