docs(comments): 注释中文化 · internal/runtime/orchestration（29 文件，纯替换）

- 只翻注释/文档字符串：剥离注释后代码行逐字节不变（机械校验只剩允许的行尾注释形态）
- 裁决编号与 design 节号（02.4.3 / 11.4.2 / design/05 §9 等）逐字保留
- 复核：go build 绿；orchestration 及其子包（audit/comm）测试绿；gofmt 干净

internal/runtime/orchestration/options.go

@@ -12,94 +12,86 @@ import (
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/trace"
 )
 
-// Defaults for the orchestration layer.
+// 编排层的默认值。
 const (
-	// DefaultMaxParallel is the maximum number of sub-agents that run at once
-	// when Options.MaxParallel is non-positive.
+	// DefaultMaxParallel 是 Options.MaxParallel 为非正数时同时运行的子代理
+	// 数量上限。
 	DefaultMaxParallel = 4
 
-	// defaultAgentID is the comm probe identity used when Options.AgentID is
-	// blank and a probe must be built from Bus.
+	// defaultAgentID 是 Options.AgentID 为空、且必须由 Bus 构建探针时所用的
+	// comm 探针身份。
 	defaultAgentID = "orchestrator"
 )
 
-// Options configures a Scheduler built by New. All fields are optional; each nil
-// dependency degrades gracefully (a missing Loop makes sub-agents fail fast, a
-// missing Comm skips progress events, a missing Approver makes Approve error,
-// and so on).
+// Options 配置由 New 构建的 Scheduler。所有字段都可选；每个为 nil 的依赖都优雅
+// 降级（缺 Loop 使子代理快速失败，缺 Comm 跳过进度事件，缺 Approver 使 Approve
+// 报错，等等）。
 type Options struct {
-	// MaxParallel caps how many sub-agents execute concurrently. Excess sub-agents
-	// queue until a slot frees. Non-positive selects DefaultMaxParallel (4).
+	// MaxParallel 限制同时执行的子代理数量。超出的子代理排队直到有空位。
+	// 非正数则选用 DefaultMaxParallel（4）。
 	MaxParallel int
 
-	// PerAgentTimeout bounds every sub-agent's run. When it elapses the sub-agent
-	// is aborted (status aborted). Non-positive means no timeout.
+	// PerAgentTimeout 约束每个子代理的运行时限。超时后该子代理被中止
+	// （状态 aborted）。非正数表示不设时限。
 	PerAgentTimeout time.Duration
 
-	// Loop is the execution template: a *loop.Loop used to run every sub-agent.
-	// It must be safe for concurrent Run calls (as loop.Loop documents); the
-	// template's agent/tools/guardrails/persona apply to every sub-agent. When
-	// nil, sub-agents fail fast with ErrNoRunner.
+	// Loop 是执行模板：用于运行每个子代理的 *loop.Loop。它必须能安全地并发调用
+	// Run（如 loop.Loop 自身文档所述）；模板的 agent/tools/guardrails/persona
+	// 适用于每个子代理。为 nil 时子代理以 ErrNoRunner 快速失败。
 	Loop *loop.Loop
 
-	// Bus is the in-process event bus used for progress events and, when Comm is
-	// nil, to build a default comm probe. When nil no events are published.
+	// Bus 是进程内事件总线，用于发布进度事件；Comm 为 nil 时也由它构建默认
+	// comm 探针。为 nil 时不发布任何事件。
 	Bus bus.Bus
 
-	// Comm is the comm probe used to publish progress events. When nil, a probe
-	// bound to AgentID is built from Bus (when Bus is non-nil).
+	// Comm 是用于发布进度事件的 comm 探针。为 nil 时，用 Bus（Bus 非 nil 时）
+	// 构建一个绑定到 AgentID 的探针。
 	Comm *comm.Probe
 
-	// Memory is the long-term memory store used by SinkMemory. Optional.
+	// Memory 是 SinkMemory 所用的长期记忆存储。可选。
 	Memory *memory.Store
 
-	// Tracer emits a per-sub-agent span (kind subagent) around each run. Optional.
+	// Tracer 为每次运行发射一个子代理 span（kind subagent）。可选。
 	Tracer *trace.Tracer
 
-	// Flow, when non-nil, receives the sub-agent span transitions so a spawned
-	// branch appears in the flow graph of the session named by
-	// AgentSpec.ParentSession (design/19 §2). *loop.FlowPublisher is the
-	// production implementation. Optional: a nil sink leaves sub-agent branches
-	// unvisualized (the sub-agent's own inner spans still fold into the parent
-	// graph through the loop's flow branch).
+	// Flow 非 nil 时接收子代理 span 的状态转移，使派生出的分支出现在
+	// AgentSpec.ParentSession 所指会话的流程图里（design/19 §2）。
+	// *loop.FlowPublisher 是生产实现。可选：sink 为 nil 时子代理分支不被可视化
+	// （子代理自身的内部 span 仍会经循环的 flow 分支折进父图）。
 	Flow FlowSpanSink
 
-	// Approver records sensitive-operation review-and-approve (代审) triggered by
-	// Approve. Policy judgement belongs to the upper layer. Optional.
+	// Approver 记录由 Approve 触发的敏感操作「代审」。策略判断属于上层。可选。
 	Approver *audit.Approver
 
-	// PersonaExists reports whether a role id can run with its own instructions,
-	// i.e. whether the per-role agent pool behind Loop (loop.Options.Agents) has an
-	// entry for it (design/22 §8-2). It gates AgentSpec.PersonaID: a dispatch naming
-	// an id this returns false for is rejected with ErrUnknownPersona rather than
-	// running as the default role's prompt. Nil means "this deployment knows no
-	// role", so a dispatch that names a role is rejected too — deciding nothing
-	// silently is the point. Omitting the persona is unaffected by this.
+	// PersonaExists 报告某个角色 id 能否以自身指令运行，即 Loop 背后的按角色
+	// agent 池（loop.Options.Agents）里是否有它的条目（design/22 §8-2）。它把守
+	// AgentSpec.PersonaID：指名了一个它返回 false 的 id 的派发会被拒绝并返回
+	// ErrUnknownPersona，而不是按默认角色的提示词运行。为 nil 意味着「本部署不认识
+	// 任何角色」，因此指名角色的派发同样被拒 —— 关键是绝不悄悄替调用方做决定。
+	// 省略 persona 的派发不受它影响。
 	PersonaExists func(personaID string) bool
 
-	// Logger is the base logger. Nil is replaced with a discard logger tagged with
-	// source "orchestration".
+	// Logger 是基础 logger。为 nil 时替换为标注了来源 "orchestration" 的
+	// 丢弃式 logger。
 	Logger *slog.Logger
 
-	// AgentID is the comm probe identity. When blank and a probe must be built
-	// from Bus, "orchestrator" is used.
+	// AgentID 是 comm 探针身份。为空且必须由 Bus 构建探针时，使用
+	// "orchestrator"。
 	AgentID string
 }
 
-// FlowSpanSink folds a span transition into a session's live flow graph so the
-// realtime visualization shows the work in flight (design/19 §1). *loop.FlowPublisher
-// is the production implementation; tests substitute a capturing fake. The
-// interface keeps orchestration from depending on the concrete publisher beyond
-// the loop template it already takes.
+// FlowSpanSink 把一个 span 的状态转移折进会话的实时流程图，使实时可视化展示在飞的
+// 工作（design/19 §1）。*loop.FlowPublisher 是生产实现；测试替换为捕获式假实现。
+// 该接口让编排层除了已有的循环模板之外，不必再依赖那个具体发布器。
 type FlowSpanSink interface {
-	// SpanStarted registers a running placeholder node for a span that just began.
+	// SpanStarted 为一个刚刚开始的 span 登记运行中的占位节点。
 	SpanStarted(sessionID string, sp *trace.Span)
-	// SpanFinished folds a just-finished span into the session graph.
+	// SpanFinished 把一个刚结束的 span 折进会话图。
 	SpanFinished(sessionID string, sp *trace.Span)
 }
 
-// wrapLoop adapts a *loop.Loop into the runner interface, substituting a no-op
-// runner (fail-fast) when the template is nil.
+// wrapLoop 把 *loop.Loop 适配成 runner 接口；模板为 nil 时替换为空操作 runner
+// （快速失败）。
 func wrapLoop(l *loop.Loop) runner {
 	if l == nil {
 		return noopRunner{}
@@ -107,12 +99,11 @@ func wrapLoop(l *loop.Loop) runner {
 	return l
 }
 
-// scopedRunner picks the runner that executes sub: without a tool whitelist the
-// configured template runs as-is（缺省全开，继承主 agent 全量工具集）；with one,
-// a *loop.Loop template is derived through WithToolWhitelist so only the listed
-// tools pass（design/05 §7 裁决 02.4.1）. A non-loop runner (tests inject mocks)
-// is returned unchanged — the whitelist still rides the run context for it to
-// observe via loop.ToolWhitelistFrom.
+// scopedRunner 挑选执行 sub 的 runner：没有工具白名单时按原样运行已配置的模板
+// （缺省全开，继承主 agent 全量工具集）；有白名单时，为 *loop.Loop 模板经
+// WithToolWhitelist 派生出只放行所列工具的新模板（design/05 §7 裁决 02.4.1）。
+// 非 loop 的 runner（测试注入的 mock）原样返回 —— 白名单仍随运行上下文传递，它可经
+// loop.ToolWhitelistFrom 自行读取。
 func (s *Scheduler) scopedRunner(sub *SubAgent) runner {
 	if len(sub.ToolWhitelist) == 0 {
 		return s.runner
@@ -123,9 +114,8 @@ func (s *Scheduler) scopedRunner(sub *SubAgent) runner {
 	return s.runner
 }
 
-// effectiveTimeout resolves the deadline one sub-agent runs under: a positive
-// per-call override wins; otherwise the scheduler's PerAgentTimeout applies
-// (non-positive = no deadline).
+// effectiveTimeout 解析某个子代理运行时所受的时限：正的按调用覆盖优先；否则套用
+// 调度器的 PerAgentTimeout（非正 = 无期限）。
 func effectiveTimeout(override, schedulerDefault time.Duration) time.Duration {
 	if override > 0 {
 		return override