7 commits

Author	SHA1	Message	Date
jinli.yl	b3a0a2b030	fix(evaluation): clarify usage semantics and atomic counters	2026-07-31 22:09:06 +08:00
sa-buc	a777976dd8	feat: agentscope dual-version compat & benchmark improvements ... - Add version_tuple utility for semantic version comparison - AsAgentWrapper: version-aware InjectionConfig, max_iters doubling, and token usage collection (reply vs reply_stream) for AS>=2.0.5/<2.0.5 - Default inject_runtime_state=False in wrapper to avoid benchmark time-anchor conflicts; remove per-callsite injection_config overrides - longmemeval run.py: support question_ids filter in dataset config - Fix unused import in test_evaluation_interface; format fixes	2026-07-31 13:21:03 +08:00
酱牛肉	b5471e668d	support agent scope 2.0.5	2026-07-30 18:14:58 +08:00
酱牛肉	a028cae33d	benchmark输出完整token消耗统计	2026-07-30 14:43:33 +08:00
酱牛肉	26f221e765	token消耗量统计	2026-07-30 14:09:20 +08:00
酱牛肉	e14ff16cac	job counter	2026-07-30 12:33:40 +08:00
酱牛肉	4e06d59aca	feat(evaluation): add check_job_count interface and report search calls in benchmarks ... - Extract _counter_key from BaseJob._record_call for reusable counter lookup - Add reme.utils.evaluation_interface.check_job_count read-only helper - Track and report average search calls per query in beam and longmemeval benchmarks	2026-07-30 12:09:57 +08:00