fix: game service api block when a game is running

texas_holdem/engine.py

@@ -1,6 +1,8 @@
 from __future__ import annotations
 
+from copy import deepcopy
 from random import Random
+from threading import RLock
 from time import time
 
 from texas_holdem.agents import PokerAgent
@@ -54,6 +56,7 @@ class TableGame:
         self.small_blind = small_blind
         self.big_blind = big_blind
         self.rng = rng or Random()
+        self.lock = RLock()
         self.hand_number = 0
         self.button_index: int | None = None
         self.board = []
@@ -64,6 +67,7 @@ class TableGame:
         # first hand that played under those stakes, which makes it trivial
         # to reconstruct the schedule from the outside.
         self.blind_history: list[BlindLevel] = []
+        self._completed_snapshot: dict[str, object] = self._to_dict_unlocked()
 
     @property
     def is_complete(self) -> bool:
@@ -83,6 +87,14 @@ class TableGame:
         :attr:`blind_history` whenever it changes (including the very first
         hand) so external observers can replay the schedule.
         """
+        with self.lock:
+            return self._run_hand_locked(small_blind=small_blind, big_blind=big_blind)
+
+    def _run_hand_locked(
+        self,
+        small_blind: int | None = None,
+        big_blind: int | None = None,
+    ) -> HandSummary:
         if self.is_complete:
             raise GameComplete("game is complete")
 
@@ -151,6 +163,7 @@ class TableGame:
             finished_at=time(),
         )
         self.hand_summaries.append(summary)
+        self._completed_snapshot = deepcopy(self._to_dict_unlocked())
         return summary
 
     def run_hands(
@@ -166,24 +179,47 @@ class TableGame:
         with the first hand of this call; subsequent calls can raise them
         again. Leaving them ``None`` keeps the current level unchanged.
         """
-        if max_hands <= 0:
-            raise ValueError("max_hands must be positive")
-        summaries = []
-        for _ in range(max_hands):
-            if self.is_complete:
-                break
-            # Only the first hand of the batch needs to apply the blind
-            # override; after that the engine reuses the stored values.
-            summaries.append(
-                self.run_hand(small_blind=small_blind, big_blind=big_blind)
-            )
-            small_blind = None
-            big_blind = None
-            if until_one_left and self.is_complete:
-                break
-        return summaries
+        with self.lock:
+            if max_hands <= 0:
+                raise ValueError("max_hands must be positive")
+            summaries = []
+            for _ in range(max_hands):
+                if self.is_complete:
+                    break
+                # Only the first hand of the batch needs to apply the blind
+                # override; after that the engine reuses the stored values.
+                summaries.append(
+                    self._run_hand_locked(
+                        small_blind=small_blind,
+                        big_blind=big_blind,
+                    )
+                )
+                small_blind = None
+                big_blind = None
+                if until_one_left and self.is_complete:
+                    break
+            return summaries
 
     def to_dict(self) -> dict[str, object]:
+        with self.lock:
+            return self._to_dict_unlocked()
+
+    def snapshot_completed(self) -> dict[str, object]:
+        """Return a stable snapshot from the latest completed hand boundary.
+
+        If a hand is currently running under ``self.lock``, this method does
+        not block. It returns the most recent completed hand summary and
+        stacks captured in memory, which is exactly what status endpoints
+        need while a long-running HTTP-agent decision is in progress.
+        """
+        if self.lock.acquire(blocking=False):
+            try:
+                return deepcopy(self._to_dict_unlocked())
+            finally:
+                self.lock.release()
+        return deepcopy(self._completed_snapshot)
+
+    def _to_dict_unlocked(self) -> dict[str, object]:
         return {
             "game_id": self.game_id,
             "status": "complete" if self.is_complete else "running",
@@ -449,9 +485,18 @@ class TableGame:
         try:
             requested = agent.decide(observation)
         except Exception:
-            requested = PlayerAction("fold")
+            requested = self._default_action(observation.legal_actions)
         return self._coerce_action(requested, observation.legal_actions)
 
+    def _default_action(self, legal_actions: list[dict[str, object]]) -> PlayerAction:
+        by_action = {str(action["action"]): action for action in legal_actions}
+        for action_type in ("check", "call", "fold"):
+            if action_type in by_action:
+                legal = by_action[action_type]
+                return PlayerAction(action_type, int(legal.get("amount") or 0))
+        legal = legal_actions[0]
+        return PlayerAction(str(legal["action"]), int(legal.get("amount") or 0))
+
     def _coerce_action(
         self,
         requested: PlayerAction,
@@ -581,7 +626,7 @@ class TableGame:
         swallow individual exceptions so a flaky remote endpoint cannot
         break the table flow.
         """
-        snapshot = self.to_dict()
+        snapshot = self._to_dict_unlocked()
         for agent in self.agents.values():
             try:
                 agent.on_game_update(snapshot)