7bb9718c34
Replies stayed long because the prompt stack gave conflicting length signals: the persona said "one sentence (two at the very most)" AND told the model to "state the answer in a sentence, then add a dry observation" (a 2nd sentence), while voice_style said "two to three sentences maximum". The model followed the longest. Make all three sources agree on exactly one sentence: the persona's aside must now fold into the same sentence as a trailing clause (never a 2nd sentence), voice_style caps at one sentence, and agents/llm.md says 한 문장. Shorter replies also cut Edge-TTS latency, since synth time scales with text length. Specs (prompts.spec.md) and docs/llm_contexts.md updated; deterministic prompt-contract tests added.
190 lines
8.3 KiB
Python
190 lines
8.3 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,
|
|
load_agent_instructions,
|
|
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
|
|
|
|
def test_persona_enforces_single_sentence(self):
|
|
# Spoken replies must be one sentence (TTS latency scales with text
|
|
# length, and the user asked for one-sentence answers). The persona must
|
|
# state the single-sentence rule and must NOT carry the old "two at the
|
|
# very most" allowance that let the model run long.
|
|
prompt = build_system_prompt("Jarvis")
|
|
assert "single short sentence" in prompt
|
|
assert "Never write a second sentence" in prompt
|
|
assert "two at the very most" not in prompt
|
|
|
|
def test_persona_aside_does_not_authorise_a_second_sentence(self):
|
|
# The dry aside must fold into the one sentence, not become a 2nd one.
|
|
prompt = build_system_prompt("Jarvis")
|
|
assert "SINGLE sentence" in prompt
|
|
assert "never add it as " 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
|
|
|
|
def test_edge_is_multilingual(self):
|
|
# Edge TTS (the default Korean voice) is not English-only: no lock → the
|
|
# user's own language, and a lock is honoured (not forced to English).
|
|
assert reply_language_directive(None, "edge") is None
|
|
directive = reply_language_directive("Korean", "edge")
|
|
assert directive is not None and "Korean" in directive
|
|
assert directive != ENGLISH_ONLY_DIRECTIVE
|
|
|
|
|
|
class TestLoadAgentInstructions:
|
|
"""Operator can extend the reply LLM's system prompt by dropping *.md files
|
|
into an agents/ folder. The loader concatenates them in filename order and
|
|
fails open so a missing/empty/broken folder never breaks a reply."""
|
|
|
|
def test_missing_dir_returns_empty(self, tmp_path):
|
|
assert load_agent_instructions(str(tmp_path / "does-not-exist")) == ""
|
|
|
|
def test_empty_dir_returns_empty(self, tmp_path):
|
|
assert load_agent_instructions(str(tmp_path)) == ""
|
|
|
|
def test_reads_and_concatenates_single_file(self, tmp_path):
|
|
(tmp_path / "rules.md").write_text("Always be brief.", encoding="utf-8")
|
|
assert load_agent_instructions(str(tmp_path)) == "Always be brief."
|
|
|
|
def test_files_are_ordered_by_filename(self, tmp_path):
|
|
# Filename prefixes let the operator control ordering.
|
|
(tmp_path / "10-second.md").write_text("SECOND", encoding="utf-8")
|
|
(tmp_path / "00-first.md").write_text("FIRST", encoding="utf-8")
|
|
result = load_agent_instructions(str(tmp_path))
|
|
assert result.index("FIRST") < result.index("SECOND")
|
|
|
|
def test_only_md_files_are_read(self, tmp_path):
|
|
(tmp_path / "note.txt").write_text("IGNORE ME", encoding="utf-8")
|
|
(tmp_path / "use.md").write_text("USE ME", encoding="utf-8")
|
|
result = load_agent_instructions(str(tmp_path))
|
|
assert "USE ME" in result
|
|
assert "IGNORE ME" not in result
|
|
|
|
def test_blank_files_are_skipped(self, tmp_path):
|
|
(tmp_path / "blank.md").write_text(" \n ", encoding="utf-8")
|
|
(tmp_path / "real.md").write_text("Real instruction.", encoding="utf-8")
|
|
assert load_agent_instructions(str(tmp_path)) == "Real instruction."
|
|
|
|
def test_env_var_is_used_when_no_arg(self, tmp_path, monkeypatch):
|
|
(tmp_path / "a.md").write_text("FROM ENV", encoding="utf-8")
|
|
monkeypatch.setenv("AGENTS_DIR", str(tmp_path))
|
|
assert load_agent_instructions() == "FROM ENV"
|
|
|
|
def test_explicit_arg_overrides_env(self, tmp_path, monkeypatch):
|
|
(tmp_path / "env.md").write_text("ENV", encoding="utf-8")
|
|
other = tmp_path / "other"
|
|
other.mkdir()
|
|
(other / "arg.md").write_text("ARG", encoding="utf-8")
|
|
monkeypatch.setenv("AGENTS_DIR", str(tmp_path))
|
|
assert load_agent_instructions(str(other)) == "ARG"
|
|
|
|
def test_a_file_path_instead_of_dir_returns_empty(self, tmp_path):
|
|
f = tmp_path / "file.md"
|
|
f.write_text("x", encoding="utf-8")
|
|
# Pointed at a file, not a directory → fail-open.
|
|
assert load_agent_instructions(str(f)) == ""
|