sa-buc ef6b0d74e1 feat(read): add session-aware formatting for read tool and update BEAM eval ... - Add truncate_session_output in _file_io.py to render jsonl session lines as [speaker @ time] content before byte-budget truncation - Add read_step_format_session flag to ReadStep, honoring injected job kwargs (precedence) and YAML fallback - Inject read_step_format_session=True into BaseAgenticAnswerStep so agentic answer reads render session transcripts human-readably - Refine BEAM agentic_answer prompt: continue multi-angle search after preliminary answer, forbid fabrication/extrapolation - Update BEAM config to 1M variant and add sequential 100K-eval / 1M-build shell script - Refresh benchmark/results_md/beam.md with latest results		2026-08-05 13:24:22 +08:00
..
__init__.py	feat(benchmark): add BEAM & restructure LongMemEval evaluation framework (#375)	2026-07-21 19:09:50 +08:00
agentic_answer.py	feat(benchmark): add BEAM & restructure LongMemEval evaluation framework (#375)	2026-07-21 19:09:50 +08:00
agentic_answer.yaml	feat(read): add session-aware formatting for read tool and update BEAM eval	2026-08-05 13:24:22 +08:00
auto_memory.py	refactor(beam): rename max_chunk_words to max_segment_words, drop one-off pilot scripts	2026-08-04 15:28:46 +08:00
auto_memory.yaml	feat(beam): enhance auto_memory with source markers and pilot ingest tooling	2026-08-04 15:28:23 +08:00
llm_judge.py	chore(benchmark): isolate dataset/workspaces/results per benchmark	2026-07-31 17:57:53 +08:00
llm_judge.yaml	feat(benchmark): add BEAM & restructure LongMemEval evaluation framework (#375)	2026-07-21 19:09:50 +08:00