From 6cd500393064f7e7fd19d08d4383e203079300e6 Mon Sep 17 00:00:00 2001
From: Phillip Tarrant <ptarrant@gmail.com>
Date: Fri, 10 Jul 2026 12:11:54 -0500
Subject: [PATCH] feat(api): route the npc role to its own model

---
 api/app/config.py         | 4 ++++
 api/app/routing.py        | 6 ++++++
 api/tests/test_routing.py | 8 ++++++++
 3 files changed, 18 insertions(+)

diff --git a/api/app/config.py b/api/app/config.py
index 4981f57..4d07e1e 100644
--- a/api/app/config.py
+++ b/api/app/config.py
@@ -18,5 +18,9 @@ def narrator_model() -> str:
     return os.environ.get("OLLAMA_NARRATOR_MODEL", "qwen3.5:latest")
 
 
+def npc_model() -> str:
+    return os.environ.get("OLLAMA_NPC_MODEL", "qwen3.5:latest")
+
+
 def call_log_path() -> str | None:
     return os.environ.get("CALL_LOG_PATH") or None
diff --git a/api/app/routing.py b/api/app/routing.py
index 98d9dba..8cf1669 100644
--- a/api/app/routing.py
+++ b/api/app/routing.py
@@ -22,4 +22,10 @@ def for_role(role: str) -> RoleConfig:
             options={"temperature": 0.8, "top_p": 0.9, "num_predict": 300},
             think=False,  # qwen3.x thinking OFF; harmless on non-thinking models
         )
+    if role == "npc":
+        return RoleConfig(
+            model=config.npc_model(),
+            options={"temperature": 0.8, "top_p": 0.9, "num_predict": 320},
+            think=False,
+        )
     raise KeyError(f"no routing for role: {role}")
diff --git a/api/tests/test_routing.py b/api/tests/test_routing.py
index d455598..fe1eef4 100644
--- a/api/tests/test_routing.py
+++ b/api/tests/test_routing.py
@@ -19,3 +19,11 @@ def test_env_overrides_model(monkeypatch):
 def test_unknown_role_raises():
     with pytest.raises(KeyError):
         for_role("wizard")
+
+
+def test_npc_role_routes_to_npc_model(monkeypatch):
+    monkeypatch.setenv("OLLAMA_NPC_MODEL", "some-npc-model")
+    cfg = for_role("npc")
+    assert cfg.model == "some-npc-model"
+    assert cfg.think is False
+    assert "num_predict" in cfg.options