feat(智能体): 不设硬性预算上限,花费改为可见
- 去掉每天次数、每天花费、单次花费、单次 token 四个上限的拦截;设置项登记为弃用,旧值兼容读取、不生效 - 保留单次工具调用次数与时长两个防跑飞限制,缺省调宽(120 次 / 1800 秒,后台调查 20 次) - 新增 GET /agent/usage:今天与最近 7 天按会话类型(对话 / 巡检 / 后台调查 / 整理识别 / 子会话)的次数、token 与费用 - 设置 agent.autoIdentifyOrganize(整理识别不到时叫智能体识别,缺省开)一并加在智能体设置里 - runner 里加整理识别会话的能力白名单与调查会话去重键解析(investigationDecisionId) Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei
This commit is contained in:
1 parent
7b7fadbfb6
commit
414ea7c890
10 files changed
+259
-48
No files matched your search
@@ -77,6 +77,13 @@ export const reviewApi = {
|
||||
),
|
||||
/** Agent 会话(W2-D):建 run 只入队持久任务 runAgent;增量经全局 SSE(agent.*),断线按 runSeq 用 afterSeq 补读 */
|
||||
agentRuns: {
|
||||
usage: ep({
|
||||
method: "get",
|
||||
path: "/agent/usage",
|
||||
scope: "read",
|
||||
summary: "智能体用量:今天与最近 7 天按会话类型的次数、token 与费用",
|
||||
response: agent.AgentSpend,
|
||||
}),
|
||||
list: ep({
|
||||
method: "get",
|
||||
path: "/agent/runs",
|
||||
|
||||
Reference in new issue
Block a user