ReMe/benchmark/longmemeval/config.yaml
sa-buc 60564d5d54 refactor(benchmark): make session compression config-driven via compress_session flag
Move session-transcript compression from LME hard-coded injection to a
runtime context flag set by evaluation.compress_session in each
benchmark config. Compression is off by default for both BEAM and LME,
and BaseAgenticAnswerStep now conditionally injects the _search compress
payload only when the flag is truthy.
2026-08-04 16:22:11 +08:00

33 lines
1.6 KiB
YAML

# LongMemEval evaluation configuration
# This file controls what/how to evaluate.
dataset:
path: "benchmark/longmemeval/dataset/longmemeval_s_reme_cleaned.json"
start_index: 0 # first item index
num_items: 500 # how many items to evaluate (starting from start_index)
max_sessions: 0 # 0 = all sessions; >0 = limit sessions per item for testing
question_types: [] # filter by question_type; empty list = no filtering (all types)
workspace_root: "benchmark/longmemeval/workspaces/longmemeval-s" # workspace root for item workspaces
evaluation:
# LLM-as-judge uses the 'judge' as_llm component defined in lme.yaml
# Model and credentials are configured there (reading from .env)
# Judgment is always binary (yes/no) — defined in lme/llm_judge.yaml
num_workers: 32 # 0 = auto (cpu_count - 2, min 1); 1 = sequential; >1 = parallel
filter_future_sessions: true # true = only ingest sessions with timestamp <= question_date
compress_session: false # true = compress session chunks in search_v2 (query-aware); false = no compression
reme:
config: "lme.yaml" # reme config to use (in reme/config/)
# Dream trigger: when gap between consecutive sessions crosses this hour (23:00)
dream_trigger_hour: 23
# Dream scan_days for each trigger
dream_scan_days: 2
dream_max_units: 5
output:
dir: "benchmark/longmemeval/results"
log_dir: "logs" # log directory (relative to project root)
log_prefix: "longmemeval" # benchmark name used in log filenames
log_to_console: true
log_to_file: true