steven_li
6e9e74d1ee
添加 RuntimeContext 类用于捕获模型运行时的日期时间信息， 包括UTC时间、本地时间和时区信息，并在系统提示中显示这些信息。 同时增加最大上下文消息数和工具迭代次数的配置选项， 将验证服务从引擎加载器中移除，并更新相关的数据结构和接口。 BREAKING CHANGE: 移除了验证服务，相关字段被替换为证据状态和接受状态。 - 添加 RuntimeContext 类和相关渲染方法 - 增加 max_context_messages 和 max_tool_iterations 配置 - 移除 ValidationService 相关代码 - 更新消息记录中的验证状态字段 - 添加原始工具调用检测和回退处理
202 lines
7.1 KiB
Python
202 lines
7.1 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"],
|
|
"ephemeral_guidance_id": None,
|
|
"ephemeral_guidance_name": 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": [],
|
|
"ephemeral_guidance_id": None,
|
|
"ephemeral_guidance_name": 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_evidence_recorded",
|
|
event_payload={
|
|
"task_id": "task-1",
|
|
"attempt_index": 1,
|
|
"evidence_status": "recorded",
|
|
},
|
|
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 sub_run["metadata"]["ephemeral_guidance_id"] is None
|
|
assert any(event["actor_name"] == "Evidence" for event in projection["events"])
|
|
assert any(run["session_id"] == "web:test" for run in projection["runs"])
|
|
|
|
|
|
def test_process_projection_exposes_ephemeral_guidance_artifacts(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",
|
|
)
|
|
)
|
|
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"],
|
|
"ephemeral_guidance_ids": ["eg_123"],
|
|
"skill_resolution_report": [
|
|
{
|
|
"node_id": "research",
|
|
"skill_query": "research workflow",
|
|
"selected_skill_names": [],
|
|
"ephemeral_guidance_id": "eg_123",
|
|
"ephemeral_guidance_name": "research-workflow",
|
|
"ephemeral_used": True,
|
|
"reason": "generated ephemeral guidance",
|
|
}
|
|
],
|
|
},
|
|
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": [],
|
|
"ephemeral_skill_names": ["ephemeral:research-workflow"],
|
|
"ephemeral_guidance_id": "eg_123",
|
|
"ephemeral_guidance_name": "research-workflow",
|
|
"ephemeral_used": True,
|
|
"finish_reason": "stop",
|
|
}
|
|
],
|
|
},
|
|
context_visible=False,
|
|
)
|
|
|
|
projection = SessionProcessProjector(session, run_store).project("web:test")
|
|
|
|
sub_run = next(run for run in projection["runs"] if run["run_id"] == "sub-run")
|
|
assert sub_run["metadata"]["ephemeral_guidance_id"] == "eg_123"
|
|
assert projection["artifacts"][0]["artifact_id"] == "sub-run:ephemeral-guidance:eg_123"
|
|
assert projection["artifacts"][0]["metadata"]["ephemeral_guidance_name"] == "research-workflow"
|