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
2026-08-03 01:22:30 +08:00
parent 864c696b70
commit a031521776
25 changed files with 563 additions and 45 deletions
@@ -588,6 +588,10 @@ impl LlmProvider for AnthropicCompatProvider {
                    prompt_tokens: resp.usage.input_tokens,
                    completion_tokens: resp.usage.output_tokens,
                    total_tokens: resp.usage.input_tokens + resp.usage.output_tokens,
+                    // anthropic cache 字段:creation(写入)= miss 全价语义,read(命中)= hit 低价
+                    prompt_cache_hit_tokens: resp.usage.cache_read_input_tokens,
+                    prompt_cache_miss_tokens: resp.usage.cache_creation_input_tokens,
+                    reasoning_tokens: 0,
                };
                AttemptOutcome::Ok(CompletionResponse {
                    text,