316 lines
12 KiB
Python
316 lines
12 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,
|
|
)
|
|
session.append_message(
|
|
"web:test",
|
|
run_id="main-run",
|
|
role="system",
|
|
event_type="task_acceptance_recorded",
|
|
event_payload={
|
|
"task_id": "task-1",
|
|
"attempt_index": 1,
|
|
"acceptance_type": "accept",
|
|
},
|
|
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"])
|
|
|
|
planned_event = next(event for event in projection["events"] if event["kind"] == "task_planned")
|
|
assert planned_event["metadata"]["timeline_type"] == "plan"
|
|
assert planned_event["metadata"]["plan_mode"] == "team"
|
|
assert planned_event["metadata"]["strategy"] == "sequence"
|
|
assert planned_event["metadata"]["selected_skill_names"] == ["research-workflow"]
|
|
|
|
skill_event = next(event for event in projection["events"] if event["kind"] == "skill_selected")
|
|
assert skill_event["metadata"]["timeline_type"] == "skill"
|
|
assert skill_event["metadata"]["skill_names"] == ["research-workflow"]
|
|
|
|
team_event = next(event for event in projection["events"] if event["kind"] == "agent_team_created")
|
|
assert team_event["metadata"]["timeline_type"] == "agent_team"
|
|
assert team_event["metadata"]["team_run_ids"] == ["sub-run"]
|
|
|
|
node_event = next(event for event in projection["events"] if event["kind"] == "agent_finished")
|
|
assert node_event["metadata"]["timeline_type"] == "agent_progress"
|
|
assert "node_result" not in node_event["metadata"]
|
|
|
|
evidence_event = next(event for event in projection["events"] if event["kind"] == "task_result_ready")
|
|
assert evidence_event["metadata"]["timeline_type"] == "result"
|
|
assert evidence_event["status"] == "done"
|
|
|
|
acceptance_event = next(event for event in projection["events"] if event["kind"] == "task_acceptance_recorded")
|
|
assert acceptance_event["metadata"]["timeline_type"] == "acceptance"
|
|
|
|
|
|
def test_process_projection_maps_failed_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="failed-sub-run",
|
|
session_id="failed-sub-session",
|
|
task_id="task-1",
|
|
attempt_index=1,
|
|
task_text="failed sub task",
|
|
started_at="2026-01-01T00:00:01+00:00",
|
|
ended_at="2026-01-01T00:00:02+00:00",
|
|
success=False,
|
|
finish_reason="error",
|
|
)
|
|
)
|
|
session.append_message(
|
|
"web:test",
|
|
role="system",
|
|
event_type="task_team_run_failed",
|
|
event_payload={
|
|
"task_id": "task-1",
|
|
"attempt_index": 1,
|
|
"team_success": False,
|
|
"team_run_ids": ["failed-sub-run"],
|
|
"error": "research node failed",
|
|
"node_results": [
|
|
{
|
|
"node_id": "research",
|
|
"success": False,
|
|
"error": "source unavailable",
|
|
"run_id": "failed-sub-run",
|
|
"finish_reason": "error",
|
|
}
|
|
],
|
|
},
|
|
context_visible=False,
|
|
)
|
|
|
|
projection = SessionProcessProjector(session, run_store).project("web:test")
|
|
|
|
team_event = next(event for event in projection["events"] if event["kind"] == "agent_team_created")
|
|
assert team_event["status"] == "error"
|
|
assert team_event["metadata"]["timeline_type"] == "agent_team"
|
|
assert team_event["metadata"]["team_run_ids"] == ["failed-sub-run"]
|
|
|
|
node_event = next(event for event in projection["events"] if event["kind"] == "agent_finished")
|
|
assert node_event["status"] == "error"
|
|
assert node_event["metadata"]["timeline_type"] == "agent_progress"
|
|
|
|
|
|
def test_process_projection_uses_normalized_plan_metadata_defaults(tmp_path: Path) -> None:
|
|
session = SessionManager(tmp_path)
|
|
run_store = RunMemoryStore(tmp_path / "memory" / "runs")
|
|
session.append_message(
|
|
"web:test",
|
|
role="system",
|
|
event_type="task_execution_planned",
|
|
event_payload={
|
|
"task_id": "task-1",
|
|
"attempt_index": 1,
|
|
"plan_mode": None,
|
|
"strategy": None,
|
|
},
|
|
context_visible=False,
|
|
)
|
|
|
|
projection = SessionProcessProjector(session, run_store).project("web:test")
|
|
|
|
root_run = next(run for run in projection["runs"] if run["run_id"] == "task:task-1:attempt:1")
|
|
assert root_run["metadata"]["plan_mode"] == "single"
|
|
assert root_run["metadata"]["strategy"] == "single"
|
|
planned_event = next(event for event in projection["events"] if event["kind"] == "task_planned")
|
|
assert planned_event["metadata"]["plan_mode"] == "single"
|
|
assert planned_event["metadata"]["strategy"] == "single"
|
|
|
|
|
|
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"
|