修复策划 Agent 历史思考位置
Project CI / AI game creator shell Rust crates (pull_request) Successful in 2m8s
Project CI / Native shell tests (pull_request) Has been cancelled
Project CI / Frontend tests (pull_request) Has been cancelled
Project CI / Repository checks (pull_request) Has been cancelled
Project CI / AI game creator shell web tests (pull_request) Has been cancelled
Project CI / Backend tests (pull_request) Has been cancelled
Project CI / AI game creator shell Rust tests (pull_request) Has been cancelled
Project CI / AI game creator shell Rust crates (pull_request) Successful in 2m8s
Project CI / Native shell tests (pull_request) Has been cancelled
Project CI / Frontend tests (pull_request) Has been cancelled
Project CI / Repository checks (pull_request) Has been cancelled
Project CI / AI game creator shell web tests (pull_request) Has been cancelled
Project CI / Backend tests (pull_request) Has been cancelled
Project CI / AI game creator shell Rust tests (pull_request) Has been cancelled
按用户回合与响应顺序绑定持久化 reasoning,跨越 tool-only 响应。 合并同一正文对应的多段 reasoning,避免无归属内容堆积在消息列表底部。 补充策划 Runtime 顺序回归测试并更新里程碑文档。
This commit is contained in:
@@ -17,6 +17,7 @@
|
||||
- 已完成共享 reasoning 字段、Provider 解析、策划事件映射以及正文流式收尾的前两轮提交。
|
||||
- 当前第三轮聚焦策划 Agent 前端 reasoning 生命周期:按 `projectPath + clientTurnId` 绑定事件,回合结束后保留本轮 reasoning,下一轮或项目切换时清理。
|
||||
- 现有 `<details>` 展示保持默认收起,并提供明确的展开/收起入口;不新增持久化字段,也不改动 GameAgent、Direct/Codex、supervisor 或已退役链路。
|
||||
- 已核对实际会话产物:Responses 原生 `history` 已持久化 `reasoning` / `reasoning_text`,当前修复补齐 `reasoning_text` 提取,并在策划会话恢复时回填最近一轮 reasoning。
|
||||
|
||||
## 背景与现状
|
||||
|
||||
@@ -195,6 +196,19 @@ npm run check:encoding
|
||||
git diff --check
|
||||
```
|
||||
|
||||
## 第六轮定位:历史 reasoning 位置修复
|
||||
|
||||
持久化 Responses history 中,reasoning 不一定紧邻可见 `message`:一次 Provider 响应可能先产生 reasoning 和多个 `function_call`,下一次响应才产生正文。原实现遇到下一段 reasoning 就提前结束上一段,无法绑定到 `session.messages` 中的正确 assistant 响应,前端遂把无 `messageId` 的条目统一追加到列表底部。
|
||||
|
||||
修复方式是按每个用户回合分别收集:
|
||||
|
||||
- `session.history` 中 reasoning 的响应顺序;
|
||||
- `session.messages` 中 assistant 消息的响应顺序。
|
||||
|
||||
两者按顺序绑定,允许 reasoning 跨越 tool-only Responses;同一正文对应多段 reasoning 时前端合并显示,仍使用默认折叠的单个思考区域。只有没有任何可见 assistant 消息的异常历史才保留为底部 orphan。
|
||||
|
||||
验证:新增 tool-only Responses 顺序回归测试,策划 Runtime 定向测试 11/11 通过;前端聚合逻辑保留历史多段 reasoning 的顺序。
|
||||
|
||||
## 当前状态与下一步
|
||||
|
||||
当前仅完成问题定位和方案设计,未修改业务代码。进入实现前应先评审本里程碑的字段语义、默认关闭策略、Responses 事件覆盖范围和 reasoning 是否进入 debug 记录;评审通过后再为单个里程碑建立对应的 `【实施计划】` 文档。
|
||||
当前已完成 Provider 解析、策划 Runtime 生命周期、历史 reasoning 恢复及响应顺序归属修复;待本轮提交后继续按定向回归结果推进后续验收。字段语义、默认关闭策略、Responses 事件覆盖范围和 reasoning 不进入普通上下文的约束保持不变。
|
||||
|
||||
Reference in New Issue
Block a user