Both services/ai_orchestrator_service/voice.py and the aimaq persona/DOMAIN
SCOPE prompt were bind-mounted straight from the host on the aimaq stack,
bypassing git and CI entirely since they were first hand-edited in prod.
voice.py: merged the host's live business logic (gas/aimaq domain keyword
list, off-domain Kazakh/Russian replies, disabled re-correction of an already
obtained name) with the timeout_seconds fix from 09bcf74 that never reached
aimaq because the bind mount blocked it.
aimaq.env.production: replaced the AI_OPERATOR_* env values (which were never
interpolated -- {agent_name}/{company_name} would have been read literally)
with the final resolved Zhanna/Kazakgaz Aimaq text including the DOMAIN SCOPE
clause, matching what was actually live on the host.
Parametrize ai_operator_default_config() via AI_OPERATOR_* env vars,
falling back to the existing hardcoded defaults so the other two stacks
(call-center, sales-call-center) that share this code are unaffected.
Set aimaq-only overrides matching the client-provided script (Скрипт
ии-оператора КГА.docx): agent renamed to Жанна, company to Казакгаз
Аймак, the voice greeting now asks the caller whether Russian or
Kazakh is more convenient before anything else, and the base system
prompt instructs the model to commit to whichever language the caller
picks for the rest of the call, ask how to address them, and confirm
there's nothing else before saying goodbye.
Enables the new Routing Engine for the Tele2 Kazgaz DID +77476456048
(lands on queue 7100/voice_lab_ai): AI handoff now reserves a real L2
agent from the pool instead of the static extension redirect.
Streaming TTS caused poor voice quality in live testing on Creator
plan too — not just a quota-era fluke. Reverting to non-streaming
synthesis until the root cause is understood.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Lower AI_VOICE_VAD_TRAILING_SILENCE_MS from 500 to 350 so the bot
starts responding sooner after the caller stops speaking.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Swap RU and KK TTS voice IDs to "Nataly Mi Soft voice" — a soft,
gentle, young female voice verified for Russian on eleven_turbo_v2_5.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
AudioSocket was delivering 16kHz audio despite the telecom-kz trunk being
codec-restricted to alaw/ulaw, causing the 8k->16k ASR resample to double
an already-16kHz stream to an effective 32kHz labeled as 16000 Hz -
audible as slow, deep-pitched, unintelligible speech. Force
audioread/writeformat=slin before AudioSocket() so the channel always
delivers narrowband 8kHz, matching every rate assumption in the runtime.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
A separate deployment on the same host (aimaq-call-center) already binds
127.0.0.1:9019, so this project's ai-voice-runtime-service could never
start there. Remap the host side to 9024 and point Asterisk's
AudioSocket target at the new port; the container still listens on 9019
internally.
Wires the production number 87273901485 (SIP account 86205414@sip.telecom.kz)
into the voice stack as a no-registration IP trunk. Inbound INVITEs are
identified by source IP 92.46.61.21 and routed straight into the AI-first
entrypoint (7100), with the existing AudioSocket -> live operator fallback
preserved.
The Asterisk container was also never started by the source-based CI deploy
(only the registry-based path brought it up). Patch scripts/deploy_gitlab.sh
to also run docker-compose.asterisk.server.yml so the voice channel stays in
sync with the rest of the platform on every push to the default branch.
- deployment/asterisk/pjsip.conf: add telecom-kz aor/auth/endpoint/identify
- deployment/asterisk/entrypoint.sh: inject ASTERISK_TELECOM_KZ_PASSWORD
- deployment/asterisk/extensions.conf: new [from-telecom] context -> 7100
- .env.production.template: document ASTERISK_TELECOM_KZ_PASSWORD
- scripts/deploy_gitlab.sh: also bring up the asterisk compose file
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
arystanbek
arys
didar