16 commits

Author	SHA1	Message	Date
jinliyl	a4f606c6a8	fix(dsh): recover memory backlogs and protect endpoint credentials (#653) ... * fix(dsh): recover memory backlogs and protect endpoint credentials * fix(dsh): address outbox and idempotency review findings	2026-10-21 18:58:29 +08:00
celanwang	681cc85fb5	fix(auto-memory): serialize session transcript writes per session (#633) ... * fix(auto-memory): serialize session transcript writes per session _save_session_messages ran its read-merge-write on the per-session JSONL transcript without any lock. Concurrent HTTP requests saving the same session could interleave: two writers both appending against a stale snapshot write overlapping history twice, and an append racing a full rewrite can be overwritten by the rewriter's stale merge, losing messages. Hold get_path_lock(path) across the whole read, merge, and write, consistent with the existing session image handling in the same file. Merge, ordering, and can_append logic are unchanged. Add deterministic regression tests that gate one writer's read between snapshot capture and write: concurrent appends must merge disjoint messages in created_at order, and an appended message must survive a concurrent full rewrite. Both tests fail without the lock. Closes #622 * test(auto-memory): make session-lock regression tests deterministic Replace fixed sleeps with explicit synchronization: a shared operation log records lock/read/write progress per writer, and writer A holds its post-read pause until writer B is queued on the transcript lock. The tests now assert the serialization order from the log (B reads only after A's write completed) in addition to transcript content, so they no longer depend on IO timing. Also fix pylint findings from CI: use from-import for the auto_memory module and drop unused tmp_path parameters.	2026-10-19 16:13:42 +08:00
WQS	c1de31ab2c	feat(auto-memory): save session images with source links (#574) ... * feat(auto-memory): save session images with contextual source links * fix(auto-memory): validate image provenance before persistence * refactor(auto-memory): keep image attachment helpers in the memory step * fix(auto-memory): preserve main session persistence order * refactor(auto-memory): simplify image reuse and source frontmatter	2026-10-09 17:42:13 +08:00
WQS	6125fc197d	feat(auto-memory): add session image support (#532) ... * feat(auto-memory): add opt-in image input * feat(auto-memory): caption session images into source-linked notes * fix(auto-memory): version Pillow 10 compatible image preparation * fix(auto-memory): harden image evidence and retry boundaries * fix(auto-memory): preserve image evidence across replay and concurrent writes Keep persisted image positions through disabled history backfills and transcript filtering. Merge note links atomically, map 16-bit grayscale without clipping, recheck restored caption owners, and reuse unchanged identity metadata during batch publication. Add regressions and document conservative custom-rename behavior. * refactor(auto-memory): restore main baseline for image modes v2 * refactor(images): share resource caption preprocessing and model calls * feat(watch): support scoped exclusions for managed session images * feat(auto-memory): add opt-in resource and caption-only image input * refactor(auto-memory): keep caption-only mode with text fallback * refactor(auto-memory): make caption-only mode dispatch explicit * docs(auto-memory): focus image guide on caption-only mode * feat(auto-memory): add direct multimodal image extraction * refactor(auto-memory): route direct images through the vision model * test(auto-memory): consolidate overlapping image regressions * feat(auto-memory): interleave direct images with conversation text * docs(auto-memory): clarify history rendering scope for direct inputs * feat(auto-memory): require vision declaration for direct-only images * refactor(auto-memory): keep bound model and native image helpers * refactor(auto-memory): keep image inputs native and opt-in * refactor(auto-memory): simplify image docs and tests * refactor(auto-memory): confine image adaptation to image requests * refactor(auto-memory): remove image switch type validation	2026-09-20 15:35:00 +08:00
xyf2020	06fb46fa48	feat(tags): add configurable tag indexing and filtered hybrid search (#530) ... * 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 * Add configurable tag indexing and tag listing * Add tag-filtered hybrid search with exact candidate ranking * Remove obsolete generated files * Rename tag index key to tag_key and reject reserved fields * Extract automatic tagging into a dedicated step * Restrict frontmatter updates to authorized keys * Refine tag filtering and automatic memory tagging * Require underscore-separated tags in auto-tag prompts - Forbid spaces in tags and require underscores (e.g. sam_altman) in both English and Chinese auto_tag prompts, with English examples switched to English entities (OpenAI, gold) - Drop prompt-string assertions superseded by the new tagging rule - Merge construction/runtime tag_key validation tests into one parametrized case * Make max_tags_per_file configurable in auto-tag step * Consolidate tag index tests * Fix search test fixture lint warnings * Align tag contracts and index health behavior * Fall back when tag index is unavailable --------- Co-authored-by: jinli.yl <jinli.yl@alibaba-inc.com>	2026-09-10 18:01:09 +08:00
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
jinliyl	f5ec230fef	feat: add DSH memory integration and organize extensions (#461) ... * feat: add DSH memory integration and organize extensions * fix: support newer DSH release candidates * fix: address DSH integration review feedback * fix: handle DSH cross-day retry edge cases	2026-08-20 15:31:51 +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
xyf2020	f34dcdb09b	feat(Step tools): add white/black path prefix permission filtering to read, edit, write (#391) ... * feat(read): add white/black path prefix permission filtering to ReadStep * feat: add PrefixCheck mixin for path-prefix permission in file I/O steps * feat: add injected_job_kwargs mechanism and refine path-prefix permission * refactor(file_io): consolidate prefix_check into _path module	2026-07-27 17:20:21 +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
Ziyang Guo	c060933e4d	fix(auto-memory): preserve message timestamps (#310) ... * fix(auto-memory): preserve message timestamps * fix(auto-memory): infer daily date from messages * feat(file_io): add strict date parsing and improve daily date handling - Add new parse_daily_date function for strict YYYY-MM-DD validation - Replace extract_daily_date with parse_daily_date for explicit date validation - Change _messages_day to use max date instead of min for historical imports - Reorder imports to maintain consistent module ordering - Move session message saving after date validation in auto_memory - Add comprehensive tests for invalid date rejection before saving - Add tests for strict YYYY-MM-DD date format validation - Update test names to reflect latest date behavior --------- Co-authored-by: Ziyang Guo <121015044+RunMarshal@users.noreply.github.com> Co-authored-by: jinli.yl <jinli.yl@alibaba-inc.com>	2026-07-01 17:15:07 +08:00
jinliyl	ffb4d08c4f	feat(mem): Enhance daily note system with metadata handling and write functionality (#295) ... * feat(file_io): add daily_write step for creating daily notes with conversation metadata - Add DailyWriteStep class that delegates to write job for creating daily notes - Register daily_write job in default configuration with proper parameters - Include validation for name and session_id path components - Add test coverage for daily_write functionality including metadata handling - Preserve existing job execution method in application.py after repositioning - Update base_step.py to use positional-only parameter syntax for job methods - Import and expose DailyWriteStep in file_io module initialization - Override reserved metadata keys (name, description, session_id, source_conversation) with fixed values - Refresh daily index after successful write operation - Generate proper source conversation links in markdown format * feat(daily): refactor daily note system with enhanced metadata handling - Introduce validate_filename_component function and export it - Add _INDEX_HIDDEN_METADATA_KEYS to hide conversation metadata from index - Update scan_notes to exclude hidden metadata keys from index rendering - Modify auto_memory to use daily_write tool and manage session frontmatter - Implement session note lookup and renaming based on frontmatter name - Update daily_list to return flattened note metadata including session info - Change daily_write to dispatch write step instead of running job - Add test cases for updated daily note functionality and metadata handling - Update version from 0.4.0.2 to 0.4.0.3 * fix(evolve): correct metadata update in auto memory response - Fixed trailing comma issue in metadata dictionary update - Ensured proper formatting of response metadata structure - Maintained existing functionality while fixing syntax error * refactor(auto_resource): replace daily_create with dynamic note management - Remove DailyCreateStep and related exports from file_io module - Replace static daily note creation with dynamic resource-linked card system - Implement LLM-suggested naming with frontmatter-driven file management - Add source_resource linking for tracking original files - Introduce collision handling with hash-based suffixes - Update documentation to reflect new resource card workflow - Modify auto_resource prompts to use write/edit tools instead of daily_create - Adjust test fixture comments to match new agent behavior - Update framework diagrams and quick start examples accordingly * feat(app): add version info to app initialization and update auto-memory logic - Include version number in application startup logging - Remove tool result truncation logic from auto-memory step - Update auto-memory to exclude tool_result blocks from saved history - Add test case to verify tool results are filtered out from message saving - Update YAML prompts to clarify filename naming rules without dates - Modify configuration to support new dispatch steps format with persistence control * feat(auto_memory): add note modification tracking and optimize frontmatter updates - Add _note_bytes and _note_modified methods to track actual file changes - Optimize frontmatter updates by checking existing metadata before update - Add modified flag to response metadata indicating actual note changes - Update logging to include modified status in various operations - Add comprehensive tests for modified/unmodified detection scenarios - Enhance result hook logic to skip when no actual changes occur - Refactor metadata handling to properly track creation vs modification status	2026-06-25 21:54:56 +08:00
jinliyl	8b82ff88d0	feat(evolve): enhance agent reply processing and logging capabilities (#293) ... * feat(evolve): enhance agent reply processing and logging capabilities - Add agent_reply_result_text function to extract final user-visible text from agent replies - Implement comprehensive logging throughout auto_memory, auto_resource, and dream modules - Add max_units configuration option to limit extracted memory units - Improve error handling and validation in auto_resource step - Refactor dream extract step to respect max_units limit during processing - Enhance summary rendering in dream finish step with detailed breakdown - Add result hook functionality for embedding hosts integration - Implement loose resource filename handling for root-level resources - Update test cases to reflect new functionality and improved error messages * test(background-steps): update fake upsert function to include created parameter - Modified fake_upsert function to accept 'created' parameter instead of '_created' - Added 'created' field to captured dictionary in fake_upsert function - Included 'created': True in the expected response dictionary for test case - Updated test assertion to match new parameter structure	2026-06-24 22:08:47 +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

Renamed from reme4/steps/evolve/auto_memory.py (Browse further)