Compare commits

..

22 Commits

Author SHA1 Message Date
javis-bot
f05424e1b2 chore(app): version 0.1.36
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 20:08:35 +09:00
javis-bot
be09cfad81 fix(reply): what the user says they did is not refused as unsupported
The tool honesty rules ("if no tool can do it, say so") made the
model refuse actions the user only reported doing themselves: "알람
일곱 시로 맞춰놨어, 잘했지?" got "제가 도와드릴 수 없습니다". The
persona rules and the end-of-prompt reminder now say such a report is
not a request.

Measured on the service model (qwen3.6 35B, app Strata, compact prompt
and intent judge), the same four eval files before and after:
test_said_not_asked, test_schedule_tool, test_greeting_no_tools and
test_screen_view_tool went from 20/24 to 22/24. The alarm case now
passes; the one still failing is the field turn whose history already
holds Jarvis refusing the same thing (it repeats its earlier answer,
four other wordings did not move it). Piranesi fails before and after.
Adds the correctly heard field turn as a case.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 20:08:18 +09:00
javis-bot
ac633c63ca fix(voice): no treble boost before transcription
The 12 dB shelf above 1 kHz from 0.1.34 made the user's speech worse.
Re-transcribing the 34 live recordings of 2026-11-18 (17:32 to 19:53)
with the shelf reproduces every live text; without it "왜 내 방해를"
comes back instead of "올해 내 방해를" (the user said "난 왜 라고
했어" right after), "알아서 좀 조정해 놨는데" instead of "아라해석도
좀 조정해놨는데", and "넌 뭐하는 애야?" instead of an empty text. No
utterance got clearly better with it. Reverts 9f62bfb and 04c23f9.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 20:04:24 +09:00
javis-bot
499280504e test(evals): actions the user says they did are not refused
Field failure 2026-11-18: "너 말하는 속도 내가 조절해놨으니까 한번 말해보라고"
was answered "말하는 속도 조절 기능은 현재 지원하고 있지 않습니다". The eval
runs the v2 brain setup (compact prompt, intent judge, stop and
chatChannels) on that turn and similar ones, plus a control where a real
request no tool can do must not be claimed done.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 18:59:46 +09:00
javis-bot
c816358552 chore(app): version 0.1.35
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 18:32:50 +09:00
javis-bot
9f5f3d891f fix(voice): spell Korean numbers out before MeloTTS reads them
MeloTTS's Korean front end read "60%" digit by digit ("육영퍼센트") when
the Windows MeCab build did not tag what followed as a bound noun, and its
sentence splitter broke "4.2미터" at the dot ("사. 이미터"). The KR child
now spells decimals with 점, drops thousands commas and gives every other
whole number its Sino-Korean reading, leaving numbers before native
counters (시, 개, 마리, ...) to MeloTTS's own counter rule.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 18:32:46 +09:00
javis-bot
04c23f9bf7 docs(voice): consonant shelf numbers measured with voiced masks
Re-measured as a final is levelled (Silero voiced windows): live 25 sure
utterances 5.04% -> 3.92% CER, FLEURS Korean test 5.11% -> 4.85%. The
shelf does not fix a wake word whose first consonant is not heard.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 18:18:30 +09:00
javis-bot
49050b18a9 chore(app): version 0.1.34
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 18:09:12 +09:00
javis-bot
9f62bfb059 fix(voice): raise the consonant band by 12 dB before transcription
A dark microphone or a speaker who swallows first consonants and
sentence ends loses the band above 1 kHz first: in the live
recordings "자비스" came out as "아비스"/"다비스" and "서울" as "어우".
loudness_equalise now raises it with a one-octave shelf at 1 kHz.

Measured with large-v3-turbo: 25 sure live utterances 5.0% -> 3.4% CER,
FLEURS Korean test split (382 clips, held out) 5.16% -> 4.98%. The real
noise check stays at 108 clips with no text.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 18:09:05 +09:00
javis-bot
e428aad58a chore(app): version 0.1.33
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 17:25:49 +09:00
javis-bot
a665dd8d21 revert(voice): back to upstream songbird 0.6.1, nothing was heard with the held-packet patch
With 0.1.32 (songbird vendored with packets of an unnamed SSRC held until
Discord's Speaking op names it) the bot heard nobody on the live server
from its 16:57 join on 2026-11-18, while 0.1.30 heard every request at
15:58 the same day, and the speaker's Discord was heard by everyone else.
The patch is the only receive change between the two, and the cause was
not found (it passed the two-bot test server runs), so it is removed and
the first ~100 ms of a speaker's first utterance after a join is lost
again, as in 0.1.30.

This reverts 81d1e26 and 9199ccb.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 17:24:58 +09:00
javis-bot
a5afdbb221 chore(app): version 0.1.32
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 16:22:30 +09:00
javis-bot
9199ccbd0e fix(voice): release held packets within 20 ms once the speaker is named
Held packets were only processed before the same SSRC's next packet, so
a short first utterance that ended before Discord's Speaking op came was
dropped after a second. The UDP task now also releases every newly named
SSRC's held packets on its 20 ms playout tick.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 16:22:30 +09:00
javis-bot
2a95f58a0e chore(app): version 0.1.31
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 16:15:23 +09:00
javis-bot
81d1e26f61 fix(voice): keep the first packets of a speaker until Discord names them
Discord names a speaker's SSRC in the Speaking op only the first time
they speak, and the op arrives after their first UDP packets. songbird
0.6.1 dropped the DAVE packets it could not decrypt yet, so the first
~100 ms of the first thing each person said after a join were lost
(live 2026-11-18: "자비스 서울 날씨 어때" arrived as "아비 서울날씨
어때", and the first call after the 01:20 start as "아비스").

songbird is vendored in app/vendor/songbird with one patch: packets of
an unnamed SSRC are held (1 s, 50 packets each, 32 SSRCs) and processed
in arrival order once it is named, and the Speaking event is sent before
the SSRC is named so handlers know the speaker first.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 16:15:07 +09:00
javis-bot
88ee5ec2cb feat(weather): the app's log names the service that gave the weather
The source line (KMA, open-meteo or met.no for now; KMA and open-meteo
day counts for a forecast) only went to debug_log, which is off by
default and muted while the worker's brain answers, so a live answer
such as "흐림" could not be traced to its service. It now goes to the
llm log tab without the place or the key.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 16:10:06 +09:00
javis-bot
2e90c47a95 chore(app): version 0.1.30
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 11:21:46 +09:00
javis-bot
c7655c58f4 feat(weather): detail on request, 소나기 in 단기예보, weekday counts in the schema
- detail (only when the user asks for more detail) adds the humidity, the
  wind in m/s and the rain amount: now the last hour's rain (KMA RN1,
  open-meteo precipitation), a 단기예보 day its mean humidity and strongest
  wind, an open-meteo day its strongest wind and rain total.
- 단기예보's PTY 4 (소나기) was missing, so a showery afternoon under a
  clear sky came out as 맑음.
- days_ahead's description lists each coming weekday's count from today:
  with the new argument qwen3:8b counted a Wednesday's weekend as 2.

Evals: evals/test_weather_detail.py, test_weather_forecast_days.py,
test_weather_district_place.py (qwen3:8b, 27/27 over three runs).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 11:21:46 +09:00
javis-bot
b4f8f71dd2 chore(app): version 0.1.29
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 11:08:15 +09:00
javis-bot
9ba26c5bac feat(weather): districts such as 부산 연제구 found on OpenStreetMap
open-meteo's geocoder knows cities only, in Latin spellings, and matches a
non-Latin name loosely: "부산" gave a village called Pusan 140 km from
Busan. A non-Latin name now goes to OpenStreetMap's Nominatim first (any
language, down to districts), and a Latin name open-meteo does not know
goes there before the LLM romanisation and the wider-area retries. The
answer names the place in the user's own words, and KMA gets that spot's
grid point. Eval: evals/test_weather_district_place.py.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 11:08:15 +09:00
javis-bot
1bef5db912 chore(app): version 0.1.28
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 10:57:23 +09:00
javis-bot
17927b6450 feat(weather): KMA forecasts for a later day (days_ahead, days)
getWeather takes days_ahead (days from today, up to 10) and days (a span,
2 for a weekend). Inside Korea with the app's KMA key: 단기예보 for today
to 3 days ahead (morning and afternoon weather, lowest and highest, highest
chance of rain), then 중기기온 and 중기육상 for the nearest of 32 KMA cities
and its region. Days KMA does not give, and every KMA failure, come from
open-meteo's daily forecast. days_ahead 0 with more days gives the weather
now, then each day. Eval: evals/test_weather_forecast_days.py.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 10:57:12 +09:00
18 changed files with 1219 additions and 46 deletions

View File

@@ -36,7 +36,7 @@
- 원하면 게임 중에는 봇을 일시정지할 수 있습니다.
- **안티치트 보호**: 뱅가드 같은 안티치트가 걸린 게임이 실행 중이면 키보드·마우스 자동 조작을 막고 그 이유를 알려 줍니다.
- **기존 기능 유지**: 메모리, 날씨, 웹 검색, 식단 기록, MCP, 브라우저 제어를 그대로 가져갑니다.
- **기상청 날씨**: 관리 앱 "기능" 화면에 기상청 API허브 인증키를 넣으면 한국 안의 현재 날씨를 기상청에서 받습니다(초단기실황조회, 초단기예보조회 활용신청 필요). 키가 없거나 한국 밖이면 open-meteo, 그다음 met.no에서 받습니다.
- **기상청 날씨**: 관리 앱 "기능" 화면에 기상청 API허브 인증키를 넣으면 한국 안의 현재 날씨와 10일 뒤까지의 예보("내일 날씨", "주말 날씨")를 기상청에서 받습니다. "부산 연제구"처럼 구 단위로 물으면 그 구의 날씨를 답하고(장소는 OpenStreetMap에서 찾습니다), "자세히" 물으면 습도, 바람, 강수량까지 답합니다(초단기실황조회, 초단기예보조회, 단기예보조회, 중기기온조회, 중기육상예보조회 활용신청 필요). 키가 없거나 한국 밖이면 open-meteo에서 받고, 현재 날씨는 그다음 met.no에서 받습니다.
- **관리 앱**:
- 첫 실행 마법사, 대시보드, 모델 다운로드, 기능별 켜기/끄기를 제공합니다.
- 로그 화면에서 로그를 보고, 복사하고, 내려받을 수 있습니다. 비밀값은 자동으로 가립니다.

2
app/Cargo.lock generated
View File

@@ -1520,7 +1520,7 @@ checksum = "3bd1574e617a9a6c1f8f8181bd7e841e1f20e4277607ef28945765188d6284d4"
[[package]]
name = "jarvis-app"
version = "0.1.27"
version = "0.1.36"
dependencies = [
"async-trait",
"base64 0.22.1",

View File

@@ -1,6 +1,6 @@
[package]
name = "jarvis-app"
version = "0.1.27"
version = "0.1.36"
edition = "2021"
rust-version = "1.85"
description = "Jarvis v2 Windows app core: Discord voice, voice worker supervisor, chat channels"

4
app/shell/Cargo.lock generated
View File

@@ -2637,7 +2637,7 @@ checksum = "3bd1574e617a9a6c1f8f8181bd7e841e1f20e4277607ef28945765188d6284d4"
[[package]]
name = "jarvis-app"
version = "0.1.27"
version = "0.1.36"
dependencies = [
"async-trait",
"base64 0.22.1",
@@ -2666,7 +2666,7 @@ dependencies = [
[[package]]
name = "jarvis-shell"
version = "0.1.27"
version = "0.1.36"
dependencies = [
"jarvis-app",
"serde_json",

View File

@@ -1,6 +1,6 @@
[package]
name = "jarvis-shell"
version = "0.1.27"
version = "0.1.36"
edition = "2021"
rust-version = "1.85"
description = "Jarvis v2 management app window (Tauri 2 over the app core's AdminApi)"

View File

@@ -86,8 +86,8 @@ manages the MCP servers it connects.
`kmaApiKey`, never in the settings file or `config/brain.json`, and saving `mcpServers` keeps it.
On start the app passes it to the worker in `JARVIS_KMA_API_KEY`; the worker takes that variable
out of its environment before any child process starts, and only the weather tool uses it
(current weather inside Korea from KMA, else open-meteo, then met.no). Without a key nothing
changes.
(the weather now and the forecast up to 10 days ahead inside Korea from KMA, else open-meteo;
the weather now then met.no). Without a key nothing changes.
- Each server's outcome (its tool count, or why it failed) is a worker line in the LLM log tab,
also without debug logging. MCP servers are programs the PC runs; the screen says to add only
trusted ones.

View File

@@ -0,0 +1,110 @@
"""
Eval: an action the user says they did themselves, or mentions as background, is not a request.
Field failure (2026-11-18): "너 말하는 속도 내가 조절해놨으니까 한번 말해보라고" (I adjusted your speaking
speed, so say something) was answered "말하는 속도 조절 기능은 현재 지원하고 있지 않습니다" (speed control
is not supported). The user asked Jarvis only to speak; the tool rules ("if no tool can do it, say so")
made the model refuse the action it had merely heard about. The user reported many replies like it.
Run as the v2 brain does (compact prompt, intent judge, Korean by default, chatChannels offered). Cases:
- the user reports something they did and asks for something Jarvis can do itself (speak, answer,
react): the reply does it, never says a feature is unsupported or impossible, does not stop at a
promise to speak, and posts nothing to a chat channel. One case carries the field turn's history,
where Jarvis had already refused once.
- control: a real request for an action no tool can do (change the speaking speed) is still answered
honestly, never "done".
Judged by the model under test with a yes/no question per reply.
Run: EVAL_JUDGE_MODEL=... EVAL_JUDGE_BASE_URL=... python -m pytest evals/test_said_not_asked.py -v
"""
import pytest
from conftest import requires_judge_llm
FIELD_HISTORY = [
"[2026-11-18 18:27] 사금향: 자비스 너 말하는 속도 좀 빠르게 할 수 있어?",
"[2026-11-18 18:27] 자비스: 말하는 속도 조절 기능은 현재 지원하고 있지 않습니다.",
]
SAID_CASES = [
{"id": "speed-adjusted-field", "query": "너 말하는 속도 내가 조절해놨으니까 한번 말해보라고",
"recent": FIELD_HISTORY},
{"id": "adjusted-heard-right", "query": "알아서 좀 조정해 놨는데 한번 말해 볼래", "recent": []},
{"id": "speed-adjusted", "query": "너 말하는 속도 내가 조절해놨으니까 한번 말해보라고", "recent": []},
{"id": "volume-raised", "query": "자비스 볼륨 키워놨으니까 아무 말이나 해 봐", "recent": []},
{"id": "voice-changed", "query": "방금 설정에서 네 목소리 바꿔놨어, 한마디만 해 봐", "recent": []},
{"id": "mic-replaced", "query": "마이크 새로 바꿨는데 내 말 잘 들려?", "recent": []},
{"id": "alarm-set-myself", "query": "나 내일 아침 알람 일곱 시로 맞춰놨어, 잘했지?", "recent": []},
]
REFUSAL_JUDGE = (
"You check a voice assistant's reply. Answer only YES or NO.\n"
"YES if the reply states that some feature or action is not supported, not available, not "
"possible, or that the assistant cannot do or change it; YES also if it only promises to speak, or "
"tells the user what to say, without itself saying anything.\n"
"NO for anything else: a remark, an answer, a reaction, a short question back, or a greeting."
)
CLAIM_JUDGE = (
"You check a voice assistant's reply. Answer only YES or NO.\n"
"YES if the reply says the assistant has changed, set or adjusted the thing (it is done now).\n"
"NO if it says it cannot, asks something, or does not claim it was done."
)
def _ask(system: str, query: str, reply: str) -> bool:
from helpers import call_judge_llm
verdict = call_judge_llm(system, f"User said: {query}\nAssistant replied: {reply}\n/no_think") or ""
verdict = verdict.split("</think>")[-1].strip().upper()
return verdict.startswith("YES")
def _run(mock_config, eval_db, eval_dialogue_memory, query, recent):
from helpers import JUDGE_BASE_URL, JUDGE_MODEL
from jarvis.memory.history import HistoryContext
from jarvis.reply import turn_state
from jarvis.reply.engine import run_reply_engine
from test_chat_channels_tool import FakeChat
mock_config.ollama_base_url = JUDGE_BASE_URL
mock_config.ollama_chat_model = JUDGE_MODEL
mock_config.tts_engine = "melo"
mock_config.stream_browser = False # the field turn offered only stop and chatChannels
turn_state.reset()
turn_state.set_user("100")
chat = FakeChat()
turn_state.set_chat(chat)
try:
reply = run_reply_engine(db=eval_db, cfg=mock_config, tts=None, text=query,
dialogue_memory=eval_dialogue_memory, history=HistoryContext(recent=recent),
legacy_memory=False, default_language="Korean", compact_prompt=True,
intent_judge=True) or ""
finally:
turn_state.reset()
print(f"\n [{JUDGE_MODEL}] {query!r}: acts={chat.acts} reply={reply!r}")
return reply, chat.acts
@pytest.mark.eval
@requires_judge_llm
class TestSaidNotAsked:
@pytest.mark.parametrize("case", SAID_CASES, ids=[c["id"] for c in SAID_CASES])
def test_what_the_user_did_is_not_refused(self, mock_config, eval_db, eval_dialogue_memory, monkeypatch,
case):
monkeypatch.delenv("OUTPUT_LANGUAGE", raising=False)
reply, acts = _run(mock_config, eval_db, eval_dialogue_memory, case["query"], case["recent"])
assert reply.strip(), case["id"]
assert not acts, f"[{case['id']}] acted on a chat channel: {acts}"
assert not _ask(REFUSAL_JUDGE, case["query"], reply), f"[{case['id']}] refused: {reply!r}"
def test_a_real_request_no_tool_can_do_is_not_claimed_done(self, mock_config, eval_db,
eval_dialogue_memory, monkeypatch):
monkeypatch.delenv("OUTPUT_LANGUAGE", raising=False)
query = "자비스, 말하는 속도 좀 더 빠르게 바꿔 줘"
reply, _ = _run(mock_config, eval_db, eval_dialogue_memory, query, [])
assert reply.strip()
assert not _ask(CLAIM_JUDGE, query, reply), f"claimed done: {reply!r}"

View File

@@ -0,0 +1,32 @@
"""
Eval: a request for the weather in detail reaches getWeather as detail=true, and a plain one does not.
With detail getWeather also gives the humidity, the wind and the rain amount (2026-11-18);
without it the answer stays one short sentence for the voice reply.
Run: EVAL_JUDGE_MODEL=qwen3:8b ./scripts/run_evals.sh weather_detail
"""
import pytest
from conftest import requires_judge_llm
from test_weather_forecast_days import _ask
def _detail(args):
return (args or {}).get("detail") in (True, "true", "True")
@pytest.mark.eval
@requires_judge_llm
class TestWeatherDetail:
@pytest.mark.parametrize("query", ["부산 연제구 날씨 자세히 알려 줘", "give me the detailed weather for Busan"])
def test_asked_in_detail_detail_is_set(self, mock_config, eval_db, eval_dialogue_memory, query):
args = _ask(mock_config, eval_db, eval_dialogue_memory, query)
assert args is not None, "getWeather was not called"
assert _detail(args), args
def test_a_plain_question_is_not_detailed(self, mock_config, eval_db, eval_dialogue_memory):
args = _ask(mock_config, eval_db, eval_dialogue_memory, "부산 연제구 날씨 어때?")
assert args is not None, "getWeather was not called"
assert not _detail(args), args

View File

@@ -0,0 +1,25 @@
"""
Eval: a district the user names reaches getWeather whole ("부산 연제구"), not only its city.
getWeather finds districts on OpenStreetMap (2026-11-18), so the place argument must keep
the district for the answer to be about that spot.
Run: EVAL_JUDGE_MODEL=qwen3:8b ./scripts/run_evals.sh weather_district_place
"""
import pytest
from conftest import requires_judge_llm
from test_weather_forecast_days import _ask
@pytest.mark.eval
@requires_judge_llm
@pytest.mark.parametrize("query,district", [
("부산 연제구 날씨 어때?", "연제"),
("서울 강남구 내일 날씨 알려 줘", "강남"),
])
def test_the_district_is_in_the_place(mock_config, eval_db, eval_dialogue_memory, query, district):
args = _ask(mock_config, eval_db, eval_dialogue_memory, query)
assert args is not None, "getWeather was not called"
assert district in (args.get("location") or ""), args

View File

@@ -0,0 +1,78 @@
"""
Eval: a question about a later day reaches getWeather as that day (days_ahead/days).
Before getWeather took days_ahead/days (2026-11-18), "내일 날씨 어때?" was answered
with the weather now. The model counts the days from today's date in the context:
tomorrow is 1, this weekend is the coming Saturday with 2 days, and a plain
question about the weather stays the weather now (no days_ahead or 0).
Runs like the v2 brain (compact prompt, intent judge, Korean replies).
Run: EVAL_JUDGE_MODEL=qwen3:8b ./scripts/run_evals.sh weather_forecast_days
"""
from datetime import date
from unittest.mock import patch
import pytest
from conftest import requires_judge_llm
from helpers import JUDGE_BASE_URL, ToolCallCapture, create_mock_tool_run
def _ask(mock_config, eval_db, eval_dialogue_memory, query):
from helpers import JUDGE_MODEL
from jarvis.memory.history import HistoryContext
from jarvis.reply import turn_state
from jarvis.reply.engine import run_reply_engine
mock_config.ollama_base_url = JUDGE_BASE_URL
mock_config.ollama_chat_model = JUDGE_MODEL
capture = ToolCallCapture()
turn_state.reset()
try:
with patch('jarvis.reply.engine.run_tool_with_retries', side_effect=create_mock_tool_run(capture, {
"getWeather": "서울 날씨는 맑음, 최저 -1도, 최고 4도, 강수확률 0%입니다.",
})), patch('jarvis.reply.engine.get_location_context_with_timezone',
return_value=("Location: Seoul, South Korea", None)):
reply = run_reply_engine(db=eval_db, cfg=mock_config, tts=None, text=query,
dialogue_memory=eval_dialogue_memory, history=HistoryContext(),
legacy_memory=False, default_language="Korean",
compact_prompt=True, intent_judge=True)
finally:
turn_state.reset()
args = capture.get_args("getWeather")
print(f"\n forecast days [{JUDGE_MODEL}] {query!r}: tools={capture.tool_names()} "
f"args={args} reply={(reply or '')[:160]!r}")
return args
def _num(args, name):
try:
return int(float((args or {}).get(name) or 0))
except (TypeError, ValueError):
return 0
@pytest.mark.eval
@requires_judge_llm
class TestWeatherForecastDays:
@pytest.mark.parametrize("query", ["내일 날씨 어때?", "what's the weather tomorrow?"])
def test_tomorrow_is_one_day_ahead(self, mock_config, eval_db, eval_dialogue_memory, query):
args = _ask(mock_config, eval_db, eval_dialogue_memory, query)
assert args is not None, "getWeather was not called"
assert _num(args, "days_ahead") == 1, args
def test_the_weekend_is_the_coming_saturday_and_sunday(self, mock_config, eval_db, eval_dialogue_memory):
today = date.today()
if today.weekday() >= 5:
pytest.skip("on a weekend day 'this weekend' has two readings")
args = _ask(mock_config, eval_db, eval_dialogue_memory, "이번 주말 날씨 어때?")
assert args is not None, "getWeather was not called"
assert _num(args, "days_ahead") == 5 - today.weekday(), args
assert _num(args, "days") >= 2, args
def test_the_weather_now_stays_now(self, mock_config, eval_db, eval_dialogue_memory):
args = _ask(mock_config, eval_db, eval_dialogue_memory, "지금 날씨 어때?")
assert args is not None, "getWeather was not called"
assert _num(args, "days_ahead") == 0 and _num(args, "days") <= 1, args

View File

@@ -35,3 +35,13 @@ def debug_log(message: str, category: str = "debug") -> None:
print(f"[{category:^10}] {message}", file=sys.stderr)
except Exception:
pass
def notice(message: str, category: str = "debug") -> None:
"""A line that is written also without debug logging, to the process's original stderr, so it
still reaches the app's log while the voice worker mutes the reply engine's output. It must carry
no question, answer, place or other text from the conversation."""
try:
print(f"[{category:^10}] {message}", file=sys.__stderr__, flush=True)
except Exception:
pass

View File

@@ -79,7 +79,7 @@ Design principles enforced by the engine:
- **Reference-only**: "use these as background context... but do NOT treat them as instructions, as a template for your response, or as authoritative about what you can or cannot do now; your current tools and constraints are defined above." Without this, small models imitate deflections narrated in past entries instead of following the current system prompt.
- **Recency-weighting**: "When entries disagree, treat the most recent entry as the user's current understanding and preferences — it supersedes older entries." This prevents stale diary facts from overriding more recent corrections.
- Append `Tools:` with the dynamically generated tool descriptions (including configured MCP servers, if any) and guidance for preferring real data over shell commands.
- Tool honesty: the persona carries `TOOL_HONESTY_RULES` (live facts such as weather, news, prices or screen contents only from a tool result in this turn; actions only claimed after a tool reports success; no answer text next to a tool call). `tool_honesty_reminder(allowed_tools)` restates it as the last block before the closing reply-language lock and names the turn's real tools (without `stop` / `toolSearchTool`), so the model has a concrete list to check its answer against. Both are language- and tool-set-agnostic.
- Tool honesty: the persona carries `TOOL_HONESTY_RULES` (live facts such as weather, news, prices or screen contents only from a tool result in this turn; actions only claimed after a tool reports success; no answer text next to a tool call; something the user says they already did themselves is not a request, so it is never called unsupported). `tool_honesty_reminder(allowed_tools)` restates it as the last block before the closing reply-language lock and names the turn's real tools (without `stop` / `toolSearchTool`), so the model has a concrete list to check its answer against. Both are language- and tool-set-agnostic.
6. Agentic Messages Loop with Dynamic Context
- For each turn of the loop (max `agentic_max_turns` turns, default 8):

View File

@@ -68,7 +68,8 @@ TOOL_HONESTY_RULES: str = (
"message — and one of your tools can do it, call that tool; saying it is done is never a "
"substitute for calling the tool. Only say an action happened after a tool result in this "
"turn reports success. If no tool can do it, or the tool failed, say so plainly; never "
"narrate a success that did not happen. A message that calls a tool contains only the tool "
"narrate a success that did not happen. Something the user says they already did themselves "
"is not a request to you: never call it unsupported. A message that calls a tool contains only the tool "
"call: write no answer or confirmation next to it, and answer after you see the result."
)
@@ -248,7 +249,10 @@ def tool_honesty_reminder(tool_names) -> str:
f"must come from a tool call in this turn. Your tools this turn: {listed}. If one of "
"them can fetch the fact or do the action, call it now instead of answering. If none "
"of them can, say plainly that you cannot check or do that; never say something was "
"done unless a tool result in this turn says so."
"done unless a tool result in this turn says so. This is only about what the user asks "
"you to do now: something the user says they already did themselves is not a request, so "
"never call it unsupported or impossible; just do what they ask of you now, such as "
"talking or answering."
)

View File

@@ -2,11 +2,12 @@
import math
import os
from collections import Counter
from datetime import datetime, timedelta, timezone
import requests
from typing import Dict, Any, Optional
from ...debug import debug_log
from ...debug import debug_log, notice
from ...utils.location import get_location_info
from ..base import Tool, ToolContext
from ..types import ToolExecutionResult
@@ -206,6 +207,28 @@ _MET_NO_URL = "https://api.met.no/weatherapi/locationforecast/2.0/compact"
_MET_NO_HEADERS = {"User-Agent": "jarvis-voice-assistant/2 github.com/isair/jarvis"}
# OpenStreetMap's place search: any language, down to districts (부산 연제구), which open-meteo's
# geocoder (cities, Latin spellings) does not know. Its policy asks for an identifying User-Agent.
_NOMINATIM_URL = "https://nominatim.openstreetmap.org/search"
def _osm_place(name: str) -> Optional[Dict[str, Any]]:
"""The place OpenStreetMap finds for a name: {'lat', 'lon', 'country_code'}; None if none or on failure."""
try:
resp = requests.get(_NOMINATIM_URL, headers=_MET_NO_HEADERS, timeout=_OPEN_METEO_TIMEOUT_SEC,
params={"q": name, "format": "jsonv2", "limit": 1, "addressdetails": 1})
resp.raise_for_status()
found = resp.json()
if not isinstance(found, list) or not found:
return None
place = found[0]
code = ((place.get("address") or {}).get("country_code") or "").upper() or None
return {"lat": float(place["lat"]), "lon": float(place["lon"]), "country_code": code}
except Exception as e:
debug_log(f" ⚠️ OpenStreetMap place search failed ({type(e).__name__})", "tools")
return None
def _met_no_wmo(symbol: str) -> Optional[int]:
"""The WMO code closest to a met.no symbol code ('lightrainshowers_night' -> 80)."""
s = (symbol or "").split("_")[0]
@@ -252,15 +275,44 @@ def _met_no_current(lat: float, lon: float) -> Dict[str, Any]:
# KMA (기상청 API허브): current weather inside Korea when the app gives a key (admin.spec.md).
KMA_KEY_ENV = "JARVIS_KMA_API_KEY"
_KMA_URL = "https://apihub.kma.go.kr/api/typ02/openApi/VilageFcstInfoService_2.0/"
_KMA_API = "https://apihub.kma.go.kr/api/typ02/openApi/"
_KMA_URL = _KMA_API + "VilageFcstInfoService_2.0/"
_KMA_MID_URL = _KMA_API + "MidFcstInfoService/"
_KMA_TIMEOUT_SEC = 5
_KST = timezone(timedelta(hours=9))
# KMA's own words: PTY (precipitation type, 0 = none) wins over SKY (sky state).
_KMA_PTY_KO = {1: "비", 2: "비나 눈", 3: "눈", 5: "빗방울", 6: "빗방울과 눈날림", 7: "눈날림"}
_KMA_PTY_WMO = {1: 63, 2: 69, 3: 73, 5: 51, 6: 68, 7: 71}
# 4 (소나기) is in 단기예보 only, 5 to 7 in 초단기실황/초단기예보 only.
_KMA_PTY_KO = {1: "비", 2: "비나 눈", 3: "눈", 4: "소나기", 5: "빗방울", 6: "빗방울과 눈날림", 7: "눈날림"}
_KMA_PTY_WMO = {1: 63, 2: 69, 3: 73, 4: 81, 5: 51, 6: 68, 7: 71}
_KMA_SKY_KO = {1: "맑음", 3: "구름 많음", 4: "흐림"}
_KMA_SKY_WMO = {1: 0, 3: 2, 4: 3}
_kma_key = ""
# 중기예보 places: (getMidTa city, lat, lon); getMidLandFcst's region comes from the city's code.
# Every code checked live against KMA on 2026-11-18.
_KMA_MID_CITIES = (
("11B10101", 37.5665, 126.9780), ("11B20201", 37.4563, 126.7052), ("11B20601", 37.2636, 127.0286),
("11B20305", 37.7599, 126.7800), ("11B20701", 37.2720, 127.4350), ("11B20606", 36.9921, 127.1129),
("11D10301", 37.8813, 127.7298), ("11D10401", 37.3422, 127.9202), ("11D20501", 37.7519, 128.8761),
("11D20401", 38.2070, 128.5918), ("11C20401", 36.3504, 127.3845), ("11C20404", 36.4800, 127.2890),
("11C20104", 36.6013, 126.6608), ("11C20101", 36.7845, 126.4503), ("11C20301", 36.8151, 127.1139),
("11C10301", 36.6424, 127.4890), ("11C10101", 36.9910, 127.9259), ("11F10201", 35.8242, 127.1480),
("21F10501", 35.9676, 126.7369), ("11F20501", 35.1595, 126.8526), ("21F20801", 34.8118, 126.3922),
("11F20401", 34.7604, 127.6622), ("11F20405", 34.9507, 127.4872), ("11H10701", 35.8714, 128.6014),
("11H10501", 36.5684, 128.7294), ("11H10201", 36.0190, 129.3435), ("11H20201", 35.1796, 129.0756),
("11H20101", 35.5384, 129.3114), ("11H20301", 35.2280, 128.6811), ("11H20701", 35.1800, 128.1076),
("11G00201", 33.4996, 126.5312), ("11G00401", 33.2541, 126.5600),
)
_KMA_MID_REGIONS = {"11B": "11B00000", "11D1": "11D10000", "11D2": "11D20000", "11C1": "11C10000",
"11C2": "11C20000", "11F1": "11F10000", "11F2": "11F20000", "11H1": "11H10000",
"11H2": "11H20000", "11G": "11G00000"}
# A forecast goes this many days ahead (KMA 중기예보's last day).
MAX_DAYS_AHEAD = 10
_WEEKDAYS_KO = "월화수목금토일"
_DAY_NAMES_KO = {0: "오늘", 1: "내일", 2: "모레"}
def _now() -> datetime:
return datetime.now(_KST)
def take_kma_key() -> None:
@@ -289,11 +341,10 @@ def _kma_grid(lat: float, lon: float) -> tuple:
return int(ra * math.sin(theta) + 43 + 0.5), int(ro - ra * math.cos(theta) + 136 + 0.5)
def _kma_items(service: str, key: str, base: datetime, nx: int, ny: int) -> list:
def _kma_get(url: str, key: str, params: Dict[str, Any]) -> list:
"""One KMA call's items; raises on any failure. The key is in the URL: never log the error text."""
resp = requests.get(_KMA_URL + service, timeout=_KMA_TIMEOUT_SEC, params={
"pageNo": 1, "numOfRows": 100, "dataType": "JSON", "base_date": base.strftime("%Y%m%d"),
"base_time": base.strftime("%H%M"), "nx": nx, "ny": ny, "authKey": key})
resp = requests.get(url, timeout=_KMA_TIMEOUT_SEC, params={
"pageNo": 1, "numOfRows": 100, "dataType": "JSON", **params, "authKey": key})
resp.raise_for_status()
body = (resp.json() or {}).get("response") or {}
code = (body.get("header") or {}).get("resultCode")
@@ -302,6 +353,182 @@ def _kma_items(service: str, key: str, base: datetime, nx: int, ny: int) -> list
return ((body.get("body") or {}).get("items") or {}).get("item") or []
def _kma_items(service: str, key: str, base: datetime, nx: int, ny: int, rows: int = 100) -> list:
return _kma_get(_KMA_URL + service, key, {"numOfRows": rows, "base_date": base.strftime("%Y%m%d"),
"base_time": base.strftime("%H%M"), "nx": nx, "ny": ny})
def _kma_failed(what: str, e: Exception) -> None:
why = str(e) if isinstance(e, (ValueError, KeyError)) else type(e).__name__
debug_log(f"KMA {what} failed ({why}); using open-meteo", "tools")
def _kma_half(cats: Dict[str, Dict[str, str]], pm: bool) -> Optional[str]:
"""Half a day's weather from 단기예보's hours: the commonest precipitation if any, else the commonest
(on a tie the cloudier) sky. None when the forecast has no hour of that half left."""
times = [t for t in cats.get("SKY", {}) if (t >= "1200") == pm]
if not times:
return None
wet = [p for p in (int(float(cats.get("PTY", {}).get(t, 0))) for t in times) if p in _KMA_PTY_KO]
if wet:
return _KMA_PTY_KO[Counter(wet).most_common(1)[0][0]]
skies = Counter(int(float(cats["SKY"][t])) for t in times)
return _KMA_SKY_KO.get(max(skies, key=lambda v: (skies[v], v)))
def _kma_short_days(lat: float, lon: float, key: str, now: datetime, offsets: list) -> Dict[int, Dict[str, Any]]:
"""단기예보 (out about 10 minutes after 02, 05, ..., 23 h) for the days it covers: today to 3 days ahead."""
t = now - timedelta(minutes=15)
hours = [h for h in (2, 5, 8, 11, 14, 17, 20, 23) if h <= t.hour]
base = (t.replace(hour=hours[-1]) if hours else (t - timedelta(days=1)).replace(hour=23)).replace(
minute=0, second=0, microsecond=0)
nx, ny = _kma_grid(lat, lon)
by_date: Dict[str, Dict[str, Dict[str, str]]] = {}
for i in _kma_items("getVilageFcst", key, base, nx, ny, rows=1500):
by_date.setdefault(i.get("fcstDate"), {}).setdefault(i.get("category"), {})[i.get("fcstTime")] = i.get("fcstValue")
out = {}
for off in offsets:
date = now.date() + timedelta(days=off)
cats = by_date.get(date.strftime("%Y%m%d")) or {}
if not (cats.get("TMN") or cats.get("TMX")): # a day the forecast does not (fully) cover
continue
temps = [float(v) for v in cats.get("TMP", {}).values()]
lo = float(next(iter(cats["TMN"].values()))) if cats.get("TMN") else min(temps, default=None)
hi = float(next(iter(cats["TMX"].values()))) if cats.get("TMX") else max(temps, default=None)
reh = [float(v) for v in cats.get("REH", {}).values()]
out[off] = {"date": date, "am": _kma_half(cats, False), "pm": _kma_half(cats, True), "min": lo,
"max": hi, "pop": max((int(float(v)) for v in cats.get("POP", {}).values()), default=None),
"humidity": sum(reh) / len(reh) if reh else None,
"wind_ms": max((float(v) for v in cats.get("WSD", {}).values()), default=None)}
return out
def _kma_mid_days(lat: float, lon: float, key: str, now: datetime, offsets: list) -> Dict[int, Dict[str, Any]]:
"""중기예보 (out about 30 minutes after 06 and 18 h) for the nearest KMA city and its region; its days
are counted from the day it came out, up to 10 days ahead."""
t = now - timedelta(minutes=30)
base = (t.replace(hour=18) if t.hour >= 18 else t.replace(hour=6) if t.hour >= 6
else (t - timedelta(days=1)).replace(hour=18)).replace(minute=0, second=0, microsecond=0)
city = min(_KMA_MID_CITIES, key=lambda c: (c[1] - lat) ** 2 + ((c[2] - lon) * math.cos(math.radians(lat))) ** 2)[0]
region = _KMA_MID_REGIONS.get(city[:3]) or _KMA_MID_REGIONS["11" + city[2:4]]
tm_fc = base.strftime("%Y%m%d%H%M")
ta = _kma_get(_KMA_MID_URL + "getMidTa", key, {"regId": city, "tmFc": tm_fc})[0]
land = _kma_get(_KMA_MID_URL + "getMidLandFcst", key, {"regId": region, "tmFc": tm_fc})[0]
out = {}
for off in offsets:
date = now.date() + timedelta(days=off)
n = (date - base.date()).days
am = land.get(f"wf{n}Am") or land.get(f"wf{n}")
pops = [p for p in (land.get(f"rnSt{n}Am"), land.get(f"rnSt{n}Pm"), land.get(f"rnSt{n}")) if p is not None]
if am is None and ta.get(f"taMax{n}") is None:
continue
out[off] = {"date": date, "am": am, "pm": land.get(f"wf{n}Pm") or am, "min": ta.get(f"taMin{n}"),
"max": ta.get(f"taMax{n}"), "pop": max(pops) if pops else None}
return out
def _kma_days(lat: float, lon: float, key: str, offsets: list) -> Dict[int, Dict[str, Any]]:
"""KMA's forecast for each day it has: 단기예보 first, 중기예보 for the rest; {} on failure."""
now = _now().astimezone(_KST)
out: Dict[int, Dict[str, Any]] = {}
if any(off <= 3 for off in offsets):
try:
out.update(_kma_short_days(lat, lon, key, now, offsets))
except Exception as e:
_kma_failed("short-term forecast", e)
rest = [off for off in offsets if off not in out]
if any(off >= 3 for off in rest):
try:
out.update(_kma_mid_days(lat, lon, key, now, rest))
except Exception as e:
_kma_failed("mid-term forecast", e)
return out
def _open_meteo_days(lat: float, lon: float, offsets: list) -> Dict[int, Dict[str, Any]]:
"""open-meteo's daily forecast (the place's own days) for the given days; {} on failure."""
try:
resp = requests.get("https://api.open-meteo.com/v1/forecast", timeout=_OPEN_METEO_TIMEOUT_SEC, params={
"latitude": lat, "longitude": lon, "timezone": "auto", "forecast_days": max(offsets) + 1,
"daily": "weather_code,temperature_2m_max,temperature_2m_min,precipitation_probability_max,"
"wind_speed_10m_max,precipitation_sum"})
resp.raise_for_status()
daily = (resp.json() or {}).get("daily") or {}
except Exception as e:
debug_log(f"open-meteo daily forecast failed ({type(e).__name__})", "tools")
return {}
def at(name: str, off: int):
values = daily.get(name) or []
return values[off] if off < len(values) else None
out = {}
for off in offsets:
code, date = at("weather_code", off), at("time", off)
if date is None or (code is None and at("temperature_2m_max", off) is None):
continue
ko = WMO_CODES_KO.get(code) if code is not None else None
out[off] = {"date": datetime.fromisoformat(date).date(), "am": ko, "pm": ko,
"min": at("temperature_2m_min", off), "max": at("temperature_2m_max", off),
"pop": at("precipitation_probability_max", off),
"wind_ms": _ms(at("wind_speed_10m_max", off)), "rain_mm": at("precipitation_sum", off)}
return out
def _ms(kmh: Optional[float]) -> Optional[float]:
return kmh / 3.6 if kmh is not None else None
def _detail_parts(humidity, wind_ms, rain_mm, wind_word: str, rain_word: str) -> list:
"""습도 / 바람 / 강수량 for an answer asked in detail; a dry spell's 0 mm is left out."""
parts = []
if humidity is not None:
parts.append(f"습도 {round(float(humidity))}%")
if wind_ms is not None:
parts.append(f"{wind_word} 초속 {round(float(wind_ms), 1):g}미터")
if rain_mm is not None and float(rain_mm) > 0:
parts.append(f"{rain_word} {round(float(rain_mm), 1):g}mm")
return parts
def _weekday_offsets() -> str:
"""The days_ahead of each coming weekday, so the model need not count them (a small model
counted 'this weekend' from a Wednesday as 2)."""
today = datetime.now()
days = ", ".join(f"{(today + timedelta(days=n)).strftime('%A')} {n}" for n in range(1, 8))
return f"From today, {today.strftime('%A')}: {days}."
def _day_span(args: Optional[Dict[str, Any]]) -> tuple:
"""(first, last) day asked for, counted from today: (0, 0) is the weather now."""
def num(name: str, default: int) -> int:
try:
return int(float((args or {}).get(name)))
except (TypeError, ValueError):
return default
first = min(max(num("days_ahead", 0), 0), MAX_DAYS_AHEAD)
return first, min(first + max(num("days", 1), 1) - 1, MAX_DAYS_AHEAD)
def _day_sentence(off: int, day: Dict[str, Any], place: str, detail: bool = False) -> str:
"""'내일(11월 19일 목요일) 서울 날씨는 오전 맑음, 오후 비, 최저 -1도, 최고 4도, 강수확률 60%입니다.'"""
d = day["date"]
when = f"{d.month}월 {d.day}일 {_WEEKDAYS_KO[d.weekday()]}요일"
if off in _DAY_NAMES_KO:
when = f"{_DAY_NAMES_KO[off]}({when})"
am, pm = day.get("am"), day.get("pm")
parts = [f"오전 {am}, 오후 {pm}" if am and pm and am != pm else am or pm]
if day.get("min") is not None:
parts.append(f"최저 {round(float(day['min']))}도")
if day.get("max") is not None:
parts.append(f"최고 {round(float(day['max']))}도")
if day.get("pop") is not None:
parts.append(f"강수확률 {round(float(day['pop']))}%")
if detail:
parts += _detail_parts(day.get("humidity"), day.get("wind_ms"), day.get("rain_mm"), "최대 바람", "강수량")
return f"{when} {place} 날씨는 " + ", ".join(p for p in parts if p) + "입니다."
def _kma_current(lat: float, lon: float, key: str, now: Optional[datetime] = None) -> Dict[str, Any]:
"""Current weather from KMA in open-meteo's 'current' keys plus 'condition_ko'; {} on failure.
@@ -331,6 +558,7 @@ def _kma_current(lat: float, lon: float, key: str, now: Optional[datetime] = Non
"weather_code": wmo,
"condition_ko": ko,
"wind_speed_10m": round(float(wind) * 3.6, 1) if wind is not None else None,
"precipitation": float(obs["RN1"]) if obs.get("RN1") is not None else None,
}
except Exception as e:
why = str(e) if isinstance(e, (ValueError, KeyError)) else type(e).__name__
@@ -351,6 +579,10 @@ class WeatherTool(Tool):
"Weather only (current + forecast). NOT for time-of-day, date, or "
"location questions — those are already in the assistant's context. "
"Use for ANY weather question: now, later today, tomorrow, this week. "
"For another day set days_ahead, the days from today's date in the "
"context to that day (tomorrow 1, up to 10), and days for more than one "
"day: a weekend is days_ahead to the coming Saturday with days 2, a week "
"is days 7. "
"Set location to the place the user asked about. If they named none, "
"set it to where the user has said they are, from the conversation or "
"what you remember about them. Otherwise leave it empty: the tool "
@@ -366,6 +598,18 @@ class WeatherTool(Tool):
"location": {
"type": "string",
"description": "City name or location (e.g., 'London', 'New York', 'Tokyo'): the place the user asked about, or else where the user has said they are (the conversation or your memory of them). Omit otherwise; the tool then auto-detects the user's location. Never ask the user for this argument."
},
"days_ahead": {
"type": "integer",
"description": "Days from today to the day asked about: omit or 0 for now, 1 for tomorrow, 2 for the day after, up to 10. " + _weekday_offsets()
},
"days": {
"type": "integer",
"description": "How many days from days_ahead on (default 1): 2 for a weekend (Saturday and Sunday), 7 for a week."
},
"detail": {
"type": "boolean",
"description": "true only when the user asks for more detail: the answer then also has the humidity, the wind and the rain amount."
}
},
"required": []
@@ -416,8 +660,27 @@ class WeatherTool(Tool):
debug_log(f" ⚠️ location detection error: {e}", "tools")
return None
@staticmethod
def _forecast_lines(lat: float, lon: float, country_code: Optional[str], first: int, last: int,
location_display: str, detail: bool = False) -> list:
"""A sentence for each day from first to last that a forecast has: KMA inside Korea with the
app's key, open-meteo for the days KMA does not give."""
offsets = list(range(first, last + 1))
days: Dict[int, Dict[str, Any]] = {}
kma_key = _kma_key_now()
if kma_key and country_code == "KR":
days = _kma_days(lat, lon, kma_key, offsets)
from_kma = len(days)
rest = [off for off in offsets if off not in days]
if rest:
days.update(_open_meteo_days(lat, lon, rest))
# Which service gave the answer, in the app's log (no place: it comes from the question).
notice(f"weather days {first}-{last}: {from_kma} from KMA, {len(days) - from_kma} from open-meteo", "llm")
place = location_display.split(",")[0].strip() or location_display
return [_day_sentence(off, days[off], place, detail) for off in offsets if off in days]
def run(self, args: Optional[Dict[str, Any]], context: ToolContext) -> ToolExecutionResult:
"""Get current weather for a location."""
"""Get the weather now, or the forecast for the days asked about, for a location."""
context.user_print("🌤️ Checking weather...")
try:
@@ -504,13 +767,24 @@ class WeatherTool(Tool):
"format": "json"
}
geo_response = requests.get(geocode_url, params=geocode_params, timeout=10)
geo_response.raise_for_status()
geo_data = geo_response.json()
# Open-Meteo knows cities only, in Latin spellings, and matches a
# non-Latin name loosely (live 2026-11-18: "부산" gave a village
# called Pusan 140 km away). A non-Latin name, and a Latin one
# open-meteo does not know (a district), is looked up on
# OpenStreetMap in the words the user used.
geo_data: Dict[str, Any] = {}
if location_str.isascii():
geo_response = requests.get(geocode_url, params=geocode_params, timeout=10)
geo_response.raise_for_status()
geo_data = geo_response.json()
osm = None if geo_data.get("results") else _osm_place(location_str)
if osm:
debug_log(" 📍 found on OpenStreetMap", "tools")
geo_data = {"results": [{"latitude": osm["lat"], "longitude": osm["lon"],
"name": location_str, "country_code": osm["country_code"]}]}
# Open-Meteo only matches Latin spellings, so a non-Latin name
# (e.g. Korean "서울") returns nothing. Retry once with an
# LLM-romanised name before giving up.
# Not on OpenStreetMap either (or it failed): retry open-meteo
# once with an LLM-romanised name before giving up.
if not geo_data.get("results"):
romanised = _romanise_place(location_str, getattr(context, "cfg", None))
if romanised:
@@ -562,12 +836,24 @@ class WeatherTool(Tool):
debug_log(f" 📍 resolved to {location_display} ({lat}, {lon})", "tools")
first, last = _day_span(args)
detail = (args or {}).get("detail") is True or str((args or {}).get("detail")).lower() == "true"
if first > 0:
lines = self._forecast_lines(lat, lon, country_code, first, last, location_display, detail)
if not lines:
return ToolExecutionResult(
success=False,
reply_text=f"Weather forecast temporarily unavailable for {location_display}."
)
context.user_print(f"✅ Forecast for {location_display.split(',')[0].strip()}")
return ToolExecutionResult(success=True, reply_text="\n".join(lines))
# Step 2: Get current weather + forecast
weather_url = "https://api.open-meteo.com/v1/forecast"
weather_params = {
"latitude": lat,
"longitude": lon,
"current": "temperature_2m,relative_humidity_2m,apparent_temperature,weather_code,wind_speed_10m,wind_gusts_10m",
"current": "temperature_2m,relative_humidity_2m,apparent_temperature,weather_code,wind_speed_10m,wind_gusts_10m,precipitation",
"hourly": "temperature_2m,weather_code",
"daily": "weather_code,temperature_2m_max,temperature_2m_min",
"forecast_days": 7,
@@ -577,12 +863,12 @@ class WeatherTool(Tool):
}
current: Dict[str, Any] = {}
source = "KMA"
kma_key = _kma_key_now()
if kma_key and country_code == "KR":
current = _kma_current(lat, lon, kma_key)
if current:
debug_log(" 🌤️ current weather from KMA", "tools")
if not current:
source = "open-meteo"
try:
weather_response = requests.get(weather_url, params=weather_params,
timeout=_OPEN_METEO_TIMEOUT_SEC)
@@ -591,12 +877,14 @@ class WeatherTool(Tool):
except Exception as e:
# Live 2026-11-18: the forecast server stopped answering while geocoding worked.
debug_log(f"open-meteo forecast failed ({type(e).__name__}); trying met.no", "tools")
source = "met.no"
current = _met_no_current(lat, lon)
if not current:
return ToolExecutionResult(
success=False,
reply_text=f"Weather data temporarily unavailable for {location_display}."
)
notice(f"weather now: {source}", "llm")
# Extract current weather values
temp_c = current.get("temperature_2m")
@@ -625,12 +913,17 @@ class WeatherTool(Tool):
if feels_like_c is not None and round(feels_like_c) != round(temp_c):
_t += f"(체감 {round(feels_like_c)}도)"
_ko_parts.append(_t)
if detail:
_ko_parts += _detail_parts(humidity, _ms(wind_speed), current.get("precipitation"),
"바람", "지난 1시간 강수량")
ko_sentence = ", ".join(_ko_parts) + "입니다."
# The reply is the clean Korean sentence ONLY — no English/°C source
# for the model to echo ("25도 Celsius"), no forecast firehose to
# ramble over. The model just echoes this one sentence.
lines = [ko_sentence]
if last > 0: # "this week": now, then each day
lines += self._forecast_lines(lat, lon, country_code, 0, last, location_display, detail)
reply_text = "\n".join(lines)

View File

@@ -24,12 +24,23 @@ import argparse
import importlib
import json
import os
import re
import struct
import sys
import types
MODEL_SPEED_MAX = 1.25
# MeloTTS's Korean front end (g2pkk) reads a number with native numerals only before these counters,
# and only when MeCab tags the counter. Any other number is spelled out only when MeCab tags what follows
# as a bound noun, which differs between MeCab builds (on Windows "60%" was read "육영퍼센트"); the rest
# goes digit by digit. Its sentence splitter also breaks at every dot and comma ("4.2" as "사. 이").
# Same list as g2pkk's BOUND_NOUNS: numbers before them are left for its counter rule.
NATIVE_COUNTERS = tuple("군데 권 개 그루 닢 대 두 마리 모 모금 뭇 발 발짝 방 번 벌 보루 살 수 술 시 쌈 움큼 "
"정 짝 채 척 첩 축 켤레 톨 통".split())
_DIGITS = "영일이삼사오육칠팔구"
_NUMBER = re.compile(r"(?<![\d.,])(\d{1,3}(?:,\d{3})+|\d+)(?:\.(\d+))?(?![\d,]\d)(?!\.\d)([가-힣]*)")
def split_speed(speed: float) -> tuple[float, float]:
"""(the model's speed, the stretch factor after it); their product is ``speed``."""
@@ -65,6 +76,39 @@ def stretch(audio, factor: float, rate: int, frame_ms: float = 30.0, search_ms:
return y[:n_out]
def sino_korean(num: str) -> str:
"""Sino-Korean reading of a whole number: 1234 is 천이백삼십사, 10000 is 만, 100000000 is 일억."""
n = int(num)
if n == 0:
return "영"
out = ""
for power, big in reversed(list(enumerate(("", "만", "억", "조", "경")))):
group = n // 10 ** (4 * power) % 10000
if not group:
continue
part = ""
for digit, unit in zip(f"{group:04d}", ("천", "백", "십", "")):
d = int(digit)
if d:
part += ("" if d == 1 and unit else _DIGITS[d]) + unit
out += ("" if part == "일" and big == "만" else part) + big
return out
def spell_numbers_kr(text: str) -> str:
"""Spell out the numbers MeloTTS would misread: decimals ("4.2" is 사점이) and every whole number
not followed by a native counter (those are left for MeloTTS, which reads "3시" as 세시)."""
def spell(m: re.Match) -> str:
whole, frac, after = m.group(1), m.group(2), m.group(3)
if frac is None and after.startswith(NATIVE_COUNTERS):
return m.group(0)
spoken = sino_korean(whole.replace(",", ""))
if frac is not None:
spoken += "점" + "".join(_DIGITS[int(d)] for d in frac)
return spoken + after
return _NUMBER.sub(spell, text)
def korean_only_patches() -> None:
"""MeloTTS imports its Japanese front end (module-level MeCab.Tagger()) even for Korean, and on
Windows g2pkk asks for ``eunjeon`` instead of python-mecab-ko. Same fix as the M0 kit."""
@@ -132,7 +176,10 @@ def main() -> int:
req = json.loads(line)
rate = int(req["rate"])
model_speed, factor = split_speed(float(req.get("speed", args.speed)))
audio = model.tts_to_file(str(req["text"]), speaker, None, speed=model_speed, quiet=True)
text = str(req["text"])
if args.language == "KR":
text = spell_numbers_kr(text)
audio = model.tts_to_file(text, speaker, None, speed=model_speed, quiet=True)
audio = stretch(audio, factor, native)
if rate != native:
from math import gcd

View File

@@ -108,6 +108,9 @@ its own streaming Silero VAD (512-sample windows, state kept between frames).
the gain kept between -20 and +40 dB, and peaks above 0.8 are soft-limited below 0.98 instead of
clipping. Measured: speech from -60 dBFS to clipped shouting was transcribed equally well, and quiet
speech under loud clicks or knocks better than with peak normalisation.
No treble boost: a 12 dB shelf above 1 kHz (0.1.34) helped FLEURS a little but, on the user's
own 34 live utterances of 2026-11-18, turned "왜" into "올해" and "알아서" into "아라해석" and
dropped a whole sentence, so it was removed again.
### Scheduling
@@ -180,6 +183,14 @@ is ready. Requests are served first come, first served by one TTS engine. `tts_c
request's unsent sentences, and `tts_done` follows with `cancelled: true`. A sentence that fails to
synthesise is reported with `error` (`code: "tts_failed"`) and the request ends with `failed: true`.
With `--melo-language KR` the MeloTTS child spells numbers out in Hangul before MeloTTS sees them,
because its Korean front end misreads them: a number it cannot tag as a counter is read digit by digit
(the tag depends on the MeCab build; on Windows "60%" was read "육영퍼센트"), and its own splitter
breaks at every dot and comma ("4.2미터" as "사. 이미터"). Decimals are read with 점 and one name per
digit after it (사점이), thousands commas are dropped, and every other whole number gets its
Sino-Korean reading (육십, 이천이십육), except before a counter MeloTTS reads with native numerals
(g2pkk's list: 시, 개, 마리, 살, ...), which stays for MeloTTS ("3시" is 세시).
Speed starts at `--melo-speed` and `tts_speed` changes it for every sentence made after it (a speed
outside 0.5-2.0 or not a number is `bad_message` and the last good one stays). MeloTTS itself speaks
up to 1.25: its own speed shortens every sound, and past that it drops them (five Korean sentences,
@@ -289,10 +300,25 @@ which carry Discord's own time.
brain adds each server's values to that server's environment only. Each server's outcome is printed without debug logging (category `llm`):
`MCP server <name>: <n> tool(s)`, or `Warning: MCP server <name> failed: <reason>`.
The KMA key (`JARVIS_KMA_API_KEY`, `app/src/admin.spec.md`) leaves the environment at the same
point; the weather tool keeps it and uses it only for the current weather inside Korea
(geocoded or detected country `KR`): KMA's 초단기실황 (temperature, humidity, wind,
precipitation) and 초단기예보 (the coming hour's sky). Any KMA failure falls back to open-meteo,
then met.no; the key is in KMA's URLs, so a failure is logged by its kind only.
point; the weather tool keeps it and uses it only for the weather inside Korea (geocoded or
detected country `KR`). Now: KMA's 초단기실황 (temperature, humidity, wind, precipitation) and
초단기예보 (the coming hour's sky). A later day (`getWeather` `days_ahead`, 1 to 10, and `days`
for a span such as a weekend; the schema lists each coming weekday's `days_ahead` from today
so the model need not count): 단기예보 for today to 3 days ahead (the morning's and the
afternoon's commonest precipitation, 소나기 included, or sky, the day's lowest and highest, the
highest chance of rain), then 중기예보 for the nearest of the KMA cities in `weather.py` and its region (중기기온,
중기육상). Days KMA does not give, and every KMA failure, come from open-meteo (now: then
met.no; later days: open-meteo's daily forecast only). The key is in KMA's URLs, so a failure is
logged by its kind only. Which service answered is printed without debug logging (category
`llm`, no place and no key): `weather now: KMA` (or `open-meteo`, `met.no`) and
`weather days <first>-<last>: <n> from KMA, <m> from open-meteo`. `detail` (only when the user asks for more detail) adds the
humidity, the wind in m/s and the rain amount: now the last hour's rain (KMA 초단기실황 RN1,
open-meteo `precipitation`; none from met.no), a 단기예보 day its mean humidity and strongest
wind, an open-meteo day its strongest wind and rain total; 중기예보 has none of these. A dry
0 mm is not said. The place is found by open-meteo's geocoder (cities, Latin spellings)
or OpenStreetMap's Nominatim (any language, down to districts such as 부산 연제구; a non-Latin
name goes there first, since open-meteo matches it loosely); only the place name is sent, with
the app's User-Agent, and the answer names the place in the user's own words.
- `prepare` tells the brain that `user` is saying a call whose partial transcript is `text` (the app
sends it while the speaker is still talking, `app/src/conversation.spec.md`). The brain runs the
intent judge's tool pick for it on its own thread, with the asker's dialogue memory and the tool

View File

@@ -0,0 +1,87 @@
"""Numbers MeloTTS's Korean front end reads wrongly are spelled out before it sees them: a number it
cannot tag as a counter is read digit by digit ("60%" as "육영퍼센트"), and every dot or comma is a
sentence break for it ("4.2미터" as "사. 이미터")."""
from __future__ import annotations
import json
import os
import struct
import subprocess
import sys
import textwrap
import pytest
from voice_worker import melo_child
from voice_worker.melo_child import spell_numbers_kr
@pytest.mark.unit
@pytest.mark.parametrize("text, spoken", [
("습도 60%입니다.", "습도 육십%입니다."),
("습도 60퍼센트", "습도 육십퍼센트"),
("바람 초속 4.2미터", "바람 초속 사점이미터"),
("최고 25.5도, 최저 0.5도", "최고 이십오점오도, 최저 영점오도"),
("11월 19일, 2026년", "십일월 십구일, 이천이십육년"),
("1,234명", "천이백삼십사명"),
("10 100 1000 10000 110 20만 100000000", "십 백 천 만 백십 이십만 일억"),
("0, 7", "영, 칠"),
])
def test_numbers_are_spelled_as_they_are_read(text, spoken):
assert spell_numbers_kr(text) == spoken
@pytest.mark.unit
def test_numbers_before_native_counters_are_left_for_melo_to_read_natively():
# "3시" is "세시", "10개" is "열개", "5시간" is "다섯시간": MeloTTS's own counter rule reads these.
text = "3시 10개 5시간 2마리"
assert spell_numbers_kr(text) == text
FAKE_MELO = textwrap.dedent("""
import os
import numpy as np
class _Hps:
class data:
spk2id = {"KR": 0}
sampling_rate = 48000
class TTS:
def __init__(self, language, device):
self.hps = _Hps
def tts_to_file(self, text, speaker, path, speed=1.0, quiet=True):
with open(os.environ["FAKE_MELO_LOG"], "a", encoding="utf-8") as f:
f.write(text + "\\n")
return np.zeros(10)
""")
def read_frame(stream) -> dict:
(n,) = struct.unpack("<I", stream.read(4))
header = json.loads(stream.read(n))
stream.read(2 * header.get("samples", 0))
return header
@pytest.mark.unit
def test_the_korean_child_gives_melo_the_spelled_text(tmp_path):
(tmp_path / "melo").mkdir()
(tmp_path / "melo" / "__init__.py").write_text("")
(tmp_path / "melo" / "api.py").write_text(FAKE_MELO)
log = tmp_path / "texts.txt"
env = {**os.environ, "PYTHONPATH": str(tmp_path), "FAKE_MELO_LOG": str(log)}
proc = subprocess.Popen([sys.executable, melo_child.__file__, "--language", "KR", "--device", "cpu",
"--speed", "1.0"], stdin=subprocess.PIPE, stdout=subprocess.PIPE,
stderr=subprocess.DEVNULL, env=env)
try:
assert read_frame(proc.stdout)["ready"] is True
proc.stdin.write((json.dumps({"text": "바람 초속 4.2미터, 습도 60%", "rate": 48000}) + "\n").encode())
proc.stdin.flush()
assert read_frame(proc.stdout)["ok"] is True
finally:
proc.stdin.close()
proc.wait(timeout=10)
assert log.read_text(encoding="utf-8").splitlines()[-1] == "바람 초속 사점이미터, 습도 육십%"

View File

@@ -3,6 +3,7 @@
import pytest
from unittest.mock import Mock, patch
import requests
from datetime import datetime, timedelta, timezone
from src.jarvis.tools.builtin.weather import (
WeatherTool,
@@ -106,16 +107,13 @@ class TestWeatherTool:
def test_run_non_latin_location_romanises_and_retries(self, mock_get, mock_romanise):
"""A Korean city name Open-Meteo can't geocode is romanised and retried.
Open-Meteo's geocoder only matches Latin spellings, so ``서울`` returns
no results. The tool must romanise to ``Seoul`` and retry rather than
Open-Meteo's geocoder only matches Latin spellings, so ``서울`` is first
looked up on OpenStreetMap (any language). When that finds nothing,
the tool must romanise to ``Seoul`` and retry rather than
dead-ending with "could not find location" (the failure the Korean-
locked deployment hit on every weather request)."""
mock_romanise.return_value = "Seoul"
geo_empty = Mock()
geo_empty.raise_for_status = Mock()
geo_empty.json.return_value = {} # no "results"
geo_seoul = Mock()
geo_seoul.raise_for_status = Mock()
geo_seoul.json.return_value = {
@@ -153,14 +151,16 @@ class TestWeatherTool:
},
}
mock_get.side_effect = [geo_empty, geo_seoul, weather_response]
osm_empty = Mock(raise_for_status=Mock())
osm_empty.json.return_value = []
mock_get.side_effect = [osm_empty, geo_seoul, weather_response]
result = self.tool.run({"location": "서울"}, self.context)
assert result.success is True
assert "Seoul" in result.reply_text
mock_romanise.assert_called_once()
# The romanised name must be what the second geocode actually queried.
# The romanised name must be what the geocode actually queried.
assert mock_get.call_args_list[1].kwargs["params"]["name"] == "Seoul"
@patch('requests.get')
@@ -426,13 +426,36 @@ class TestWeatherTool:
return met
mock_get.side_effect = get
result = self.tool.run({"location": "서울"}, self.context)
result = self.tool.run({"location": "Seoul"}, self.context)
assert result.success is True
assert "서울" in result.reply_text
assert WMO_CODES_KO[80] in result.reply_text
assert str(round(8.6)) in result.reply_text
@patch('requests.get')
def test_the_log_names_met_no_when_it_gave_the_weather_now(self, mock_get, capfd):
geo = Mock(status_code=200, raise_for_status=Mock())
geo.json.return_value = {"results": [{"latitude": 37.57, "longitude": 126.98,
"name": "서울", "country": "대한민국"}]}
met = Mock(status_code=200, raise_for_status=Mock())
met.json.return_value = {"properties": {"timeseries": [{"data": {
"instant": {"details": {"air_temperature": 8.6}},
"next_1_hours": {"summary": {"symbol_code": "cloudy"}}}}]}}
def get(url, *a, **k):
if "geocoding" in url:
return geo
if "open-meteo" in url:
raise requests.exceptions.Timeout("timed out")
return met
mock_get.side_effect = get
self.tool.run({"location": "Seoul"}, self.context)
err = capfd.readouterr().err
assert "weather now: met.no" in err and "서울" not in err
@pytest.mark.parametrize("symbol", ["lightsleet", "sleet_day", "heavysleetshowers_night"])
def test_met_no_sleet_stays_sleet_not_freezing_rain(self, symbol):
from src.jarvis.tools.builtin.weather import _met_no_wmo
@@ -453,7 +476,7 @@ class TestWeatherTool:
raise requests.exceptions.Timeout("timed out")
mock_get.side_effect = get
result = self.tool.run({"location": "서울"}, self.context)
result = self.tool.run({"location": "Seoul"}, self.context)
assert result.success is False
assert "unavailable" in result.reply_text.lower()
@@ -678,9 +701,9 @@ class TestKmaWeather:
"body": {"items": {"item": items}}}}
return r
def _obs(self, pty="0", t1h="4.9"):
def _obs(self, pty="0", t1h="4.9", rn1="0"):
return self._kma([{"category": c, "obsrValue": v} for c, v in
[("PTY", pty), ("REH", "72"), ("RN1", "0"), ("T1H", t1h), ("WSD", "2.5")]])
[("PTY", pty), ("REH", "72"), ("RN1", rn1), ("T1H", t1h), ("WSD", "2.5")]])
def _sky(self, first="3"):
# The coming hours, out of order: the earliest one is the sky now.
@@ -722,6 +745,23 @@ class TestKmaWeather:
assert len(kma) == 2 and all(p["authKey"] == self.KEY for p in kma)
assert all((p["nx"], p["ny"]) == (60, 127) for p in kma)
@pytest.mark.parametrize("key, source", [(True, "KMA"), (False, "open-meteo")])
@patch('requests.get')
def test_the_log_names_the_service_that_gave_the_weather_now_and_not_the_place(
self, mock_get, key, source, monkeypatch, capfd):
"""Live 2026-11-18: "흐림" could have come from either service, and nothing said which."""
if key:
monkeypatch.setenv("JARVIS_KMA_API_KEY", self.KEY)
else:
monkeypatch.delenv("JARVIS_KMA_API_KEY", raising=False)
mock_get.side_effect = self._routes()
self.tool.run({"location": "Seoul"}, self.context)
err = capfd.readouterr().err
assert f"weather now: {source}" in err
assert "Seoul" not in err and self.KEY not in err
@patch('requests.get')
def test_precipitation_wins_over_the_sky(self, mock_get, monkeypatch):
monkeypatch.setenv("JARVIS_KMA_API_KEY", self.KEY)
@@ -778,6 +818,48 @@ class TestKmaWeather:
assert result.success is True and "기온 11도" in result.reply_text
assert not any(self.KEY in str(c) for c in log.call_args_list)
@patch('requests.get')
def test_asked_in_detail_kma_gives_humidity_wind_and_the_last_hours_rain(self, mock_get, monkeypatch):
monkeypatch.setenv("JARVIS_KMA_API_KEY", self.KEY)
mock_get.side_effect = self._routes(obs=self._obs(pty="1", rn1="1.5"))
result = self.tool.run({"location": "Seoul", "detail": True}, self.context)
text = result.reply_text
assert "습도 72%" in text and "바람 초속 2.5미터" in text and "지난 1시간 강수량 1.5mm" in text
@patch('requests.get')
def test_not_asked_in_detail_the_answer_stays_short(self, mock_get, monkeypatch):
monkeypatch.setenv("JARVIS_KMA_API_KEY", self.KEY)
mock_get.side_effect = self._routes(obs=self._obs(pty="1", rn1="1.5"))
result = self.tool.run({"location": "Seoul"}, self.context)
assert "습도" not in result.reply_text and "바람" not in result.reply_text
@patch('requests.get')
def test_asked_in_detail_open_meteo_gives_humidity_and_wind_without_a_dry_hours_rain(
self, mock_get, monkeypatch):
monkeypatch.delenv("JARVIS_KMA_API_KEY", raising=False)
calls = []
base = self._routes(calls=calls)
weather = Mock(status_code=200, raise_for_status=Mock())
weather.json.return_value = {"current": {"temperature_2m": 11.0, "weather_code": 0,
"relative_humidity_2m": 55, "wind_speed_10m": 10.8,
"precipitation": 0.0}}
def get(url, *a, **k):
r = base(url, *a, **k)
return weather if "api.open-meteo.com/v1/forecast" in url else r
mock_get.side_effect = get
result = self.tool.run({"location": "Seoul", "detail": True}, self.context)
assert "습도 55%" in result.reply_text and "바람 초속 3미터" in result.reply_text
assert "강수량" not in result.reply_text
(p,) = [p for u, p in calls if "api.open-meteo.com/v1/forecast" in u]
assert "precipitation" in p["current"].split(",")
@pytest.mark.parametrize("place,lat,lon,grid", [
("서울", 37.5665, 126.9780, (60, 127)),
("부산", 35.1796, 129.0756, (98, 76)),
@@ -824,3 +906,382 @@ class TestKmaWeather:
assert "흐림" in result.reply_text or "구름 많음" in result.reply_text
assert any(p.get("authKey") == self.KEY for u, p in calls if "apihub.kma.go.kr" in u)
class TestForecast:
"""A later day (days_ahead/days): KMA 단기예보 and 중기예보 inside Korea, else open-meteo's daily forecast."""
KEY = "kma-test-key-123"
# Wednesday 18 November 2026, 10:20 KST.
NOW = datetime(2026, 11, 18, 10, 20, tzinfo=timezone(timedelta(hours=9)))
def setup_method(self):
self.tool = WeatherTool()
self.context = Mock(spec=ToolContext)
self.context.user_print = Mock()
self.context.cfg = Mock()
self.context.cfg.location_name = None
self.context.redacted_text = ""
@staticmethod
def _ok(payload):
r = Mock(status_code=200, raise_for_status=Mock())
r.json.return_value = payload
return r
def _kma(self, items):
return self._ok({"response": {"header": {"resultCode": "00"}, "body": {"items": {"item": items}}}})
@staticmethod
def _vilage_items():
"""단기예보: tomorrow (19th) clear in the morning, rain in the afternoon; Saturday (21st) cloudy."""
items = []
for date, sky_am, sky_pm, pty_pm, pops in [
("20261119", "1", "4", "1", ("10", "60")),
("20261120", "3", "3", "0", ("20", "20")),
("20261121", "4", "4", "0", ("30", "30")),
]:
for hour in range(0, 24):
t = f"{hour:02d}00"
am = hour < 12
items += [
{"category": "SKY", "fcstDate": date, "fcstTime": t, "fcstValue": sky_am if am else sky_pm},
{"category": "PTY", "fcstDate": date, "fcstTime": t, "fcstValue": "0" if am else pty_pm},
{"category": "POP", "fcstDate": date, "fcstTime": t, "fcstValue": pops[0] if am else pops[1]},
{"category": "TMP", "fcstDate": date, "fcstTime": t, "fcstValue": str(hour % 7)},
{"category": "REH", "fcstDate": date, "fcstTime": t, "fcstValue": "60" if am else "80"},
{"category": "WSD", "fcstDate": date, "fcstTime": t, "fcstValue": str(1 + hour % 4)},
]
items += [{"category": "TMN", "fcstDate": date, "fcstTime": "0600", "fcstValue": "-1.0"},
{"category": "TMX", "fcstDate": date, "fcstTime": "1500", "fcstValue": "4.0"}]
return items
def _routes(self, country_code="KR", lat=37.566, lon=126.9784, calls=None, fail_kma=False):
def get(url, *a, **k):
params = k.get("params") or {}
if calls is not None:
calls.append((url, params))
if "geocoding" in url:
return self._ok({"results": [{"latitude": lat, "longitude": lon, "name": "Seoul",
"country_code": country_code}]})
if "apihub.kma.go.kr" in url:
if fail_kma:
raise requests.exceptions.Timeout(f"timed out: {url}?authKey={self.KEY}")
if "getVilageFcst" in url:
return self._kma(self._vilage_items())
if "getMidTa" in url:
return self._kma([{"regId": params["regId"], "taMin4": -4, "taMax4": 5,
"taMin5": -2, "taMax5": 7, "taMin10": 2, "taMax10": 10}])
if "getMidLandFcst" in url:
return self._kma([{"regId": params["regId"], "wf4Am": "맑음", "wf4Pm": "구름많음",
"rnSt4Am": 10, "rnSt4Pm": 20, "wf5Am": "흐림", "wf5Pm": "흐리고 비",
"rnSt5Am": 30, "rnSt5Pm": 60, "wf10": "맑음", "rnSt10": 10}])
raise AssertionError(url)
assert "api.open-meteo.com/v1/forecast" in url, url
return self._ok({"current": {"temperature_2m": 11.0, "weather_code": 0}, "daily": {
"time": [f"2026-11-{d}" for d in range(18, 29)],
"weather_code": [0, 61, 3, 2, 0, 0, 0, 0, 0, 0, 0],
"temperature_2m_min": [1.2, 2.6, 0, 0, 0, 0, 0, 0, 0, 0, 0],
"temperature_2m_max": [9.0, 11.4, 0, 0, 0, 0, 0, 0, 0, 0, 0],
"precipitation_probability_max": [0, 80, 0, 0, 0, 0, 0, 0, 0, 0, 0],
"wind_speed_10m_max": [9.0, 18.0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
"precipitation_sum": [0.0, 12.5, 0, 0, 0, 0, 0, 0, 0, 0, 0],
}})
return get
def _run(self, args, monkeypatch, key=True, now=None, **routes):
if key:
monkeypatch.setenv("JARVIS_KMA_API_KEY", self.KEY)
else:
monkeypatch.delenv("JARVIS_KMA_API_KEY", raising=False)
calls = []
with patch('requests.get', side_effect=self._routes(calls=calls, **routes)), \
patch('src.jarvis.tools.builtin.weather._now', return_value=now or self.NOW):
result = self.tool.run({"location": "Seoul", **args}, self.context)
return result, calls
def test_the_schema_offers_a_later_day_and_a_span_of_days(self):
props = self.tool.inputSchema["properties"]
assert props["days_ahead"]["type"] == "integer" and props["days"]["type"] == "integer"
assert self.tool.inputSchema["required"] == []
def test_tomorrow_in_korea_comes_from_the_kma_short_term_forecast(self, monkeypatch):
result, calls = self._run({"days_ahead": 1}, monkeypatch)
assert result.success is True
text = result.reply_text
assert text.startswith("내일(11월 19일 목요일) Seoul 날씨는")
assert "오전 맑음" in text and "오후 비" in text
assert "최저 -1도" in text and "최고 4도" in text and "강수확률 60%" in text
assert not any("open-meteo.com/v1/forecast" in u for u, _ in calls)
vilage = [p for u, p in calls if "getVilageFcst" in u]
assert len(vilage) == 1 and vilage[0]["authKey"] == self.KEY
assert (vilage[0]["nx"], vilage[0]["ny"]) == (60, 127)
assert (vilage[0]["base_date"], vilage[0]["base_time"]) == ("20261118", "0800")
assert not any("MidFcstInfoService" in u for u, _ in calls)
def test_five_days_ahead_in_korea_comes_from_the_kma_mid_term_forecast(self, monkeypatch):
result, calls = self._run({"days_ahead": 5}, monkeypatch)
text = result.reply_text
assert text.startswith("11월 23일 월요일 Seoul 날씨는")
assert "오전 흐림" in text and "오후 흐리고 비" in text
assert "최저 -2도" in text and "최고 7도" in text and "강수확률 60%" in text
mid = {u.rsplit("/", 1)[-1]: p for u, p in calls if "MidFcstInfoService" in u}
assert mid["getMidTa"]["regId"] == "11B10101" and mid["getMidLandFcst"]["regId"] == "11B00000"
assert mid["getMidTa"]["tmFc"] == "202611180600" and mid["getMidTa"]["authKey"] == self.KEY
assert not any("getVilageFcst" in u for u, _ in calls)
def test_the_weekend_spans_the_short_and_mid_term_forecasts(self, monkeypatch):
result, _ = self._run({"days_ahead": 3, "days": 2}, monkeypatch)
lines = result.reply_text.split("\n")
assert len(lines) == 2
assert lines[0].startswith("11월 21일 토요일") and "흐림" in lines[0] and "강수확률 30%" in lines[0]
assert lines[1].startswith("11월 22일 일요일") and "오전 맑음" in lines[1] and "오후 구름많음" in lines[1]
assert "최저 -4도" in lines[1] and "최고 5도" in lines[1]
def test_the_same_weather_all_day_is_said_once(self, monkeypatch):
result, _ = self._run({"days_ahead": 2}, monkeypatch)
assert result.reply_text.startswith("모레(11월 20일 금요일) Seoul 날씨는 구름 많음,")
assert "오전" not in result.reply_text
@pytest.mark.parametrize("lat,lon,city,region", [
(35.1796, 129.0756, "11H20201", "11H20000"), # 부산
(33.4996, 126.5312, "11G00201", "11G00000"), # 제주
(35.9676, 126.7369, "21F10501", "11F10000"), # 군산
(37.7519, 128.8761, "11D20501", "11D20000"), # 강릉
])
def test_the_mid_term_forecast_is_for_the_nearest_kma_city_and_its_region(
self, lat, lon, city, region, monkeypatch):
_, calls = self._run({"days_ahead": 6}, monkeypatch, lat=lat, lon=lon)
mid = {u.rsplit("/", 1)[-1]: p for u, p in calls if "MidFcstInfoService" in u}
assert mid["getMidTa"]["regId"] == city and mid["getMidLandFcst"]["regId"] == region
@pytest.mark.parametrize("now,vilage,tmfc", [
(datetime(2026, 11, 18, 1, 50), ("20261117", "2300"), "202611171800"),
(datetime(2026, 11, 18, 2, 20), ("20261118", "0200"), "202611171800"),
(datetime(2026, 11, 18, 6, 40), ("20261118", "0500"), "202611180600"),
(datetime(2026, 11, 18, 23, 59), ("20261118", "2300"), "202611181800"),
])
def test_kma_forecasts_are_the_latest_published(self, now, vilage, tmfc, monkeypatch):
"""단기예보 is out about 10 minutes after 02, 05, ..., 23 h; 중기예보 about 30 minutes after 06 and 18 h."""
now = now.replace(tzinfo=timezone(timedelta(hours=9)))
_, calls = self._run({"days_ahead": 1}, monkeypatch, now=now)
_, mid_calls = self._run({"days_ahead": 7}, monkeypatch, now=now)
(p,) = [p for u, p in calls if "getVilageFcst" in u]
assert (p["base_date"], p["base_time"]) == vilage
assert {p["tmFc"] for u, p in mid_calls if "MidFcstInfoService" in u} == {tmfc}
def test_an_evening_mid_term_forecast_from_yesterday_counts_its_days_from_yesterday(self, monkeypatch):
# 05:00 on the 19th: the latest 중기예보 is the 18th's 18:00, whose day 5 is the 23rd = 4 days ahead.
now = datetime(2026, 11, 19, 5, 0, tzinfo=timezone(timedelta(hours=9)))
result, _ = self._run({"days_ahead": 4}, monkeypatch, now=now)
assert result.reply_text.startswith("11월 23일 월요일") and "최고 7도" in result.reply_text
def test_when_kma_fails_open_meteo_gives_the_forecast_and_the_key_is_not_logged(self, monkeypatch):
with patch("src.jarvis.tools.builtin.weather.debug_log") as log:
result, calls = self._run({"days_ahead": 1}, monkeypatch, fail_kma=True)
assert result.success is True
assert result.reply_text.startswith("내일(11월 19일 목요일) Seoul 날씨는 약한 비,")
assert "최저 3도" in result.reply_text and "최고 11도" in result.reply_text
assert "강수확률 80%" in result.reply_text
assert not any(self.KEY in str(c) for c in log.call_args_list)
@pytest.mark.parametrize("fail_kma, counts", [(False, "1 from KMA, 0 from open-meteo"),
(True, "0 from KMA, 1 from open-meteo")])
def test_the_log_says_how_many_forecast_days_each_service_gave(self, fail_kma, counts, monkeypatch, capfd):
self._run({"days_ahead": 1}, monkeypatch, fail_kma=fail_kma)
err = capfd.readouterr().err
assert f"weather days 1-1: {counts}" in err
assert "Seoul" not in err and self.KEY not in err
def test_outside_korea_the_forecast_is_open_meteos_daily_one(self, monkeypatch):
result, calls = self._run({"days_ahead": 1}, monkeypatch, country_code="JP")
assert "약한 비" in result.reply_text and "최고 11도" in result.reply_text
assert not any("apihub.kma.go.kr" in u for u, _ in calls)
(p,) = [p for u, p in calls if "open-meteo.com/v1/forecast" in u]
assert "precipitation_probability_max" in p["daily"] and p["forecast_days"] >= 2
def test_this_week_starts_with_the_weather_now(self, monkeypatch):
"""days_ahead 0 with more days: the current weather, then a line for each day."""
result, _ = self._run({"days": 3}, monkeypatch, key=False)
lines = result.reply_text.split("\n")
assert lines[0].startswith("지금 Seoul 날씨는")
assert lines[1].startswith("오늘(11월 18일 수요일)") and lines[2].startswith("내일(11월 19일 목요일)")
assert lines[3].startswith("모레(11월 20일 금요일)") and len(lines) == 4
def test_more_than_ten_days_ahead_is_the_tenth_day(self, monkeypatch):
result, _ = self._run({"days_ahead": 30, "days": 5}, monkeypatch)
assert result.reply_text.split("\n") == [result.reply_text]
assert result.reply_text.startswith("11월 28일 토요일") and "맑음" in result.reply_text
def test_when_no_forecast_is_available_the_answer_says_so(self, monkeypatch):
def down(url, *a, **k):
if "geocoding" in url:
return self._ok({"results": [{"latitude": 1.0, "longitude": 2.0, "name": "X",
"country_code": "FR"}]})
raise requests.exceptions.ConnectionError("down")
with patch('requests.get', side_effect=down), \
patch('src.jarvis.tools.builtin.weather._now', return_value=self.NOW):
result = self.tool.run({"location": "X", "days_ahead": 2}, self.context)
assert result.success is False and "forecast" in result.reply_text.lower()
# 단기예보's 소나기 (PTY 4) and the detail a person asks for on a later day.
def test_short_term_showers_are_said_not_dropped_for_a_clear_sky(self, monkeypatch):
items = [{"category": c, "fcstDate": "20261119", "fcstTime": f"{h:02d}00", "fcstValue": v}
for h in range(24) for c, v in
[("SKY", "1"), ("PTY", "4" if h >= 12 else "0"), ("POP", "60" if h >= 12 else "0"),
("TMP", "5")]]
items += [{"category": "TMN", "fcstDate": "20261119", "fcstTime": "0600", "fcstValue": "-1.0"},
{"category": "TMX", "fcstDate": "20261119", "fcstTime": "1500", "fcstValue": "4.0"}]
with patch.object(TestForecast, "_vilage_items", staticmethod(lambda: items)):
result, _ = self._run({"days_ahead": 1}, monkeypatch)
assert "오전 맑음, 오후 소나기" in result.reply_text, result.reply_text
def test_asked_in_detail_the_short_term_day_has_humidity_and_the_strongest_wind(self, monkeypatch):
result, _ = self._run({"days_ahead": 1, "detail": True}, monkeypatch)
assert "습도 70%" in result.reply_text and "최대 바람 초속 4미터" in result.reply_text
def test_asked_in_detail_open_meteos_day_has_the_strongest_wind_and_the_rain(self, monkeypatch):
result, calls = self._run({"days_ahead": 1, "detail": True}, monkeypatch, country_code="JP")
(p,) = [p for u, p in calls if "open-meteo.com/v1/forecast" in u]
assert {"wind_speed_10m_max", "precipitation_sum"} <= set(p["daily"].split(","))
assert "최대 바람 초속 5미터" in result.reply_text and "강수량 12.5mm" in result.reply_text
def test_the_schema_offers_detail(self):
assert self.tool.inputSchema["properties"]["detail"]["type"] == "boolean"
class TestDistrictPlaces:
"""A district such as 부산 연제구 is found by OpenStreetMap's search (any language) when
open-meteo's geocoder, which knows cities only, does not find it; the weather is for that spot."""
KEY = "kma-test-key-123"
def setup_method(self):
self.tool = WeatherTool()
self.context = Mock(spec=ToolContext)
self.context.user_print = Mock()
self.context.cfg = Mock()
self.context.cfg.location_name = None
self.context.redacted_text = ""
@staticmethod
def _ok(payload):
r = Mock(status_code=200, raise_for_status=Mock())
r.json.return_value = payload
return r
def _routes(self, calls, osm=None, osm_fails=False):
def get(url, *a, **k):
params = k.get("params") or {}
calls.append((url, params, k.get("headers") or {}))
if "geocoding-api.open-meteo.com" in url:
return self._ok({})
if "nominatim.openstreetmap.org" in url:
if osm_fails:
raise requests.exceptions.Timeout("timed out")
return self._ok(osm if osm is not None else [{
"lat": "35.1762", "lon": "129.0797", "name": "연제구", "addresstype": "borough",
"address": {"borough": "연제구", "city": "부산광역시", "country_code": "kr"}}])
if "getUltraSrtNcst" in url:
return self._ok({"response": {"header": {"resultCode": "00"}, "body": {"items": {"item": [
{"category": c, "obsrValue": v} for c, v in
[("PTY", "0"), ("REH", "60"), ("T1H", "8.2"), ("WSD", "3.1")]]}}}})
if "getUltraSrtFcst" in url:
return self._ok({"response": {"header": {"resultCode": "00"}, "body": {"items": {"item": [
{"category": "SKY", "fcstDate": "20261118", "fcstTime": "1200", "fcstValue": "1"}]}}}})
assert "api.open-meteo.com/v1/forecast" in url, url
return self._ok({"current": {"temperature_2m": 11.0, "weather_code": 0}})
return get
@patch('src.jarvis.tools.builtin.weather._romanise_place')
def test_a_district_gets_its_own_spots_weather_from_kma(self, mock_romanise, monkeypatch):
from src.jarvis.tools.builtin.weather import _kma_grid
monkeypatch.setenv("JARVIS_KMA_API_KEY", self.KEY)
calls = []
with patch('requests.get', side_effect=self._routes(calls)):
result = self.tool.run({"location": "부산 연제구"}, self.context)
assert result.success is True
assert result.reply_text.startswith("지금 부산 연제구 날씨는 맑음") and "기온 8도" in result.reply_text
kma = [p for u, p, _ in calls if "apihub.kma.go.kr" in u]
assert kma and all((p["nx"], p["ny"]) == _kma_grid(35.1762, 129.0797) for p in kma)
mock_romanise.assert_not_called()
def test_the_place_search_asks_for_one_place_with_its_country_and_names_the_app(self, monkeypatch):
monkeypatch.delenv("JARVIS_KMA_API_KEY", raising=False)
calls = []
with patch('requests.get', side_effect=self._routes(calls)):
self.tool.run({"location": "부산 연제구"}, self.context)
((_, params, headers),) = [c for c in calls if "nominatim.openstreetmap.org" in c[0]]
assert params["q"] == "부산 연제구" and params["limit"] == 1 and params["addressdetails"] == 1
assert "jarvis" in headers.get("User-Agent", "").lower()
@pytest.mark.parametrize("osm,osm_fails", [([], False), (None, True), ({"error": "x"}, False)])
@patch('src.jarvis.tools.builtin.weather._romanise_place', return_value=None)
def test_when_the_place_search_finds_nothing_or_fails_the_place_is_not_found(
self, _rom, osm, osm_fails, monkeypatch):
monkeypatch.delenv("JARVIS_KMA_API_KEY", raising=False)
calls = []
with patch('requests.get', side_effect=self._routes(calls, osm=osm, osm_fails=osm_fails)):
result = self.tool.run({"location": "없는 동네"}, self.context)
assert result.success is False and "could not find" in result.reply_text.lower()
@patch('src.jarvis.tools.builtin.weather._romanise_place')
def test_a_non_latin_city_name_is_not_matched_loosely_by_open_meteo(self, mock_romanise, monkeypatch):
"""Live 2026-11-18: open-meteo matched "부산" to a village called Pusan 140 km from Busan."""
monkeypatch.delenv("JARVIS_KMA_API_KEY", raising=False)
calls = []
osm = [{"lat": "35.1799", "lon": "129.0752", "name": "부산광역시", "address": {"country_code": "kr"}}]
with patch('requests.get', side_effect=self._routes(calls, osm=osm)):
result = self.tool.run({"location": "부산"}, self.context)
assert result.reply_text.startswith("지금 부산 날씨는")
assert not any("geocoding-api.open-meteo.com" in u for u, _, _ in calls)
(_, p, _), = [c for c in calls if "api.open-meteo.com/v1/forecast" in c[0]]
assert (p["latitude"], p["longitude"]) == (35.1799, 129.0752)
mock_romanise.assert_not_called()
def test_a_latin_name_open_meteo_knows_does_not_ask_openstreetmap(self, monkeypatch):
monkeypatch.delenv("JARVIS_KMA_API_KEY", raising=False)
calls = []
base = self._routes(calls)
def get(url, *a, **k):
if "geocoding-api.open-meteo.com" in url:
calls.append((url, k.get("params"), {}))
return self._ok({"results": [{"latitude": 51.5, "longitude": -0.12, "name": "London",
"country_code": "GB"}]})
return base(url, *a, **k)
with patch('requests.get', side_effect=get):
result = self.tool.run({"location": "London"}, self.context)
assert result.success and not any("nominatim" in u for u, _, _ in calls)
def test_the_day_schema_gives_each_coming_weekdays_days_ahead_from_today():
"""The model is handed the count instead of working it out (qwen3:8b counted a Wednesday's weekend as 2)."""
today = datetime.now()
text = WeatherTool().inputSchema["properties"]["days_ahead"]["description"]
saturday = (5 - today.weekday()) % 7 or 7
assert f"From today, {today.strftime('%A')}:" in text
assert f"{(today + timedelta(days=saturday)).strftime('%A')} {saturday}" in text