fix(identity): 接通身份信号提取与持久化 — 对话中起名跨会话记忆

根因: 记忆提取管道(COMBINED_EXTRACTION_PROMPT)提取5种画像信号
但无身份信号(agent_name/user_name)，不存在从对话到AgentConfig.name
或IdentityFiles的写回路径。

修复内容:
- ProfileSignals 增加 agent_name/user_name 字段
- COMBINED_EXTRACTION_PROMPT 增加身份提取指令
- parse_profile_signals 解析新字段 + 回退推断
- GrowthIntegration 存储身份信号到 VikingStorage
- post_conversation_hook 写回 soul.md + emit Tauri 事件
- streamStore 规则化检测 agent 名字并更新 AgentConfig.name
- cold-start-mapper 新增 detectAgentNameSuggestion

链路: 对话→提取→VikingStorage→hook写回soul.md→事件→前端刷新

desktop/src-tauri/src/intelligence_hooks.rs

@@ -8,6 +8,8 @@
 use tracing::{debug, warn};
 
 use std::sync::Arc;
+use tauri::Emitter;
+use zclaw_growth::VikingStorage;
 
 use crate::intelligence::identity::IdentityManagerState;
 use crate::intelligence::heartbeat::HeartbeatEngineState;
@@ -56,12 +58,15 @@ pub async fn pre_conversation_hook(
 ///
 /// 1. Record interaction for heartbeat engine
 /// 2. Record conversation for reflection engine, trigger reflection if needed
+/// 3. Detect identity signals and write back to identity files
 pub async fn post_conversation_hook(
     agent_id: &str,
     _user_message: &str,
     _heartbeat_state: &HeartbeatEngineState,
     reflection_state: &ReflectionEngineState,
     llm_driver: Option<Arc<dyn LlmDriver>>,
+    identity_state: &IdentityManagerState,
+    app: &tauri::AppHandle,
 ) {
     // Step 1: Record interaction for heartbeat
     crate::intelligence::heartbeat::record_interaction(agent_id);
@@ -200,6 +205,71 @@ pub async fn post_conversation_hook(
             reflection_result.improvements.len()
         );
     }
+
+    // Step 3: Detect identity signals from recent memory extraction and write back
+    if let Ok(storage) = crate::viking_commands::get_storage().await {
+        let identity_prefix = format!("agent://{}/identity/", agent_id);
+
+        // Check for agent_name identity signal
+        let agent_name_uri = format!("{}agent-name", identity_prefix);
+        if let Ok(Some(entry)) = VikingStorage::get(storage.as_ref(), &agent_name_uri).await {
+            // Extract name from content like "助手的名字是小马"
+            let name = entry.content.strip_prefix("助手的名字是")
+                .map(|n| n.trim().to_string())
+                .unwrap_or_else(|| entry.content.clone());
+
+            if !name.is_empty() {
+                // Update IdentityFiles.soul to include the agent name
+                let mut manager = identity_state.lock().await;
+                let current_soul = manager.get_file(agent_id, crate::intelligence::identity::IdentityFile::Soul);
+
+                // Only update if the name isn't already in the soul
+                if !current_soul.contains(&name) {
+                    let updated_soul = if current_soul.is_empty() {
+                        format!("# ZCLAW 人格\n\n你的名字是{}。\n\n你是一个成长性的中文 AI 助手。", name)
+                    } else if current_soul.contains("你的名字是") || current_soul.contains("你的名字：") {
+                        // Replace existing name line
+                        let re = regex::Regex::new(r"你的名字是[^\n]+").unwrap();
+                        re.replace(&current_soul, format!("你的名字是{}", name)).to_string()
+                    } else {
+                        // Prepend name to existing soul
+                        format!("你的名字是{}。\n\n{}", name, current_soul)
+                    };
+
+                    if let Err(e) = manager.update_file(agent_id, "soul", &updated_soul) {
+                        warn!("[intelligence_hooks] Failed to update soul with agent name: {}", e);
+                    } else {
+                        debug!("[intelligence_hooks] Updated agent name to '{}' in soul", name);
+                    }
+                }
+                drop(manager);
+
+                // Emit event for frontend to update AgentConfig.name
+                let _ = app.emit("zclaw:agent-identity-updated", serde_json::json!({
+                    "agentId": agent_id,
+                    "agentName": name,
+                }));
+            }
+        }
+
+        // Check for user_name identity signal
+        let user_name_uri = format!("{}user-name", identity_prefix);
+        if let Ok(Some(entry)) = VikingStorage::get(storage.as_ref(), &user_name_uri).await {
+            let name = entry.content.strip_prefix("用户的名字是")
+                .map(|n| n.trim().to_string())
+                .unwrap_or_else(|| entry.content.clone());
+
+            if !name.is_empty() {
+                let mut manager = identity_state.lock().await;
+                let profile = manager.get_file(agent_id, crate::intelligence::identity::IdentityFile::UserProfile);
+
+                if !profile.contains(&name) {
+                    manager.append_to_user_profile(agent_id, &format!("- 用户名字: {}", name));
+                    debug!("[intelligence_hooks] Appended user name '{}' to profile", name);
+                }
+            }
+        }
+    }
 }
 
 /// Build memory context by searching VikingStorage for relevant memories

desktop/src-tauri/src/kernel_commands/chat.rs

@@ -324,6 +324,7 @@ pub async fn agent_chat_stream(
 
     let hb_state = heartbeat_state.inner().clone();
     let rf_state = reflection_state.inner().clone();
+    let id_state_hook = identity_state.inner().clone();
 
     // Clone the guard map for cleanup in the spawned task
     let guard_map: SessionStreamGuard = stream_guard.inner().clone();
@@ -380,12 +381,14 @@ pub async fn agent_chat_stream(
                         let hb = hb_state.clone();
                         let rf = rf_state.clone();
                         let driver = llm_driver.clone();
+                        let id_state = id_state_hook.clone();
+                        let app_hook = app.clone();
                         if driver.is_none() {
                             tracing::debug!("[agent_chat_stream] Post-hook firing without LLM driver (schedule intercept path)");
                         }
                         tokio::spawn(async move {
                             crate::intelligence_hooks::post_conversation_hook(
-                                &agent_id_hook, &message_hook, &hb, &rf, driver,
+                                &agent_id_hook, &message_hook, &hb, &rf, driver, &id_state, &app_hook,
                             ).await;
                         });
                     }

desktop/src/lib/cold-start-mapper.ts

@@ -146,6 +146,32 @@ export function detectNameSuggestion(message: string): string | undefined {
   return undefined;
 }
 
+/**
+ * Detect if user gives the agent a name (e.g., "叫你小马", "以后叫你小马", "你的名字是小马").
+ * Returns the detected agent name or undefined.
+ */
+export function detectAgentNameSuggestion(message: string): string | undefined {
+  if (!message) return undefined;
+  const patterns = [
+    /叫你[""''「」]?(\S{1,8})[""''「」]?[吧。！]?/,
+    /你的名字[是为][""''「」]?(\S{1,8})[""''「」]?[。！]?/,
+    /以后叫你[""''「」]?(\S{1,8})[""''「」]?[吧。！]?/,
+    /给你起[个]?名[字]?(?:叫)?[""''「」]?(\S{1,8})[""''「」]?/,
+    /name you (\S{1,15})/i,
+    /call you (\S{1,15})/i,
+  ];
+  for (const pattern of patterns) {
+    const match = message.match(pattern);
+    if (match && match[1]) {
+      const name = match[1].replace(/[吧。！，、]/g, '').trim();
+      if (name.length >= 1 && name.length <= 8) {
+        return name;
+      }
+    }
+  }
+  return undefined;
+}
+
 /**
  * Determine the next cold start phase based on current phase and user message.
  */

desktop/src/store/chat/streamStore.ts

@@ -34,6 +34,8 @@ import {
 } from './conversationStore';
 import { useMessageStore } from './messageStore';
 import { useArtifactStore } from './artifactStore';
+import { llmSuggest } from '../../lib/llm-service';
+import { detectNameSuggestion, detectAgentNameSuggestion } from '../../lib/cold-start-mapper';
 
 const log = createLogger('StreamStore');
 
@@ -371,7 +373,30 @@ function createCompleteHandler(
       .map(m => ({ role: m.role, content: m.content }));
     const convId = useConversationStore.getState().currentConversationId;
     getMemoryExtractor().extractFromConversation(filtered, agentId, convId ?? undefined)
-      .then(() => {
+      .then(async () => {
+        // Detect name preference from last user message (e.g. "叫我小马")
+        const lastUserMsg = [...msgs].reverse().find(m => m.role === 'user');
+        const detectedName = lastUserMsg ? detectNameSuggestion(lastUserMsg.content) : undefined;
+        if (detectedName && agentId) {
+          try {
+            const { useAgentStore } = await import('../agentStore');
+            await useAgentStore.getState().updateClone(agentId, { userName: detectedName });
+            log.info(`Updated userName to "${detectedName}" from conversation`);
+          } catch (e) {
+            log.warn('Failed to persist detected userName:', e);
+          }
+        }
+        // Detect agent name change (e.g. "叫你小马", "以后叫你小马")
+        const detectedAgentName = lastUserMsg ? detectAgentNameSuggestion(lastUserMsg.content) : undefined;
+        if (detectedAgentName && agentId) {
+          try {
+            const { useAgentStore } = await import('../agentStore');
+            await useAgentStore.getState().updateClone(agentId, { name: detectedAgentName });
+            log.info(`Updated agent name to "${detectedAgentName}" from conversation`);
+          } catch (e) {
+            log.warn('Failed to persist detected agent name:', e);
+          }
+        }
         if (typeof window !== 'undefined') {
           window.dispatchEvent(new CustomEvent('zclaw:agent-profile-updated', {
             detail: { agentId }
@@ -391,15 +416,17 @@ function createCompleteHandler(
       }
     });
 
-    // Follow-up suggestions
+    // Follow-up suggestions (async LLM call with keyword fallback)
     const latestMsgs = chat.getMessages() || [];
-    const completedMsg = latestMsgs.find(m => m.id === assistantId);
-    if (completedMsg?.content) {
-      const suggestions = generateFollowUpSuggestions(completedMsg.content);
-      if (suggestions.length > 0) {
-        set({ suggestions });
-      }
-    }
+    const conversationMessages = latestMsgs
+      .filter(m => m.role === 'user' || m.role === 'assistant')
+      .filter(m => !m.streaming)
+      .map(m => ({ role: m.role, content: m.content }));
+
+    generateLLMSuggestions(conversationMessages, set).catch(err => {
+      log.warn('Suggestion generation error:', err);
+      set({ suggestionsLoading: false });
+    });
   };
 }
 
@@ -410,6 +437,8 @@ export interface StreamState {
   isLoading: boolean;
   chatMode: ChatModeType;
   suggestions: string[];
+  /** Whether LLM-generated suggestions are being fetched. */
+  suggestionsLoading: boolean;
   /** Run ID of the currently active stream (null when idle). */
   activeRunId: string | null;
 
@@ -425,6 +454,7 @@ export interface StreamState {
 
   // Suggestions
   setSuggestions: (suggestions: string[]) => void;
+  setSuggestionsLoading: (loading: boolean) => void;
 
   // Skill search
   searchSkills: (query: string) => {
@@ -440,7 +470,7 @@ export interface StreamState {
 // Follow-up suggestion generator
 // ---------------------------------------------------------------------------
 
-function generateFollowUpSuggestions(content: string): string[] {
+function generateKeywordFallback(content: string): string[] {
   const suggestions: string[] = [];
   const lower = content.toLowerCase();
 
@@ -473,6 +503,148 @@ function generateFollowUpSuggestions(content: string): string[] {
   return suggestions;
 }
 
+/**
+ * Parse LLM response into an array of suggestion strings.
+ * Handles: raw JSON array, markdown-fenced JSON, trailing/leading text.
+ */
+function parseSuggestionResponse(raw: string): string[] {
+  let cleaned = raw.trim();
+  // Strip markdown code fences
+  cleaned = cleaned.replace(/^```(?:json)?\s*\n?/i, '');
+  cleaned = cleaned.replace(/\n?```\s*$/i, '');
+  cleaned = cleaned.trim();
+
+  // Direct JSON parse
+  try {
+    const parsed = JSON.parse(cleaned);
+    if (Array.isArray(parsed)) {
+      return parsed
+        .filter((item): item is string => typeof item === 'string' && item.trim().length > 0)
+        .slice(0, 3);
+    }
+  } catch { /* fall through */ }
+
+  // Extract JSON array from surrounding text
+  const arrayMatch = cleaned.match(/\[[\s\S]*?\]/);
+  if (arrayMatch) {
+    try {
+      const parsed = JSON.parse(arrayMatch[0]);
+      if (Array.isArray(parsed)) {
+        return parsed
+          .filter((item): item is string => typeof item === 'string' && item.trim().length > 0)
+          .slice(0, 3);
+      }
+    } catch { /* fall through */ }
+  }
+
+  // Last resort: split by newlines, strip list markers
+  const lines = cleaned
+    .split(/\n/)
+    .map(l => l.replace(/^[-*\d.)\]]+\s*/, '').trim())
+    .filter(l => l.length > 0 && l.length < 60);
+  if (lines.length > 0) {
+    return lines.slice(0, 3);
+  }
+
+  return [];
+}
+
+/**
+ * Generate contextual follow-up suggestions via LLM.
+ * Routes through SaaS relay or local kernel based on connection mode.
+ * Falls back to keyword-based approach on any failure.
+ */
+async function generateLLMSuggestions(
+  messages: Array<{ role: string; content: string }>,
+  set: (partial: Partial<StreamState>) => void,
+): Promise<void> {
+  set({ suggestionsLoading: true });
+
+  try {
+    const recentMessages = messages.slice(-6);
+    const context = recentMessages
+      .map(m => `${m.role === 'user' ? '用户' : '助手'}: ${m.content}`)
+      .join('\n\n');
+
+    const connectionMode = typeof localStorage !== 'undefined'
+      ? localStorage.getItem('zclaw-connection-mode')
+      : null;
+
+    let raw: string;
+
+    if (connectionMode === 'saas') {
+      // SaaS relay: use saasClient directly for reliable auth
+      raw = await llmSuggestViaSaaS(context);
+    } else {
+      // Local kernel: use llm-service adapter (GatewayLLMAdapter → agent_chat)
+      raw = await llmSuggest(context);
+    }
+
+    const suggestions = parseSuggestionResponse(raw);
+
+    if (suggestions.length > 0) {
+      set({ suggestions, suggestionsLoading: false });
+    } else {
+      const lastAssistant = messages.filter(m => m.role === 'assistant').pop()?.content || '';
+      set({ suggestions: generateKeywordFallback(lastAssistant), suggestionsLoading: false });
+    }
+  } catch (err) {
+    log.warn('LLM suggestion generation failed, using keyword fallback:', err);
+    const lastAssistant = messages.filter(m => m.role === 'assistant').pop()?.content || '';
+    set({ suggestions: generateKeywordFallback(lastAssistant), suggestionsLoading: false });
+  }
+}
+
+/**
+ * Generate suggestions via SaaS relay, using saasStore auth directly.
+ */
+async function llmSuggestViaSaaS(context: string): Promise<string> {
+  const { useSaaSStore } = await import('../saasStore');
+  const { saasUrl, authToken } = useSaaSStore.getState();
+
+  if (!saasUrl || !authToken) {
+    throw new Error('SaaS not authenticated');
+  }
+
+  const { saasClient } = await import('../../lib/saas-client');
+  saasClient.setBaseUrl(saasUrl);
+  saasClient.setToken(authToken);
+
+  const response = await saasClient.chatCompletion(
+    {
+      model: 'default',
+      messages: [
+        { role: 'system', content: LLM_PROMPTS_SYSTEM },
+        { role: 'user', content: `以下是对话中最近的消息：\n\n${context}\n\n请生成 3 个后续问题。` },
+      ],
+      max_tokens: 500,
+      temperature: 0.7,
+      stream: false,
+    },
+    AbortSignal.timeout(15000),
+  );
+
+  if (!response.ok) {
+    const errText = await response.text().catch(() => 'unknown error');
+    throw new Error(`SaaS relay error ${response.status}: ${errText.substring(0, 100)}`);
+  }
+
+  const data = await response.json();
+  return data?.choices?.[0]?.message?.content || '';
+}
+
+const LLM_PROMPTS_SYSTEM = `你是对话分析助手。根据最近的对话内容，生成 3 个用户可能想继续探讨的问题。
+
+要求：
+- 每个问题必须与对话内容直接相关，具体且有针对性
+- 帮助用户深入理解、实际操作或拓展思路
+- 每个问题不超过 30 个中文字符
+- 不要重复对话中已讨论过的内容
+- 使用与用户相同的语言
+
+只输出 JSON 数组，包含恰好 3 个字符串。不要输出任何其他内容。
+示例：["如何在生产环境中部署？", "这个方案的成本如何？", "有没有更简单的替代方案？"]`;
+
 // ---------------------------------------------------------------------------
 // ChatStore injection (avoids circular imports)
 // ---------------------------------------------------------------------------
@@ -499,6 +671,7 @@ export const useStreamStore = create<StreamState>()(
   isLoading: false,
   chatMode: 'thinking' as ChatModeType,
   suggestions: [],
+  suggestionsLoading: false,
   activeRunId: null as string | null,
 
   // ── Chat Mode ──
@@ -508,6 +681,7 @@ export const useStreamStore = create<StreamState>()(
   getChatModeConfig: () => CHAT_MODES[get().chatMode].config,
 
   setSuggestions: (suggestions: string[]) => set({ suggestions }),
+  setSuggestionsLoading: (loading: boolean) => set({ suggestionsLoading: loading }),
 
   setIsLoading: (loading: boolean) => set({ isLoading: loading }),
 
@@ -535,7 +709,7 @@ export const useStreamStore = create<StreamState>()(
     const currentAgent = convStore.currentAgent;
     const sessionKey = convStore.sessionKey;
 
-    set({ suggestions: [] });
+    set({ suggestions: [], suggestionsLoading: false });
     const effectiveSessionKey = sessionKey || crypto.randomUUID();
     const effectiveAgentId = resolveGatewayAgentId(currentAgent);
     const agentId = currentAgent?.id || 'zclaw-main';
@@ -849,13 +1023,15 @@ export const useStreamStore = create<StreamState>()(
             }
 
             const latestMsgs = _chat?.getMessages() || [];
-            const completedMsg = latestMsgs.find(m => m.id === streamingMsg.id);
-            if (completedMsg?.content) {
-              const suggestions = generateFollowUpSuggestions(completedMsg.content);
-              if (suggestions.length > 0) {
-                get().setSuggestions(suggestions);
-              }
-            }
+            const conversationMessages = latestMsgs
+              .filter(m => m.role === 'user' || m.role === 'assistant')
+              .filter(m => !m.streaming)
+              .map(m => ({ role: m.role, content: m.content }));
+
+            generateLLMSuggestions(conversationMessages, set).catch(err => {
+              log.warn('Suggestion generation error:', err);
+              set({ suggestionsLoading: false });
+            });
           }
         }
       } else if (delta.stream === 'hand') {