All characters on nemotron-4b; one cold-load per fork

app.py

@@ -63,11 +63,14 @@ MAX_CHARACTERS = 10
 INITIAL_CHARACTERS = 4
 DEFAULT_NAMES = ["Ada", "Bram", "Cyra", "Doro", "Eli", "Faye", "Gus", "Hild", "Ira", "Juno"]
 
-# Heroes always run on Nemotron 4B (sponsor model, highest-quality reasoning
-# in the side panel on camera). Everyone else uses DEFAULT_MODEL_ID
-# (Llama 3.2 3B) — small enough to be cheap to fork but large enough to
-# drive the smolagents CodeAgent format. Heroes are pinned by NAME so a
-# reset or fresh world always yields the same heroes.
+# All characters run on Nemotron 4B (sponsor model, strong reasoning,
+# and — critically — sharing one model across every character means each
+# @spaces.GPU fork only pays ONE cold-load instead of one-per-distinct-
+# model. Used to be a mixed stack (heroes=Nemotron, wanderer=Llama 3.2 3B)
+# but the second model added ~17s of per-fork cold-load whenever Doro's
+# turn came up, with no narrative benefit. HERO_NAMES still tracks who's
+# pinned to a specific archetype (engineer/diplomat/saboteur); model is
+# uniform.
 HERO_MODEL_ID = "nemotron-4b"
 HERO_NAMES = ("Ada", "Bram", "Cyra")
 
@@ -105,9 +108,9 @@ def _resolve_and_warm_models() -> None:
     except Exception as e:
         tlog(f"[townlet] model path resolve skipped: {e}")
         return
-    # Only the models the spawn config actually uses. Resolving paths for
-    # roster models we never load would waste ~5s of startup per model.
-    for model_id in ("nemotron-4b", "llama-3b"):
+    # Single model — every character uses nemotron-4b. Resolving paths
+    # for roster models we never load would waste ~5s of startup per model.
+    for model_id in ("nemotron-4b",):
         spec = ROSTER.get(model_id)
         if spec is None:
             continue
@@ -149,7 +152,8 @@ def _spawn_one(name: str | None = None) -> Character | None:
     # the lock). Code, not the LLM, picks the exact stand-tile.
     spawn_place = RNG.choice(("cave", "well", "locker_row", "town_hall"))
     pos = stand_tile_for(spawn_place, name)
-    model_id = HERO_MODEL_ID if name in HERO_NAMES else DEFAULT_MODEL_ID
+    # Single model for all characters — see HERO_MODEL_ID comment above.
+    model_id = HERO_MODEL_ID
     char = Character(
         name=name,
         personality=arch.personality,

docs/blog.md

@@ -27,6 +27,7 @@ The end result, I think showed two things.
 
  - The characters and limits did not give me the results, visually I had hoped for, they did use the shell and message board which was interesting to see.
  - The charactes did not evolve as I had hoped. I did include a dream feature that periodically should have shiffted behaviour, but it did not do enough.
- - 
+
+
 
 THe

game/models.py

@@ -26,7 +26,7 @@ class ModelSpec:
     card_url: str
 
 
-DEFAULT_MODEL_ID = "llama-3b"
+DEFAULT_MODEL_ID = "nemotron-4b"
 
 
 ROSTER: dict[str, ModelSpec] = {