Marius Mutu
e589e4885e
Second voice UX iteration. Targets Marius's live-test pain points from today.
- **Voice-mode system prompt** (personality/VOICE_MODE.md, plumbed via
claude_session.build_system_prompt(voice_mode=True)) — when the voice
adapter starts a session, append voice-tailored instructions: short replies,
no markdown, no abbreviations, time without seconds, distances rounded
to "mii"/"milioane", no curly quotes / em-dash / ellipsis. Marius asked
for a "in-the-car friend" persona for voice.
- **Isolated voice session key** (router.py) — voice mode uses
`voice:<channel_id>` so it doesn't share context with the text adapter
on the same Discord channel. Fresh start, voice prompt applied
automatically without `/clear` ceremony. `/clear` drops both keys.
- **Metric units + Romanian thousands** (src/voice/normalize.py) —
`384.000 km` was being read as "trei sute optzeci și patru virgulă zero
zero zero km" because the dot was treated as decimal separator and `km`
wasn't expanded. New `normalize_thousands` collapses Romanian thousands
separators (`X.000`/`X.000.000`) before number expansion, and
`expand_units` handles km/kg/cm/mm/ml/ha/mp with correct Romanian
pluralization ("un kilometru", "două kilograme", "douăzeci de
centimetri", "o sută de kilometri" with "de" particle).
- **`/voice setvoice <M1-F5>` slash command** (discord_voice.py) — Discord
native autocomplete; swaps the live TTSQueue voice_id AND persists
voice.default_voice to config.json. No restart needed.
- **Verbal voice change** (src/voice/voice_commands.py — new module +
29 tests) — say "schimbă vocea pe M5" / "vorbește cu vocea F3" / "voce
em cinci" from inside the voice channel. Detector requires both a
trigger word (voce/vorbește/schimbă/treci pe) and a recognizable voice
ID (direct "M5", word form "em cinci", or fallback substring match for
Whisper-mangled forms like "unul cinci"=M5 and "Mâcinci"=M5). On
detection: live-swap, persist to config, mirror to chat with
`🎤 ... / 🔊 Voce → M5`, speak short ack in the NEW voice, skip
Claude. "pământinci" still can't be recovered (no recoverable digit
substring); user gets passthrough to Claude in that case.
- **Whisper initial_prompt** now lists the voice-command vocabulary so
STT biases toward producing clean "M5" / "F3" tokens instead of
inventing "pământ" / "unul" phonetic neighbors.
- **Fast barge-in** (pipeline.py EchoVoiceSink) — previously `ttsq.clear()`
only fired in `on_segment_done` (after 800ms silence + 2-3s STT ≈ 3s lag).
Now also fires from the sink as soon as VAD detects ≥2 consecutive
windows (~200ms) of sustained speech on Marius's user while Echo has
pending TTS frames. Single-window glitches don't cut Echo off; sustained
speech does. (Acoustic echo bleed-through still requires headphones —
no AEC in the bot.)
- Tests: 130 voice + router tests pass; updated test_router.py to expect
`/clear` to drop both text and voice session keys.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
123 lines
2.5 KiB
JSON
123 lines
2.5 KiB
JSON
{
|
|
"bot": {
|
|
"name": "Echo",
|
|
"default_model": "sonnet",
|
|
"owner": "949388626146517022",
|
|
"admins": [
|
|
"5040014994"
|
|
]
|
|
},
|
|
"channels": {
|
|
"echo-core": {
|
|
"id": "1471916752119009432",
|
|
"default_model": "sonnet"
|
|
},
|
|
"echo-work": {
|
|
"id": "1466726254312030259",
|
|
"default_model": "sonnet"
|
|
},
|
|
"echo-sprijin": {
|
|
"id": "1466739361503772864",
|
|
"default_model": "sonnet"
|
|
},
|
|
"echo-self": {
|
|
"id": "1466739112747864175",
|
|
"default_model": "sonnet"
|
|
}
|
|
},
|
|
"telegram_channels": {},
|
|
"whatsapp": {
|
|
"enabled": true,
|
|
"bridge_url": "http://127.0.0.1:8098",
|
|
"owner": "40723197939",
|
|
"admins": []
|
|
},
|
|
"whatsapp_channels": {
|
|
"echo-test": {
|
|
"id": "120363424350922235@g.us",
|
|
"default_model": "sonnet"
|
|
}
|
|
},
|
|
"heartbeat": {
|
|
"enabled": false,
|
|
"interval_minutes": 120,
|
|
"channel": "echo-core",
|
|
"model": "haiku",
|
|
"quiet_hours": [
|
|
23,
|
|
7
|
|
],
|
|
"checks": {
|
|
"email": true,
|
|
"calendar": true,
|
|
"kb_index": true,
|
|
"git": false
|
|
},
|
|
"cooldowns": {
|
|
"email": 1800,
|
|
"calendar": 1800,
|
|
"kb_index": 14400,
|
|
"git": 14400
|
|
}
|
|
},
|
|
"newsletter_cercetasi": {
|
|
"enabled": true,
|
|
"cron": "0 17 * * 4,5,1",
|
|
"channel": "echo-core"
|
|
},
|
|
"allowed_tools": [
|
|
"Read",
|
|
"Edit",
|
|
"Write",
|
|
"Glob",
|
|
"Grep",
|
|
"WebFetch",
|
|
"WebSearch",
|
|
"Bash(python3 *)",
|
|
"Bash(.venv/bin/python3 *)",
|
|
"Bash(pip *)",
|
|
"Bash(pytest *)",
|
|
"Bash(git *)",
|
|
"Bash(npm *)",
|
|
"Bash(node *)",
|
|
"Bash(npx *)",
|
|
"Bash(systemctl --user *)",
|
|
"Bash(trash *)",
|
|
"Bash(mkdir *)",
|
|
"Bash(cp *)",
|
|
"Bash(mv *)",
|
|
"Bash(ls *)",
|
|
"Bash(cat *)",
|
|
"Bash(chmod *)",
|
|
"Bash(docker *)",
|
|
"Bash(docker-compose *)",
|
|
"Bash(docker compose *)",
|
|
"Bash(ssh *@10.0.20.*)",
|
|
"Bash(ssh root@10.0.20.*)",
|
|
"Bash(ssh echo@10.0.20.*)",
|
|
"Bash(scp *10.0.20.*)",
|
|
"Bash(rsync *10.0.20.*)"
|
|
],
|
|
"discord": {
|
|
"email_webhook_url": "https://discord.com/api/webhooks/1496421990846697583/OM8z1eBsJC6-UB9-Zi5RkHP23NNv9UrEznRMx4Y3wSWOFmLazPoi-8_iEKMp0Qgsqr-m"
|
|
},
|
|
"ollama": {
|
|
"url": "http://10.0.20.161:11434"
|
|
},
|
|
"voice": {
|
|
"allowed_user_ids": [
|
|
"949388626146517022"
|
|
],
|
|
"user_name": "Marius",
|
|
"default_voice": "M5",
|
|
"auto_leave_minutes": 5
|
|
},
|
|
"paths": {
|
|
"personality": "personality/",
|
|
"tools": "tools/",
|
|
"memory": "memory/",
|
|
"logs": "logs/",
|
|
"sessions": "sessions/"
|
|
}
|
|
}
|