mirror of
https://gitcode.com/JianFeeeee/HomeAgent.git
synced 2026-09-21 17:38:10 +00:00
配套 SDK 提交:homeagent-sdk ba49dfd(公开 API 纯追加,无签名变更)。
本仓第三方的库镜像同步至该版本,以保证全新 clone 能编译。
## 1. 注入标志位(内核侧)
- 7 条注入路径(排队/中断/同步 × 纯文本/带媒体 + 旧 NoMem 变体)解析并转发
no_memory / context_policy / cleaner_name;策略在入口**校验**,
非法值报错而不是静默降级成 none(降级会让调用方以为自己声明的裁剪在生效)。
- 新增 validateContextPolicy(与 tool.register 同一套规则)与 pubSdkInjectOpts。
- input.register 不再手写字段白名单重建 ChannelDef,改为整体传递 + 补 ContextPolicy。
- io 层:applyInjectOpts 把标志位写进事件 payload,仅非零时写
(零值与旧 payload 逐字节一致,事件订阅方与旧内核都不受影响)。
- ioAdapter / procCore / internal-sdk 别名补齐六个 *Opts 实现。
## 2. 修掉「输入无条件裁剪」这个真缺陷
eventloop 此前对**每条非中断输入**都调 `context.Prune(...)`:破坏性(低相关事件被
归档移出上下文)且无法从调用点看出是谁触发的。改为 pruneOnInput/pruneDeclared:
优先级:注入点声明(payload.context_policy)> 通道声明(ChannelDef.ContextPolicy)
> 默认**不裁剪**
查询向量仍取清洗后的内容;新增 cleanInputFor 解析清洗文本,优先级为
注入点声明的 cleaner(cleaner_name)> 按 source 查到的通道 cleaner > 原文,
名字查不到时**记日志再回退**(注入是 fire-and-forget,插件看不到错误,
至少要在内核日志留下「你声明的清洗没生效」的痕迹)。
## 3. jieba 词库内嵌(修「猜 GOMODCACHE → 静默失效」)
原 jiebaDictDir() 去猜 GOMODCACHE/GOPATH/~/go/pkg/mod,部署机上通常没有 Go 模块
缓存 → GetJieba() 返回 nil → 分词/关键词提取/NLP 依存解析(进而 doc→graph 三元组
抽取)/静态词向量 tokenizer **一律静默返回空列表**,只有一行日志。本机看起来正常
只因开发机与生产机重合、恰好有那份缓存。
现在词库随二进制分发:internal/memory/jiebadict/ 5 文件约 11.6MB + go:embed,
按**内容哈希**命名缓存目录落盘(词库升级不复用旧文件),已齐全则跳过写入。
模块缓存降为兜底。homed 体积 32MB。
顺带确认(并有测试佐证):gojieba 的 Tag() 不需要 pos_dict/ 目录——
cppjieba 的 PosTagger 从主词典每行的词性列取 tag。
## 4. homed 放弃 Windows 原生,改走 WSL2
插件体系依赖「继承的 fd」+「统一共享内存区的段内偏移解引用」,Windows 既无 fd
继承语义,其句柄模型也无法表达后者;强行适配等于再维护一套平台专属 ABI
(C ABI 时代三套 ABI 并存曾导致改写型插件在某平台静默失效)。
- cmd/homed/platform_{windows,other}.go:原生 Windows 启动即拒绝并打印 WSL2 指引。
- internal/plugin/proc/shmalloc_windows.go:allocShm 直接返回「请用 WSL2」,
**不返回半可用的段**(与 shmalloc_other.go 同风格:未支持平台显式报错);
procEnvForShm 返回 nil。顺手修掉两处长期编译错误
(cryptorand→rand、h.evData→h.unified.evtData),使 GOOS=windows 至少能编译。
注:homed 本就编不出 Windows——internal/memory 依赖 cgo-only 的 gojieba。
- deploy/packaging/installer.nsi:不再安装 homed.exe/initconfig.exe,改为携带
**linux payload** 并调用新的 install-via-wsl.ps1;退出码 20/21 表示
「需先装 WSL/发行版」,走指引而非报错。
- deploy/packaging/windows/install-via-wsl.ps1(新):检测 WSL → 引导安装 →
确保 WSL2 → 送包进发行版 → 在 WSL 内按 Linux 方式安装。**复用 Linux 包与
linux/setup.sh**,不另写一套安装逻辑;落点与 deb 布局统一
(/usr/bin/homed + /usr/lib/homeagent/setup.sh)。
- deploy/packaging/linux/setup.sh:API Key 允许 HOMEAGENT_API_KEY 覆盖
(否则安装器界面显示一份、config.db 里另一份 → 登录不上)。
- deploy/packaging/build.sh:windows 目标只构建 waiter + gui,并新增
stage_linux_payload 把 Linux 包暂存给安装器;homed/initconfig 在 windows
目标下明确拒绝。
## 5. 插件调用点统一写明意图
- webui 的 OpenAI 兼容端点(固定提示词模板)→ InjectTextSyncNoMemory。
- agentcli 的 5 处纯状态通知(已启动/超时/执行结束/进程退出/读取结束)→ NoMemory;
**带输出**的 2 处(定时反馈、有新输出)刻意保留记忆并注明理由。
- timer 的定时提醒 → NoMemory(中断本来也隐含 NoMemory,这里是写明意图)。
## 6. 版本
meta.Version 仍为 1.2.0(main 是下一个未发布中版本);
SDKCompatibleVersion 1.1.0 → **1.2.0**(本内核已实现 SDK 1.2.0 全部新增方法)。
## 测试
- core:默认不裁剪(无声明/none/空)、通道 opt-in、注入点双向覆盖通道、
nil context/io 安全、cleaner 优先级与未知名回退。
- io:零值 opts 与历史 payload 逐键相同;text/中断/媒体三类注入标志位都落到
payload;旧方法仍生效。
- proc:validateContextPolicy 只接受 ""/none/prune,报错含位置与实际值;
**跨进程** e2e——testdata 插件经 io.injectText 送出三个标志位,断言它们穿过 RPC
到达内核。
- memory:模块缓存不可见时内嵌词库仍可用(分词与 POS 内容词均非空)、
落盘幂等、内容哈希稳定。
验证:go build ./... / go vet ./... / go vet -tags onnxruntime ./...
go test -short ./internal/memory/... ./internal/nlp/... ./internal/plugin/...
./internal/agent/{core,io}/... ./pkg/...
501 lines
11 KiB
Go
501 lines
11 KiB
Go
package main
|
||
|
||
import (
|
||
"encoding/json"
|
||
"fmt"
|
||
"net/http"
|
||
"os"
|
||
"path/filepath"
|
||
"sort"
|
||
"strconv"
|
||
"strings"
|
||
"sync"
|
||
"time"
|
||
|
||
sdk "gitcode.com/JianFeeeee/homeagent-sdk/sdk"
|
||
"github.com/mmcdole/gofeed"
|
||
)
|
||
|
||
const injectDedupWindow = 5 * time.Minute
|
||
|
||
type FeedSub struct {
|
||
URL string `json:"url"`
|
||
Title string `json:"title"`
|
||
AddedAt string `json:"added_at"`
|
||
Interval int `json:"interval"`
|
||
}
|
||
|
||
type Plugin struct {
|
||
name string
|
||
sdk *sdk.PluginSDK
|
||
client *http.Client
|
||
fp *gofeed.Parser
|
||
dataDir string
|
||
mu sync.RWMutex
|
||
feeds []FeedSub
|
||
seenGUIDs map[string]bool
|
||
injected map[string]time.Time
|
||
stopCh chan struct{}
|
||
stopOnce sync.Once
|
||
wg sync.WaitGroup
|
||
pollTicker *time.Ticker
|
||
}
|
||
|
||
func NewPluginFactory(name string, config map[string]interface{}) (sdk.Plugin, error) {
|
||
return &Plugin{name: name}, nil
|
||
}
|
||
|
||
func (p *Plugin) Name() string { return p.name }
|
||
|
||
func getSetting[T string | int64 | float64](s sdk.SettingsAPI, key string, fallback T) T {
|
||
v, err := s.Get(key)
|
||
if err != nil || v == nil {
|
||
return fallback
|
||
}
|
||
switch any(fallback).(type) {
|
||
case string:
|
||
if sv, ok := v.(string); ok {
|
||
return any(sv).(T)
|
||
}
|
||
case int64:
|
||
switch val := v.(type) {
|
||
case float64:
|
||
return any(int64(val)).(T)
|
||
case string:
|
||
if n, err := strconv.ParseInt(val, 10, 64); err == nil {
|
||
return any(n).(T)
|
||
}
|
||
}
|
||
case float64:
|
||
switch val := v.(type) {
|
||
case float64:
|
||
return any(val).(T)
|
||
case string:
|
||
if n, err := strconv.ParseFloat(val, 64); err == nil {
|
||
return any(n).(T)
|
||
}
|
||
}
|
||
}
|
||
return fallback
|
||
}
|
||
|
||
func readArg(args map[string]interface{}, key string) string {
|
||
if v, ok := args[key]; ok && v != nil {
|
||
if s, ok := v.(string); ok {
|
||
return s
|
||
}
|
||
}
|
||
return ""
|
||
}
|
||
|
||
func readArgInt(args map[string]interface{}, key string, fallback int) int {
|
||
if v, ok := args[key]; ok && v != nil {
|
||
switch n := v.(type) {
|
||
case float64:
|
||
return int(n)
|
||
case int64:
|
||
return int(n)
|
||
}
|
||
}
|
||
return fallback
|
||
}
|
||
|
||
func (p *Plugin) Start(s *sdk.PluginSDK) error {
|
||
s.SetAutoRestart(true)
|
||
p.sdk = s
|
||
p.client = &http.Client{Timeout: 30 * time.Second}
|
||
p.fp = gofeed.NewParser()
|
||
p.stopCh = make(chan struct{})
|
||
p.seenGUIDs = make(map[string]bool)
|
||
p.injected = make(map[string]time.Time)
|
||
p.feeds = []FeedSub{}
|
||
|
||
dataDirVal, err := s.Settings().GetCore("core.daemon.data_dir")
|
||
if err != nil || dataDirVal == "" {
|
||
dataDirVal = "."
|
||
}
|
||
p.dataDir = filepath.Join(fmt.Sprint(dataDirVal), "rss")
|
||
if err := os.MkdirAll(p.dataDir, 0755); err != nil {
|
||
fmt.Printf("[%s] mkdir %s: %v\n", p.name, p.dataDir, err)
|
||
}
|
||
p.loadData()
|
||
|
||
// 卸载(删除)时清理订阅数据目录;重载不触发
|
||
s.RegisterOnRemoveHandler(p.cleanupData)
|
||
|
||
s.Settings().RegisterDef(sdk.ConfigDef{
|
||
Key: "poll_interval", Default: "30", Type: "string",
|
||
DisplayName: "Poll Interval", Description: "Default polling interval in minutes (default: 30)",
|
||
Category: "rss",
|
||
})
|
||
|
||
tp := p.name + "_"
|
||
s.RegisterTool(tp+"subscribe", sdk.ToolDef{
|
||
Name: tp + "subscribe", Description: "Subscribe to an RSS/Atom feed URL",
|
||
NoMemory: true,
|
||
Parameters: map[string]interface{}{
|
||
"type": "object",
|
||
"properties": map[string]interface{}{
|
||
"url": map[string]interface{}{"type": "string", "description": "Feed URL"},
|
||
"interval": map[string]interface{}{"type": "integer", "description": "Poll interval in minutes (default: 30, minimum: 5)"},
|
||
},
|
||
"required": []string{"url"},
|
||
},
|
||
}, p.handleSubscribe)
|
||
|
||
s.RegisterTool(tp+"unsubscribe", sdk.ToolDef{
|
||
Name: tp + "unsubscribe", Description: "Unsubscribe from a feed",
|
||
NoMemory: true,
|
||
Parameters: map[string]interface{}{
|
||
"type": "object",
|
||
"properties": map[string]interface{}{
|
||
"url": map[string]interface{}{"type": "string", "description": "Feed URL to unsubscribe"},
|
||
},
|
||
"required": []string{"url"},
|
||
},
|
||
}, p.handleUnsubscribe)
|
||
|
||
s.RegisterTool(tp+"list", sdk.ToolDef{
|
||
Name: tp + "list", Description: "List all subscribed feeds",
|
||
Parameters: map[string]interface{}{
|
||
"type": "object",
|
||
"properties": map[string]interface{}{},
|
||
},
|
||
}, p.handleList)
|
||
|
||
s.RegisterTool(tp+"check_now", sdk.ToolDef{
|
||
Name: tp + "check_now", Description: "Manually check all feeds for new articles now",
|
||
NoMemory: true,
|
||
Parameters: map[string]interface{}{
|
||
"type": "object",
|
||
"properties": map[string]interface{}{},
|
||
},
|
||
}, p.handleCheckNow)
|
||
|
||
pollMin := int(getSetting(s.Settings(), "poll_interval", int64(30)))
|
||
if pollMin < 5 {
|
||
pollMin = 5
|
||
}
|
||
p.pollTicker = time.NewTicker(time.Duration(pollMin) * time.Minute)
|
||
|
||
p.wg.Add(1)
|
||
go p.pollLoop()
|
||
|
||
fmt.Printf("[%s] started (%d feeds, poll every %dm)\n", p.name, len(p.feeds), pollMin)
|
||
return nil
|
||
}
|
||
|
||
func (p *Plugin) Stop() error {
|
||
p.stopOnce.Do(func() { close(p.stopCh) })
|
||
p.pollTicker.Stop()
|
||
p.wg.Wait()
|
||
p.saveData()
|
||
fmt.Printf("[%s] stopped\n", p.name)
|
||
return nil
|
||
}
|
||
|
||
func (p *Plugin) pollLoop() {
|
||
defer p.wg.Done()
|
||
|
||
p.checkAllFeeds()
|
||
|
||
for {
|
||
select {
|
||
case <-p.pollTicker.C:
|
||
p.checkAllFeeds()
|
||
case <-p.stopCh:
|
||
return
|
||
}
|
||
}
|
||
}
|
||
|
||
func (p *Plugin) checkAllFeeds() {
|
||
p.mu.RLock()
|
||
feeds := make([]FeedSub, len(p.feeds))
|
||
copy(feeds, p.feeds)
|
||
p.mu.RUnlock()
|
||
|
||
for _, feed := range feeds {
|
||
select {
|
||
case <-p.stopCh:
|
||
return
|
||
default:
|
||
}
|
||
p.checkFeed(feed)
|
||
}
|
||
}
|
||
|
||
func (p *Plugin) checkFeed(sub FeedSub) {
|
||
parsed, err := p.fp.ParseURL(sub.URL)
|
||
if err != nil {
|
||
return
|
||
}
|
||
|
||
title := parsed.Title
|
||
if title == "" {
|
||
title = sub.URL
|
||
}
|
||
|
||
var newArticles []*gofeed.Item
|
||
for _, item := range parsed.Items {
|
||
guid := item.GUID
|
||
if guid == "" {
|
||
guid = item.Link
|
||
}
|
||
if guid == "" {
|
||
continue
|
||
}
|
||
guid = sub.URL + "|" + guid
|
||
p.mu.RLock()
|
||
seen := p.seenGUIDs[guid]
|
||
p.mu.RUnlock()
|
||
if !seen {
|
||
newArticles = append(newArticles, item)
|
||
}
|
||
}
|
||
|
||
if len(newArticles) == 0 {
|
||
return
|
||
}
|
||
|
||
now := time.Now()
|
||
toInject := make([]*gofeed.Item, 0, len(newArticles))
|
||
p.mu.Lock()
|
||
for _, item := range newArticles {
|
||
guid := item.GUID
|
||
if guid == "" {
|
||
guid = item.Link
|
||
}
|
||
if guid == "" {
|
||
continue
|
||
}
|
||
key := sub.URL + "|" + guid
|
||
if t, ok := p.injected[key]; ok && now.Sub(t) < injectDedupWindow {
|
||
continue
|
||
}
|
||
p.injected[key] = now
|
||
p.seenGUIDs[key] = true
|
||
toInject = append(toInject, item)
|
||
}
|
||
p.mu.Unlock()
|
||
|
||
if len(toInject) == 0 {
|
||
return
|
||
}
|
||
|
||
var lines []string
|
||
lines = append(lines, fmt.Sprintf("📡 %s (%s) — %d 篇新文章:", title, sub.URL, len(toInject)))
|
||
for _, item := range toInject {
|
||
pubDate := ""
|
||
if item.PublishedParsed != nil {
|
||
pubDate = item.PublishedParsed.Format("01-02 15:04")
|
||
}
|
||
line := fmt.Sprintf(" • %s", item.Title)
|
||
if pubDate != "" {
|
||
line += fmt.Sprintf(" [%s]", pubDate)
|
||
}
|
||
if item.Link != "" {
|
||
line += "\n " + item.Link
|
||
}
|
||
lines = append(lines, line)
|
||
}
|
||
|
||
// 中断注入是「系统通知」,NoMemory 写明意图:这类提醒不参与记忆计算,
|
||
// 原文仍进上下文(模型当轮看得到)。
|
||
p.sdk.InjectInterruptTextOpts("rss", "rss", strings.Join(lines, "\n"),
|
||
sdk.InjectOptions{NoMemory: true})
|
||
p.saveData()
|
||
}
|
||
|
||
func (p *Plugin) handleSubscribe(args map[string]interface{}) (interface{}, error) {
|
||
url := readArg(args, "url")
|
||
if url == "" {
|
||
return map[string]interface{}{"isError": true, "content": "URL is required"}, nil
|
||
}
|
||
|
||
p.mu.RLock()
|
||
for _, f := range p.feeds {
|
||
if f.URL == url {
|
||
p.mu.RUnlock()
|
||
return map[string]interface{}{"isError": true, "content": "Already subscribed to: " + url}, nil
|
||
}
|
||
}
|
||
p.mu.RUnlock()
|
||
|
||
interval := readArgInt(args, "interval", 30)
|
||
if interval < 5 {
|
||
interval = 5
|
||
}
|
||
|
||
parsed, err := p.fp.ParseURL(url)
|
||
if err != nil {
|
||
return map[string]interface{}{"isError": true, "content": "Failed to parse feed: " + err.Error()}, nil
|
||
}
|
||
|
||
feedTitle := parsed.Title
|
||
if feedTitle == "" {
|
||
feedTitle = url
|
||
}
|
||
|
||
sub := FeedSub{
|
||
URL: url,
|
||
Title: feedTitle,
|
||
AddedAt: time.Now().Format("2006-01-02 15:04"),
|
||
Interval: interval,
|
||
}
|
||
|
||
guidCount := 0
|
||
p.mu.Lock()
|
||
for _, item := range parsed.Items {
|
||
guid := item.GUID
|
||
if guid == "" {
|
||
guid = item.Link
|
||
}
|
||
if guid == "" {
|
||
continue
|
||
}
|
||
p.seenGUIDs[url+"|"+guid] = true
|
||
guidCount++
|
||
}
|
||
p.mu.Unlock()
|
||
|
||
p.mu.Lock()
|
||
p.feeds = append(p.feeds, sub)
|
||
p.mu.Unlock()
|
||
p.saveData()
|
||
|
||
return map[string]interface{}{
|
||
"content": fmt.Sprintf("Subscribed to: %s\nTitle: %s\nArticles found: %d\nPoll interval: %d min", url, feedTitle, guidCount, interval),
|
||
}, nil
|
||
}
|
||
|
||
func (p *Plugin) handleUnsubscribe(args map[string]interface{}) (interface{}, error) {
|
||
url := readArg(args, "url")
|
||
if url == "" {
|
||
return map[string]interface{}{"isError": true, "content": "URL is required"}, nil
|
||
}
|
||
|
||
p.mu.Lock()
|
||
found := false
|
||
for i, f := range p.feeds {
|
||
if f.URL == url {
|
||
p.feeds = append(p.feeds[:i], p.feeds[i+1:]...)
|
||
found = true
|
||
break
|
||
}
|
||
}
|
||
if !found {
|
||
p.mu.Unlock()
|
||
return map[string]interface{}{"isError": true, "content": "Not subscribed to: " + url}, nil
|
||
}
|
||
|
||
for guid := range p.seenGUIDs {
|
||
if strings.HasPrefix(guid, url+"|") {
|
||
delete(p.seenGUIDs, guid)
|
||
}
|
||
}
|
||
p.mu.Unlock()
|
||
p.saveData()
|
||
|
||
return map[string]interface{}{"content": "Unsubscribed: " + url}, nil
|
||
}
|
||
|
||
func (p *Plugin) handleList(args map[string]interface{}) (interface{}, error) {
|
||
p.mu.RLock()
|
||
defer p.mu.RUnlock()
|
||
|
||
if len(p.feeds) == 0 {
|
||
return map[string]interface{}{"content": "No subscriptions. Use rss_subscribe to add one."}, nil
|
||
}
|
||
|
||
sort.Slice(p.feeds, func(i, j int) bool {
|
||
return p.feeds[i].Title < p.feeds[j].Title
|
||
})
|
||
|
||
var lines []string
|
||
lines = append(lines, fmt.Sprintf("📡 Subscriptions (%d):", len(p.feeds)))
|
||
for _, f := range p.feeds {
|
||
lines = append(lines, fmt.Sprintf(" • %s\n %s (every %dm, added %s)", f.Title, f.URL, f.Interval, f.AddedAt))
|
||
}
|
||
|
||
return map[string]interface{}{"content": strings.Join(lines, "\n")}, nil
|
||
}
|
||
|
||
func (p *Plugin) handleCheckNow(args map[string]interface{}) (interface{}, error) {
|
||
select {
|
||
case <-p.stopCh:
|
||
return map[string]interface{}{"isError": true, "content": "plugin is stopping"}, nil
|
||
default:
|
||
}
|
||
p.wg.Add(1)
|
||
go func() {
|
||
defer p.wg.Done()
|
||
p.checkAllFeeds()
|
||
}()
|
||
return map[string]interface{}{"content": "Checking all feeds for updates..."}, nil
|
||
}
|
||
|
||
func (p *Plugin) dataFile() string {
|
||
return filepath.Join(p.dataDir, "feeds.json")
|
||
}
|
||
|
||
func (p *Plugin) loadData() {
|
||
b, err := os.ReadFile(p.dataFile())
|
||
if err != nil {
|
||
return
|
||
}
|
||
var data struct {
|
||
Feeds []FeedSub `json:"feeds"`
|
||
SeenGUIDs map[string]bool `json:"seen"`
|
||
}
|
||
if json.Unmarshal(b, &data) != nil {
|
||
return
|
||
}
|
||
if data.Feeds != nil {
|
||
p.feeds = data.Feeds
|
||
}
|
||
if data.SeenGUIDs != nil {
|
||
p.seenGUIDs = data.SeenGUIDs
|
||
}
|
||
}
|
||
|
||
func (p *Plugin) saveData() {
|
||
p.mu.RLock()
|
||
defer p.mu.RUnlock()
|
||
data := struct {
|
||
Feeds []FeedSub `json:"feeds"`
|
||
SeenGUIDs map[string]bool `json:"seen"`
|
||
}{
|
||
Feeds: p.feeds,
|
||
SeenGUIDs: p.seenGUIDs,
|
||
}
|
||
b, _ := json.MarshalIndent(data, "", " ")
|
||
atomicWriteJSON(p.dataFile(), b)
|
||
}
|
||
|
||
// cleanupData 卸载时清理订阅数据目录(feeds.json 等)
|
||
func (p *Plugin) cleanupData() {
|
||
p.mu.Lock()
|
||
defer p.mu.Unlock()
|
||
if p.dataDir == "" {
|
||
return
|
||
}
|
||
for _, f := range []string{"feeds.json"} {
|
||
path := filepath.Join(p.dataDir, f)
|
||
if err := os.Remove(path); err != nil && !os.IsNotExist(err) {
|
||
fmt.Printf("[%s] onRemove cleanup %s: %v\n", p.name, path, err)
|
||
}
|
||
}
|
||
}
|
||
|
||
|
||
|
||
// atomicWriteJSON 原子写 JSON:先写临时文件再 rename,避免进程崩溃截断数据文件。
|
||
func atomicWriteJSON(path string, data []byte) error {
|
||
tmp := path + ".tmp"
|
||
if err := os.WriteFile(tmp, data, 0644); err != nil {
|
||
return err
|
||
}
|
||
return os.Rename(tmp, path)
|
||
}
|