lxy/DevFlow
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

修复: token 汇总正确性(会话级双计/is_estimated跨端/流式usage传递) + is_estimated SELECT 缺失修复

Browse Source
This commit is contained in:
lxy
2026-08-09 23:59:55 +08:00
parent 11f4978ec1
commit 6bafdcd5a5
16 changed files with 189 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/df-ai-core/src/provider.rs
+9 -6
View File
@@ -42,25 +42,25 @@ impl ContentPart {
impl ChatMessage {
pub fn system(content: impl Into<String>) -> Self {
Self { id: Some(new_message_id()), role: MessageRole::System, content: content.into(), parts: None, tool_call_id: None, tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, timestamp: Some(now_millis_i64()) }
Self { id: Some(new_message_id()), role: MessageRole::System, content: content.into(), parts: None, tool_call_id: None, tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, is_estimated: None, timestamp: Some(now_millis_i64()) }
}
pub fn user(content: impl Into<String>) -> Self {
Self { id: Some(new_message_id()), role: MessageRole::User, content: content.into(), parts: None, tool_call_id: None, tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, timestamp: Some(now_millis_i64()) }
Self { id: Some(new_message_id()), role: MessageRole::User, content: content.into(), parts: None, tool_call_id: None, tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, is_estimated: None, timestamp: Some(now_millis_i64()) }
}
pub fn assistant(content: impl Into<String>) -> Self {
Self { id: Some(new_message_id()), role: MessageRole::Assistant, content: content.into(), parts: None, tool_call_id: None, tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, timestamp: Some(now_millis_i64()) }
Self { id: Some(new_message_id()), role: MessageRole::Assistant, content: content.into(), parts: None, tool_call_id: None, tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, is_estimated: None, timestamp: Some(now_millis_i64()) }
}
pub fn assistant_with_tools(content: impl Into<String>, tool_calls: Vec<ToolCall>) -> Self {
Self { id: Some(new_message_id()), role: MessageRole::Assistant, content: content.into(), parts: None, tool_call_id: None, tool_calls: Some(tool_calls), model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, timestamp: Some(now_millis_i64()) }
Self { id: Some(new_message_id()), role: MessageRole::Assistant, content: content.into(), parts: None, tool_call_id: None, tool_calls: Some(tool_calls), model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, is_estimated: None, timestamp: Some(now_millis_i64()) }
}
pub fn tool_result(call_id: impl Into<String>, content: impl Into<String>) -> Self {
Self { id: Some(new_message_id()), role: MessageRole::Tool, content: content.into(), parts: None, tool_call_id: Some(call_id.into()), tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, timestamp: Some(now_millis_i64()) }
Self { id: Some(new_message_id()), role: MessageRole::Tool, content: content.into(), parts: None, tool_call_id: Some(call_id.into()), tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, is_estimated: None, timestamp: Some(now_millis_i64()) }
}
/// 多模态 user 消息：content 文本 + parts（含 Image 片）。
/// content 作为人类可读文本（也作非 vision 端点降级载荷）；parts 透传给 vision 端点。
pub fn user_parts(content: impl Into<String>, parts: Vec<ContentPart>) -> Self {
Self { id: Some(new_message_id()), role: MessageRole::User, content: content.into(), parts: Some(parts), tool_call_id: None, tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, timestamp: Some(now_millis_i64()) }
Self { id: Some(new_message_id()), role: MessageRole::User, content: content.into(), parts: Some(parts), tool_call_id: None, tool_calls: None, model: None, status: None, reasoning_content: None, prompt_tokens: None, completion_tokens: None, prompt_cache_hit_tokens: None, prompt_cache_miss_tokens: None, reasoning_tokens: None, is_estimated: None, timestamp: Some(now_millis_i64()) }
}
/// 是否含图片片（供 provider 判定走多模态分支）。
@@ -320,6 +320,7 @@ mod tests {
prompt_cache_hit_tokens: None,
prompt_cache_miss_tokens: None,
reasoning_tokens: None,
is_estimated: None,
timestamp: None,
};
assert_eq!(m.content, "字面量构造");
@@ -377,6 +378,7 @@ mod tests {
prompt_cache_hit_tokens: None,
prompt_cache_miss_tokens: None,
reasoning_tokens: None,
is_estimated: None,
timestamp: None,
};
let json = serde_json::to_string(&m).unwrap();
@@ -437,6 +439,7 @@ mod tests {
prompt_cache_hit_tokens: None,
prompt_cache_miss_tokens: None,
reasoning_tokens: None,
is_estimated: None,
timestamp: None,
};
let json = serde_json::to_string(&m).unwrap();
crates/df-ai-core/src/types.rs
+4
View File
@@ -138,6 +138,10 @@ pub struct ChatMessage {
/// 前端仅 > 0 时显示(reason 后缀);老 JSON 反序列化为 None。
#[serde(default, skip_serializing_if = "Option::is_none")]
pub reasoning_tokens: Option<u32>,
/// 本轮 prompt 是否估算值(round_usage.prompt_tokens==0 → estimated_prompt 兜底打标)。
/// 供 reload 逐条回显「估算」标注,对齐 live 态 AiCompleted.is_estimated;老消息 None(向前兼容)。
#[serde(default, skip_serializing_if = "Option::is_none")]
pub is_estimated: Option<bool>,
}
/// 当前 Unix 毫秒(ChatMessage 打戳用;df-ai-core 不依赖 df-types,内联避免新增依赖)。