mirror of
https://gitcode.com/JianFeeeee/HomeAgent.git
synced 2026-10-15 12:15:16 +00:00
6d38a164eb
## 背景 仓库早已迁移到 GitHub（`github.com/JianFeeeee/HomeAgent`，CI/CD 都在那边跑）， gitcode 保留为**国内只读镜像**（`ci.yml` 的 sync-gitcode-main 快进推送）。 但 go.mod 的 module 路径一直是 `gitcode.com/JianFeeeee/...` —— 既与权威源 不符，`meta.SourceURL`（AGPL §13 的源码提供入口）也指向镜像而非实际运行的代码。 ## 关键区分（这是本次改动安全的前提） 两个 module 是**不同**的，影响面差一个数量级： | module | 谁依赖 | 改它的后果 | |---|---|---| | `.../HomeAgent`（主仓） | **只有主仓自己** | 内部重构，零外部影响 | | `.../homeagent-sdk`（SDK 仓） | 主仓 49 文件 + 所有外部插件 | 需重编插件 | ★ 实测确认：**插件不 import 主仓 module**（`strings qq/plugin.bin | grep HomeAgent` = 0）， 只依赖 SDK 仓。而插件与内核的边界是 **RPC 方法名字符串** （`plugin.init` / `tool.invoke`…，见 proc/protocol.go），**与 Go module 名无关**。 ⇒ module 改名**不改变任何 wire 协议**，现网已装的插件照常运行。 SDK 的 GitHub 仓名是 `homeagentsdk`（无连字符），module 路径必须与之精确匹配， 否则 `go get` 会因路径不符失败，故取 `github.com/JianFeeeee/homeagentsdk`。 ## 改动 - `go.mod` / `go.sum`：两个 module 路径 + require/replace - 277 个 Go 文件 + Makefile + 打包脚本的 import 与 ldflags 路径 - SDK 仓 `meta.CoreModule`、`tools/hmapdev` 的 module 声明与工程模板 - 对外文档/链接的仓库地址（README、PLUGIN_DEV、OVERVIEW 等） ## 明确**保留** gitcode 的地方（镜像机制，不能动） - `GITCODE_TOKEN`、`GC_URL="…@gitcode.com"`（CI 同步 job） - `gitcode.com/api/v5/...`（release 附件上传） - git remote `gitcode`（镜像拉取/推送） - `docs/zh/ci-cd-runbook.md`（整篇讲镜像运维） ## 验证 - `go build ./...` / `go vet ./...` 绿 - `go test ./... -count=1` → 48 包 ok / 0 FAIL - hmapdev 工具链编译通过（`third_party/homeagent-sdk/tools/hmapdev`） - 全仓残留检查：module 形态的 `gitcode.com/JianFeeeee` = 0 - 镜像机制抽验：GC_URL / @gitcode / api/v5 / remote 均完好 ## 顺带修正 `hmapdev/templates.go` 的注释此前写「gitcode 的模块不在 proxy.golang.org 上」—— module 已迁 GitHub，该论断不再成立。改为如实说明**为何仍默认 replace 到本机 SDK**： 离线可构建、避免版本漂移、内网可用。理由与托管地无关，故 replace 保留。
106 lines
7.6 KiB
Markdown
106 lines
7.6 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.
|
|
|
|
**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
|
|
- 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: webui / cli / timer / cmd / mcp / agentcli / healthcheck / pluginmgr / clawhubadapter / files / cfgmgr
|
|
- 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
|