5836c2ce5c
refactor(memory): 拆除描述式媒体索引，媒体成为一等块并按原生向量融合
...
背景：此前媒体是靠「生成的描述文本」将就进记忆的——写 marker 进正文、
再由正则反解成 media_refs 与图库里的 type=Media 实体。这条链路有三个
致命缺陷：描述由异步模型生成（未生成前媒体等于不存在）、语义检索实质上
只搜描述文字、图库里的「媒体节点」是描述文本的投影而不是媒体本身。
本提交把这条链路整体拆除，媒体改为按自己的原生向量参与记忆：
一、描述链彻底删除（无残留、无兼容分支）
- media.Item 去掉 Description/DescribedBy 与对应列；
- 删除 Store.Describe / Store.Search / Store.Pending；
- 删除 Agent.mediaDescribeLoop / describePendingMedia 与配置项
core.memory.media.describe_on_ingest；
- SDK 侧 MediaAttachment 去掉 Description（见 SDK 仓独立提交）。
二、marker 机制删除，媒体归属改为结构化块边
- 删除 mediaMarkerLine/parseMediaMarkers/mediaEntityName/mediaTriplesFromText/
extractMediaDigests/sentenceWithMediaMarkers/docMediaContext；
- memory.Triple 新增 MediaDigests 结构化字段；句子文本保持原样，
不再被 marker 污染；
- 块以 sentence --contains--> block / document --contains--> block 结构边
挂到承载节点（新增 documents 表与 document 节点种类）；
- 模型未给原句时用「主谓宾。」拼一句自然语言作落点，不造 marker 文本。
三、旧数据迁移（幂等）
- 新增 GraphDB.MigrateLegacyMediaEntities：把 type=Media 的旧实体按短 digest
还原成原生块、挂回原句子、删除旧实体与描述关系；Agent 启动时执行；
- CleanupOrphanedSentences 同时看关系引用与块边，避免把只靠块存活的句子
连同块边一起删掉。
四、向量融合：媒体按图本身被召回
- 新增 vector.FuseVectors（逐维求和 + L2 归一化）；
- Doc.DenseVec = 文本向量 ⊕ 文档块的媒体向量（同 fingerprint 才融合），
新增 Doc.DenseFP，指纹变化触发重算；
- ContextEvent.DenseVec 同理融合事件块；事件新增 DenseFP，Prune 只在
同一统一空间内比稠密余弦；
- 跨模态视觉路只召回「仍被某层记忆块持有」的媒体，CAS 全库字节不再
直接充当记忆检索结果。
五、同时纳入本分支既有的嵌入基础改造（此前工作区未提交，缺它 HEAD 不可构建）
- internal/tfidf 懒回退包、千问三段式多模态 ONNX 空间的 Go 侧
（qwen/embedder.go、image.go、model_input.go）、CLIP 移除、
sdk.NewStore 分词器签名与调用点、embed 侧车 systemd 单元。
验证：go build ./... 、go vet ./...（含 -tags medialive）均通过；
在 HEAD 的独立 worktree 上重放本次暂存集后 go test -short ./internal/...
全部通过（端口冲突类用例在隔离环境中亦通过）。未提交工作区中与本改造
无关的改动（HarmonyOS、waiter、devicebridge、plan.md 等）。
2026-09-11 11:45:24 +08:00
dae01f9c06
refactor(memory): 移除 media_refs/引用计数，媒体成为一等记忆块
...
媒体此前是"文本块 + digest 引用 + owner 账本 + 独立 GC"：ContextEvent.Media
记 digest，media_refs 表用 owner_kind/owner_id 保活，ref_count 决定 GC 能否清。
这与文本记忆块的管理方式不一致，也是本次一并纠正的核心偏差。
改为与文本块完全一致的生命周期：
1. 一等记忆块直接由所在层持有
- ContextEvent.Blocks / Doc.Blocks / GraphDB memory_blocks
- 块带 modality/digest/MIME/size/vector/fingerprint，文本、图片、视频同构
- Context→Document→Graph 迁移的是块本身（ID 不变），迁移后清空源容器，
同一块不同时存在于两层
2. 删除平行生命周期账本
- media.Store 去掉 media_refs 表、OwnerKind 常量、RefCount 字段、
AddRef/DropRef/DropOwner/Refs、ref_count 列与索引
- 删除 mediaGCLoop、GC(keep,minAge)、容量上限与 media.gc_* / media.max_mb 配置
- 媒体内容在块被永久删除时一并删除（media.Store.Delete + forgetPayloads），
与"删除文本块即删除内容"同一语义
3. L3 原生结构
- memory_blocks / memory_block_edges（contains/depicts/derived_from）
- 边端点必须是真实图节点，不再用 owner 字符串伪装关系
- BlocksForNode 支持 sentence --contains--> block 反查
4. SDK 与检索同步
- 插件附件/标记直接变成块，不再 AddRef
- 跨模态检索改用 QueryMediaScored（CAS 内不再有孤儿缓存需要过滤）
测试全部改写为块语义：删除 refcount/media_refs/GC 断言，新增块迁移、
单层不变量、Delete 语义与并发删除回归。
注：cmd/homed/main.go 同时携带工作区中既有的 CLIP→Qwen 模型目录接线改动。
2026-09-11 10:57:22 +08:00
580d5f5501
feat(doc): dense vector index for unified text+media retrieval
...
文档层引入稠密向量索引，与媒体检索共享同一多模态空间：
- Doc 加 DenseVec 字段（json:-，运行时计算）
- Consume/QueryScored 优先使用 denseSearchScored（brute-force cosine），
未配置时退化到 TF-IDF 倒排检索
- buildDenseIndex 在 Agent 启动时为全部文档一次性计算稠密向量
- L0 RelevanceContext 支持 denseSpace（Prune 使用稠密余弦），
退化到 fastText 稀疏余弦
vector 包新增 DenseCosine（[]float64 brute-force cosine）。
验证：492 篇文档 brute-force ~300ms，全部测试通过。
2026-09-09 18:56:44 +08:00
f855893d1c
feat(memory): 媒体接入 L0/L2——digest 挂到对话事件，归档时引用随之转移
...
在 a822674
2026-09-04 20:53:32 +08:00
a899d777c3
sdk: embed non-toolchain SDK in third_party, add NoMemory/Cleaner support
...
- Embed sdk/, example/, meta/, go.mod from homeagent-sdk (no .git)
- Core .gitignore excludes SDK toolchain: bin/, tools/, package/
- RegisterInputChannel + ChannelDef(NoMemory, Cleaner) in SDK
- IOManager input channel registry with GetInputChannelDef
- eventloop: apply channel Cleaner/NoMemory to interrupt text
- context engine: channelDefLookup applied in textForVector
- document store: ChannelCleaner param for archive functions
- All callers/adapters updated with ChannelDef{} default
2026-07-29 14:48:23 +08:00
d19b7bd13e
fix: 修复记忆系统自循环与计算层污染
...
- 删 syncGraphToDocs(): Graph 快照不再写入 Document，避免污染向量索引和三层隔离
- 删 toolCallRing(): 已被工具 NoMemory/Cleaner 机制取代，不再需要独立环形缓冲
- 加 toolOutputClean 回调线程 Prune→ContextToDoc: 归档时按 NoMemory 跳过、Cleaner 清洗后再过 jieba，原文保留
- 加 eval_status 持久化 (RecallPending/UpdateEvalStatus/ResolveEvaluating): 避免重复 LLM 评估
2026-07-26 19:36:25 +08:00
634c3ff4ad
fix: doc_query chronological insert, register cli/webui output channels
...
- context.go: add InsertByTimestamp for chronological context insertion
- toolcall.go: doc_query uses InsertByTimestamp instead of Append
- agent_tools_test.go: update tests to use payload/type keys
- cli/plugin.go: register output_send__cli channel
- webui/plugin.go: register output_send__webui channel
2026-07-25 16:25:06 +08:00
31664a7853
feat: NoMemory/Cleaner memory system + doc update
...
- _sdk_local/ removed (moved to standalone sdk repo)
- internal/agent/core: NoMemory/Cleaner data-flow breakpoints
- internal/memory: clean_text, document store refactor
- internal/plugin/registry.go: plugin API alignment
- docs: PLUGIN_DEV.md, ARCHITECTURE.md NoMemory/Cleaner docs
- plan.md, review.md: status update
2026-07-25 11:17:31 +08:00
3fc2151588
refactor: pluginize text cleaning and tool NoMemory control
...
- SDK: ToolDef.NoMemory field, PluginSDK.RegisterTextCleaner/TextCleaners
- Registry: aggregate text cleaners from plugins, expose CleanText()
- Memory: replace hardcoded QQ regex CleanTemplateText with dynamic CleanText/SetTextCleaner
- StageHost: add ToolDef(name) lookup
- eventloop: check ToolDef.NoMemory before emitMemoryCandidate
- context/Prune: replace hardcoded agentcli/terminal source filter with ToolsUsed NoMemory check
- agentcli/cmd: mark tools with NoMemory: true
- main.go: wire memory.SetTextCleaner(pluginReg.CleanText)
2026-07-24 14:49:08 +08:00
4495447b85
fix(document memory): dedup graph sync, filter terminal output from archive, add min relevance threshold
2026-07-19 14:21:04 +08:00
8ae1d19869
refactor: output channel interface (payload/meta/type) + memory fixes
...
- Redesign output_send__ tools: content JSON string -> structured
payload/meta/type params for LLM reliability
- executeOutputSendTool: route by type with capability check
- executeOutputSendHelp: show meta format + type enum
- Updated system prompt rules for new interface
- docToTriples: use jieba exact mode adjacent co-occurrence
- Unify vector space: Doc.Vector field, ContextToDoc vectorizer,
ReindexWithVectorizer on startup
2026-07-19 10:29:21 +08:00
7892d7b0f2
feat: multi-language embedding with CleanTemplateText + three-branch vector strategy
...
- StaticEmbedder: pre-trained ConceptNet Numberbatch/fastText word embeddings,
auto-download with TF-IDF fallback, comma-separated multi-model paths
- CleanTemplateText: regex stripping of QQ tool call templates and noise
- textForVector: per-source vector strategy (agent→Response, user→Input,
cold_storage→both)
- Indexer.BuildContext and ExtractKeywords now clean input before vectorization
- Protect recent 10 events in Prune (regression fix: use local var not const)
2026-07-17 21:02:35 +08:00
7f28b997e6
feat: output channel redesign - per-channel output gates, LLM chain events, SDKConfig
...
- Output channels generate per-channel tools: output_send__{name} (type=output) + output_send__{name}_help
- content is JSON string transparently passed to plugin handler for routing
- EventAgentLLMChain: full LLM response forwarded after each turn for webui/logs
- sdk.New refactored to SDKConfig struct (no more 13 positional args)
- RegisterOutputChannel adds desc param for JSON format documentation
- channelDevice simplified (no Tools method), desc field added
- Child agent permission updated for output_send__ prefix
- System prompt: output gates, multi-call, long messages split
- WebUI: subscribes to EventAgentLLMChain in SSE, no output channel
- Tests updated for new naming convention
2026-07-16 12:11:16 +08:00
1f1233b823
refactor: P0-P3 fixes, C1 cleanup, architecture diagrams, go.work upgrade
...
- P0-1: ProviderError type + ReportStatus for precise 401/403 detection
- P0-2: Remove -config flag from deploy/homeagent.service
- P2-1: 5s debounce on context.go Save()
- P2-2→C1: Delete output_set_channel entirely
- P2-3: Extract mediaDataURL/mediaChat helpers
- P2-4: Dedup defaultSources var
- P3: Delete dead packages (embed/tokenizer/container/snapshot)
- P3: Delete dead functions (messagesToMap, RunStageAll)
- CL: Update .gitignore, docs, Makefile, gojieba removal
- Config: Delete config/config.yaml, update docs
- Arch: Remove EmitOutputTo from emitResponse
- CL-1: go.work 1.19→1.21
- Docs: Add Mermaid architecture diagrams to README
- Docs: Add kernel-rebuild requires plugin-rebuild note to PLUGIN_DEV.md
2026-07-12 11:42:56 +08:00
2edc039351
fix: correct context pruning order and vector alignment
...
- Prune context BEFORE processing (LSTM forget gate pattern)
so LLM only sees relevant context, instead of pruning after the fact
- Fix ensureTrained() to recompute all event vectors after retraining
vectorizer, fixing feature-space mismatch between stored vectors and
query vector that made relevance scoring effectively random
- Add read lock to knowledge BuildTree() (data race fix)
- Log writeIndex() errors instead of discarding them
- Fix TOCTOU race in document ContextToDoc() dedup
- Fix healthcheck timing (measure elapsed before cleanup)
- Refactor waiter CLI into separate files (state, conn, config, editor,
history, builtin) for maintainability
- Add CLI plugin API key authentication
2026-07-07 17:07:38 +08:00
3e3c6a24d2
v4 architecture: pipeline stages, SDK, event bus, LLM-driven memory consolidation
...
- SDK PluginAPI (internal/plugin/sdk/): RegisterTool/RegisterStage/Subscribe/Publish
- EventBus (internal/events/): system-level pub/sub with wildcard support
- StageHost (internal/agent/core/stages.go): 7-stage message pipeline
- Agent core: on_input/pre_action/post_action/before_toolcall/after_toolcall/before_output/after_output
- Plugin Registry: SDK plugin registration and tool routing
- GraphDB.MergeEntities: entity consolidation with relation redirection
- memory_merge tool: allows LLM to merge similar entities
- Consolidation task: heartbeat detects conflicts, enqueues via IO for LLM decision
- _consolidation_ internal channel for system-level memory maintenance
- Comprehensive documentation: ARCHITECTURE.md, PLAN.md, DESIGN.md, README.md
- 54 tests across all packages, all passing
2026-07-03 08:04:39 +08:00
bc26850b50
feat: complete HomeAgent architecture v2
...
- IO abstraction layer with OutputChannel routing and capability validation
- Three-layer memory (Context-Document-Graph) with TF-IDF relevance pruning
- OneBot V11 QQ protocol plugin with Reverse WebSocket client
- Plugin system with hot-reload (SKILL.md + native factories)
- Knowledge system with TF-IDF vector indexing
- Personality system (personal.md)
- Text memory (JSONL with rotation)
- Change tracker (overlayfs) with rollback
- Lua adapter VM
- Design document (DESIGN.md)
Module: gitcode.com/JianFeeeee/HomeAgent
2026-07-02 12:04:36 +08:00
