chat/config.py

@@ -23,6 +23,13 @@ class Settings(BaseModel):
     retrieval_k: int = 4
     narrative_budget_hard: int = 8000
     narrative_budget_soft: int = 6000
+    # Cap on each generated bot response. ~400 tokens ≈ 1–2 short paragraphs.
+    # Bump if you want longer scenes; drop to 200 for terse banter.
+    narrative_max_tokens: int = 400
+    # Sampling temperature for narrative generation. 0.7 = grounded /
+    # consistent; 0.85 = creative-but-in-character (default); 1.0 = wide
+    # variety, can drift; >1.0 = often off-the-rails.
+    narrative_temperature: float = 0.85
     classifier_budget_hard: int = 4000
     classifier_timeout_s: float = 30.0
     # Featherless free tier and lower paid tiers cap concurrent connections.

chat/services/prompt.py

@@ -211,7 +211,9 @@ def _closing_instruction(speaker_name: str, addressee_name: str) -> str:
         f"Continue the scene as {speaker_name}, in their voice, responding "
         "naturally. Use *asterisks* for actions and quotes for dialogue. "
         f"Stay in character. Do not narrate {addressee_name}'s actions or "
-        "thoughts."
+        "thoughts. "
+        "Keep your response to a single beat — one or two short paragraphs "
+        "at most. Don't monologue; leave room for the other person to react."
     )
 
 

chat/services/regenerate.py

@@ -156,7 +156,10 @@ async def regenerate_assistant_turn(
     # 5. Stream the new narrative.
     accumulated: list[str] = []
     async for chunk in client.stream(
-        messages, model=settings.narrative_model
+        messages,
+        model=settings.narrative_model,
+        max_tokens=settings.narrative_max_tokens,
+        temperature=settings.narrative_temperature,
     ):
         accumulated.append(chunk)
         await publish(

chat/web/turns.py

@@ -198,7 +198,10 @@ async def post_turn(
 
     async def _stream() -> None:
         async for chunk in client.stream(
-            messages, model=settings.narrative_model
+            messages,
+            model=settings.narrative_model,
+            max_tokens=settings.narrative_max_tokens,
+            temperature=settings.narrative_temperature,
         ):
             accumulated.append(chunk)
             await publish(