Solve monthly overflow as reported in #399 #400
Conversation
📝 WalkthroughWalkthroughUpdates changelog with PR 400; modifies Circle node clock sync to compute target date via direct day difference (timedelta) instead of a modulo wrap; adds tests and test data to cover a month-end/day-of-week rollover scenario. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #400 +/- ##
==========================================
+ Coverage 82.05% 82.07% +0.02%
==========================================
Files 36 36
Lines 8156 8182 +26
==========================================
+ Hits 6692 6715 +23
- Misses 1464 1467 +3 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@plugwise_usb/nodes/circle.py`:
- Around line 885-891: The month overflow handling around calculating
circle_timestamp is wrong: when (difference := days_diff - days_to_end_of_month)
> 0 you adjust corrected_day but do not advance the month, producing incorrect
dates; replace the manual day correction logic (the block using
last_day_of_month, days_to_end_of_month, corrected_day and
dt_now.replace(day=...)) by computing circle_timestamp as dt_now +
timedelta(days=days_diff) (using the existing dt_now and days_diff variables) so
month/year boundaries are handled correctly and remove the fragile
corrected_day/replace logic.
There was a problem hiding this comment.
Pull request overview
Fixes clock synchronization date calculation when the target weekday crosses a month boundary (avoiding invalid datetime.replace(day=...) behavior at month-end).
Changes:
- Update
clock_synchronize()to compute the target date viadt_now + timedelta(days=...)to handle month rollovers safely. - Add an “Ongoing” changelog entry referencing the PR/issue.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
plugwise_usb/nodes/circle.py |
Switches clock-sync date computation to timedelta arithmetic to prevent month-end overflow. |
CHANGELOG.md |
Documents the fix in the ongoing changelog section. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| dt_now = datetime.now(tz=UTC) | ||
| days_diff = (response.day_of_week.value - dt_now.weekday()) % 7 | ||
| circle_timestamp: datetime = dt_now.replace( | ||
| day=dt_now.day + days_diff, | ||
| target_date = dt_now + timedelta(days=days_diff) | ||
| circle_timestamp = target_date.replace( |
There was a problem hiding this comment.
This change fixes a tricky end-of-month boundary case, but there’s no regression test covering the date rollover logic. Consider adding a focused async unit test that freezes time near month-end (e.g., Jan 31) and mocks the clock-get response so clock_synchronize() exercises the (dt_now + timedelta(...)) path without raising and computes the expected circle_timestamp.
There was a problem hiding this comment.
@coderabbitai please suggest a simple regression test that covers this update.
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Find existing test files for the circle.py module
fd -e py test.*circle tests
Length of output: 0
🏁 Script executed:
#!/bin/bash
# Check the project structure and look for test directory
fd -t d test
Length of output: 6
🏁 Script executed:
#!/bin/bash
# Look for pytest configuration or test patterns
find . -name "pytest.ini" -o -name "setup.cfg" -o -name "pyproject.toml" | head -5
Length of output: 16
🏁 Script executed:
#!/bin/bash
# Search for existing clock_synchronize tests to understand the pattern
rg -n "clock_synchronize" --type py -g '*test*' -C 3
Length of output: 0
🏁 Script executed:
#!/bin/bash
# Check if freezegun or other mocking libraries are already used
rg -n "freezegun|freeze_time|mock_datetime" --type py -g '*test*'
Length of output: 594
🏁 Script executed:
#!/bin/bash
# Check dependencies to see what testing libraries are available
cat requirements*.txt pyproject.toml setup.py setup.cfg 2>/dev/null | grep -i "test\|mock\|freeze"
Length of output: 339
🏁 Script executed:
#!/bin/bash
# Look at the test file structure to understand how Circle tests are organized
rg -n "class.*Circle|def test.*circle" --type py tests/test_usb.py -A 2 | head -50
Length of output: 171
🏁 Script executed:
#!/bin/bash
# Check how CircleClockGetRequest is mocked in existing tests
rg -n "CircleClockGetRequest|clock" --type py tests/test_usb.py -B 2 -A 5 | head -80
Length of output: 3329
🏁 Script executed:
#!/bin/bash
# Look at the imports and how responses are mocked
head -50 tests/test_usb.py
Length of output: 2263
🏁 Script executed:
#!/bin/bash
# Look for how CircleClockGetRequest responses are created/mocked
rg -n "CircleClockGetResponse|ClockGetResponse" --type py -B 2 -A 5 | head -60
Length of output: 0
🏁 Script executed:
#!/bin/bash
# Check the responses module to see what CircleClockGet response looks like
rg -n "class.*ClockGet" plugwise_usb/messages/responses.py -A 15 | head -40
Length of output: 0
🏁 Script executed:
#!/bin/bash
# Look at how day_of_week and time are structured in responses
rg -n "day_of_week|DayOfWeek" plugwise_usb/messages/ -A 2 | head -40
Length of output: 1809
🏁 Script executed:
#!/bin/bash
# Look at how async methods are tested with mocked responses
rg -n "async def test.*circle" tests/test_usb.py -A 30 | head -80
Length of output: 1312
🏁 Script executed:
#!/bin/bash
# Check response structure and how to create mock responses
rg -n "class.*CircleClock" plugwise_usb/messages/responses.py -B 2 -A 20 | head -60
Length of output: 690
🏁 Script executed:
#!/bin/bash
# Look at how monkeypatch is used to mock request.send()
rg -n "monkeypatch.*send|mock.*Request" tests/test_usb.py -B 2 -A 5 | head -50
Length of output: 2050
@bouwew Here's a simple regression test that covers the month overflow fix:
`@freeze_time`("2026-01-31 10:30:00", real_asyncio=True)
async def test_clock_synchronize_month_overflow(
self, monkeypatch: pytest.MonkeyPatch
) -> None:
"""Test clock_synchronize handles month-end date rollover correctly.
Regression test for issue `#399`: ensures that when the Circle's day_of_week
differs from the current weekday near month-end, the date calculation
doesn't attempt an invalid day value (e.g., Jan 32).
"""
mock_serial = MockSerial(None)
monkeypatch.setattr(
pw_connection_manager,
"create_serial_connection",
mock_serial.mock_connection,
)
monkeypatch.setattr(pw_sender, "STICK_TIME_OUT", 0.2)
monkeypatch.setattr(pw_requests, "NODE_TIME_OUT", 2.0)
stick = pw_stick.Stick("test_port", cache_enabled=False)
await stick.connect()
await stick.initialize()
# Get a Circle node
circle_node = stick.nodes.get("0098765432101234")
assert circle_node is not None
await circle_node.load()
# Mock CircleClockGetRequest.send() to return a response where
# day_of_week is Saturday (5) while frozen time is Friday (4), Jan 31
async def mock_clock_get_send(self):
response = pw_responses.CircleClockResponse()
response.timestamp = dt.now(tz=UTC)
# Set day_of_week to Saturday (5), requiring +1 day from Friday Jan 31
# Old code: Jan 31 + 1 = day 32 (ValueError)
# New code: Jan 31 + timedelta(days=1) = Feb 1 (correct)
response.day_of_week.value = 5 # Saturday
response.time.value = dt.now(tz=UTC).time()
return response
monkeypatch.setattr(
pw_requests.CircleClockGetRequest,
"send",
mock_clock_get_send,
)
# This should not raise ValueError about invalid day
result = await circle_node.clock_synchronize()
assert result is True
await stick.disconnect()Key aspects of this test:
- Freezes time to Jan 31 - the last day of the month where adding days could cause overflow
- Mocks the clock response to return
day_of_week=5(Saturday) when the frozen date is Friday, requiring a +1 day calculation - Verifies no exception is raised and the method returns
True - The old code would fail with
ValueError: day is out of range for monthwhen tryingreplace(day=32) - The new code succeeds by using
timedelta(days=1)which correctly rolls over to Feb 1
You can add this test to your tests/test_usb.py file in the appropriate test class. Would you like me to adjust the test to match a specific node setup in your test suite?
🧠 Learnings used
Learnt from: bouwew
Repo: plugwise/python-plugwise-usb PR: 255
File: plugwise_usb/nodes/circle.py:477-482
Timestamp: 2025-06-19T06:38:04.702Z
Learning: In plugwise_usb/nodes/circle.py, the timestamp comparison `prev_address_timestamp - self._last_collected_energy_timestamp` in the `get_missing_energy_logs` method is intentional. The code iterates backwards through time-ordered energy log addresses, where `prev_address_timestamp` contains the more recent timestamp from the previous iteration, and this subtraction correctly calculates the time gap to determine when to stop collecting outdated data.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@tests/test_usb.py`:
- Around line 3043-3083: The test_test_clock_synchronize_month_overflow case
doesn't force a month rollover because the frozen date "2026-01-31" is already
Saturday (weekday 5) and mock_clock_get_send sets response.day_of_week.value = 5
so days_diff == 0; update the test so the mocked day_of_week differs by +1 to
force crossing into February (e.g., set response.day_of_week.value = 6) or
change the frozen time in the `@freeze_time` decorator to a Friday date so that
mock_clock_get_send's day_of_week=5 results in a +1 day rollover; modify the
mock_clock_get_send implementation (and/or the freeze_time value) inside
test_clock_synchronize_month_overflow to ensure days_diff != 0 and the code path
that adds timedelta(days=1) is exercised.
|
dirixmjm
left a comment
dirixmjm
left a comment
There was a problem hiding this comment.
LGTM!
Bedankt voor de actie.
|
@dirixmjm Thanks, but I'm not there yet, trying to recreate the |
Summary by CodeRabbit
Bug Fixes
Tests
Documentation
✏️ Tip: You can customize this high-level summary in your review settings.