feat(webui): persist agent activity events
This commit is contained in:
Xubin Ren
@@ -82,6 +82,96 @@ class TestToolEventProgress:
|
||||
),
|
||||
]
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_write_file_emits_file_edit_progress(self, tmp_path: Path) -> None:
|
||||
loop = _make_loop(tmp_path)
|
||||
target = tmp_path / "foo.txt"
|
||||
target.write_text("old\n", encoding="utf-8")
|
||||
tool_call = ToolCallRequest(
|
||||
id="call-write",
|
||||
name="write_file",
|
||||
arguments={"path": "foo.txt", "content": "new\nextra\n"},
|
||||
)
|
||||
calls = iter([
|
||||
LLMResponse(content="", tool_calls=[tool_call]),
|
||||
LLMResponse(content="Done", tool_calls=[]),
|
||||
])
|
||||
loop.provider.chat_with_retry = AsyncMock(side_effect=lambda *a, **kw: next(calls))
|
||||
loop.tools.get_definitions = MagicMock(return_value=[])
|
||||
loop.tools.prepare_call = MagicMock(
|
||||
return_value=(None, {"path": "foo.txt", "content": "new\nextra\n"}, None),
|
||||
)
|
||||
|
||||
async def execute(name: str, params: dict) -> str:
|
||||
target.write_text(params["content"], encoding="utf-8")
|
||||
return "ok"
|
||||
|
||||
loop.tools.execute = AsyncMock(side_effect=execute)
|
||||
file_events: list[dict] = []
|
||||
|
||||
async def on_progress(
|
||||
content: str,
|
||||
*,
|
||||
tool_hint: bool = False,
|
||||
tool_events: list[dict] | None = None,
|
||||
file_edit_events: list[dict] | None = None,
|
||||
) -> None:
|
||||
if file_edit_events:
|
||||
file_events.extend(file_edit_events)
|
||||
|
||||
final_content, _, _, _, _ = await loop._run_agent_loop([], on_progress=on_progress)
|
||||
|
||||
assert final_content == "Done"
|
||||
assert [event["phase"] for event in file_events] == ["start", "end"]
|
||||
assert file_events[0] == {
|
||||
"version": 1,
|
||||
"call_id": "call-write",
|
||||
"tool": "write_file",
|
||||
"path": "foo.txt",
|
||||
"phase": "start",
|
||||
"added": 2,
|
||||
"deleted": 1,
|
||||
"approximate": True,
|
||||
"status": "editing",
|
||||
}
|
||||
assert file_events[1]["status"] == "done"
|
||||
assert file_events[1]["approximate"] is False
|
||||
assert (file_events[1]["added"], file_events[1]["deleted"]) == (2, 1)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_exec_does_not_emit_file_edit_progress(self, tmp_path: Path) -> None:
|
||||
loop = _make_loop(tmp_path)
|
||||
tool_call = ToolCallRequest(
|
||||
id="call-exec",
|
||||
name="exec",
|
||||
arguments={"command": "printf hi > foo.txt"},
|
||||
)
|
||||
calls = iter([
|
||||
LLMResponse(content="", tool_calls=[tool_call]),
|
||||
LLMResponse(content="Done", tool_calls=[]),
|
||||
])
|
||||
loop.provider.chat_with_retry = AsyncMock(side_effect=lambda *a, **kw: next(calls))
|
||||
loop.tools.get_definitions = MagicMock(return_value=[])
|
||||
loop.tools.prepare_call = MagicMock(
|
||||
return_value=(None, {"command": "printf hi > foo.txt"}, None),
|
||||
)
|
||||
loop.tools.execute = AsyncMock(return_value="ok")
|
||||
file_events: list[dict] = []
|
||||
|
||||
async def on_progress(
|
||||
content: str,
|
||||
*,
|
||||
tool_hint: bool = False,
|
||||
tool_events: list[dict] | None = None,
|
||||
file_edit_events: list[dict] | None = None,
|
||||
) -> None:
|
||||
if file_edit_events:
|
||||
file_events.extend(file_edit_events)
|
||||
|
||||
await loop._run_agent_loop([], on_progress=on_progress)
|
||||
|
||||
assert file_events == []
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_bus_progress_forwards_tool_events_to_outbound_metadata(self, tmp_path: Path) -> None:
|
||||
"""When run() handles a bus message, _tool_events lands in OutboundMessage metadata."""
|
||||
@@ -130,6 +220,42 @@ class TestToolEventProgress:
|
||||
assert finish["phase"] == "end"
|
||||
assert finish["result"] == "file.txt"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_bus_progress_forwards_file_edit_events_for_websocket_only(self, tmp_path: Path) -> None:
|
||||
bus = MessageBus()
|
||||
provider = MagicMock()
|
||||
provider.get_default_model.return_value = "test-model"
|
||||
loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model")
|
||||
edit_events = [{
|
||||
"call_id": "call-write",
|
||||
"tool": "write_file",
|
||||
"path": "foo.txt",
|
||||
"phase": "start",
|
||||
"added": 1,
|
||||
"deleted": 0,
|
||||
"approximate": True,
|
||||
"status": "editing",
|
||||
}]
|
||||
|
||||
websocket_progress = await loop._build_bus_progress_callback(InboundMessage(
|
||||
channel="websocket",
|
||||
sender_id="u1",
|
||||
chat_id="chat1",
|
||||
content="edit",
|
||||
))
|
||||
await websocket_progress("", file_edit_events=edit_events)
|
||||
outbound = await bus.consume_outbound()
|
||||
assert outbound.metadata["_file_edit_events"] == edit_events
|
||||
|
||||
telegram_progress = await loop._build_bus_progress_callback(InboundMessage(
|
||||
channel="telegram",
|
||||
sender_id="u1",
|
||||
chat_id="chat2",
|
||||
content="edit",
|
||||
))
|
||||
await telegram_progress("", file_edit_events=edit_events)
|
||||
assert bus.outbound_size == 0
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_non_streaming_channel_does_not_publish_codex_progress_deltas(
|
||||
self,
|
||||
@@ -353,8 +479,93 @@ class TestToolEventProgress:
|
||||
assert session_updated is not None
|
||||
|
||||
assert (session_updated.metadata or {}).get("_session_updated") is True
|
||||
assert (session_updated.metadata or {}).get("_session_update_scope") == "metadata"
|
||||
assert provider.chat_with_retry.await_count == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_webui_title_generation_uses_turn_model_snapshot(
|
||||
self,
|
||||
tmp_path: Path,
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
bus = MessageBus()
|
||||
provider = MagicMock()
|
||||
provider.get_default_model.return_value = "test-model"
|
||||
provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="Done", tool_calls=[]))
|
||||
loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model")
|
||||
loop.tools.get_definitions = MagicMock(return_value=[])
|
||||
loop.consolidator.maybe_consolidate_by_tokens = AsyncMock(return_value=False) # type: ignore[method-assign]
|
||||
|
||||
captured: dict[str, object] = {}
|
||||
|
||||
async def fake_title_after_turn(**kwargs: object) -> bool:
|
||||
captured.update(kwargs)
|
||||
return False
|
||||
|
||||
monkeypatch.setattr(
|
||||
"nanobot.utils.webui_turn_helpers.maybe_generate_webui_title_after_turn",
|
||||
fake_title_after_turn,
|
||||
)
|
||||
scheduled_title: list[object] = []
|
||||
|
||||
def schedule_background(coro: object) -> None:
|
||||
name = getattr(coro, "__qualname__", "")
|
||||
if "_generate_title_and_notify" in name:
|
||||
scheduled_title.append(coro)
|
||||
elif hasattr(coro, "close"):
|
||||
coro.close()
|
||||
|
||||
loop._schedule_background = schedule_background # type: ignore[method-assign]
|
||||
|
||||
await loop._dispatch(InboundMessage(
|
||||
channel="websocket",
|
||||
sender_id="u1",
|
||||
chat_id="chat1",
|
||||
content="say hello",
|
||||
metadata={"webui": True},
|
||||
))
|
||||
|
||||
assert len(scheduled_title) == 1
|
||||
loop.provider = MagicMock()
|
||||
loop.model = "switched-after-turn"
|
||||
|
||||
await scheduled_title[0] # type: ignore[misc]
|
||||
|
||||
assert captured["provider"] is provider
|
||||
assert captured["model"] == "test-model"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_webui_command_turn_does_not_schedule_title_generation(
|
||||
self,
|
||||
tmp_path: Path,
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
bus = MessageBus()
|
||||
provider = MagicMock()
|
||||
provider.get_default_model.return_value = "test-model"
|
||||
provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="Done", tool_calls=[]))
|
||||
loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model")
|
||||
|
||||
async def fake_title_after_turn(**_kwargs: object) -> bool:
|
||||
raise AssertionError("command-only turns should not generate titles")
|
||||
|
||||
monkeypatch.setattr(
|
||||
"nanobot.utils.webui_turn_helpers.maybe_generate_webui_title_after_turn",
|
||||
fake_title_after_turn,
|
||||
)
|
||||
scheduled: list[object] = []
|
||||
loop._schedule_background = scheduled.append # type: ignore[method-assign]
|
||||
|
||||
await loop._dispatch(InboundMessage(
|
||||
channel="websocket",
|
||||
sender_id="u1",
|
||||
chat_id="chat1",
|
||||
content="/model",
|
||||
metadata={"webui": True},
|
||||
))
|
||||
|
||||
assert scheduled == []
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_non_websocket_dispatch_does_not_publish_turn_end_marker(self, tmp_path: Path) -> None:
|
||||
bus = MessageBus()
|
||||
|
||||
Reference in New Issue
Block a user