fix(ha-diag-agent): structlog event kwarg collision + replace aioresponses

- main.py: rename event= to ha_event= in _log.warning() — structlog treats
  'event' as a reserved positional arg; the old name caused TypeError when
  any check returned unhealthy results (events were still emitted, but the
  check was logged as check_error instead of check_unhealthy)
- tests/test_ha_client.py: replace aioresponses with unittest.mock — aioresponses
  0.7.8 is incompatible with aiohttp >=3.12 (missing stream_writer kwarg)
- pyproject.toml: remove aioresponses from dev dependencies

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

hosts/piha/runtime/ha-diag-agent/docker-compose.override.yml

@@ -0,0 +1,10 @@
+services:
+  ha-diag-agent:
+    # Pin events to the piha-specific subdirectory; overrides the ${NODE_NAME}
+    # variable substitution in the base compose file which requires a shell env var.
+    volumes:
+      - /opt/homelab/events/piha:/events
+      - /var/lib/ha-diag-agent:/data
+      - /opt/homelab/config/ha-diag-agent:/config:ro
+    mem_limit: 128m
+    restart: unless-stopped

services/ha-diag-agent/env.example

@@ -2,11 +2,14 @@
 # Copy to /opt/homelab/config/ha-diag-agent/.env on the target node
 
 # Home Assistant connection (required)
-HA_URL=http://homeassistant.local:8123
+# piha:          HA_URL=http://localhost:8123
+# chelsty-infra: HA_URL=http://100.70.180.90:8123  (chelsty-ha Tailscale IP)
+HA_URL=http://localhost:8123
+# Obtain from HA UI: Settings → People → <diag_agent user> → Long-Lived Access Tokens
 HA_TOKEN=your-long-lived-token-here
 HA_TIMEOUT=10.0
 
-# Node identity
+# Node identity  (must match the node's canonical name in the homelab inventory)
 NODE_NAME=piha
 LOCATION_TAG=ken
 

services/ha-diag-agent/pyproject.toml

@@ -22,7 +22,6 @@ dependencies = [
 dev = [
     "pytest>=8.1",
     "pytest-asyncio>=0.23",
-    "aioresponses>=0.7",
 ]
 
 [tool.setuptools.packages.find]

services/ha-diag-agent/src/ha_diag/main.py

@@ -68,7 +68,7 @@ async def _run_check_and_emit(
                 _log.warning(
                     "check_unhealthy",
                     check=check.name,
-                    event=result.event_type,
+                    ha_event=result.event_type,
                     msg=result.message,
                 )
 

services/ha-diag-agent/tests/test_ha_client.py

@@ -1,8 +1,9 @@
-"""Tests for HAClient using aioresponses to mock aiohttp."""
+"""Tests for HAClient using unittest.mock to avoid aioresponses/aiohttp version coupling."""
 from __future__ import annotations
 
+from unittest.mock import AsyncMock, MagicMock
+
 import pytest
-from aioresponses import aioresponses
 
 from ha_diag.ha_client import HAClient, make_session
 
@@ -10,11 +11,30 @@ HA_URL = "http://homeassistant.test:8123"
 TOKEN = "test-token"
 
 
+def _mock_resp(payload=None, text=None, status=200):
+    """Return a mock that behaves like an aiohttp response context manager."""
+    resp = MagicMock()
+    resp.status = status
+    if status >= 400:
+        resp.raise_for_status.side_effect = Exception(f"HTTP {status}")
+    else:
+        resp.raise_for_status = MagicMock()
+    resp.json = AsyncMock(return_value=payload if payload is not None else {})
+    resp.text = AsyncMock(return_value=text or "")
+    resp.__aenter__ = AsyncMock(return_value=resp)
+    resp.__aexit__ = AsyncMock(return_value=False)
+    return resp
+
+
+def _mock_session(get_resp=None):
+    session = MagicMock()
+    session.get.return_value = get_resp or _mock_resp()
+    return session
+
+
 @pytest.mark.asyncio
 async def test_get_api_status_ok():
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/", payload={"message": "API running."})
-        async with make_session(TOKEN) as session:
+    session = _mock_session(_mock_resp({"message": "API running."}))
     client = HAClient(HA_URL, session)
     result = await client.get_api_status()
     assert result == {"message": "API running."}
@@ -22,9 +42,7 @@ async def test_get_api_status_ok():
 
 @pytest.mark.asyncio
 async def test_get_api_status_unauthorized():
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/", status=401)
-        async with make_session(TOKEN) as session:
+    session = _mock_session(_mock_resp(status=401))
     client = HAClient(HA_URL, session)
     with pytest.raises(Exception):
         await client.get_api_status()
@@ -33,9 +51,7 @@ async def test_get_api_status_unauthorized():
 @pytest.mark.asyncio
 async def test_get_states_returns_list():
     payload = [{"entity_id": "light.living_room", "state": "on"}]
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/states", payload=payload)
-        async with make_session(TOKEN) as session:
+    session = _mock_session(_mock_resp(payload))
     client = HAClient(HA_URL, session)
     states = await client.get_states()
     assert isinstance(states, list)
@@ -45,9 +61,7 @@ async def test_get_states_returns_list():
 @pytest.mark.asyncio
 async def test_get_config_returns_dict():
     payload = {"version": "2024.1.0", "location_name": "Home"}
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/config", payload=payload)
-        async with make_session(TOKEN) as session:
+    session = _mock_session(_mock_resp(payload))
     client = HAClient(HA_URL, session)
     config = await client.get_config()
     assert config["version"] == "2024.1.0"
@@ -59,9 +73,7 @@ async def test_get_entity_registry_returns_list():
         {"entity_id": "light.hall", "platform": "zha", "area_id": "hallway"},
         {"entity_id": "sensor.temp", "platform": "mqtt", "area_id": None},
     ]
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/config/entity_registry", payload=payload)
-        async with make_session(TOKEN) as session:
+    session = _mock_session(_mock_resp(payload))
     client = HAClient(HA_URL, session)
     registry = await client.get_entity_registry()
     assert len(registry) == 2
@@ -71,12 +83,7 @@ async def test_get_entity_registry_returns_list():
 @pytest.mark.asyncio
 async def test_make_session_sets_auth_header():
     """make_session injects the Bearer token in all requests."""
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/", payload={"message": "API running."})
     async with make_session("my-secret-token") as session:
-            client = HAClient(HA_URL, session)
-            await client.get_api_status()
-        # Verify the Authorization header was sent
         assert session.headers.get("Authorization") == "Bearer my-secret-token"
 
 
@@ -89,47 +96,42 @@ async def test_make_session_sets_auth_header():
 async def test_entity_registry_cached_on_second_call():
     """Second call within TTL returns cache, making only one HTTP request."""
     payload = [{"entity_id": "light.hall", "platform": "zha", "area_id": "hallway"}]
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/config/entity_registry", payload=payload)
-        async with make_session(TOKEN) as session:
+    session = _mock_session(_mock_resp(payload))
     client = HAClient(HA_URL, session, entity_registry_cache_ttl=300.0)
     r1 = await client.get_entity_registry()
-            r2 = await client.get_entity_registry()  # from cache — no second HTTP call
+    r2 = await client.get_entity_registry()  # from cache
     assert r1 == r2
-    # aioresponses would raise ConnectionError on the unmocked second request
-    # if caching weren't working; reaching here means it used the cache.
+    session.get.assert_called_once()  # only one HTTP request
 
 
 @pytest.mark.asyncio
-async def test_entity_registry_cache_bypassed_after_ttl(monkeypatch):
-    """After TTL expiry, next call fetches fresh data."""
-    import time
+async def test_entity_registry_cache_bypassed_after_ttl():
+    """After TTL expiry (ttl=0), next call fetches fresh data."""
     payload = [{"entity_id": "light.hall", "platform": "zha", "area_id": "hallway"}]
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/config/entity_registry", payload=payload)
-        m.get(f"{HA_URL}/api/config/entity_registry", payload=payload)
-        async with make_session(TOKEN) as session:
+    session = _mock_session(_mock_resp(payload))
+    # TTL=0 means every call is stale → two fetches
+    session.get.side_effect = [_mock_resp(payload), _mock_resp(payload)]
     client = HAClient(HA_URL, session, entity_registry_cache_ttl=0.0)
-            await client.get_entity_registry()   # fetches
-            await client.get_entity_registry()   # TTL=0 → fetches again
+    await client.get_entity_registry()
+    await client.get_entity_registry()
+    assert session.get.call_count == 2
 
 
 @pytest.mark.asyncio
 async def test_invalidate_registry_cache_forces_refetch():
     """invalidate_registry_cache() makes the next call hit the network."""
     payload = [{"entity_id": "light.hall", "platform": "zha", "area_id": ""}]
-    with aioresponses() as m:
-        m.get(f"{HA_URL}/api/config/entity_registry", payload=payload)
-        m.get(f"{HA_URL}/api/config/entity_registry", payload=payload)
-        async with make_session(TOKEN) as session:
+    session = _mock_session(_mock_resp(payload))
+    session.get.side_effect = [_mock_resp(payload), _mock_resp(payload)]
     client = HAClient(HA_URL, session, entity_registry_cache_ttl=300.0)
     await client.get_entity_registry()
     client.invalidate_registry_cache()
-            await client.get_entity_registry()  # must hit network again
+    await client.get_entity_registry()
+    assert session.get.call_count == 2
 
 
 @pytest.mark.asyncio
 async def test_entity_registry_cache_default_ttl_is_300():
-    async with make_session(TOKEN) as session:
+    session = _mock_session()
     client = HAClient(HA_URL, session)
     assert client._registry_cache_ttl == 300.0