feat(voice_worker): a short voice prompt and one judgement before each v2 answer

- compact_prompt: the v2 persona in a tenth of v1's words, answers as short as
  possible, the full tool guidance only on turns with a data tool. A greeting's
  reply prompt went from about 4,500 to 1,400 tokens on Strata.
- intent_judge: the tool router judges whether the turn needs tools; the
  planner runs only when it does. prepare_intent runs the pick ahead on a
  partial transcript (worker message prepare), and the reply reuses it.
- Without stream_browser the screen-share tools are not offered.
- The time context carries the 12-hour form (10:37 was read as pm).
- A <tool_call> block written as the reply is parsed as a call, not spoken.

Evals (Qwen3.6 on Strata, EVAL_COMPACT_PROMPT=1 EVAL_INTENT_JUDGE=1):
221 passed, 4 failed (known failures); new evals/test_voice_reply_length.py
(v2 answers 234 chars against v1's 416) and test_reply_language_default.py.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
javis-bot
2026-11-12 12:25:15 +09:00
parent 7623d6d002
commit 46e4e75d05
13 changed files with 721 additions and 44 deletions

View File

@@ -0,0 +1,108 @@
"""The v2 brain's compact prompt (voice_worker.spec.md, "History and brain").
Strata reads every prompt from the start, so prompt length is reply latency. Behaviour: the compact
prompt is far shorter than v1's for the same turn, still carries the tool honesty rules and the
reply-language default, and brings the full tool guidance only on turns that offer a data tool.
"""
from unittest.mock import Mock, patch
import pytest
from src.jarvis.memory.conversation import DialogueMemory
from src.jarvis.memory.history import HistoryContext
from src.jarvis.reply.engine import run_reply_engine
from src.jarvis.reply.prompts.model_variants import TOOL_CONSTRAINTS_LARGE
from src.jarvis.system_prompt import COMPACT_ACTION_RULE, TOOL_HONESTY_RULES, default_language_directive
from tests.test_ollama_num_predict import _mock_cfg
def _system_prompt(compact, routed):
cfg = _mock_cfg(512)
cfg.stream_browser = False
cfg.tool_selection_strategy = "llm"
with patch("src.jarvis.reply.engine.plan_query", return_value=["Reply to the user."]), \
patch("src.jarvis.reply.engine.select_tools", return_value=list(routed)), \
patch("src.jarvis.reply.engine._extra_config", lambda key, default="": default), \
patch("src.jarvis.reply.engine.extract_text_from_response", return_value="네."), \
patch("src.jarvis.reply.engine.chat_with_messages") as mock_chat:
mock_chat.return_value = {"message": {"content": "네."}}
run_reply_engine(db=Mock(), cfg=cfg, tts=None, text="안녕?", dialogue_memory=DialogueMemory(),
history=HistoryContext(), legacy_memory=False, default_language="Korean",
compact_prompt=compact)
messages = mock_chat.call_args.kwargs.get("messages") or mock_chat.call_args.args[2]
return messages[0]["content"]
@pytest.mark.unit
@pytest.mark.parametrize("routed", [[], ["getWeather"]])
def test_the_compact_prompt_is_far_shorter_and_keeps_the_rules(routed):
full, compact = _system_prompt(False, routed), _system_prompt(True, routed)
assert len(compact) < len(full) * 0.6, (len(compact), len(full))
for prompt in (full, compact):
assert TOOL_HONESTY_RULES in prompt
assert default_language_directive("Korean") in prompt
@pytest.mark.unit
def test_the_full_tool_guidance_comes_only_with_a_data_tool():
chatty = _system_prompt(True, [])
assert COMPACT_ACTION_RULE in chatty and TOOL_CONSTRAINTS_LARGE not in chatty
weather = _system_prompt(True, ["getWeather"])
assert TOOL_CONSTRAINTS_LARGE in weather and COMPACT_ACTION_RULE not in weather
def _intent_turn(prepared, routed=("getWeather",)):
cfg = _mock_cfg(512)
cfg.stream_browser = False
cfg.tool_selection_strategy = "llm"
with patch("src.jarvis.reply.engine.plan_query", return_value=["Reply to the user."]) as planner, \
patch("src.jarvis.reply.engine.select_tools", return_value=list(routed)) as router, \
patch("src.jarvis.reply.engine._extra_config", lambda key, default="": default), \
patch("src.jarvis.reply.engine.extract_text_from_response", return_value="네."), \
patch("src.jarvis.reply.engine.chat_with_messages") as mock_chat:
mock_chat.return_value = {"message": {"content": "네."}}
run_reply_engine(db=Mock(), cfg=cfg, tts=None, text="날씨 어때?", dialogue_memory=DialogueMemory(),
history=HistoryContext(), legacy_memory=False, intent_judge=True,
prepared_tools=prepared)
tools = [t["function"]["name"] for t in (mock_chat.call_args.kwargs.get("tools") or [])]
return planner.call_count, router.call_count, tools
@pytest.mark.unit
def test_the_intent_judge_plans_only_turns_that_need_a_tool():
# No tool needed: one router call, then the answer.
assert _intent_turn(None, routed=())[:2] == (0, 1)
# A tool turn: the planner orders the steps.
planner, router, tools = _intent_turn(None)
assert (planner, router) == (1, 1) and "getWeather" in tools
@pytest.mark.unit
def test_a_prepared_pick_replaces_the_router_call():
planner, router, tools = _intent_turn([])
assert (planner, router) == (0, 0)
planner, router, tools = _intent_turn(["webSearch"])
assert (planner, router) == (1, 0) and "webSearch" in tools and "getWeather" not in tools
@pytest.mark.unit
@pytest.mark.parametrize("stream", [False, True])
def test_screen_share_tools_are_offered_only_in_screen_share_mode(stream):
cfg = _mock_cfg(512)
cfg.stream_browser = stream
cfg.tool_selection_strategy = "llm"
with patch("src.jarvis.reply.engine.plan_query", return_value=[]), \
patch("src.jarvis.reply.engine.select_tools", return_value=[]) as router, \
patch("src.jarvis.reply.engine._extra_config", lambda key, default="": default), \
patch("src.jarvis.reply.engine._maybe_deterministic_site_search", return_value=None), \
patch("src.jarvis.reply.engine.extract_text_from_response", return_value="네."), \
patch("src.jarvis.reply.engine.chat_with_messages") as mock_chat:
mock_chat.return_value = {"message": {"content": "네."}}
run_reply_engine(db=Mock(), cfg=cfg, tts=None, text="피곤하다", dialogue_memory=DialogueMemory(),
history=HistoryContext(), legacy_memory=False)
offered = set(router.call_args.kwargs["builtin_tools"])
screen = {"controlBrowser", "browseAndPlay", "setBroadcast"}
assert (screen <= offered) if stream else not (screen & offered)
assert "getWeather" in offered

View File

@@ -297,3 +297,21 @@ class TestTextToolCallGuidancePrompt:
"an example would reinforce the exact behaviour we want to "
"stop."
)
class TestToolCallBlockAsText:
"""`<tool_call>` blocks written as the reply (Qwen XML or Hermes JSON) are tool calls, not
speech, also for a tool that is not on offer (the engine then says it is not available)."""
def test_qwen_xml(self):
content = ("<tool_call>\n<function=setTimer>\n<parameter=duration>\n5 minutes\n</parameter>\n"
"</function>\n</tool_call>")
name, args, call_id = _extract(content)
assert name == "setTimer" and args == {"duration": "5 minutes"} and call_id
def test_hermes_json(self):
name, args, _ = _extract('<tool_call>\n{"name": "webSearch", "arguments": {"search_query": "x"}}\n</tool_call>')
assert name == "webSearch" and args == {"search_query": "x"}
def test_prose_mentioning_tags_is_not_a_call(self):
assert _extract("I would call <tool_call> if I could.")[0] is None

View File

@@ -372,9 +372,11 @@ def test_the_brain_answers_in_korean_by_default_even_with_a_v1_english_voice(tmp
seen = {}
def fake_engine(db, cfg, tts, text, mem, language=None, history=None, legacy_memory=True,
default_language=None):
default_language=None, compact_prompt=False, **kw):
seen["directive"] = reply_language_directive(None, cfg.tts_engine, default_language)
seen["language"] = language
seen["compact"] = compact_prompt
seen["stream_browser"] = cfg.stream_browser
return "ok"
import jarvis.reply.engine as engine
@@ -382,6 +384,8 @@ def test_the_brain_answers_in_korean_by_default_even_with_a_v1_english_voice(tmp
brain_mod.JarvisBrain().reply("100", "what time is it?", HistoryContext())
assert seen["directive"] == default_language_directive("Korean")
assert seen["language"] == "ko"
# The short voice prompt, and no v1 screen-share browser (it needs v1's Node bot).
assert seen["compact"] is True and seen["stream_browser"] is False
# Without a default the brain answers in the asker's language.
brain_mod.JarvisBrain(language=None, reply_language=None).reply("100", "q", HistoryContext())
assert seen["directive"] is None and seen["language"] is None
@@ -966,3 +970,138 @@ def test_a_chat_question_the_app_never_reports_counts_as_not_posted(store):
actions, results = run_delete_then_yes(store, dict(via="chat", speak=False), no_report,
delivery_timeout_s=0.1)
assert actions == [] and results == [("지워", True), ("응, 지워", False)]
class PreparingBrain(FakeBrain):
"""Each prepare waits until the test lets it finish."""
def __init__(self):
super().__init__()
import threading
self.prepared = []
self.release = threading.Event()
def prepare(self, user, text, chat):
self.prepared.append((user, text, chat))
self.release.wait(5)
@pytest.mark.unit
def test_prepare_runs_one_at_a_time_per_user_and_only_the_newest_different_text_waits(store):
brain = PreparingBrain()
async def body(url):
async with connect(url) as ws:
await hello(ws, stt={"partials": False})
await send(ws, type="prepare", user="100", text="자비스 오늘")
await asyncio.sleep(0.2)
await send(ws, type="prepare", user="100", text="자비스 오늘 서울")
await send(ws, type="prepare", user="100", text="자비스 오늘 서울 날씨 어때")
await send(ws, type="prepare", user="200", text="자비스 안녕")
await asyncio.sleep(0.2)
assert sorted(brain.prepared) == [("100", "자비스 오늘", False), ("200", "자비스 안녕", False)]
brain.release.set()
await asyncio.sleep(0.3)
# About the same as the one just prepared: not prepared again.
await send(ws, type="prepare", user="100", text="자비스 오늘 서울 날씨 어때?")
await asyncio.sleep(0.3)
await send(ws, type="reply", id="r1", user="100", text="x", via="voice", speak=False)
return await recv_until(ws, lambda m: isinstance(m, dict) and m.get("type") == "reply_text")
seen = asyncio.run(with_worker(body, store=store, brain=brain))
assert [t for u, t, _ in brain.prepared if u == "100"] == ["자비스 오늘", "자비스 오늘 서울 날씨 어때"]
assert not [m for m in seen if isinstance(m, dict) and m.get("type") == "error"], "nothing is sent back"
@pytest.mark.unit
def test_a_brain_without_prepare_ignores_it(store):
async def body(url):
async with connect(url) as ws:
await hello(ws, stt={"partials": False})
await send(ws, type="prepare", user="100", text="자비스 안녕")
await send(ws, type="reply", id="r1", user="100", text="hi", via="voice", speak=False)
return await recv_until(ws, lambda m: isinstance(m, dict) and m.get("type") == "reply_text")
seen = asyncio.run(with_worker(body, store=store, brain=FakeBrain()))
assert not [m for m in seen if isinstance(m, dict) and m.get("type") == "error"]
def _jarvis_brain(tmp_path, monkeypatch, plans):
"""A real JarvisBrain with the engine's judge and reply replaced: ``plans`` maps text to a pick."""
pytest.importorskip("mcp") # the real brain needs the jarvis dependencies (--brain)
from voice_worker import brain as brain_mod
import jarvis.reply.engine as engine
cfg = tmp_path / "config.json"
cfg.write_text(json.dumps({"db_path": str(tmp_path / "jarvis.db")}))
monkeypatch.setenv("JARVIS_CONFIG_PATH", str(cfg))
seen = {"judged": [], "prepared": []}
def fake_prepare(cfg, text, mem, chat_available):
seen["judged"].append((text, chat_available))
return plans.get(text)
def fake_engine(db, cfg, tts, text, mem, prepared_tools=None, intent_judge=False, **kw):
seen["prepared"].append(prepared_tools)
seen["intent_judge"] = intent_judge
mem.add_message("user", text)
mem.add_message("assistant", "ok")
return "ok"
monkeypatch.setattr(engine, "prepare_intent", fake_prepare)
monkeypatch.setattr(engine, "run_reply_engine", fake_engine)
return brain_mod.JarvisBrain(), seen
@pytest.mark.unit
def test_a_reply_uses_the_pick_prepared_for_about_the_same_text(tmp_path, monkeypatch):
from jarvis.memory.history import HistoryContext
plan = ["getWeather"]
b, seen = _jarvis_brain(tmp_path, monkeypatch, {"자비스 오늘 서울 날씨 어": plan})
b.prepare("100", "자비스 오늘 서울 날씨 어", True)
assert seen["judged"] == [("자비스 오늘 서울 날씨 어", True)]
b.reply("100", "자비스, 오늘 서울 날씨 어때?", HistoryContext())
assert seen["prepared"] == [plan] and seen["intent_judge"] is True
# Used once: the next reply judges for itself.
b.reply("100", "자비스, 오늘 서울 날씨 어때?", HistoryContext())
assert seen["prepared"][-1] is None
@pytest.mark.unit
def test_a_prepared_pick_is_not_used_for_other_words_another_person_or_a_changed_dialogue(tmp_path, monkeypatch):
from jarvis.memory.history import HistoryContext
plan = ["webSearch"]
b, seen = _jarvis_brain(tmp_path, monkeypatch, {"자비스 오늘 서울 날씨 어때": plan})
b.prepare("100", "자비스 오늘 서울 날씨 어때", False)
b.reply("100", "자비스, 내일 회의 몇 시지?", HistoryContext())
b.prepare("100", "자비스 오늘 서울 날씨 어때", False)
b.reply("200", "자비스 오늘 서울 날씨 어때", HistoryContext())
assert seen["prepared"] == [None, None]
b.prepare("100", "자비스 오늘 서울 날씨 어때", False)
b._memory("100").add_message("user", "something said meanwhile")
b.reply("100", "자비스 오늘 서울 날씨 어때", HistoryContext())
assert seen["prepared"][-1] is None
@pytest.mark.unit
def test_a_reply_waits_for_a_pick_still_being_prepared_for_its_text(tmp_path, monkeypatch):
import threading
import time as _time
from jarvis.memory.history import HistoryContext
plan = [] # "no tools" is a pick too
b, seen = _jarvis_brain(tmp_path, monkeypatch, {})
import jarvis.reply.engine as engine
def slow_prepare(cfg, text, mem, chat_available):
_time.sleep(0.4)
return plan
monkeypatch.setattr(engine, "prepare_intent", slow_prepare)
t = threading.Thread(target=b.prepare, args=("100", "자비스 날씨 어때", False))
t.start()
_time.sleep(0.1)
b.reply("100", "자비스 날씨 어때?", HistoryContext())
t.join()
assert seen["prepared"] == [plan]