docs(runtime): internal/runtime/loop 44 个文件注释改中文（逐行 1:1，代码零字节改动）

主人 2026-10-03 拍板「注释一律中文」；本模块按长期分批协议（一个模块一次派工）执行。
注释行数 1329 → 1329 逐行 1:1（含中文 33 → 1304）；行尾注释 5 条一并译。
校验：机械校验（非注释改动行）= 空；独立 Go AST 程序（剥注释复渲）证明 44/44 文件代码全等；
全树 go test ./... 58 包 ok / 0 FAIL；交叉编译绿。
gofmt：capacity_loop_test.go / flow.go 改动前即未格式化，按铁律保留原样未动。

internal/runtime/loop/vision.go

@@ -6,34 +6,34 @@ import (
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/model"
 )
 
-// ImageResolver is the loop's seam to the multimodal vision layer (design/06
-// §0). It is called once at the start of Run for every message that carries an
-// image content part, and may rewrite that message so the main model can reason
-// over the image. The concrete resolver lives in the vision package and decides,
-// via the vision Router, whether to keep the image for a vision-capable main
-// model or fold it into a text description produced by the vision/OCR tool ("先
-// 看图再对话"). Nil leaves the image content untouched so it flows straight to a
-// vision-capable main model.
+// ImageResolver 是循环通向多模态视觉层的接缝（design/06
+// §0）。它在 Run 开始时对每条携带图像内容部件的消息调用一次，
+// 并可以改写该消息，使主模型能对图像进行推理。具体
+// resolver 位于 vision 包，它通过 vision Router 决定
+// 是保留图像给支持视觉的主模型，还是折叠为
+// vision/OCR 工具产出的文字描述（「先
+// 看图再对话」）。为 nil 时图像内容保持原样，直接流向
+// 支持视觉的主模型。
 type ImageResolver interface {
-	// Resolve rewrites msg, which carries at least one image content part. It
-	// returns the (possibly rewritten) message. An error leaves the original
-	// message in place so the turn still proceeds.
+	// Resolve 改写 msg，其中至少携带一个图像内容部件。它
+	// 返回（可能已改写的）消息。出错时保留原始
+	// 消息，使该 turn 仍能继续。
 	Resolve(ctx context.Context, msg model.Message) (model.Message, error)
 }
 
-// ImageResolveFunc adapts a function to the ImageResolver interface.
+// ImageResolveFunc 把一个函数适配为 ImageResolver 接口。
 type ImageResolveFunc func(ctx context.Context, msg model.Message) (model.Message, error)
 
-// Resolve implements ImageResolver.
+// Resolve 实现 ImageResolver。
 func (f ImageResolveFunc) Resolve(ctx context.Context, msg model.Message) (model.Message, error) {
 	return f(ctx, msg)
 }
 
-// resolveImages rewrites every image-bearing message in messages using the
-// injected resolver. It returns the input slice unchanged when no resolver is
-// configured, no image is present, or a message fails to resolve (the failure is
-// logged and the original message is kept so the turn still runs). A fresh slice
-// is returned when any message changed.
+// resolveImages 用注入的 resolver 改写 messages 中每条
+// 携带图像的消息。未配置 resolver、没有图像、或某条消息
+// 解析失败（失败会被记录日志并保留原消息，使该 turn 仍能
+// 运行）时，它原样返回输入切片。任一消息发生变化时
+// 返回一个新切片。
 func (l *Loop) resolveImages(ctx context.Context, messages []model.Message) []model.Message {
 	if l.imageResolver == nil {
 		return messages
@@ -60,7 +60,7 @@ func (l *Loop) resolveImages(ctx context.Context, messages []model.Message) []mo
 	return out
 }
 
-// messageHasImage reports whether any content part of msg is an image part.
+// messageHasImage 报告 msg 是否有任何内容部件是图像部件。
 func messageHasImage(m model.Message) bool {
 	for _, part := range m.Content {
 		if part.Type == model.ContentTypeImage {