Version: 0.9.3.dev.260407
后端:
1.Execute 上下文修复(无限循环 / 重复确认根治)
- 更新node/execute.go:speak 写入历史(修复旧 TODO);confirm 动作 speak 不再丢失;
continue 无工具调用时写 reason 保证上下文推进;区分 tool_call 数组/JSON损坏两种
correction hint;goal_check hint 区分 plan/ReAct 模式
- 更新node/execute.go:新增 AlwaysExecute 字段,extra.always_execute=true 时写工具
跳过确认闸门直接执行并持久化
- 更新model/graph_run_state.go:AgentGraphRequest 新增 AlwaysExecute;新增
WriteSchedulePreviewFunc 类型和 WriteSchedulePreview Dep
- 更新service/agentsvc/agent.go:新增 readAgentExtraBool 辅助
2.粗排全链路修复
- 更新service/agentsvc/agent_newagent.go:makeRoughBuildFunc 改用 HybridScheduleEntry
而非 TaskClassItem.EmbeddedTime,普通时段放置不再被丢弃
- 更新conv/schedule_provider.go:LoadScheduleState 从 task class 日期范围推算多周
规划窗口,不再硬编码当前周 7 天;DayMapping 覆盖全部相关周,粗排跨周结果不再
被 WeekDayToDay 静默丢弃
- 更新node/rough_build.go:pinned block 区分有/无未覆盖 pending 任务两种情况,
有 pending 时明确操作顺序(find_free→place)和完成判定,防止 LLM 重复调
list_tasks;新增 countPendingTasks 辅助(只统计 Slots 为空的真正未覆盖任务)
- 更新model/common_state.go:新增 StartDirectExecute(),Chat 直接路由 execute 时
清空旧 PlanSteps,修复跨会话 HasPlan() 误判导致 ReAct 走 plan 模式的 bug
- 更新node/chat.go:handleRouteExecute 改用 StartDirectExecute()
3.排程预览缓存迁移至 Deliver 节点
- 更新node/agent_nodes.go:Deliver 节点完成后调用 WriteSchedulePreview,只有任务
真正完成才写预览缓存,中断路径不写中间态
- 更新service/agentsvc/agent_newagent.go:注入 makeWriteSchedulePreviewFunc;移除
graph 结束后的内联写入;makeRoughBuildFunc 注释修正
- 更新conv/schedule_preview.go:ScheduleStateToPreview 补设 GeneratedAt
- 更新model/agent.go:GetSchedulePlanPreviewResponse 新增 HybridEntries 字段
- 更新service/agentsvc/agent_schedule_preview.go:GET handler Redis/MySQL 两条路径
均透传 HybridEntries
4.Execute thinking 模式修复
- 更新newAgent/llm/ark_adapter.go:thinking 开启时强制 temperature=1,MaxTokens 自
动托底至 16000,调用方与适配层行为对齐
- 更新node/execute.go:调用参数同步改为 temperature=1.0 / MaxTokens=16000
undo:
1.流式推送换行未修复(undo)
2.上下文依然待审视
前端:无
仓库:无
This commit is contained in:
@@ -4,6 +4,7 @@ import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
|
||||
newagentmodel "github.com/LoveLosita/smartflow/backend/newAgent/model"
|
||||
newagenttools "github.com/LoveLosita/smartflow/backend/newAgent/tools"
|
||||
@@ -214,6 +215,7 @@ func (n *AgentNodes) Execute(ctx context.Context, st *newagentmodel.AgentGraphSt
|
||||
ScheduleState: scheduleState,
|
||||
SchedulePersistor: st.Deps.SchedulePersistor,
|
||||
OriginalScheduleState: st.OriginalScheduleState,
|
||||
AlwaysExecute: st.Request.AlwaysExecute,
|
||||
},
|
||||
); err != nil {
|
||||
return nil, err
|
||||
@@ -247,6 +249,16 @@ func (n *AgentNodes) Deliver(ctx context.Context, st *newagentmodel.AgentGraphSt
|
||||
return nil, err
|
||||
}
|
||||
|
||||
// 任务完成后写排程预览缓存:只有走到 Deliver 才代表排程结果已稳定,
|
||||
// 中断(confirm/ask_user)路径不写,避免把中间态暴露给前端。
|
||||
if st.Deps.WriteSchedulePreview != nil && st.ScheduleState != nil {
|
||||
flowState := st.EnsureFlowState()
|
||||
if err := st.Deps.WriteSchedulePreview(ctx, st.ScheduleState, flowState.UserID, flowState.ConversationID, flowState.TaskClassIDs); err != nil {
|
||||
// 写缓存失败不阻断主流程,降级为仅 log。
|
||||
log.Printf("[WARN] deliver: 写入排程预览缓存失败 chat=%s: %v", flowState.ConversationID, err)
|
||||
}
|
||||
}
|
||||
|
||||
saveAgentState(ctx, st)
|
||||
return st, nil
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user