yams/release-notes.md
2026-05-11 01:23:22 +00:00

67 KiB
Raw Permalink Blame History

🤖 I have created a release beep boop

0.15.0 (2026-05-11)

Added

  • add BM25 variant RRF fusion to lexical backend (73fbe4c)
  • add FAISS HNSW vector backend with ConfigResolver policy (dc6aaa1)
  • add hint for graph to search and grep files (52fa720)
  • add RM3 pseudo-relevance feedback + adopt research-tuned config (cbb8650)
  • adding additional benchmark and validating onnxruntime model usage for embedding generations. Should be much faster (3101780)
  • adding additional tests, making the aggressive profile scaling better (a9bad18)
  • adding adidtional tasks (c7c5b63)
  • adding doctor check for keychain storage of r2 secrets (d09918a)
  • adding drain to constrexpr metrics (4d6c163)
  • adding fuzz test for new download logic, removing r2 endpoint from tests, decoupling embedding / onnxruntime logic for work from previous commit (2e20416)
  • adding fuzzing updates and fixes in ipc (c64a0b2)
  • adding instrumentation and config options for build and repair system. Bumping simeon and improving topology system with experimental findings (8de19b8)
  • adding perf optimizations for search and grep based on previous commit. Improving model logic for future embeddinggemma and improved colbert support. Re-ranking fixes for search to improve retrieval accuracy. (f3399c0)
  • adding simeon https://github.com/trvon/simeon (d7f6ad4)
  • adding storage check, db corruption check and tests (eae3c5a)
  • adding support for phss vector search, test fixes, daemon status regression fix, ci fixes for docker builds with new third-party library (e88578a)
  • adding yams corpus tuner (a97952e)
  • additional cleanup from taskflow migration (82daf7d)
  • additional config imrpovements and deeper integrations of simeon in yams search (f27077b)
  • additional dev leakage cleanup for query and tick logic (106aa0b)
  • additional improvements to reduce read and request contention (226cea7)
  • additional locks patterns reduced (bb651d8)
  • additional optimizations and improvements for package validation and ingestion speed (e6e0b39)
  • additional optimizations for faster responses and ASAN fixes (8e4b0df)
  • additional test and ASAN/TSAN fixes (bf11646)
  • additional test clean up and expansion for benchmarks (b6b6ba9)
  • additional test improvements, improved logic for ingestion queue to increase throughput and client stability (be77f1f)
  • address bugs with scaling, batching in daemon processing (1d255d5)
  • address search gaps (46d4c2c)
  • address test drift, removing hnsw remants for simeon backend implementation, continued refactor of vector backend (d8cb076)
  • ann improvements (c00aded)
  • auto complete improvements and topology refactor to improve graph rebuilding on ingestion (58cba44)
  • beginning sandbox support work and retrieval optimizations (6df2332)
  • bench harness data_dir reuse + richer telemetry, doc updates (cc49704)
  • benchmark and validation testing against original system before swap (5715ae9)
  • benchmark expansion and normalization. Imrpoving metrics for repair and models (f4f3c05)
  • benchmark fixes and instrumentation (39037c0)
  • benchmark, model testing / enhancements, insertion performance updates (c831103)
  • breaking: breaking change. removing onnxruntime for embeddings in favor of simeon. embeddings will now use less system resources, run faster but require avx/neon support per library (2b60bed)
  • bug fixes in daemon lifecycle, cleaning up tests and resolving test failures (2360828)
  • build improvements, docs updated and optimizations for cli latency (8777a27)
  • bump submodule (90dc507)
  • bumping ghidra plugin model (a5d5ddc)
  • bumping homebrew module (3b24ea7)
  • bumping simeon module and linking new fragmented strategy (0eeed2e)
  • bumping simeon, improving graph building, clustering, configuration tuning of said system and updating benchmark files. Additional fixes for daemon readiness and status return underload. (a01bd76)
  • checkpoint for updated unit test for daemon communication / protobuf errors. Expanding untested surface with optimizations for communication and ingestion. Additional work for ci apt / rpm install improvements, systemd configuration for installs and improved validation testing of packaging logic to reduce gpg errors. (13be8fd)
  • ci/test regressions updates, reinstated onnxruntime (simeon will still be default), expanding topology instrumentation in search, newsletter update with throughput comparison (f825bc3)
  • cleaning up additional locks in service manager (ff110ac)
  • cleaning up codebase and improving treesitter plugin (2381c90)
  • cleaning up comments and migrating search to simeon (8914169)
  • cleaning up daemon components. Additional taskflow improvements. Fixing windows build error in daemon_command (7daee1b)
  • cleaning up request path and fixing checkpoint logic underload (082c381)
  • cleaning up test suite (a930776)
  • CLI request handling refactor for unified load and error handling. Continued refactor and improvement of search engine with scoped tuning (48a955e)
  • completion fixes and reduce bottleneck of ingestion on add from cli (4c9ce1e)
  • completitions fixes. Starting topology routing work for semantic clusters (0c74dcb)
  • config cleanup and expansion (8bdad0c)
  • continued corectness improvements, ANN / vectordb improvements (ef3d925)
  • continued extraction from serach engine and vector improvements. This allows for better testing and experimentation (6174b13)
  • CorpusStats-driven tuning accuracy + per-query community detection. Fixes for clion meson detection (473274d)
  • Correctness fixes for flaky tests, improvements for linux build logic based on clion change. Improvement of tuning / governor daemon logic to simplify scaling logic (2b2552e)
  • correctness improvements and bumping sqlite_vec_backend lib (c9ad8f5)
  • daemon communication optimizations (c61796b)
  • daemon lifecycle improvements for supervisor mode, search now uses topology logic, homebrew formula launches yams in foreground mode and test updates (036e5e7)
  • daemon: adaptive physical-walk TTL + statvfs fast-path, hot-tier getenv<6E>TuningSnapshot, RepairScheduling/RepairTuning slice extractions (f4ffb3d)
  • early embeddinggemma support (7a8c261)
  • expanding graph usage in search (8401db1)
  • expanding graph utility in search, fixing Dockerfile build logic and improving search tracing logic for graph performance (211596a)
  • expanding instrumentation for optimizations and improvements for search / retrieval functions (80e0724)
  • expanding mcp UI support, improvements for slots for component usage and other socket server stabilizations (9254264)
  • expanding metrics for graphs ingestion pipeline and search pipeline. Fixing graph building duplication and improve metrics (d5048d5)
  • expanding mobile abi compiled support (8da76c9)
  • expanding search metrics for manual tuning (8252588)
  • expanding storage system to work with r2 backends via object storage plugin. Updating benchmarks and documentation (41a2282)
  • expanding topology instrumentation to expose quality of clusters, cli ux improvements and expanded modifiers (1fcb7cf)
  • expanding topology system and search for better testing and simeon integration (8c313fc)
  • expansion of topology system into repair and ingestion pipelines (3c2f61b)
  • experimenting with parallelization of onnx reranker (1c2bd4f)
  • extending instrumentation for memory and cluster profiling. COntinue UX improvements for grep and search cli commands and mcp (8417340)
  • extracted public and categorized methods from service manager. (a9bc8a7)
  • extractor reranker and helpers from search engine. Establishing dual paths for simeon and onnxruntime to present heavy vs light system trade offs (e44c28b)
  • fixes for repair batching logic, hnsw rebuild and search refinements before graph building improvements land (12e4b19)
  • fixing brittleness in CI pip usage that breaks under package updates and system delayed updates. Improving graph repair process and reducing locks in ingestion pipeline (a1253d1)
  • fixing bug with multiple processes access gpu, read/write pools now added in metadata repository, and updated plugins for opencode and vscode (94a4947)
  • fixing ci for windows packaging (a2ec698)
  • fixing sandboxing latency issue and streamlining all cli commands (minus doctor and daemon) with similar logic to detect if in sandbox so this works with codex (77c0613)
  • fixing TSAN issues in MCP. implementing cloudflare code mode https://blog.cloudflare.com/code-mode-mcp/ (91e2123)
  • further homebrew bug fixes and improvements (902f75c)
  • further removing hnsw references and centralizing on simeon pq implementation (4617bf4)
  • further search improvements and daemon sleep fixes. Commit before service manager refactor/cleanup (569ffae)
  • fuzzing and config expansion. Moving to optimizing ingestion. Adding tunable embedding (chunk size etc.) (44a94ea)
  • fuzzing tooling (907cddf)
  • graph clustering improvements for topology system. Checkpoint before experiment with better clustering systems and simeon module bump (3ac9bd6)
  • graph expansion logic improvements for search testing, repair improvements for embeddings (a99efd1)
  • grep performance improvements (648a9e5)
  • hardening client reponses and improving search engine precision through optimization loop (513d430)
  • Hardening moodel logic for embedings. Adding trace-linked feedback event persistence checkpoint (8256917)
  • homebrew fixes for nightly formula install (58a8cf8)
  • implementing embedding chunking strategy and two staged ingestion that processes then distributes document data (a44c2fb)
  • improved online metrics for corpus (9db8d79)
  • improved search fusion logic and tuning parameters. CI improvements, reverting to push with wrangler in CI. Experimenting with vector rebuild to address additional lost overhead in search (8b7bfe5)
  • improvement for topology rebuilds on ingestion and in repair (3183dae)
  • improvements for repair logic (2b1e498)
  • improving benchmark by adding to doctor command with persistence to tune search engine, improving topology epoch tracking and connecting adaptive tuner (463a377)
  • improving daemon command socket handling and helpful logs (52b6ef2)
  • improving ingestion speed with kg batch and updating metrics to use constexpr (0c8ffea)
  • improving packaging logic for homebrew and addressing pip install regression in tests (3cccde2)
  • improving repair logic and search engine metrics for tuning logic (825d9aa)
  • Improving search speed for hybrid engine. Trying best to balance speed and precision (c475f10)
  • improving sql access under contention and expanding tuning logic with graph (37b95bf)
  • improving tuning and expanding instrumentation for memory allocation (06b4992)
  • imrpovements for repair and graph clustering logic and search usage (ad8d7ac)
  • ingestion optimizations and regression test updates (e13ff15)
  • installation tests and build improvements. Test fixes related to optimizations for reranker (883eb11)
  • instrumentation improvements for benchmarks, shell completition improvements, packaging updates for completions and docs updates (f4fffd7)
  • instrumented embedding for deeper insight into hotspots. Fixed CoreML scaling that resulted in high ram usage due to VRAM calculation. Expanded testing for embedding and draining of work (cc28b8a)
  • instrumenting search engine and graph tools to investigate poor graph retrieval performance (6d1ef52)
  • integrate simeon concept mining into lexical backend (102d5a1)
  • introducing epochs for search rebuilding (a4fdb70)
  • large commit, new tune command, search tuning and improved corpus learning with persistent values (9c23fcf)
  • large update. Documentation update, config and plugin hardning and improvements related to loading trust. Exposed trust state in the doctor command with hints on improvements. Bug fixes and test improvements to reduce flakiness and TSAN issues (099bbef)
  • leveraging taskflow for ingestion pipeline. search engine optimizations (325ab78)
  • linking fix for onnx plugin for windows builds (8523b77)
  • lint run and sandbox detection improvements for non sandbox envs (b72eb95)
  • linter: running linter on codebase (94c8e6a)
  • list and documentation updates (44733e9)
  • massive commit. Download logic updates with expanding controls (stop, start, resume etc.) from daemon control. This is used in my archive openclaw agent. This commit also includes work to harden onnxruntime abi access. this should allow loading newer abi's when builds are pinned to 1.23.0. (86ec015)
  • mcp and skill file update to reflect code mode (782d416)
  • memory optimizations, and topology tuning improvements (926ef8a)
  • merge and site update (1d7b15d)
  • merge vscode settings (c973a24)
  • migrating additional subsystems to write coordinator. Addressing symspell holding write pool and blocking ingestion (9b69495)
  • mobile binding improvements (3540000)
  • mobile bindings expansion, update mcp for graph operations and download tool hardening (c4ae922)
  • move newsletter to sourcehut (de6a5b1)
  • moving changelogs to archive, implementing TurboQuant then will integrate in vector engine (147f5ca)
  • optimizations based on profile runs in hashing and work coordinator. test updates and correctness fixes (c49f0ba)
  • optimizations for data returns and harden daemon status and normalize MCP/version responses (9a1ed08)
  • optimizations for multiclient usage, updated benchmarks and ci correctness improvements to improve test runs collection (53326b6)
  • optimizing query logic to reduce hangs with large corpuses (2c8664b)
  • performance optimizations for list retrieval (cbb0cf6)
  • persist semantic dedupe suggestions and apply them via repair (549de4a)
  • post installation fix for homebrew to enable packaged plugins (8e6c52c)
  • profile for building mobile bindings (09c8e0f)
  • profiling improvements (9b774d6)
  • prompt update for code mode mcp (cb20b94)
  • recovery test improvements (00c3a76)
  • reduce sleeps in daemon service manager, ingestion pipeline and moving towards event driven design (8d48496)
  • refactor vector engine to reduce monoliths in codebase (be0feac)
  • refactoring search graph logic and adding sematic graph edges for better relationships (efbf102)
  • refining readiness strings with constexpr. Final release testing for v0.13.0 (5eab5b9)
  • reinforcing proxy path for quick ux, adding topology tuning engine for corpus cluster usage in search, simeon memory management improvements (2ced7a7)
  • release please (f9c94e8)
  • release please update (dd8b7a4)
  • reliability improvements for daemon lifecycle, submodule bumps, plugin improvements and search tuning optimizations based on benchmarks (a3fd217)
  • removing experiments and unifying compression in embeddings storage. (d669c00)
  • removing isolated and deadcode from graph command (3c8d60a)
  • removing other graph clustering algorithms for hdbscan with sgc (6fa8b03)
  • removing unnecessary abstraction and adding some optimizations for embeddings generation (814672f)
  • repair logic improvements, expanding config options to disable rebuilding/repair for memory constrained systems (7de4d95)
  • resolving bug introduced in socketserver (8cb2986)
  • reverted taskflow experiment (a449afc)
  • sandbox testing expansion (sandbox relates to how the daemon communicates in sandbox). Graph optimizations for retrieval and UX improvements. Will continue improving graph system (3b1a300)
  • search / grep freshness and query intent router improvements. Test improvements (55a7f5a)
  • search / retrieval optimizations for performance and accuracy (ce36736)
  • search improvements, changelog fixes and test expansions for refactored code (2d412a5)
  • search improvements, changelog fixes and test expansions for refactored code (52b8d4c)
  • search improvements, test correctness fixes and bug fixes (9c201af)
  • search improvements, UBSan meson option, CI quality job, and fix clang-tidy findings (677f67e)
  • search optimizations (expanding re-ranking work to recovery items that are not strong candidates based on how they are retrieved). Test improvements and TSAN/ASAN fixes. (d353e53)
  • search optimizations resulting in improved recall. Updating vector embedding metrics traffic (96d8dca)
  • search persistence hardening, socket server improvements to reduce churn, vector persistence improvements, and test coverage improvements (680cb47)
  • search/grep retrieval based improvements, test expansions and bug fixes (2e87c3c)
  • search: add concept_count and concept_mining_enabled accessors (a61d0fe)
  • search: integrate simeon EntropyRouter strategy lane, corpus-state tuning (8fd830e)
  • search: reduce graph noise, add edge-creation diagnostics (1f9bc76)
  • security fixes for plugin install and adding additional UTF-8 string sanitization (8f06bd6)
  • setup.ps1 improvements (28c56d6)
  • setup.ps1 improvements (58ade70)
  • site update (b6e7c7e)
  • stability improvements for document ingestion (cd7c698)
  • starting remote storage work, config v3, and config migration (8af4d35)
  • streamlining tuning and pool logic in daemon (dea5315)
  • submodule commits and test expansions (508f3c2)
  • test cleanups (0beaf58)
  • test coverage improvements, list hardening for wildcard usage, search and benchmark optimizations for retrievals (9e918b7)
  • test fixes, metric expansion, build improvements for gliner (df0c78c)
  • test hardening, added benchmark for multiclient and improve stability to support up to 16 clients before performance degrades, improved parallization and request handling in daemon ingestion pipeline (33821d9)
  • test improvements, ASAN fixes, and onnx model performance improvements (6a90f8c)
  • test improvements, doc updates for download expansion (f3de749)
  • test imrpovements, infer fixes in search changes from previous commits (4a3dce8)
  • test suite improvements. Migrating remaining tests to catch2. Improving hnsw for usage in benchmarks (15e049d)
  • tuning improvements for graph influence (e1d2db3)
  • tuning improvements with expanded db metrics, package hardening and updated tests (8516a1b)
  • tuning topology system to work better with simeon via configuration (e4a8639)
  • TurboQuant imrpovements (1bc6b7d)
  • TurboQuant integration for re-ranking, starting with benchmarks, then moving to integration (1692306)
  • TurboQuant now supports end-to-end packed-vector storage, reranking, and direct compressed ANN traversal with persisted per-coordinate calibration and validated multi-dimension performance. (8b39304)
  • TurboQuant search and ANN compression improvements. CLi client regression fixes (6874b22)
  • updating brew install guide (5a764ac)
  • updating docs with r2 benchmarks (ca79b36)
  • updating embedding default checking to paragraph (11ba59f)
  • updating git module to https (d7e55e0)
  • updating homebrew formulas to correctly link nightly builds (4edc40a)
  • updating metrics for search and retrieval for future learning system. Additional tuning for search performance (8f38ee7)
  • updating release to properly sign packages (8174f2a)
  • updating staging (c182221)
  • updating zyp pdf extractor to use v0.16.0 compat in plugin build (bc100ef)
  • vector optimizations. Most performance gains in search felt on macos (bb0d33a)
  • vendoring and migrating correctly to use tinyfsm (fdac636)
  • vendoring hdbscan for clustering of documents, refactor duplicate code logic in cli and daemon paths, topology instrumentation (6cdba45)
  • versioning bumping opencode plugin (7ee2091)
  • write coordinator (dae95f4)

Fixed

  • adding cap at onnx concurrency limit (0c8a5ee)
  • additional cli and search optimizations to reduce latency, test coverage improvements (727d5b3)
  • additional correctness issues in repairservic, backgroundtask manager, tuning advisor and daemon (cbdef02)
  • additional merge fixes and search improvements (55b2dc5)
  • additional repair logic improvements to unify repair system. Search improvements and graph building optimizations for retrieval performance improvement (96eb95f)
  • address ci source venv and graph repair timeouts (e8ddb31)
  • address daemon starvation/deadlock paths and aligning ownership of run loop lifecycle (61d92c9)
  • address regressions in onnx runtime generation from previous commit. Addressing critical bugs (fff1ca1)
  • address test failures and improve daemon status ux (a3be3c6)
  • addressing build regressions where fiass needed openmp installed (18b10dc)
  • addressing code smell from previous commits (debfbca)
  • addressing gap where graph nodes not populated at ingestion (25214af)
  • addressing gaps and todo in storage implementation. Improving tests (d0e33f4)
  • addressing TSAN and empty catch blocks (4cf1704)
  • addressing unoptimal copies of vectors in repair path (a3f1d52)
  • addressing UX issue with daemon status readiness (11ef101)
  • addressing windows build error (5961e6d)
  • apply tuning logic for profiles to GPU (04b55be)
  • ASAN fixes in daemon lifecycle. grep testing improvements (c3c4d1d)
  • asan: Addressing asan test regressions and suite failures from recent changes (0204072)
  • bug fixes and test improvements for small correctness issues (4fe9ce6)
  • bug fixes for resource limiting and onnxruntime model shapes for embeddings (b40b60f)
  • bug fixes from test regressions and test infrastructure improvements (f4b3576)
  • bypass broken Gemma CoreML path and restore ANN/TurboQuant search (a0b4915)
  • ci and repo updates (f7819d0)
  • ci build fix for pinned version change. checkpoiting write improvements before move all writes to single component (438572c)
  • CI fix (625c573)
  • ci fixes and experiment for search / cluster routing (c55ce54)
  • ci fixes, coverage improvements and test improvements and bugs fixes (9091a9f)
  • ci: ci build fixes for windows, linux, macos tests lanes (49b40d5)
  • ci: ci test and bug fixes. Improvements for testing topology construction (42ee44c)
  • ci: recover release-please to release handoff (3e7624c)
  • ci: restore cache-hit guard for macOS/Windows warm step (c3127d5)
  • ci: revert Conan profile ccache wiring (breaks compiler_executables) (07ad866)
  • ci: test fixes (7d29f96)
  • ci: test fixes and newsletter numbers updates (42406b9)
  • ci: tolerate untagged release-please drafts (a650c25)
  • clang warning fixes and daemon startup wal guard and fallback regression fix (c2a9d32)
  • clang-tidy / infer fixes. Fix for test.yml builds (a56bc5d)
  • cleaning up benchmark page and adding CmakeLists.txt (f8b794d)
  • cleaning up ENV leakage from debugging (49a106a)
  • cleaning up macos build detection logic (970f253)
  • cleaning up object references (f69c388)
  • cleaning up postingest pipeline (8b79d8a)
  • cleaning up startup logic and timers as corpus grows (2ee0a75)
  • cleanup storage override logic (29ef276)
  • cli clean up of old comments and duplicate code. search improvements as we migrate yams to simeon. (6c2c31f)
  • cli regression fixes and turboquant improvements for storage retrieval logic (2922835)
  • code cleanup and bug fixes related to plugin system trust (782561b)
  • code mode fixes and tests update for ci (49f0f90)
  • concurrency and race condition fixes (57b7e20)
  • continued correctness improvements. Added vec0 search mode and benchmark plumbing for YAMS retrieval (5795a0f)
  • continued turboquant work. added additional api's and improved testing / perf tests (7609d63)
  • continuing improvement of error catching and logging improvements (6d95573)
  • Copilot review feedback and gitignore for artifacts (#26) (e27d5e3)
  • correct fixes in the search engine and windows build improvements (a4f4756)
  • correctness fix for abalation test, fixes for daemon response (regression is present underload/repair) (4f92b4e)
  • correctness fixes for stale sqlite handles (apart of previous work), improvements in test suite and continue work for search optimizations (9c496e6)
  • create dir helper cleanup and windows build fix (7a71bf7)
  • daemon: WAL flush on shutdown, corrupt-DB salvage, test hardening, ASAN fix (#27) (867deed)
  • disable faiss on Apple Clang macOS, remove hardcoded /opt/homebrew paths (8433d4f)
  • disable faiss on Apple Clang macOS, restore profile cache keys (f14c7d6)
  • docker: add gfortran for openblas arm64 build (8f5b0d0)
  • docker: add wget for Zig, disable faiss (597aed4)
  • docs,ci: addressing breaking changes in zig v0.16.x in Dockerfile, docs update and code cleanup (8772cc8)
  • download logic improvements and ci test fixes. Stagging download fixes seperate from search features (2d5c662)
  • enforce resource caps (d86eb06)
  • expanding cli test suite, addressing ASAN issues and improving error handling (9dc3847)
  • expanding utf-8 sanitization and expand search tracing and test coverage (81cc38a)
  • expose gpu usage, add command imrpovments and other bug fixes (a3522b8)
  • fix bad version update (c3d3ca4)
  • fix cli commands and working on retrieval optimizations (dd93cf8)
  • fix config snapshot logic in CompressionMontor, RecoveryManager, TranscationManager and CompressionsError handler (6ee7c57)
  • fix for test messing up config (422d857)
  • fix issues with mobile bindings and improving abi alignment (1962ff6)
  • fixing apt update, re-rolling gpg public key (76f9170)
  • fixing bind issue when generating large batches in repair (1e0ca15)
  • fixing ci push to repo (8b9a443)
  • fixing ci upload and release trigging logic (451b441)
  • fixing daemon inflight request lock and pid regression (74e9346)
  • fixing daemon regression for startup logic resulting in ipc eof, expanding release please to update conan file version, expanding benchmark docs (d92f66d)
  • fixing fragiling SocketServer loop (e5eaaf8)
  • fixing ipc eof seen in streaming commands (154aa25)
  • Fixing issues that break windows release build. This should allow new msvc version Working on debug builds. (a0fd82e)
  • fixing leakage of build artifacts in release, unifying repair path, adding cache to tuning path and bumping simeon version (127bc9e)
  • fixing mcp code routing and paramater normalization with a light refactor (ce56050)
  • fixing mcp download bug, updating socket server configs for more client connections (247f337)
  • fixing neon build and memory pressure issues (0975e3e)
  • fixing onnx model logic so that memory does not hold indefinitely. Removing re-ranker logic from plugin (801980c)
  • fixing onnxruntime linking isuses which result in degraded state on linux (fdf2c32)
  • fixing pipeline ingestion of kg and embeddings. Still finding stalls and will continue to investigate (cc1212b)
  • fixing regressions with serach engien start (3f03eb2)
  • fixing repair regression (e39273a)
  • fixing rpm builds (9b6461e)
  • fixing s3 signing bug (92bb0c5)
  • fixing scaling logic of embedding generation that fallback to CPU (120d98b)
  • fixing search regression when fuzzy search triggered and testing improvements (943393a)
  • fixing semantic drift of readiness system, improving cli routing to reduce churn to proxy socket and improving daemon lifecycle logic (07805cc)
  • fixing stale issue related to repair manager, mcp suggestions logic that leads to looped behavior in long sessions and ci test failures (1c9f03c)
  • fixing stop regression when socket exists to fast, fixing bug in binary detection where agent added files were seen as text. Added repair fix to improve binary classification of files without extensions (bed12ed)
  • hardening release CI, addressing issues with onnxruntime linking on macos and linux and expanding benchmark (31eb110)
  • hardening socket timeout logic (bf65ad8)
  • HNSW and topology rebuilds are now batched in repair. Cleaning up from previous migration work (bdcff5b)
  • house cleaning (a177027)
  • improve stats from embeddings used to trigger search rebuild: (e2772f2)
  • improved plugin locking around onnx session state and ownership improvements (2d0df86)
  • improvement of graph node source and retrieval logic and sandbox fixes in add command (38629de)
  • improvements based on TSAN and strict quality gates (4a26ce6)
  • improvements for embedding generation (embedding gemma specific issue) and Dockerfile regression fix (e09778b)
  • improvements for embedding repair routing to hot model. Continued search / graph build retrieval improvements (364a114)
  • improvements for laoding handling in UX response (3b5fb8f)
  • improving connection churn handling (a9ccee9)
  • improving daemon repsonsiveness and instrumented the daemon client for improved benchmark tracing (c781640)
  • improving graph repair (1a0667d)
  • improving repair check (6eb1635)
  • improving socket and chunking reliability and robustness. Added better regression tests and errror logging logic for state connections (ff77c6b)
  • improving test coverage and addressign ASAN issues (081fb74)
  • lifecycle regression fix and repair improvements (677756b)
  • macos homebrew packaging fixes (7a55178)
  • make Gemma CoreML fallback automatic (d5967de)
  • mcp router fix (2f505b0)
  • metadata optimizations (2a0f020)
  • metadata: deduplicate batch entries before UPSERT (68a49e7)
  • metadata: retry constraint failures in executeQueryOnPool (e971b56)
  • moved SocketServer read/write into dedicated IOCoordinator and fixed proxy socket paths resolution logic. Fixed TSAN race in SymSpell init (4ecdbe7)
  • moving submodule to https (e197573)
  • optimizations for hnsw rebuilding logic, test expansions and improvements (b0c8d96)
  • patching ipc:eof error in repair (0fdd4d8)
  • perf: pushing newsletter, and embedding lock update (fe8cbd1)
  • pipeline scaling fixes, post ingestion benchmark updates (2184993)
  • plugin bug fix for reranker (2a11749)
  • prune fixes for build artifacts, readiness improvements and hnsw api unification (1b6f137)
  • re-ranker embedding generation fix, test failures drift fix, search improvements for graph query expansion and gliner improvements for building graph (e8a6296)
  • readiness ux fix (a008438)
  • refining communication path in daemon (c510d55)
  • refining ingestion logic (52303af)
  • regressions fixes in request handlers and correctness improvements in repair service (6d1ec69)
  • release please fix (b9373db)
  • release please fix, improvements for embedding generation (check if model is loading an query that). continue work on search retrieval improvement related to on going graph improvements (3f3ba05)
  • removed reduant corpus adapter (ea6cd51)
  • removing claude/skills (1c800e0)
  • removing duplicate shim logic (0703a28)
  • removing gtest and continued cleanup work of test suite (e2c8ba0)
  • repair fix in db optimize (ba9030b)
  • repair fixes for embedding generations and stalls, mcp code mode improvements for smarter routing, test improvements and additional search / graph optimizations (aee787d)
  • repairmanager, post ingest and pipeline fixes (c4a7992)
  • reranker and internal benchmark fixes to address updates and test regressions (32bac6d)
  • resolving TSAN issues and expanding graph building to use gliner data (fc284f3)
  • review: change tryEnqueue to by-reference, prevent batch destruction (c256458)
  • ROCM/MIGraphX onnxruntime test validate improvements (7764a0c)
  • search: wire GLiNER concept extractor, fix PQ dirty race, add KG NER awareness (6704e0b)
  • simeon bump and double lock addressed in search (3615254)
  • small fixes for benchmarks and documentation update (d7ab484)
  • SocketServer slots for proxy and cli requests, fixed tests and increase doctor request handling (430057f)
  • staging ROCM improvements (fd32c51)
  • suspected deadlock fixes in repair, bugs addressed in request logic. Continued triage from infer output and test failures (e261420)
  • tear down fixes for tests (991e047)
  • test and ci fixes and search improvements. Adding a router for tuning logic (01c72ec)
  • test build error fixes (bd20aee)
  • test coverage updates and address protobuf bug in search (554bf47)
  • test fixes (11304c6)
  • test fixes and search fusion update to correctly expose simeontext fusion so that it does not drop ft5s candidates. Still explore fusion optimizations (7ae52e8)
  • test fixes related to metadata optimizations and some search tuning checkpoints before refactor experiment (d1225ab)
  • test improvements and CI harning for slower tests (4245090)
  • test improvements and correctness improvements using check-quality script (985d03a)
  • test regression and build fixes (ed80f97)
  • test updates and benchmark updates for grep (29b5172)
  • testing improvements and bug fixes (0cdb3ab)
  • testing improvements and bug fixes in daemon logic for lifecycle management (014e12c)
  • test: relax stuck-docs CHECK to >= 0 (background loop may pre-process) (70ff865)
  • tests: update turboquant_bench docs and fix unused-variable warning (7c3b4c0)
  • text fixes, connection handingly fixes and continued refactor work (f381597)
  • topology fixes improvements, alignment in daemon readiness checkpoint (1f9387e)
  • tree-diff benchmark regression accounting and stabilize subtree fast-path measurement (e41ec38)
  • TSAN fixes and sample updates (15980aa)
  • tsan fixes, test instrumentation improvements and improved sql handler logic (2fd9164)
  • updating conanfile for onnxruntime to respect system version, updated tests for windows compat, update vectors to enforce wal check point so files does not explode in size (d86ac66)
  • updating gpg signing and homebrew logic for releases (ca7a491)
  • updating other cli commands to work with sandbox detection update (c4e61e8)
  • updating readme and linking benchmark pages (1526545)
  • vector and embedding count fixes related to repair functionality. Improvements for search and tuning scope of candidates (d25cc39)
  • vector: guard faiss backend init behind YAMS_HAS_FAISS (bec8164)
  • windows build fixes (2e966c4)
  • windows build fixes and test instrumentation to resolve ANN precision issues (c32db6e)
  • windows test fixes (901337b)

Security

  • adding opengrep config to githook with rules. Addressing additional concerns (3dd0e2b)
  • additional security fixes (faee34e)
  • additional security fixes and improvements for storage correctness (5581fa0)
  • addressing before underflow (32f458b)
  • addressing codeql security finding and expanding opengrep rules (2d84e44)
  • dev scripts and hooks update, perf update, security fixes for quality issues (5adb8f1)
  • expanding opengrep suite and addressing issues (c25a4ad)
  • storage implementation improvements (886c9c0)
  • updates to opengrep rules, repair subsystem scanning logic and windows build logic (f3ffb92)

Performance

  • accelerate grep and search with RE2 regex and SIMD memmem (9bdef80)
  • additional optimizations for freeing memory when idle and processing files (ff24452)
  • cleaning up search experiments, moving to new routing system for search for larger corpus improvements, repair system now triggers semantic / graph repair (ae1f0c1)
  • improve compress behavior for r2. Compress locally and transmit and retrieve compressed data (0ef3f8a)
  • instrumentation and ingestion optimizations (611d770)
  • mcp: eliminate throwaway RetrievalService instances in all MCP handlers (1ef15c6)
  • startup optimizations (9ac4513)

This PR was generated with Release Please. See documentation.