docs(comments): 注释中文化 · internal/runtime/multimodal（21 文件，纯替换）

- 只翻注释/文档字符串，代码零变化：go/scanner 词法流比对 21 文件 token+字面量全等，增删行数 1:1（467/467）
- 刻意保留非散文英文：JSON Schema description、工具 Description() 返回值、adapter prompt、API 路径与命令示例、环境变量名
- 逐行确认代码前缀未变，未触碰其他模块

internal/runtime/multimodal/vision/resolver.go

@@ -7,31 +7,31 @@ import (
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/model"
 )
 
-// ModelInfoProvider supplies the main model's vision capability so the resolver
-// can route an image the way the vision Router decides (design/06 §0). It is
-// called per image; the same provider is shared across a single resolution.
+// ModelInfoProvider 提供主模型的视觉能力，使解析器
+// 能按 vision Router 的判定（design/06 §0）路由图像。它按
+// 图像逐个调用；同一次解析中共享同一个 provider。
 type ModelInfoProvider func() ModelInfo
 
-// ToolInvoker invokes a registered tool (the vision or OCR tool) by name with
-// the given arguments. It is satisfied by *tool.Dispatcher.Invoke.
+// ToolInvoker 按名字与给定参数调用一个已注册的工具（视觉或 OCR
+// 工具）。由 *tool.Dispatcher.Invoke 满足。
 type ToolInvoker func(ctx context.Context, name string, args map[string]any) (any, error)
 
-// MessageResolver is the loop's concrete ImageResolver. For each image part in a
-// user message it asks the vision Router how to route it: when the main model
-// supports vision and is confident, the image part is kept so the main model sees
-// the image; otherwise the vision/OCR tool is invoked and its text result replaces
-// the image part, so a text-only main model can reason over the image ("先看图再
-// 对话"). It is safe for concurrent use.
+// MessageResolver 是 loop 的具体 ImageResolver。对用户消息中的
+// 每个图像部件，它向 vision Router 询问如何路由：当主模型
+// 支持视觉且有信心时，保留该图像部件让主模型看到
+// 图像；否则调用 vision/OCR 工具，用其文字结果替换
+// 图像部件，使纯文本主模型也能对图像推理（「先看图再
+// 对话」）。它可安全并发使用。
 type MessageResolver struct {
 	router *Router
 	info   ModelInfoProvider
 	invoke ToolInvoker
 }
 
-// NewMessageResolver builds a MessageResolver. router decides the layer; info
-// reports the main model's vision capability; invoke runs a registered vision/OCR
-// tool. A nil invoke leaves any tool route failed (the image is then kept), so a
-// resolver without tools degrades to the main-model path.
+// NewMessageResolver 构造一个 MessageResolver。router 决定
+// 分层；info 报告主模型的视觉能力；invoke 运行一个已注册的 vision/OCR
+// 工具。invoke 为 nil 时任何工具路由都会失败（此时图像被保留），
+// 因此没有工具的解析器会降级到主模型路径。
 func NewMessageResolver(router *Router, info ModelInfoProvider, invoke ToolInvoker) *MessageResolver {
 	return &MessageResolver{
 		router: router,
@@ -40,10 +40,10 @@ func NewMessageResolver(router *Router, info ModelInfoProvider, invoke ToolInvok
 	}
 }
 
-// Resolve rewrites msg so every image part is either kept (main model sees it) or
-// replaced by a text description produced by the vision/OCR tool. Text parts are
-// preserved in order. It errors only when an image cannot be routed or a tool
-// invocation fails; the caller (loop) then keeps the original message.
+// Resolve 改写 msg，使每个图像部件要么被保留（主模型能看到它），
+// 要么被 vision/OCR 工具产出的文字描述替换。文本部件
+// 按原顺序保留。它仅在图像无法路由或工具
+// 调用失败时报错；此时调用方（loop）保留原始消息。
 func (r *MessageResolver) Resolve(ctx context.Context, msg model.Message) (model.Message, error) {
 	if r.router == nil {
 		return msg, nil
@@ -63,8 +63,8 @@ func (r *MessageResolver) Resolve(ctx context.Context, msg model.Message) (model
 	return model.Message{Role: msg.Role, Content: out}, nil
 }
 
-// resolveImage picks a route and either keeps the image (KindMain) or folds it
-// into a text description via the vision/OCR tool.
+// resolveImage 选出一条路由：要么保留图像（KindMain），
+// 要么经 vision/OCR 工具把它折叠为文字描述。
 func (r *MessageResolver) resolveImage(ctx context.Context, imageURL string) (model.Content, error) {
 	target := ModelInfo{}
 	if r.info != nil {
@@ -73,7 +73,7 @@ func (r *MessageResolver) resolveImage(ctx context.Context, imageURL string) (mo
 	decision := r.router.Route(target, RouteRequest{})
 	switch decision.Kind {
 	case KindMain:
-		// A vision-capable main model sees the image directly.
+		// 支持视觉的主模型直接看到这张图。
 		return model.Content{Type: model.ContentTypeImage, ImageURL: imageURL}, nil
 	case KindVisionTool:
 		return r.invokeTool(ctx, decision.Tool, map[string]any{
@@ -89,8 +89,8 @@ func (r *MessageResolver) resolveImage(ctx context.Context, imageURL string) (mo
 	}
 }
 
-// invokeTool runs a registered vision/OCR tool and turns its text result into a
-// text content part. field is the result map key ("description" or "text").
+// invokeTool 运行一个已注册的 vision/OCR 工具，并把其文字结果转成
+// 文本内容部件。field 是结果 map 的键（"description" 或 "text"）。
 func (r *MessageResolver) invokeTool(ctx context.Context, toolName string, args map[string]any, field string) (model.Content, error) {
 	if r.invoke == nil {
 		return model.Content{}, fmt.Errorf("%s: %w", toolName, ErrNotConfigured)
@@ -102,8 +102,8 @@ func (r *MessageResolver) invokeTool(ctx context.Context, toolName string, args
 	return model.Content{Type: model.ContentTypeText, Text: descriptionFragment(fieldText(result, field))}, nil
 }
 
-// fieldText extracts a string field from a tool result map, tolerating the
-// map[string]any shape returned by the vision/OCR tools.
+// fieldText 从工具结果的 map 中取出字符串字段，兼容
+// vision/OCR 工具返回的 map[string]any 形状。
 func fieldText(result any, field string) string {
 	m, ok := result.(map[string]any)
 	if !ok {
@@ -113,8 +113,8 @@ func fieldText(result any, field string) string {
 	return s
 }
 
-// descriptionFragment labels a tool-produced description so the model can tell it
-// refers to the picture the user attached.
+// descriptionFragment 给工具产出的描述加上标注，使模型能看出它
+// 指的是用户附上的那张图。
 func descriptionFragment(desc string) string {
 	if desc == "" {
 		return "[图片内容] 无法识别该图片"