Add Gomoku CC:Ladder

configs/ladder/README.md

@@ -12,6 +12,15 @@ You can follow these steps to create your own "CC:<arena>" ladder.
 The tricky part is typically finding a large collection of human solutions for a particular arena.
 We've typically found that googling for online leaderboards or awesome-<arena> repositories (e.g. [BattleSnake](https://github.com/BattlesnakeOfficial/awesome-battlesnake)) is a good strategy.
 
+### Gomoku (newly added)
+
+The [CC:Gomoku](https://github.com/CodeClash-ai/Gomoku) repo hosts the human bots on `human/*`
+branches (like the other arenas, bot code lives only on the branches, not in this repo): 21
+open-source Gomoku/Gobang AIs ported into the arena's single-file `get_move(board, color)` contract
+— pure-Python minimax/MCTS/threat-search bots imported directly, plus JS/Java/C++ engines (e.g.
+lihongxun945, blackstone, blupig) reimplemented in stdlib Python — alongside a strategic starter.
+AlphaZero/CNN bots were skipped (need trained weights).
+
 ## Config layout
 
 Each arena has a few kinds of config in this folder:

configs/ladder/make_gomoku.yaml

@@ -0,0 +1,64 @@
+# Round-robin over the human Gomoku bots (ported from open-source repos + a strategic starter),
+# used to RANK them via Elo/Bradley-Terry -> see gomoku.yaml for the ladder.
+# rounds:0 = dummy players just play the baseline Gomoku game (no code edits). Colors are randomized
+# per game, so sims_per_round averages over first-move advantage. N bots -> N*(N-1)/2 pairs.
+# Bots live on CodeClash-ai/Gomoku human/* branches; Docker required.
+#
+# COST (measured ~8-9s/game -> ~4-4.5 min/pair at sims_per_round=30; 22 bots -> 231 pairs
+# ~= 16.5 core-hours; pairs are single-threaded so wall = core-hours / workers):
+#   * Mac 10-core (--workers 8): ~2 h    * 32-core box (-w 30): ~33 min
+# Matchups are decisive (frequent 30-0 sweeps), so 30 sims ranks cleanly; bump to 60 only if
+# the Elo confidence intervals overlap. Keep --workers <= cores-2. Resumable (skips logged pairs).
+# Run: uv run codeclash ladder make configs/ladder/make_gomoku.yaml --workers 8
+tournament:
+  rounds: 0
+game:
+  name: Gomoku
+  sims_per_round: 30
+players:
+- agent: dummy
+  branch_init: human/gomoku/blupig
+- agent: dummy
+  branch_init: human/gomoku/canberkakcali
+- agent: dummy
+  branch_init: human/gomoku/colingogogo
+- agent: dummy
+  branch_init: human/gomoku/gonghailong
+- agent: dummy
+  branch_init: human/gomoku/haslam22
+- agent: dummy
+  branch_init: human/gomoku/hovanhoa
+- agent: dummy
+  branch_init: human/gomoku/husus
+- agent: dummy
+  branch_init: human/gomoku/junxiaosong_mcts
+- agent: dummy
+  branch_init: human/gomoku/kali_hac
+- agent: dummy
+  branch_init: human/gomoku/kevin2014123
+- agent: dummy
+  branch_init: human/gomoku/lihongxun945
+- agent: dummy
+  branch_init: human/gomoku/linhusp
+- agent: dummy
+  branch_init: human/gomoku/marblexu
+- agent: dummy
+  branch_init: human/gomoku/qwertyforce
+- agent: dummy
+  branch_init: human/gomoku/rayfc_mcts
+- agent: dummy
+  branch_init: human/gomoku/russell_a
+- agent: dummy
+  branch_init: human/gomoku/smahot
+- agent: dummy
+  branch_init: human/gomoku/tsrmkumoko
+- agent: dummy
+  branch_init: human/gomoku/xkien2k4
+- agent: dummy
+  branch_init: human/gomoku/zhangshun97
+- agent: dummy
+  branch_init: human/gomoku/zitongmao
+- agent: dummy
+  branch_init: human/muhtasham/strategic-starter
+prompts:
+  game_description: Gomoku ladder