"""Worker-level regression tests for the terminal run.delivery event (#4272 slice 1).""" import asyncio from types import SimpleNamespace from unittest.mock import AsyncMock from uuid import uuid4 import pytest from langchain_core.messages import AIMessage, ToolMessage from langgraph.types import Command from deerflow.runtime.events.store.memory import MemoryRunEventStore from deerflow.runtime.runs.manager import RunManager from deerflow.runtime.runs.schemas import RunStatus from deerflow.runtime.runs.store.memory import MemoryRunStore from deerflow.runtime.runs.worker import RunContext, run_agent def _make_bridge(): return SimpleNamespace(publish=AsyncMock(), publish_end=AsyncMock(), cleanup=AsyncMock()) async def _delivery_events(store: MemoryRunEventStore, thread_id: str, run_id: str) -> list[dict]: events = await store.list_events(thread_id, run_id) return [e for e in events if e["event_type"] == "run.delivery"] @pytest.mark.anyio async def test_delivery_event_records_present_files_paths_on_success(): run_manager = RunManager() record = await run_manager.create("thread-1") store = MemoryRunEventStore() class DummyAgent: async def astream(self, graph_input, config=None, stream_mode=None, subgraphs=False): journal = config["context"]["__run_journal"] ai = AIMessage(content="", tool_calls=[{"id": "call_1", "name": "present_files", "args": {}}]) journal._remember_current_run_tool_calls(ai, caller="lead_agent") journal.on_tool_end( Command( update={ "artifacts": ["/mnt/user-data/outputs/report.md"], "messages": [ToolMessage("Successfully presented files", tool_call_id="call_1")], } ), run_id=uuid4(), ) yield {"messages": []} await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=None, event_store=store), agent_factory=lambda *, config: DummyAgent(), graph_input={}, config={}, ) await asyncio.sleep(0) delivery = await _delivery_events(store, "thread-1", record.run_id) assert len(delivery) == 1 assert delivery[0]["content"]["presented"] == 1 assert delivery[0]["content"]["paths"] == ["/mnt/user-data/outputs/report.md"] assert delivery[0]["content"]["by_tool"] == {"present_files": ["/mnt/user-data/outputs/report.md"]} fetched = await run_manager.get(record.run_id) assert fetched.status == RunStatus.success @pytest.mark.anyio async def test_delivery_event_presented_zero_without_artifact_production(): run_manager = RunManager() record = await run_manager.create("thread-1") store = MemoryRunEventStore() class DummyAgent: async def astream(self, graph_input, config=None, stream_mode=None, subgraphs=False): yield {"messages": []} await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=None, event_store=store), agent_factory=lambda *, config: DummyAgent(), graph_input={}, config={}, ) await asyncio.sleep(0) delivery = await _delivery_events(store, "thread-1", record.run_id) assert len(delivery) == 1 assert delivery[0]["content"] == {"presented": 0, "paths": [], "by_tool": {}} fetched = await run_manager.get(record.run_id) assert fetched.status == RunStatus.success @pytest.mark.anyio async def test_delivery_event_is_singleton_across_goal_continuations(monkeypatch): run_manager = RunManager() record = await run_manager.create("thread-1") store = MemoryRunEventStore() stream_calls = 0 continuation_calls = 0 class ContinuingAgent: async def astream(self, graph_input, config=None, stream_mode=None, subgraphs=False): nonlocal stream_calls stream_calls += 1 journal = config["context"]["__run_journal"] tool_call_id = f"call_{stream_calls}" journal._remember_current_run_tool_calls( AIMessage(content="", tool_calls=[{"id": tool_call_id, "name": "present_files", "args": {}}]), caller="lead_agent", ) artifacts = ["/mnt/user-data/outputs/report.md"] if stream_calls == 2: artifacts.append("/mnt/user-data/outputs/appendix.md") journal.on_tool_end( Command( update={ "artifacts": artifacts, "messages": [ToolMessage("Successfully presented files", tool_call_id=tool_call_id)], } ), run_id=uuid4(), ) yield {"messages": []} async def prepare_continuation(**kwargs): nonlocal continuation_calls continuation_calls += 1 if continuation_calls == 1: return {"messages": []} return None monkeypatch.setattr("deerflow.runtime.runs.worker._prepare_goal_continuation_input", prepare_continuation) await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=None, event_store=store), agent_factory=lambda *, config: ContinuingAgent(), graph_input={}, config={}, ) delivery = await _delivery_events(store, "thread-1", record.run_id) assert stream_calls == 2 assert len(delivery) == 1 assert delivery[0]["content"] == { "presented": 2, "paths": [ "/mnt/user-data/outputs/report.md", "/mnt/user-data/outputs/appendix.md", ], "by_tool": { "present_files": [ "/mnt/user-data/outputs/report.md", "/mnt/user-data/outputs/appendix.md", ] }, } @pytest.mark.anyio async def test_delivery_event_emitted_exactly_once_on_error_path(): run_manager = RunManager() record = await run_manager.create("thread-1") store = MemoryRunEventStore() class FailingAgent: async def astream(self, graph_input, config=None, stream_mode=None, subgraphs=False): raise RuntimeError("boom") yield # pragma: no cover - make this an async generator await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=None, event_store=store), agent_factory=lambda *, config: FailingAgent(), graph_input={}, config={}, ) await asyncio.sleep(0) delivery = await _delivery_events(store, "thread-1", record.run_id) assert len(delivery) == 1 assert delivery[0]["content"]["presented"] == 0 fetched = await run_manager.get(record.run_id) assert fetched.status == RunStatus.error @pytest.mark.anyio async def test_delivery_is_durable_before_terminal_run_status(): events = MemoryRunEventStore() class OrderingRunStore(MemoryRunStore): async def update_status(self, run_id, status, *, error=None, stop_reason=None): if status not in {"pending", "running"}: receipt = await events.list_events("thread-1", run_id, event_types=["run.delivery"]) assert len(receipt) == 1 return await super().update_status(run_id, status, error=error, stop_reason=stop_reason) run_store = OrderingRunStore() run_manager = RunManager(store=run_store) record = await run_manager.create("thread-1") class DummyAgent: async def astream(self, graph_input, config=None, stream_mode=None, subgraphs=False): yield {"messages": []} await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=None, event_store=events), agent_factory=lambda *, config: DummyAgent(), graph_input={}, config={}, ) assert (await run_store.get(record.run_id))["status"] == "success" @pytest.mark.anyio async def test_delivery_write_retries_before_persisting_success(): class FlakyReceiptStore(MemoryRunEventStore): def __init__(self): super().__init__() self.attempts = 0 async def put_if_absent(self, **kwargs): self.attempts += 1 if self.attempts == 1: raise RuntimeError("transient event store outage") return await super().put_if_absent(**kwargs) event_store = FlakyReceiptStore() run_store = MemoryRunStore() run_manager = RunManager(store=run_store) record = await run_manager.create("thread-1") class DummyAgent: async def astream(self, graph_input, config=None, stream_mode=None, subgraphs=False): yield {"messages": []} await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=None, event_store=event_store), agent_factory=lambda *, config: DummyAgent(), graph_input={}, config={}, ) assert event_store.attempts == 2 assert len(await _delivery_events(event_store, "thread-1", record.run_id)) == 1 assert (await run_store.get(record.run_id))["status"] == "success" @pytest.mark.anyio async def test_delivery_write_failure_preserves_real_durable_terminal_status(): class FailingReceiptStore(MemoryRunEventStore): def __init__(self): super().__init__() self.attempts = 0 async def put_if_absent(self, **kwargs): self.attempts += 1 raise RuntimeError("event store unavailable") run_store = MemoryRunStore() run_manager = RunManager(store=run_store) record = await run_manager.create("thread-1") event_store = FailingReceiptStore() class DummyAgent: async def astream(self, graph_input, config=None, stream_mode=None, subgraphs=False): yield {"messages": []} await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=None, event_store=event_store), agent_factory=lambda *, config: DummyAgent(), graph_input={}, config={}, ) # A receipt outage must not let lease recovery rewrite a genuine success # as an error. After bounded retries, preserve the worker's real outcome. assert event_store.attempts > 1 assert record.status == RunStatus.success assert (await run_store.get(record.run_id))["status"] == "success" @pytest.mark.anyio async def test_delivery_event_emitted_when_checkpoint_preflight_fails(monkeypatch): run_manager = RunManager() run_manager.update_run_completion = AsyncMock(wraps=run_manager.update_run_completion) record = await run_manager.create("thread-1") store = MemoryRunEventStore() compatibility_check = AsyncMock(side_effect=RuntimeError("incompatible checkpoint")) monkeypatch.setattr("deerflow.runtime.runs.worker.aensure_checkpoint_mode_compatible", compatibility_check) def unexpected_agent_factory(**kwargs): raise AssertionError("agent must not be built after preflight failure") await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=object(), event_store=store), agent_factory=unexpected_agent_factory, graph_input={}, config={}, ) delivery = await _delivery_events(store, "thread-1", record.run_id) assert len(delivery) == 1 assert delivery[0]["content"] == {"presented": 0, "paths": [], "by_tool": {}} fetched = await run_manager.get(record.run_id) assert fetched.status == RunStatus.error run_manager.update_run_completion.assert_not_awaited() @pytest.mark.anyio async def test_delivery_event_emitted_when_cancelled_waiting_for_prior_finalization(monkeypatch): run_manager = RunManager() run_manager.update_run_completion = AsyncMock(wraps=run_manager.update_run_completion) record = await run_manager.create("thread-1") store = MemoryRunEventStore() monkeypatch.setattr( run_manager, "wait_for_prior_finalizing", AsyncMock(side_effect=asyncio.CancelledError()), ) def unexpected_agent_factory(**kwargs): raise AssertionError("agent must not be built after preflight cancellation") await run_agent( _make_bridge(), run_manager, record, ctx=RunContext(checkpointer=None, event_store=store), agent_factory=unexpected_agent_factory, graph_input={}, config={}, ) delivery = await _delivery_events(store, "thread-1", record.run_id) assert len(delivery) == 1 assert delivery[0]["content"] == {"presented": 0, "paths": [], "by_tool": {}} fetched = await run_manager.get(record.run_id) assert fetched.status == RunStatus.interrupted run_manager.update_run_completion.assert_not_awaited()