Add files via upload

config.example.yaml

@@ -10,7 +10,7 @@
 # ============================================
 
 # 前端显示的版本号（可选，不填则显示默认版本）
-version: "v1.7.10"
+version: "v1.7.9"
 # 服务器配置
 server:
   host: 0.0.0.0 # 监听地址，0.0.0.0 表示监听所有网络接口

docs/zh-CN/README.md

@@ -12,7 +12,7 @@
 ## 核心概念与编排
 
 - [架构说明](architecture.md) · [安全模型](security-model.md) · [RBAC](rbac.md)
-- [Agent 与角色](agent-and-role-guide.md) · [Skills](skills-guide.md) · [Eino 多代理](MULTI_AGENT_EINO.md)
+- [Agent 与角色](agent-and-role-guide.md) · [Skills](skills-guide.md) · [Eino 多代理](MULTI_AGENT_EINO.md) · [Agent 最终回复治理](agent-finalization-best-practices.md)
 - [工作流](workflow-graph.md) · [工具执行治理](tool-execution-governance.md) · [人机协同最佳实践](hitl-best-practices.md)
 
 ## 功能指南

docs/zh-CN/agent-finalization-best-practices.md

@@ -0,0 +1,333 @@
+# Agent 最终回复治理最佳实践
+
+[返回中文文档](README.md)
+
+调研日期：2026-07-28
+
+本文聚焦一个具体问题：Agent 在工具调用、推理、计划或子代理协作尚未真正完成时，输出了一段“像结论”的自然语言，前端或编排层把它当作最终回复展示。结论先说清楚：成熟 Agent 系统不会用“最近一段 assistant 文本”判断任务完成，而是用运行时状态、工具状态、验证结果和显式终态事件共同决定是否 final。
+
+## 一、核心结论
+
+1. **最终回复是运行时事件，不是自然语言内容。**
+   “已拿到”“下一步”“Huge breakthrough”这类文本只能作为候选观察或进展，不能作为完成信号。
+
+2. **过程面和交付面必须隔离。**
+   `thinking`、`reasoning_chain`、`planning`、`response_delta`、子代理回复、工具输出都属于过程面；只有通过 final gate 的 `response` / `final` 事件才能写入主消息气泡和 `messages.content`。
+
+3. **复杂任务需要 verifier，而不是更长 prompt。**
+   Prompt 可以提醒模型谨慎，但最终完成必须由代码层判断：是否仍有待执行工具、后台 execution、未完成计划步骤、未验证证据、未记录事实/漏洞、未清理或未说明不可清理。
+
+4. **不同 agent 模式不同，但 final 治理原则一致。**
+   单代理、Deep、Plan-Execute、Supervisor 都需要 final gate。区别只是 gate 的证据来源不同：单代理看工具轨迹，Deep 还要看子代理结果，Plan-Execute 要看 Replanner 的终止判断，Supervisor 要看 `exit` 与 supervisor 汇总。
+
+## 二、成熟 Agent 的公开做法
+
+| 系统 | 公开做法 | 对 final 治理的启发 |
+|---|---|---|
+| Codex | OpenAI 的 Codex prompting guide 建议不要在 prompt 中强行要求 upfront plan、preamble 或 status updates，因为这可能导致 rollout 未完成就停止。 | 不要把“模型自己说的阶段性计划/状态”当完成依据；agent harness 应负责执行循环和收尾。 |
+| Claude Code | Claude Code 提供 `PreToolUse`、`PostToolUse`、`Stop` 等 hooks；`PostToolUse` 明确发生在工具成功执行之后。 | 生命周期事件比自然语言可靠。验证、审计、阻断应挂在确定的阶段边界上。 |
+| Claude Code Subagents | 子代理有独立上下文、自定义系统提示、特定工具权限和独立权限；子代理适合隔离大量检索/日志/文件读取。 | 子代理输出是证据材料，不是主任务最终结论；主代理必须汇总、验收、再 final。 |
+| Claude Code Plan Mode | Plan mode 先读文件并产出计划，获得批准前不编辑。 | 计划与执行是不同状态；计划完成不等于任务完成。 |
+| Cursor Plan Mode | Cursor Plan Mode 会研究代码库、询问澄清问题、生成可审查计划，并等待用户确认后再构建。 | UI 层把 plan/review/build 拆开，用户不会把计划误认为最终交付。 |
+| OpenCode | OpenCode 把 Build、Plan、Review、Debug、Docs 等 agent 分成不同工具权限与用途，Plan agent 只分析规划不做修改。 | 用 agent 能力边界降低误触发：能规划的 agent 不等于能执行完成。 |
+| Eino ADK | Eino ADK 提供事件驱动输出、Runner 回调、中断、checkpoint，以及 Supervisor、Plan-Execute 等协作原语。Plan-Execute 由 Planner、Executor、Replanner 协作。 | 当前项目选型方向正确；需要把事件驱动能力进一步固化为 finalization contract。 |
+
+主要参考：
+
+- OpenAI Codex Prompting Guide: https://developers.openai.com/cookbook/examples/gpt-5/codex_prompting_guide
+- Claude Code Hooks: https://docs.anthropic.com/en/docs/claude-code/hooks
+- Claude Code Subagents: https://docs.anthropic.com/en/docs/claude-code/sub-agents
+- Claude Code Common Workflows: https://docs.anthropic.com/en/docs/claude-code/common-workflows
+- Cursor Agent Best Practices: https://cursor.com/blog/agent-best-practices
+- OpenCode Agents: https://opencode.ai/docs/agents/
+- CloudWeGo Eino ADK: https://www.cloudwego.io/docs/eino/core_modules/eino_adk/
+- CloudWeGo Eino ADK Patterns: https://www.cloudwego.io/docs/eino/overview/eino_adk0_1/
+
+## 三、通用最佳实践
+
+### 1. 建立 Finalization Contract
+
+所有执行入口统一产出一个结构化收尾对象，只有它允许触发最终回复。
+
+```go
+type FinalizationDecision struct {
+    Status             string   // in_progress | completed | blocked | failed | cancelled
+    Finalizable        bool
+    CompletionReason   string   // verified | user_cancelled | timeout | blocked | failed
+    FinalText          string
+    EvidenceVerified   bool
+    EvidenceRefs       []string
+    PendingToolRuns    []string
+    PendingPlanSteps   []string
+    PendingApprovals   []string
+    MissingChecks      []string
+}
+```
+
+硬规则：
+
+- `Finalizable=false` 时禁止发送 `response` 终态事件。
+- `Status=in_progress` 时只能发 `progress`、`planning`、`tool_*`、`reasoning_chain` 等过程事件。
+- `FinalText` 不能为空，但非空不代表可以 final。
+- `PendingToolRuns`、`PendingPlanSteps`、`PendingApprovals` 任一非空时不能 `completed`。
+- `EvidenceVerified=false` 时不能把候选输出写成已验证结论。
+
+### 2. 固定 SSE 事件语义
+
+推荐事件分层：
+
+| 事件 | 展示位置 | 可否写 `messages.content` | 说明 |
+|---|---|---:|---|
+| `progress` | 任务状态/时间线 | 否 | 简短进度 |
+| `planning` | 执行详情 | 否 | 主代理计划、阶段性判断 |
+| `reasoning_chain` / `thinking` | 执行详情 | 否 | 推理/思考摘要 |
+| `tool_call` / `tool_result` | 执行详情 | 否 | 工具事件 |
+| `eino_agent_reply` | 执行详情 | 否 | 子代理返回材料 |
+| `finalization_check` | 执行详情 | 否 | verifier 结果 |
+| `finalization_auto_continue` | 执行详情 | 否 | verifier 触发的工程续跑，`contextInjection=false` |
+| `response` | 主消息气泡 | 是 | 只能在 `data.finalized=true` 时使用 |
+| `done` | 关闭流 | 否 | 仅表示流结束，不表示任务成功 |
+| `error` / `cancelled` | 主消息气泡或系统提示 | 是，终态失败类 | 必须带原因 |
+
+### 3. 把“最终候选”与“最终回复”分开
+
+模型可以输出候选结论，但候选结论必须先进入 `final_candidate` 或 `planning`，再由 verifier 决定是否提升：
+
+```text
+assistant text
+  -> candidate
+  -> finalization gate
+  -> response(finalized=true)
+```
+
+不要这样做：
+
+```text
+assistant text
+  -> response
+```
+
+### 4. Stop-time Verification
+
+借鉴 Claude Code hook 思路，在 agent run 停止时做一次确定性检查：
+
+- 所有工具调用都有对应 tool result。
+- 后台 execution 都处于 terminal 状态，或被明确登记为仍在运行且任务状态为 `in_progress` / `blocked`。
+- Plan-Execute 没有未执行的 required step。
+- Supervisor 没有未汇总的子代理结果。
+- 在 evidence-required 策略下，至少存在可查询到的 completed 工具执行证据。
+
+### 5. 子代理输出只作证据
+
+子代理返回不能直接成为用户最终回复。主代理必须完成：
+
+- 去重和冲突合并。
+- 证据强度排序。
+- 不确定性标注。
+- 范围边界确认。
+- 用户可读交付。
+
+### 6. Prompt 只做软约束，代码做硬约束
+
+Prompt 中可以写：
+
+```text
+Interim observations must be marked as progress, not final.
+Do not produce a final answer until verification is complete.
+```
+
+但真正决定 final 的必须是后端字段和状态机。否则模型只要生成一段像最终结论的自然语言，UI 仍可能误判。
+
+## 四、CyberStrikeAI 当前落地状态
+
+当前项目已经具备一套显式 final gate：
+
+- [internal/agentfinalizer/decision.go](../../internal/agentfinalizer/decision.go) 是唯一的最终回复决策契约。
+- [internal/handler/finalization_helpers.go](../../internal/handler/finalization_helpers.go) 负责把决策结果写入 `process_details`，并且只有 `Finalizable=true` 时才调用 `UpdateAssistantMessageFinalize`。
+- [internal/handler/eino_single_agent.go](../../internal/handler/eino_single_agent.go)、[internal/handler/multi_agent.go](../../internal/handler/multi_agent.go)、[internal/handler/workflow_integration.go](../../internal/handler/workflow_integration.go)、[internal/handler/batch_queue_executor.go](../../internal/handler/batch_queue_executor.go) 均已在收尾处接入 finalizer。
+- [web/static/js/monitor.js](../../web/static/js/monitor.js) 只把 `data.finalized === true` 的 `response` 当最终回复；未最终化文本会显示为最终回复检查未通过。
+- [web/static/js/webshell.js](../../web/static/js/webshell.js) 将流式正文标记为候选输出，只有 `response(finalized=true)` 才切换为完成态。
+- [internal/agentfinalizer/decision_test.go](../../internal/agentfinalizer/decision_test.go) 覆盖 pending tool、HITL、空输出、证据策略要求但缺执行证据、失败证据不能支撑最终化、完成态证据可 final 等回归场景。
+- [internal/handler/finalization_auto_continue.go](../../internal/handler/finalization_auto_continue.go) 在缺 completed 执行证据时最多自动续跑 2 段；续跑只恢复已有模型轨迹，不向 agent 注入新的 user/system 文案。
+
+当前契约的核心规则：
+
+1. **模型自然语言只是 candidate。**
+   `RunResult.Response` 不能直接升级为最终回复，必须经过 `agentfinalizer.Decide`。
+
+2. **所有 `response` 事件必须携带终态字段。**
+   至少包含 `finalized`、`finalizable`、`status`、`completionReason`、`evidenceVerified`、`evidenceRefs`、`pendingExecutionIds`、`missingChecks`。
+
+3. **未完成工具会阻断 final。**
+   `queued/running` 工具执行仍存在时，决策结果为 `in_progress/pending_tool_executions`。
+
+4. **执行证据必须由结构化策略声明。**
+   后端不从用户自然语言、助手回复或 agent mode 名称中推断执行意图。聊天请求通过 `finalization.requireExecutionEvidence` 显式声明；WebShell、Workflow、批量、机器人等执行入口由调用点显式传入 policy。policy 要求证据时，至少需要一个可查询到的 `completed` 工具执行记录；只有 failed/cancelled 记录不能支撑最终化。
+
+5. **缺执行证据先工程续跑，再阻断。**
+   Eino 单代理和 Eino 多代理主链路在 `missing_execution_evidence` 时会先通过已有 trace 自动续跑，不注入额外上下文；达到续跑上限后仍缺证据才写入 blocked。
+
+6. **HITL 和空输出不会 final。**
+   workflow 等待人工确认、空 assistant 文本、Eino 空输出占位均会写入阻断文案，而不是成功总结。
+
+## 五、贴合当前项目的推荐架构
+
+当前采用的链路是：
+
+```text
+Agent / Eino ADK events
+  -> event normalizer
+  -> process_details
+  -> finalization verifier
+  -> response(finalized=true)
+  -> messages.content
+```
+
+### 1. 后端统一 Finalizer
+
+职责：
+
+- 接收 `RunResult` / 候选文本、`mcpExecutionIds`、会话与助手消息 ID、HITL 状态、编排模式。
+- 通过数据库查询工具执行状态，识别 pending、completed、failed、cancelled 等证据状态。
+- 返回 `FinalizationDecision`。
+- 不调用高风险工具，只做状态和证据检查。
+
+### 2. RunResult 终态字段
+
+[internal/multiagent/runner.go](../../internal/multiagent/runner.go) 已扩展终态字段：
+
+```go
+type RunResult struct {
+    Response             string
+    MCPExecutionIDs      []string
+    LastAgentTraceInput  string
+    LastAgentTraceOutput string
+
+    Finalized           bool
+    Status              string
+    CompletionReason    string
+    EvidenceVerified    bool
+    EvidenceRefs        []string
+    PendingExecutionIDs []string
+    MissingChecks       []string
+}
+```
+
+### 3. 发送 `response` 的条件
+
+在单代理、多代理、工作流、批处理收尾处统一执行：
+
+```go
+decision := h.finalizeAgentRunForDelivery(...)
+if !decision.Finalizable {
+    sendEvent("finalization_check", "任务尚未达到最终回复条件", decision)
+    sendEvent("response", finalizationBlockedMessage(decision), finalizationResponsePayload(decision, extra))
+    return
+}
+
+sendEvent("response", decision.FinalText, finalizationResponsePayload(decision, extra))
+```
+
+### 4. 前端只信 `finalized=true`
+
+在 [web/static/js/monitor.js](../../web/static/js/monitor.js) 的 `case 'response'` 中执行硬判断：
+
+```js
+const responseFinalized = isFinalizedResponseData(responseData);
+const bubbleText = responseFinalized
+  ? resolvedResponseText
+  : (event.message || '任务尚未达到最终回复条件，暂不生成成功结论。');
+markAssistantFinalizationState(assistantIdFinal, responseData);
+```
+
+WebShell 侧同理：`response_delta` 可以用于实时预览，但 UI 文案应标记为“执行中输出”，只有最终 `response(finalized=true)` 才显示为完成态。
+
+### 5. 各模式 final gate
+
+| 模式 | 谁可以产出最终候选 | 谁决定 final | 必须检查 |
+|---|---|---|---|
+| Eino 单代理 | 单代理最后助手文本 | Finalizer | 无 pending tool、证据引用完整、任务状态 terminal |
+| Deep | 主代理汇总文本 | Finalizer | 子代理结果已汇总；子代理文本不能直接 final；工具状态 terminal |
+| Plan-Execute | Replanner 结束后的汇总文本 | Replanner + Finalizer | Executor 单步输出不能 final；计划步骤完成或明确 blocked |
+| Supervisor | Supervisor 的 `exit` / 汇总文本 | Supervisor + Finalizer | transfer 已返回；无未处理专家结果；最终由 supervisor 统一口径 |
+
+### 6. 安全测试场景的证据 gate
+
+安全测试、WebShell、批量验证、Workflow 和多代理执行等 evidence-required 场景，最终回复必须至少满足：
+
+- 有明确目标和授权范围标识。
+- 有可复核证据引用，例如工具 execution id、请求/响应摘要、截图路径、命令输出摘要、事实/漏洞记录 ID。
+- 有身份或影响验证结果，而不是只凭 marker 文本判断。
+- 已记录到项目黑板或漏洞库，或明确说明未绑定项目导致无法记录。
+- 高风险动作已清理、回滚、取消，或明确说明未执行清理的原因。
+- 仍在运行的扫描/命令/WebShell/C2 任务不能被隐式当作完成。
+
+注意：这里的 gate 是治理规则，不要求最终报告暴露敏感利用细节；可以只给证据摘要和内部引用。
+
+## 六、落地状态与后续增强
+
+### P0：先修“误 final”（已落地）
+
+1. 已引入 `FinalizationDecision`。
+2. 主要 agent SSE `response` 事件已携带 `data.finalized/finalizable/status/completionReason` 等字段。
+3. 前端 `monitor.js` 和 `webshell.js` 已按 `finalized=true` 区分候选输出和最终回复。
+4. `RunResult.Response` 仍保留兼容字段名，但语义已由 finalizer 统一提升；后续可再拆成 `CandidateResponse` / `FinalResponse`，减少误用空间。
+5. Plan-Execute / Deep / Supervisor / Eino Single 等模式均通过统一 handler 收尾 gate。
+
+### P1：补证据链（部分落地）
+
+1. 已用 `mcp_execution:<id>` 作为基础 evidence refs。
+2. `finalization_check` 事件已展示 pending execution 与 missing checks。
+3. 执行入口已启用显式 execution evidence policy；Eino 主链路在 policy 要求证据且缺少 completed 工具证据时先无注入续跑，达到上限后才阻断 final。
+4. 后续建议：为 `record_vulnerability`、`upsert_project_fact`、项目黑板记录建立更细粒度 evidence refs。
+5. 后续建议：最终报告模板固定包含“结论、证据、风险/不确定性、后续动作”。
+
+### P2：体验和观测（后续增强）
+
+1. 在任务卡片展示 `in_progress / verifying / finalizing / completed / blocked`。
+2. 为 finalizer 加日志和指标：误拦截率、缺失证据类型、pending tool 数量。
+3. 支持“继续验证”按钮，从 `FinalizationDecision.MissingChecks` 自动生成下一轮输入。
+
+## 七、验收测试建议
+
+至少加入这些回归测试：
+
+1. **推理文本不 final**
+   模拟 `reasoning_chain` 里出现看似完成的候选结论，但本轮没有 completed 工具执行证据；预期主消息气泡不显示成功结论，只显示执行中或阻断态。
+
+2. **主代理阶段性输出不 final**
+   模拟 `response_start/delta` 输出“下一步继续验证”；预期只进入 timeline `planning`。
+
+3. **未完成后台工具不 final**
+   工具返回 `execution_id` 且状态 `running`；即使模型给出总结，也只能 `in_progress`。
+
+4. **Plan-Execute Executor 输出不 final**
+   Executor 输出“突破成功”，但 Replanner 未结束；预期不触发 `messages.content` finalize。
+
+5. **Supervisor 子代理输出不 final**
+   子代理返回确定结论，Supervisor 未 `exit`；预期只进入 `eino_agent_reply`。
+
+6. **最终事件必须带 finalized**
+   前端收到旧格式 `response` 无 `finalized=true`；预期候选内容只进入详情/警告，主消息显示阻断态，不创建成功最终气泡。
+
+7. **失败和取消可终态**
+   `error` / `cancelled` 仍可更新助手消息，但 `completionReason` 必须是 `failed` / `user_cancelled`，不能伪装为成功完成。
+
+## 八、推荐默认策略
+
+对 CyberStrikeAI，建议默认策略是：
+
+```text
+eino_single：轻量任务可用，但 final gate 必须开启
+deep：复杂安全测试默认推荐
+plan_execute：目标明确、需要严格“规划-执行-重规划”的任务推荐
+supervisor：多专家路由任务使用，不作为默认泛化模式
+```
+
+最终治理一句话：
+
+```text
+messages.content 只能来自 FinalizationDecision.FinalText；
+process_details 可以展示所有过程；
+前端只能把 response(finalized=true) 当最终回复。
+```

internal/agentfinalizer/decision.go

@@ -0,0 +1,266 @@
+package agentfinalizer
+
+import (
+	"strings"
+
+	"cyberstrike-ai/internal/database"
+	"cyberstrike-ai/internal/mcp"
+	"cyberstrike-ai/internal/multiagent"
+)
+
+const (
+	StatusCompleted    = "completed"
+	StatusInProgress   = "in_progress"
+	StatusBlocked      = "blocked"
+	StatusFailed       = "failed"
+	StatusCancelled    = "cancelled"
+	StatusAwaitingHITL = "awaiting_hitl"
+
+	ReasonVerified        = "verified"
+	ReasonPendingTools    = "pending_tool_executions"
+	ReasonEmptyResponse   = "empty_response"
+	ReasonAwaitingHITL    = "awaiting_hitl"
+	ReasonFailed          = "failed"
+	ReasonCancelled       = "cancelled"
+	ReasonMissingEvidence = "missing_execution_evidence"
+)
+
+// Decision is the single contract that may promote an agent run to a final
+// user-facing answer. Natural-language assistant text is only a candidate until
+// this object says Finalizable.
+type Decision struct {
+	Status               string   `json:"status"`
+	Finalizable          bool     `json:"finalizable"`
+	Finalized            bool     `json:"finalized"`
+	CompletionReason     string   `json:"completionReason"`
+	FinalText            string   `json:"finalText,omitempty"`
+	EvidenceVerified     bool     `json:"evidenceVerified"`
+	EvidenceRefs         []string `json:"evidenceRefs,omitempty"`
+	PendingExecutionIDs  []string `json:"pendingExecutionIds,omitempty"`
+	PendingToolRuns      []string `json:"pendingToolRuns,omitempty"`
+	MissingChecks        []string `json:"missingChecks,omitempty"`
+	AgentMode            string   `json:"agentMode,omitempty"`
+	ConversationID       string   `json:"conversationId,omitempty"`
+	AssistantMessageID   string   `json:"messageId,omitempty"`
+	CandidateResponseLen int      `json:"candidateResponseLen,omitempty"`
+}
+
+type Input struct {
+	Response                 string
+	MCPExecutionIDs          []string
+	ConversationID           string
+	AssistantMessageID       string
+	AgentMode                string
+	Status                   string
+	CompletionReason         string
+	AwaitingHITL             bool
+	RequireExecutionEvidence bool
+}
+
+func FromRunResult(db *database.DB, result *multiagent.RunResult, in Input) Decision {
+	if result != nil {
+		if strings.TrimSpace(in.Response) == "" {
+			in.Response = result.Response
+		}
+		if len(in.MCPExecutionIDs) == 0 {
+			in.MCPExecutionIDs = result.MCPExecutionIDs
+		}
+		if strings.TrimSpace(in.Status) == "" {
+			in.Status = result.Status
+		}
+		if strings.TrimSpace(in.CompletionReason) == "" {
+			in.CompletionReason = result.CompletionReason
+		}
+	}
+	d := Decide(db, in)
+	if result != nil {
+		result.Finalized = d.Finalized
+		result.Status = d.Status
+		result.CompletionReason = d.CompletionReason
+		result.EvidenceVerified = d.EvidenceVerified
+		result.EvidenceRefs = append([]string(nil), d.EvidenceRefs...)
+		result.PendingExecutionIDs = append([]string(nil), d.PendingExecutionIDs...)
+		result.MissingChecks = append([]string(nil), d.MissingChecks...)
+	}
+	return d
+}
+
+func Decide(db *database.DB, in Input) Decision {
+	text := strings.TrimSpace(in.Response)
+	status := strings.TrimSpace(in.Status)
+	if status == "" {
+		status = StatusCompleted
+	}
+	reason := strings.TrimSpace(in.CompletionReason)
+	if reason == "" {
+		reason = ReasonVerified
+	}
+	d := Decision{
+		Status:               status,
+		CompletionReason:     reason,
+		FinalText:            text,
+		EvidenceVerified:     true,
+		EvidenceRefs:         evidenceRefs(in.MCPExecutionIDs),
+		AgentMode:            strings.TrimSpace(in.AgentMode),
+		ConversationID:       strings.TrimSpace(in.ConversationID),
+		AssistantMessageID:   strings.TrimSpace(in.AssistantMessageID),
+		CandidateResponseLen: len([]rune(text)),
+	}
+
+	if in.AwaitingHITL {
+		d.Status = StatusAwaitingHITL
+		d.CompletionReason = ReasonAwaitingHITL
+		d.EvidenceVerified = false
+		d.MissingChecks = append(d.MissingChecks, "workflow is awaiting HITL approval")
+		return d
+	}
+	if isEmptyCandidate(text) {
+		d.Status = StatusBlocked
+		d.CompletionReason = ReasonEmptyResponse
+		d.EvidenceVerified = false
+		d.MissingChecks = append(d.MissingChecks, "assistant final text is empty or only an empty-response placeholder")
+		return d
+	}
+	switch status {
+	case StatusInProgress, StatusBlocked, StatusFailed, StatusCancelled, StatusAwaitingHITL:
+		d.Status = status
+		d.EvidenceVerified = false
+		if d.CompletionReason == ReasonVerified {
+			d.CompletionReason = status
+		}
+		d.MissingChecks = append(d.MissingChecks, "agent run status is "+status)
+		return d
+	}
+
+	pending := pendingExecutions(db, in.MCPExecutionIDs)
+	if len(pending) > 0 {
+		d.Status = StatusInProgress
+		d.CompletionReason = ReasonPendingTools
+		d.EvidenceVerified = false
+		d.PendingExecutionIDs = pending
+		d.PendingToolRuns = append([]string(nil), pending...)
+		d.MissingChecks = append(d.MissingChecks, "tool execution still queued or running")
+		return d
+	}
+
+	if in.RequireExecutionEvidence && !hasCompletedEvidence(db, in.MCPExecutionIDs) {
+		d.Status = StatusBlocked
+		d.CompletionReason = ReasonMissingEvidence
+		d.EvidenceVerified = false
+		d.MissingChecks = append(d.MissingChecks, "execution evidence is required but no completed tool execution was recorded")
+		return d
+	}
+
+	d.Finalizable = true
+	d.Finalized = true
+	d.Status = StatusCompleted
+	if d.CompletionReason == "" {
+		d.CompletionReason = ReasonVerified
+	}
+	return d
+}
+
+func ResponsePayload(d Decision, extra map[string]interface{}) map[string]interface{} {
+	out := map[string]interface{}{
+		"finalized":           d.Finalized,
+		"finalizable":         d.Finalizable,
+		"status":              d.Status,
+		"completionReason":    d.CompletionReason,
+		"evidenceVerified":    d.EvidenceVerified,
+		"evidenceRefs":        d.EvidenceRefs,
+		"pendingExecutionIds": d.PendingExecutionIDs,
+		"pendingToolRuns":     d.PendingToolRuns,
+		"missingChecks":       d.MissingChecks,
+	}
+	if d.ConversationID != "" {
+		out["conversationId"] = d.ConversationID
+	}
+	if d.AssistantMessageID != "" {
+		out["messageId"] = d.AssistantMessageID
+	}
+	if d.AgentMode != "" {
+		out["agentMode"] = d.AgentMode
+	}
+	for k, v := range extra {
+		out[k] = v
+	}
+	return out
+}
+
+func isEmptyCandidate(s string) bool {
+	s = strings.TrimSpace(s)
+	if s == "" {
+		return true
+	}
+	return strings.Contains(s, "no assistant text was captured") ||
+		strings.Contains(s, "未捕获到助手文本输出")
+}
+
+func evidenceRefs(ids []string) []string {
+	out := make([]string, 0, len(ids))
+	seen := make(map[string]struct{}, len(ids))
+	for _, id := range ids {
+		id = strings.TrimSpace(id)
+		if id == "" {
+			continue
+		}
+		if _, ok := seen[id]; ok {
+			continue
+		}
+		seen[id] = struct{}{}
+		out = append(out, "mcp_execution:"+id)
+	}
+	return out
+}
+
+func pendingExecutions(db *database.DB, ids []string) []string {
+	if db == nil || len(ids) == 0 {
+		return nil
+	}
+	out := make([]string, 0)
+	seen := make(map[string]struct{}, len(ids))
+	for _, id := range ids {
+		id = strings.TrimSpace(id)
+		if id == "" {
+			continue
+		}
+		if _, ok := seen[id]; ok {
+			continue
+		}
+		seen[id] = struct{}{}
+		exec, err := db.GetToolExecution(id)
+		if err != nil || exec == nil {
+			continue
+		}
+		switch strings.TrimSpace(exec.Status) {
+		case mcp.ToolExecutionStatusQueued, mcp.ToolExecutionStatusRunning:
+			out = append(out, id)
+		}
+	}
+	return out
+}
+
+func hasCompletedEvidence(db *database.DB, ids []string) bool {
+	if db == nil || len(ids) == 0 {
+		return false
+	}
+	seen := make(map[string]struct{}, len(ids))
+	for _, id := range ids {
+		id = strings.TrimSpace(id)
+		if id == "" {
+			continue
+		}
+		if _, ok := seen[id]; ok {
+			continue
+		}
+		seen[id] = struct{}{}
+		exec, err := db.GetToolExecution(id)
+		if err != nil || exec == nil {
+			continue
+		}
+		if strings.TrimSpace(exec.Status) == mcp.ToolExecutionStatusCompleted {
+			return true
+		}
+	}
+	return false
+}

internal/agentfinalizer/decision_test.go

@@ -0,0 +1,132 @@
+package agentfinalizer
+
+import (
+	"path/filepath"
+	"testing"
+	"time"
+
+	"cyberstrike-ai/internal/database"
+	"cyberstrike-ai/internal/mcp"
+
+	"go.uber.org/zap"
+)
+
+func newDecisionTestDB(t *testing.T) *database.DB {
+	t.Helper()
+	db, err := database.NewDB(filepath.Join(t.TempDir(), "finalizer.db"), zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	t.Cleanup(func() { _ = db.Close() })
+	return db
+}
+
+func saveDecisionTestExecution(t *testing.T, db *database.DB, id, status string) {
+	t.Helper()
+	if err := db.SaveToolExecution(&mcp.ToolExecution{
+		ID:        id,
+		ToolName:  "test::tool",
+		Arguments: map[string]interface{}{"input": id},
+		Status:    status,
+		StartTime: time.Now(),
+	}); err != nil {
+		t.Fatalf("SaveToolExecution(%s): %v", id, err)
+	}
+}
+
+func TestDecideBlocksPendingToolExecutions(t *testing.T) {
+	db := newDecisionTestDB(t)
+	saveDecisionTestExecution(t, db, "run-queued", mcp.ToolExecutionStatusQueued)
+	saveDecisionTestExecution(t, db, "run-running", mcp.ToolExecutionStatusRunning)
+	saveDecisionTestExecution(t, db, "run-completed", mcp.ToolExecutionStatusCompleted)
+
+	d := Decide(db, Input{
+		Response:        "工具还没全部结束时，这只是一段候选输出。",
+		MCPExecutionIDs: []string{"run-queued", "run-running", "run-completed"},
+	})
+
+	if d.Finalizable || d.Finalized {
+		t.Fatalf("pending tools should not be finalizable: %+v", d)
+	}
+	if d.Status != StatusInProgress || d.CompletionReason != ReasonPendingTools {
+		t.Fatalf("status/reason = %s/%s, want %s/%s", d.Status, d.CompletionReason, StatusInProgress, ReasonPendingTools)
+	}
+	if got, want := len(d.PendingExecutionIDs), 2; got != want {
+		t.Fatalf("pending execution count = %d, want %d (%v)", got, want, d.PendingExecutionIDs)
+	}
+}
+
+func TestDecideBlocksAwaitingHITLAndEmptyCandidate(t *testing.T) {
+	hitl := Decide(nil, Input{Response: "等待人工审批", AwaitingHITL: true})
+	if hitl.Finalizable || hitl.Status != StatusAwaitingHITL || hitl.CompletionReason != ReasonAwaitingHITL {
+		t.Fatalf("HITL decision mismatch: %+v", hitl)
+	}
+
+	empty := Decide(nil, Input{Response: "⚠️ Eino 执行完成，但未捕获到助手文本输出。"})
+	if empty.Finalizable || empty.Status != StatusBlocked || empty.CompletionReason != ReasonEmptyResponse {
+		t.Fatalf("empty candidate decision mismatch: %+v", empty)
+	}
+}
+
+func TestDecideBlocksWhenExecutionEvidenceIsRequiredButMissing(t *testing.T) {
+	d := Decide(nil, Input{
+		Response:                 "任务已处理完成。",
+		RequireExecutionEvidence: true,
+	})
+	if d.Finalizable || d.Finalized {
+		t.Fatalf("missing required execution evidence should not finalize: %+v", d)
+	}
+	if d.Status != StatusBlocked || d.CompletionReason != ReasonMissingEvidence {
+		t.Fatalf("status/reason = %s/%s, want %s/%s", d.Status, d.CompletionReason, StatusBlocked, ReasonMissingEvidence)
+	}
+	if d.EvidenceVerified {
+		t.Fatalf("missing required execution evidence should be marked unverified: %+v", d)
+	}
+	if len(d.MissingChecks) == 0 {
+		t.Fatalf("missing checks should explain the evidence gap: %+v", d)
+	}
+}
+
+func TestDecideBlocksWhenOnlyFailedEvidenceIsRecorded(t *testing.T) {
+	db := newDecisionTestDB(t)
+	saveDecisionTestExecution(t, db, "run-failed", mcp.ToolExecutionStatusFailed)
+	saveDecisionTestExecution(t, db, "run-cancelled", mcp.ToolExecutionStatusCancelled)
+
+	d := Decide(db, Input{
+		Response:                 "任务已处理完成。",
+		MCPExecutionIDs:          []string{"run-failed", "run-cancelled"},
+		RequireExecutionEvidence: true,
+	})
+
+	if d.Finalizable || d.Finalized {
+		t.Fatalf("failed evidence should not satisfy required execution evidence: %+v", d)
+	}
+	if d.Status != StatusBlocked || d.CompletionReason != ReasonMissingEvidence {
+		t.Fatalf("status/reason = %s/%s, want %s/%s", d.Status, d.CompletionReason, StatusBlocked, ReasonMissingEvidence)
+	}
+}
+
+func TestDecideFinalizesCompletedEvidence(t *testing.T) {
+	db := newDecisionTestDB(t)
+	saveDecisionTestExecution(t, db, "run-ok", mcp.ToolExecutionStatusCompleted)
+
+	d := Decide(db, Input{
+		Response:                 "任务已处理完成，见工具执行记录。",
+		MCPExecutionIDs:          []string{"run-ok"},
+		RequireExecutionEvidence: true,
+	})
+
+	if !d.Finalizable || !d.Finalized || d.Status != StatusCompleted {
+		t.Fatalf("completed execution should finalize: %+v", d)
+	}
+	if !d.EvidenceVerified || len(d.EvidenceRefs) != 1 {
+		t.Fatalf("evidence refs mismatch: %+v", d)
+	}
+}
+
+func TestDecideAllowsInformationalAnswerWhenExecutionEvidenceIsNotRequired(t *testing.T) {
+	d := Decide(nil, Input{Response: "这是一个概念解释，不需要执行工具。"})
+	if !d.Finalizable || !d.Finalized || d.Status != StatusCompleted {
+		t.Fatalf("informational response should finalize when execution evidence is not required: %+v", d)
+	}
+}

internal/database/conversation.go

@@ -23,6 +23,7 @@ type Conversation struct {
 	Title     string    `json:"title"`
 	ProjectID string    `json:"projectId,omitempty"`
 	RoleName  string    `json:"roleName,omitempty"`
+	AgentMode string    `json:"agentMode,omitempty"`
 	Pinned    bool      `json:"pinned"`
 	CreatedAt time.Time `json:"createdAt"`
 	UpdatedAt time.Time `json:"updatedAt"`
@@ -59,29 +60,30 @@ func (db *DB) CreateConversationWithWebshell(webshellConnectionID, title string,
 		}
 	}
 	roleName := normalizeConversationRoleName(meta.RoleName)
+	agentMode := normalizeConversationAgentMode(meta.AgentMode)
 
 	var err error
 	wsID := strings.TrimSpace(webshellConnectionID)
 	switch {
 	case wsID != "" && projectID != "":
 		_, err = db.Exec(
-			"INSERT INTO conversations (id, title, created_at, updated_at, webshell_connection_id, project_id, role_name) VALUES (?, ?, ?, ?, ?, ?, ?)",
+			"INSERT INTO conversations (id, title, created_at, updated_at, webshell_connection_id, project_id, role_name, agent_mode) VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
-			id, title, now, now, wsID, projectID, roleName,
+			id, title, now, now, wsID, projectID, roleName, agentMode,
 		)
 	case wsID != "":
 		_, err = db.Exec(
-			"INSERT INTO conversations (id, title, created_at, updated_at, webshell_connection_id, role_name) VALUES (?, ?, ?, ?, ?, ?)",
+			"INSERT INTO conversations (id, title, created_at, updated_at, webshell_connection_id, role_name, agent_mode) VALUES (?, ?, ?, ?, ?, ?, ?)",
-			id, title, now, now, wsID, roleName,
+			id, title, now, now, wsID, roleName, agentMode,
 		)
 	case projectID != "":
 		_, err = db.Exec(
-			"INSERT INTO conversations (id, title, created_at, updated_at, project_id, role_name) VALUES (?, ?, ?, ?, ?, ?)",
+			"INSERT INTO conversations (id, title, created_at, updated_at, project_id, role_name, agent_mode) VALUES (?, ?, ?, ?, ?, ?, ?)",
-			id, title, now, now, projectID, roleName,
+			id, title, now, now, projectID, roleName, agentMode,
 		)
 	default:
 		_, err = db.Exec(
-			"INSERT INTO conversations (id, title, created_at, updated_at, role_name) VALUES (?, ?, ?, ?, ?)",
+			"INSERT INTO conversations (id, title, created_at, updated_at, role_name, agent_mode) VALUES (?, ?, ?, ?, ?, ?)",
-			id, title, now, now, roleName,
+			id, title, now, now, roleName, agentMode,
 		)
 	}
 	if err != nil {
@@ -93,6 +95,7 @@ func (db *DB) CreateConversationWithWebshell(webshellConnectionID, title string,
 		Title:     title,
 		ProjectID: projectID,
 		RoleName:  roleName,
+		AgentMode: agentMode,
 		CreatedAt: now,
 		UpdatedAt: now,
 	}
@@ -240,10 +243,11 @@ func (db *DB) GetConversation(id string) (*Conversation, error) {
 
 	var projectID sql.NullString
 	var roleName sql.NullString
+	var agentMode sql.NullString
 	err := db.QueryRow(
-		"SELECT id, title, pinned, created_at, updated_at, project_id, role_name FROM conversations WHERE id = ?",
+		"SELECT id, title, pinned, created_at, updated_at, project_id, role_name, agent_mode FROM conversations WHERE id = ?",
 		id,
-	).Scan(&conv.ID, &conv.Title, &pinned, &createdAt, &updatedAt, &projectID, &roleName)
+	).Scan(&conv.ID, &conv.Title, &pinned, &createdAt, &updatedAt, &projectID, &roleName, &agentMode)
 	if err != nil {
 		if err == sql.ErrNoRows {
 			return nil, fmt.Errorf("对话不存在")
@@ -256,6 +260,9 @@ func (db *DB) GetConversation(id string) (*Conversation, error) {
 	if roleName.Valid {
 		conv.RoleName = normalizeConversationRoleName(roleName.String)
 	}
+	if agentMode.Valid {
+		conv.AgentMode = normalizeConversationAgentMode(agentMode.String)
+	}
 
 	// 尝试多种时间格式解析
 	var err1, err2 error
@@ -330,10 +337,11 @@ func (db *DB) GetConversationLite(id string) (*Conversation, error) {
 
 	var projectID sql.NullString
 	var roleName sql.NullString
+	var agentMode sql.NullString
 	err := db.QueryRow(
-		"SELECT id, title, pinned, created_at, updated_at, project_id, role_name FROM conversations WHERE id = ?",
+		"SELECT id, title, pinned, created_at, updated_at, project_id, role_name, agent_mode FROM conversations WHERE id = ?",
 		id,
-	).Scan(&conv.ID, &conv.Title, &pinned, &createdAt, &updatedAt, &projectID, &roleName)
+	).Scan(&conv.ID, &conv.Title, &pinned, &createdAt, &updatedAt, &projectID, &roleName, &agentMode)
 	if err != nil {
 		if err == sql.ErrNoRows {
 			return nil, fmt.Errorf("对话不存在")
@@ -346,6 +354,9 @@ func (db *DB) GetConversationLite(id string) (*Conversation, error) {
 	if roleName.Valid {
 		conv.RoleName = normalizeConversationRoleName(roleName.String)
 	}
+	if agentMode.Valid {
+		conv.AgentMode = normalizeConversationAgentMode(agentMode.String)
+	}
 
 	// 尝试多种时间格式解析
 	var err1, err2 error
@@ -384,6 +395,17 @@ func normalizeConversationRoleName(roleName string) string {
 	return roleName
 }
 
+func normalizeConversationAgentMode(agentMode string) string {
+	agentMode = strings.ToLower(strings.TrimSpace(agentMode))
+	agentMode = strings.ReplaceAll(agentMode, "-", "_")
+	switch agentMode {
+	case "deep", "plan_execute", "supervisor":
+		return agentMode
+	default:
+		return "eino_single"
+	}
+}
+
 func (db *DB) SetConversationRoleName(id, roleName string) error {
 	roleName = normalizeConversationRoleName(roleName)
 	_, err := db.Exec(
@@ -396,6 +418,18 @@ func (db *DB) SetConversationRoleName(id, roleName string) error {
 	return nil
 }
 
+func (db *DB) SetConversationAgentMode(id, agentMode string) error {
+	agentMode = normalizeConversationAgentMode(agentMode)
+	_, err := db.Exec(
+		"UPDATE conversations SET agent_mode = ? WHERE id = ?",
+		agentMode, id,
+	)
+	if err != nil {
+		return fmt.Errorf("更新对话模式失败: %w", err)
+	}
+	return nil
+}
+
 func conversationProjectIDColumn(alias string) string {
 	if alias != "" {
 		return alias + ".project_id"
@@ -520,7 +554,7 @@ func (db *DB) ListConversations(limit, offset int, search, sortBy, projectID str
 		where, args = appendConversationProjectFilter(where, args, projectID, "c")
 		args = append(args, limit, offset)
 		rows, err = db.Query(
-			`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id, c.role_name
+			`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id, c.role_name, c.agent_mode
 			 FROM conversations c`+where+`
 			 `+orderClause+`
 			 LIMIT ? OFFSET ?`,
@@ -536,7 +570,7 @@ func (db *DB) ListConversations(limit, offset int, search, sortBy, projectID str
 		}
 		args = append(args, limit, offset)
 		rows, err = db.Query(
-			"SELECT id, title, COALESCE(pinned, 0), created_at, updated_at, project_id, role_name FROM conversations"+where+" "+orderClause+" LIMIT ? OFFSET ?",
+			"SELECT id, title, COALESCE(pinned, 0), created_at, updated_at, project_id, role_name, agent_mode FROM conversations"+where+" "+orderClause+" LIMIT ? OFFSET ?",
 			args...,
 		)
 	}
@@ -564,7 +598,7 @@ func (db *DB) ListConversationsForAccess(limit, offset int, search, sortBy, proj
 		where, args = appendConversationAccessFilter(where, args, userID, scope, "c")
 		args = append(args, limit, offset)
 		rows, err = db.Query(
-			`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id, c.role_name
+			`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id, c.role_name, c.agent_mode
 			 FROM conversations c`+where+`
 			 `+orderClause+`
 			 LIMIT ? OFFSET ?`, args...)
@@ -579,7 +613,7 @@ func (db *DB) ListConversationsForAccess(limit, offset int, search, sortBy, proj
 		}
 		args = append(args, limit, offset)
 		rows, err = db.Query(
-			"SELECT id, title, COALESCE(pinned, 0), created_at, updated_at, project_id, role_name FROM conversations"+where+" "+orderClause+" LIMIT ? OFFSET ?",
+			"SELECT id, title, COALESCE(pinned, 0), created_at, updated_at, project_id, role_name, agent_mode FROM conversations"+where+" "+orderClause+" LIMIT ? OFFSET ?",
 			args...)
 	}
 	if err != nil {
@@ -597,7 +631,8 @@ func scanConversationRows(rows *sql.Rows) ([]*Conversation, error) {
 		var pinned int
 		var projectID sql.NullString
 		var roleName sql.NullString
-		if err := rows.Scan(&conv.ID, &conv.Title, &pinned, &createdAt, &updatedAt, &projectID, &roleName); err != nil {
+		var agentMode sql.NullString
+		if err := rows.Scan(&conv.ID, &conv.Title, &pinned, &createdAt, &updatedAt, &projectID, &roleName, &agentMode); err != nil {
 			return nil, fmt.Errorf("扫描对话失败: %w", err)
 		}
 		if projectID.Valid {
@@ -606,6 +641,9 @@ func scanConversationRows(rows *sql.Rows) ([]*Conversation, error) {
 		if roleName.Valid {
 			conv.RoleName = normalizeConversationRoleName(roleName.String)
 		}
+		if agentMode.Valid {
+			conv.AgentMode = normalizeConversationAgentMode(agentMode.String)
+		}
 		var err1, err2 error
 		conv.CreatedAt, err1 = time.Parse("2006-01-02 15:04:05.999999999-07:00", createdAt)
 		if err1 != nil {
@@ -665,7 +703,7 @@ func (db *DB) ListUngroupedConversations(limit, offset int, sortBy, projectID st
 	where, args = appendConversationProjectFilter(where, args, projectID, "c")
 	args = append(args, limit, offset)
 	rows, err := db.Query(
-		`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id, c.role_name `+
+		`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id, c.role_name, c.agent_mode `+
 			where+`
 		 `+orderClause+`
 		 LIMIT ? OFFSET ?`,
@@ -689,7 +727,7 @@ func (db *DB) ListUngroupedConversationsForAccess(limit, offset int, sortBy, pro
 	where, args = appendConversationAccessFilter(where, args, userID, scope, "c")
 	args = append(args, limit, offset)
 	rows, err := db.Query(
-		`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id, c.role_name `+
+		`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id, c.role_name, c.agent_mode `+
 			where+`
 		 `+orderClause+`
 		 LIMIT ? OFFSET ?`,

internal/database/conversation_create_meta.go

@@ -6,6 +6,7 @@ type ConversationCreateMeta struct {
 	WebShellConnectionID string
 	ProjectID            string
 	RoleName             string
+	AgentMode            string
 	ClientIP             string
 	SessionHint          string
 }

internal/database/database.go

@@ -184,6 +184,7 @@ func (db *DB) initTables() error {
 		created_at DATETIME NOT NULL,
 		updated_at DATETIME NOT NULL,
 		role_name TEXT NOT NULL DEFAULT '默认',
+		agent_mode TEXT NOT NULL DEFAULT 'eino_single',
 		last_react_input TEXT,
 		last_react_output TEXT
 	);`
@@ -1174,6 +1175,21 @@ func (db *DB) migrateConversationsTable() error {
 		}
 	}
 
+	// 检查 agent_mode 字段是否存在（对话绑定的执行模式，用于历史任务切换时恢复对话模式）
+	err = db.QueryRow("SELECT COUNT(*) FROM pragma_table_info('conversations') WHERE name='agent_mode'").Scan(&count)
+	if err != nil {
+		if _, addErr := db.Exec("ALTER TABLE conversations ADD COLUMN agent_mode TEXT NOT NULL DEFAULT 'eino_single'"); addErr != nil {
+			errMsg := strings.ToLower(addErr.Error())
+			if !strings.Contains(errMsg, "duplicate column") && !strings.Contains(errMsg, "already exists") {
+				db.logger.Warn("添加agent_mode字段失败", zap.Error(addErr))
+			}
+		}
+	} else if count == 0 {
+		if _, err := db.Exec("ALTER TABLE conversations ADD COLUMN agent_mode TEXT NOT NULL DEFAULT 'eino_single'"); err != nil {
+			db.logger.Warn("添加agent_mode字段失败", zap.Error(err))
+		}
+	}
+
 	return nil
 }
 

internal/handler/agent.go

@@ -333,6 +333,12 @@ type ChatReasoningRequest struct {
 	Effort string `json:"effort,omitempty"`
 }
 
+// ChatFinalizationRequest is a caller-provided delivery policy. The server does
+// not infer execution intent from natural-language user text.
+type ChatFinalizationRequest struct {
+	RequireExecutionEvidence *bool `json:"requireExecutionEvidence,omitempty"`
+}
+
 // ChatRequest 聊天请求
 type ChatRequest struct {
 	Message              string                  `json:"message" binding:"required"`
@@ -344,6 +350,7 @@ type ChatRequest struct {
 	AIChannelID          string                  `json:"aiChannelId,omitempty"`          // 会话级 AI 通道；空则使用 ai.default_channel
 	Hitl                 *HITLRequest            `json:"hitl,omitempty"`
 	Reasoning            *ChatReasoningRequest   `json:"reasoning,omitempty"`
+	Finalization         ChatFinalizationRequest `json:"finalization,omitempty"`
 	// Orchestration 仅对 /api/multi-agent、/api/multi-agent/stream：deep | plan_execute | supervisor；空则等同 deep。机器人/批量等无请求体时由服务端默认 deep。/api/eino-agent* 不使用此字段。
 	Orchestration string `json:"orchestration,omitempty"`
 }
@@ -672,6 +679,14 @@ type ChatResponse struct {
 	MCPExecutionIDs     []string  `json:"mcpExecutionIds,omitempty"` // 本次对话中执行的MCP调用ID列表
 	ConversationID      string    `json:"conversationId"`            // 对话ID
 	Time                time.Time `json:"time"`
+	Finalizable         bool      `json:"finalizable"`
+	Finalized           bool      `json:"finalized"`
+	Status              string    `json:"status,omitempty"`
+	CompletionReason    string    `json:"completionReason,omitempty"`
+	EvidenceVerified    bool      `json:"evidenceVerified"`
+	EvidenceRefs        []string  `json:"evidenceRefs,omitempty"`
+	PendingExecutionIDs []string  `json:"pendingExecutionIds,omitempty"`
+	MissingChecks       []string  `json:"missingChecks,omitempty"`
 }
 
 func (h *AgentHandler) finalizeRobotAgentError(ctx context.Context, assistantMessageID, conversationID string, resultMA *multiagent.RunResult, errMA error) (string, string, error) {
@@ -687,19 +702,20 @@ func (h *AgentHandler) finalizeRobotAgentError(ctx context.Context, assistantMes
 }
 
 func (h *AgentHandler) finalizeRobotAgentSuccess(assistantMessageID, conversationID string, resultMA *multiagent.RunResult) (string, string, error) {
-	if assistantMessageID != "" {
+	decision := h.finalizeAgentRunForDeliveryWithPolicy(conversationID, assistantMessageID, "robot", resultMA, resultMA.MCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(resultMA.LastAgentTraceInput), true)
-		if errU := h.db.UpdateAssistantMessageFinalize(assistantMessageID, resultMA.Response, resultMA.MCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(resultMA.LastAgentTraceInput)); errU != nil {
+	responseText := decision.FinalText
-			h.logger.Warn("机器人：更新助手消息失败", zap.Error(errU))
+	if !decision.Finalizable {
+		responseText = finalizationBlockedMessage(decision)
 	}
-	} else {
+	if assistantMessageID == "" {
-		if _, err := h.db.AddMessage(conversationID, "assistant", resultMA.Response, resultMA.MCPExecutionIDs); err != nil {
+		if _, err := h.db.AddMessage(conversationID, "assistant", responseText, resultMA.MCPExecutionIDs); err != nil {
 			h.logger.Warn("机器人：保存助手消息失败", zap.Error(err))
 		}
 	}
 	if resultMA.LastAgentTraceInput != "" || resultMA.LastAgentTraceOutput != "" {
 		_ = h.db.SaveAgentTrace(conversationID, resultMA.LastAgentTraceInput, resultMA.LastAgentTraceOutput)
 	}
-	return resultMA.Response, conversationID, nil
+	return responseText, conversationID, nil
 }
 
 func (h *AgentHandler) runRobotEinoSingleWithRetry(
@@ -830,6 +846,9 @@ func (h *AgentHandler) ProcessMessageForRobot(ctx context.Context, platform stri
 	progressCallback := h.createProgressCallback(taskCtx, cancelWithCause, conversationID, assistantMessageID, nil)
 
 	robotMode := config.NormalizeAgentMode(agentMode)
+	if err := h.db.SetConversationAgentMode(conversationID, robotMode); err != nil {
+		h.logger.Warn("机器人：更新对话模式失败", zap.String("conversationId", conversationID), zap.String("agentMode", robotMode), zap.Error(err))
+	}
 	switch robotMode {
 	case "eino_single":
 		return h.runRobotEinoSingleWithRetry(taskCtx, conversationID, finalMessage, agentHistoryMessages, roleTools, progressCallback, assistantMessageID, &taskStatus)

internal/handler/batch_queue_executor.go

@@ -238,6 +238,11 @@ func (h *AgentHandler) executeOneBatchSubTask(queueID string, queue *BatchTaskQu
 		useBatchMulti = true
 		batchOrch = "deep"
 	}
+	if useBatchMulti {
+		_ = h.db.SetConversationAgentMode(conversationID, batchOrch)
+	} else {
+		_ = h.db.SetConversationAgentMode(conversationID, "eino_single")
+	}
 
 	var resultMA *multiagent.RunResult
 	var runErr error
@@ -268,19 +273,38 @@ func (h *AgentHandler) executeOneBatchSubTask(queueID string, queue *BatchTaskQu
 
 	h.logger.Info("批量任务执行成功", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID))
 
-	resText := resultMA.Response
 	mcpIDs := resultMA.MCPExecutionIDs
 	lastIn := resultMA.LastAgentTraceInput
 	lastOut := resultMA.LastAgentTraceOutput
+	reasoningContent := multiagent.AggregatedReasoningFromTraceJSON(lastIn)
+	agentMode := "batch_eino_single"
+	if useBatchMulti {
+		agentMode = "batch_eino_" + batchOrch
+	}
+	decision := h.finalizeAgentRunForDeliveryWithPolicy(conversationID, assistantMessageID, agentMode, resultMA, mcpIDs, reasoningContent, true)
+	resText := decision.FinalText
+	if !decision.Finalizable {
+		resText = finalizationBlockedMessage(decision)
+		finishStatus = decision.Status
+		sendEvent("finalization_check", resText, decision)
+	}
+	sendEvent("response", resText, finalizationResponsePayload(decision, map[string]interface{}{
+		"conversationId":   conversationID,
+		"messageId":        assistantMessageID,
+		"agentMode":        agentMode,
+		"mcpExecutionIds":  mcpIDs,
+		"batchQueueId":     queueID,
+		"batchTaskId":      task.ID,
+		"batchTaskStatus":  map[bool]string{true: string(BatchTaskStatusCompleted), false: string(BatchTaskStatusFailed)}[decision.Finalizable],
+		"candidatePreview": safeTruncateString(resultMA.Response, 500),
+	}))
 
-	if assistantMessageID != "" {
+	if assistantMessageID == "" {
-		if updateErr := h.db.UpdateAssistantMessageFinalize(assistantMessageID, resText, mcpIDs, multiagent.AggregatedReasoningFromTraceJSON(lastIn)); updateErr != nil {
+		_, err = h.db.AddMessage(conversationID, "assistant", resText, mcpIDs)
-			h.logger.Warn("更新助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(updateErr))
+	} else if !decision.Finalizable {
-			if _, err = h.db.AddMessage(conversationID, "assistant", resText, mcpIDs); err != nil {
+		err = nil
-				h.logger.Error("保存助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
 	}
-		}
+	if err != nil {
-	} else if _, err = h.db.AddMessage(conversationID, "assistant", resText, mcpIDs); err != nil {
 		h.logger.Error("保存助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
 	}
 
@@ -290,6 +314,10 @@ func (h *AgentHandler) executeOneBatchSubTask(queueID string, queue *BatchTaskQu
 		}
 	}
 
+	if !decision.Finalizable {
+		h.batchTaskManager.UpdateTaskStatusWithConversationID(queueID, task.ID, BatchTaskStatusFailed, resText, finalizationCheckMessage(decision), conversationID)
+		return
+	}
 	h.batchTaskManager.UpdateTaskStatusWithConversationID(queueID, task.ID, BatchTaskStatusCompleted, resText, "", conversationID)
 }
 

internal/handler/eino_empty_response_continue.go

@@ -68,8 +68,7 @@ func (h *AgentHandler) tryContinueOnEinoEmptyResponse(
 	case <-time.After(backoff):
 	}
 
-	inject := multiagent.FormatEmptyResponseContinueUserMessage()
+	h.applyEinoTraceResumeSegment(conversationID, result, curHistory, curFinalMessage, "")
-	h.applyEinoTraceResumeSegment(conversationID, result, curHistory, curFinalMessage, inject)
 	if progressCallback != nil {
 		progressCallback("eino_empty_response_continue", "已恢复上下文，正在续跑…", map[string]interface{}{
 			"conversationId":   conversationID,
@@ -77,6 +76,7 @@ func (h *AgentHandler) tryContinueOnEinoEmptyResponse(
 			"attempt":          *attempt,
 			"maxAttempts":      maxAttempts,
 			"contextSource":    "empty_response_continue",
+			"contextInjection": false,
 		})
 	}
 	return true

internal/handler/eino_single_agent.go

@@ -10,6 +10,7 @@ import (
 	"sync"
 	"time"
 
+	"cyberstrike-ai/internal/agentfinalizer"
 	"cyberstrike-ai/internal/mcp"
 	"cyberstrike-ai/internal/multiagent"
 
@@ -189,6 +190,8 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 	// 同一请求内分段续跑时，主代理 iteration 事件按偏移累计，避免 UI 出现「第3轮 → 第1轮」回跳。
 	var mainIterationOffset int
 	var emptyResponseContinueAttempt int
+	var finalizationAutoContinueAttempt int
+	var decision agentfinalizer.Decision
 
 	for {
 		segmentMainIterationMax := 0
@@ -258,6 +261,13 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 				baseCtx, cancelWithCause, taskCtx, timeoutCancel = h.rebindEinoRunningTask(taskCtx, conversationID, timeoutCancel)
 				continue
 			}
+			decision = h.decideAgentRunForDeliveryWithPolicy(conversationID, assistantMessageID, "eino_single", result, cumulativeMCPExecutionIDs, requestRequiresExecutionEvidence(&req))
+			if h.tryAutoContinueAfterFinalization(taskCtx, conversationID, result, decision, &finalizationAutoContinueAttempt, &curHistory, &curFinalMessage, progressCallback) {
+				mainIterationOffset += segmentMainIterationMax
+				timeoutCancel()
+				baseCtx, cancelWithCause, taskCtx, timeoutCancel = h.rebindEinoRunningTask(taskCtx, conversationID, timeoutCancel)
+				continue
+			}
 			timeoutCancel()
 			break
 		}
@@ -358,9 +368,10 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 
 	timeoutCancel()
 
-	if assistantMessageID != "" {
+	if decision.CompletionReason == "" {
-		_ = h.db.UpdateAssistantMessageFinalize(assistantMessageID, result.Response, cumulativeMCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(result.LastAgentTraceInput))
+		decision = h.decideAgentRunForDeliveryWithPolicy(conversationID, assistantMessageID, "eino_single", result, cumulativeMCPExecutionIDs, requestRequiresExecutionEvidence(&req))
 	}
+	h.persistFinalizationDecision(conversationID, assistantMessageID, "eino_single", cumulativeMCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(result.LastAgentTraceInput), decision)
 
 	if result.LastAgentTraceInput != "" || result.LastAgentTraceOutput != "" {
 		if err := h.db.SaveAgentTrace(conversationID, result.LastAgentTraceInput, result.LastAgentTraceOutput); err != nil {
@@ -368,12 +379,19 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 		}
 	}
 
-	sendEvent("response", result.Response, map[string]interface{}{
+	responseText := decision.FinalText
+	if !decision.Finalizable {
+		responseText = finalizationBlockedMessage(decision)
+		sendEvent("finalization_check", responseText, decision)
+		taskStatus = decision.Status
+		h.tasks.UpdateTaskStatus(conversationID, taskStatus)
+	}
+	sendEvent("response", responseText, finalizationResponsePayload(decision, map[string]interface{}{
 		"mcpExecutionIds": cumulativeMCPExecutionIDs,
 		"conversationId":  conversationID,
 		"messageId":       assistantMessageID,
 		"agentMode":       "eino_single",
-	})
+	}))
 	sendEvent("done", "", map[string]interface{}{"conversationId": conversationID})
 }
 
@@ -429,6 +447,9 @@ func (h *AgentHandler) EinoSingleAgentLoop(c *gin.Context) {
 	curMsg := prep.FinalMessage
 	var result *multiagent.RunResult
 	var runErr error
+	var emptyResponseContinueAttempt int
+	var finalizationAutoContinueAttempt int
+	var decision agentfinalizer.Decision
 	for {
 		result, runErr = multiagent.RunEinoSingleChatModelAgent(
 			taskCtx,
@@ -446,28 +467,46 @@ func (h *AgentHandler) EinoSingleAgentLoop(c *gin.Context) {
 			chatReasoningToClientIntent(req.Reasoning),
 			h.agentSessionContextBlock(prep.ConversationID),
 		)
-		if runErr == nil {
+		if runErr != nil {
-			break
-		}
 			if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
 				h.persistEinoAgentTraceForResume(prep.ConversationID, result)
 			}
 			c.JSON(http.StatusInternalServerError, gin.H{"error": runErr.Error()})
 			return
 		}
-
+		mw := &h.config.MultiAgent.EinoMiddleware
-	if prep.AssistantMessageID != "" {
+		if h.tryContinueOnEinoEmptyResponse(taskCtx, mw, prep.ConversationID, result, &emptyResponseContinueAttempt, &curHist, &curMsg, progressCallback) {
-		_ = h.db.UpdateAssistantMessageFinalize(prep.AssistantMessageID, result.Response, result.MCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(result.LastAgentTraceInput))
+			continue
 		}
+		decision = h.decideAgentRunForDeliveryWithPolicy(prep.ConversationID, prep.AssistantMessageID, "eino_single", result, result.MCPExecutionIDs, requestRequiresExecutionEvidence(&req))
+		if h.tryAutoContinueAfterFinalization(taskCtx, prep.ConversationID, result, decision, &finalizationAutoContinueAttempt, &curHist, &curMsg, progressCallback) {
+			continue
+		}
+		break
+	}
+
+	h.persistFinalizationDecision(prep.ConversationID, prep.AssistantMessageID, "eino_single", result.MCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(result.LastAgentTraceInput), decision)
 	if result.LastAgentTraceInput != "" || result.LastAgentTraceOutput != "" {
 		_ = h.db.SaveAgentTrace(prep.ConversationID, result.LastAgentTraceInput, result.LastAgentTraceOutput)
 	}
 
+	responseText := decision.FinalText
+	if !decision.Finalizable {
+		responseText = finalizationBlockedMessage(decision)
+	}
 	c.JSON(http.StatusOK, gin.H{
-		"response":           result.Response,
+		"response":            responseText,
 		"conversationId":      prep.ConversationID,
 		"mcpExecutionIds":     result.MCPExecutionIDs,
 		"assistantMessageId":  prep.AssistantMessageID,
 		"agentMode":           "eino_single",
+		"finalized":           decision.Finalized,
+		"finalizable":         decision.Finalizable,
+		"status":              decision.Status,
+		"completionReason":    decision.CompletionReason,
+		"evidenceVerified":    decision.EvidenceVerified,
+		"evidenceRefs":        decision.EvidenceRefs,
+		"pendingExecutionIds": decision.PendingExecutionIDs,
+		"missingChecks":       decision.MissingChecks,
 	})
 }

internal/handler/finalization_auto_continue.go

@@ -0,0 +1,77 @@
+package handler
+
+import (
+	"context"
+	"time"
+
+	"cyberstrike-ai/internal/agent"
+	"cyberstrike-ai/internal/agentfinalizer"
+	"cyberstrike-ai/internal/multiagent"
+
+	"go.uber.org/zap"
+)
+
+const finalizationAutoContinueMaxAttempts = 2
+
+func shouldAutoContinueAfterFinalization(d agentfinalizer.Decision, attempt int) bool {
+	if d.Finalizable || d.Finalized {
+		return false
+	}
+	if attempt >= finalizationAutoContinueMaxAttempts {
+		return false
+	}
+	return d.CompletionReason == agentfinalizer.ReasonMissingEvidence
+}
+
+func (h *AgentHandler) tryAutoContinueAfterFinalization(
+	taskCtx context.Context,
+	conversationID string,
+	result *multiagent.RunResult,
+	decision agentfinalizer.Decision,
+	attempt *int,
+	curHistory *[]agent.ChatMessage,
+	curFinalMessage *string,
+	progressCallback func(eventType, message string, data interface{}),
+) bool {
+	if !shouldAutoContinueAfterFinalization(decision, *attempt) || result == nil || !multiagent.HasEinoResumeTrace(result) {
+		return false
+	}
+	*attempt++
+	h.persistEinoAgentTraceForResume(conversationID, result)
+	if hist, err := h.loadHistoryFromAgentTrace(conversationID); err == nil && len(hist) > 0 {
+		*curHistory = hist
+	} else if h.logger != nil {
+		h.logger.Warn("finalization auto-continue could not restore trace",
+			zap.String("conversationId", conversationID),
+			zap.Error(err))
+		return false
+	}
+	// Agent 无感续跑：不追加新的 user/system 文案，只使用上一段模型可见轨迹继续 Runner。
+	*curFinalMessage = ""
+	if progressCallback != nil {
+		progressCallback("finalization_auto_continue", "最终回复检查尚未收敛，正在基于已有轨迹继续执行…", map[string]interface{}{
+			"conversationId":      conversationID,
+			"source":              "finalizer",
+			"attempt":             *attempt,
+			"maxAttempts":         finalizationAutoContinueMaxAttempts,
+			"status":              decision.Status,
+			"completionReason":    decision.CompletionReason,
+			"missingChecks":       decision.MissingChecks,
+			"pendingExecutionIds": decision.PendingExecutionIDs,
+			"contextInjection":    false,
+		})
+	}
+	select {
+	case <-taskCtx.Done():
+		return false
+	case <-time.After(finalizationAutoContinueBackoff(*attempt)):
+		return true
+	}
+}
+
+func finalizationAutoContinueBackoff(attempt int) time.Duration {
+	if attempt <= 1 {
+		return 500 * time.Millisecond
+	}
+	return time.Duration(attempt) * time.Second
+}

internal/handler/finalization_auto_continue_test.go

@@ -0,0 +1,59 @@
+package handler
+
+import (
+	"testing"
+
+	"cyberstrike-ai/internal/agentfinalizer"
+)
+
+func TestShouldAutoContinueAfterFinalization(t *testing.T) {
+	missingEvidence := agentfinalizer.Decision{
+		Status:           agentfinalizer.StatusBlocked,
+		CompletionReason: agentfinalizer.ReasonMissingEvidence,
+	}
+	if !shouldAutoContinueAfterFinalization(missingEvidence, 0) {
+		t.Fatal("missing execution evidence should trigger auto-continue")
+	}
+	if shouldAutoContinueAfterFinalization(missingEvidence, finalizationAutoContinueMaxAttempts) {
+		t.Fatal("auto-continue should stop at max attempts")
+	}
+
+	finalized := agentfinalizer.Decision{
+		Status:           agentfinalizer.StatusCompleted,
+		CompletionReason: agentfinalizer.ReasonVerified,
+		Finalizable:      true,
+		Finalized:        true,
+	}
+	if shouldAutoContinueAfterFinalization(finalized, 0) {
+		t.Fatal("finalized decision should not auto-continue")
+	}
+
+	awaitingHITL := agentfinalizer.Decision{
+		Status:           agentfinalizer.StatusAwaitingHITL,
+		CompletionReason: agentfinalizer.ReasonAwaitingHITL,
+	}
+	if shouldAutoContinueAfterFinalization(awaitingHITL, 0) {
+		t.Fatal("awaiting HITL should not auto-continue without approval")
+	}
+}
+
+func TestRequestRequiresExecutionEvidenceUsesExplicitPolicyOnly(t *testing.T) {
+	if requestRequiresExecutionEvidence(nil) {
+		t.Fatal("nil request should not require execution evidence")
+	}
+	if requestRequiresExecutionEvidence(&ChatRequest{}) {
+		t.Fatal("missing finalization policy should not require execution evidence")
+	}
+	require := true
+	if !requestRequiresExecutionEvidence(&ChatRequest{
+		Finalization: ChatFinalizationRequest{RequireExecutionEvidence: &require},
+	}) {
+		t.Fatal("explicit true policy should require execution evidence")
+	}
+	require = false
+	if requestRequiresExecutionEvidence(&ChatRequest{
+		Finalization: ChatFinalizationRequest{RequireExecutionEvidence: &require},
+	}) {
+		t.Fatal("explicit false policy should not require execution evidence")
+	}
+}

internal/handler/finalization_helpers.go

@@ -0,0 +1,171 @@
+package handler
+
+import (
+	"fmt"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/agentfinalizer"
+	"cyberstrike-ai/internal/multiagent"
+
+	"go.uber.org/zap"
+)
+
+func (h *AgentHandler) finalizeAgentRunForDelivery(
+	conversationID string,
+	assistantMessageID string,
+	agentMode string,
+	result *multiagent.RunResult,
+	mcpExecutionIDs []string,
+	reasoningContent string,
+) agentfinalizer.Decision {
+	return h.finalizeAgentRunForDeliveryWithPolicy(conversationID, assistantMessageID, agentMode, result, mcpExecutionIDs, reasoningContent, false)
+}
+
+func (h *AgentHandler) finalizeAgentRunForDeliveryWithPolicy(
+	conversationID string,
+	assistantMessageID string,
+	agentMode string,
+	result *multiagent.RunResult,
+	mcpExecutionIDs []string,
+	reasoningContent string,
+	requireExecutionEvidence bool,
+) agentfinalizer.Decision {
+	decision := agentfinalizer.FromRunResult(h.db, result, agentfinalizer.Input{
+		ConversationID:           conversationID,
+		AssistantMessageID:       assistantMessageID,
+		AgentMode:                agentMode,
+		MCPExecutionIDs:          mcpExecutionIDs,
+		RequireExecutionEvidence: requireExecutionEvidence,
+	})
+	h.persistFinalizationDecision(conversationID, assistantMessageID, agentMode, mcpExecutionIDs, reasoningContent, decision)
+	return decision
+}
+
+func (h *AgentHandler) decideAgentRunForDeliveryWithPolicy(
+	conversationID string,
+	assistantMessageID string,
+	agentMode string,
+	result *multiagent.RunResult,
+	mcpExecutionIDs []string,
+	requireExecutionEvidence bool,
+) agentfinalizer.Decision {
+	return agentfinalizer.FromRunResult(h.db, result, agentfinalizer.Input{
+		ConversationID:           conversationID,
+		AssistantMessageID:       assistantMessageID,
+		AgentMode:                agentMode,
+		MCPExecutionIDs:          mcpExecutionIDs,
+		RequireExecutionEvidence: requireExecutionEvidence,
+	})
+}
+
+func (h *AgentHandler) decideAgentRunForDelivery(
+	conversationID string,
+	assistantMessageID string,
+	agentMode string,
+	result *multiagent.RunResult,
+	mcpExecutionIDs []string,
+) agentfinalizer.Decision {
+	return agentfinalizer.FromRunResult(h.db, result, agentfinalizer.Input{
+		ConversationID:           conversationID,
+		AssistantMessageID:       assistantMessageID,
+		AgentMode:                agentMode,
+		MCPExecutionIDs:          mcpExecutionIDs,
+		RequireExecutionEvidence: false,
+	})
+}
+
+func (h *AgentHandler) persistFinalizationDecision(
+	conversationID string,
+	assistantMessageID string,
+	agentMode string,
+	mcpExecutionIDs []string,
+	reasoningContent string,
+	decision agentfinalizer.Decision,
+) {
+	if assistantMessageID == "" || h.db == nil {
+		return
+	}
+	_ = h.db.AddProcessDetail(assistantMessageID, conversationID, "finalization_check", finalizationCheckMessage(decision), decision)
+	if decision.Finalizable {
+		if err := h.db.UpdateAssistantMessageFinalize(assistantMessageID, decision.FinalText, mcpExecutionIDs, reasoningContent); err != nil && h.logger != nil {
+			h.logger.Warn("更新最终助手消息失败", zap.Error(err), zap.String("conversationId", conversationID), zap.String("agentMode", agentMode))
+		}
+		return
+	}
+	_, _ = h.db.Exec("UPDATE messages SET content = ?, updated_at = ? WHERE id = ?", finalizationBlockedMessage(decision), time.Now(), assistantMessageID)
+}
+
+func (h *AgentHandler) finalizeCandidateForDelivery(
+	conversationID string,
+	assistantMessageID string,
+	agentMode string,
+	response string,
+	mcpExecutionIDs []string,
+	awaitingHITL bool,
+	reasoningContent string,
+) agentfinalizer.Decision {
+	return h.finalizeCandidateForDeliveryWithPolicy(conversationID, assistantMessageID, agentMode, response, mcpExecutionIDs, awaitingHITL, reasoningContent, false)
+}
+
+func (h *AgentHandler) finalizeCandidateForDeliveryWithPolicy(
+	conversationID string,
+	assistantMessageID string,
+	agentMode string,
+	response string,
+	mcpExecutionIDs []string,
+	awaitingHITL bool,
+	reasoningContent string,
+	requireExecutionEvidence bool,
+) agentfinalizer.Decision {
+	decision := agentfinalizer.Decide(h.db, agentfinalizer.Input{
+		Response:                 response,
+		ConversationID:           conversationID,
+		AssistantMessageID:       assistantMessageID,
+		AgentMode:                agentMode,
+		MCPExecutionIDs:          mcpExecutionIDs,
+		AwaitingHITL:             awaitingHITL,
+		RequireExecutionEvidence: requireExecutionEvidence,
+	})
+	if assistantMessageID == "" || h.db == nil {
+		return decision
+	}
+	_ = h.db.AddProcessDetail(assistantMessageID, conversationID, "finalization_check", finalizationCheckMessage(decision), decision)
+	if decision.Finalizable {
+		if err := h.db.UpdateAssistantMessageFinalize(assistantMessageID, decision.FinalText, mcpExecutionIDs, reasoningContent); err != nil && h.logger != nil {
+			h.logger.Warn("更新最终助手消息失败", zap.Error(err), zap.String("conversationId", conversationID), zap.String("agentMode", agentMode))
+		}
+		return decision
+	}
+	_, _ = h.db.Exec("UPDATE messages SET content = ?, updated_at = ? WHERE id = ?", finalizationBlockedMessage(decision), time.Now(), assistantMessageID)
+	return decision
+}
+
+func finalizationCheckMessage(d agentfinalizer.Decision) string {
+	if d.Finalizable {
+		return "最终回复检查通过。"
+	}
+	return finalizationBlockedMessage(d)
+}
+
+func finalizationBlockedMessage(d agentfinalizer.Decision) string {
+	parts := []string{"任务尚未达到最终回复条件，暂不生成成功结论。"}
+	if d.CompletionReason != "" {
+		parts = append(parts, "原因: "+d.CompletionReason)
+	}
+	if len(d.PendingExecutionIDs) > 0 {
+		parts = append(parts, fmt.Sprintf("仍有 %d 个工具执行未结束: %s", len(d.PendingExecutionIDs), strings.Join(d.PendingExecutionIDs, ", ")))
+	}
+	if len(d.MissingChecks) > 0 {
+		parts = append(parts, "缺失检查: "+strings.Join(d.MissingChecks, "; "))
+	}
+	return strings.Join(parts, "\n")
+}
+
+func finalizationResponsePayload(d agentfinalizer.Decision, extra map[string]interface{}) map[string]interface{} {
+	return agentfinalizer.ResponsePayload(d, extra)
+}
+
+func requestRequiresExecutionEvidence(req *ChatRequest) bool {
+	return req != nil && req.Finalization.RequireExecutionEvidence != nil && *req.Finalization.RequireExecutionEvidence
+}

internal/handler/multi_agent.go

@@ -10,6 +10,7 @@ import (
 	"sync"
 	"time"
 
+	"cyberstrike-ai/internal/agentfinalizer"
 	"cyberstrike-ai/internal/config"
 	"cyberstrike-ai/internal/mcp"
 	"cyberstrike-ai/internal/multiagent"
@@ -197,6 +198,13 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 	// 同一请求内分段续跑时，主代理 iteration 事件按偏移累计，避免 UI 出现「第3轮 → 第1轮」回跳。
 	var mainIterationOffset int
 	var emptyResponseContinueAttempt int
+	var finalizationAutoContinueAttempt int
+	effectiveOrch := config.NormalizeMultiAgentOrchestration(h.config.MultiAgent.Orchestration)
+	if o := strings.TrimSpace(req.Orchestration); o != "" {
+		effectiveOrch = config.NormalizeMultiAgentOrchestration(o)
+	}
+	agentMode := "eino_" + effectiveOrch
+	var decision agentfinalizer.Decision
 
 	for {
 		segmentMainIterationMax := 0
@@ -267,6 +275,13 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 				baseCtx, cancelWithCause, taskCtx, timeoutCancel = h.rebindEinoRunningTask(taskCtx, conversationID, timeoutCancel)
 				continue
 			}
+			decision = h.decideAgentRunForDeliveryWithPolicy(conversationID, assistantMessageID, agentMode, result, cumulativeMCPExecutionIDs, requestRequiresExecutionEvidence(&req))
+			if h.tryAutoContinueAfterFinalization(taskCtx, conversationID, result, decision, &finalizationAutoContinueAttempt, &curHistory, &curFinalMessage, progressCallback) {
+				mainIterationOffset += segmentMainIterationMax
+				timeoutCancel()
+				baseCtx, cancelWithCause, taskCtx, timeoutCancel = h.rebindEinoRunningTask(taskCtx, conversationID, timeoutCancel)
+				continue
+			}
 			timeoutCancel()
 			break
 		}
@@ -367,9 +382,10 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 
 	timeoutCancel()
 
-	if assistantMessageID != "" {
+	if decision.CompletionReason == "" {
-		_ = h.db.UpdateAssistantMessageFinalize(assistantMessageID, result.Response, cumulativeMCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(result.LastAgentTraceInput))
+		decision = h.decideAgentRunForDeliveryWithPolicy(conversationID, assistantMessageID, agentMode, result, cumulativeMCPExecutionIDs, requestRequiresExecutionEvidence(&req))
 	}
+	h.persistFinalizationDecision(conversationID, assistantMessageID, agentMode, cumulativeMCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(result.LastAgentTraceInput), decision)
 
 	if result.LastAgentTraceInput != "" || result.LastAgentTraceOutput != "" {
 		if err := h.db.SaveAgentTrace(conversationID, result.LastAgentTraceInput, result.LastAgentTraceOutput); err != nil {
@@ -377,16 +393,19 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 		}
 	}
 
-	effectiveOrch := config.NormalizeMultiAgentOrchestration(h.config.MultiAgent.Orchestration)
+	responseText := decision.FinalText
-	if o := strings.TrimSpace(req.Orchestration); o != "" {
+	if !decision.Finalizable {
-		effectiveOrch = config.NormalizeMultiAgentOrchestration(o)
+		responseText = finalizationBlockedMessage(decision)
+		sendEvent("finalization_check", responseText, decision)
+		taskStatus = decision.Status
+		h.tasks.UpdateTaskStatus(conversationID, taskStatus)
 	}
-	sendEvent("response", result.Response, map[string]interface{}{
+	sendEvent("response", responseText, finalizationResponsePayload(decision, map[string]interface{}{
 		"mcpExecutionIds": cumulativeMCPExecutionIDs,
 		"conversationId":  conversationID,
 		"messageId":       assistantMessageID,
-		"agentMode":       "eino_" + effectiveOrch,
+		"agentMode":       agentMode,
-	})
+	}))
 	sendEvent("done", "", map[string]interface{}{"conversationId": conversationID})
 }
 
@@ -437,6 +456,14 @@ func (h *AgentHandler) MultiAgentLoop(c *gin.Context) {
 	curMsg := prep.FinalMessage
 	var result *multiagent.RunResult
 	var runErr error
+	var emptyResponseContinueAttempt int
+	var finalizationAutoContinueAttempt int
+	effectiveOrch := config.NormalizeMultiAgentOrchestration(h.config.MultiAgent.Orchestration)
+	if o := strings.TrimSpace(req.Orchestration); o != "" {
+		effectiveOrch = config.NormalizeMultiAgentOrchestration(o)
+	}
+	agentMode := "eino_" + effectiveOrch
+	var decision agentfinalizer.Decision
 	for {
 		result, runErr = multiagent.RunDeepAgent(
 			taskCtx,
@@ -456,9 +483,7 @@ func (h *AgentHandler) MultiAgentLoop(c *gin.Context) {
 			chatReasoningToClientIntent(req.Reasoning),
 			h.agentSessionContextBlock(prep.ConversationID),
 		)
-		if runErr == nil {
+		if runErr != nil {
-			break
-		}
 			if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
 				h.persistEinoAgentTraceForResume(prep.ConversationID, result)
 			}
@@ -470,10 +495,18 @@ func (h *AgentHandler) MultiAgentLoop(c *gin.Context) {
 			c.JSON(http.StatusInternalServerError, gin.H{"error": errMsg})
 			return
 		}
-
+		mw := &h.config.MultiAgent.EinoMiddleware
-	if prep.AssistantMessageID != "" {
+		if h.tryContinueOnEinoEmptyResponse(taskCtx, mw, prep.ConversationID, result, &emptyResponseContinueAttempt, &curHist, &curMsg, progressCallback) {
-		_ = h.db.UpdateAssistantMessageFinalize(prep.AssistantMessageID, result.Response, result.MCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(result.LastAgentTraceInput))
+			continue
 		}
+		decision = h.decideAgentRunForDeliveryWithPolicy(prep.ConversationID, prep.AssistantMessageID, agentMode, result, result.MCPExecutionIDs, requestRequiresExecutionEvidence(&req))
+		if h.tryAutoContinueAfterFinalization(taskCtx, prep.ConversationID, result, decision, &finalizationAutoContinueAttempt, &curHist, &curMsg, progressCallback) {
+			continue
+		}
+		break
+	}
+
+	h.persistFinalizationDecision(prep.ConversationID, prep.AssistantMessageID, agentMode, result.MCPExecutionIDs, multiagent.AggregatedReasoningFromTraceJSON(result.LastAgentTraceInput), decision)
 
 	if result.LastAgentTraceInput != "" || result.LastAgentTraceOutput != "" {
 		if err := h.db.SaveAgentTrace(prep.ConversationID, result.LastAgentTraceInput, result.LastAgentTraceOutput); err != nil {
@@ -481,11 +514,23 @@ func (h *AgentHandler) MultiAgentLoop(c *gin.Context) {
 		}
 	}
 
+	responseText := decision.FinalText
+	if !decision.Finalizable {
+		responseText = finalizationBlockedMessage(decision)
+	}
 	c.JSON(http.StatusOK, ChatResponse{
-		Response:        result.Response,
+		Response:            responseText,
 		MCPExecutionIDs:     result.MCPExecutionIDs,
 		ConversationID:      prep.ConversationID,
 		Time:                time.Now(),
+		Finalizable:         decision.Finalizable,
+		Finalized:           decision.Finalized,
+		Status:              decision.Status,
+		CompletionReason:    decision.CompletionReason,
+		EvidenceVerified:    decision.EvidenceVerified,
+		EvidenceRefs:        decision.EvidenceRefs,
+		PendingExecutionIDs: decision.PendingExecutionIDs,
+		MissingChecks:       decision.MissingChecks,
 	})
 }
 

internal/handler/multi_agent_prepare.go

@@ -6,6 +6,7 @@ import (
 
 	"cyberstrike-ai/internal/agent"
 	"cyberstrike-ai/internal/audit"
+	"cyberstrike-ai/internal/config"
 	"cyberstrike-ai/internal/database"
 	"cyberstrike-ai/internal/mcp/builtin"
 	"cyberstrike-ai/internal/security"
@@ -25,6 +26,13 @@ type multiAgentPrepared struct {
 	UserMessageID      string
 }
 
+func chatRequestAgentMode(req *ChatRequest, source string) string {
+	if strings.HasPrefix(strings.TrimSpace(source), "multi_agent") {
+		return config.NormalizeMultiAgentOrchestration(req.Orchestration)
+	}
+	return "eino_single"
+}
+
 func (h *AgentHandler) prepareMultiAgentSession(req *ChatRequest, c *gin.Context, source string) (*multiAgentPrepared, error) {
 	if len(req.Attachments) > maxAttachments {
 		return nil, fmt.Errorf("附件最多 %d 个", maxAttachments)
@@ -57,6 +65,7 @@ func (h *AgentHandler) prepareMultiAgentSession(req *ChatRequest, c *gin.Context
 		meta := audit.ConversationCreateMetaFromGin(c, source)
 		meta.ProjectID = projectID
 		meta.RoleName = req.Role
+		meta.AgentMode = chatRequestAgentMode(req, source)
 		if webshellID != "" {
 			meta.Source = source + "_webshell"
 			meta.WebShellConnectionID = webshellID
@@ -84,6 +93,9 @@ func (h *AgentHandler) prepareMultiAgentSession(req *ChatRequest, c *gin.Context
 	if err := h.db.SetConversationRoleName(conversationID, req.Role); err != nil {
 		h.logger.Warn("更新对话角色失败", zap.String("conversationId", conversationID), zap.String("role", req.Role), zap.Error(err))
 	}
+	if err := h.db.SetConversationAgentMode(conversationID, chatRequestAgentMode(req, source)); err != nil {
+		h.logger.Warn("更新对话模式失败", zap.String("conversationId", conversationID), zap.String("source", source), zap.String("orchestration", req.Orchestration), zap.Error(err))
+	}
 
 	agentHistoryMessages, err := h.loadHistoryFromAgentTrace(conversationID)
 	if err != nil {

internal/handler/openapi.go

@@ -35,6 +35,17 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 		scheme = "https"
 	}
 
+	finalizationRequestSchema := map[string]interface{}{
+		"type":        "object",
+		"description": "最终回复交付策略。后端不会从自然语言内容推断执行意图；执行入口应显式声明是否要求 completed 工具证据。",
+		"properties": map[string]interface{}{
+			"requireExecutionEvidence": map[string]interface{}{
+				"type":        "boolean",
+				"description": "为 true 时，缺少 completed 工具执行记录会触发无注入续跑或最终阻断；普通聊天可省略或设为 false。",
+			},
+		},
+	}
+
 	spec := map[string]interface{}{
 		"openapi": "3.0.0",
 		"info": map[string]interface{}{
@@ -85,6 +96,70 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 					},
 					"required": []string{"projectId"},
 				},
+				"AgentChatResponse": map[string]interface{}{
+					"type":        "object",
+					"description": "Agent 非流式响应。response 只是交付文本；是否为成功最终回复必须以 finalized/finalizable/status 为准。",
+					"properties": map[string]interface{}{
+						"response": map[string]interface{}{
+							"type":        "string",
+							"description": "交付给用户的文本。finalized=false 时为阻断/未完成说明，不是成功结论。",
+						},
+						"conversationId": map[string]interface{}{
+							"type":        "string",
+							"description": "对话 ID",
+						},
+						"assistantMessageId": map[string]interface{}{
+							"type":        "string",
+							"description": "助手消息 ID（部分接口返回）",
+						},
+						"mcpExecutionIds": map[string]interface{}{
+							"type":        "array",
+							"description": "本轮关联的 MCP 工具执行 ID",
+							"items":       map[string]interface{}{"type": "string"},
+						},
+						"agentMode": map[string]interface{}{
+							"type":        "string",
+							"description": "agent 模式，例如 eino_single、eino_deep、workflow",
+						},
+						"finalized": map[string]interface{}{
+							"type":        "boolean",
+							"description": "是否已经通过最终回复检查。只有 true 才能当成功最终回复。",
+						},
+						"finalizable": map[string]interface{}{
+							"type":        "boolean",
+							"description": "候选输出是否可提升为最终回复。",
+						},
+						"status": map[string]interface{}{
+							"type":        "string",
+							"description": "最终化状态",
+							"enum":        []string{"completed", "in_progress", "blocked", "failed", "cancelled", "awaiting_hitl"},
+						},
+						"completionReason": map[string]interface{}{
+							"type":        "string",
+							"description": "最终化或阻断原因，例如 verified、pending_tool_executions、missing_execution_evidence",
+						},
+						"evidenceVerified": map[string]interface{}{
+							"type":        "boolean",
+							"description": "证据是否满足最终化要求",
+						},
+						"evidenceRefs": map[string]interface{}{
+							"type":        "array",
+							"description": "证据引用，例如 mcp_execution:<id>",
+							"items":       map[string]interface{}{"type": "string"},
+						},
+						"pendingExecutionIds": map[string]interface{}{
+							"type":        "array",
+							"description": "仍处于 queued/running 的工具执行 ID",
+							"items":       map[string]interface{}{"type": "string"},
+						},
+						"missingChecks": map[string]interface{}{
+							"type":        "array",
+							"description": "未通过最终化检查的原因列表",
+							"items":       map[string]interface{}{"type": "string"},
+						},
+					},
+					"required": []string{"response", "conversationId", "finalized", "finalizable", "status", "evidenceVerified"},
+				},
 				"Conversation": map[string]interface{}{
 					"type": "object",
 					"properties": map[string]interface{}{
@@ -1581,6 +1656,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 										"conversationId":       map[string]interface{}{"type": "string"},
 										"role":                 map[string]interface{}{"type": "string"},
 										"webshellConnectionId": map[string]interface{}{"type": "string"},
+										"finalization":         finalizationRequestSchema,
 									},
 									"required": []string{"message"},
 								},
@@ -1588,7 +1664,14 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 						},
 					},
 					"responses": map[string]interface{}{
-						"200": map[string]interface{}{"description": "成功，响应格式同 /api/eino-agent"},
+						"200": map[string]interface{}{
+							"description": "成功。只有 finalized=true 表示成功最终回复；finalized=false 时 response 为未完成/阻断说明。",
+							"content": map[string]interface{}{
+								"application/json": map[string]interface{}{
+									"schema": map[string]interface{}{"$ref": "#/components/schemas/AgentChatResponse"},
+								},
+							},
+						},
 						"400": map[string]interface{}{"description": "参数错误"},
 						"401": map[string]interface{}{"description": "未授权"},
 						"500": map[string]interface{}{"description": "执行失败"},
@@ -1599,7 +1682,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 				"post": map[string]interface{}{
 					"tags":        []string{"对话交互"},
 					"summary":     "发送消息并获取 AI 回复（Eino ADK 单代理，SSE）",
-					"description": "向 AI 发送消息并获取流式回复（SSE）。由 Eino **单代理** ADK 执行；事件类型与多代理流式一致（含 `tool_call` / `response_delta` / `thinking` 等）。**不依赖** `multi_agent.enabled`。",
+					"description": "向 AI 发送消息并获取流式回复（SSE）。由 Eino **单代理** ADK 执行；事件类型与多代理流式一致（含 `tool_call` / `response_delta` / `thinking` 等）。`response_start` / `response_delta` 仅为候选/过程输出；只有 `type: response` 且 `data.finalized=true` 才表示成功最终回复。缺 completed 执行证据时可能先发送 `finalization_auto_continue`，表示服务端基于已有 trace 无注入续跑。`data.finalized=false` 时 message 为未完成/阻断说明。**不依赖** `multi_agent.enabled`。",
 					"operationId": "sendMessageEinoSingleAgentStream",
 					"requestBody": map[string]interface{}{
 						"required": true,
@@ -1612,6 +1695,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 										"conversationId":       map[string]interface{}{"type": "string"},
 										"role":                 map[string]interface{}{"type": "string"},
 										"webshellConnectionId": map[string]interface{}{"type": "string"},
+										"finalization":         finalizationRequestSchema,
 									},
 									"required": []string{"message"},
 								},
@@ -1625,7 +1709,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 								"text/event-stream": map[string]interface{}{
 									"schema": map[string]interface{}{
 										"type":        "string",
-										"description": "SSE 流",
+										"description": "SSE 流。终态 response 事件 data 包含 finalized、finalizable、status、completionReason、evidenceVerified、evidenceRefs、pendingExecutionIds、missingChecks；过程事件可能包含 finalization_auto_continue。",
 									},
 								},
 							},
@@ -1663,6 +1747,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 											"type":        "string",
 											"description": "WebShell 连接 ID（可选，与 Eino 单/多代理流式行为一致）",
 										},
+										"finalization": finalizationRequestSchema,
 										"orchestration": map[string]interface{}{
 											"type":        "string",
 											"description": "Eino 预置编排：deep | plan_execute | supervisor；缺省 deep",
@@ -1676,7 +1761,12 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 					},
 					"responses": map[string]interface{}{
 						"200": map[string]interface{}{
-							"description": "成功，响应格式同 /api/eino-agent",
+							"description": "成功。只有 finalized=true 表示成功最终回复；finalized=false 时 response 为未完成/阻断说明。",
+							"content": map[string]interface{}{
+								"application/json": map[string]interface{}{
+									"schema": map[string]interface{}{"$ref": "#/components/schemas/AgentChatResponse"},
+								},
+							},
 						},
 						"400": map[string]interface{}{"description": "参数错误"},
 						"401": map[string]interface{}{"description": "未授权"},
@@ -1689,7 +1779,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 				"post": map[string]interface{}{
 					"tags":        []string{"对话交互"},
 					"summary":     "发送消息并获取 AI 回复（Eino 多代理，SSE）",
-					"description": "与 `POST /api/eino-agent/stream` 类似；由 Eino 多代理执行。`orchestration` 指定 deep / plan_execute / supervisor，缺省 deep。**前提**：`multi_agent.enabled: true`；未启用时 SSE 内首条为 `type: error` 后接 `done`。支持 `webshellConnectionId`。",
+					"description": "与 `POST /api/eino-agent/stream` 类似；由 Eino 多代理执行。`orchestration` 指定 deep / plan_execute / supervisor，缺省 deep。`response_start` / `response_delta` 仅为候选/过程输出；只有 `type: response` 且 `data.finalized=true` 才表示成功最终回复。缺 completed 执行证据时可能先发送 `finalization_auto_continue`，表示服务端基于已有 trace 无注入续跑。**前提**：`multi_agent.enabled: true`；未启用时 SSE 内首条为 `type: error` 后接 `done`。支持 `webshellConnectionId`。",
 					"operationId": "sendMessageMultiAgentStream",
 					"requestBody": map[string]interface{}{
 						"required": true,
@@ -1702,6 +1792,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 										"conversationId":       map[string]interface{}{"type": "string"},
 										"role":                 map[string]interface{}{"type": "string"},
 										"webshellConnectionId": map[string]interface{}{"type": "string"},
+										"finalization":         finalizationRequestSchema,
 										"orchestration": map[string]interface{}{
 											"type":        "string",
 											"description": "deep | plan_execute | supervisor；缺省 deep",
@@ -1720,7 +1811,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 								"text/event-stream": map[string]interface{}{
 									"schema": map[string]interface{}{
 										"type":        "string",
-										"description": "SSE 流",
+										"description": "SSE 流。终态 response 事件 data 包含 finalized、finalizable、status、completionReason、evidenceVerified、evidenceRefs、pendingExecutionIds、missingChecks；过程事件可能包含 finalization_auto_continue。",
 									},
 								},
 							},

internal/handler/workflow_integration.go

@@ -152,20 +152,37 @@ func (h *AgentHandler) runRoleWorkflowStreamIfBound(
 		sendEvent("done", "", map[string]interface{}{"conversationId": conversationID})
 		return true
 	}
-	if prep.AssistantMessageID != "" {
+	decision := h.finalizeCandidateForDeliveryWithPolicy(
-		_ = h.db.UpdateAssistantMessageFinalize(prep.AssistantMessageID, result.Response, nil, "")
+		prep.ConversationID,
+		prep.AssistantMessageID,
+		"workflow",
+		result.Response,
+		nil,
+		result.AwaitingHITL,
+		"",
+		true,
+	)
+	responseText := decision.FinalText
+	if !decision.Finalizable {
+		responseText = finalizationBlockedMessage(decision)
+		taskStatus = decision.Status
+		h.tasks.UpdateTaskStatus(conversationID, taskStatus)
+		sendEvent("finalization_check", responseText, decision)
 	}
-	payload := map[string]interface{}{
+	payload := finalizationResponsePayload(decision, map[string]interface{}{
 		"conversationId": prep.ConversationID,
 		"messageId":      prep.AssistantMessageID,
 		"agentMode":      "workflow",
 		"workflowRunId":  result.RunID,
-	}
+	})
 	if result.AwaitingHITL {
 		payload["workflowStatus"] = "awaiting_hitl"
 		payload["awaitingHitl"] = true
+	} else {
+		payload["workflowStatus"] = result.Status
+		payload["awaitingHitl"] = false
 	}
-	sendEvent("response", result.Response, payload)
+	sendEvent("response", responseText, payload)
 	sendEvent("done", "", map[string]interface{}{"conversationId": prep.ConversationID})
 	return true
 }
@@ -251,17 +268,37 @@ func (h *AgentHandler) runRoleWorkflowJSONIfBound(c *gin.Context, req *ChatReque
 		c.JSON(http.StatusInternalServerError, gin.H{"error": errMsg, "conversationId": conversationID})
 		return true
 	}
-	if prep.AssistantMessageID != "" {
+	decision := h.finalizeCandidateForDeliveryWithPolicy(
-		_ = h.db.UpdateAssistantMessageFinalize(prep.AssistantMessageID, result.Response, nil, "")
+		prep.ConversationID,
+		prep.AssistantMessageID,
+		"workflow",
+		result.Response,
+		nil,
+		result.AwaitingHITL,
+		"",
+		true,
+	)
+	responseText := decision.FinalText
+	if !decision.Finalizable {
+		responseText = finalizationBlockedMessage(decision)
+		taskStatus = decision.Status
 	}
 	c.JSON(http.StatusOK, gin.H{
-		"response":           result.Response,
+		"response":            responseText,
 		"conversationId":      prep.ConversationID,
 		"assistantMessageId":  prep.AssistantMessageID,
 		"agentMode":           "workflow",
 		"workflowRunId":       result.RunID,
 		"workflowStatus":      result.Status,
 		"awaitingHitl":        result.AwaitingHITL,
+		"finalized":           decision.Finalized,
+		"finalizable":         decision.Finalizable,
+		"status":              decision.Status,
+		"completionReason":    decision.CompletionReason,
+		"evidenceVerified":    decision.EvidenceVerified,
+		"evidenceRefs":        decision.EvidenceRefs,
+		"pendingExecutionIds": decision.PendingExecutionIDs,
+		"missingChecks":       decision.MissingChecks,
 	})
 	return true
 }

internal/multiagent/runner.go

@@ -40,6 +40,13 @@ type RunResult struct {
 	MCPExecutionIDs      []string
 	LastAgentTraceInput  string // 已序列化的消息带（JSON）：原生循环或 Eino 均写入，供续跑/攻击链等恢复上下文
 	LastAgentTraceOutput string // 本轮助手侧对外展示文本（摘要或最终回复）
+	Finalized            bool
+	Status               string
+	CompletionReason     string
+	EvidenceVerified     bool
+	EvidenceRefs         []string
+	PendingExecutionIDs  []string
+	MissingChecks        []string
 }
 
 // toolCallPendingInfo tracks a tool_call emitted to the UI so we can later

web/static/css/style.css

@@ -3990,6 +3990,17 @@ html[data-theme="dark"] .new-chat-btn:focus-visible {
     border-top-left-radius: 2px;
 }
 
+.message.assistant.assistant-not-finalized .message-bubble {
+    border-color: rgba(245, 124, 0, 0.28);
+    border-left: 4px solid #f57c00;
+    background: linear-gradient(90deg, rgba(245, 124, 0, 0.08), rgba(245, 124, 0, 0.035));
+    box-shadow: 0 6px 18px rgba(245, 124, 0, 0.08);
+}
+
+.message.assistant.assistant-not-finalized .message-bubble strong:first-child {
+    color: #b45309;
+}
+
 .message.assistant .message-bubble pre {
     margin: 0;
     white-space: pre-wrap;
@@ -7381,6 +7392,16 @@ html[data-theme="dark"] .login-card .login-submit:disabled {
     background: rgba(245, 124, 0, 0.09);
 }
 
+.timeline-item-finalization_check {
+    border-left-color: #f57c00;
+    background: linear-gradient(90deg, rgba(245, 124, 0, 0.1), rgba(96, 125, 139, 0.045));
+}
+
+.timeline-item-finalization_check .timeline-item-title {
+    color: #9a5200;
+    font-weight: 600;
+}
+
 .timeline-item-tool_calls_detected {
     border-left-color: #0277bd;
     background: rgba(2, 119, 189, 0.06);
@@ -22967,6 +22988,18 @@ tr.mcp-stats-tool-row[data-tool-name]:focus-visible {
     font-weight: 500;
     color: var(--text-secondary);
 }
+
+.webshell-ai-timeline-finalization_check {
+    border-left: 3px solid #f57c00;
+    padding-left: 10px;
+    background: linear-gradient(90deg, rgba(245, 124, 0, 0.08), transparent);
+}
+
+.webshell-ai-timeline-finalization_check .webshell-ai-timeline-title {
+    color: #9a5200;
+    font-weight: 600;
+}
+
 .webshell-ai-timeline-msg {
     margin-top: 4px;
     padding-left: 0;
@@ -23144,6 +23177,11 @@ tr.mcp-stats-tool-row[data-tool-name]:focus-visible {
     background: var(--bg-secondary);
     border: 1px solid var(--border-color);
 }
+.webshell-ai-msg.assistant.webshell-ai-candidate-output {
+    border-color: rgba(245, 124, 0, 0.28);
+    background: linear-gradient(90deg, rgba(245, 124, 0, 0.08), rgba(245, 124, 0, 0.035));
+    box-shadow: 0 6px 16px rgba(245, 124, 0, 0.08);
+}
 .webshell-ai-msg.assistant.webshell-ai-msg-error {
     max-width: 72%;
     border-color: rgba(220, 53, 69, 0.35);
@@ -36232,12 +36270,42 @@ html[data-theme="dark"] .timeline-item-user_interrupt_continue {
     background: rgba(251, 191, 36, 0.08);
 }
 
+html[data-theme="dark"] .timeline-item-finalization_check {
+    background: linear-gradient(90deg, rgba(251, 191, 36, 0.1), rgba(30, 41, 59, 0.18));
+    border-left-color: #fbbf24;
+}
+
+html[data-theme="dark"] .timeline-item-finalization_check .timeline-item-title,
+html[data-theme="dark"] .webshell-ai-timeline-finalization_check .webshell-ai-timeline-title {
+    color: #fbbf24;
+}
+
 html[data-theme="dark"] .message.assistant .message-bubble {
     background: #111827;
     color: var(--text-primary);
     border-color: var(--border-color);
 }
 
+html[data-theme="dark"] .message.assistant.assistant-not-finalized .message-bubble {
+    border-color: rgba(251, 191, 36, 0.24);
+    border-left-color: #fbbf24;
+    background: linear-gradient(90deg, rgba(251, 191, 36, 0.08), rgba(17, 24, 39, 0.9));
+    box-shadow: 0 8px 22px rgba(0, 0, 0, 0.22);
+}
+
+html[data-theme="dark"] .message.assistant.assistant-not-finalized .message-bubble strong:first-child {
+    color: #fbbf24;
+}
+
+html[data-theme="dark"] .webshell-ai-timeline-finalization_check {
+    border-left-color: #fbbf24;
+    background: linear-gradient(90deg, rgba(251, 191, 36, 0.08), rgba(17, 24, 39, 0.12));
+}
+
+html[data-theme="dark"] .webshell-ai-msg.assistant.webshell-ai-candidate-output {
+    background: linear-gradient(90deg, rgba(251, 191, 36, 0.08), rgba(17, 24, 39, 0.12));
+}
+
 html[data-theme="dark"] .message-copy-btn {
     background: #1f2937;
     border-color: #334155;

web/static/js/assets.js

@@ -1147,6 +1147,7 @@ async function sendAssetsToChat(assets, template) {
     input.value = message;
     if (typeof adjustTextareaHeight === 'function') adjustTextareaHeight(input);
     // 消息流可能持续很久；启动发送即可返回，让提交弹窗立即关闭。
+    window.__csNextChatFinalizationPolicy = { requireExecutionEvidence: true };
     void sendMessage();
 }
 

web/static/js/chat.js

@@ -80,6 +80,7 @@ let chatAttachmentSeq = 0;
 
 // 对话模式：eino_single = Eino ADK 单代理（/api/eino-agent/stream）；deep / plan_execute / supervisor = Eino 多代理（/api/multi-agent/stream，请求体 orchestration）
 const AGENT_MODE_STORAGE_KEY = 'cyberstrike-chat-agent-mode';
+const AGENT_MODE_CONVERSATION_STORAGE_PREFIX = 'cyberstrike-chat-agent-mode:conversation';
 const AI_CHANNEL_STORAGE_KEY = 'cyberstrike-chat-ai-channel';
 const REASONING_MODE_LS = 'cyberstrike-chat-reasoning-mode';
 const REASONING_EFFORT_LS = 'cyberstrike-chat-reasoning-effort';
@@ -733,6 +734,44 @@ function chatAgentModeNormalizeStored(stored, cfg) {
     return CHAT_AGENT_MODE_EINO_SINGLE;
 }
 
+function normalizeConversationAgentModeForUI(mode) {
+    const v = String(mode || '').trim().toLowerCase().replace(/-/g, '_');
+    if (chatAgentModeIsEinoSingle(v)) return v;
+    if (chatAgentModeIsEino(v)) {
+        return multiAgentAPIEnabled ? v : CHAT_AGENT_MODE_EINO_SINGLE;
+    }
+    return '';
+}
+
+function conversationAgentModeStorageKey(conversationId) {
+    return `${AGENT_MODE_CONVERSATION_STORAGE_PREFIX}:${String(conversationId || '').trim()}`;
+}
+
+function readConversationAgentModePreference(conversationId) {
+    if (!conversationId) return '';
+    try {
+        return normalizeConversationAgentModeForUI(localStorage.getItem(conversationAgentModeStorageKey(conversationId)) || '');
+    } catch (e) {
+        return '';
+    }
+}
+
+function saveConversationAgentModePreference(conversationId, mode) {
+    const normalized = normalizeConversationAgentModeForUI(mode);
+    if (!conversationId || !normalized) return;
+    try {
+        localStorage.setItem(conversationAgentModeStorageKey(conversationId), normalized);
+    } catch (e) { /* ignore */ }
+}
+
+function applyConversationAgentMode(conversationId, conversation) {
+    const saved = readConversationAgentModePreference(conversationId);
+    const fromServer = normalizeConversationAgentModeForUI(conversation && (conversation.agentMode || conversation.agent_mode));
+    const mode = saved || fromServer;
+    if (!mode) return;
+    syncAgentModeFromValue(mode);
+}
+
 if (typeof window !== 'undefined') {
     window.csaiHitlGlobalToolWhitelist = window.csaiHitlGlobalToolWhitelist || [];
     window.csaiHitlDefaultReviewer = window.csaiHitlDefaultReviewer || 'human';
@@ -1098,6 +1137,7 @@ function toggleAgentModePanel() {
 function selectAgentMode(mode) {
     const ok = chatAgentModeIsEinoSingle(mode) || chatAgentModeIsEino(mode);
     if (!ok) return;
+    saveConversationAgentModePreference(currentConversationId, mode);
     try {
         localStorage.setItem(AGENT_MODE_STORAGE_KEY, mode);
     } catch (e) { /* ignore */ }
@@ -1351,6 +1391,10 @@ async function sendMessage() {
         conversationId: currentConversationId,
         role: typeof getCurrentRole === 'function' ? getCurrentRole() : ''
     };
+    if (window.__csNextChatFinalizationPolicy && typeof window.__csNextChatFinalizationPolicy === 'object') {
+        body.finalization = window.__csNextChatFinalizationPolicy;
+        window.__csNextChatFinalizationPolicy = null;
+    }
     let streamConversationId = body.conversationId ? String(body.conversationId) : null;
     const isStreamStillVisibleForRequest = function () {
         if (!document.getElementById(progressId)) return false;
@@ -1405,6 +1449,7 @@ async function sendMessage() {
     try {
         const modeSel = document.getElementById('agent-mode-select');
         let modeVal = modeSel ? modeSel.value : CHAT_AGENT_MODE_EINO_SINGLE;
+        saveConversationAgentModePreference(streamConversationId || currentConversationId, modeVal);
         const useMulti = multiAgentAPIEnabled && chatAgentModeIsEino(modeVal);
         const streamPath = useMulti ? '/api/multi-agent/stream' : '/api/eino-agent/stream';
         if (useMulti && modeVal) {
@@ -4845,6 +4890,7 @@ async function loadConversation(conversationId) {
         if (typeof window.setCurrentRole === 'function') {
             window.setCurrentRole(conversationRoleName || '默认');
         }
+        applyConversationAgentMode(conversationId, conversation);
         try {
             window.currentConversationId = conversationId;
         } catch (e) { /* ignore */ }

web/static/js/info-collect.js

@@ -1334,6 +1334,7 @@ function scanFofaRow(encodedRowJson, clickEvent) {
         }
         if (autoSend) {
             if (typeof sendMessage === 'function') {
+                window.__csNextChatFinalizationPolicy = { requireExecutionEvidence: true };
                 sendMessage();
             } else {
                 alert(_t('infoCollect.noSendMessage'));

web/static/js/monitor.js

@@ -198,6 +198,92 @@ function resolveFinalAssistantResponseText(finalMessage, streamState) {
     return finalMessage;
 }
 
+function isFinalizedResponseData(data) {
+    return !!(data && data.finalized === true);
+}
+
+function hasFinalizationContract(data) {
+    if (!data || typeof data !== 'object') return false;
+    return Object.prototype.hasOwnProperty.call(data, 'finalized')
+        || Object.prototype.hasOwnProperty.call(data, 'finalizable')
+        || Object.prototype.hasOwnProperty.call(data, 'completionReason')
+        || Object.prototype.hasOwnProperty.call(data, 'evidenceVerified')
+        || Object.prototype.hasOwnProperty.call(data, 'missingChecks');
+}
+
+function finalizationCheckTitle(data) {
+    return isFinalizedResponseData(data) ? '最终回复检查通过' : '最终回复检查未通过';
+}
+
+function finalizationReasonLabel(reason, status) {
+    const key = String(reason || status || '').trim();
+    const labels = {
+        pending_tool_executions: '等待工具执行完成',
+        missing_execution_evidence: '缺少完成态证据',
+        awaiting_hitl: '等待人工确认',
+        empty_response: '未捕获到有效回复',
+        missing_finalization_contract: '缺少最终化证明',
+        in_progress: '仍在验证',
+        blocked: '检查未通过',
+        failed: '任务失败',
+        cancelled: '任务已取消',
+        verified: '已验证'
+    };
+    return labels[key] || key || '检查未通过';
+}
+
+function finalizationMissingCheckLabel(check) {
+    const s = String(check || '').trim();
+    if (!s) return '';
+    if (s.indexOf('tool execution still queued or running') !== -1) return '仍有工具执行未结束';
+    if (s.indexOf('execution evidence is required but no completed tool execution was recorded') !== -1) return '本轮要求执行证据，但没有 completed 工具记录';
+    if (s.indexOf('workflow is awaiting HITL approval') !== -1) return '工作流正在等待人工确认';
+    if (s.indexOf('assistant final text is empty') !== -1) return '未捕获到有效最终文本';
+    if (s.indexOf('agent run status is ') === 0) return '任务状态仍为 ' + s.replace('agent run status is ', '');
+    return s;
+}
+
+function compactStringList(values, limit) {
+    const arr = Array.isArray(values) ? values.filter(Boolean).map(String) : [];
+    const max = limit || 3;
+    if (arr.length <= max) return arr;
+    return arr.slice(0, max).concat('另 ' + (arr.length - max) + ' 项');
+}
+
+function finalizationNoticeMarkdown(responseData, eventMessage) {
+    const hasContract = hasFinalizationContract(responseData);
+    const reason = hasContract
+        ? finalizationReasonLabel(responseData && responseData.completionReason, responseData && responseData.status)
+        : finalizationReasonLabel('missing_finalization_contract');
+    const lines = ['**仍在验证，暂不生成最终结论**', '', '状态：' + reason];
+    const pending = compactStringList(responseData && responseData.pendingExecutionIds, 3);
+    if (pending.length) {
+        lines.push('待完成工具：`' + pending.join('`, `') + '`');
+    }
+    const rawMissingChecks = responseData && responseData.missingChecks;
+    const missingChecks = Array.isArray(rawMissingChecks)
+        ? rawMissingChecks
+        : (rawMissingChecks ? [rawMissingChecks] : []);
+    const missing = compactStringList(missingChecks.map(finalizationMissingCheckLabel).filter(Boolean), 3);
+    if (missing.length) {
+        lines.push('待完成检查：' + missing.join('；'));
+    }
+    if (!hasContract && eventMessage != null && String(eventMessage).trim() !== '') {
+        lines.push('', '候选输出已移入过程详情，避免误判为最终结论。');
+    }
+    return lines.join('\n');
+}
+
+function markAssistantFinalizationState(assistantMessageId, responseData) {
+    const assistantElement = document.getElementById(assistantMessageId);
+    if (!assistantElement) return;
+    const finalized = isFinalizedResponseData(responseData);
+    assistantElement.dataset.finalized = finalized ? 'true' : 'false';
+    assistantElement.dataset.finalizationStatus = responseData && responseData.status ? String(responseData.status) : '';
+    assistantElement.classList.toggle('assistant-finalized', finalized);
+    assistantElement.classList.toggle('assistant-not-finalized', !finalized);
+}
+
 /**
  * 主通道 response 结束时：将流式占位条目固化为 planning（与后端 flushResponsePlan 落库类型一致），
  * 避免 integrateProgressToMCPSection 快照前删除占位导致「助手输出」仅刷新后才出现。
@@ -2440,6 +2526,26 @@ function handleStreamEvent(event, progressElement, progressId,
             });
             break;
 
+        case 'finalization_check':
+            const finalizationCheckData = event.data || {};
+            const finalizationCheckPassed = isFinalizedResponseData(finalizationCheckData);
+            addTimelineItem(timeline, 'finalization_check', {
+                title: finalizationCheckTitle(finalizationCheckData),
+                message: finalizationCheckPassed ? (event.message || '最终回复检查通过。') : finalizationNoticeMarkdown(finalizationCheckData, event.message),
+                data: event.data,
+                expanded: !finalizationCheckPassed
+            });
+            break;
+
+        case 'finalization_auto_continue':
+            addTimelineItem(timeline, 'progress', {
+                title: '继续验证',
+                message: event.message,
+                data: event.data,
+                expanded: false
+            });
+            break;
+
         case 'hitl_interrupt':
             const hitlTargetItem = findToolCallItemForHitl(timeline, event.data || {});
             if (hitlTargetItem && hitlTargetItem.id) {
@@ -2958,7 +3064,12 @@ function handleStreamEvent(event, progressElement, progressId,
             const streamState = responseStreamStateByProgressId.get(progressId);
             const existingAssistantId = streamState?.assistantId || getAssistantId();
             let assistantIdFinal = existingAssistantId;
-            const bubbleText = resolveFinalAssistantResponseText(event.message, streamState);
+            const responseFinalized = isFinalizedResponseData(responseData);
+            const responseHasFinalizationContract = hasFinalizationContract(responseData);
+            const resolvedResponseText = resolveFinalAssistantResponseText(event.message, streamState);
+            const bubbleText = responseFinalized
+                ? resolvedResponseText
+                : finalizationNoticeMarkdown(responseData, event.message);
 
             if (!assistantIdFinal) {
                 assistantIdFinal = addMessage('assistant', bubbleText, mcpIds, progressId);
@@ -2967,11 +3078,12 @@ function handleStreamEvent(event, progressElement, progressId,
                 setAssistantId(assistantIdFinal);
                 updateAssistantBubbleContent(assistantIdFinal, bubbleText, true);
             }
+            markAssistantFinalizationState(assistantIdFinal, responseData);
 
             // 将 response_start/response_delta 占位固化为 planning，与后端落库一致后再快照过程详情
             if (streamState && streamState.itemId) {
-                finalizeMainResponseStreamItem(streamState, event.message, responseData);
+                finalizeMainResponseStreamItem(streamState, responseFinalized ? event.message : '', responseData);
-            } else if (timeline && bubbleText && String(bubbleText).trim() && !isEinoEmptyResponsePlaceholder(event.message)) {
+            } else if (timeline && responseFinalized && bubbleText && String(bubbleText).trim() && !isEinoEmptyResponsePlaceholder(event.message)) {
                 addTimelineItem(timeline, 'planning', {
                     title: typeof einoMainStreamPlanningTitle === 'function'
                         ? einoMainStreamPlanningTitle(responseData)
@@ -2980,6 +3092,13 @@ function handleStreamEvent(event, progressElement, progressId,
                     data: responseData,
                     expanded: false
                 });
+            } else if (timeline && !responseFinalized && !responseHasFinalizationContract && resolvedResponseText && String(resolvedResponseText).trim()) {
+                addTimelineItem(timeline, 'finalization_check', {
+                    title: '候选输出缺少最终化证明',
+                    message: resolvedResponseText,
+                    data: Object.assign({}, responseData, { missingFinalizationContract: true }),
+                    expanded: true
+                });
             }
 
             // 最终回复时隐藏进度卡片（多代理模式下，迭代过程已完整展示）

web/static/js/webshell.js

@@ -1338,6 +1338,55 @@ function escapeHtmlAttr(s) {
     return escapeHtml(s).replace(/"/g, '"').replace(/'/g, ''');
 }
 
+function webshellFinalizationReasonLabel(reason, status) {
+    var key = String(reason || status || '').trim();
+    var labels = {
+        pending_tool_executions: '等待工具执行完成',
+        missing_execution_evidence: '缺少完成态证据',
+        awaiting_hitl: '等待人工确认',
+        empty_response: '未捕获到有效回复',
+        missing_finalization_contract: '缺少最终化证明',
+        in_progress: '仍在验证',
+        blocked: '检查未通过',
+        failed: '任务失败',
+        cancelled: '任务已取消',
+        verified: '已验证'
+    };
+    return labels[key] || key || '检查未通过';
+}
+
+function webshellFinalizationMissingCheckLabel(check) {
+    var s = String(check || '').trim();
+    if (!s) return '';
+    if (s.indexOf('tool execution still queued or running') !== -1) return '仍有工具执行未结束';
+    if (s.indexOf('execution evidence is required but no completed tool execution was recorded') !== -1) return '本轮要求执行证据，但没有 completed 工具记录';
+    if (s.indexOf('workflow is awaiting HITL approval') !== -1) return '工作流正在等待人工确认';
+    if (s.indexOf('assistant final text is empty') !== -1) return '未捕获到有效最终文本';
+    if (s.indexOf('agent run status is ') === 0) return '任务状态仍为 ' + s.replace('agent run status is ', '');
+    return s;
+}
+
+function webshellFinalizationNotice(data, eventMessage, hasContract) {
+    var reason = hasContract
+        ? webshellFinalizationReasonLabel(data && data.completionReason, data && data.status)
+        : webshellFinalizationReasonLabel('missing_finalization_contract');
+    var lines = ['仍在验证，暂不生成最终结论', '状态：' + reason];
+    var pending = Array.isArray(data && data.pendingExecutionIds) ? data.pendingExecutionIds.filter(Boolean).map(String) : [];
+    if (pending.length) {
+        lines.push('待完成工具：' + pending.slice(0, 3).join(', ') + (pending.length > 3 ? ' 等' : ''));
+    }
+    var missing = Array.isArray(data && data.missingChecks)
+        ? data.missingChecks.map(webshellFinalizationMissingCheckLabel).filter(Boolean)
+        : [];
+    if (missing.length) {
+        lines.push('待完成检查：' + missing.slice(0, 2).join('；') + (missing.length > 2 ? ' 等' : ''));
+    }
+    if (!hasContract && eventMessage) {
+        lines.push('候选输出已移入过程详情。');
+    }
+    return lines.join('\n');
+}
+
 function escapeSingleQuotedShellArg(value) {
     var s = value == null ? '' : String(value);
     return "'" + s.replace(/'/g, "'\\''") + "'";
@@ -3393,7 +3442,10 @@ function runWebshellAiSend(conn, inputEl, sendBtn, messagesContainer) {
         message: message,
         webshellConnectionId: conn.id,
         conversationId: convId,
-        role: wsRole
+        role: wsRole,
+        finalization: {
+            requireExecutionEvidence: true
+        }
     };
     if (!convId) {
         var wsPid = getWebshellAiProjectSelection(conn);
@@ -3465,6 +3517,8 @@ function runWebshellAiSend(conn, inputEl, sendBtn, messagesContainer) {
                         streamingTarget = '';
                         webshellStreamingTypingId += 1;
                         streamingTypingId = webshellStreamingTypingId;
+                        assistantDiv.dataset.finalized = 'false';
+                        assistantDiv.classList.add('webshell-ai-candidate-output');
                         assistantDiv.textContent = '…';
                         messagesContainer.scrollTop = messagesContainer.scrollHeight;
                     } else if (_et === 'response_delta') {
@@ -3485,6 +3539,23 @@ function runWebshellAiSend(conn, inputEl, sendBtn, messagesContainer) {
                         }
                     } else if (_et === 'response') {
                         var text = (_em != null && _em !== '') ? _em : (typeof _ed === 'string' ? _ed : '');
+                        var finalized = !!(_ed && _ed.finalized === true);
+                        var hasFinalizationContract = !!(_ed && (
+                            Object.prototype.hasOwnProperty.call(_ed, 'finalized') ||
+                            Object.prototype.hasOwnProperty.call(_ed, 'finalizable') ||
+                            Object.prototype.hasOwnProperty.call(_ed, 'completionReason') ||
+                            Object.prototype.hasOwnProperty.call(_ed, 'evidenceVerified') ||
+                            Object.prototype.hasOwnProperty.call(_ed, 'missingChecks')
+                        ));
+                        assistantDiv.dataset.finalized = finalized ? 'true' : 'false';
+                        assistantDiv.classList.toggle('webshell-ai-candidate-output', !finalized);
+                        assistantDiv.classList.toggle('webshell-ai-finalized-output', finalized);
+                        if (!finalized && !hasFinalizationContract && text) {
+                            appendTimelineItem('finalization_check', '候选输出缺少最终化证明', text, Object.assign({}, _ed || {}, { missingFinalizationContract: true }));
+                            text = webshellFinalizationNotice(_ed || {}, text, false);
+                        } else if (!finalized && hasFinalizationContract) {
+                            text = webshellFinalizationNotice(_ed || {}, text, true);
+                        }
                         if (text) {
                             streamingTarget = String(text);
                             webshellStreamingTypingId += 1;
@@ -3493,6 +3564,11 @@ function runWebshellAiSend(conn, inputEl, sendBtn, messagesContainer) {
                         }
 
                     // ─── Terminal events ───
+                    } else if (_et === 'finalization_check') {
+                        var finalizationOk = !!(_ed && _ed.finalized === true);
+                        appendTimelineItem('finalization_check', finalizationOk ? '最终回复检查通过' : '最终回复检查未通过', finalizationOk ? (_em || '最终回复检查通过。') : webshellFinalizationNotice(_ed || {}, _em, true), _ed);
+                    } else if (_et === 'finalization_auto_continue') {
+                        appendTimelineItem('progress', '继续验证', _em, _ed);
                     } else if (_et === 'error' && _em) {
                         streamingTypingId += 1;
                         var errLabel = wsTOr('chat.error', '错误');