# BEAM evaluation configuration
# This file controls what/how to evaluate.

dataset:
  beam_root: "benchmark/beam/dataset/BEAM"   # BEAM dataset root
  chat_size: "1M"                        # 100K | 500K | 1M | 10M (dataset variant)
  case_ids: []                          # empty = all cases; or ["1", "2", "3"]
  start_index: 0                        # first case index (for pagination)
  num_items: 0                          # 0 = all cases; >0 = limit
  workspace_root: "benchmark/beam/workspaces/beam"  # workspace root for case workspaces

evaluation:
  num_workers: 20                       # 0 = auto; 1 = sequential; >1 = parallel (per-case)
  compress_session: false               # true = compress session chunks in search_v2 (query-aware); false = no compression

reme:
  config: "benchmark"                   # shared ReMe benchmark preset
  plugins: [beam, beam-judge]

output:
  dir: "benchmark/beam/results"
  log_dir: "logs"                       # log directory (relative to project root)
  log_prefix: "beam"                    # benchmark name used in log filenames
  log_to_console: true
  log_to_file: true