Code quality assessment: no changes

[Copilot]

Assessed overall code quality across the integration. No code changes were made — findings are documented below for prioritization.

Key Findings

• Multi-instance unsafe hass.data: device, device_id, write_manager, register_manager stored at hass.data[DOMAIN] (global) instead of under entry_id — breaks with two simultaneous config entries
• decode_value duplicated in sensor.py, cop_sensor.py, and tests/test_helpers.py; value_codec.py exists for exactly this purpose
• Dual metadata system: sensor_meta.py (97 entries, 971 lines) and register map 6th-tuple element both define sensor metadata with no clear precedence rule
• 13 bare except Exception catches across thz_device.py, __init__.py, calendar.py, config_flow.py
• 20 functions > 50 lines; send_request() and _list_serial_ports() reach CC≈26
• asyncio.sleep(0.01) held inside async with device.lock in 9 places — blocks other entities from device access during write operations
• 15 failing tests: 13 due to missing pytest-asyncio (not in requirements_test.txt), 2 due to incomplete mock setup
• Test-to-code ratio 0.37x; 13 production modules have no dedicated test file (calendar, cop_sensor, config_flow, number, switch, select, time, value_codec, others)
• 86 auto-fixable lint errors (E501, W293); 4 internal development markdown files (BUGFIX_*.md, CODE_REVIEW_*.md, etc.) clutter repo root

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[bigbadoooff]

@copilot

analyze again with the current state of development branch

[Copilot]

@copilot

analyze again with the current state of development branch

Here is the updated assessment against the current tip of development (commit 0f4d664).

---

Code Quality Assessment — development branch (2026-02-24)

What Changed Since Last Assessment

Four commits landed since the previous analysis:

Commit	Change	Quality impact
1d8340f	Remove Monthly + Yearly COP sensors	✅ cop_sensor.py shrunk from 886 → 577 lines, 5 classes → 3
992b25b	Fix area schema to use vol.In	✅ Minor correctness fix
710f2bb	Add BLOCK_LABELS dict to const.py + translations	➡ Neutral — adds 61-line dict to const.py, improves UI
0f4d664	Fix ventilator speed unit/device_class	✅ Correctness fix in sensor_meta.py

---

Metrics at a Glance (dev branch vs previous)

Metric	Previous	Now	Δ
Production lines	11,704	11,486	−218 ✅
Test functions	386	393	+7 ✅
Tests passing	371	378	+7 ✅
Tests failing	15	15	0 (same failures)
Lint errors (ruff)	86	80	−6 ✅
Broad except Exception	13	13	0
Functions > 50 lines	20	20	0
High-CC functions (≥10)	10	14	+4 ⚠️
Type hint coverage	80%	81%	+1% ✅
Test/code ratio	0.37x	0.38x	≈same

---

Findings — Status by Category

✅ Resolved / Improved

• cop_sensor.py reduced from 886 → 577 lines by removing unused Monthly/Yearly COP classes. The native_value CC≈11 offender from the previous report (the monthly/yearly classes) is now gone.
• Ventilator speed sensor now has correct device_class and unit.
• Area schema fixed to use vol.In (stricter, correct).
• 7 new tests added, all passing.

⚠️ Still Open (unchanged from previous report)

1. decode_value duplicated — still copy-pasted in sensor.py and cop_sensor.py. value_codec.py exists for this. The cop_sensor.py copy still has the comment "duplicated to avoid circular imports" even though importing from value_codec has no circularity at all.

2. hass.data multi-instance safety — device, device_id, write_manager, register_manager are still stored at hass.data[DOMAIN] (global, not per entry_id). A second config entry would overwrite the first. The duplicate setdefault is now actually three calls (lines 44, 86, 156) instead of two.

3. sensor_meta.py — still 971 lines / 97 entries. The file's module docstring still claims to be the metadata store, while register map tuples also carry metadata via a 6th element. No single source of truth.

4. 13 bare except Exception — identical count and locations as before. No narrowing of exception types.

5. 20 functions > 50 lines — same list. send_request() (136 lines, CC≈26) and _list_serial_ports() (96 lines, CC≈26) remain the worst offenders.

6. High-CC function count increased from 10 → 14 — _async_enable_integration_disabled_entities() (CC≈14) and should_hide_entity_by_default() (CC≈11, grown due to new BLOCK_LABELS content in const.py) are newly flagged. The function should_hide_entity_by_default at CC≈11 / 58 lines is itself a smell — hiding logic should be data-driven (a set of keywords), not a chain of if branches.

7. asyncio.sleep(0.01) inside async with device.lock — still present in 9 places across switch.py, select.py, number.py, time.py, calendar.py, schedule.py.

8. 15 failing tests — identical set. 13 fail due to pytest-asyncio not being in requirements_test.txt. 2 fail due to incomplete mock in test_thz_device_extended.py. These are non-functional tests that appear to be written but never run.

9. has_entity_name only conditionally set (when a translation_key exists) — entity naming is inconsistent between translated and untranslated entities.

10. 1 live f-string in a _LOGGER call — thz_device.py:630 uses _LOGGER.error(f"...") instead of _LOGGER.error("...", e). 6 commented-out _LOGGER debug lines also remain in thz_device.py.

11. 4 internal markdown files in repo root — BUGFIX_CONNECTION_TIMEOUT.md, CODE_REVIEW_SUMMARY.md, IMPLEMENTATION_SUMMARY.md, REFACTORING_SUMMARY.md are developer artefacts, not user docs. Should move to docs/ or be removed.

---

Priority Order for Next Steps

Priority	Item
High	Fix hass.data global-vs-per-entry (multi-instance safety)
High	Add pytest-asyncio to requirements_test.txt to un-fail 13 tests
Medium	Consolidate decode_value into value_codec.py
Medium	Narrow the 13 except Exception to specific types
Medium	Make should_hide_entity_by_default data-driven (set of keywords/prefixes) to reduce CC
Low	Move the 4 internal .md files out of repo root
Low	Fix the lone f-string logger call + remove 6 commented-out debug lines in thz_device.py

Overall grade: C+ → B− (slight improvement due to COP cleanup and test additions, but the structural issues remain untouched).