steven_li
8a12c30141
新增内部Task系统，包括验证、反馈门控机制，实现自动质量验证 (通过率>=0.75)和用户反馈闭环(satisfied/revise/abandon)。 实现Agent Team v1协调器，支持sequence/parallel/dag执行策略， sub-agent复用主AgentLoop，每个run使用独立memory snapshot。 建立Skill学习pipeline，包含draft/审核/发布/回滚完整生命周期， 通过Task验证通过且用户满意才生成学习候选。 重构目录结构，移除third_party依赖，建立统一engine内核， 所有agent共享运行时基础组件。 更新ContextBuilder清理provider消息字段，增强SkillContext版本管理， 集成TaskExecutionPlanner和TaskSkillResolver实现技能解析机制。
123 lines
4.2 KiB
Python
123 lines
4.2 KiB
Python
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
from beaver.engine.session import SessionManager
|
|
from beaver.memory.runs import RunMemoryStore, RunRecord
|
|
from beaver.services.process_service import SessionProcessProjector
|
|
|
|
|
|
def test_process_projection_maps_task_team_events(tmp_path: Path) -> None:
|
|
session = SessionManager(tmp_path)
|
|
run_store = RunMemoryStore(tmp_path / "memory" / "runs")
|
|
run_store.append_run_record(
|
|
RunRecord(
|
|
run_id="sub-run",
|
|
session_id="sub-session",
|
|
task_id="task-1",
|
|
attempt_index=1,
|
|
task_text="sub task",
|
|
started_at="2026-01-01T00:00:01+00:00",
|
|
ended_at="2026-01-01T00:00:02+00:00",
|
|
success=True,
|
|
finish_reason="stop",
|
|
)
|
|
)
|
|
run_store.append_run_record(
|
|
RunRecord(
|
|
run_id="main-run",
|
|
session_id="web:test",
|
|
task_id="task-1",
|
|
attempt_index=1,
|
|
task_text="main task",
|
|
started_at="2026-01-01T00:00:03+00:00",
|
|
ended_at="2026-01-01T00:00:04+00:00",
|
|
success=True,
|
|
finish_reason="stop",
|
|
)
|
|
)
|
|
session.append_message(
|
|
"web:test",
|
|
role="system",
|
|
event_type="task_execution_planned",
|
|
event_payload={
|
|
"task_id": "task-1",
|
|
"attempt_index": 1,
|
|
"plan_mode": "team",
|
|
"strategy": "sequence",
|
|
"node_ids": ["research"],
|
|
"skill_queries": ["research workflow"],
|
|
"selected_skill_names": ["research-workflow"],
|
|
"skill_resolution_report": [
|
|
{
|
|
"node_id": "research",
|
|
"skill_query": "research workflow",
|
|
"selected_skill_names": ["research-workflow"],
|
|
"generated_skill_draft_id": None,
|
|
"ephemeral_used": False,
|
|
"reason": "matched published skill",
|
|
}
|
|
],
|
|
"reason": "needs research",
|
|
},
|
|
context_visible=False,
|
|
)
|
|
session.append_message(
|
|
"web:test",
|
|
role="system",
|
|
event_type="task_team_run_completed",
|
|
event_payload={
|
|
"task_id": "task-1",
|
|
"attempt_index": 1,
|
|
"team_success": True,
|
|
"team_run_ids": ["sub-run"],
|
|
"node_results": [
|
|
{
|
|
"node_id": "research",
|
|
"success": True,
|
|
"output_text": "evidence",
|
|
"run_id": "sub-run",
|
|
"skill_query": "research workflow",
|
|
"selected_skill_names": ["research-workflow"],
|
|
"ephemeral_skill_names": [],
|
|
"generated_skill_draft_id": None,
|
|
"ephemeral_used": False,
|
|
"finish_reason": "stop",
|
|
}
|
|
],
|
|
},
|
|
context_visible=False,
|
|
)
|
|
session.append_message(
|
|
"web:test",
|
|
role="system",
|
|
event_type="task_synthesis_completed",
|
|
event_payload={"task_id": "task-1", "attempt_index": 1, "main_run_id": "main-run"},
|
|
context_visible=False,
|
|
)
|
|
session.append_message(
|
|
"web:test",
|
|
run_id="main-run",
|
|
role="system",
|
|
event_type="task_validation_snapshotted",
|
|
event_payload={
|
|
"task_id": "task-1",
|
|
"attempt_index": 1,
|
|
"validation_result": {"accepted": True, "score": 0.9},
|
|
"retry_scheduled": False,
|
|
},
|
|
context_visible=False,
|
|
)
|
|
|
|
projection = SessionProcessProjector(session, run_store).project("web:test")
|
|
|
|
run_ids = {run["run_id"] for run in projection["runs"]}
|
|
assert "task:task-1:attempt:1" in run_ids
|
|
assert "sub-run" in run_ids
|
|
assert "main-run" in run_ids
|
|
sub_run = next(run for run in projection["runs"] if run["run_id"] == "sub-run")
|
|
assert sub_run["metadata"]["selected_skill_names"] == ["research-workflow"]
|
|
assert sub_run["metadata"]["skill_query"] == "research workflow"
|
|
assert any(event["actor_name"] == "Validator" for event in projection["events"])
|
|
assert any(run["session_id"] == "web:test" for run in projection["runs"])
|