feat(orchestration,loop,flow): 接线子代理编排 — 派发入口 + 分支归父会话 + 节点日志(含脱敏)

修的是「文档说 ✅、生产不可达」:此前 Scheduler.Spawn 只有测试调用方、无 bus 入口、无派发工具;Span.Record 无生产调用方 → 泳道画不出、节点日志恒空。
- 入口:subagent_spawn 工具(internal/runtime/orchestration/spawntool.go,同包便于用真 Scheduler/loop/Tracer/Flow 做集成测试;注册在 cmd/cyrene/subagent_tool.go 照 terminal_tool 范式)。默认 owner-only,不设 AllowInGroup/AllowInStranger;安全仍由 restrictSchemas + applyToolSecurityGate 双层保证,未绕代审
- 父会话归属:AgentSpec.ParentSession(请求语义)→ Scheduler 转运行期 ctx 标记 loop.WithFlowBranch → 分支 span 以父 session 发布;**allow 谓词一行未改**;单图语义靠「分支 Run 不调 StartRound/EndRound」+ FlowPublisher 不新建图;未归属 spawn 一张图都不发(有测试锁)
- 前台最多等 2s(对齐 task.autoBackgroundThreshold)→ 合并结果作工具结果;转后台则广播 bus subagent.result(design/05 §9 回填 hook);新增 Scheduler.Wait(ids) 按批等待(Join 会串并发批次,故不重用)
- 子代理跑在 WithoutCancel(ctx):保留 span 归属、不被工具超时/回合结束顺手杀掉;生命周期由 PerAgentTimeout + CancelAll 约束;内部 WithMutedBroadcast 静音(不进前台 stream)
- 节点日志:loop/spanlog.go 新增 llm.done / tool.done / subagent.done;工具参数**只记键名不记值**;仅步骤真正结束才追加(跳过/被拒路径不发,不伪造)
- 脱敏(红线):新增 trace/redact.go(形状规则 sk-/Bearer/JWT/key:value + 键名规则 api_key/token/authorization/password…,递归嵌套、不改调用方事件),graph.go 发布前必经;**顺带修掉一个既有泄漏**:result_summary prop 原先未脱敏(工具结果里的密钥会进图),由图级变异测试抓出
- 测试:新增 22 个(工具级 / 图级 / 日志级),含 4 次变异验证(去掉 WithFlowBranch、去掉 record*、还原未脱敏、去掉静音 各自 FAIL);-race 过 orchestration+trace+loop
- 已知限制:真实模型端到端未验(无凭据/不起服务);工具白名单是 design gap 未做;subagent.result 暂无消费者(design/15 未实现);后台子代理跨轮次边界迟到 span 会丢泳道根;PerAgentTimeout=10min 待确认
This commit is contained in:
AskaEth committed 2026-10-03 19:39:38 +08:00
1 parent 3f79159fbd
commit de1fa83b79
25 files changed
+2173 -97

No files matched your search

+5
View File
@@ -21,6 +21,10 @@ type stepOutcome struct {
// call (Anthropic max_tokens / end_turn / tool_use), recorded on the llm_call
// span so a truncation is visible even when the step itself ended normally.
modelStopReason string
// model is the routed model that served the call, known on the streaming path
// (which builds the request itself) and empty on the agent path. It is
// recorded on the llm_call span's log event.
model string
}
// step runs a single model call. When an OnStream callback is configured it
@@ -53,6 +57,7 @@ func (l *Loop) step(ctx context.Context, sessionID string, messages []model.Mess
l.spanProp(llmSpan, "model_stop_reason", out.modelStopReason)
}
l.spanProp(llmSpan, "tool_calls", len(out.toolCalls))
l.recordLLMDone(llmSpan, out)
l.finishSpan(llmSpan, trace.SpanStatusOK)
return out, nil
}