22 commits

Author	SHA1	Message	Date
xyf2020	f04eedb3ab	feat(Tag filter): Add an optional rebuildable tag index for file frontmatter (#517) ... * Add optional tag generation and normalization to auto memory * Add tag index components and clean up temporary JSONL files * Preserve tag index state when reconciliation fails * Refactor and streamline application implementation * Fix pylint C1803 warnings in tag normalization tests * Document optional tag index configuration * Make tag index failures non-blocking and disable auto-memory tags * fix(tag-index): fail closed and support reindexing * fix(tag-index): preserve complete query expressions --------- Co-authored-by: jinli.yl <jinli.yl@alibaba-inc.com>	2026-09-07 15:52:17 +08:00
WQS	5c17874f73	feat(auto_resource): interpret image resources into daily notes (#500) ... * feat: add auto_image step for image resource caption notes * feat: wire image resources into the resource watch loop * refactor: split auto resource processors behind router * refactor: align resource processor module names * refactor: preserve auto resource compatibility * refactor: clarify auto resource routing structure * fix: address auto resource review concerns * test: scope auto resource fixtures * docs: align auto resource processor wording * test: cover image resize failures * fix: harden image resource lifecycle * fix: preserve resource image detail and linked daily ownership * style(file-graph): stabilize multiline docstring formatting	2026-09-07 12:00:38 +08:00
xyf2020	3f2eb6235f	feat(benchmark): extract BEAM and LongMemEval into standalone plugins (#512) ... * Simplify project implementation * Centralize benchmark agentic answer base class * Remove bundled ReMe source snapshots * Preserve local benchmark configs and plugin discovery behavior * docs: enrich job parameter descriptions in beam and lme plugin configs * Simplify project structure and remove obsolete code * Move benchmark search step configuration into BEAM and LME plugins * Rename benchmark judge packages to avoid import collisions * Remove explicit plugin package loading in favor of entry-point discovery * Export benchmark plugin Steps from public packages	2026-09-03 14:06:39 +08:00
jinliyl	fc4a5398a8	fix(index): make embedding rebuild explicit and scoped (#508) ... * fix(index): make embedding rebuild explicit and scoped * fix(index): harden scoped reindex completion * fix(index): guard embedding space transitions * fix(index): serialize reindex with mutations * docs(index): clarify scoped reindex semantics * docs(index): explain synchronous checkpoint snapshots * fix(index): serialize checkpoint publication	2026-08-28 23:25:17 +08:00
jinliyl	ebcb154e37	fix(search): isolate range dedup state (#465)	2026-08-20 16:15:30 +08:00
jinliyl	9218a2d0e3	refactor: derive dialog paths from session_dir (#421) ... * refactor: derive dialog paths from session directory * fix: normalize configured session paths * fix: align dialog watch paths with writers * fix: reject absolute session directories	2026-08-06 17:07:14 +08:00
xyf2020	5bc46c88b6	feat(benchmark): enhance session memory retrieval and isolate benchmark assets (#409) ... * chore(benchmark): isolate dataset/workspaces/results per benchmark - Move shared benchmark/{datasets,memory_workspaces,results} into per-benchmark subdirs benchmark/<name>/{dataset,workspaces,results} - Update beam/longmemeval config.yaml and run.py path defaults - Relocate longmemeval download.py to benchmark/longmemeval/ (downloads into dataset/ subdir); inline dataset download docs into README - Update .gitignore: benchmark/*/{dataset,workspaces,results}/ - Move result-{beam,longmemeval}.md to benchmark/results_md/ and drop result- prefix; update README links - Fix stale path refs in llm_judge.py and logs/demo_search_format.py * feat(benchmark): add read tool to agentic answer and update BEAM results - Add 'read' to job_tools in BaseAgenticAnswerStep for file reading capability - Document read tool usage in lme/agentic_answer.yaml system prompt - Update result-beam.md with latest evaluation scores (OVERALL: 0.623/0.580) * feat(auto_memory): add source line-number markers for note traceability - Add _format_history hook in AutoMemoryStep with line-number annotation - Override in BeamAutoMemoryStep to prefix each turn with [Ln] for citation - Add session_file variable to prompt templates for source marker paths - Simplify repeated extraction rules by referencing system prompt - Enhance agentic_answer search strategy (multi-search, read tool hint) - Add warning log on ReadStep failure * feat(beam): enhance auto_memory with source markers and pilot ingest tooling * refactor(beam): rename max_chunk_words to max_segment_words, drop one-off pilot scripts * feat: add CompressorStep and search_v2 dual-mode session compression - Add CompressorStep (reme/steps/evolve/compressor.py) for direct LLM text compression with optional query-guided relevance filtering - Extend search_v2_step to support query-aware and query-independent session transcript compression via _compress injected kwargs - Refactor _source_format.py: split into render_chunk_entries + join_chunk_entries; session chunks now render line-aligned with L<n>: prefixes for verbatim/compressed parity - Add JOB_TOOLS and INJECTED_JOB_KWARGS to BaseAgenticAnswerStep for per-subclass tool and parameter injection - LmeAgenticAnswerStep injects _search._compress payload to enable query-aware compression during benchmark evaluation - Record compression ablation results in result-longmemeval.md - Add unit tests for CompressorStep and search compression paths * refactor(compress): relax session compression to lenient format-preserving strategy and update LME results * 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. * feat(lme/auto_memory): add source attribution markers with line numbers Add _format_history to annotate each turn with [Ln] line numbers and expose {session_file} in prompts so the agent can emit bare wikilink-style source markers like [[session/dialog/s1.jsonl#L1-L2,L5-L6]] at the end of factual entries. Consolidate the per-prompt body/format rules into references to the system prompt to avoid drift, and add frontmatter- protection guidance for the edit tool. * feat: improve agentic answer prompt and update beam 100K results - Strengthen abstention rule: prohibit extrapolation from related but non-direct evidence - Add multi-angle search after preliminary answer to check for conflicting/supplementary/updated information - Add max-iteration fallback to 'Information not found' - Update beam.md with 100K results (agentscope 2.0.4.post1, from scratch) including per-type token consumption and memory construction stats - config.yaml: 100K dataset, 20 workers for BEAM evaluation - run.py: add memory construction token usage tracking (default agent) - Overall: 0.635 → 0.654 (+0.019), contradiction_resolution: 0.338 → 0.478 (+0.140), abstention: 0.500 → 0.525 (+0.025) * 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 * chore(config): disable expand_links in beam and lme search_v2 configs * refactor(beam): drop one-off sequential 100K-eval-then-1M-build script * fix(benchmark): add compressor job to beam config and fix BEAM clone instructions - Add compressor job and compressor as_llm component to reme/config/beam.yaml (aligned with lme.yaml) so that compress_session: true works for BEAM - Add graceful degradation guard in search_v2._compress_session_entries: when the compressor job is missing from the active config, log a warning and skip compression instead of raising 'Job compressor not found'. Skipped when there is no app_context so unit tests mocking run_job still drive compression behavior. - Fix BEAM download instructions in README.md/README_ZH.md: add mkdir -p before cd benchmark/beam/dataset (the directory is gitignored and absent in a fresh clone) * fix(steps): guard compressor exceptions and fix ReadStep boolean override 1. search_v2: catch per-entry exceptions from run_job('compressor') inside compress() so asyncio.gather never propagates a compressor failure (e.g. temporary LLM outage). The failing entry keeps its original body while remaining entries are still compressed, preserving already-retrieved search results. 2. read: replace 'context_value or yaml_value' with an existence check so that a runtime-injected False can explicitly disable a YAML-true read_step_format_session flag. Add focused unit tests for both paths. * fix(search_v2): use existence check for strict_date_filter boolean override Replace 'context_value or yaml_value' with an existence-based check so that a runtime-injected False can explicitly disable a YAML-true strict_date_filter flag, consistent with the read_step_format_session fix. * refactor(search): simplify strict_date_filter fallback to truthiness-or * style(test): rename unused param to satisfy pylint W0613 --------- Co-authored-by: sa-buc <jiangniurou.xyf@dail-algo011164204033.ET135>	2026-08-05 19:23:42 +08:00
jinliyl	eac8223387	feat: add frontend-ready wikilink graph APIs (#414)	2026-08-05 16:45:50 +08:00
jinliyl	a9ec334adc	feat: simplify wikilink semantics and support line anchors (#412) ... * feat: simplify local links and support line anchors * fix: align line anchor tests with CI lint * fix: preserve local links across file moves * fix: encode markdown paths when rewriting links * refactor(read): keep explicit line range parameters * fix: simplify legacy link predicate compatibility * docs: align local link behavior with implementation * fix: skip unsupported markdown destination escapes * fix: normalize workspace link paths across platforms * fix: bound markdown link scanning * fix: keep local link processing linear * docs: clarify permissive markdown link parsing * fix: handle local link processing failures * refactor: limit file links to wikilink syntax * docs: align wikilink contract with implementation * fix: normalize dream and neighbor paths on Windows * fix: resolve workspace path for neighbor expansion	2026-08-05 11:47:50 +08:00
xyf2020	4eb2adf961	feat(faiss_file_store): upgrade FAISS to HNSW index with async reindex (#390) ... * feat(file_store): upgrade FAISS to HNSW index with async reindex and path constraint - Replace IndexFlatIP with IndexHNSWFlat for better recall/speed tradeoff - Add dynamic efSearch (limit * 5) scaled to query request size - Add async_reindex option: background rebuild with generation-based invalidation - Extract _delete_nodes() in LocalFileStore for subclass reuse - Add unit tests for file store consistency * fix: resolve pylint warnings in faiss store and test file * refactor(file_store): replace generation-based reindex with event-flag worker - Replace _reindex_generation/lock/task with a single long-lived worker coroutine consuming an asyncio.Event flag; repeated submissions coalesce - Use local index reference in vector_search to avoid TOCTOU on self._faiss_index - Pass index explicitly to _set_ef_search for consistency - Track _index_writes to re-arm reindex after concurrent writes - Update tests to match new internal API * fix: resolve pylint too-many-return-statements and implicit-booleaness warnings * feat(file_store): add refine maintenance hook and incremental embedding backfill - Add refine() idle-time maintenance hook to BaseFileStore/LocalFileStore - FaissLocalFileStore: incremental vector add on backfill instead of full rebuild - Dynamic tombstone compaction threshold scaled by index size - Add RefineStoreStep with daily cron job (refine_store_cron) - Enable faiss backend and embedding_store by default in default.yaml - Add unit tests for faiss index maintenance * chore(deps): promote faiss-cpu to core dependencies faiss backend is now the default file_store, so faiss-cpu moves from the optional [core] extra to the base dependencies list. * feat: rename refine_store to optimize_index and add vecdb_path_constraint - Rename refine_store step to optimize_index with cron job scheduling - Add vecdb_path_constraint to file_store components - Update default.yaml with optimize_index_cron and faiss backend comment - Update memory_search docs (en/zh) for FAISS vector management - Update unit tests for index maintenance * feat(faiss): add embedding digest to reject stale sidecar after partial dump Add _chunks_embedding_digest() that computes an order-independent SHA-256 over (chunk_id, float16 embedding) pairs. The digest is written into the idmap sidecar at dump time and verified at load time. A mismatch means the sidecar vectors belong to a different chunk generation than the authoritative JSONL — detectable even when the live-ID set is unchanged (same-ID in-place update crash window). Add test_faiss_rejects_stale_sidecar_after_partial_dump reproducing the crash-between-writes scenario and asserting digest-based rejection. Compress verbose docstrings/comments in existing tests for pylint line budget. --------- Co-authored-by: sa-buc <jiangniurou.xyf@dail-algo011164204033.ET135>	2026-07-27 19:54:38 +08:00
xyf2020	630f26b119	feat(search): scoped dedup, session-chunk merge, and unified recall formatting (#384) ... * feat(search): add tool_context-scoped chunk dedup with TTL Introduce _ToolContextDedupMixin shared by search/vector_search/bm25_search to skip already-seen chunks within one agent tool_context. Per-context state lives in app_context.metadata with configurable TTL (default 24h). * feat(search): unify chunk answer rendering with merge and explicit empty messages - Refactor SearchStep/VectorSearchStep/Bm25SearchStep to share format_chunks_answer for consistent source rendering and adjacent session-chunk merging. - Distinguish empty results: ALL_RETURNED_MESSAGE when dedup removes everything vs NO_RESULTS_MESSAGE when nothing matched. - Bump JsonlFileChunker default max_chars to 4000. - Add unit tests for source-format merge and empty-result messages. * refactor(config): reorganize file_chunker components and move jsonl max_chars into config - Register explicit markdown/json/jsonl chunkers in beam.yaml and lme.yaml with markdown options (embed_toc, max_ast_sections, frontmatter handling) and jsonl max_chars=4000. - Restrict default chunker to txt/log extensions. - Revert JsonlFileChunker code default max_chars back to 2000; the 4000 value now lives in config. * chore(benchmark): increase longmemeval num_items from 64 to 500 * refactor(search): split SearchStep into simplified and v2 variants, extract counter utility - Extract global_counter_next from ApplicationContext into reme/utils/counter.py as a standalone function operating on metadata dict with lazy initialization. - Split SearchStep into two variants: - SearchStep (simplified): inline chunk.id dedup, single-branch vector/keyword optimization based on vector_weight, inline answer formatting. - SearchV2Step (full): preserves _ToolContextDedupMixin with interval-subset-aware dedup and format_chunks_answer with session-aware chunk merging. - Update beam.yaml and lme.yaml to use search_v2_step for benchmark jobs. - Rename existing search tests to test_search_v2_step_* and add new test_search_step_* tests covering the simplified variant. * fix: normalise missing trailing newline in _build_union_chunk to prevent line collision * refactor: lazy-init counter tree in ApplicationContext metadata - Remove hardcoded _counter_tree and _counter_tree_lock initialization from ApplicationContext.metadata; rely on lazy initialization in reme.utils.counter.global_counter_next on first call - Set longmemeval num_items back to 500 - Remove obsolete trailing-newline collision tests --------- Co-authored-by: sa-buc <jiangniurou.xyf@dail-algo011164204033.ET135>	2026-07-22 17:17:23 +08:00
xyf2020	7b1da5a9ee	feat(benchmark): add BEAM & restructure LongMemEval evaluation framework (#375) ... * feat(eval): add LongMemEval evaluation framework with tool_defaults date injection - Add evaluation/longmemeval/ with run.py, config.yaml, and test scripts - Add reme/config/longmemeval.yaml for evaluation-specific model config - Add tool_defaults mechanism to as_agent_wrapper for injecting default tool kwargs (uses setdefault so LLM-provided values take priority) - Pass tool_defaults={'daily_write': {'date': day}} in auto_memory to ensure notes always use the correct historical date - Add timestamp interpolation (_interpolate_timestamps) in auto_memory for filling missing created_at fields via linear interpolation - Evaluation pipeline: ingest sessions -> dream -> search -> answer -> judge - Uses qwen3.6-flash for memory, qwen3.7-max for answer/judge * chore: gitignore logs/results/demo.py, keep empty dirs * chore: update .gitignore * feat(eval): add multiprocessing and session time filtering to longmemeval runner - Replace async execution with synchronous + multiprocessing for parallel item evaluation - Add filter_future_sessions option to only ingest sessions <= question date - Add question_types filtering in config - Add result summary with binary accuracy and avg score - Update config defaults (oracle variant, 50 items, 32 workers) - Minor code style fixes in agent_wrapper and auto_memory * feat: add bench_query_step with ReAct agent for benchmark query phase - Add BenchQueryStep using agent_wrapper with search job tool - Replace manual search+LLM answer in run.py with bench_query_job - Remove unused answer LLM config from longmemeval.yaml - Register benchmark step module in steps/__init__.py * feat: add start_date/end_date time filter support for search job - Add _extract_date_from_path to extract validated YYYY-MM-DD from chunk paths - Add start_date/end_date filtering in _matches_search_filter - Implement progressive recall in FaissLocalFileStore.vector_search - Promote start_date/end_date from context to search_filter in SearchStep - Add start_date/end_date parameters to search job in default.yaml - Add unit tests for date filter functionality * fix: validate/normalize date filters and harden _extract_date_from_path Address three code-review comments on the time_filter search feature: 1. Validate/normalize start_date and end_date before string comparison. _matches_search_filter does lexicographic comparison against path_date (always canonical YYYY-MM-DD). Raw caller values like '2026-2-28' or 'abc' would produce silently wrong results. Now SearchStep normalizes valid dates via extract_daily_date (with strptime fallback for non-zero-padded input) and silently ignores invalid dates with a logger.warning, removing them from the filter. 2. Clarify behavior for paths without embedded dates. Added optional strict_date_filter parameter (default False). When True and at least one date bound is active, chunks whose path yields no date (e.g. digest/personal/topic.md) are excluded. When False (default), the existing behavior is preserved — dateless paths pass through. 3. Harden _extract_date_from_path against non-standard suffixes. Previously parts[1].split('.')[0] accepted '2026-05-18.anything' as a valid date. Now only exact 'YYYY-MM-DD' (dir) and 'YYYY-MM-DD.md' (day-index) forms are accepted. * feat(eval): LLM-as-Judge per-type prompt routing, binary-only, progress tracking - Remove 0-5 score metric, keep only binary (yes/no) classification - Load per-question-type judge prompts from llm-as-judge.json (temporal-reasoning, knowledge-update, single-session-preference, __default__) - Replace SCORE_JUDGE_PROMPT with type-specific BINARY_JUDGE_PROMPT template - judge_response(): parameter 'metric' -> 'question_type', returns single 'judgment' - Summary output: add per-type accuracy breakdown, remove score stats - Add progress tracking: background thread prints PROGRESS every 10min - Add FINAL progress line and total elapsed time on completion - Add --log-level, --reme-log-level, -q CLI arguments - Parallel mode: pool.map -> pool.imap_unordered for real-time progress - config.yaml: full oracle (10000 items), 32 workers, all question types - Add kill.sh (process cleanup) and run_async.sh (background eval launcher) * docs: add LongMemEval oracle evaluation results (61.6% accuracy) * feat(bench): add MAX_ITERATION limit to BenchQueryStep and add _auto_memory.yaml * feat: add golden session benchmark & eval_only mode with refined prompt - Add benchmark/longmemeval/run_golden_session.py for golden session evaluation - Refine PROMPTED_SYSTEM_PROMPT: concise answer rule, remove 'Information not found' fallback - Add eval_only mode to run.py (--eval_only flag) - Add multiple eval config variants (evalonly, full, test5) - Add analyze_results.py for result parsing - Update auto_memory.yaml, longmemeval.yaml, application_config - Update result-longmemeval.md with latest evaluation results - Add benchmark results to .gitignore * update: refine answer prompts and increase max iteration to 6 - Tighten prompted-answer system prompt for more concise output - Comment out 'Information not found' fallback rule - Increase MAX_ITERATION from 5 to 6 in bench_query - Add recall_eval.py - Update evaluation results * feat(chunker): add dedicated JSON and JSONL file chunkers (cherry-pick from upstream #325) - Add JsonFileChunker: structure-aware chunking preserving nested key paths, optional list-to-dict conversion, size measured by json.dumps() char count - Add JsonlFileChunker: line-aligned sliding-window chunking with configurable overlap, supports char/byte mode switching - Register both chunkers in default.yaml (json for .json, jsonl for .jsonl) - Add comprehensive unit tests (21 + 20 test cases) * feat(service): add CLI service for local job execution (from upstream #334) - Introduce CliService to execute single jobs locally without serving ports - Add prepare_start_config and should_precheck_start functions for CLI job setup - Update reme start command to use CLI service when job argument is provided - Add show_metadata to client kwargs for optional CLI metadata output - Add unit tests for CLI service functionality and configuration handling * feat(steps): add BM25/vector search steps, Python execute step, and draft steps (from upstream #334) - Add Bm25SearchStep for plain BM25 keyword search with tool_context deduplication - Add VectorSearchStep for plain vector search with tool_context deduplication - Add PythonExecuteStep to run Python code in subprocess with timeout handling - Add AddDraftStep/ReadAllDraftStep for draft accumulation scoped by tool context - Update SearchStep with tool_context dedup, dynamic default limit via REME_SEARCH_LIMIT env, and candidate_multiplier default changed from 3.0 to 5.0 - Add comprehensive unit tests for all new steps * feat(search): add tool context deduplication and improve search configuration (#321) * feat(search): add tool context deduplication and improve search configuration - Modify _make_tool methods to accept and inject tool_context_id parameter - Add tool_context_id handling in AS and CC agent wrappers - Increase search candidate multiplier from 3.0 to 5.0 in default config - Extend HTTP client timeout from 30s to 3600s - Add tool context deduplication logic to prevent duplicate search results - Implement TTL-based expiration for seen chunks in tool contexts - Add comprehensive unit tests for tool context deduplication behavior - Update .gitignore to exclude longmemeval directory - Add time import for timestamp functionality in search step * refactor(search): replace time module with datetime for timestamp generation - Removed unused time import - Added static method _now_ts using datetime.timestamp - Updated clock parameter to use _now_ts method instead of time.time - Maintained same timestamp precision and functionality * fix(file_io): fix risk of out-workspace paths (#322) * fix(file_io): fix risk of out-workspace paths * chore(file_io): remove unused unittest file * fix(as_embedding): support both agentscope 2.0.2 and 2.0.3 (#323) 2.0.3 promoted `dimensions` to a required first-class constructor argument while keeping a backfill from `parameters.dimensions`; 2.0.2 has no such argument and reads `dimensions` from `Parameters`. Keep `dimensions` in `Parameters` for both versions and, when the model constructor accepts `dimensions`, pass `dimensions=None` so 2.0.3's backfill promotes it out of `parameters`. Co-authored-by: Claude Fable 5 <noreply@anthropic.com> * Bump version to 0.4.0.7 * refactor: delegate LLM-as-Judge to answer_judge_step and update eval config/results - run.py: replace inline judge logic with judge_response_via_job using app.run_job('answer_judge') - longmemeval.yaml: expand benchmark configuration - bench_query.py: enhance benchmark query step - result-longmemeval.md: update evaluation results - judge_all_plus_results.json: add judge all-plus results * refactor: split longmemeval.yaml into lme.yaml/beam.yaml and unify job names - Split reme/config/longmemeval.yaml into lme.yaml (LongMemEval) and beam.yaml (BEAM) - Unify job names across both configs: agentic_answer, answer_judge, context_answer - Update evaluation/longmemeval/run.py and evaluation/beam/run_beam_eval.py to use unified job names - Update all evaluation config YAMLs to reference lme.yaml - Add BEAM benchmark step implementations (agentic_answer, context_answer, llm_judge) - Remove obsolete config_test5.yaml and test_5sessions.py * eval: BEAM 100K & LongMemEval cleaned-S 评测结果记录 - BEAM 100K eval-only (32并发, 20 case): Agentic 0.631, Prompted 0.468 - LongMemEval final GT (500题): Agentic 89.0%, Prompted 83.6% - 新增 benchmark/result-beam.md, benchmark/result-longmemeval.md - benchmark/beam/config.yaml: num_workers=32 * refactor: restructure benchmark directory and clean up gitignore rules - Consolidate benchmark outputs to benchmark/results/ with .gitkeep - Remove old benchmark scripts, configs and result files from benchmark/beam/ and benchmark/longmemeval/ - Add datasets/README.md and datasets/README_EN.md with download instructions - Add datasets/longmemeval/download.py and final_groundtruth_cleaned_s.json - Add memory_workspaces .gitkeep placeholders - Restructure .gitignore: fix duplicate entries, add BEAM dataset exclusion, refine logs/results ignore patterns - Remove stale result-beam.md and result-longmemeval.md from project root * chore: clean up longmemeval benchmark scripts and update dataset docs - Remove obsolete longmemeval benchmark runner/stats scripts - Update datasets/longmemeval README and add Chinese translation - Clean up final_groundtruth_cleaned_s.json * docs(benchmark): add reproduction guide for LongMemEval and BEAM - Add bilingual README for benchmark runners (EN/ZH) - Cover prerequisites, dataset download, run commands, configs, outputs, logs, and kill.sh * refactor: migrate auto_memory steps from evolve to benchmark-specific modules - Split auto_memory into beam and lme benchmark-specific implementations - Add auto_memory.py and auto_memory.yaml under steps/benchmark/beam and steps/benchmark/lme - Slim down evolve/auto_memory.py and auto_memory.yaml to shared base only - Remove obsolete evolve/_auto_memory.yaml - Update benchmark run.py, config YAMLs, and step __init__.py registrations - Update llm_judge and context_answer minor adjustments - Remove outdated test_lme_final_answer_review.py * revert(as_agent_wrapper): sync with upstream/main Remove local-only comment to keep file identical with upstream/main. * style: add trailing commas in benchmark __init__.py __all__ lists * chore: disable vector_weight range assertion in SearchStep * chore: add tests/integration/logs/ to .gitignore * refactor: replace scipy.stats.kendalltau with pure numpy implementation scipy is not listed in project dependencies. Implement Kendall's tau-b rank correlation using only numpy to remove the undeclared dependency. * feat(benchmark): add binary score metrics, update BEAM 1M results, and improve LLM retry/prompt config - benchmark/beam/run.py: add binary score calculation per rubric item and per-type/overall binary stats - benchmark/beam/config.yaml: switch to 1M dataset, reduce workers to 18 - benchmark/result-beam.md: add 1M evaluation results with binary scores - benchmark/result-longmemeval.md: minor formatting - reme/config/beam.yaml: increase max_retries to 5 and add retry_delay 5.0 for all LLM components - reme/config/lme.yaml: increase max_retries to 5 and add retry_delay for judge/prompted/bench components - reme/steps/benchmark/lme/agentic_answer.yaml: improve search strategy and answer rules prompts * fix(benchmark): fix line-too-long and add pylint disable for main() * refactor(longmemeval): use single cleaned-S dataset with embedded ground truth - Switch to agentscope-ai/ReMe_longmemeval_clean_s_v2 HuggingFace source - Remove separate final_groundtruth_cleaned_s.json (ground truth now in data file) - Simplify download.py to fetch only longmemeval_s_reme_cleaned.json - Remove dataset.variant and dataset.ground_truth_path config options - Update benchmark and datasets READMEs to reflect new workflow - Update .gitignore for new dataset filename * fix: rename loop variable to avoid pylint redefined-outer-name warning * refactor(benchmark): restructure datasets/memory_workspaces into benchmark and simplify auto_memory steps * refactor(benchmark): extract BaseAgenticAnswerStep into base module - Add reme/steps/benchmark/base/agentic_answer.py with shared agentic answer logic - Refactor beam/lme AgenticAnswerStep to inherit from BaseAgenticAnswerStep - Simplify lme/context_answer.py and update context_answer.yaml - Update result-longmemeval.md with latest evaluation results (agentic 91.0%) * refactor(benchmark): remove context_answer steps and unused configs - Remove beam/lme context_answer job definitions and step implementations - Remove prompted LLM component from beam.yaml and lme.yaml - Delete jinli_lme.yaml (no longer needed) - Simplify benchmark run.py scripts - Clean up .gitkeep files and update .gitignore - Remove unused import in search.py * chore: remove benchmark/results/.gitkeep --------- Co-authored-by: sa-buc <jiangniurou.xyf@dail-algo011164204033.ET135> Co-authored-by: jinliyl <6469360+jinliyl@users.noreply.github.com> Co-authored-by: imrewce <wce@pku.edu.cn> Co-authored-by: Sen Huang <48879559+ployts@users.noreply.github.com> Co-authored-by: Claude Fable 5 <noreply@anthropic.com>	2026-07-21 19:09:50 +08:00
jinliyl	b4333fbef8	feat(index): add bounded memory-aware batch processing (#381) ... * test(background_steps): add comprehensive tests for batch processing and memory management - Add test for catalog upserts in batches of at most 100 files - Add test for catalog deletes in batches of at most 100 paths - Add test for index memory budget reducing batches to one file - Add test for memory target limiting cumulative batch size - Add test for invalid batch memory settings rejection - Add test for continuing after one batch fails - Add test for yielding to event loop while building batch - Add test for modified file reusing unchanged embedding - Add test for reporting memory estimation failure without aborting feat(update_changes): implement bounded batch processing with memory management - Add configurable batch parameters with default values - Implement memory budget calculation based on available system memory - Add file inspection and memory estimation before processing - Implement batch flushing when limits are reached - Add proper error handling for batch operations - Support async yielding during batch building - Add comprehensive validation for batch configuration parameters - Implement memory estimation for indexing operations - Add batch size limiting for delete operations * test(steps): add tests for memory estimation failure handling - Add test case for isolated file processing when memory estimation fails - Add test case for proper release of flushed items before building next file - Implement weak reference tracking to verify payload lifetime management - Create parametrized tests for both source and item memory estimation methods - Add assertions to verify single-item batch behavior on estimation failures - Include comprehensive error handling verification for memory budget calculations * chore(version): bump version to 0.4.1.3 - Update __version__ from 0.4.1.2 to 0.4.1.3 in __init__.py * feat(index): support batch settings from environment * refactor(index): use direct batch defaults * refactor(index): configure memory estimates through step args * ci: simplify Windows smoke dependencies	2026-07-20 17:25:00 +08:00
jinliyl	c3b1e93918	feat(index): add file size limits and oversized file handling (#362) ... * feat(index): add file size limits and oversized file handling - Implement max_file_bytes configuration option for content processing jobs - Add default 20MB file size limit for background processing in default config - Skip oversized files during auto_resource step with appropriate metadata - Clear stale index entries when oversized files are modified - Add size-based filtering logic to update_changes step with skip reporting - Include file size validation in UpdateIndexStep with proper response handling - Add comprehensive tests for oversized file scenarios in auto_resource and update_index - Document file size limits in constants with appropriate thresholds * chore(version): bump version to 0.4.1.1 - Update __version__ from 0.4.1.0 to 0.4.1.1 in __init__.py * fix(index): isolate batch metadata and handle file races	2026-07-15 21:01:18 +08:00
jinliyl	bf7ca17705	feat(benchmark): add LongMemEval golden answer validation (#335) ... * feat(benchmark): add golden answer validation and session review for LongMemEval - Introduce GoldenCheckStep to validate LongMemEval golden answers using structured verdicts - Add SessionReviewStep to extract query/answer-relevant evidence from all sessions - Implement concurrent session processing with configurable concurrency limits - Create check_golden job configuration with lme_review and lme_judge agent wrappers - Add Qwen3.7-plus model configuration for enhanced processing capabilities - Include python_execute tool integration for agent-based reasoning and date validation - Generate comprehensive JSON output with session summaries and validation verdicts - Add run_check_golden.py script for batch processing across all LongMemEval samples - Configure proper logging initialization with console and file output options - Update component registry and file I/O modules to support new benchmark features * feat(scripts): add script to summarize LongMemEval check_golden verdicts - Parse check_golden.json files across all LongMemEval samples - Calculate accuracy metrics for golden answers and session IDs - Provide breakdown by question type with percentage calculations - Add command line options for listing bad samples and JSON output - Include progress tracking showing completed vs pending samples - Display confidence scores and date sanity checks statistics * refactor(benchmark): move golden check scripts to longmemeval directory - Moved run_check_golden.py from scripts/ to benchmark/longmemeval/ - Moved stats_check_golden.py from scripts/ to benchmark/longmemeval/ - Updated path resolution to use parents[2] instead of parent.parent - Added new --list-run-failed option to stats script - Added logging directory constant and functions for tracking launched samples - Enhanced stats output with launched count and run failure information - Improved error reporting with run failure details and log file paths * feat(benchmark): add LongMemEval agentic answer workflow with session extraction - Add LmeAgenticAnswerStep, LmeAutoMemoryStep, and LmeExtractSessionStep to __init__.py - Create shared helper render_with_source for displaying search results with session_id - Implement agentic_answer step with vector_search, bm25_search, and extract_session_by_id tools - Add auto_memory step to convert each session into search-friendly daily notes - Create extract_session step to retrieve and analyze raw session content by session_id - Update jinli_lme.yaml with auto_memory, vector_search, bm25_search, and agentic_answer jobs - Configure lme_memory, lme_extract, and lme_agentic_answer agent wrappers - Enhance search steps with include_source option to show session_id metadata - Add proper session_id tracking and collision handling in daily note generation * feat(benchmark): add LongMemEval agentic answer evaluation pipeline - Add session_id tracking to agentic_answer.py result metadata - Introduce run_agentic_answer.py driver for complete pipeline execution - Implement auto_memory, update_index, and agentic_answer job orchestration - Add concurrent execution with configurable limits and staggering - Create aggregation script for collecting tool-call trails and results - Add stats_agentic_answer.py for comprehensive result analysis - Implement resume capability with existing output detection - Generate aggregate.json with per-sample breakdown and tool call summaries * feat(steps): add ClearPathsStep for cleaning workspace outputs before rebuild - Introduce ClearPathsStep to remove stale workspace files/directories - Add support for specifying paths and config_keys as targets to clear - Implement safety checks to prevent deletion of files outside workspace - Add logging for cleared paths and warnings for invalid paths - Configure clear_paths_step in jinli_lme.yaml to clean daily_dir - Add clear_paths_step to clean mem_answer.json before rebuilds * feat(benchmark): add resume functionality to agentic answer runner - Replace --force flag with --resume flag for controlling job execution - By default every job reruns with clean rebuild behavior using config clear steps - Add --resume option to skip samples whose output already exists and continue interrupted batches - Update documentation to reflect new default clean rebuild behavior - Modify job skipping logic to honor resume flag instead of force flag - Update dry-run output to show correct todo jobs based on resume status - Change default example command to use --resume for continuing interrupted runs * feat(benchmark): generate JSONL output for check golden records - Add write_check_golden_list function to create JSONL file - Write all readable check_golden records as JSONL format - Include check_golden_list path in stats output - Display generated JSONL file path in summary report - Maintain UTF-8 encoding with non-ASCII character support * refactor(benchmark): rename answer judge step and integrate LME LLM judge - Rename AnswerJudgeStep to LmeLlmJudgeStep and update imports - Add new llm_judge configuration in jinli_lme.yaml - Update run_agentic_answer.py to include llm_judge in pipeline - Modify LmeLlmJudgeStep to read from query.json and answer.json - Write LLM judgement results back to mem_answer.json - Add command line options for start/end sample range selection - Update aggregate.json generation to include LLM judgement data - Add resume capability for llm_judge job based on judgement presence * refactor(benchmark): rename answer judge step and integrate LME LLM judge - Rename AnswerJudgeStep to LmeLlmJudgeStep and update imports - Add new llm_judge configuration in jinli_lme.yaml - Update run_agentic_answer.py to include llm_judge in pipeline - Modify LmeLlmJudgeStep to read from query.json and answer.json - Write LLM judgement results back to mem_answer.json - Add command line options for start/end sample range selection - Update aggregate.json generation to include LLM judgement data - Add resume capability for llm_judge job based on judgement presence * feat(steps): add wait_for_paths_step to block until workspace files exist - Introduce WaitForPathsStep class that polls for required workspace-relative paths - Add step registration with 'wait_for_paths_step' backend identifier - Implement path validation to ensure targets are within workspace boundaries - Add polling mechanism with configurable intervals via poll_seconds parameter - Include logging functionality with log_every_seconds parameter for status updates - Add metadata tracking of waited paths and duration in response object - Register step in index module and expose in public API - Configure step in jinli_lme.yaml to wait for session_review.json before golden check - Add script rename from run_check_golden.py to run_golden_check.py with enhanced options * feat(benchmark): enhance longmemeval benchmarking with concurrency and progress tracking - Add benchmark extra dependency group with portalocker requirement - Introduce concurrent execution support for golden_check and session_review workflows - Add progress reporting interval option with real-time status updates - Implement global throttling mechanism for session review requests using file locks - Enhance golden check validation with current schema verification - Add active task tracking and graceful shutdown handling - Rename check_golden scripts to golden_check for consistency - Update statistics reporting with correct/incorrect terminology instead of reasonable - Add stale format detection and compatibility handling for verdict fields - Include both_correct rate calculation in accuracy metrics - Add concurrency and staggering options for better resource management * ci(workflow): add Windows smoke test workflow - Create new workflow file .github/workflows/windows-smoke.yml - Configure workflow to trigger on push and pull request events - Set up Python environment with version 3.11 - Install package dependencies using pip - Run version job as smoke test for CLI functionality - Enable concurrency control to prevent duplicate runs - Use matrix strategy for Python version testing * feat(benchmark): add retry mechanism and health check for session review - Added retry configuration options (retry_initial_seconds, retry_max_seconds, retry_max_attempts) to jinli_lme.yaml - Implemented exponential backoff retry logic with configurable parameters in session_review step - Added output_is_healthy function to verify session_review.json integrity and absence of failed reviews - Updated resume functionality to skip only healthy outputs instead of all existing files - Integrated JSON parsing and validation to check for failed reviews in output files - Enhanced error handling and logging for retry attempts and recovery scenarios * feat(benchmark): add LongMemEval session review statistics script - Create stats_session_review.py to summarize session_review.json artifacts - Add command line options for listing failed, missing, and run failed samples - Implement JSON output mode for programmatic consumption - Calculate and display health statistics including total samples, healthy outputs, failed sessions - Provide detailed failure information with session IDs and error messages - Generate re-run commands for samples with failed reviews - Add percentage calculations for better statistical overview - Include support for multiple output formats and detailed logging * feat(benchmark): add LongMemEval output cleanup script and enhance golden check retry logic - Added clean_sample_outputs.py script to remove generated LongMemEval files while preserving source inputs - Implemented configurable retry mechanism in golden_check.py with exponential backoff strategy - Added retry parameters (initial/max seconds and max attempts) to control failure recovery behavior - Integrated asyncio support for asynchronous sleep during retry intervals - Configured default retry settings in jinli_lme.yaml with 5s initial and 300s maximum intervals - Preserved core files (query.json, answer.json, session/) while cleaning generated artifacts * feat(benchmark): add AppleDouble file cleanup to sample output cleaner - Remove AppleDouble files starting with '._' recursively including under session/ - Add is_under helper function to check if path is inside parent directory - Track targets in set to avoid duplicate processing - Include AppleDouble files in cleanup targets when not already covered by existing targets - Maintain dry-run mode as default behavior with --apply flag for actual deletion * refactor(benchmark): update LongMemEval sample output cleaning script - Add time and Iterator imports for enhanced functionality - Add --progress-every argument to control progress reporting frequency - Replace is_under function with iter_sample_targets generator - Implement detailed progress tracking with timing measurements - Add sample-by-sample processing with elapsed time reporting - Include AppleDouble file detection within session directory - Update target counting and deletion statistics display - Add conditional progress updates based on progress-every setting - Improve dry-run mode with would-delete indication * chore(benchmark): increase initial interval for session review step - Changed START_INTERVAL_SECONDS from 1.0 to 3.0 seconds - Adjusted timing parameters for better benchmark stability * refactor(benchmark): implement coordinated retry mechanism for session reviews - Add retry gate condition to coordinate concurrent review attempts - Implement wait_for_healthy_start_slot to handle sequential retries - Create mark_retrying and mark_recovered functions to track retry states - Update reply_with_retry to accept index parameter for coordination - Add has_prior_retry logic to prevent race conditions during recovery - Ensure proper cleanup of retry state on success or failure - Maintain backward compatibility while adding coordination features * chore(benchmark): adjust session review start interval timeout - Changed START_INTERVAL_SECONDS from 3.0 to 5.0 seconds - Increased initial delay for session review benchmark step - Updated timeout configuration for improved stability * refactor(benchmark): update session review concurrency and throttling mechanism - Replace global throttle with per-process concurrency control - Add concurrency parameter with default value of 30 in config - Add start_interval_seconds parameter with default value of 2 seconds - Change default concurrency from 3 to 1 in command line interface - Update documentation to reflect new throttling behavior - Implement semaphore-based concurrency limiting for review tasks - Modify retry mechanism to use local locking instead of global files - Remove portalocker dependency for cross-process throttling * refactor(config): update session review configuration and concurrency settings - Removed deprecated retry configuration parameters from jinli_lme.yaml - Increased MAX_CONCURRENCY from 30 to 60 in session_review.py - Reduced START_INTERVAL_SECONDS from 2.0 to 1.0 in session_review.py - Cleaned up redundant backend specifications in configuration file - Simplified agent wrapper configurations by removing obsolete retry settings * feat(benchmark): enhance LME auto memory step with advanced scheduling and error handling - Add datetime parsing functionality for LongMemEval timestamps with regex pattern - Implement configurable concurrency limits with MAX_CONCURRENCY of 60 - Introduce retry mechanism with exponential backoff for agent interactions - Add session filtering based on date comparison with question_date validation - Create rate limiting with start interval control between requests - Implement sophisticated retry coordination using asyncio conditions - Add comprehensive error tracking for failed and filtered session extracts - Remove deprecated concurrency parameter from jinli_lme.yaml configuration - Add structured output validation in session review step - Include detailed metadata reporting with session statistics and errors * fix(benchmark): adjust default concurrency for auto_memory job - Changed default concurrency from 3 to 1 for auto_memory job to prevent API overload - Updated help text to reflect new default value of 1 for concurrency parameter - Modified documentation to clarify concurrency behavior varies by job type * refactor(search): replace hardcoded candidate multiplier with constant - Introduced _CANDIDATE_MULTIPLIER constant set to 10 - Replaced hardcoded factor of 5 with _CANDIDATE_MULTIPLIER in BM25 search - Replaced hardcoded factor of 5 with _CANDIDATE_MULTIPLIER in vector search - Updated test to verify both search steps use ten times limit for candidates - Imported VectorSearchStep and Bm25SearchStep in test module - Added comprehensive test case for candidate count calculation logic * feat(lme): add data inspection error handling with fallback mechanism - Implemented non-retryable data inspection error markers detection - Added _is_data_inspection_error method to identify inspection failures - Created fallback handling for data inspection errors in auto memory extraction - Added fallback handling for data inspection errors in session review - Extended failed extracts tracking with non-retryable and fallback flags - Separated fallback extracts from regular failed extracts in reporting - Enhanced error logging with specific data inspection failure messages - Updated metrics to track fallback extractions and reviews separately - Maintained existing retry logic for other exception types * feat(benchmark): enhance session review statistics with fallback tracking - Add support for identifying and listing non-retryable fallback reviews - Introduce --list-fallback argument to display fallback review details - Separate retryable failures from non-retryable fallbacks in reporting - Track fallback samples and sessions separately from failed ones - Update console output to show both retryable and non-retryable categories - Include fallback details in JSON output with reasons and session info - Modify failure counting logic to distinguish between retryable and fallback reviews * feat(benchmark): add question_id tracking and enhanced fallback reporting - Add question_id function to extract query.question_id from data - Initialize question_id_by_id dictionary to store question IDs by index - Store question_id for each sample during data processing - Enhance fallback output to include question IDs and session information - Format sample labels with question IDs when available - Display session IDs associated with each fallback case * feat(benchmark): add question_id support and improve bad sample reporting - Add question_id_for function to extract question_id from multiple sources - Add sample_label function to format samples as idx(question_id) when available - Store question_id in data dictionary during processing - Change bad_golden and bad_sessions to store full records instead of just indices - Update list_bad output to show formatted labels with question_id information - Improve error reporting with more detailed sample identification * feat(benchmark): enhance golden check stats with structured output - Add related_session_ids function to extract session IDs from verdict records - Create grouped_records function to group records by question type - Replace flat list output with JSON-formatted grouped records in list_bad option - Replace flat list output with JSON-formatted grouped records in list_bad_sessions option - Maintain Chinese labels while adding structured data presentation - Improve readability of bad verdict record display with hierarchical grouping * feat(benchmark): update data structure for question indexing - Replace sample_label with _idx field for index tracking - Add question_id field to store _question_id values - Maintain backward compatibility with empty string defaults - Preserve existing session_id functionality - Update data mapping to include new fields in grouped results * refactor(benchmark): streamline golden answer verification process - Replace relevance filtering with comprehensive information extraction - Remove is_relevant field and simplify session summary structure - Change relevant_info to extracted_info for clarity - Update golden check logic to work with full extractions instead of filtered summaries - Simplify prompt instructions to focus on complete information extraction - Remove redundant schema validation and structured output requirements - Adjust statistics calculation to match new extraction approach - Update metadata field names to reflect extraction rather than relevance checking * feat(benchmark): add selective file deletion option to clean_sample_outputs - Add --filename argument to delete only specific root-level files - Modify iter_sample_targets function to accept optional filenames filter - Implement validation for root-level filename constraints - Update function calls to pass filenames parameter - Add example usage for selective file deletion in documentation * feat(benchmark): add error count metrics to golden check statistics - Added golden_bad, session_bad, and both_bad calculation fields - Updated console output format to include error counts per question type - Modified table display to show both accuracy rates and error numbers - Enhanced statistical summary with additional error breakdown metrics * test(search): update search step tests with include_source parameter - Added include_source=False parameter to VectorSearchStep initialization - Added include_source=False parameter to Bm25SearchStep initialization - Maintained existing RuntimeContext parameters for both search steps - Updated test calls to match new constructor signature with include_source option	2026-07-13 21:26:27 +08:00
Ziyang Guo	e41b1673ad	fix(search): honor min_score in plain search steps (#338)	2026-07-13 16:32:16 +08:00
jinliyl	2612d25959	feat(lme): add cli execution and agentic search tooling (#334) ... * feat(service): add CLI service for local job execution - Introduce CliService to execute single jobs locally without serving ports - Add prepare_start_config and should_precheck_start functions for CLI job setup - Update reme start command to use CLI service when job argument is provided - Change default service backend from http to cli in jinli_lme config - Modify SearchStep to use constants and rename configuration parameters - Add unit tests for CLI service functionality and configuration handling - Update file extension support to include json format in addition to md and jsonl * feat(search): add BM25 and vector search steps with configuration updates - Add Bm25SearchStep and VectorSearchStep classes with tool context deduplication - Register new search step components in index module - Update configuration to use separate vector_search and bm25_search endpoints - Modify LLM models from qwen3.7-plus/glm-5.1 to glm-5.2 variants - Adjust search parameters and remove hybrid search implementation - Configure embedding store as default in storage settings - Remove auto-memory and file catalog configurations - Update watch directories from multiple paths to session_dir only * feat(agent): add tool result offloading and workspace management - Add tool_results_dir configuration option for offloaded tool results storage - Implement ToolResultOffloadMiddleware to persist large tool results to files - Create WorkspaceBackend to standardize file operations across tools - Add configurable builtin tools selection with sequential execution option - Integrate middleware support for agent wrapper with offloading capability - Update application initialization to create tool results directory - Add safety mechanisms for filesystem operations with sanitized filenames - Enhance agent wrapper with configurable working directory handling - Upgrade agentscope dependency to version 2.0.4 for improved features # Conflicts: # reme/application.py * feat(benchmark): add LongMemEval agentic search and result management - Introduce AgenticAnswerStep for agent-based history search - Add LmePrepareJudgeStep and LmeSaveResultStep for evaluation pipeline - Implement AddDraftStep and ReadAllDraftStep for evidence accumulation - Update configuration with new agent wrapper and search parameters - Add comparison script for analyzing agent run differences - Include documentation for LongMemEval failure analysis - Enhance tool result offloading with skip options - Modify search defaults and indexing behavior * feat(agent): implement tool result offloading with system reminders - Added tool_result_offload_message parameter to agent wrapper reply method - Implemented configurable reminder template for offloaded tool results - Created system reminder messages when tool results are offloaded to files - Added Chinese user message template for agentic answer step - Updated tool result offloading middleware to use custom reminder templates - Enhanced agentic answer instructions to handle long tool results via draft storage * feat(scripts): add LongMemEval results summarization tool - Create summarize_lme_results.py script to analyze result JSON files - Implement command line interface with answer id and dataset root options - Add support for specifying index range with start and end parameters - Include option to show failure details and non-successful completions - Calculate completion statistics and accuracy metrics - Display detailed breakdown of yes/no/other judgements - Handle missing and unreadable result files gracefully - Format output with percentages and comprehensive summary statistics * feat(summarize_lme_results): add question type breakdown to result summary - Import defaultdict from collections module - Add by_type dictionary to track statistics by question type - Count completed, yes, no, and other responses for each question type - Display detailed breakdown table showing accuracy by question type - Include question type column when processing judgements - Print comprehensive summary with question type distribution - Calculate and display accuracy percentage for each question type category * feat(lme): switch to qwen3.7-max model and add shuffle functionality - Changed default LLM model from glm-5.1 to qwen3.7-max in jinli_lme.yaml - Added random module import for shuffle functionality - Implemented --shuffle argument with BooleanOptionalAction for dataset shuffling - Added --seed argument to control random seed for reproducible shuffling - Applied random shuffle to dataset indices when shuffle is enabled - Added console output showing shuffle operation and seed information * fix(cli): set default random seed for shuffle functionality - Changed default seed value from None to 42 for consistent shuffling behavior - Ensures reproducible results when using shuffle option without explicit seed - Maintains backward compatibility while providing deterministic defaults * refactor(benchmark): update agentic answer guidelines for grounding - Updated English instruction to emphasize strict grounding in retrieved context - Modified Chinese instruction to stress evidence-based responses without inference - Removed redundant conciseness requirement in both language versions - Enhanced clarity on proper use of draft saving and retrieval mechanisms - Strengthened emphasis against hallucination of unsupported facts * refactor(benchmark): update agentic search instructions and configuration - Replace separate vector_search and bm25_search with unified search tool - Update agent instructions to use single search tool with multiple strategies - Simplify Chinese instructions for search methodology - Add comprehensive search tool configuration with hybrid vector/BM25 capabilities - Increase model retry attempts from 1 to 3 for better reliability - Remove redundant tool references from job_tools list * feat(search): add configurable search limit with environment variable support - Remove hardcoded limit and min_score parameters from config schema - Increase LLM context size from 200000 to 1000000 - Add REME_SEARCH_LIMIT environment variable support for search configuration - Implement command line argument --search-limit to override default search limit - Add input validation to ensure search limit is positive - Modify subprocess execution to pass environment variables - Update search step to use dynamic default limit from environment or fallback to 5 * refactor(benchmark): remove agentic answer step and related configurations - Removed AgenticAnswerStep class and its registration - Deleted agentic_answer.yaml prompt configuration file - Removed agentic answer related job definitions from jinli_lme.yaml - Cleaned up tool result offloading middleware implementation - Removed tool_results_dir configuration field from application config - Deleted comparison and analysis scripts for agent runs - Removed agentic answer step from LME init module exports - Updated agent wrapper to remove tool result offloading functionality - Removed unused imports and dependencies in agent wrapper module * refactor(benchmark): remove unused LME result processing components - Removed LmePrepareJudgeStep and LmeSaveResultStep classes from benchmark module - Cleaned up imports and exports in lme module initialization - Removed unused middleware configuration from agent wrapper - Deleted obsolete result.py file containing deprecated result processing logic - Simplified agent instantiation by removing middleware parameter - Updated import statements to reflect removed dependencies * refactor(index): remove unused search steps and update imports - Remove Bm25SearchStep and VectorSearchStep from index steps module - Remove unused prepare_start_config and should_precheck_start exports - Move import statements to proper location in reme.py - Update test module to use direct import path for CliService - Remove vector_search and bm25_search configurations from jinli_lme.yaml - Add workspace directory environment variable configuration - Add docstring to getcwd method in agent wrapper - Remove empty middleware list from agent wrapper initialization * feat(index): add BM25 and vector search steps with tool context deduplication - Add Bm25SearchStep for plain BM25 keyword search with tool_context deduplication - Add VectorSearchStep for plain vector search with tool_context deduplication - Implement tool context state management with TTL-based deduplication - Add support for chunk deduplication across tool contexts within TTL window - Update index steps module to include new search step classes - Add test coverage for CLI metadata output functionality - Refactor CLI service to remove unused show_status parameter - Update documentation comments to reflect internal service configuration * feat(steps): add Python code execution capability - Introduce PythonExecuteStep to run Python code in subprocess - Add configuration for python_execute step in jinli_lme.yaml - Register python_execute in available tools list - Implement timeout handling with default 60 second limit - Capture stdout/stderr output and return code metadata - Add comprehensive unit tests for execution scenarios - Support workspace directory context for code execution - Handle timeout errors and runtime exceptions gracefully * refactor(python_execute): replace subprocess with asyncio for Python code execution - Replace subprocess.run with asyncio.create_subprocess_exec for non-blocking execution - Add _PythonResult dataclass to encapsulate execution results and timeout status - Implement proper timeout handling with asyncio.wait_for and process.kill() - Update metadata to include returncode and stderr when timeout occurs - Convert synchronous _run_python method to asynchronous implementation - Maintain backward compatibility while improving execution reliability * refactor(python_execute): replace subprocess with asyncio for Python code execution - Replace subprocess.run with asyncio.create_subprocess_exec for non-blocking execution - Add _PythonResult dataclass to encapsulate execution results and timeout status - Implement proper timeout handling with asyncio.wait_for and process.kill() - Update metadata to include returncode and stderr when timeout occurs - Convert synchronous _run_python method to asynchronous implementation - Maintain backward compatibility while improving execution reliability	2026-07-08 17:43:09 +09:00
jinliyl	10da205797	feat(benchmark): add lme benchmark steps (#326) ... * refactor(search): replace time module with datetime for timestamp generation - Removed unused time import - Added static method _now_ts using datetime.timestamp - Updated clock parameter to use _now_ts method instead of time.time - Maintained same timestamp precision and functionality * test(http): add tests for HTTP client display formatting - Add test for default metadata hiding behavior in CLI output - Add test for metadata display when show_metadata is enabled - Verify _format_for_display method correctly formats response text - Test both success case and metadata inclusion scenarios * chore(build): remove longmemeval from gitignore - Removed longmemeval directory from gitignore list - Kept evaluation and datasets directories in ignore list - Updated gitignore configuration for proper version control	2026-07-07 18:53:39 +09:00
jinliyl	7369342115	feat(search): add tool context deduplication and improve search configuration (#321) ... * feat(search): add tool context deduplication and improve search configuration - Modify _make_tool methods to accept and inject tool_context_id parameter - Add tool_context_id handling in AS and CC agent wrappers - Increase search candidate multiplier from 3.0 to 5.0 in default config - Extend HTTP client timeout from 30s to 3600s - Add tool context deduplication logic to prevent duplicate search results - Implement TTL-based expiration for seen chunks in tool contexts - Add comprehensive unit tests for tool context deduplication behavior - Update .gitignore to exclude longmemeval directory - Add time import for timestamp functionality in search step * refactor(search): replace time module with datetime for timestamp generation - Removed unused time import - Added static method _now_ts using datetime.timestamp - Updated clock parameter to use _now_ts method instead of time.time - Maintained same timestamp precision and functionality	2026-07-06 16:18:39 +09:00
xyf2020	43a407bc4f	feat: add start_date/end_date time filter support for search job (#317) ... * feat: add start_date/end_date time filter support for search job - Add _extract_date_from_path to extract validated YYYY-MM-DD from chunk paths - Add start_date/end_date filtering in _matches_search_filter - Implement progressive recall in FaissLocalFileStore.vector_search - Promote start_date/end_date from context to search_filter in SearchStep - Add start_date/end_date parameters to search job in default.yaml - Add unit tests for date filter functionality * fix: validate/normalize date filters and harden _extract_date_from_path Address three code-review comments on the time_filter search feature: 1. Validate/normalize start_date and end_date before string comparison. _matches_search_filter does lexicographic comparison against path_date (always canonical YYYY-MM-DD). Raw caller values like '2026-2-28' or 'abc' would produce silently wrong results. Now SearchStep normalizes valid dates via extract_daily_date (with strptime fallback for non-zero-padded input) and silently ignores invalid dates with a logger.warning, removing them from the filter. 2. Clarify behavior for paths without embedded dates. Added optional strict_date_filter parameter (default False). When True and at least one date bound is active, chunks whose path yields no date (e.g. digest/personal/topic.md) are excluded. When False (default), the existing behavior is preserved — dateless paths pass through. 3. Harden _extract_date_from_path against non-standard suffixes. Previously parts[1].split('.')[0] accepted '2026-05-18.anything' as a valid date. Now only exact 'YYYY-MM-DD' (dir) and 'YYYY-MM-DD.md' (day-index) forms are accepted.	2026-07-03 15:58:04 +08:00
Sen Huang	e31db5fe19	docs: rename vault_dir to workspace_dir in documentation and examples (#286) ... * docs: rename vault_dir to workspace_dir in documentation and examples * refactor(extract): format long method call across multiple lines * refactor(extract): format system prompt parameters for better readability	2026-06-22 16:58:57 +08:00
jinliyl	206a53e5ed	init: reme version 0.4.0 (#284)	2026-06-22 15:41:19 +08:00