v0.7.3: 重构 Provider 层 + 计算层隔离 + Cleaner/NoMemory 架构

- 删除 OpenAIProvider/OllamaProvider 死代码，LuaAdaptedProvider 独存
- DisableThinking 从 ExtraBody 移到 CompletionRequest 顶层字段
- ContextWindow 从 Provider 签名移到 BaseConfig/ModelContextWindow() 统管
- 确认 CleanText 仅做基本空白 trim，QQ 模板剥离归插件 Cleaner
- Cleaner/NoMemory 仅作用于向量计算和 jieba 分词层，原文不变
- context.ContextEvent/Doc.Content 始终保存原文
- 删除 nlp/download.go 死代码
- media.go: context.Background() -> a.ctx 级联
- clawhubadapter: HTTP 超时
- cut.go: 跨平台 mod cache 路径 (GOMODCACHE->GOPATH->HomeDir)
- bridge_e2e_test: 移除未用 runtime import
- lua 适配器: disable_thinking 传参

assets/docs/en/ARCHITECTURE.md

@@ -10,7 +10,7 @@ HomeAgent's cognitive architecture consists of three subsystems: the event loop
 
 **The stage pipeline (StageHost)** manages two registration categories: tool definitions (ToolDef) and stage handlers (StageHandler). ToolDef includes two optional memory control fields: `NoMemory bool` — when true, the tool's output is excluded from vectorization/jieba/distillation (original text preserved); and `Cleaner func(string) string` — a filter applied before the output enters the computation layer (e.g., extracting a `content` field from JSON). Neither modifies the original output; both only affect the computation layer input. `RegisterTool` rejects duplicate names, infers the owning plugin name from the tool name prefix, and maintains a `toolPlugins` mapping. `RegisterStage` appends handlers to the corresponding stage list. On stage execution (`RunStage`), **all registered handlers execute in parallel via goroutines**, sharing a single `*StageContext` protected by `sync.RWMutex`. Individual handler panics are recovered independently without affecting other handlers. Short-circuit semantics are implemented by checking `ctx.Response != nil` — any stage handler can set this value to terminate the pipeline early. `ExecuteTool` includes built-in panic recovery with stack-trace recording. `UnregisterPluginTools` removes a plugin's tool set during hot-reload.
 
-**The context window (RelevanceContext)** maintains a chronologically ordered event list. `Append` applies `CleanTemplateText` to strip QQ templates and timestamp noise before computing the embedding vector using a three-branch strategy (agent events use Response, user events use Input, cold_storage uses Input+Response). `Prune` triggers when the event count exceeds `topK`: it **unconditionally protects the last 10 events from eviction** (recency bias), scores remaining candidates against the current input via CosineSimilarity, keeps `topK - 10` highest-scoring entries (floor at 0), then re-sorts chronologically. Pruned events from sources other than `agentcli` and `terminal` are archived to the Document layer via `docStore.ContextToDoc`, retaining original timestamps. Persistence uses 5-second debounced writes to a JSON file.
+**The context window (RelevanceContext)** maintains a chronologically ordered event list. `Append` aggregates tool outputs through `textForVector` before computing the embedding vector: `NoMemory` skips, `Cleaner` filters (per-tool cleaners registered by plugins — e.g. the QQ plugin strips its own tool-call templates), and `CleanText` finalizes with basic whitespace normalization. A three-branch strategy selects the text source (agent events use Response, user events use Input, cold_storage uses Input+Response). `Prune` triggers when the event count exceeds `topK`: it **unconditionally protects the last 10 events from eviction** (recency bias), scores remaining candidates against the current input via CosineSimilarity, keeps `topK - 10` highest-scoring entries (floor at 0), then re-sorts chronologically. Pruned events from sources other than `agentcli` and `terminal` are archived to the Document layer via `docStore.ContextToDoc`, retaining original timestamps. Persistence uses 5-second debounced writes to a JSON file.
 
 **Tool definitions are aggregated from five sources**: IOManager-registered plugin tools; StageHost-registered SDK tools; Indexer-provided memory index tools; conditionally added built-in tools (depending on non-nil state of memory/knowledge/docStore/social/pluginReg/providerManager modules — including memory operations, knowledge retrieval, document queries, social networking, plugin reloading, child-agent spawning, per-output-channel send tools, and LLM source switching); and media processing tools added based on `pendingMedia` state. `buildToolDefs()` re-aggregates all sources on each process cycle.
 
@@ -145,7 +145,7 @@ All vectorization unified under `StaticEmbedder` (`internal/memory/static_embedd
 - Configured via `core.agent.embedding_model_path` (comma-separated multi-model)
 - Path containing `numberbatch` → auto-download ConceptNet; `cc.zh.` → fastText Chinese; `cc.en.` → fastText English
 - Falls back to ConceptNet by default if no match
-- **Pre-processing**: `CleanTemplateText` strips QQ tool-call templates and timestamp noise
+- **Pre-processing**: plugins register per-tool `Cleaner` functions; `textForVector` applies them before `CleanText` final normalization
 - **Three-branch vector source**: agent→Response, user→Input, cold_storage→Input+Response
 - **TF-IDF fallback**: auto-fallback to bag-of-words TF-IDF if model download fails or not configured
 
@@ -160,7 +160,7 @@ All vectorization unified under `StaticEmbedder` (`internal/memory/static_embedd
 
 `internal/agent/core/context.go` — `RelevanceContext`
 - Maintains recent event list, writes JSON on each Append/Prune to prevent data loss
-- Pre-vectorization pipeline runs through `CleanTemplateText` to remove template noise
+- Pre-vectorization pipeline: per-tool `Cleaner` functions strip template noise, then `CleanText` for basic whitespace normalization
 - Three-branch `textForVector`: agent events → Response, user events → Input, cold_storage → Input+Response
 - Pretrained word embedding `StaticEmbedder` → CosineSimilarity, auto-fallback to TF-IDF if unavailable
 - Protects last 10 events from eviction; excess candidates are sorted by relevance and archived to document memory