fix(weather): normalize structured source language

docs/design.md

@@ -104,9 +104,9 @@ RSS 来源可以按地点 ID 限定范围，并配置正文清洗规则。`verba
 
 和风天气使用 `QWeatherJWTAuthenticator` 签发短期 JWT。认证输入包括项目 ID、凭据 ID、专属 API Host 和 Base64 编码的 Ed25519 私钥。实现不支持用长期 API Key 代替该流程。
 
-`OpenMeteoProvider` 提供全球天气，并从独立接口读取空气质量和欧洲花粉数据。适配器在生成来源正文前把 WMO 天气代码转换为可读的中文天气现象；未知代码保留为“未识别天气现象”并写入安全日志。公开接口适用于非商业使用，没有 SLA；Base URL 和可选 API Key 可以替换。
+`OpenMeteoProvider` 提供全球天气，并从独立接口读取空气质量和欧洲花粉数据。Open-Meteo API 返回语言中立的结构化数据，适配器把天气、空气质量和花粉统一转换为固定 `en` 来源正文。WMO 天气代码映射在模块加载时完成验证，未知代码保留为 “Unrecognized weather condition” 并写入安全日志。`SourceDocument` 记录英文来源语言，模型按地点配置的目标语言生成最终简报。公开接口适用于非商业使用，没有 SLA；Base URL 和可选 API Key 可以替换。
 
-`AQICNProvider` 只在最终天气结果缺少空气质量时补充当前观测。它不参与未来日期查询，也不把 PM2.5 单项 AQI 换算为浓度。
+`AQICNProvider` 只在最终天气结果缺少空气质量时补充当前观测。AQICN 的结构化数据也统一转换为固定 `en` 来源正文。它不参与未来日期查询，也不把 PM2.5 单项 AQI 换算为浓度。
 
 `NEASingaporeNowcastProvider` 只提供新加坡两小时预报。`JMAJapanForecastProvider` 只提供地点所配置预报区的日本本地预报。它们没有完整天气服务所需的全部数据，因此与 Open-Meteo 组合，而不是作为完整天气 fallback。
 

tests/test_air_quality.py

@@ -35,14 +35,16 @@ def handler(request: httpx.Request) -> httpx.Response:
 
     assert snapshot.aqi == 120
     assert snapshot.aqi_standard == "US EPA"
+    assert snapshot.category == "Unhealthy for sensitive groups"
     assert snapshot.effective_at is not None
     assert snapshot.effective_at.to_iso8601_string() == "2026-07-13T08:00:00+08:00"
     assert snapshot.time_kind is AirQualityTimeKind.OBSERVATION
     assert snapshot.pm25_aqi == 100
     assert snapshot.pm25_concentration is None
+    assert snapshot.output_language == "en"
     document = air_quality_to_document(snapshot)
-    assert "AQI：120（标准：US EPA" in document.content
-    assert "PM2.5 不可用" in document.content
+    assert "AQI: 120 (Standard: US EPA" in document.content
+    assert "PM2.5 concentration: Unavailable" in document.content
     assert "原始浓度" not in document.content
     assert "折算" not in document.content
 

tests/test_allergen.py

@@ -13,28 +13,28 @@
 
 def test_allergen_guidance_zero_is_none() -> None:
     category, guidance = allergen_guidance(0)
-    assert category == "无"
+    assert category == "None"
     assert guidance
 
 
 def test_allergen_guidance_low_band() -> None:
     category, _ = allergen_guidance(5)
-    assert category == "低"
+    assert category == "Low"
 
 
 def test_allergen_guidance_moderate_band() -> None:
     category, _ = allergen_guidance(20)
-    assert category == "中"
+    assert category == "Moderate"
 
 
 def test_allergen_guidance_high_band() -> None:
     category, _ = allergen_guidance(50)
-    assert category == "高"
+    assert category == "High"
 
 
 def test_allergen_guidance_extreme_band() -> None:
     category, _ = allergen_guidance(500)
-    assert category == "极高"
+    assert category == "Very high"
 
 
 @pytest.mark.parametrize("concentration", [-1, float("nan"), float("inf"), float("-inf")])

tests/test_languages.py

@@ -50,7 +50,7 @@ def test_weather_provider_language_metadata_distinguishes_selectable_and_fixed_s
     assert QWEATHER_LANGUAGE_SUPPORT.select("ja") == "ja"
     assert QWEATHER_LANGUAGE_SUPPORT.api_code("ja") == "ja"
     assert OPEN_METEO_LANGUAGE_SUPPORT.selectable is False
-    assert OPEN_METEO_LANGUAGE_SUPPORT.default == "zh-CN"
+    assert OPEN_METEO_LANGUAGE_SUPPORT.default == "en"
 
 
 @pytest.mark.parametrize(

tests/test_reference_data.py

@@ -78,7 +78,7 @@ def test_packaged_reference_data_is_available() -> None:
         96,
         99,
     }
-    assert weather_codes[53] == "中等强度毛毛雨"
+    assert weather_codes[53] == "Moderate drizzle"
     assert localization_table("weather_document")["ja"]["forecast"] == "天気予報"
     assert localization_table("briefing")["zh-Hans"]["weather"] == "天气信息"
     classification = telegram_error_classification()
@@ -90,12 +90,12 @@ def test_packaged_reference_data_is_available() -> None:
     "value",
     (
         {},
-        {"descriptions_zh_CN": {}},
-        {"descriptions_zh_CN": {"unknown": "晴朗"}},
-        {"descriptions_zh_CN": {"00": "晴朗"}},
-        {"descriptions_zh_CN": {"9" * 5_000: "未知"}},
-        {"descriptions_zh_CN": {"0": ""}},
-        {"descriptions_zh_CN": {"0": "晴朗"}, "unknown": {}},
+        {"descriptions_en": {}},
+        {"descriptions_en": {"unknown": "Clear sky"}},
+        {"descriptions_en": {"00": "Clear sky"}},
+        {"descriptions_en": {"9" * 5_000: "Unknown"}},
+        {"descriptions_en": {"0": ""}},
+        {"descriptions_en": {"0": "Clear sky"}, "unknown": {}},
     ),
 )
 def test_open_meteo_weather_codes_reject_invalid_data(monkeypatch, value) -> None:

tests/test_render.py

@@ -79,7 +79,7 @@ def test_renderers_fall_back_to_source_id_for_legacy_blank_name() -> None:
 def test_telegram_html_renderer_uses_context_source_name_as_attribution() -> None:
     context = SourceDocument(
         "allergen:open-meteo",
-        "Open-Meteo / CAMS ENSEMBLE 花粉过敏原",
+        "Open-Meteo / CAMS ENSEMBLE pollen allergens",
         "https://open-meteo.com/en/docs/air-quality-api",
         "Pollen data",
     )
@@ -93,14 +93,14 @@ def test_telegram_html_renderer_uses_context_source_name_as_attribution() -> Non
     rendered = TelegramHTMLRenderer().render_briefing(result, (), (context,))
 
     assert (
-        '<a href="https://open-meteo.com/en/docs/air-quality-api">Open-Meteo / CAMS ENSEMBLE 花粉过敏原</a>'
+        '<a href="https://open-meteo.com/en/docs/air-quality-api">Open-Meteo / CAMS ENSEMBLE pollen allergens</a>'
     ) in rendered.body
 
 
 def test_plain_text_renderer_uses_context_source_name_as_attribution() -> None:
     context = SourceDocument(
         "allergen:open-meteo",
-        "Open-Meteo / CAMS ENSEMBLE 花粉过敏原",
+        "Open-Meteo / CAMS ENSEMBLE pollen allergens",
         "https://open-meteo.com/en/docs/air-quality-api",
         "Pollen data",
     )
@@ -113,7 +113,9 @@ def test_plain_text_renderer_uses_context_source_name_as_attribution() -> None:
 
     rendered = PlainTextRenderer().render_briefing(result, (), (context,))
 
-    assert ("Open-Meteo / CAMS ENSEMBLE 花粉过敏原: https://open-meteo.com/en/docs/air-quality-api") in rendered.body
+    assert (
+        "Open-Meteo / CAMS ENSEMBLE pollen allergens: https://open-meteo.com/en/docs/air-quality-api"
+    ) in rendered.body
 
 
 def test_telegram_html_renders_active_warnings_section() -> None:

tests/test_weather_context.py

@@ -533,7 +533,9 @@ def handler(request: httpx.Request) -> httpx.Response:
         ).fetch(52.52, 13.41)
 
     assert len(snapshot.weather_forecast) == 2
-    assert "局部多云" in snapshot.weather_forecast[0]
+    assert snapshot.output_language == "en"
+    assert "Partly cloudy" in snapshot.weather_forecast[0]
+    assert "maximum precipitation probability 10%" in snapshot.weather_forecast[0]
     assert "WMO" not in snapshot.weather_forecast[0]
     assert snapshot.observed_at.to_iso8601_string() == "2026-07-13T08:00:00+02:00"
     assert snapshot.observed_at.timezone_name == "Europe/Berlin"
@@ -544,22 +546,31 @@ def handler(request: httpx.Request) -> httpx.Response:
 
 
 def test_open_meteo_weather_code_uses_readable_description() -> None:
-    assert _open_meteo_weather_description(53) == "中等强度毛毛雨"
+    assert _open_meteo_weather_description(53) == "Moderate drizzle"
+
+
+def test_open_meteo_weather_code_lookup_uses_cached_loader_boundary(monkeypatch) -> None:
+    monkeypatch.setattr(
+        "weather_briefing.weather_context.open_meteo_weather_code_descriptions",
+        lambda: {53: "Reloaded description"},
+    )
+
+    assert _open_meteo_weather_description(53) == "Reloaded description"
 
 
 def test_open_meteo_unknown_weather_code_uses_readable_fallback(caplog) -> None:
     with caplog.at_level("WARNING", logger="weather_briefing.weather_context"):
         description = _open_meteo_weather_description(100)
 
-    assert description == "未识别天气现象"
+    assert description == "Unrecognized weather condition"
     assert "Unknown Open-Meteo weather code code=100" in caplog.text
 
 
 def test_open_meteo_invalid_weather_code_uses_readable_fallback(caplog) -> None:
     with caplog.at_level("WARNING", logger="weather_briefing.weather_context"):
         description = _open_meteo_weather_description("53")
 
-    assert description == "未识别天气现象"
+    assert description == "Unrecognized weather condition"
     assert "Invalid Open-Meteo weather code value_type=str" in caplog.text
 
 
@@ -615,7 +626,7 @@ def handler(request: httpx.Request) -> httpx.Response:
         ).fetch_for_date(39.9, 116.3, target_date)
 
     assert len(snapshot.weather_forecast) == 1
-    assert snapshot.weather_forecast[0].startswith("2026-07-15：")
+    assert snapshot.weather_forecast[0].startswith("2026-07-15: ")
     assert snapshot.air_quality is not None
     assert snapshot.air_quality.aqi == 90
     assert snapshot.air_quality.effective_at is not None
@@ -1884,15 +1895,17 @@ def handler(request: httpx.Request) -> httpx.Response:
     assert snapshot.air_quality is not None
     assert snapshot.allergen is not None
     assert snapshot.allergen.source_id == "allergen:open-meteo"
-    assert snapshot.allergen.source_name == "Open-Meteo / CAMS ENSEMBLE 花粉过敏原"
+    assert snapshot.allergen.source_name == "Open-Meteo / CAMS ENSEMBLE pollen allergens"
+    assert snapshot.allergen.output_language == "en"
     level_names = {level.name for level in snapshot.allergen.levels}
-    assert {"桤木", "桦木", "禾本"} == level_names
-    birch = next(level for level in snapshot.allergen.levels if level.name == "桦木")
-    assert birch.category == "中"
+    assert {"Alder", "Birch", "Grass"} == level_names
+    birch = next(level for level in snapshot.allergen.levels if level.name == "Birch")
+    assert birch.category == "Moderate"
     assert birch.concentration == 15
-    assert snapshot.allergen.overall_category == "中"
+    assert snapshot.allergen.overall_category == "Moderate"
     documents = snapshot_to_documents(snapshot)
     assert "allergen:open-meteo" in [doc.id for doc in documents]
+    assert all(doc.language == "en" for doc in documents)
 
 
 async def test_open_meteo_provider_returns_no_allergen_when_pollen_absent() -> None:
@@ -1947,7 +1960,7 @@ def handler(request: httpx.Request) -> httpx.Response:
 
     assert snapshot.allergen is not None
     level_names = {level.name for level in snapshot.allergen.levels}
-    assert level_names == {"禾本"}
+    assert level_names == {"Grass"}
 
 
 async def test_open_meteo_allergen_handles_missing_time_gracefully() -> None:

weather_briefing/air_quality.py

@@ -91,7 +91,7 @@ async def fetch(
             pm25_unit=None,
             category=category,
             health_guidance=guidance,
-            output_language="zh-CN",
+            output_language="en",
         )
 
 

weather_briefing/data/air_quality_guidance.json

@@ -3,33 +3,33 @@
   "bands": [
     {
       "maximum_aqi": 50,
-      "category": "优",
-      "guidance": "空气污染风险很低，一般无需因空气质量调整户外活动。"
+      "category": "Good",
+      "guidance": "Air pollution risk is low; no activity changes are generally needed."
     },
     {
       "maximum_aqi": 100,
-      "category": "良",
-      "guidance": "极少数异常敏感人群应减少长时间、高强度户外活动。"
+      "category": "Moderate",
+      "guidance": "Unusually sensitive people should consider reducing prolonged or heavy outdoor exertion."
     },
     {
       "maximum_aqi": 150,
-      "category": "对敏感人群不健康",
-      "guidance": "儿童、活跃成年人和呼吸系统疾病人群应减少长时间户外活动。"
+      "category": "Unhealthy for sensitive groups",
+      "guidance": "Children, active adults, and people with respiratory disease should reduce prolonged outdoor exertion."
     },
     {
       "maximum_aqi": 200,
-      "category": "不健康",
-      "guidance": "敏感人群应避免长时间户外活动，其他人群也应适当减少户外活动。"
+      "category": "Unhealthy",
+      "guidance": "Sensitive groups should avoid prolonged outdoor exertion; everyone else should reduce it."
     },
     {
       "maximum_aqi": 300,
-      "category": "非常不健康",
-      "guidance": "所有人应减少户外活动，敏感人群尽量避免外出。"
+      "category": "Very unhealthy",
+      "guidance": "Everyone should reduce outdoor activity, and sensitive groups should avoid going outdoors."
     },
     {
       "maximum_aqi": null,
-      "category": "危险",
-      "guidance": "所有人应避免户外活动，并关注当地健康部门建议。"
+      "category": "Hazardous",
+      "guidance": "Everyone should avoid outdoor activity and follow local public health advice."
     }
   ]
 }

weather_briefing/data/allergen_guidance.json

@@ -1,37 +1,37 @@
 {
   "pollen_types": {
-    "alder": "桤木",
-    "birch": "桦木",
-    "grass": "禾本",
-    "mugwort": "蒿属",
-    "olive": "橄榄",
-    "ragweed": "豚草"
+    "alder": "Alder",
+    "birch": "Birch",
+    "grass": "Grass",
+    "mugwort": "Mugwort",
+    "olive": "Olive",
+    "ragweed": "Ragweed"
   },
   "bands": [
     {
       "maximum_concentration": 0,
-      "category": "无",
-      "guidance": "花粉浓度极低，过敏体质人群一般无需因花粉调整户外活动。"
+      "category": "None",
+      "guidance": "Pollen concentrations are negligible; no activity changes are generally needed."
     },
     {
       "maximum_concentration": 10,
-      "category": "低",
-      "guidance": "花粉浓度较低，少数极度敏感者可做适当防护。"
+      "category": "Low",
+      "guidance": "Pollen concentrations are low; highly sensitive people may take routine precautions."
     },
     {
       "maximum_concentration": 30,
-      "category": "中",
-      "guidance": "花粉浓度中等，过敏体质人群户外活动后建议清洗面部和鼻腔。"
+      "category": "Moderate",
+      "guidance": "Pollen concentrations are moderate; sensitive people should wash their face and nose after outdoor activity."
     },
     {
       "maximum_concentration": 100,
-      "category": "高",
-      "guidance": "花粉浓度较高，花粉过敏者应减少户外活动，外出佩戴口罩。"
+      "category": "High",
+      "guidance": "Pollen concentrations are high; people with pollen allergies should limit outdoor activity and wear a mask outside."
     },
     {
       "maximum_concentration": null,
-      "category": "极高",
-      "guidance": "花粉浓度很高，花粉过敏者应尽量避免外出，关好门窗并使用空气净化设备。"
+      "category": "Very high",
+      "guidance": "Pollen concentrations are very high; people with pollen allergies should avoid going outside, close windows, and use air filtration."
     }
   ]
 }

weather_briefing/data/open_meteo_weather_codes.json

@@ -1,32 +1,32 @@
 {
-  "descriptions_zh_CN": {
-    "0": "晴朗",
-    "1": "大致晴朗",
-    "2": "局部多云",
-    "3": "阴天",
-    "45": "有雾",
-    "48": "雾凇",
-    "51": "轻微毛毛雨",
-    "53": "中等强度毛毛雨",
-    "55": "强毛毛雨",
-    "56": "轻微冻毛毛雨",
-    "57": "强冻毛毛雨",
-    "61": "小雨",
-    "63": "中雨",
-    "65": "大雨",
-    "66": "轻微冻雨",
-    "67": "强冻雨",
-    "71": "小雪",
-    "73": "中雪",
-    "75": "大雪",
-    "77": "米雪",
-    "80": "轻微阵雨",
-    "81": "中等强度阵雨",
-    "82": "强阵雨",
-    "85": "轻微阵雪",
-    "86": "强阵雪",
-    "95": "雷暴",
-    "96": "雷暴伴轻微冰雹",
-    "99": "雷暴伴强冰雹"
+  "descriptions_en": {
+    "0": "Clear sky",
+    "1": "Mainly clear",
+    "2": "Partly cloudy",
+    "3": "Overcast",
+    "45": "Fog",
+    "48": "Depositing rime fog",
+    "51": "Light drizzle",
+    "53": "Moderate drizzle",
+    "55": "Dense drizzle",
+    "56": "Light freezing drizzle",
+    "57": "Dense freezing drizzle",
+    "61": "Slight rain",
+    "63": "Moderate rain",
+    "65": "Heavy rain",
+    "66": "Light freezing rain",
+    "67": "Heavy freezing rain",
+    "71": "Slight snowfall",
+    "73": "Moderate snowfall",
+    "75": "Heavy snowfall",
+    "77": "Snow grains",
+    "80": "Slight rain showers",
+    "81": "Moderate rain showers",
+    "82": "Violent rain showers",
+    "85": "Slight snow showers",
+    "86": "Heavy snow showers",
+    "95": "Thunderstorm",
+    "96": "Thunderstorm with slight hail",
+    "99": "Thunderstorm with heavy hail"
   }
 }