Senad Uka 0d0838e6e2 M2: agent logic in text mode
- LLMProvider interface: AnthropicLLM + ScriptedLLM test fake
- System prompt composition from super-admin template + structured tenant
  data only (§6.3); auto-generated greetings with recording disclosure,
  out-of-hours variant, chat variant
- Agent tools (§6.5): get_salon_info, check_availability (≤8 slots to model,
  agent offers ≤3), submit_booking_request (caller-ID fallback, hallucinated
  service-id guard), take_message
- Conversation loop with tool dispatch, round-limit guard, transcript capture,
  outcome classification (request_created/message_taken/info_only/abandoned)
- Terminal playground (python -m gogo.agent.cli) + demo seed (python -m gogo.seed)
- Deterministic loop tests (ScriptedLLM) + Appendix A golden-scenario
  acceptance tests against a real LLM (skipped without an API key)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-11 09:53:08 +02:00
2026-07-11 09:45:06 +02:00
2026-07-11 09:53:08 +02:00
2026-07-11 09:53:08 +02:00
2026-07-11 09:45:06 +02:00
2026-07-11 09:45:06 +02:00
2026-07-11 09:45:06 +02:00
2026-07-11 09:45:06 +02:00

Gogo Telefon

Voice-first AI receptionist for small service businesses in Bosnia and Herzegovina. The agent answers forwarded calls (and web chat), speaks Bosnian, checks real availability and sends booking proposals to the salon owner — it never books appointments itself. See docs/ and the product spec for details.

Architecture (short version)

caller → salon number (conditional forwarding) → GSM gateway → Asterisk
       → ring group (staff softphones) → no answer → voice agent (Pipecat)
       → tools HTTP → FastAPI backend → SchedulingProvider (Google Calendar | Partner API)
       → proposal email / partner push → owner action → (optional) SMS to client

Everything self-hosted except LLM + TTS APIs (swappable interfaces).

Development

uv venv && uv pip install -e '.[dev]'
docker compose up -d db        # Postgres 16 on localhost:5433 (or use your own)
export GOGO_DATABASE_URL=postgresql+psycopg://gogo:gogo@localhost:5432/gogo
.venv/bin/alembic upgrade head
.venv/bin/uvicorn gogo.main:app --reload

Run tests (SQLite, no services needed):

.venv/bin/python -m pytest

The fake partner booking API used in tests (tests/fake_partner.py) doubles as the reference implementation of Appendix B for partner IT teams:

.venv/bin/uvicorn tests.fake_partner:app --port 9100

Layout

Path What
gogo/scheduling/ SchedulingProvider interface + google_calendar, partner_api, mock
gogo/proposals/ proposal engine, action tokens, owner emails, .ics
gogo/sms/ SmsProvider (console now, GSM gateway in M5) + Bosnian templates
gogo/api/ action links, partner webhook, health
gogo/agent/ LLM agent: prompt composition, tools, conversation loop (M2)
gogo/voice/ Pipecat voice pipeline (M4)
gogo/telephony/ Asterisk/GSM/forwarding codes (M4/M5)
tests/fake_partner.py Appendix B reference implementation

All code/comments in English; all client- and owner-facing text in Bosnian (Latin).

Description
No description provided
Readme 223 KiB
Languages
Python 87.2%
HTML 11.3%
JavaScript 1.3%
Mako 0.1%