Reorganize configs: main->pvp, ladder out of ablations, models.yaml->mini/model_roster.yaml

Author: john-b-yang

codeclash/agents/mini_anthropic_model.py

@@ -11,7 +11,7 @@
 `model_class: codeclash.agents.mini_anthropic_model.AnthropicModel` and provide the API key,
 base URL, and model name (see the `*_env` config fields, which keep endpoint-specific values in
 the environment rather than in committed configs). Requires the optional `anthropic` dependency
-(`uv pip install -e '.[llama]'`). See configs/ablations/ladder/robotrumble_llama.yaml.
+(`uv pip install -e '.[llama]'`). See configs/ladder/robotrumble_llama.yaml.
 """
 
 import json

codeclash/analysis/code_evolve/main.py

@@ -18,7 +18,7 @@
 from codeclash.arenas import ARENAS
 from codeclash.constants import LOCAL_LOG_DIR
 
-MODELS_PATH = Path("configs/models.yaml")
+MODELS_PATH = Path("configs/mini/model_roster.yaml")
 TARGET_ROUNDS = [1, 15, 5, 10]
 
 

codeclash/cli/ladder.py

@@ -85,7 +85,7 @@ def make(
 ):
     """Build a ladder: run PvP tournaments across all pairs of players (for ranking).
 
-    [dim]• codeclash ladder make configs/ablations/ladder/make_battlesnake.yaml[/dim]
+    [dim]• codeclash ladder make configs/ladder/make_battlesnake.yaml[/dim]
     """
     yaml_content = config_path.read_text()
     preprocessed_yaml = resolve_includes(yaml_content, base_dir=CONFIG_DIR)

codeclash/utils/generate_confs.py

@@ -3,14 +3,14 @@
 
 Each configuration file specifies a tournament between two models in a given arena,
 including the number of rounds and simulations per round. The configurations are saved
-as YAML files in the specified output directory (default: configs/main/).
+as YAML files in the specified output directory (default: configs/pvp/).
 
 Also generates a tracking JSON file at configs/tracker.json to keep track of
 the number of tournaments and rounds played for each pair of models in each arena.
 
 Usage:
 
-python codeclash/utils/generate_confs.py -m configs/models.yaml -r 15 -s 1000
+python codeclash/utils/generate_confs.py -m configs/mini/model_roster.yaml -r 15 -s 1000
 """
 
 import argparse
@@ -184,7 +184,7 @@ def main(models, arenas, rounds: int, simulations: int, record_ratio: float, out
         "-m",
         "--models",
         type=str,
-        default="configs/models.yaml",
+        default="configs/mini/model_roster.yaml",
         help="Path to model configurations.",
     )
     parser.add_argument(
@@ -218,7 +218,7 @@ def main(models, arenas, rounds: int, simulations: int, record_ratio: float, out
         "-o",
         "--output",
         type=Path,
-        default=Path("configs/main/"),
+        default=Path("configs/pvp/"),
         help="Output directory for configuration files (default: main/).",
     )
     args = parser.parse_args()

codeclash/viewer/static/js/picker.js

@@ -503,7 +503,7 @@ async function fillTextareaWithAWSSubmitCommands() {
     // Format output as AWS submit commands
     const commands = successfulResults.map(
       (result) =>
-        `aws/run_job.py -- aws/docker_and_sync.sh codeclash run configs/main/${result.config_name}`,
+        `aws/run_job.py -- aws/docker_and_sync.sh codeclash run configs/pvp/${result.config_name}`,
     );
     textarea.value = commands.join("\n");
 

configs/ablations/ladder/README.md configs/ladder/README.mdconfigs/ablations/ladder/README.md renamed to configs/ladder/README.md

@@ -5,7 +5,7 @@ For a more static and hill-climb-able version of CodeClash, we introduce CC:Ladd
 For instance, for RobotRumble, we created a ladder by doing the following steps:
 1. From the online [leaderboard](https://robotrumble.org/boards/2), we manually crawled all open source, published bots and pushed them as branches to the [CC:RobotRumble](https://github.com/CodeClash-ai/RobotRumble) repository.
 2. We then created the `robotrumble.yaml` file in this folder.
-3. Next, from the repository root, we run `uv run codeclash ladder run configs/ablations/ladder/robotrumble.yaml`, which runs PvP Tournaments against all pairs of branches.
+3. Next, from the repository root, we run `uv run codeclash ladder run configs/ladder/robotrumble.yaml`, which runs PvP Tournaments against all pairs of branches.
 4. From these logs, we then calculate win rate to rank all models.
 
 You can follow these steps to create your own "CC:<arena>" ladder.
@@ -19,7 +19,7 @@ Each arena has a few kinds of config in this folder:
 - `make_<arena>.yaml` — the round-robin used to **build** the ladder (`ladder make`), running PvP tournaments across all pairs of human bots to rank them.
 - `<arena>.yaml` — the **run** config (`ladder run`): a climber ascends the ranked ladder rung by rung until it loses.
 - `<arena>__<model>.yaml` — per-model run configs (e.g. `battlesnake__opus_4_8.yaml`) that swap in a specific model via `model: !include mini/models/llama_<model>.yaml`.
-- `rungs/<arena>.yaml` — the ranked opponent list (worst first, strongest last), shared by both `<arena>.yaml` and every `<arena>__<model>.yaml` through `ladder: !include ablations/ladder/rungs/<arena>.yaml`. Edit the ladder in this one file and every config for that arena picks it up.
+- `rungs/<arena>.yaml` — the ranked opponent list (worst first, strongest last), shared by both `<arena>.yaml` and every `<arena>__<model>.yaml` through `ladder: !include ladder/rungs/<arena>.yaml`. Edit the ladder in this one file and every config for that arena picks it up.
 
 ## Ladder advancement rule (`ladder_rules`)
 

configs/ablations/ladder/battlesnake.yaml configs/ladder/battlesnake.yamlconfigs/ablations/ladder/battlesnake.yaml renamed to configs/ladder/battlesnake.yaml

@@ -1,10 +1,10 @@
 # CC:Ladder for BattleSnake — the ranked ladder of human bots (worst opponent first,
 # strongest last), derived from the round-robin in make_battlesnake.yaml
 # (Bradley-Terry/Elo over 1225 pairwise tournaments). An LM climber ascends rung by
-# rung until it loses.  Run:  uv run codeclash ladder run configs/ablations/ladder/battlesnake.yaml
+# rung until it loses.  Run:  uv run codeclash ladder run configs/ladder/battlesnake.yaml
 tournament:
   rounds: 5
-ladder_rules: !include ablations/ladder/ladder_rules.yaml
+ladder_rules: !include ladder/ladder_rules.yaml
 game:
   name: BattleSnake
   sims_per_round: 250
@@ -24,5 +24,5 @@ player:
         temperature: 0.2
         max_tokens: 4096
   push: True
-prompts: !include ablations/ladder/ladder_prompt.yaml
-ladder: !include ablations/ladder/rungs/battlesnake.yaml
+prompts: !include ladder/ladder_prompt.yaml
+ladder: !include ladder/rungs/battlesnake.yaml

…adder/battlesnake__gemini_3_5_flash.yaml …adder/battlesnake__gemini_3_5_flash.yamlconfigs/ablations/ladder/battlesnake__gemini_3_5_flash.yaml renamed to configs/ladder/battlesnake__gemini_3_5_flash.yaml configs/ablations/ladder/battlesnake__gemini_3_5_flash.yaml renamed to configs/ladder/battlesnake__gemini_3_5_flash.yaml

@@ -1,8 +1,8 @@
 # BattleSnake ladder climbed by gemini-3-5-flash. Requires LLAMA_API_KEY in .env.
-#   uv run codeclash ladder run configs/ablations/ladder/battlesnake__gemini_3_5_flash.yaml
+#   uv run codeclash ladder run configs/ladder/battlesnake__gemini_3_5_flash.yaml
 tournament:
   rounds: 5
-ladder_rules: !include ablations/ladder/ladder_rules.yaml
+ladder_rules: !include ladder/ladder_rules.yaml
 game:
   name: BattleSnake
   sims_per_round: 250
@@ -18,5 +18,5 @@ player:
     agent: !include mini/default.yaml
     model: !include mini/models/llama_gemini_3_5_flash.yaml
   push: True
-prompts: !include ablations/ladder/ladder_prompt.yaml
-ladder: !include ablations/ladder/rungs/battlesnake.yaml
+prompts: !include ladder/ladder_prompt.yaml
+ladder: !include ladder/rungs/battlesnake.yaml

…lations/ladder/battlesnake__gpt_5_5.yaml configs/ladder/battlesnake__gpt_5_5.yamlconfigs/ablations/ladder/battlesnake__gpt_5_5.yaml renamed to configs/ladder/battlesnake__gpt_5_5.yaml configs/ablations/ladder/battlesnake__gpt_5_5.yaml renamed to configs/ladder/battlesnake__gpt_5_5.yaml

@@ -1,8 +1,8 @@
 # BattleSnake ladder climbed by gpt-5-5. Requires LLAMA_API_KEY in .env.
-#   uv run codeclash ladder run configs/ablations/ladder/battlesnake__gpt_5_5.yaml
+#   uv run codeclash ladder run configs/ladder/battlesnake__gpt_5_5.yaml
 tournament:
   rounds: 5
-ladder_rules: !include ablations/ladder/ladder_rules.yaml
+ladder_rules: !include ladder/ladder_rules.yaml
 game:
   name: BattleSnake
   sims_per_round: 250
@@ -18,5 +18,5 @@ player:
     agent: !include mini/default.yaml
     model: !include mini/models/llama_gpt_5_5.yaml
   push: True
-prompts: !include ablations/ladder/ladder_prompt.yaml
-ladder: !include ablations/ladder/rungs/battlesnake.yaml
+prompts: !include ladder/ladder_prompt.yaml
+ladder: !include ladder/rungs/battlesnake.yaml

…ations/ladder/battlesnake__opus_4_7.yaml configs/ladder/battlesnake__opus_4_7.yamlconfigs/ablations/ladder/battlesnake__opus_4_7.yaml renamed to configs/ladder/battlesnake__opus_4_7.yaml configs/ablations/ladder/battlesnake__opus_4_7.yaml renamed to configs/ladder/battlesnake__opus_4_7.yaml

@@ -1,8 +1,8 @@
 # BattleSnake ladder climbed by opus-4-7. Requires LLAMA_API_KEY in .env.
-#   uv run codeclash ladder run configs/ablations/ladder/battlesnake__opus_4_7.yaml
+#   uv run codeclash ladder run configs/ladder/battlesnake__opus_4_7.yaml
 tournament:
   rounds: 5
-ladder_rules: !include ablations/ladder/ladder_rules.yaml
+ladder_rules: !include ladder/ladder_rules.yaml
 game:
   name: BattleSnake
   sims_per_round: 250
@@ -18,5 +18,5 @@ player:
     agent: !include mini/default.yaml
     model: !include mini/models/llama_opus_4_7.yaml
   push: True
-prompts: !include ablations/ladder/ladder_prompt.yaml
-ladder: !include ablations/ladder/rungs/battlesnake.yaml
+prompts: !include ladder/ladder_prompt.yaml
+ladder: !include ladder/rungs/battlesnake.yaml