Focus project on JAX PPO

scripts/autonomous_cycle_eval.sh

@@ -1,30 +0,0 @@
-#!/bin/bash
-# Autonomous cycle eval helper.
-# Usage: ./autonomous_cycle_eval.sh <run-prefix> [extra eval args...]
-# Finds latest run matching prefix, runs eval --ckpt latest.pt with 30 games,
-# and reports: timeouts, natural-end wins per opponent.
-
-set -euo pipefail
-
-PREFIX="${1:-}"
-shift || true
-
-if [ -z "$PREFIX" ]; then
-    echo "usage: $0 <run-prefix> [extra eval args...]"
-    exit 1
-fi
-
-RUN=$(ls -td runs/*${PREFIX}* 2>/dev/null | head -1)
-if [ -z "$RUN" ]; then
-    echo "no run matching ${PREFIX}" >&2
-    exit 1
-fi
-
-CKPT="$RUN/latest.pt"
-if [ ! -f "$CKPT" ]; then
-    echo "no checkpoint at $CKPT" >&2
-    exit 1
-fi
-
-echo "=== eval $CKPT ==="
-uv run lost-cities-ismcts eval --ckpt "$CKPT" --games 30 --verbose "$@" 2>&1

scripts/bench_inference_backend.py

@@ -37,12 +37,12 @@ def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(description="Benchmark Deep CFR traversal inference backends.")
     parser.add_argument(
         "--config-local",
-        default="configs/deep_cfr/default.yaml",
+        default="legacy/deep-cfr/configs/default.yaml",
         help="Config for the local traversal inference backend.",
     )
     parser.add_argument(
         "--config-server",
-        default="configs/deep_cfr/default_server.yaml",
+        default="legacy/deep-cfr/configs/default_server.yaml",
         help="Config for the server traversal inference backend.",
     )
     parser.add_argument("--iterations", type=int, default=10)

scripts/export_jax_ppo_onnx.py

@@ -4,6 +4,7 @@
 from __future__ import annotations
 
 import argparse
+import hashlib
 import json
 from pathlib import Path
 
@@ -86,10 +87,14 @@ def export_model(checkpoint: Path, config: Path | None, output: Path) -> None:
     )
     output.parent.mkdir(parents=True, exist_ok=True)
     onnx.save(model, output)
+    model_bytes = output.read_bytes()
     manifest = {
         "format": "coolrl-lost-cities-jax-ppo-onnx-v1",
-        "source_checkpoint": str(checkpoint.resolve()),
-        "source_config": str(config_path.resolve()),
+        "model_file": output.name,
+        "model_size_bytes": len(model_bytes),
+        "model_sha256": hashlib.sha256(model_bytes).hexdigest(),
+        "source_checkpoint": checkpoint.name,
+        "source_config": config_path.name,
         "observation_size": OBS_DIM,
         "action_size": N_ACTIONS,
         "hidden_size": cfg.network.hidden_size,

scripts/librarian-ignore.txt

@@ -7,14 +7,7 @@
 #
 # Format examples:
 #   scripts/foo.sh                   # exact path
-#   configs/deep_cfr/model-*.yaml    # glob
+#   configs/jax_ppo/model-*.yaml     # glob
 #   docs/research/*.md               # whole directory
 #
 # Comments after `#` are stripped per line. Blank lines ignored.
-
-# Future config + script described in docs/plans/model_size_experiment.md
-configs/deep_cfr/model-size-*.yaml
-scripts/run_model_size_experiment.sh
-
-# Future config described in docs/plans/torch_compile.md
-configs/deep_cfr/default_compile.yaml

scripts/profile_gpu_forward.py

@@ -1,7 +1,7 @@
 """Profile GPU forward-pass throughput for the Deep CFR trainer network.
 
 Builds the same DeepCFRMLP that ``DeepCFRTrainer.__init__`` constructs from
-``configs/deep_cfr/default.yaml``, then measures average forward-pass time on
+``legacy/deep-cfr/configs/default.yaml``, then measures average forward-pass time on
 CUDA across a sweep of batch sizes. The goal is to decide whether batched
 traversal inference (Optimization Priorities #5) is worth implementing.
 """
@@ -19,7 +19,7 @@ from coolrl_lost_cities.games.classic.deep_cfr.config import load_config
 from coolrl_lost_cities.games.classic.deep_cfr.networks import DeepCFRMLP
 
 REPO_ROOT = Path(__file__).resolve().parent.parent
-CONFIG_PATH = REPO_ROOT / "configs" / "deep_cfr" / "default.yaml"
+CONFIG_PATH = REPO_ROOT / "legacy" / "deep-cfr" / "configs" / "default.yaml"
 
 BATCH_SIZES = [1, 4, 16, 64, 256, 1024]
 WARMUP_ITERS = 10