Use offline chat prompt config to set context window of loaded chat model

Previously you couldn't configure the n_ctx of the loaded offline chat
model. This made it hard to use good offline chat model (which these
days also have larger context) on machines with lower VRAM

pyproject.toml

@@ -78,6 +78,7 @@ dependencies = [
     "phonenumbers == 8.13.27",
     "markdownify ~= 0.11.6",
     "websockets == 12.0",
+    "psutil >= 5.8.0",
 ]
 dynamic = ["version"]
 
@@ -105,7 +106,6 @@ dev = [
     "pytest-asyncio == 0.21.1",
     "freezegun >= 1.2.0",
     "factory-boy >= 3.2.1",
-    "psutil >= 5.8.0",
     "mypy >= 1.0.1",
     "black >= 23.1.0",
     "pre-commit >= 3.0.4",