mirror of
https://gitcode.com/JianFeeeee/HomeAgent.git
synced 2026-11-01 14:57:38 +00:00
f33ee3e396
上一提交只在 ARCHITECTURE 里记了终端归属。本次把这条**通用原则**补到另外两份
文档，避免只读 OVERVIEW / 插件开发指南的人仍旧按旧直觉写代码。
## OVERVIEW（中英）
设计要点新增一条「业务语义留在插件层」：内核不定义业务对象（终端、命令历史、
设备状态、媒体库都是插件域）。以终端为例说明：PTY/生命周期/输出缓冲归
agentcli，WebUI/CLI 订阅总线自攒视图，内核只提供事件总线与注册面 —— 新增一类
能力不需要改内核，也不会在核心里堆出第二套业务真相。
## PLUGIN_DEV（中英）
PluginSDK 章节新增「与其它插件联动 — 走事件总线，不要依赖内核内部组件」：
- 代码示例：订阅 terminal_output + tool_call 自己攒视图
- 两条稳定事件表（谁发布、用途）
- ★ 外部插件只能订阅、不能发布（Publish 属 withheld 能力），所以「能力所有者
需要广播状态」的插件必须内置（agentcli 即此例）
- 指向 internal/pluginview 作为参考实现，并写明「视图不是权威、晚启动会缺早期
事件」
一个准确性修正：公开 SDK **没有** EventTerminalOutput 常量（属内核内部事件
类型），所以示例里外部插件用 sdk.EventType("terminal_output") 字符串订阅，
并注明内置插件可用 internal sdk 常量 —— 避免文档给出编不过的示例。
验证：四份文档代码围栏配对（74/74、0/0）；仅文档改动，无代码影响。
116 lines
8.5 KiB
Markdown
116 lines
8.5 KiB
Markdown
**中文** | [English](../en/OVERVIEW.md)
|
|
|
|
# HomeAgent — Project Overview
|
|
|
|
## What Is This
|
|
|
|
HomeAgent is a continuously-running personal intelligent Agent framework.
|
|
|
|
Core architecture: a long-running kernel process (`homed`) that connects to various IO channels (QQ, Web, CLI, etc.) through a plugin system. The kernel handles LLM orchestration, memory management, and knowledge retrieval; plugins handle all external IO — sending/receiving messages, file operations, web search, etc.
|
|
|
|
### Design Highlights
|
|
|
|
**Separation of Core Domain and Application Domain** — The kernel (core domain) performs no IO operations; all IO capabilities belong to plugins (application domain). The boundary is defined through PluginSDK:
|
|
- Plugins register tools (Tool) with the kernel for LLM invocation
|
|
- Plugins hook into the processing pipeline (Stage) to intercept/rewrite message flow at various phases
|
|
- Plugins subscribe/publish events (Event) for loosely-coupled communication
|
|
- Plugins queue or interrupt input delivery through IO API
|
|
|
|
The significance lies in clear responsibility boundaries: the kernel focuses on orchestration and memory management, while plugins handle IO implementation — the two are not coupled.
|
|
|
|
**Business semantics stay in plugins** — the kernel does not define business
|
|
objects: terminals, command history, device state and media libraries all belong to
|
|
the plugin domain. Take terminals: the PTY, session lifecycle and output buffering
|
|
all live in `agentcli`; when WebUI or CLI needs a terminal panel it **subscribes to
|
|
the event bus** (`EventTerminalOutput` + `EventToolCall`) and builds its own view
|
|
instead of reading a state component inside the kernel. The kernel offers only the
|
|
event bus and the plugin registration surface — adding a new capability does not
|
|
require touching the kernel, and no second version of business truth accumulates there.
|
|
|
|
**Three-Layer Memory Architecture** — Manages information retention across long agent runtimes through a tiered storage strategy:
|
|
- **Context Layer**: In-memory pretrained word embedding scored event window (StaticEmbedder word vectors → CosineSimilarity, TF-IDF fallback), maintains recent context in real-time, low-relevance events automatically sink to the next layer
|
|
- **Document Layer**: JSON files + TF-IDF vector-indexed temporary memory, supports explicit submission and implicit archival, cold data distills to Graph
|
|
- **Graph Layer**: SQLite graph database, persists entities and relations, BFS traversal recall, distillation pipeline extracts triples from conversations
|
|
|
|
Three progressive layers — context, cold archive, long-term graph memory — form an information decay and consolidation pipeline from short-term to persistent storage.
|
|
|
|
**Media Memory (first-class memory blocks since v1.2.0)** — Images and audio are not attachments; they are first-class nodes of memory:
|
|
- **Content-addressed store (CAS)**: addressed by digest, metadata in SQLite and blobs on disk (two-level
|
|
bucketing), identical bytes stored once. Every `Get` re-verifies the digest (silently returning corrupt
|
|
data is worse than an error).
|
|
- **Blocks carry their own multimodal vector and fingerprint**, and are retrieved directly — there is no
|
|
media marker in the body text any more.
|
|
- **No separate GC, no reference counting, no keep-set**: blocks follow the single-layer invariant —
|
|
Context → Document → Graph is a **migration** of a block, not a copy, and nothing is kept alive by
|
|
references; **deleting a block deletes its content.**
|
|
- **Reaches the plugin boundary since v1.1.1**: plugins read and write media through `InsertWithMedia` /
|
|
`InjectInputMedia`; the model attaches media via the `media_digests` argument of `memory_commit` / `doc_commit`.
|
|
- **The old mechanism was removed entirely**: the **descriptive index** — writing the vision model's
|
|
description into the body text as a `[<mime> <short digest>] <description>` marker and retrieving by it —
|
|
together with `media_refs` reference counting, was deleted in v1.2.0. A description is second-hand
|
|
information produced by a model; retrieving "someone else's rendering of the image" is worse than
|
|
retrieving the image's own vector.
|
|
|
|
## What It Actually Does
|
|
|
|
Code is in the project root, implemented in Go.
|
|
|
|
**Kernel** (`internal/agent/core/`):
|
|
- `eventloop.go` — Message loop (`eventLoop`), queuing input from the IO layer
|
|
- `process.go` / `stages.go` — Processing pipeline: memory recall → persona injection → LLM call → tool execution → output delivery, 7 stage hooks
|
|
- `toolcall.go` — Tool scheduling and execution
|
|
- `context.go` — Context management (pretrained word embedding scoring StaticEmbedder → CosineSimilarity, TF-IDF fallback), automatic pruning of low-relevance events
|
|
- LLM calls abstracted through the Provider interface, with multi-source automatic fallback
|
|
|
|
**Memory System** (`internal/memory/`):
|
|
- **GraphDB** (`graph.go`) — SQLite, entities + relations tables, BFS traversal
|
|
- **Document Store** (`document/document.go`) — Temporary memory, JSON files + TF-IDF vector index, consume-on-read
|
|
- **Text Memory** (`text/text.go`) — Raw conversation logs, JSONL file rotation
|
|
- **Social Store** (`social/social.go`) — Persona traits + relationship network, wraps GraphDB
|
|
- **Memory Indexer** (`indexer.go`) — Auto-vectorizes GraphDB entities, recalls and injects into system prompt on user input
|
|
|
|
**Knowledge Base** (`internal/knowledge/knowledge.go`):
|
|
- File system directory `knowledge/<name>/content.md`
|
|
- TF-IDF vector search, independent index instance from the memory system
|
|
- LLM operates via three tools: `knowledge_search` / `knowledge_create` / `knowledge_list`
|
|
|
|
**Plugin System** (`internal/plugin/`):
|
|
- Built-in plugins: Go `init()` self-registration, compiled into kernel
|
|
- External plugins (since v1.0.0): compiled to an ordinary Go binary `plugin.bin`, spawned by the
|
|
kernel as an **independent subprocess**, communicating over stdio JSON-RPC (control plane) +
|
|
a shared memory segment (data plane) + an event ring (notification plane); Lua script plugins are
|
|
also supported (the C ABI shared-library channel, `-buildmode=c-shared`, was removed entirely in v1.0.0)
|
|
- PluginSDK (`internal/sdk/`) defines four channels: RegisterTool / RegisterStage / Subscribe / RegisterOutputChannel
|
|
- 7 stage hooks: on_input → pre_action → post_action → before_toolcall → after_toolcall → before_output → after_output
|
|
|
|
**LLM Provider** (`internal/agent/api/provider.go`):
|
|
- Provider interface: Name / Chat / ChatStream / MaxContextTokens
|
|
- Single implementation, `LuaAdaptedProvider`: every source goes through a Lua adapter script that
|
|
transforms requests/responses; adapter scripts live in `internal/lua/adapters/`, one `.lua` per protocol
|
|
- 10 built-in adapters: deepseek / openai / anthropic / gemini / mistral / groq / github / kimicode / ollama / server
|
|
- Sources (`core.llm.sources.<name>.*`) are configured at deploy time — the count is deployment-specific
|
|
and is not tied to the number of built-in adapters
|
|
|
|
**WebUI** (`internal/plugins/webui/`):
|
|
- Embedded SPA dashboard (`dashboard.html` packaged via `//go:embed`)
|
|
- REST API: status query, configuration management, memory operations, knowledge management, plugin management
|
|
- OpenAI API-compatible `/v1/chat/completions` endpoint
|
|
- SSE event stream `/api/v1/chat/events`
|
|
|
|
**ClawHub Adapter** (`internal/plugins/clawhubadapter/`):
|
|
- Unified loader for OC plugins (Node.js), Python sidecar, JS sidecar, and SKILL plugins
|
|
- RegistryDispatcher pattern: routes registration notifications to Tool/Provider/Channel/Stage registries
|
|
- ClawHub marketplace search and install: `clawhubadapter_search` / `clawhubadapter_npm_install`
|
|
- 9 provider types mapped to LLM-accessible tools (image generation, web search, speech, etc.)
|
|
- OC channels auto-registered as IO devices with text/file/image/audio capability flags
|
|
|
|
|
|
## Project Status
|
|
|
|
Core functionality is operational. Plugin system and SDK are ready for independent external plugin development.
|
|
|
|
- Built-in plugins (13): webui / cli / agentcli / cfgmgr / healthcheck / kbtree / multimodal / pluginmgr / clawhubadapter / remotedevice / skillmgr / seemedia / seq
|
|
- Criterion: **a plugin stays built-in only if it requires internal-SDK-only capabilities**; everything else ships as an .hmap external plugin (see ARCHITECTURE)
|
|
- External plugin examples ([homeagent-sdk](https://github.com/JianFeeeee/homeagentsdk) repo `example/`, both Go and Lua types): qq / files / a2a / ai_image / bili / browser / calendar / editdoc / memo / music / ocr / rss / sanitizer / weather / luademo
|
|
- Distribution: `.hmap` plugin package format, installable via WebUI
|