Marius Mutu
e79bed7afe
Voice utterances and text messages on the same Discord channel now share one Claude session, and Echo's voice replies are mirrored back into the text channel. Replaces the old voice:<id> session-key split. Changes: - src/adapters/_text_chunks.py: new leaf module for split_message (used by both discord_bot and voice pipeline) - src/router.py: drop voice: prefix from session_key; add [voice] marker; strip leading [speaker:/[voice] tokens from user input (anti-jailbreak); remove dead double-clear of voice: key - src/claude_session.py: include personality/VOICE_MODE.md unconditionally (rules become per-turn-aware via [speaker:] prefix instead of session flag) - src/voice/pipeline.py: VoiceSession splits text_channel_id + voice_channel_id; resolve text channel per-send (no stale refs); mirror Echo's reply text into the text channel after route_message returns - src/adapters/discord_voice.py: /voice join passes both channel ids - src/adapters/discord_bot.py: import split_message from leaf module - personality/VOICE_MODE.md: rewrite as per-turn dynamic rules; add synthesis instructions for text turns after voice turns Tests: - tests/test_router.py: 4 new cases (plain channel_id, anti-jailbreak, text-adapter regression, no-double-clear) - tests/test_pipeline_mirror.py: new — Echo reply mirror chunking, empty guard, mirror_enabled=False, send-raises resilience - tests/test_voice_session_channel_ids.py: new — split-attr contract + metrics payload schema - tests/test_voice_session_cleanup.py: update for new kwargs Plan: /home/moltbot/.claude/plans/vreau-ca-tot-textul-greedy-rivest.md Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
125 lines
4.2 KiB
Python
125 lines
4.2 KiB
Python
"""Echo-reply text mirror: VoiceSession.on_segment_done forwards Claude's
|
|
reply back into the originating text channel, chunked to Discord's 2000-char
|
|
limit, gated on mirror_enabled, and resilient to send failures.
|
|
|
|
The pipeline calls router.route_message via the injected
|
|
`router_route_message` seam so tests can drive the reply text without
|
|
monkey-patching modules or invoking the real Claude subprocess.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
|
|
from src.voice.pipeline import VoiceSession
|
|
|
|
|
|
def _make_text_channel(send_mock: AsyncMock) -> MagicMock:
|
|
tc = MagicMock(name="text_channel")
|
|
tc.send = send_mock
|
|
return tc
|
|
|
|
|
|
def _make_session(
|
|
*,
|
|
reply_text: str,
|
|
text_channel,
|
|
mirror_enabled: bool = True,
|
|
) -> VoiceSession:
|
|
bot = MagicMock(name="bot")
|
|
bot.get_channel = MagicMock(return_value=text_channel)
|
|
bot.get_user = MagicMock(return_value=None)
|
|
ttsq = MagicMock(name="ttsq")
|
|
ttsq.push_text = MagicMock()
|
|
ttsq.clear = MagicMock()
|
|
route_mock = MagicMock(name="route_message", return_value=(reply_text, False))
|
|
return VoiceSession(
|
|
text_channel_id=1001,
|
|
voice_channel_id=2002,
|
|
guild_id=42,
|
|
voice_client=MagicMock(name="voice_client"),
|
|
bot=bot,
|
|
ttsq=ttsq,
|
|
whitelist=set(),
|
|
record_enabled=False,
|
|
mirror_enabled=mirror_enabled,
|
|
transcripts_jsonl_path=None,
|
|
loop=asyncio.get_event_loop_policy().new_event_loop(),
|
|
router_route_message=route_mock,
|
|
)
|
|
|
|
|
|
def _reply_chunks(send_mock: AsyncMock) -> list[str]:
|
|
# Drop the user-mirror call (starts with the 🎤 microphone emoji); the
|
|
# rest are reply chunks.
|
|
return [
|
|
call.args[0]
|
|
for call in send_mock.call_args_list
|
|
if not call.args[0].startswith("\U0001f3a4")
|
|
]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_long_reply_splits_into_multiple_chunks():
|
|
long_reply = "răspuns lung " * 200 # ~2600 chars → ≥2 chunks at 2000-char limit
|
|
send_mock = AsyncMock(name="text_send")
|
|
text_channel = _make_text_channel(send_mock)
|
|
session = _make_session(reply_text=long_reply, text_channel=text_channel)
|
|
|
|
await session.on_segment_done(speaker_id=123, text="salut", no_speech_prob=0.1)
|
|
|
|
chunks = _reply_chunks(send_mock)
|
|
assert len(chunks) >= 2
|
|
assert "".join(chunks).replace("\n", "").strip().startswith("răspuns lung")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_empty_reply_emits_no_reply_chunks():
|
|
send_mock = AsyncMock(name="text_send")
|
|
text_channel = _make_text_channel(send_mock)
|
|
session = _make_session(reply_text="", text_channel=text_channel)
|
|
|
|
await session.on_segment_done(speaker_id=123, text="salut", no_speech_prob=0.1)
|
|
|
|
assert _reply_chunks(send_mock) == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_whitespace_only_reply_emits_no_reply_chunks():
|
|
send_mock = AsyncMock(name="text_send")
|
|
text_channel = _make_text_channel(send_mock)
|
|
session = _make_session(reply_text=" \n\t ", text_channel=text_channel)
|
|
|
|
await session.on_segment_done(speaker_id=123, text="salut", no_speech_prob=0.1)
|
|
|
|
assert _reply_chunks(send_mock) == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mirror_disabled_sends_nothing():
|
|
send_mock = AsyncMock(name="text_send")
|
|
text_channel = _make_text_channel(send_mock)
|
|
session = _make_session(
|
|
reply_text="orice răspuns", text_channel=text_channel, mirror_enabled=False,
|
|
)
|
|
|
|
await session.on_segment_done(speaker_id=123, text="salut", no_speech_prob=0.1)
|
|
|
|
assert send_mock.call_count == 0
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_send_failure_is_swallowed(caplog):
|
|
send_mock = AsyncMock(name="text_send", side_effect=RuntimeError("discord 500"))
|
|
text_channel = _make_text_channel(send_mock)
|
|
session = _make_session(reply_text="răspuns scurt", text_channel=text_channel)
|
|
|
|
with caplog.at_level("WARNING"):
|
|
# Must not raise — both user-mirror and reply-mirror trap exceptions.
|
|
await session.on_segment_done(speaker_id=123, text="salut", no_speech_prob=0.1)
|
|
|
|
# At least one warning was logged for a mirror send failure.
|
|
assert any("mirror" in rec.message.lower() for rec in caplog.records)
|