Commit Graph
11 Commits
Author SHA1 Message Date
didar 9a09a39849 feat: enhance ElevenLabs ASR provider to accumulate autonomous VAD commits
deploy / deploy (push) Successful in 31s
2026-08-23 13:20:31 +05:00
didar 206b0bafe0 feat: update real-time commit strategy for ElevenLabs ASR to VAD
deploy / deploy (push) Successful in 30s
2026-08-23 13:05:58 +05:00
didar 1a91dc4489 feat: add tenant ID handling for sales voice and telegram sync requests
deploy / deploy (push) Successful in 30s
2026-08-23 12:55:25 +05:00
didar 8dd3e238f2 feat: enhance low signal transcript handling with finalization checks and logging
deploy / deploy (push) Successful in 31s
2026-08-23 12:40:59 +05:00
didar 642104ec0d Merge pull request 'feat: make ai_operator_settings config code the source of truth' (#3) from feat/ai-operator-config-source-of-truth into main
deploy / deploy (push) Successful in 29s
Reviewed-on: #3
2026-08-21 16:17:12 +00:00
didarandClaude Sonnet 5 c5dd87ee32 feat: make ai_operator_settings config code the source of truth
Add sync_ai_operator_config_from_code() which overwrites the DB-cached
ai_operator_settings row from ai_operator_default_config() on startup
of ai_orchestrator_service and ai_voice_runtime_service. Greeting and
system prompt changes now go through git + deploy instead of manual
psql/API edits to prod. Also adds a root README pointing to existing docs.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-21 21:00:34 +05:00
didar ffa779ffa0 Move ai-voice-runtime-service host port off 9019 to avoid cross-tenant conflict
deploy / deploy (push) Canceled after 24h48m11s
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.
2026-08-20 23:22:16 +05:00
didar 13ef87eb2c Fix voice greeting test marker to hit the actually-served default
deploy / deploy (push) Canceled after 25h17m2s
The previous marker was added to operator_persona.py's inline fallback,
which only fires when config is None. Every real call path loads a
populated AIOperatorConfig via load_effective_ai_operator_config(),
so ai_operator_default_config() in services/shared/ai_operator_config.py
is the default that's actually served.
2026-08-20 22:53:27 +05:00
didar c5e11fde3d Add test marker to voice greeting to verify Gitea CI/CD deploy
deploy / deploy (push) Canceled after 25h22m40s
2026-08-20 22:47:34 +05:00
didar 4e1039ab58 Merge pull request 'Play a filler ack during slow voice decisions and cache KB search rows' (#2) from voice-latency-llm-tts-improvements into main
deploy / deploy (push) Canceled after 27h22m42s
Reviewed-on: #2
2026-08-20 09:47:45 +00:00
didar 9cc5d802d6 Merge pull request 'Add architecture longread and remove dead code found during review' (#1) from worktree-call-center-review into main
deploy / deploy (push) Canceled after 27h28m15s
Reviewed-on: #1
2026-08-20 09:42:15 +00:00