Version: 0.9.26.dev.260417

后端：
1. Prompt 层从 execute 专属骨架重构为全节点统一四段式 buildUnifiedStageMessages
  - 新增 unified_context.go：定义 StageMessagesConfig + buildUnifiedStageMessages 统一骨架，所有节点（Chat/Plan/Execute/Deliver/DeepAnswer）共用同一套 msg0~msg3 拼装逻辑
  - 新增 conversation_view.go：通用对话历史渲染 buildConversationHistoryMessage，各节点复用，不再各自维护提取逻辑
  - 新增 chat_context.go / plan_context.go / deliver_context.go：各节点自行渲染 msg1（对话视图）和 msg2（工作区），统一层只负责"怎么拼"，不再替节点决定"放什么"
  - Chat/Plan/Deliver/Execute 的 BuildXXXMessages 全部从 buildStageMessages 切到 buildUnifiedStageMessages，移除旧路径
  - 删除 execute_pinned.go：execute 记忆渲染合并到统一层 renderUnifiedMemoryContext
  - Plan prompt 不再在 user prompt 中拼装任务类 ID 列表和 renderStateSummary，改为依赖 msg2 规划工作区；Chat 粗排判断从"上下文有任务类 ID"改为"批量调度需求"
  - Deliver prompt 新增 IsAborted/IsExhaustedTerminal 区分，支持粗排收口和主动终止场景
2. Execute ReAct 上下文简化——移除归档搬运、窗口裁剪和重复工具压缩
  - 移除 splitExecuteLoopRecordsByBoundary、findLatestExecuteBoundaryMarker、tailExecuteLoops、compressExecuteLoopObservationsByTool、buildEarlyExecuteReactSummary、trimExecuteMessage1ByBudget 等六个函数
  - 移除 executeLoopWindowLimit / executeConversationTurnLimit / executeMessage1MaxRunes 等预算常量
  - msg1 不再从历史中归档上一轮 ReAct 结果，只保留真实对话流（user + assistant speak），全量注入
  - msg2 不再按 loop_closed / step_advanced 边界切分"归档/活跃"，直接全量注入全部 ReAct Loop 记录
  - token 预算由统一压缩层兜底，prompt 层不再做提前裁剪
3. 压缩层从 Execute 专属提升为全节点通用 UnifiedCompact
  - 删除 execute_compact.go（Execute 专属压缩文件）
  - 新增 unified_compact.go：UnifiedCompactInput 参数化，各节点（Plan/Chat/Deliver/Execute）构造时从自己的 NodeInput 提取公共字段，消除对 Execute 的直接依赖
  - CompactionStore 接口扩展 LoadStageCompaction / SaveStageCompaction，各节点按 stageKey 独立维护压缩状态互不覆盖
  - 非 4 段式消息时退化成按角色汇总统计，确保 context_token_stats 仍然刷新
4. Retry 重试机制全面下线
  - dao/agent.go：saveChatHistoryCore / SaveChatHistory / SaveChatHistoryInTx 移除 retry_group_id / retry_index /
  retry_from_user_message_id / retry_from_assistant_message_id 四个参数，修复乱码注释
  - dao/agent-cache.go：移除 ApplyRetrySeed 和 extractMessageHistoryID 两个方法
  - conv/agent.go：ToEinoMessages 不再回灌 retry_* 字段到运行期上下文
  - service/agentsvc/agent.go：移除 chatRetryMeta 及 resolveRetryGroupID / buildRetrySeed 等全部重试逻辑
  - service/agentsvc/agent_quick_note.go：整个文件删除（retry 快速补写路径已无用）
  - service/events/chat_history_persist.go：移除 retry 参数传递
5. 节点层瘦身 + 可见消息逐条持久化
  - agent_nodes.go 大幅简化：Chat/Plan/Execute/Deliver 节点方法移除 ToolSchema 注入、状态摘要渲染等逻辑，只做参数转发和状态落盘
  - 新增 visible_message.go：persistVisibleAssistantMessage 统一处理可见 assistant speak 的实时持久化，失败仅记日志不中断主流程
  - 新增 llm_debug.go：logNodeLLMContext 统一打印 LLM 上下文调试日志
  - graph_run_state.go 新增 PersistVisibleMessageFunc 类型 + AgentGraphDeps.PersistVisibleMessage 字段
  - service/agentsvc/agent_newagent.go 精简主循环，注入 PersistVisibleMessage 回调；agent_history.go 精简历史构建
  - token_budget.go 移除 Execute 专属预算检查，统一到通用预算

前端：
1. 移除 retry 相关 UI 和类型
  - agent.ts 移除 retry_group_id / retry_index / retry_total 字段及 normalize 逻辑
  - AssistantPanel.vue 移除 retry 相关 UI 和交互代码（约 700 行精简）
  - dashboard.ts 移除 retry 相关类型定义
  - AssistantView.vue 微调
2. ContextWindowMeter 压缩次数展示和数值格式优化
  - 新增 formatCompactCount 工具函数，千位以上用 k 单位压缩（如 80k）
  - 新增压缩次数显示
3.修复了新对话发消息时，user和assistant消息被自动调换的bug

仓库：无

backend/newAgent/node/chat.go

@@ -45,12 +45,14 @@ const (
 // 3. ConversationContext 提供历史对话；
 // 4. ConfirmAction 仅在 confirm 恢复场景下由前端传入 "accept" / "reject"。
 type ChatNodeInput struct {
-	RuntimeState        *newagentmodel.AgentRuntimeState
-	ConversationContext *newagentmodel.ConversationContext
-	UserInput           string
-	ConfirmAction       string
-	Client              *infrallm.Client
-	ChunkEmitter        *newagentstream.ChunkEmitter
+	RuntimeState          *newagentmodel.AgentRuntimeState
+	ConversationContext   *newagentmodel.ConversationContext
+	UserInput             string
+	ConfirmAction         string
+	Client                *infrallm.Client
+	ChunkEmitter          *newagentstream.ChunkEmitter
+	CompactionStore       newagentmodel.CompactionStore // 上下文压缩持久化
+	PersistVisibleMessage newagentmodel.PersistVisibleMessageFunc
 }
 
 // RunChatNode 执行一轮聊天节点逻辑。
@@ -94,6 +96,15 @@ func RunChatNode(ctx context.Context, input ChatNodeInput) error {
 	}
 	nonce := uuid.NewString()
 	messages := newagentprompt.BuildChatRoutingMessages(conversationContext, input.UserInput, flowState, nonce)
+	messages = compactUnifiedMessagesIfNeeded(ctx, messages, UnifiedCompactInput{
+		Client:          input.Client,
+		CompactionStore: input.CompactionStore,
+		FlowState:       flowState,
+		Emitter:         emitter,
+		StageName:       chatStageName,
+		StatusBlockID:   chatStatusBlockID,
+	})
+	logNodeLLMContext(chatStageName, "routing", flowState, messages)
 
 	reader, err := input.Client.Stream(ctx, messages, infrallm.GenerateOptions{
 		Temperature: 0.7,
@@ -281,7 +292,7 @@ func handleDirectReplyStream(
 	if effectiveThinking {
 		return handleThinkingReplyStream(ctx, reader, input, emitter, conversationContext, flowState)
 	}
-	return handleDirectReplyContinueStream(ctx, reader, emitter, conversationContext, flowState, firstVisible)
+	return handleDirectReplyContinueStream(ctx, reader, input, emitter, conversationContext, flowState, firstVisible)
 }
 
 // handleThinkingReplyStream 处理需要思考的回复：关闭路由流 → 第二次 thinking 流式调用。
@@ -295,7 +306,16 @@ func handleThinkingReplyStream(
 ) error {
 	_ = reader.Close()
 
-	deepMessages := newagentprompt.BuildDeepAnswerMessages(conversationContext, input.UserInput)
+	deepMessages := newagentprompt.BuildDeepAnswerMessages(flowState, conversationContext, input.UserInput)
+	deepMessages = compactUnifiedMessagesIfNeeded(ctx, deepMessages, UnifiedCompactInput{
+		Client:          input.Client,
+		CompactionStore: input.CompactionStore,
+		FlowState:       flowState,
+		Emitter:         emitter,
+		StageName:       chatStageName,
+		StatusBlockID:   chatStatusBlockID,
+	})
+	logNodeLLMContext(chatStageName, "direct_reply_thinking", flowState, deepMessages)
 	deepReader, err := input.Client.Stream(ctx, deepMessages, infrallm.GenerateOptions{
 		Temperature: 0.5,
 		MaxTokens:   2000,
@@ -322,6 +342,7 @@ func handleThinkingReplyStream(
 	deepText = strings.TrimSpace(deepText)
 	if deepText != "" {
 		conversationContext.AppendHistory(schema.AssistantMessage(deepText, nil))
+		persistVisibleAssistantMessage(ctx, input.PersistVisibleMessage, flowState, schema.AssistantMessage(deepText, nil))
 	}
 
 	flowState.Phase = newagentmodel.PhaseChatting
@@ -332,6 +353,7 @@ func handleThinkingReplyStream(
 func handleDirectReplyContinueStream(
 	ctx context.Context,
 	reader infrallm.StreamReader,
+	input ChatNodeInput,
 	emitter *newagentstream.ChunkEmitter,
 	conversationContext *newagentmodel.ConversationContext,
 	flowState *newagentmodel.CommonState,
@@ -370,7 +392,9 @@ func handleDirectReplyContinueStream(
 
 	text := fullText.String()
 	if strings.TrimSpace(text) != "" {
-		conversationContext.AppendHistory(schema.AssistantMessage(text, nil))
+		msg := schema.AssistantMessage(text, nil)
+		conversationContext.AppendHistory(msg)
+		persistVisibleAssistantMessage(ctx, input.PersistVisibleMessage, flowState, msg)
 	}
 
 	flowState.Phase = newagentmodel.PhaseChatting
@@ -568,7 +592,16 @@ func handleDeepAnswerStream(
 	if effectiveThinking {
 		thinkingOpt = infrallm.ThinkingModeEnabled
 	}
-	deepMessages := newagentprompt.BuildDeepAnswerMessages(conversationContext, input.UserInput)
+	deepMessages := newagentprompt.BuildDeepAnswerMessages(flowState, conversationContext, input.UserInput)
+	deepMessages = compactUnifiedMessagesIfNeeded(ctx, deepMessages, UnifiedCompactInput{
+		Client:          input.Client,
+		CompactionStore: input.CompactionStore,
+		FlowState:       flowState,
+		Emitter:         emitter,
+		StageName:       chatStageName,
+		StatusBlockID:   chatStatusBlockID,
+	})
+	logNodeLLMContext(chatStageName, "deep_answer", flowState, deepMessages)
 	deepReader, err := input.Client.Stream(ctx, deepMessages, infrallm.GenerateOptions{
 		Temperature: 0.5,
 		MaxTokens:   2000,
@@ -601,7 +634,9 @@ func handleDeepAnswerStream(
 	}
 
 	// 4. 完整回复写入 history。
-	conversationContext.AppendHistory(schema.AssistantMessage(deepText, nil))
+	msg := schema.AssistantMessage(deepText, nil)
+	conversationContext.AppendHistory(msg)
+	persistVisibleAssistantMessage(ctx, input.PersistVisibleMessage, flowState, msg)
 
 	flowState.Phase = newagentmodel.PhaseChatting
 	return nil