Files
javis_bot/tests/test_engine_compact_prompt.py
javis-bot 46e4e75d05 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>
2026-11-12 12:25:15 +09:00

109 lines
5.5 KiB
Python

"""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