Files
HomeAgent/internal/agent/core/status.go
JianFeeeee 5aaae93367 feat(healthcheck): 内核状态快照报出内核版本号与 ONNX 模型启用状态
healthcheck_kernel 此前没有任何「ONNX 模型是否在用」的信息,只报「向量可用/不可用」,
分不清「统一多模态空间已加载」与「退回到词嵌入/TF-IDF 路径」;人格卡要求
「版本以运行时快照为准」,也缺一个可查字段(build.version 早就在,但没人知道)。

- KernelStatus 新增 onnx 段:enabled / provider / dim / fingerprint / modalities / reason。
  判据取 Loaded()(provider 真正打开且元数据合法),**不是**「配置里写了 provider」
  —— 后者在模型缺失 / 运行时缺失时也为真,报出去就是假绿。
- 未启用时 reason 给**具体原因**:未配置(说明会走回退路径)/ 打开失败的具体错误。
  homed 把「配置的 provider 名」与「打开失败原因」透传给 Agent,仅供状态报告。
- ProviderAdapter 新增 Modalities()(可选能力,按接口断言取用,不改公开契约)。
- healthcheck_kernel 的工具描述同步说明它回答这两件事。

**顺带修一个真实 panic**:collectKernelStatus 的 knowledge 是**接口**参数,
(*knowledge.Store)(nil) 塞进接口后 `ks != nil` 仍为真 → 调 List() 直接 panic,
而 healthcheck_kernel 正是走这条路径(panic 发生在工具 goroutine 里)。
GetKernelStatus 改为先按具体指针判空、再赋给接口;并加刻画测试钉住这个成因
(一旦不再 panic 说明参数形状已变,守卫与该测试应同步删除)。

验证:单测 4 例(已启用 / 打开失败 / 未配置 / 未加载)+ 刻画测试;
隔离实例 E2E 7/7:正例 provider=chineseclip → enabled=true、dim=512、模态 2;
反例 provider=nonexistent → enabled=false 且 reason 含具体错误与 provider 名,
真实对话仍通。
2026-09-12 14:56:25 +08:00

258 lines
6.7 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

package core
import (
"fmt"
"runtime"
"time"
agentIO "gitcode.com/JianFeeeee/HomeAgent/internal/agent/io"
"gitcode.com/JianFeeeee/HomeAgent/internal/memory"
"gitcode.com/JianFeeeee/HomeAgent/internal/memory/document"
"gitcode.com/JianFeeeee/HomeAgent/internal/memory/social"
"gitcode.com/JianFeeeee/HomeAgent/internal/memory/text"
"gitcode.com/JianFeeeee/HomeAgent/internal/meta"
"gitcode.com/JianFeeeee/HomeAgent/internal/plugin"
sdk "gitcode.com/JianFeeeee/HomeAgent/internal/sdk"
"gitcode.com/JianFeeeee/HomeAgent/internal/tracker"
)
// StatusProvider 内核状态查询接口。插件通过此接口查看内核运行动态。
type StatusProvider interface {
GetKernelStatus() *KernelStatus
}
// 状态 DTO 使用内置 SDK 的中立类型,保证与插件层解耦。
type KernelStatus = sdk.KernelStatus
type PluginInfo = sdk.PluginInfo
type ChannelInfo = sdk.ChannelInfo
type MemoryStatus = sdk.MemoryStatus
type KnowledgeStatus = sdk.KnowledgeStatus
type DocumentStatus = sdk.DocumentStatus
type TextMemoryStatus = sdk.TextMemoryStatus
type SocialStatus = sdk.SocialStatus
type LLMStatus = sdk.LLMStatus
type ContextStatus = sdk.ContextStatus
type RuntimeStatus = sdk.RuntimeStatus
type TrackerStatus = sdk.TrackerStatus
type BuildStatus = sdk.BuildStatus
func channelInfoFromIO(ch agentIO.ChannelInfo) ChannelInfo {
return ChannelInfo{
Name: ch.Name,
Type: fmt.Sprintf("%d", ch.Type),
Ready: true,
}
}
// collectKernelStatus 聚合内核各子系统状态快照。
// 接收所有子系统引用均为可选——nil 表示不可用),返回统一的状态报告。
func collectKernelStatus(
startTime time.Time,
agentID string,
providerName string,
sourceCount int,
stageHost *StageHost,
iom *agentIO.IOManager,
pluginReg *plugin.Registry,
memDB *memory.GraphDB,
ks interface{ List() []string },
docStore *document.Store,
textMem *text.Memory,
socialStore *social.SocialStore,
trk *tracker.Tracker,
) *KernelStatus {
status := &KernelStatus{
Uptime: time.Since(startTime).Round(time.Second).String(),
StartTime: startTime.Format(time.RFC3339),
AgentID: agentID,
// 构建身份取自内核自己的 meta-ldflags 注入点),
// 而非 SDK 仓的硬编码版本。
Build: BuildStatus{
Version: meta.Version,
Commit: meta.Commit,
BuildTime: meta.BuildTime,
SDKCompatible: meta.SDKCompatibleVersion,
KernelName: meta.KernelName,
// AGPL-3.0 §13状态页向网络使用者展示取得源码的入口。
SourceURL: meta.SourceURL,
},
Runtime: RuntimeStatus{
Goroutines: runtime.NumGoroutine(),
GoVersion: runtime.Version(),
},
LLM: LLMStatus{
Available: providerName != "",
Provider: providerName,
Sources: sourceCount,
},
}
// Plugins
if pluginReg != nil {
names := pluginReg.List()
for _, n := range names {
status.Plugins = append(status.Plugins, PluginInfo{Name: n, Loaded: true})
}
}
// Tools
if stageHost != nil {
status.Tools = stageHost.GetToolDefs()
}
// Channels
if iom != nil {
for _, ch := range iom.ListChannels() {
status.Channels = append(status.Channels, channelInfoFromIO(ch))
}
}
// Graph memory
if memDB != nil {
status.Memory.Available = true
if info, err := memDB.Introspect(); err == nil {
if ec, ok := info["entity_count"].(int); ok {
status.Memory.EntityCount = ec
}
if rc, ok := info["relation_count"].(int); ok {
status.Memory.RelationCount = rc
}
if et, ok := info["entity_type_count"].(int); ok {
status.Memory.EntityTypes = et
}
}
}
// Knowledge
if ks != nil {
status.Knowledge.Available = true
status.Knowledge.Items = ks.List()
status.Knowledge.ItemCount = len(status.Knowledge.Items)
}
// Documents
if docStore != nil {
status.Documents.Available = true
stats := docStore.Stats()
if dc, ok := stats["doc_count"].(int); ok {
status.Documents.DocCount = dc
}
if vc, ok := stats["vector_count"].(int); ok {
status.Documents.VectorCount = vc
}
}
// Text memory
if textMem != nil {
status.TextMemory.Available = true
status.TextMemory.FileCount = textMem.FileCount()
}
// Social
if socialStore != nil {
status.Social.Available = true
if persons, err := socialStore.ListPersons(); err == nil {
status.Social.PersonCount = len(persons)
}
}
// Tracker
if trk != nil {
status.Tracker.Available = true
status.Tracker.Dir = trk.MergeDir()
}
// Memory
var m runtime.MemStats
runtime.ReadMemStats(&m)
status.Runtime.MemoryMB = int64(m.Alloc / 1024 / 1024)
return status
}
// GetKernelStatus 返回 Agent 驱动的内核状态快照。
func (a *Agent) GetKernelStatus() *KernelStatus {
providerName := ""
sourceCount := 0
if a.providerManager != nil {
sourceCount = len(a.providerManager.List())
}
if a.provider != nil {
providerName = a.provider.Name()
}
var textMem *text.Memory
if a.textMem != nil {
textMem = a.textMem
}
var socialStore *social.SocialStore
if a.social != nil {
socialStore = a.social
}
var trk *tracker.Tracker
if a.tracker != nil {
trk = a.tracker
}
// 注意knowledge 在 collectKernelStatus 里是**接口**参数,
// 而 (*knowledge.Store)(nil) 塞进接口后 `ks != nil` 仍为真 → 调 List() 直接 panic。
// 所以这里必须先判具体指针再进行接口赋值healthcheck_kernel 会走到这条路径)。
var knowledgeLister interface{ List() []string }
if a.knowledge != nil {
knowledgeLister = a.knowledge
}
ks := collectKernelStatus(
a.startTime,
string(a.id),
providerName,
sourceCount,
a.stageHost,
a.io,
a.pluginReg,
a.memory,
knowledgeLister,
a.docStore,
textMem,
socialStore,
trk,
)
ks.ONNX = a.onnxStatus()
return ks
}
// onnxStatus 汇总统一多模态向量空间ONNX 模型)的启用状态。
//
// 判据是 Loaded()provider 真正打开且元数据合法),**不是**「配置里写了 provider」——
// 后者在模型缺失 / 运行时缺失时也为真,拿它当判据就是假绿。
func (a *Agent) onnxStatus() sdk.ONNXStatus {
st := sdk.ONNXStatus{Provider: a.embeddingProvider}
if a.multimodalSpace != nil && a.multimodalSpace.Loaded() {
st.Enabled = true
st.Dim = a.multimodalSpace.Dim()
st.Fingerprint = a.multimodalSpace.Fingerprint()
// 模态是可选能力:只有底层 provider 报出来时才带出。
if mr, ok := a.multimodalSpace.(interface{ Modalities() []string }); ok {
st.Modalities = mr.Modalities()
}
return st
}
switch {
case a.embeddingError != "":
st.Reason = "打开失败: " + a.embeddingError
case a.embeddingProvider == "":
st.Reason = "未配置统一向量空间 provider走词嵌入/TF-IDF 回退路径)"
default:
st.Reason = "provider 未加载"
}
return st
}
var _ StatusProvider = (*Agent)(nil)
var _ sdk.StatusAPI = (*Agent)(nil)