feat(session,runtime): 多角色并存—按会话选角(迁移0011 + 按回合解析 + agent池 + 提取器修正)
按 DevDocs/design/22 批次 1 后端(§2/§3/§4.1-4.5/§4.7/§5 验收 1-6)。
- 迁移 0011:chat_sessions.persona_id + chat_messages.persona_id(均 DEFAULT '',无回填 → 升级零风险);同步包内幂等 DDL;**真实库升级验证**(拷贝 data/cyrene.db 到临时目录跑 MigrateUp:既有 1 会话/109 消息 persona 仍为 '',原库未被触碰)
- history:SessionMeta/Message 加 PersonaID + SetSessionPersona;ListSessions/List/scan/Append 带上
- runtime:SessionEnv.PersonaID + loop.personaFor(ctx) 替换固定 l.personaID(memory/request/turn)+ **agent 池**(Options.Agents,按角色取 instructions,未命中回落)+ **提取器不再把 persona 烤死在构造期**(多角色下记忆不再永远记在 cyrene 名下)+ **thinking 旋钮改为按会话角色解析**(否则角色 Y 会用角色 X 的预算/展示)
- gateway:会话 DTO/POST/PATCH 支持 personaId;ws/rest/voice 的 OwnerEnv 硬编改为**按会话解析角色**(actor 元数据语义不变);admin memories 搜索去掉硬编 cyrene
- Docs/api-client v0.42;**两处有意的行为收紧**已写明:POST /sessions body 非法 JSON → 400(原先完全忽略 body;空/null/{} 仍 201);POST /admin/memories/search 省略 personaId 且无默认角色 → 400(原先默认查 cyrene)
- 测试:design/22 §5 验收 1-6(记忆隔离/提示词首条 system/情绪按角色/提取 persona 归属/迁移兼容)+ 进程内 e2e(断言 adapter 收到的 model.Request.Messages[0] 即该角色的 systemPrompt)
- **已知未做(留批次 2 / 待确认)**:① IM 与渠道级未做 → **§7-3「owner 私聊镜像随主会话角色」尚未生效**;② 请求级覆盖未实现(本批只做会话级);③ **§7-5 的「上下文发送角色标记」只完成存储+DTO 半边**——消息 persona 已落库且 DTO 已带,但模型上下文不从 chat_messages 重建,「第 N 条是谁说的」尚未进上下文(需确认是否属批次 2);④「切角色重建摘要」当前是空操作(压缩未接线);⑤ thinking 旋钮仅在流式路径生效(非流式 agent.RunStep 不带,A 批次既有性质)
- 验收:go build/vet/test 全绿 + linux/amd64 与 darwin/arm64 交叉编译(既有 flake 本轮未触发;同批 session_orchestrator.go 一度 501 行 → 抽出 session_tail.go)
This commit is contained in:
1 parent
66a96d2f93
commit
0624d9ee36
46 files changed
+1908
-259
No files matched your search
+11
-3
@@ -363,6 +363,9 @@ func (a *app) wireRuntime() error {
|
||||
|
||||
personaID := a.defaultPersonaID()
|
||||
store := a.memStore
|
||||
// One agent per role, all sharing the dispatcher/guards/adapter above, so a session
|
||||
// can answer as any role (design/22 §4.2 方案 A); the loop picks per turn.
|
||||
agents, defaultAgent := a.personaAgentPool(runtimeStack, a.dispatcher, guards, ag)
|
||||
|
||||
// Spans fan out to the JSONL stderr recorder and — once wireFrontend has built
|
||||
// the gateway — to its observability buffer (cmd/cyrene/observability.go).
|
||||
@@ -410,11 +413,15 @@ func (a *app) wireRuntime() error {
|
||||
// emotion machine and affection move, and the returned mood label is written
|
||||
// onto Result.Mood and the assistant message (design/16 §3.3).
|
||||
a.emotion = a.buildEmotionObserver()
|
||||
// Reasoning knobs from the default persona (budget / effort / thinking broadcast).
|
||||
// Reasoning knobs from the default persona (budget / effort / thinking broadcast),
|
||||
// which are also the per-turn defaults: the loop re-resolves them for each turn's
|
||||
// role through PersonaKnobs, so a session bound to another role uses that role's
|
||||
// budget instead.
|
||||
thinking, reasoningEffort, thinkingShow := a.defaultThinkingOptions()
|
||||
|
||||
a.loop = loop.New(loop.Options{
|
||||
Agent: ag,
|
||||
Agent: defaultAgent,
|
||||
Agents: agents,
|
||||
Tools: a.dispatcher,
|
||||
Capacity: capDecider,
|
||||
OnCapacity: a.onCapacity,
|
||||
@@ -422,12 +429,13 @@ func (a *app) wireRuntime() error {
|
||||
OnTurnEnd: a.onTurnEnd,
|
||||
Memory: store,
|
||||
Retriever: a.retriever,
|
||||
Extractor: a.buildMemoryExtractor(personaID),
|
||||
Extractor: a.buildMemoryExtractor(),
|
||||
Checkpoint: checkpoint,
|
||||
Tracer: tracer,
|
||||
Flow: flowPub,
|
||||
Guards: guards,
|
||||
PersonaID: personaID,
|
||||
PersonaKnobs: a.personaKnobs,
|
||||
Timezone: a.cfg.Timezone,
|
||||
MaxRounds: defaultMaxRounds,
|
||||
WorkingMemory: memory.NewWorkingMemory(0),
|
||||
|
||||
Reference in new issue
Block a user