9 Commits

Include renames

Author	SHA1	Message	Date
didar	d2438b6954	feat: canonical intent taxonomy for AI operator (kb_answer -> intent_code) ... Centralizes fixed control intents and adds a data-driven intent_code field on kb_articles so many phrasings of the same FAQ question resolve to one stable code (e.g. VOUCHER_ACTIVATION) instead of a free-form, unvalidated string the LLM invented on the fly. - services/shared/intents.py: CONTROL_INTENTS + normalize_intent() - kb_articles.intent_code column (ORM + dev/sqlite runtime compat + migrations/sql/0034_* for postgres/sqlite) - kb_service CRUD exposes intent_code - orchestrator surfaces intent_code to the LLM and validates its intent output against control intents + the KB codes shown that turn - voice.py: _voice_early_intent_bucket renamed to _voice_ack_topic_bucket to stop it being conflated with the canonical FAQ intent	2026-08-31 00:17:51 +05:00
Hermes Agent	2243f305b8	feat: L1->L2 agent pool and routing engine for voice escalation ... Replaces the hardcoded single-extension redirect for AI->human call escalation with a real Agent Pool + Routing Engine: - agents/escalations/routing_rules tables (migration 0031), asterisk_call_links gains tenant_id/current_level/required_skills_json/priority. - services/routing_service/engine.py: level/tenant/skill filtered agent selection with atomic (CAS) reservation, no double-booking. - routing-service: /agents CRUD + /internal/routing/reserve-agent and /internal/routing/release-agent. - asterisk-bridge-service: voice_ai.request_handoff now uses the Routing Engine automatically for any queue_code configured in ASTERISK_QUEUE_LEVEL_MAP_JSON (all other queue_codes keep the existing static ASTERISK_TRANSFER_TARGET_MAP_JSON behavior unchanged); new POST /asterisk/live-calls/{call_id}/escalations entrypoint; agent is released back to AVAILABLE and the escalation closed when the call ends. Targets the Tele2 Kazgaz DID +77476456048 (from-tele2-kazgaz context) as the first queue wired to real L2 routing instead of AI-only. Known gap (documented in docs/architecture/l1-l2-routing-engine.md): automatic no-answer retry-to-next-agent needs a small, separately reviewed dialplan change and is left for a follow-up MR rather than guessed at blind. Tests: services/routing_service/engine.py covered by tests/test_routing_engine.py (selection filtering, atomic reservation, release); existing test_asterisk_bridge_service.py and test_routing_service_pg_counter.py suites still pass unmodified.	2026-08-28 16:22:32 +05:00
Admin	8577d97356	Implement sales CRM workflow foundation	2026-05-10 20:54:01 +05:00
Yera All	6b8f5d069b	feat(ai): add rolling conversation summary memory	2026-04-13 11:59:43 +05:00
Yera All	f2ece35588	fix(tests): isolate db state and stabilize voice runtime suite	2026-04-12 11:38:02 +05:00
Yera All	c4c8b69494	fix(sql): backfill whatsapp chat_id in compat init	2026-04-12 01:52:27 +05:00
Yera All	bdaf65a256	fix(db): avoid repeated sqlite schema initialization	2026-04-12 01:45:49 +05:00
Yera All	d959c2b2f0	Add voice name flow controls and analytics	2026-04-05 03:26:18 +05:00
Yera All	5374c202d9	Initial import with GitLab CI/CD and registry deploy flow	2026-04-02 17:05:45 +05:00