Upload policy_utils.py with huggingface_hub

policy_utils.py

@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+import json
+import time
+from pathlib import Path
+from typing import Any
+
+from toxic_royale_env.policy_models import FramePacket, PolicyAction
+
+
+def _outputs_root() -> Path:
+    # Repository root is the parent of this file.
+    return Path(__file__).resolve().parent / "outputs" / "policy_logs"
+
+
+def append_jsonl(path: Path, obj: dict[str, Any]) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("a", encoding="utf-8") as f:
+        f.write(json.dumps(obj, ensure_ascii=False) + "\n")
+
+
+def rule_policy(packet: FramePacket) -> PolicyAction:
+    """
+    Always-valid baseline:
+    - If no playable card known, wait
+    - Else play the first playable (or first in hand if playable unknown) to a safe back zone.
+    """
+    hand = (packet.player.hand if packet.player else []) or []
+    elixir = float(packet.player.elixir) if (packet.player and packet.player.elixir is not None) else None
+
+    chosen = None
+    for c in hand:
+        if c.is_playable is True:
+            chosen = c
+            break
+
+    if chosen is None and elixir is not None:
+        for c in hand:
+            if c.cost <= elixir:
+                chosen = c
+                break
+
+    if chosen is None and hand:
+        chosen = hand[0]
+
+    if chosen is None:
+        return PolicyAction(kind="wait", emote="yawn")
+
+    # Alternate back zones by tick_id parity for minimal diversity
+    tick_id = packet.meta.tick_id
+    zone = "back_left" if (tick_id % 2 == 0) else "back_right"
+
+    # Lightweight BM: laugh when we can play; yawn when we can't (handled above).
+    return PolicyAction(kind="play", card=chosen.card, zone=zone, emote="laugh")
+
+
+def should_gate(packet: FramePacket, threshold: float = 0.70) -> bool:
+    q = None
+    if packet.debug and packet.debug.detections_quality:
+        q = packet.debug.detections_quality.overall
+    if q is None:
+        return False
+    return float(q) < threshold
+
+
+def now_ms() -> int:
+    return int(time.time() * 1000)
+