feat(models): auto-mode intent remap + real coder models in preference

Settings "Auto model routing" picks which installed model fires for chat vs
coding intent when no model is pinned (auto_chat_model / auto_code_model).
_auto_select_model honors the remap; _MODEL_PREFERENCE["code"] prefers real
coder models first.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

tests/test_smoke.py

@@ -43,6 +43,19 @@ def test_keep_alive_pins_the_model():
     assert "keep_alive" not in mgr._apply_keep_alive({"model": "x"})
 
 
+def test_auto_model_remap(monkeypatch):
+    import asyncio
+    from synapse import main
+    cfg = {"model": "", "auto_chat_model": "chatX", "auto_code_model": "coderY"}
+    monkeypatch.setattr(main.store, "get_settings", lambda: cfg)
+    # code intent ("function") routes to the code remap; chat intent to the chat remap
+    assert asyncio.run(main._auto_select_model("write a function to sort a list")) == "coderY"
+    assert asyncio.run(main._auto_select_model("how are you today")) == "chatX"
+    # an explicit pin beats the remap
+    cfg["model"] = "pinnedZ"
+    assert asyncio.run(main._auto_select_model("debug this code")) == "pinnedZ"
+
+
 def test_hardware_fit_logic():
     from synapse import hardware
     assert hardware._fit(2.5, 4.0, 16.0) == "gpu"    # 2.5+1 <= 4 -> fits GPU