stroblmeandClaude Opus 5
7b67eb5a8e
A connector that misses one poll turned the health badge amber and the node on the canvas red until it recovered. `LoadedNode.health_since` marks when the status last actually changed — a rotating error detail under an unchanged status does not move it, or a connector retrying with a different errno each poll would never debounce — and `unhealthy_nodes` applies a 60 s floor to it. The floor is on the surfacing, not on the transition: the stored health is the truth the moment a node reports it, so a flow reading node health is never told a stale story. Only going down is held back; recovery clears at once. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CL9zvnnvcp1mvA8o7impxk
104 lines
3.8 KiB
Python
104 lines
3.8 KiB
Python
"""A node that loaded but is not working shows up as an issue on its flow.
|
|
|
|
Health used to go nowhere: the connector reported it, the controller stored it,
|
|
and no screen ever asked. These cover the derivation that closes that gap.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
from typing import Any
|
|
|
|
from fluksio.flow.controller import HEALTH_FLOOR, FlowController, LoadedNode
|
|
from fluksio.flow.store import FlowStore
|
|
|
|
|
|
def a_controller(tmp_path: Path) -> FlowController:
|
|
controller = FlowController(FlowStore(tmp_path / "flows"))
|
|
controller.loaded["house.owm"] = LoadedNode(
|
|
id="house.owm",
|
|
flow="house",
|
|
health="down",
|
|
health_detail="ConnectionError: name resolution failed",
|
|
)
|
|
return controller
|
|
|
|
|
|
def test_a_down_node_is_an_issue_on_its_flow(tmp_path: Path) -> None:
|
|
controller = a_controller(tmp_path)
|
|
|
|
issues = controller.flow_issues("house")
|
|
|
|
assert [issue.code for issue in issues] == ["node_unhealthy"]
|
|
assert issues[0].node == "house.owm"
|
|
assert "name resolution failed" in issues[0].message
|
|
# Not advisory: the canvas has to mark the node.
|
|
assert not issues[0].advisory
|
|
assert controller.flow_issues("other") == []
|
|
|
|
|
|
def test_the_issue_clears_when_the_node_reports_itself_well(tmp_path: Path) -> None:
|
|
controller = a_controller(tmp_path)
|
|
|
|
controller.loaded["house.owm"].health = "ok"
|
|
|
|
assert controller.flow_issues("house") == []
|
|
|
|
|
|
def _reporting_node(node_id: str, flow: str) -> Any:
|
|
"""The bit of a node `_health_changed` reads: which node, on which flow."""
|
|
return SimpleNamespace(id=node_id, flow=flow)
|
|
|
|
|
|
def a_running_controller(tmp_path: Path) -> tuple[FlowController, Any]:
|
|
"""A controller holding one healthy node, plus its health reporter."""
|
|
controller = FlowController(FlowStore(tmp_path / "flows"))
|
|
controller.loaded["house.owm"] = LoadedNode(id="house.owm", flow="house")
|
|
return controller, _reporting_node("house.owm", "house")
|
|
|
|
|
|
def test_a_node_that_drops_one_poll_never_surfaces(tmp_path: Path) -> None:
|
|
controller, node = a_running_controller(tmp_path)
|
|
|
|
controller._health_changed(node, "down", "TimeoutError: no reply")
|
|
|
|
# Stored truthfully — a flow reading node health sees it — but held back
|
|
# from the screens until the floor passes.
|
|
assert controller.loaded["house.owm"].health == "down"
|
|
assert controller.flow_issues("house") == []
|
|
|
|
controller._health_changed(node, "ok", None)
|
|
assert controller.flow_issues("house") == []
|
|
|
|
|
|
def test_a_node_still_down_past_the_floor_surfaces(tmp_path: Path) -> None:
|
|
controller, node = a_running_controller(tmp_path)
|
|
|
|
controller._health_changed(node, "down", "TimeoutError: no reply")
|
|
controller.loaded["house.owm"].health_since -= HEALTH_FLOOR
|
|
|
|
assert [issue.code for issue in controller.flow_issues("house")] == [
|
|
"node_unhealthy"
|
|
]
|
|
|
|
# Recovery is not debounced: the floor is only on the way down.
|
|
controller._health_changed(node, "ok", None)
|
|
assert controller.flow_issues("house") == []
|
|
|
|
|
|
def test_a_rotating_error_detail_does_not_restart_the_floor(tmp_path: Path) -> None:
|
|
"""The case that would quietly disable the debounce for real connectors.
|
|
|
|
A connector retrying a dead device reports a different errno each poll. If
|
|
the detail moved the mark, the node would never reach the floor and would
|
|
never be reported down at all.
|
|
"""
|
|
controller, node = a_running_controller(tmp_path)
|
|
|
|
controller._health_changed(node, "down", "OSError: [Errno 113] no route")
|
|
controller.loaded["house.owm"].health_since -= HEALTH_FLOOR
|
|
controller._health_changed(node, "down", "OSError: [Errno 110] timed out")
|
|
|
|
issues = controller.flow_issues("house")
|
|
assert [issue.code for issue in issues] == ["node_unhealthy"]
|
|
assert "Errno 110" in issues[0].message
|