stream: strip <think> blocks + broaden meta-leak filter for Nemotron reasoning output

game/stream.py

@@ -18,6 +18,7 @@ context-appropriate canned monologue.
 
 from __future__ import annotations
 
+import re
 import traceback
 
 from backend.factory import get_llm
@@ -102,8 +103,19 @@ def _short(args: dict) -> str:
     return ", ".join(out)
 
 
+_THINK_RX = re.compile(r"<think>.*?</think>", re.DOTALL | re.IGNORECASE)
+
+
 def _clean(text: str) -> str:
     text = (text or "").strip()
+    # Nemotron 3 Nano and other reasoning models wrap chain-of-thought in
+    # <think>...</think> blocks; the final answer follows. Drop the block.
+    text = _THINK_RX.sub("", text).strip()
+    # If the reply was truncated mid-reasoning (open tag, no close), drop
+    # everything before the dangling opener so we don't surface meta-text.
+    if "<think>" in text.lower():
+        idx = text.lower().rfind("<think>")
+        text = text[idx + len("<think>"):].lstrip()
     # Strip markdown code fences if the model wrapped its reply in them.
     if text.startswith("```"):
         text = text.lstrip("`").lstrip()
@@ -118,8 +130,19 @@ def _clean(text: str) -> str:
     META_MARKERS = (
         "the user wants",
         "we need to produce",
+        "we need to output",
+        "i need to output",
+        "i need to write",
+        "i need to craft",
+        "i need to produce",
         "i'll write",
         "i will write",
+        "let me craft",
+        "let me write",
+        "let's craft",
+        "let's write",
+        "should reflect",
+        "should be in",
         "2-3 sentence",
         "2 to 3 sentence",
         "inner monologue",