docs(cyrene): cmd/cyrene 存量英文注释中文化（22 个非测试文件，仅注释）

- 四组并行完成：main/wire*.go、wire_capacity|channels|runtime、channels|persona_*|emotion|observability、
  voice|plugins|stream|skills|vision|subagent_tool|extractor|mcp|sessionread_tool|terminal_tool。
- 机械校验（git diff -U0 去 // 行与空行）仅剩 wire_frontend.go:84 一处行尾注释：代码前缀
  「\ta.gw = gw 」经 cat -A 与 HEAD 逐字节比对一致（allow 清单已声明）。
- 验收：隔离 worktree（HEAD + 本批 patch）go build/vet 绿、全树 58 包 ok、
  linux/amd64 + darwin/arm64 交叉编译绿；gofmt -l 干净。
- 备注：整树两次红均为负载敏感 flake（backthink / orchestration 的 timeout 类用例单独 -count=20 全过）。

cmd/cyrene/extractor.go

@@ -9,27 +9,23 @@ import (
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/model"
 )
 
-// memoryOwnerRoleID is the role id the composition root authors extracted
-// memories with; the owner is the only actor whose private memory is written
-// (group/stranger conversations never extract at all, design/11 §2).
+// memoryOwnerRoleID 是组合根写入提取出的记忆时所用的角色 id；主人是唯一会写入
+// 私有记忆的 actor（群聊/陌生人会话根本不提取，design/11 §2）。
 const memoryOwnerRoleID = "owner"
 
-// buildMemoryExtractor selects the memory extractor the loop runs after each
-// settled turn (design/03 §1 LLM 异步自动提取):
+// buildMemoryExtractor 选择循环在每轮落定后运行的记忆提取器（design/03 §1
+// LLM 异步自动提取）：
 //
-//   - the LLM extractor when the provider stack has a usable active group, so
-//     the model denoises and deduplicates what is worth remembering;
-//   - the deterministic ManualExtractor otherwise, so a keyless deployment still
-//     records the owner's explicit "记住 X" directives instead of failing a model
-//     call on every turn.
+//   - provider 栈存在可用的活动组时用 LLM 提取器，由模型去噪并去重真正值得记的内容；
+//   - 否则用确定性的 ManualExtractor，使无 key 的部署仍能记录主人显式的「记住 X」
+//     指令，而不是每轮都让模型调用失败。
 //
-// The extractor deliberately holds NO persona: one process now answers as several
-// roles (design/22 §4.2), so a persona baked in here would file every extracted
-// memory under that one role. The loop stamps each item with the role that
-// produced the turn when it persists it (loop.persistMemories).
+// 该提取器刻意不持有任何人设：一个进程现在会以多个角色作答（design/22 §4.2），
+// 若在此固化某个人设，就会把所有提取出的记忆都归到那一个角色下。循环在持久化时
+// 用产生该轮的角色逐条打标（loop.persistMemories）。
 //
-// The loop detaches the LLM extractor to a background goroutine (ExtractAsync);
-// see internal/runtime/loop/memory.go.
+// 循环会把 LLM 提取器分离到后台 goroutine（ExtractAsync）；见
+// internal/runtime/loop/memory.go。
 func (a *app) buildMemoryExtractor() memory.Extractor {
 	if llmGroupUsable(a.llm) {
 		a.log.Info("memory extractor: llm", "model", a.llm.Model(), "provider", a.llm.Provider())
@@ -39,14 +35,12 @@ func (a *app) buildMemoryExtractor() memory.Extractor {
 	return memory.NewManualExtractor("", memoryOwnerRoleID)
 }
 
-// llmGroupUsable reports whether the active model group of the runtime stack can
-// actually be called: a model and a base URL are mandatory, and either an API key
-// is configured or the endpoint is a local/private address, where a keyless call
-// is the normal case (a self-hosted OpenAI-compatible server).
+// llmGroupUsable 报告运行时栈的活动模型组是否真的可调用：模型与 base URL 是必需
+// 项，且要么配置了 API key，要么端点是本地/内网地址 —— 后者无 key 调用属正常情况
+// （自托管的 OpenAI 兼容服务）。
 //
-// It is deliberately a cheap structural check, never a probe request: boot must
-// not spend a model call. A group that looks usable but fails at call time only
-// logs an extraction error (extraction failures are never fatal).
+// 它刻意只做廉价的静态检查，绝不发探测请求：启动不该花掉一次模型调用。看起来可用
+// 但调用时才失败的组，只会记一条提取错误日志（提取失败从不致命）。
 func llmGroupUsable(llm *model.RuntimeLLM) bool {
 	if llm == nil {
 		return false
@@ -61,8 +55,8 @@ func llmGroupUsable(llm *model.RuntimeLLM) bool {
 	return keylessEndpoint(group.BaseURL)
 }
 
-// keylessEndpoint reports whether baseURL points at a loopback or private-network
-// host, where a missing API key is expected rather than a misconfiguration.
+// keylessEndpoint 报告 baseURL 是否指向回环或内网主机 —— 这类地址上缺少 API key
+// 是预期情况，而非配置错误。
 func keylessEndpoint(baseURL string) bool {
 	parsed, err := url.Parse(strings.TrimSpace(baseURL))
 	if err != nil {