memorix 1.0.8 → 1.0.10

package/CHANGELOG.md

@@ -1,9 +1,63 @@
 # Changelog
 
-All notable changes to this project will be documented in this file.
-
-## [1.0.8] - 2026-04-19
-
+All notable changes to this project will be documented in this file.
+
+## [1.0.10] - 2026-06-08
+
+### Added -- Low-Intrusion Handoff Diagnostics
+- **Privacy-safe handoff receipts (#95)** -- Added `memorix receipt --json` for cross-agent memory debugging. Receipts expose project identity hashes, write/search counts, recent observation ID hashes, and privacy boundaries without raw chat, raw memory text, raw search queries, tool payloads, or local file paths.
+- **Doctor receipt mode** -- Added `memorix doctor --receipt` so support/debugging can include the same receipt summary alongside normal health diagnostics.
+- **Cross-agent memory boundary docs** -- Documented the operational boundary: MCP connection success does not mean a memory was written, and shared memory means stored memories are searchable across clients in the same Git project, not that chat transcripts are mirrored.
+- **TUI Agent LLM config scope** -- Added `agent` / `MEMORIX_AGENT_LLM_*` configuration for TUI/chat agent calls. Memory formation, compression, rerank, and embedding remain on their existing `llm` / `embedding` configuration paths. If `agent` is unset, TUI chat falls back to `llm` for backward compatibility.
+
+### Changed
+- **Generated agent rules are less intrusive** -- Rules now prefer `memorix_search` when useful and treat `memorix_session_start` as optional, reserved for handoff, long-running work, session recovery, team coordination, or HTTP project binding.
+- **Agent Team wording tightened** -- Public docs now frame Agent Team as optional autonomous-agent/subagent coordination state rather than an IDE-window chat room. Existing `team_*` APIs and CLI namespaces are unchanged.
+
+### Fixed
+- **Release publish blocker** -- `tests/integration/release-blockers.test.ts` now reserves an ephemeral local TCP port for the real `memorix serve-http` smoke test instead of assuming port `19879` is free. This removes a CI-only `EADDRINUSE` failure that blocked the npm publish workflow.
+- **Standalone dashboard embedding config (#46 follow-up)** -- `memorix dashboard` now loads project `.env` / project YAML before dashboard status routes initialize embedding provider state, matching `status`, `doctor`, and TUI behavior.
+
+### Documentation
+- Added a small moving-between-machines note covering `memorix transfer export/import` without changing the Memorix package name or primary README structure.
+
+## [1.0.9] - 2026-05-19
+
+### Added -- Knowledge Base / LLM Wiki Foundation
+- **First-class Knowledge Base layer** -- Added a readable project knowledge layer generated from durable memory, git-backed facts, mini-skills, and project evidence. The Knowledge Base is a shared human-and-AI surface, not a replacement for raw observations and not a TUI-only feature.
+- **Knowledge graph projection** -- Added a semantic graph projection over the same eligible knowledge inputs, preserving source refs for navigation and traceability.
+- **Dashboard Knowledge foundation** -- Dashboard surfaces can consume the same generated knowledge contract as the TUI, keeping Knowledge Base and graph semantics aligned.
+
+### Added -- TUI Knowledge Workbench
+- **Tabbed terminal workbench** -- Reworked the TUI around `Home`, `Knowledge`, `Memory`, `Workbench`, and `Graph` tabs.
+- **Knowledge browsing** -- Added a Knowledge tab for generated wiki sections, item summaries, entities, and source refs.
+- **Memory browsing** -- Added a Memory tab for recent/search/detail flows with ref-focused navigation from Knowledge.
+- **Workbench session center** -- Added explicit session status, explicit bind/end actions, context source summary, and chat. Entering the tab does not auto-start a session.
+- **Graph text browser** -- Added a terminal-native Knowledge Graph tab with summary stats, cluster browsing, node detail, light filtering, and Graph -> Knowledge jumps.
+- **Cross-surface ref navigation** -- Added Knowledge -> Memory, Memory -> Knowledge, and Graph -> Knowledge navigation paths based on stable refs where available.
+
+### Changed
+- **Knowledge architecture clarified** -- Documented the memory layer as the primary input to the knowledge layer, while project evidence such as docs, source structure, and git facts act as secondary inputs.
+- **TUI scope tightened** -- The TUI now behaves as a knowledge-native workbench, not a placeholder coding-agent harness. No fake Run Task / Review controls are exposed.
+- **Session semantics preserved** -- `session_start` remains explicit and lightweight. Agent Team join remains opt-in.
+
+### Fixed
+- **Formation duplicate detection (#94)** -- Fixed Formation resolve comparing raw Orama/BM25 ranking scores against normalized similarity thresholds. Noisy log-dump memories with high backend scores no longer discard unrelated valid memories as duplicates.
+- **TUI chat input lock** -- Fixed a regression where after a free-text chat response the bottom input bar became unresponsive because the chat overlay disabled the CommandBar. Chat overlay now keeps input active so users can continue the conversation.
+- **TUI read-only overlay input lock** -- Fixed read-only overlays such as `/doctor` disabling the CommandBar. Users can now keep typing commands or questions while diagnostics and other non-action views are open.
+- **TUI shortcut/input conflicts** -- Fixed CommandBar conflicts with view shortcuts such as Graph `f`/`k`, Memory `k`, and Knowledge `m` while still allowing normal first-character input.
+- **Graph TypeScript build issue** -- Fixed a type-only re-export under `verbatimModuleSyntax`.
+
+### Known Limitations
+- The Knowledge Base and Knowledge Graph are read-only generated projections in 1.0.9.
+- 1.0.9 does not include a desktop app, realtime agent messaging layer, GraphRAG system, graph editing, or full coding-agent harness.
+
+### Stats
+- **Verified TUI subset:** 95 passing tests across `interaction`, `workbench`, and `graph` suites.
+- **Release gates run during cleanup:** `npm run lint`, `npm run build`, and full `npm test`.
+
+## [1.0.8] - 2026-04-19
+
 ### Added -- Operator CLI Surface
 - **Namespaced operator commands** -- Added human-oriented CLI namespaces for `session`, `memory`, `reasoning`, `retention`, `formation`, `audit`, `transfer`, `skills`, `team`, `task`, `message`, `lock`, `handoff`, `poll`, `sync`, and `ingest` so Memorix-native operations no longer require raw MCP tool calls.
 - **Lightweight session start + explicit collaboration join** -- `memorix session start` now opens project-bound memory sessions without auto-registering a team identity. Operators can opt into collaboration with `--joinTeam`, or join later via `memorix team join`, while still getting default role mapping from `agentType` when they do join.

package/README.md

@@ -52,7 +52,7 @@ Most coding agents remember only the current thread. Memorix gives them a shared
 <tr><td><b>🔍 Source-Aware Retrieval</b></td><td>"What changed" queries favor Git Memory; "why" queries favor reasoning; project-scoped by default, global on demand</td></tr>
 <tr><td><b>⚙️ Memory Quality Pipeline</b></td><td>Formation (LLM-assisted evaluation), dedup, consolidation, retention with exponential decay — memory stays clean, not noisy</td></tr>
 <tr><td><b>🔄 Workspace & Rules Sync</b></td><td>One command to migrate MCP configs, workflows, rules, and skills across Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro, etc.</td></tr>
-<tr><td><b>👥 Agent Team</b></td><td>Opt-in autonomous-agent state: task board with role-based claiming, inter-agent messaging, advisory file locks, situational-awareness poll</td></tr>
+<tr><td><b>👥 Agent Team</b></td><td>Opt-in autonomous-agent state: task board with role-based claiming, handoff messages, advisory file locks, situational-awareness poll</td></tr>
 <tr><td><b>🤖 Multi-Agent Orchestration</b></td><td><code>memorix orchestrate</code> runs a structured coordination loop — plan → parallel execution → verify → fix → review — with capability routing and worktree isolation</td></tr>
 <tr><td><b>📋 Session Lifecycle</b></td><td>Session start/end with handoff summaries, watermark tracking (new memories since last session), cross-session context recovery</td></tr>
 <tr><td><b>🎯 Project Skills</b></td><td>Auto-generate SKILL.md from memory patterns; promote observations to permanent mini-skills injected at session start</td></tr>
@@ -123,9 +123,11 @@ Deeper details on startup, project binding, config precedence, and agent workflo
 
 ![Memorix TUI Workbench](https://raw.githubusercontent.com/AVIDS2/memorix/main/assets/readme-tui-workbench.png)
 
-Running `memorix` without arguments opens an interactive fullscreen terminal UI (requires a TTY). Use it for chat with project memory, search, quick memory capture, diagnostics, background service control, dashboard launch, and IDE setup. Press `/help` inside the TUI for the current command list.
-
-Single-shot chat (no TUI): `memorix ask "your question"`.
+Running `memorix` without arguments opens an interactive fullscreen terminal UI (requires a TTY). Use it for chat with project memory, search, quick memory capture, diagnostics, background service control, dashboard launch, and IDE setup. Press `/help` inside the TUI for the current command list.
+
+In 1.0.9 the TUI is organized as a knowledge workbench with `Home`, `Knowledge`, `Memory`, `Workbench`, and `Graph` tabs. It can browse the generated Knowledge Base, inspect memory detail, jump between wiki refs and source observations, view the text Knowledge Graph, and keep chatting after answers without leaving the terminal.
+
+Single-shot chat (no TUI): `memorix ask "your question"`.
 
 ### Operator CLI
 
@@ -239,9 +241,10 @@ For the full IDE matrix, Windows notes, and troubleshooting, see [docs/SETUP.md]
 | Capture Git truth | `memorix git-hook --force`, `memorix ingest commit`, `memorix ingest log` | [Git Memory Guide](docs/GIT_MEMORY.md) |
 | Run dashboard + HTTP MCP | `memorix background start` | [Setup Guide](docs/SETUP.md), [Docker](docs/DOCKER.md) |
 | Keep memory-only sessions lightweight | `memorix_session_start(projectRoot=...)` or `memorix session start` | [Agent Operator Playbook](docs/AGENT_OPERATOR_PLAYBOOK.md#8-what-an-agent-should-do-at-session-start) |
-| Join the autonomous agent team | `memorix session start --joinTeam` or `memorix team join` | [TEAM.md](TEAM.md), [API Reference](docs/API_REFERENCE.md#9-agent-team-tools) |
-| Run autonomous multi-agent work | `memorix orchestrate --goal "..."` | [API Reference](docs/API_REFERENCE.md) |
-| Sync agent configs/rules | `memorix sync workspace ...`, `memorix sync rules ...` | [Setup Guide](docs/SETUP.md) |
+| Join the autonomous agent team | `memorix session start --joinTeam` or `memorix team join` | [TEAM.md](TEAM.md), [API Reference](docs/API_REFERENCE.md#9-agent-team-tools) |
+| Run autonomous multi-agent work | `memorix orchestrate --goal "..."` | [API Reference](docs/API_REFERENCE.md) |
+| Debug cross-agent memory handoff | `memorix receipt --json` or `memorix doctor --receipt` | Privacy-safe hashes/counts only; no raw chat or memory text |
+| Sync agent configs/rules | `memorix sync workspace ...`, `memorix sync rules ...` | [Setup Guide](docs/SETUP.md) |
 | Use Memorix from code | `import { createMemoryClient } from 'memorix/sdk'` | [API Reference](docs/API_REFERENCE.md) |
 
 The most common loop is deliberately small:
@@ -260,7 +263,9 @@ HTTP MCP sessions idle out after 30 minutes by default. If your client does not
 MEMORIX_SESSION_TIMEOUT_MS=86400000 memorix background start  # 24h
 ```
 
-Agent Team is **not** the normal memory startup path and it is **not** a chat room between IDE windows. Join only when you need tasks, messages, locks, or a structured autonomous-agent workflow. For real multi-agent execution, prefer:
+Shared memory means stored memories are searchable across clients bound to the same Git project. It does not mean every chat message is mirrored automatically. For support/debugging, `memorix receipt --json` and `memorix doctor --receipt` show project identity, write/search counts, and hashed IDs without raw prompts or memory text.
+
+Agent Team is **not** the normal memory startup path and it is **not** a chat room between IDE windows. Join only when you need tasks, handoff messages, locks, or a structured autonomous-agent/subagent workflow. For real multi-agent execution, prefer:
 
 ```bash
 memorix orchestrate --goal "Add user authentication" --agents claude-code,cursor,codex
@@ -429,19 +434,16 @@ Additional deep references:
 
 ---
 
-## What's New in 1.0.8
-
-Version `1.0.8` builds on the 1.0.7 coordination/storage/team baseline with a CLI-first operator surface, official Docker path, dashboard refinements, and broad hooks fixes.
-
-- **CLI-First Product Surface**: Every Memorix-native operator capability now has a task-oriented CLI route — `session`, `memory`, `reasoning`, `retention`, `formation`, `audit`, `transfer`, `skills`, `team`, `task`, `message`, `lock`, `handoff`, `poll`, `sync`, `ingest`. MCP remains the integration protocol and optional graph-compatibility layer.
-- **Docker Deployment**: Official `Dockerfile`, `compose.yaml`, healthcheck, `--host` binding, and [DOCKER.md](docs/DOCKER.md) for running the HTTP control plane in a container.
-- **Multi-Agent Orchestrator**: `memorix orchestrate` runs plan, parallel execution, verification, fix, review, and merge loops across Claude, Codex, Gemini CLI, and OpenCode with capability routing, worktree isolation, and agent fallback.
-- **SQLite Canonical Store**: Observations, mini-skills, sessions, and archives in SQLite. Shared DB handle, freshness-safe retrieval, dead `JsonBackend` removed.
-- **Opt-in Agent Team**: task board, messages, file locks, handoff artifacts, and autonomous-agent heartbeat state. `session_start` is lightweight by default; team identity is opt-in via `joinTeam` or `team_manage join`.
-- **Dashboard Semantic Layering**: Team page filter tabs (Active/Recent/Historical), de-emphasized historical agents, project switcher grouped by real/temporary/placeholder, identity page cleanup.
-- **Hooks Fixes**: OpenCode event-name key mapping + `Bun.spawn` → `spawnSync`; Copilot `pwsh` fallback + global-hooks guard; hook handler diagnostic logging.
-- **Programmatic SDK**: `import { createMemoryClient } from 'memorix/sdk'` to store, search, get, and resolve observations directly from your own code without MCP or CLI. Also exports `createMemorixServer` and `detectProject`.
-- **Test Suite Stabilization**: E2e and live-LLM tests are excluded from the default suite, and load-sensitive tests are isolated so the default verification path stays deterministic.
+## What's New in 1.0.10
+
+Version `1.0.10` tightens Memorix's low-intrusion operator story: privacy-safe handoff diagnostics, clearer cross-agent memory boundaries, optional session semantics in generated rules, independent TUI agent LLM config, a better fresh-project cold-start path, safer update behavior, and a release-gate fix so the real `serve-http` smoke test no longer depends on port `19879` being free on the runner.
+
+- **Privacy-Safe Handoff Receipt**: `memorix receipt --json` and `memorix doctor --receipt` expose hashes/counts for project identity, writes, and optional probe results without leaking raw chat, memory text, queries, tool payloads, or local paths.
+- **Lower-Intrusion Agent Guidance**: Generated rules now treat `memorix_session_start` as optional and avoid repeating `memorix_search` in the same turn after a confirmed fresh-project cold start.
+- **Separate TUI Agent LLM Config**: `agent` / `MEMORIX_AGENT_LLM_*` lets TUI chat use a different provider/model from memory formation and rerank, while preserving fallback to `llm`.
+- **Fresh-Project UX Fix**: Empty project searches now explicitly say the tool call worked but the project has no stored Memorix memories yet, instead of looking like a generic retrieval failure.
+- **Safer Update Checks**: Auto-update now defaults to notify-only; background install is explicit opt-in via `MEMORIX_AUTO_UPDATE=install`.
+- **Dashboard Config Consistency**: Standalone dashboard status now loads project `.env` and project YAML before embedding/LLM status routes initialize, matching CLI and TUI behavior.
 
 ---
 

package/README.zh-CN.md

@@ -123,9 +123,11 @@ Memorix 使用两类文件：
 
 ![Memorix TUI Workbench](https://raw.githubusercontent.com/AVIDS2/memorix/main/assets/readme-tui-workbench.png)
 
-在终端中直接运行 `memorix`（不带参数）即可打开交互式全屏 TUI（需要 TTY）。它适合用于项目记忆问答、搜索、快速存储、诊断、后台服务控制、Dashboard 打开和 IDE 配置。进入 TUI 后用 `/help` 查看当前命令列表。
-
-单次聊天（不进 TUI）：`memorix ask "your question"`。
+在终端中直接运行 `memorix`（不带参数）即可打开交互式全屏 TUI（需要 TTY）。它适合用于项目记忆问答、搜索、快速存储、诊断、后台服务控制、Dashboard 打开和 IDE 配置。进入 TUI 后用 `/help` 查看当前命令列表。
+
+在 1.0.9 中，TUI 已整理成知识工作台：`Home`、`Knowledge`、`Memory`、`Workbench`、`Graph` 五个 tab。它可以浏览生成的 Knowledge Base、查看记忆详情、在 wiki refs 和源 observation 之间跳转、查看文本化 Knowledge Graph，并且在回答结束后继续保持输入可用。
+
+单次聊天（不进 TUI）：`memorix ask "your question"`。
 
 ### Operator CLI
 
@@ -427,11 +429,24 @@ Memorix 不是一条单线流水线。它从多个入口接收记忆，把内容
 - [`llms.txt`](llms.txt)
 - [`llms-full.txt`](llms-full.txt)
 
----
-
-## 1.0.8 更新亮点
-
-`1.0.8` 在 1.0.7 的多 Agent 协调 / SQLite / 团队身份基线上，进一步收成了 CLI-first operator surface、官方 Docker 路径、Dashboard 语义分层和大量 Hooks 修复。
+---
+
+## 1.0.10 更新亮点
+
+`1.0.10` 继续把 Memorix 往更低侵入、更容易排障的 operator 体验上收紧：跨 agent 交接诊断更安全、共享记忆边界更清晰、生成规则更克制、TUI agent LLM 配置更独立，同时补上了一个发版阻断修复：真实 `serve-http` 冒烟测试改为运行时申请空闲本地端口，不再依赖 CI 机器上的 `19879` 端口必须空闲。
+
+- **隐私安全的交接 Receipt**：`memorix receipt --json` 和 `memorix doctor --receipt` 提供项目身份哈希、写入/检索计数、最近 observation ID 哈希和可选 probe 结果计数，用于跨 agent memory 排障；不暴露原始 chat、记忆文本、查询、tool payload 或本地路径。
+- **更低侵入的 Agent 指南**：生成规则现在把 `memorix_session_start` 视为可选动作，只在 handoff、长任务、session 恢复、team 协调或 HTTP 项目绑定时推荐使用。
+- **独立的 TUI Agent LLM 配置**：新增 `agent` / `MEMORIX_AGENT_LLM_*` 配置路径，允许 TUI chat 使用与 memory formation、rerank、embedding 不同的 provider/model；未配置时仍回退到 `llm`。
+- **Fresh Project 体验修复**：空项目搜索现在会明确说明「工具调用成功，但当前 Git 项目还没有 Memorix memories」，而不是表现得像一个泛化检索失败。
+- **更安全的更新检查**：自动更新默认切回 notify-only；后台静默安装需要显式设置 `MEMORIX_AUTO_UPDATE=install`。
+- **Dashboard 配置一致性**：独立 `memorix dashboard` 现在会在状态路由初始化 embedding/LLM 前先加载项目 `.env` 和 YAML，和 CLI、TUI、doctor/status 保持一致。
+
+---
+
+## 1.0.8 更新亮点
+
+`1.0.8` 在 1.0.7 的多 Agent 协调 / SQLite / 团队身份基线上，进一步收成了 CLI-first operator surface、官方 Docker 路径、Dashboard 语义分层和大量 Hooks 修复。
 
 - **CLI-First 产品面**：所有 Memorix 原生能力都已经有面向人的 CLI 路径 — `session`、`memory`、`reasoning`、`retention`、`formation`、`audit`、`transfer`、`skills`、`team`、`task`、`message`、`lock`、`handoff`、`poll`、`sync`、`ingest`。MCP 保留为标准接入协议和可选 graph-compatibility 层。
 - **Docker 部署**：官方 `Dockerfile`、`compose.yaml`、健康检查、`--host` 绑定，详见 [DOCKER.md](docs/DOCKER.md)。