[2.0] Add new Frontier-CS 2.0 problem vector_db_ann_disk

2.0/problems/vector_db_ann_disk/config.yaml

@@ -0,0 +1,41 @@
+tag: systems
+runtime:
+  language: rust
+  timeout_seconds: 10800
+  environment: "Rust project; hidden disk ANN benchmark; Python/NumPy judge"
+  apt_packages:
+    - build-essential
+    - cargo
+    - git
+    - rustc
+  judge_apt_packages:
+    - build-essential
+    - cargo
+    - rustc
+    - python3-pip
+    - python3-numpy
+  judge_pip_packages:
+    - faiss-cpu
+  docker:
+    image: ubuntu:24.04
+environment:
+  # If these resource limits change, also update the resource budget text in
+  # readme and harbor/app/README.md so agents can design parallel algorithms
+  # for the actual CPU and memory budget.
+  cpus: 8
+  memory_mb: 8192
+  storage_mb: 8192
+  build_timeout_seconds: 3600
+evaluation:
+  # The judge drives the search service with this many concurrent workers.
+  # Keep this aligned with the CPU budget unless the task is intentionally
+  # changed into a higher-concurrency service benchmark.
+  query_concurrency: 8
+  queries_per_worker: 64
+submission:
+  kind: directory
+  path: /app
+  exclude:
+    - target
+    - .git
+    - .frontier-cs

2.0/problems/vector_db_ann_disk/evaluate.sh

@@ -0,0 +1,37 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+
+if [[ $# -gt 0 ]]; then
+  exec python3 "$SCRIPT_DIR/evaluator.py" "$@"
+fi
+
+SOLUTION="/work/execution_env/solution_env/solution.rs"
+if [[ ! -f "$SOLUTION" ]]; then
+  echo "Error: Missing $SOLUTION" >&2
+  exit 1
+fi
+
+if ! command -v cargo >/dev/null 2>&1 || ! python3 -c 'import numpy, faiss' >/dev/null 2>&1; then
+  export DEBIAN_FRONTEND=noninteractive
+  apt-get update -qq
+  apt-get install -y -qq --no-install-recommends \
+    build-essential cargo rustc python3-pip python3-numpy >/dev/null
+  python3 -c 'import faiss' >/dev/null 2>&1 || \
+    pip3 install --break-system-packages -q faiss-cpu
+fi
+
+WORKDIR=$(mktemp -d)
+trap 'rm -rf "$WORKDIR"' EXIT
+cp -R "$SCRIPT_DIR/harbor/app/." "$WORKDIR/"
+cp "$SOLUTION" "$WORKDIR/src/db.rs"
+
+# The repository validator checks that the evaluator path works; the full
+# 100M-vector disk benchmark is exercised through Harbor.
+export FRONTIER_VECTOR_DB_N="${FRONTIER_VECTOR_DB_N:-5000}"
+export FRONTIER_VECTOR_DB_Q="${FRONTIER_VECTOR_DB_Q:-16}"
+export FRONTIER_VECTOR_DB_WARMUP="${FRONTIER_VECTOR_DB_WARMUP:-4}"
+export FRONTIER_VECTOR_DB_CACHE="${FRONTIER_VECTOR_DB_CACHE:-/tmp/frontier_vector_db_ann_disk_ci}"
+
+python3 "$SCRIPT_DIR/evaluator.py" "$WORKDIR"