# Benchmark configuration — single source of truth.
#
# All parameters aligned with the upstream evaluation reference so that
# benchmark numbers are directly comparable to published LoCoMo results.
# BenchmarkConfig reads this file on every run.

# --- EverOS server ---
cascade_timeout = 7200                      # max seconds to wait for cascade + OME to complete
batch_size = 25                             # messages per /add request (everos caps at 500)

# --- Search ---
methods = "agentic"                         # comma-separated: keyword, vector, hybrid, agentic
top_k = 10                                  # episodes to retrieve per question
eval_owner = "speaker_a"                    # which speaker's memory partition to query

# --- Answer LLM ---
answer_model = "gpt-4.1-mini"              # LLM for generating answers from retrieved context
answer_temperature = 0.0                    # deterministic answers
answer_max_tokens = 32768                   # max output tokens per answer call
answer_timeout = 300.0                      # per-request socket timeout (seconds)
answer_max_retries = 5                      # retry budget (HTTP + empty-response retries)

# --- Judge LLM ---
judge_model = "gpt-4o-mini"                # LLM judge for correctness evaluation
judge_temperature = 0.0                     # deterministic judging
judge_timeout = 300.0                       # per-request socket timeout (seconds)
judge_max_retries = 5                       # retry budget
judge_runs = 3                              # majority vote across N independent judge runs

# --- Concurrency ---
conversations_concurrency = 10                 # how many conversations run at the same time
search_concurrency = 5                         # concurrent /search requests per conversation
eval_concurrency = 20                          # concurrent answer/judge LLM calls per conversation