jianf/HomeAgent
1
0
Fork 0
mirror of https://gitcode.com/JianFeeeee/HomeAgent.git synced 2026-09-23 10:28:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

v0.7.2: 根目录清理 + Agent 心跳重构 + 内嵌 ONNX 模型

Browse Source 
- 根目录清理: branding/docs/knowledge -> assets/, package/tools/deploy -> deploy/
- meta.go: Version 0.7.2, SDKCompatibleVersion 语义改为最高兼容
- Makefile: 版本回退 0.7.2
- registry.go: 系统提示词改用 meta.Version 格式化
- Agent 心跳: reorgGraph 拆分为三个独立循环(archive/merge/review)，各自可配间隔
- GraphDB: 新增 sentences 表 + 关系句子溯源 + ClearSentenceID + CleanupOrphanedSentences
- Knowledge: 支持词嵌入向量化器
- NLP 四阶段流水线: Parse -> Extract -> Verify -> Fuse + SentenceRef
- 移除远程 HTTP 解析器(remote_parser.go)
- 新增内嵌 ONNX 模型(vocab + dep_parser.onnx):
  +build onnxruntime: 全量 ONNX Runtime 推理
  !build onnxruntime: 内嵌词表规则式降级解析器
- config: core.agent.onnx_model_path 替代 dep_parser_url
This commit is contained in:
JianFeeeee
2026-07-28 09:56:26 +08:00
parent 1cb3e87dde
commit 2c5f9ff262
47 changed files with 26141 additions and 242 deletions
Download Patch File Download Diff File Expand all files Collapse all files

122
internal/agent/core/agent.go
View File

@ -7,8 +7,8 @@ import (
"sync"
"time"
agentAPI "gitcode.com/JianFeeeee/HomeAgent/internal/agent/api"
agentPkg "gitcode.com/JianFeeeee/HomeAgent/internal/agent"
agentAPI "gitcode.com/JianFeeeee/HomeAgent/internal/agent/api"
agentIO "gitcode.com/JianFeeeee/HomeAgent/internal/agent/io"
"gitcode.com/JianFeeeee/HomeAgent/internal/events"
"gitcode.com/JianFeeeee/HomeAgent/internal/knowledge"
@ -26,19 +26,19 @@ import (
// Agent — 单 agent，不区分会话/实例
type Agent struct {
mu sync.Mutex
id types.AgentID
provider agentAPI.Provider
mu sync.Mutex
id types.AgentID
provider agentAPI.Provider
providerManager *agentAPI.ProviderManager
io *agentIO.IOManager
memory *memory.GraphDB
indexer *memory.Indexer
skills *skill.Manager
tracker *tracker.Tracker
context *RelevanceContext
systemPrompt string
ctx context.Context
cancel context.CancelFunc
io *agentIO.IOManager
memory *memory.GraphDB
indexer *memory.Indexer
skills *skill.Manager
tracker *tracker.Tracker
context *RelevanceContext
systemPrompt string
ctx context.Context
cancel context.CancelFunc
// 文档记忆（第二层）
docStore *document.Store
@ -62,6 +62,11 @@ type Agent struct {
// 定期心跳蒸馏
distillInterval time.Duration
// 三个独立心跳任务间隔
archiveInterval time.Duration // 冷文档归档
reviewInterval time.Duration // 关系复审
mergeInterval time.Duration // 实体合并检测
// 上下文裁剪：活跃上下文最大条数，超出按相关性裁剪
maxContextSize int
@ -110,30 +115,33 @@ type Agent struct {
}
type AgentConfig struct {
ID types.AgentID
SystemPrompt string
Provider agentAPI.Provider
ID types.AgentID
SystemPrompt string
Provider agentAPI.Provider
ProviderManager *agentAPI.ProviderManager
IO *agentIO.IOManager
Memory *memory.GraphDB
Indexer *memory.Indexer
Skills *skill.Manager
Tracker *tracker.Tracker
IO *agentIO.IOManager
Memory *memory.GraphDB
Indexer *memory.Indexer
Skills *skill.Manager
Tracker *tracker.Tracker
DocStore *document.Store
Knowledge *knowledge.Store
SocialStore *social.SocialStore
TextMemory *text.Memory
Personality *agentPkg.Personality
PluginReg *plugin.Registry
PluginDir string
DistillInterval time.Duration
MaxContextSize int // 活跃上下文最大条数，超出按相关性裁剪
ContextSavePath string // 上下文持久化路径，空则不持久化
EmbeddingModelPath string // 预训练词嵌入模型路径（word2vec 文本格式），空则不使用
StageHost *StageHost
EventBus *events.Bus
ThinkingEnabled bool
DocStore *document.Store
Knowledge *knowledge.Store
SocialStore *social.SocialStore
TextMemory *text.Memory
Personality *agentPkg.Personality
PluginReg *plugin.Registry
PluginDir string
DistillInterval time.Duration
ArchiveInterval time.Duration // 冷文档归档间隔（L3→L4），0 则使用 DistillInterval
ReviewInterval time.Duration // 关系复审间隔，0 则使用 DistillInterval
MergeInterval time.Duration // 实体合并检测间隔，0 则使用 DistillInterval
MaxContextSize int // 活跃上下文最大条数，超出按相关性裁剪
ContextSavePath string // 上下文持久化路径，空则不持久化
EmbeddingModelPath string // 预训练词嵌入模型路径（word2vec 文本格式），空则不使用
StageHost *StageHost
EventBus *events.Bus
ThinkingEnabled bool
InputProcessing types.InputProcessingConfig // 非文本输入处理配置
}
@ -143,6 +151,15 @@ func New(cfg AgentConfig) *Agent {
if cfg.DistillInterval <= 0 {
cfg.DistillInterval = 30 * time.Minute
}
if cfg.ArchiveInterval <= 0 {
cfg.ArchiveInterval = cfg.DistillInterval
}
if cfg.ReviewInterval <= 0 {
cfg.ReviewInterval = cfg.DistillInterval
}
if cfg.MergeInterval <= 0 {
cfg.MergeInterval = cfg.DistillInterval
}
if cfg.MaxContextSize <= 0 {
cfg.MaxContextSize = 30
}
@ -152,6 +169,10 @@ func New(cfg AgentConfig) *Agent {
cfg.DocStore.SetVectorizer(embedder)
cfg.DocStore.ReindexWithVectorizer(embedder)
}
if cfg.Knowledge != nil {
cfg.Knowledge.SetVectorizer(embedder)
cfg.Knowledge.ReindexWithVectorizer(embedder)
}
rc := NewRelevanceContext(cfg.ContextSavePath, embedder)
if cfg.StageHost != nil {
@ -179,19 +200,21 @@ func New(cfg AgentConfig) *Agent {
personality: cfg.Personality,
pluginReg: cfg.PluginReg,
pluginDir: cfg.PluginDir,
distillInterval: cfg.DistillInterval,
maxContextSize: cfg.MaxContextSize,
stageHost: cfg.StageHost,
eventBus: cfg.EventBus,
selfInputCh: make(chan string, 64),
childResults: make(map[string]string),
interceptCh: make(chan *agentIO.InputEvent, 64),
pluginHealth: newPluginHealthTracker(),
thinkingEnabled: cfg.ThinkingEnabled,
inputCfg: cfg.InputProcessing,
embedder: embedder,
noMergeMarkers: make(map[string]int),
distillInterval: cfg.DistillInterval,
archiveInterval: cfg.ArchiveInterval,
reviewInterval: cfg.ReviewInterval,
mergeInterval: cfg.MergeInterval,
maxContextSize: cfg.MaxContextSize,
stageHost: cfg.StageHost,
eventBus: cfg.EventBus,
selfInputCh: make(chan string, 64),
childResults: make(map[string]string),
interceptCh: make(chan *agentIO.InputEvent, 64),
pluginHealth: newPluginHealthTracker(),
thinkingEnabled: cfg.ThinkingEnabled,
inputCfg: cfg.InputProcessing,
embedder: embedder,
noMergeMarkers: make(map[string]int),
}
}
@ -199,6 +222,9 @@ func (a *Agent) Start() {
go a.eventLoop()
go a.interceptLoop()
go a.distillLoop()
go a.archiveLoop()
go a.mergeLoop()
go a.reviewLoop()
log.Printf("[agent] %s started, waiting for IO interrupts", a.id)
}

173
internal/agent/core/distill.go
View File

@ -28,6 +28,11 @@ func (a *Agent) enqueueConsolidationTask(task ConsolidationTask) {
log.Printf("[agent] enqueued consolidation task: %s", task.Reason)
}
// ──────────────────────────────────────────────
// 四个独立心跳循环，各自拥有独立的 ticker 和配置
// ──────────────────────────────────────────────
// distillLoop 上下文裁剪（L2 蒸馏），使用 distillInterval
func (a *Agent) distillLoop() {
defer func() {
if r := recover(); r != nil {
@ -36,7 +41,7 @@ func (a *Agent) distillLoop() {
go a.distillLoop()
}
}()
if a.docStore == nil && a.memory == nil {
if a.docStore == nil {
return
}
ticker := time.NewTicker(a.distillInterval)
@ -47,7 +52,6 @@ func (a *Agent) distillLoop() {
case <-ticker.C:
log.Printf("[agent] heartbeat distill tick")
a.distillContext()
a.reorgGraph()
a.autoReloadPlugins()
case <-a.ctx.Done():
return
@ -55,6 +59,88 @@ func (a *Agent) distillLoop() {
}
}
// archiveLoop 冷文档归档（L3→L4），使用 archiveInterval
func (a *Agent) archiveLoop() {
defer func() {
if r := recover(); r != nil {
log.Printf("[agent] archiveLoop panic recovered: %v\n%s", r, debug.Stack())
time.Sleep(time.Second)
go a.archiveLoop()
}
}()
if a.memory == nil {
return
}
ticker := time.NewTicker(a.archiveInterval)
defer ticker.Stop()
for {
select {
case <-ticker.C:
log.Printf("[agent] heartbeat archive tick")
a.archiveColdDocs()
case <-a.ctx.Done():
return
}
}
}
// mergeLoop 实体合并检测（GraphDB → LLM 裁决），使用 mergeInterval
func (a *Agent) mergeLoop() {
defer func() {
if r := recover(); r != nil {
log.Printf("[agent] mergeLoop panic recovered: %v\n%s", r, debug.Stack())
time.Sleep(time.Second)
go a.mergeLoop()
}
}()
if a.memory == nil {
return
}
ticker := time.NewTicker(a.mergeInterval)
defer ticker.Stop()
for {
select {
case <-ticker.C:
log.Printf("[agent] heartbeat merge tick")
a.detectEntityMerge()
case <-a.ctx.Done():
return
}
}
}
// reviewLoop 关系复审（GraphDB → ClearSentenceID → CleanupOrphanedSentences），使用 reviewInterval
func (a *Agent) reviewLoop() {
defer func() {
if r := recover(); r != nil {
log.Printf("[agent] reviewLoop panic recovered: %v\n%s", r, debug.Stack())
time.Sleep(time.Second)
go a.reviewLoop()
}
}()
if a.memory == nil {
return
}
ticker := time.NewTicker(a.reviewInterval)
defer ticker.Stop()
for {
select {
case <-ticker.C:
log.Printf("[agent] heartbeat review tick")
a.reviewRelations()
case <-a.ctx.Done():
return
}
}
}
// ──────────────────────────────────────────────
// 蒸馏逻辑
// ──────────────────────────────────────────────
func (a *Agent) distillContext() {
if a.docStore == nil {
return
@ -68,14 +154,16 @@ func (a *Agent) distillContext() {
}
}
// ──────────────────────────────────────────────
// 冷文档归档：docStore → GraphDB (L3→L4)
// ──────────────────────────────────────────────
func (a *Agent) reorgGraph() {
func (a *Agent) archiveColdDocs() {
if a.memory == nil {
return
}
log.Printf("[agent] graph reorg start")
log.Printf("[agent] cold doc archival start")
if a.indexer != nil {
if err := a.indexer.Sync(); err != nil {
@ -102,6 +190,18 @@ func (a *Agent) reorgGraph() {
}
}
}
}
// ──────────────────────────────────────────────
// 实体合并检测：GraphDB → LLM 裁决
// ──────────────────────────────────────────────
func (a *Agent) detectEntityMerge() {
if a.memory == nil {
return
}
log.Printf("[agent] entity merge detection start")
result, err := a.memory.Recall(nil, nil, 1, "")
if err != nil || result == nil || len(result.Entities) < 2 {
@ -167,9 +267,68 @@ func (a *Agent) reorgGraph() {
}
if llmCandidates > 0 {
log.Printf("[agent] graph reorg: %d merge candidates sent for LLM decision", llmCandidates)
log.Printf("[agent] entity merge: %d merge candidates sent for LLM decision", llmCandidates)
} else {
log.Printf("[agent] graph reorg: no similar entities found")
log.Printf("[agent] entity merge: no similar entities found")
}
}
// ──────────────────────────────────────────────
// 关系复审：GraphDB → ClearSentenceID → CleanupOrphanedSentences
// ──────────────────────────────────────────────
func (a *Agent) reviewRelations() {
if a.memory == nil {
return
}
log.Printf("[agent] relation review start")
reviewCount := 0
const maxReviewBatch = 5
relResult, err := a.memory.Recall(nil, nil, 1, "")
if err != nil || relResult == nil {
return
}
for _, rel := range relResult.Relations {
if reviewCount >= maxReviewBatch {
break
}
if rel.SentenceID == 0 || rel.SentenceText == "" {
continue
}
a.enqueueConsolidationTask(ConsolidationTask{
Type: "relation_review",
Reason: fmt.Sprintf(
"【关系复审】原始句子: '%s'\n当前三元组: (%s → %s → %s) 置信度 %.2f\n请判断是否需要修正（如相对引用未解析、主宾颠倒、噪音三元组等），如需修正请用 memory_edit 工具",
rel.SentenceText, rel.SourceName, rel.RelationType, rel.TargetName, rel.Confidence,
),
Data: map[string]interface{}{
"relation_id": rel.ID,
"source": rel.SourceName,
"relation_type": rel.RelationType,
"target": rel.TargetName,
"confidence": rel.Confidence,
"sentence": rel.SentenceText,
},
})
// 清除句子引用（复审后解除关联）
if err := a.memory.ClearSentenceID(rel.ID); err != nil {
log.Printf("[agent] clear sentence_id for relation %d: %v", rel.ID, err)
}
reviewCount++
}
if reviewCount > 0 {
// 清理无引用的句子
if deleted, err := a.memory.CleanupOrphanedSentences(); err != nil {
log.Printf("[agent] cleanup orphaned sentences: %v", err)
} else if deleted > 0 {
log.Printf("[agent] cleanup %d orphaned sentences", deleted)
}
log.Printf("[agent] relation review: %d relations sent for review", reviewCount)
}
}