memorix 1.4.4 → 1.4.6

package/CHANGELOG.md

@@ -2,6 +2,75 @@
 
 All notable changes to this project will be documented in this file.
 
+## [1.4.6] - 2026-08-14
+
+### Added
+- **Memory-native brief block** -- Every task brief opens with a "You and
+  this workspace" block: the user profile (personal `user-profile`
+  observations), the latest ended session summary, and recent durable
+  long-term memories, all inside the existing token budget. Older callers
+  and fixtures without the block are unaffected.
+- **Long-term memory self-maintenance (rule leg, no LLM required)** --
+  Explicit long-term requests (MCP `longTerm: true`, CLI add/promote)
+  auto-qualify on the spot instead of waiting for a manual review;
+  hook-captured and Git-derived candidates keep the review path. Stale
+  qualified/approved records auto-archive after 30 days without activity,
+  and a newer record auto-supersedes same-title records in the same scope
+  and kind. Maintenance runs in the existing durable lane at session start,
+  after each explicit promotion, then on a daily heartbeat. Approval stays
+  an explicit operator action.
+- **`memorix purge`** -- Retires the current project's memories from
+  retrieval (`--all` for every project, `--yes` required outside a
+  terminal). Observations and long-term records are archived, never
+  hard-deleted, so the audit trail survives.
+- **Eval coverage** -- New deterministic, offline exams pin the always-on
+  brief, long-term maintenance, profile parity, purge safety, git ingest
+  policy, media schema honesty, and server config defaults.
+
+### Changed
+- **Installed tool profile matches taught tools** -- `memorix setup` and
+  every plugin template now run `memorix serve --mode lite`, so the tools
+  taught in generated guidance (sessions, timeline, reasoning, retention)
+  actually exist. Repo guidance marks the full-only tools
+  (`promote`, `rules_sync`, `workspace_sync`) with `MEMORIX_MODE=full`.
+- **Honest media schema** -- With the generation/transcription gates
+  closed, `memorix_media` no longer advertises `generate-image`,
+  `generate-video`, or `derive-audio` (or their parameters); agents see
+  only what the operator enabled.
+- **Config that does something** -- `[server].port` and
+  `[server].dashboardPort` are now real startup defaults for `serve-http`
+  and `dashboard`; `git.ingest_on_commit` actually gates post-commit
+  ingestion and `git.max_diff_size` caps captured diff content. The
+  never-consumed `mcpServers` key was removed from `memorix.yml`
+  (unknown keys are ignored), and `[team]`/`[hooks]` are documented as
+  parsed-but-reserved.
+
+### Fixed
+- **Guidance hygiene** -- Generated agent guidance now teaches
+  store-the-underivable, dual-channel feedback, verify-before-use, the
+  ignore contract, user-profile capture, and session-end summaries.
+- **Session search dedup** -- `memorix_search` demotes rows already shown
+  in the same session (duplicate rate 25% → 19% in the replay exam, hits
+  and token budget unchanged).
+- **Dead code removal** -- Removed the superseded slash-REPL, the legacy
+  in-memory team layer, retired TUI components, and duplicate commands
+  (about 4,600 net lines), each verified unreferenced before deletion.
+
+## [1.4.5] - 2026-08-14
+
+### Added
+- **DeepSeek Harness integration** -- `memorix setup --agent dsh` installs
+  Memorix into DeepSeek's official harness: a `@deepseek-ai/dsh-mcp-client`
+  row in `$DSH_HOME/cordis.patch.yml` (tools appear as `mcp__memorix__*`),
+  AGENTS.md guidance at the harness and project levels, and official skills
+  under `$DSH_HOME/skills` or `.dsh/skills`. Existing user patch rows are
+  preserved and installs are idempotent. DSH has no hook surface, so none is
+  written. `doctor`, `repair`, `uninstall`, and `setup --list` cover the new
+  target, and MCP checks for user-level-only adapters now run under an
+  explicit global scope (fixing the same latent skip for Trae). Native
+  validation composed the generated patch with the real
+  `@deepseek-ai/dsh@0.1.0-rc.6` launcher.
+
 ## [1.4.4] - 2026-08-14
 
 ### Added

package/CLAUDE.md

@@ -61,6 +61,10 @@ Use `memorix_resolve` when a task is done or a bug is fixed. This keeps future s
 
 ### Tools quick reference
 
+The installed `memorix serve --mode lite` surface exposes every tool below
+except the three marked `MEMORIX_MODE=full` (set that env var or `--mode full`
+to enable them).
+
 | Tool | Use when |
 |---|---|
 | `memorix_search` | Find relevant past context |
@@ -73,9 +77,9 @@ Use `memorix_resolve` when a task is done or a bug is fixed. This keeps future s
 | `memorix_session_start` | Load session context (handoff, team coordination) |
 | `memorix_timeline` | See chronological context around a memory |
 | `memorix_retention` | Check memory health and archive expired items |
-| `memorix_promote` | Turn repeated patterns into permanent skills |
-| `memorix_rules_sync` | Inspect or sync rules across agents |
-| `memorix_workspace_sync` | Inspect or migrate workspace integrations |
+| `memorix_promote` (MEMORIX_MODE=full) | Turn repeated patterns into permanent skills |
+| `memorix_rules_sync` (MEMORIX_MODE=full) | Inspect or sync rules across agents |
+| `memorix_workspace_sync` (MEMORIX_MODE=full) | Inspect or migrate workspace integrations |
 
 ## Active Work
 

package/README.md

@@ -6,7 +6,7 @@
 
 <p align="center">
   <strong>Local-first shared memory layer for AI coding agents.</strong><br>
-  One project memory system for Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and any MCP-capable agent.
+  One project memory system for Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, DeepSeek Harness, and any MCP-capable agent.
 </p>
 
 <p align="center">
@@ -171,6 +171,11 @@ Memorix connects through the interfaces each agent already supports: plugin pack
 <sub>package + MCP + hooks + skills</sub>
 </td>
 <td align="center" width="12.5%">
+<a href="https://github.com/deepseek-ai/deepseek-harness"><img src="https://github.com/deepseek-ai.png?size=120" alt="DeepSeek Harness" width="48" height="48"></a><br>
+<strong>DeepSeek Harness</strong><br>
+<sub>MCP patch + AGENTS.md + skills</sub>
+</td>
+<td align="center" width="12.5%">
 <a href="https://modelcontextprotocol.io"><img src="https://github.com/modelcontextprotocol.png?size=120" alt="Any MCP Client" width="48" height="48"></a><br>
 <strong>Any MCP Client</strong><br>
 <sub>stdio or HTTP MCP</sub>
@@ -193,7 +198,7 @@ Integration surfaces:
 | Plugin or bundle package | Installs plugin, compatible-bundle, or package files where the agent supports them | Claude Code, Codex, CodeBuddy Code, GitHub Copilot CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi |
 | Extension | Installs extension files where the agent supports them | Gemini CLI |
 | Local plugin | Installs local plugin files where the agent loads them directly | OpenCode |
-| MCP/rules config | Writes MCP, rules, steering, guidance, or hook config for IDEs and agents that expose those surfaces | Cursor, Windsurf, Kiro, Trae |
+| MCP/rules config | Writes MCP, rules, steering, guidance, or hook config for IDEs and agents that expose those surfaces | Cursor, Windsurf, Kiro, Trae, DeepSeek Harness |
 | Skills | Turns durable project knowledge into reusable task guidance | `memorix skills` and `memorix_promote` |
 | memcode | Opens the bundled terminal agent that already uses Memorix memory | `memorix` or `memcode` |
 
@@ -254,6 +259,7 @@ memorix setup --agent openclaw --global
 memorix setup --agent hermes --global
 memorix setup --agent codebuddy --global
 memorix setup --agent omp --global
+memorix setup --agent dsh --global
 ```
 
 What it installs depends on the target agent, but the goal is the same: make Memorix available wherever you open that agent without asking you to wire every repo by hand.
@@ -271,6 +277,7 @@ What it installs depends on the target agent, but the goal is the same: make Mem
 - Hermes Agent: installs into Hermes home (`%LOCALAPPDATA%\hermes` on native Windows, `~/.hermes` elsewhere, or `HERMES_HOME`), enables the plugin in `config.yaml`, registers plugin hooks, slash/CLI commands, skills, and writes MCP config.
 - CodeBuddy Code: installs a user-scope local marketplace plugin under `~/.codebuddy/memorix-local` with MCP, skills, and hooks. It does not change existing CodeBuddy model, permission, or settings files; CodeBuddy keeps third-party hook approval in its own `/hooks` flow.
 - Oh-my-Pi: installs an `omp.extensions` package with extension hook events, a `memorix` command, official skills, and writes MCP config.
+- DeepSeek Harness: writes a Memorix `@deepseek-ai/dsh-mcp-client` row into `$DSH_HOME/cordis.patch.yml` (default `~/.dsh/cordis.patch.yml`), appends guidance to the harness `AGENTS.md`, and installs official skills under `$DSH_HOME/skills`. The row follows DSH's own shipped Memorix reference, so tools appear as `mcp__memorix__*`.
 
 Need a quieter install? Add `--noHooks` for targets where setup can control hook capture separately from the host's official package entry. It keeps MCP and guidance, but skips Memorix hook capture.
 
@@ -428,7 +435,7 @@ This opens memcode, a terminal coding agent that uses the same Memorix project m
 
 Search is project-scoped by default. `scope="global"` searches across projects. The search boosts Git Memory for "what changed" questions and reasoning records for "why" questions.
 
-Long-term memory is deliberately not an automatic dump of every note. A source observation, Claim, workflow, session, and code snapshot keep their existing roles. An agent may ask `memorix_store` to create an additional long-term **candidate**, but candidates never enter task context. Use `memorix memory long-term qualify|approve|archive|supersede` to record the evidence-backed lifecycle. Only a manually created or user-confirmed `user + portable` item may be considered in another local project; project code, Git facts, tests, workflows, sessions, and observations cannot be promoted into portable user memory.
+Long-term memory is deliberately not an automatic dump of every note. A source observation, Claim, workflow, session, and code snapshot keep their existing roles. An agent may ask `memorix_store` to create an additional long-term record; an explicit request auto-qualifies and enters task briefs as a durable anchor, while hook-captured or Git-derived candidates stay pending until qualified. Approval stays an explicit operator review. Use `memorix memory long-term approve|archive|supersede` to record the evidence-backed lifecycle. Only a manually created or user-confirmed `user + portable` item may be considered in another local project; project code, Git facts, tests, workflows, sessions, and observations cannot be promoted into portable user memory.
 
 `memorix context "..."` is the default Memory Autopilot entry. It builds a compact task-lensed brief for agents: bugfix tasks lean toward tests and repros, release tasks lean toward package/changelog/build checks, onboarding tasks lean toward docs and entry points, and stale or unrelated memories stay in warning lanes instead of flooding the prompt. A normal new task does not receive an old-session dump. For an explicit continuation, `memorix resume "..."` adds only the latest useful session summary, up to three readable durable anchors, and at most one recent source-labelled host compact checkpoint. A durable anchor carries a `durable:<id>` reference, so an agent can expand the full reviewed record through `memorix_detail` only when needed. Keyword matches stay primary; when no reviewed durable item matches and an embedding provider is configured, Memorix makes one 1.8-second, no-retry semantic fallback for paraphrases or cross-language tasks. A slow or unavailable provider simply leaves the normal keyword-only Workset intact. A checkpoint is lifecycle evidence, not durable memory or a transcript backup. Agents should read the suggested files before trusting stored memory.
 
@@ -443,12 +450,15 @@ Long-term memory is deliberately not an automatic dump of every note. A source o
 | Debug HTTP MCP in the foreground | `memorix serve-http --port 3211` |
 | Inspect or manage memory directly | `memorix memory`, `memorix reasoning`, `memorix session`, `memorix ingest`, `memorix media` |
 | Manage reviewed long-term memory | `memorix memory long-term list|show|add|promote|qualify|approve|archive|supersede` |
+| Retire memories from retrieval | `memorix purge` (current project), `memorix purge --all --yes` (everything) |
 | Inspect native compaction continuity | `memorix checkpoint list|show|context|archive` |
 | Use the interactive terminal memory control plane | `memorix workbench` |
 | Use the bundled terminal agent | `memorix` or `memcode` |
 | Run orchestrated subagent work | `memorix orchestrate --goal "..."` |
 
-`memorix serve` defaults to `--mode micro` (9 tools) to keep MCP tool schemas small for agents. Use `--mode lite` for the extended solo memory surface, `--mode team` for coordination tools, or `--mode full` for advanced and compatibility tools such as checkpoint inspection.
+`memorix serve` defaults to `--mode micro` (9 tools) to keep MCP tool schemas small for agents. `memorix setup` writes `--mode lite` into the installed MCP config so every tool taught in the generated guidance is reachable. Use `--mode team` for coordination tools, or `--mode full` for advanced and compatibility tools such as checkpoint inspection.
+
+Shortcuts and aliases: `memorix search` / `remember` / `recent` are direct query shortcuts, `bg`/`bs` start the background service, `hook` runs the hook launcher, and `memorix config get|path|migrate` inspects or migrates config files.
 
 `memorix orchestrate` uses the current checkout for single-worker runs. When running multiple workers, it creates task worktrees under `.worktrees/` and merges successful task branches back. Use `--isolated` to force worktree isolation for one worker, `--no-worktree` to disable it, `--allow-dirty` to run with uncommitted changes, and `--no-auto-merge` to preserve task worktrees for manual review.
 

package/README.zh-CN.md

@@ -6,7 +6,7 @@
 
 <p align="center">
   <strong>面向 AI Coding Agent 的本地优先共享记忆层。</strong><br>
-  让 Claude Code、Codex、CodeBuddy Code、Cursor、Windsurf、Copilot、Gemini CLI、OpenCode、OpenClaw、Hermes Agent、Oh-my-Pi、Pi、Kiro、Antigravity、Trae 和任何 MCP Agent 共用同一套项目记忆。
+  让 Claude Code、Codex、CodeBuddy Code、Cursor、Windsurf、Copilot、Gemini CLI、OpenCode、OpenClaw、Hermes Agent、Oh-my-Pi、Pi、Kiro、Antigravity、Trae、DeepSeek Harness 和任何 MCP Agent 共用同一套项目记忆。
 </p>
 
 <p align="center">
@@ -170,6 +170,11 @@ Memorix 通过目标 Agent 已有的接口接入：插件包、MCP、项目规
 <sub>package + MCP + hooks + skills</sub>
 </td>
 <td align="center" width="12.5%">
+<a href="https://github.com/deepseek-ai/deepseek-harness"><img src="https://github.com/deepseek-ai.png?size=120" alt="DeepSeek Harness" width="48" height="48"></a><br>
+<strong>DeepSeek Harness</strong><br>
+<sub>MCP patch + AGENTS.md + skills</sub>
+</td>
+<td align="center" width="12.5%">
 <a href="https://modelcontextprotocol.io"><img src="https://github.com/modelcontextprotocol.png?size=120" alt="Any MCP Client" width="48" height="48"></a><br>
 <strong>Any MCP Client</strong><br>
 <sub>stdio or HTTP MCP</sub>
@@ -192,7 +197,7 @@ Memorix 通过目标 Agent 已有的接口接入：插件包、MCP、项目规
 | 插件 / Bundle / Package | 给支持插件、兼容 bundle 或 package 的 Agent 安装对应文件 | Claude Code、Codex、CodeBuddy Code、GitHub Copilot CLI、Antigravity、OpenClaw、Hermes Agent、Oh-my-Pi、Pi |
 | Extension | 给支持 extension 的 Agent 安装对应文件 | Gemini CLI |
 | 本地插件 | 给直接加载本地插件文件的 Agent 安装插件 | OpenCode |
-| MCP / rules 配置 | 给支持 MCP、rules、steering、guidance 或 hooks 的 IDE 和 Agent 写入配置 | Cursor、Windsurf、Kiro、Trae |
+| MCP / rules 配置 | 给支持 MCP、rules、steering、guidance 或 hooks 的 IDE 和 Agent 写入配置 | Cursor、Windsurf、Kiro、Trae、DeepSeek Harness |
 | Skills | 把沉淀下来的项目知识提升成可复用任务指导 | `memorix skills` 和 `memorix_promote` |
 | memcode | 打开已经接好 Memorix 记忆的内置终端 Agent | `memorix` 或 `memcode` |
 
@@ -253,6 +258,7 @@ memorix setup --agent openclaw --global
 memorix setup --agent hermes --global
 memorix setup --agent codebuddy --global
 memorix setup --agent omp --global
+memorix setup --agent dsh --global
 ```
 
 它会做的事情取决于目标 Agent，但目标是一致的：你以后在哪里打开这个 Agent，Memorix 就可以在哪里被使用，而不是让你一个仓库一个仓库重复配置。
@@ -270,6 +276,7 @@ memorix setup --agent omp --global
 - Hermes Agent：安装到 Hermes home（Windows native 默认为 `%LOCALAPPDATA%\hermes`，其他平台默认为 `~/.hermes`，也支持 `HERMES_HOME`），在 `config.yaml` 启用插件，注册 plugin hooks、slash/CLI commands、skills，并写入 MCP 配置。
 - CodeBuddy Code：安装用户级本地市场插件到 `~/.codebuddy/memorix-local`，包含 MCP、skills 和 hooks。它不会修改既有的 CodeBuddy 模型、权限或 settings 文件；第三方 hook 仍由 CodeBuddy 自己的 `/hooks` 流程确认。
 - Oh-my-Pi：安装 `omp.extensions` package，包含 extension hook 事件、`memorix` command、官方 skills，并写入 MCP 配置。
+- DeepSeek Harness：向 `$DSH_HOME/cordis.patch.yml`（默认 `~/.dsh/cordis.patch.yml`）写入一行 Memorix `@deepseek-ai/dsh-mcp-client`，向 harness 的 `AGENTS.md` 追加使用规范，并把官方 skills 安装到 `$DSH_HOME/skills`。这一行遵循 DSH 自带的 Memorix 参考配置，因此工具以 `mcp__memorix__*` 形式出现。
 
 如果你想要更安静一点的安装，可以对那些 setup 能独立控制 hook capture 的 target 加 `--noHooks`。它会保留 MCP 和使用规范，只跳过 Memorix 的 hook 自动捕获。