8a2a109d5e
Harden the reply-language lock so qwen2.5:3b reliably stays in the locked language instead of leaking the query language back in: - reply_language_directive(): single resolver with clear precedence — explicit OUTPUT_LANGUAGE lock wins over the Piper/Chatterbox English-only fallback (this deployment's actual TTS is Korean MeloTTS, so the legacy English lock was both wrong and contradicting the Korean lock). - Stronger, override-explicit directive wording, inserted near the FRONT of the system prompt so a small model gives it primacy over the persona. - build_system_prompt(output_language=...): rewrite the persona's "in the user's language" clause to the locked language so the persona stops fighting the lock. - docs/llm_contexts.md: document the resolver, precedence, and placement. Live-verified on the running brain (qwen2.5:3b): Korean voice-style input and a cold English query both return fully Korean replies with no CJK/Hanja leak. Tests cover unset/set/agnostic/whitespace + precedence + persona rewrite.
111 lines
4.5 KiB
Python
111 lines
4.5 KiB
Python
"""Tests for the unified persona system prompt.
|
|
|
|
The persona should match the user's configured wake word so renaming the
|
|
wake word to e.g. "Friday" produces a butler named Friday, not one still
|
|
hardcoded to Jarvis.
|
|
"""
|
|
|
|
from jarvis.system_prompt import (
|
|
build_system_prompt,
|
|
output_language_directive,
|
|
reply_language_directive,
|
|
ENGLISH_ONLY_DIRECTIVE,
|
|
)
|
|
|
|
|
|
class TestBuildSystemPrompt:
|
|
def test_default_name_is_jarvis(self):
|
|
prompt = build_system_prompt()
|
|
assert "named Jarvis" in prompt
|
|
|
|
def test_custom_name_replaces_jarvis(self):
|
|
prompt = build_system_prompt("Friday")
|
|
assert "named Friday" in prompt
|
|
assert "named Jarvis" not in prompt
|
|
|
|
def test_lowercase_wake_word_is_capitalised(self):
|
|
prompt = build_system_prompt("friday".capitalize())
|
|
assert "named Friday" in prompt
|
|
|
|
def test_blank_name_falls_back_to_jarvis(self):
|
|
assert "named Jarvis" in build_system_prompt("")
|
|
assert "named Jarvis" in build_system_prompt(" ")
|
|
assert "named Jarvis" in build_system_prompt(None) # type: ignore[arg-type]
|
|
|
|
def test_default_keeps_user_language_clause(self):
|
|
# Without a lock, the persona still mirrors the user's language.
|
|
assert "in the user's language" in build_system_prompt("Jarvis")
|
|
|
|
def test_language_lock_rewrites_user_language_clause(self):
|
|
# With a lock, the contradicting "user's language" clause is rewritten
|
|
# so the persona does not fight the OUTPUT_LANGUAGE directive.
|
|
prompt = build_system_prompt("Jarvis", "Korean")
|
|
assert "in the user's language" not in prompt
|
|
assert "in Korean" in prompt
|
|
|
|
|
|
class TestOutputLanguageDirective:
|
|
"""A deployment may lock replies to a single language via OUTPUT_LANGUAGE.
|
|
|
|
Unset (the default) must keep the assistant's multilingual behaviour of
|
|
replying in the user's own language, so the helper returns None and no
|
|
directive is injected.
|
|
"""
|
|
|
|
def test_unset_returns_none(self):
|
|
assert output_language_directive(None) is None
|
|
assert output_language_directive("") is None
|
|
assert output_language_directive(" ") is None
|
|
|
|
def test_set_language_is_named_and_exclusive(self):
|
|
directive = output_language_directive("Korean")
|
|
assert directive is not None
|
|
assert "Korean" in directive
|
|
# Must force exclusivity, not merely prefer the language.
|
|
assert "only" in directive.lower()
|
|
|
|
def test_language_agnostic(self):
|
|
# The helper takes any language string — no hardcoded single language.
|
|
assert "French" in (output_language_directive("French") or "")
|
|
assert "日本語" in (output_language_directive("日本語") or "")
|
|
|
|
def test_strips_surrounding_whitespace(self):
|
|
directive = output_language_directive(" Korean ")
|
|
assert directive is not None
|
|
assert "Korean" in directive
|
|
assert " Korean" not in directive
|
|
|
|
|
|
class TestReplyLanguageDirective:
|
|
"""Precedence: explicit OUTPUT_LANGUAGE lock > English-only TTS > free.
|
|
|
|
The lock must override the Piper/Chatterbox English fallback, because a
|
|
deployment that sets OUTPUT_LANGUAGE (e.g. Korean) also runs a TTS voice
|
|
that can speak it. Without this, the English lock and the Korean lock
|
|
contradict each other and the model reverts to English.
|
|
"""
|
|
|
|
def test_lock_overrides_english_only_tts(self):
|
|
directive = reply_language_directive("Korean", "piper")
|
|
assert directive is not None
|
|
assert "Korean" in directive
|
|
assert directive != ENGLISH_ONLY_DIRECTIVE
|
|
|
|
def test_english_only_tts_forces_english_without_lock(self):
|
|
assert reply_language_directive(None, "piper") == ENGLISH_ONLY_DIRECTIVE
|
|
assert reply_language_directive("", "chatterbox") == ENGLISH_ONLY_DIRECTIVE
|
|
|
|
def test_no_lock_multilingual_tts_is_free(self):
|
|
# A non-English-only engine (e.g. melo) with no lock → reply in the
|
|
# user's own language, so no directive.
|
|
assert reply_language_directive(None, "melo") is None
|
|
|
|
def test_unknown_tts_defaults_to_english_only(self):
|
|
# Preserves the original getattr(cfg, 'tts_engine', 'piper') default:
|
|
# an unknown/missing engine is treated conservatively as English-only.
|
|
assert reply_language_directive(None, None) == ENGLISH_ONLY_DIRECTIVE
|
|
|
|
def test_lock_wins_even_with_multilingual_tts(self):
|
|
directive = reply_language_directive("Korean", "melo")
|
|
assert directive is not None and "Korean" in directive
|