优化: token分项显示(in/cache/out/reasoning)+ 详情面板 + base前置

token分项(各计费不同,不显 total):df-ai 解析 provider cache/reasoning(openai_compat prompt_cache_hit/miss/reasoning_tokens + anthropic cache_read/creation)+ TokenUsage 加字段(全构造点)+ AiMessage/AiCompleted/DB V39(ai_messages 加 cache_hit/miss/reasoning 列)+ message_repo 映射(持久化)+ 前端 MessageList 显 in·cache·out·reason(in=cache_miss 全价,reasoning 有才显)+ 点击 token 弹详情面板(完整 usage+缓存命中率+model)+ df-miniapp 同步

base前置(提升 prompt cache 命中率):chat.rs aug 拼 base 后(4处)+ knowledge_inject 知识拼 base 后(固定 base 前缀,cache 命中)

附修:replace_conversation 原 13 列 INSERT 丢消息级 token → 改 18 列

src/composables/ai/useAiEvents.ts

@@ -693,11 +693,15 @@ function handleLifecycleEvent(event: AiChatEvent): boolean {
       }
       void loadConversations()
       // token 用量记录(开关开时):lastTokenUsage 供当前回复展示,convTokenTotal 累加对话总量
+      // 分项 token(2026-08-02):cache_hit/cache_miss/reasoning 透传,前端 in=cache_miss 分计费展示
       if (isShowTokenUsage()) {
         state.lastTokenUsage = {
           prompt: event.prompt_tokens,
           completion: event.completion_tokens,
           total: event.total_tokens,
+          cache_hit: event.prompt_cache_hit_tokens,
+          cache_miss: event.prompt_cache_miss_tokens,
+          reasoning: event.reasoning_tokens,
         }
         if (state.convTokenTotal) {
           state.convTokenTotal.prompt += event.prompt_tokens
@@ -707,10 +711,20 @@ function handleLifecycleEvent(event: AiChatEvent): boolean {
           state.convTokenTotal = { prompt: event.prompt_tokens, completion: event.completion_tokens, total: event.total_tokens }
         }
         // 每轮 token 写入对应 assistant 消息(最后一条 AI 消息),供 MessageList 逐条显示。
+        // 同时写消息级 cache/reasoning 字段(详情面板 + 分项显示用)。
         for (let i = state.messages.length - 1; i >= 0; i--) {
           const m = state.messages[i]
           if (m.role === 'assistant' && !m.isError) {
-            m.tokenUsage = { prompt: event.prompt_tokens, completion: event.completion_tokens }
+            m.tokenUsage = {
+              prompt: event.prompt_tokens,
+              completion: event.completion_tokens,
+              cache_hit: event.prompt_cache_hit_tokens,
+              cache_miss: event.prompt_cache_miss_tokens,
+              reasoning: event.reasoning_tokens,
+            }
+            m.prompt_cache_hit_tokens = event.prompt_cache_hit_tokens
+            m.prompt_cache_miss_tokens = event.prompt_cache_miss_tokens
+            m.reasoning_tokens = event.reasoning_tokens
             break
           }
         }