mirror of
https://gitcode.com/JianFeeeee/HomeAgent.git
synced 2026-09-21 09:28:14 +00:00
docs: README 更新到 v1.2.0，并纠正已在 v1.2.0 删除的机制
README 的「项目状态」停在 **v1.1.1**，而且其中两条描述与当前实现**相反**： 「媒体以 `[<mime> <短digest>] <描述>` 标记存在于纯文本记忆中，描述是可检索的 语义记忆」与「引用计数式 GC（有引用者绝不删）」——这两套机制正是 v1.2.0 拆掉的。 本次不重写历史条目（它们记录了演进），而是： 1. 「项目状态」顶部新增 **v1.2.0** 条目：统一多模态向量空间（模型中立 SPI + Chinese-CLIP 默认，含「纯文本语义弱于 MLLM 型嵌入器」这一已知代价）、 媒体升为图记忆一等节点（并写明具体删掉了什么）、数据面全量走共享内存 （协议 2、不支持滚动升级）、注入标志位、发行包默认启用 ONNX 且随包模型、 homed 改走 WSL2、以及三个安装链静默失败的修复。 2. 在 v1.2.0 条目后加一条显式提示：下方历史条目中的「描述式索引」与 「媒体引用计数式 GC」**已在 v1.2.0 移除**——避免读者按旧文档理解现行行为。 3. 「下载」：Windows 安装器的版本号改到 v1.2.0，并写明自 v1.2.0 起因 homed 不再支持 Windows 原生，安装器改为引导到 WSL2 并在其中按 Linux 方式安装； 同时注明安装器含 AGPL 许可页。 中英双份同步。SDK 仓 README 另在 SDK 仓提交（d893bfa）。
This commit is contained in:
JianFeeeee
29
README.md
29
README.md
@ -195,6 +195,33 @@ internal/
|
||||
|
||||
## 项目状态
|
||||
|
||||
**v1.2.0** — 统一多模态向量空间 + 媒体升为图记忆一等节点 + 数据面全量迁到共享内存。
|
||||
|
||||
- **模型中立的统一向量空间**：内核不再适配任何具体模型，只提供公共 provider SPI
|
||||
（`pkg/embedding`：`Modality` / `Input{Data,MIME}` / `Info{Dimension,Fingerprint,Modalities}`
|
||||
+ 名字注册表），实现在 `providers/*`。默认 **Chinese-CLIP ViT-B/16** —— text 与 image
|
||||
落在**同一空间**（512 维、指纹 `cd2a495cf990`、Apache-2.0、独立实测常驻约 1.15GB）；
|
||||
`qwen3vl` 保留（2048 维、常驻约 9.4GB，供内存充足或将来要视频的机器切回）。
|
||||
文本检索仍由既有词向量 / TF-IDF 兜底：CLIP 双塔的**纯文本语义弱于 MLLM 型嵌入器**，
|
||||
这是已知并写进文档的代价。
|
||||
- **媒体是图数据库的一等节点与边**：**彻底删除**「用文本描述式索引图片」这套将就机制，
|
||||
以及 `media_refs` 与媒体引用计数。记忆块遵循单层不变量——Context → Document → Graph
|
||||
是块的**迁移**，不是复制、也不靠引用保活。
|
||||
- **数据面全部走共享内存**（工具调用帧 / Cleaner / 输入输出通道 / 媒体块 / 文档与知识正文），
|
||||
RPC 只传偏移描述符；**RPC 协议升到 2**，fd3 布局改变，**不支持滚动升级**——
|
||||
内核与全部插件必须同批重建、同批安装，存量插件须用新版 `plugindev` 重编。
|
||||
- 注入可声明 `InjectOptions{NoMemory, ContextPolicy}`（**默认仍记入记忆、默认不裁剪**）；
|
||||
裁剪必须显式声明，且先经插件注册的 `Cleaner`。SDK 1.2.0 相对 1.1.0 **纯追加**。
|
||||
- **发行包默认启用** ONNX 向量空间，并把模型（754MB）与 ONNX Runtime（24MB）随
|
||||
server/full 包发布；`homed` 放弃 Windows 原生支持改走 WSL2；jieba 词库内嵌进二进制。
|
||||
- 修掉三个**安装链静默失败**：`initconfig` 因 `CGO_ENABLED=0` 是空操作（打印凭据却一个字节
|
||||
没写）、全新安装被误判「已有配置」而整体跳过默认值播种（装完 0 插件）、deb 的 `postinst`
|
||||
查错 unit 路径导致 `enable` 从未执行。
|
||||
- 自本版起以 **AGPL-3.0-only** 发布（含网络条款；插件静态链接 SDK 故须同许可，见「许可」）。
|
||||
|
||||
> 以下历史条目保留原文以呈现演进，其中两条机制**已在 v1.2.0 移除**：
|
||||
> 「媒体以 `[<mime> <短digest>] <描述>` 标记参与检索」（描述式索引）与「媒体引用计数式 GC」。
|
||||
|
||||
**v1.1.1** — 多模态贯通**插件边界**。v1.1.0 让记忆系统支持了二进制多媒体节点，但那条链路只对内核自己开放；本版打通到插件与模型。公开 SDK 新增媒体字段与三个媒体注入接口（配套 [SDK v1.1.0](https://gitcode.com/JianFeeeee/homeagent-sdk/releases/tag/v1.1.0)，整条 1.1.x 线共用），内核实现对应四个 RPC。桥接层此前在**静默裁字段**：插件交进来的 `Confidence`/类型/`SentenceText` 全被丢弃、`Doc` 只留三个字段、`Remove` 不解引用（媒体永久算「被引用」，GC 收不掉）。`processTextInput`/`processMediaInput` 归一成一条 `processInput`，媒体路径由此获得它一直缺的去重、`no_memory`、通道 `Cleaner`、中断语义、`EventRawInput`。修掉三处真实缺陷：**用户发的图从来没出现在 WebUI 聊天记录里**（媒体路径发布 map 而订阅方断言 string）、**`memory_commit` 的 `sentence_text` 从未暴露给模型**（而它是媒体绑定链的必经环节）、**`PluginSDK` 两处并发竞态**（`-race` 实测 11 处，插件重载瞬间偶发 nil 解引用崩溃）。
|
||||
|
||||
**v1.1.0** — 记忆系统支持**二进制多媒体节点**。内容寻址媒体存储（CAS + SQLite 元数据 + 磁盘 blob，`Get` always 重校 digest），贯通 L0（上下文事件）/L2（文档）/L3（图谱句子）三层，引用计数式 GC（有引用者绝不删）。视觉模型生成的描述文本是持久语义记忆，blob 只是可被容量 GC 淘汰的缓存。
|
||||
@ -224,7 +251,7 @@ internal/
|
||||
| **client** | waiter + 桌面 GUI | 连接远程 HomeAgent |
|
||||
|
||||
- Linux：`.deb`（amd64/arm64）、`.rpm`（x86_64）、`.tar.gz`
|
||||
- Windows：`HomeAgent_v1.1.1_{Full,Server,Client}_win64.exe`（NSIS 安装向导）
|
||||
- Windows：`HomeAgent_v1.2.0_{Full,Server,Client}_win64.exe`（NSIS 安装向导，含 AGPL 许可页）。自 v1.2.0 起因 `homed` 不再支持 Windows 原生（依赖 fd 继承与共享内存段内偏移解引用），安装器改为引导到 **WSL2**，并把 Linux 包送进发行版里按 Linux 方式安装。
|
||||
- 免安装：`homeagent-bin-<os>_<arch>.tar.gz`（含 homed/waiter/initconfig）
|
||||
- 校验：`SHA256SUMS`
|
||||
|
||||
|
||||
36
README_EN.md
36
README_EN.md
@ -184,6 +184,40 @@ External plugin development: see [homeagent-sdk](https://gitcode.com/JianFeeeee/
|
||||
|
||||
## Project Status
|
||||
|
||||
**v1.2.0** — unified multimodal vector space, media promoted to first-class graph memory, and the whole data plane moved into shared memory.
|
||||
|
||||
- **Model-neutral unified embedding space**: the kernel no longer adapts to any specific model.
|
||||
It exposes only a public provider SPI (`pkg/embedding`: `Modality` / `Input{Data,MIME}` /
|
||||
`Info{Dimension,Fingerprint,Modalities}` + a name registry), with implementations under
|
||||
`providers/*`. Default: **Chinese-CLIP ViT-B/16** — text and image land in the **same space**
|
||||
(512-dim, fingerprint `cd2a495cf990`, Apache-2.0, ~1.15GB RSS measured standalone);
|
||||
`qwen3vl` is kept (2048-dim, ~9.4GB) for machines with headroom or future video. Text search
|
||||
still falls back to the existing word-vector / TF-IDF path — a CLIP dual tower's pure-text
|
||||
semantics are **weaker than an MLLM-style embedder**, a cost documented rather than hidden.
|
||||
- **Media are first-class nodes and edges in the graph DB**: the "index images via generated
|
||||
text descriptions" stopgap, `media_refs` and media reference counting are **removed**.
|
||||
Memory blocks follow a single-layer invariant — Context → Document → Graph is a **migration**,
|
||||
not a copy, and not kept alive by references.
|
||||
- **The entire data plane goes through shared memory** (tool-call frames, Cleaners, input/output
|
||||
lanes, media blocks, document and knowledge bodies); RPC carries only offset descriptors.
|
||||
**RPC protocol is now 2**: the fd3 layout changed and there is **no rolling upgrade** —
|
||||
kernel and all plugins must be rebuilt and installed together.
|
||||
- Injections can declare `InjectOptions{NoMemory, ContextPolicy}` (**defaults: still recorded,
|
||||
not pruned**); pruning must be requested explicitly and goes through the plugin's registered
|
||||
`Cleaner`. SDK 1.2.0 is **purely additive** over 1.1.0.
|
||||
- **Release packages enable the ONNX space by default** and bundle the model (754MB) plus
|
||||
ONNX Runtime (24MB) in the server/full packages; `homed` drops native Windows support in
|
||||
favour of WSL2; the jieba dictionary is embedded in the binary.
|
||||
- Fixed three **silent install-chain failures**: `initconfig` was a no-op (`CGO_ENABLED=0` stub)
|
||||
that printed credentials without writing any, fresh installs were misdetected as "already
|
||||
configured" so default seeding was skipped entirely (0 plugins installed), and the deb
|
||||
`postinst` looked for the unit in the wrong path so `enable` never ran.
|
||||
- Licensed **AGPL-3.0-only** from this version on (network clause included; statically linked
|
||||
plugins must match — see License).
|
||||
|
||||
> The historical entries below are kept verbatim to show the evolution; two mechanisms in them
|
||||
> were **removed in v1.2.0**: text-description-based media indexing, and reference-counted media GC.
|
||||
|
||||
**v1.1.1** — Multimodal reaches the **plugin boundary**. v1.1.0 gave the memory system binary
|
||||
multimedia nodes, but that path was open only to the kernel itself; this release opens it to
|
||||
plugins and the model. The public SDK gains media fields and three media injection methods
|
||||
@ -231,7 +265,7 @@ semantic memory; the blob is only a cache that capacity GC may evict.
|
||||
| **client** | waiter + desktop GUI | Connecting to a remote HomeAgent |
|
||||
|
||||
- Linux: `.deb` (amd64/arm64), `.rpm` (x86_64), `.tar.gz`
|
||||
- Windows: `HomeAgent_v1.1.1_{Full,Server,Client}_win64.exe` (NSIS installer)
|
||||
- Windows: `HomeAgent_v1.2.0_{Full,Server,Client}_win64.exe` (NSIS installer, includes the AGPL license page). Since v1.2.0 `homed` no longer supports native Windows (it relies on fd inheritance and in-segment offset dereferencing), so the installer bootstraps **WSL2** and installs the Linux packages inside the distribution the same way a Linux host would.
|
||||
- Portable: `homeagent-bin-<os>_<arch>.tar.gz` (homed/waiter/initconfig)
|
||||
- Verification: `SHA256SUMS`
|
||||
|
||||
|
||||
Reference in New Issue
Block a user