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-tauri/src/commands/ai/agentic/helpers.rs

@@ -61,6 +61,7 @@ pub async fn try_continue_agent_loop(
             };
             let ev = AiChatEvent::AiCompleted {
                 total_tokens: 0, prompt_tokens: 0, completion_tokens: 0,
+                prompt_cache_hit_tokens: 0, prompt_cache_miss_tokens: 0, reasoning_tokens: 0,
                 incomplete: None,
                 conversation_id: Some(emit_conv_id),
                 pinned_goals: snap.pinned_goals_snapshot.clone(),
@@ -111,6 +112,7 @@ pub async fn try_continue_agent_loop(
     if !still_generating {
         let ev = AiChatEvent::AiCompleted {
             total_tokens: 0, prompt_tokens: 0, completion_tokens: 0,
+            prompt_cache_hit_tokens: 0, prompt_cache_miss_tokens: 0, reasoning_tokens: 0,
             incomplete: None,
             conversation_id: Some(conv_id_owned.clone()),
             pinned_goals: snap.pinned_goals_snapshot.clone(),