memorix 1.8.9 → 1.9.1

package/CHANGELOG.md

@@ -4,6 +4,52 @@ All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
 
+## [1.9.1] - 2026-09-08
+
+### Changed
+- **Large-scale retrieval** -- SQLite FTS5 is now the persistent lexical
+  candidate index. It stays synchronized on insert, update, delete, and can be
+  rebuilt from the durable observations table.
+- **Disk-backed semantic retrieval** -- the optional local LanceDB shadow index
+  stores only vector IDs and metadata, uses HNSW with scalar quantization once
+  the corpus is large enough, and fuses bounded semantic candidates with FTS5
+  results. Search falls back to Orama when the optional native package is not
+  available.
+- **Lazy large-corpus startup** -- projects above the Orama hydration threshold
+  keep SQLite as the source of truth and do not load the complete observation
+  corpus into the interactive agent process. Detail, export, and maintenance
+  paths can still load the data they explicitly need.
+- **Large-store acceptance** -- adds regression coverage and verified gates for
+  1k, 10k, 40k, and 100k records without reducing the durable memory corpus.
+- **Post-threshold vector writes** -- newly generated vectors still reach the
+  persistent semantic index after the in-memory Orama corpus is released.
+
+### Fixed
+- **Stale lexical index on upsert** -- replace-style SQLite writes could leave
+  old terms in an external-content FTS index. Observation upserts now preserve
+  trigger-visible row updates so old terms are removed.
+- **Optional native dependency bundling** -- LanceDB is resolved at runtime so
+  unsupported platforms or installations without its native binary continue
+  to build and use the FTS5/Orama fallback.
+
+## [1.9.0] - 2026-09-07
+
+### Added
+- **Opt-in multi-device sync** -- adds a project-scoped observation
+  event contract with privacy filtering, local outbox retry, conflict evidence,
+  device-clone protection, bounded relay pulls, and filesystem/GitHub/S3/
+  Postgres transport boundaries. It is disabled by default and keeps local
+  SQLite as the canonical store.
+- **Sync hardening** -- retracts records that become private or agent-targeted,
+  keeps imported observations and sync state atomic, rejects immutable-key
+  collisions, verifies every pulled content hash, and uses stable continuation
+  cursors so large pulls do not skip events.
+- **Resource hardening** -- coalesces deferred vector workers across hook
+  processes, respects retry cooldowns, drains due vector jobs through one
+  recoverable worker, removes the redundant full-document detail cache, and
+  batches startup vector hydration to reduce CPU/RAM peaks without imposing a
+  small corpus limit.
+
 ## [1.8.9] - 2026-09-06
 
 ### Added

package/README.md

@@ -63,7 +63,11 @@ Use Claude Code today, Codex tomorrow, and Cursor in the afternoon. The agent ca
 | Static rule files drift | Gotchas, fixes, and project skills evolve from real work |
 | Parallel agent work gets messy | `memorix orchestrate` coordinates task context, handoffs, locks, verification, and review loops |
 
-Memorix is local-first. SQLite is the canonical store, Orama handles search, and LLM-backed formation/embedding is optional. Without model keys, Memorix still works with local full-text retrieval.
+Memorix is local-first. SQLite is the canonical store. Small projects use the
+in-process Orama path; larger projects use a persistent SQLite FTS5 candidate
+index and, when available, an optional local LanceDB semantic shadow index.
+Both indexes are rebuildable and are never a limit on how many durable memories
+you can keep. LLM-backed formation and embedding remain optional.
 
 ### Capabilities
 
@@ -85,6 +89,7 @@ Memorix is more than a memory store. It also installs agent integrations, keeps
 | Orchestration and team work | Task planning, worker handoffs, file locks, messages, verification gates, and review loops | `memorix orchestrate`, `memorix team`, `memorix lock` |
 | memcode | A bundled terminal coding agent that already reads and writes the same project memory | `memorix`, `memcode` |
 | CLI and SDK | Scriptable access for automation, imports/exports, diagnostics, and custom integrations | `memorix ...`, `createMemoryClient()` |
+| Optional multi-device sync | Project-scoped, privacy-filtered observation events with local SQLite kept canonical; GitHub JSONL, filesystem, S3, or Postgres relay | `memorix sync store status\|push\|pull` |
 
 <h2 id="works-with-your-agent"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-agents.svg"><img src="assets/tags/section-agents.svg" alt="Works with every agent" height="32" /></picture></h2>
 
@@ -218,6 +223,12 @@ CLI, MCP, and HTTP are different entry points:
 - `memorix serve` is the stdio MCP bridge used by IDEs and coding agents. Its default tool profile is `micro`, so agents see only the compact core tool set.
 - `memorix background start` / `memorix serve-http` run the HTTP service for a shared endpoint, dashboard, VPS Docker deployment, or multiple clients.
 
+Multi-device store sync is opt-in and separate from HTTP sharing. It never
+uploads the live SQLite database or WAL files. By default it only relays
+qualified project-visible observations; personal, agent-targeted, candidate,
+ephemeral, and other-project records stay local. Set `MEMORIX_SYNC_PROVIDER` and
+inspect `memorix sync store status --json` before the first push.
+
 <h2 id="install"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-install.svg"><img src="assets/tags/section-install.svg" alt="Install" height="32" /></picture></h2>
 
 Requirements:

package/README.zh-CN.md

@@ -62,7 +62,7 @@ Memorix 给你已经在用的 AI 编程 Agent 加上一套共享、可检索的
 | 静态规则文件容易过期 | 坑点、修复和项目技能从真实工作中持续沉淀 |
 | 并行 Agent 工作容易乱 | `memorix orchestrate` 负责协调任务上下文、交接、文件锁、验证和 review 流程 |
 
-Memorix 是本地优先的。SQLite 是权威存储，Orama 负责搜索，LLM 记忆整理和 embedding 是可选能力。没有模型 key 时，Memorix 仍然可以用本地全文检索工作。
+Memorix 是本地优先的。SQLite 是权威存储。小项目使用进程内 Orama；数据量较大时，关键词检索使用持久化的 SQLite FTS5 候选索引，并在可用时使用本地 LanceDB 语义影子索引。索引都可以重建，也不会限制你能长期保存多少条记忆。LLM 记忆整理和 embedding 仍然是可选能力。
 
 ### 能力矩阵
 
@@ -84,6 +84,7 @@ Memorix 不只是一个记忆库。它还负责安装 Agent 接入、保留有
 | Orchestration 和团队协作 | 任务规划、worker 交接、文件锁、消息、验证门和 review loop | `memorix orchestrate`、`memorix team`、`memorix lock` |
 | memcode | 内置终端 Coding Agent，默认读写同一套项目记忆 | `memorix`、`memcode` |
 | CLI 和 SDK | 给自动化、导入导出、诊断和自定义集成使用的本地接口 | `memorix ...`、`createMemoryClient()` |
+| 可选多设备同步 | 按项目隔离、经过隐私过滤的记忆事件同步；本地 SQLite 仍是主库 | `memorix sync store status\|push\|pull` |
 
 <h2 id="支持你的-agent"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-agents.svg"><img src="assets/tags/section-agents.svg" alt="Works with every agent" height="32" /></picture></h2>
 
@@ -217,6 +218,11 @@ CLI、MCP 和 HTTP 是不同入口：
 - `memorix serve` 是给 IDE / Coding Agent 使用的 stdio MCP 桥。
 - `memorix background start` / `memorix serve-http` 是 HTTP 服务，用于共享端点、Dashboard、VPS Docker 部署或多客户端。
 
+多设备记忆同步是可选功能，和 HTTP 共享服务不是一回事。它不会上传
+`memorix.db`、WAL 或 SHM 文件。默认只同步当前项目中已确认且项目可见的
+观察记录；个人、指定 Agent、候选、短期和其它项目的记录会留在本地。设置
+`MEMORIX_SYNC_PROVIDER` 后，先运行 `memorix sync store status --json` 再 push。
+
 <h2 id="安装"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-install.svg"><img src="assets/tags/section-install.svg" alt="安装" height="32" /></picture></h2>
 
 要求：