Initial commit: avc-phone-ai codebase + CLAUDE.md

.env.example

@@ -0,0 +1,62 @@
+# Copy to .env and fill in. run.sh auto-loads it.
+
+# ── Public ingress (Twilio dials this back) ──────────────────────────────────
+# Public hostname; nginx terminates TLS here and proxies to the app. Must match the
+# Twilio webhook host (Twilio signs https://PUBLIC_HOST/voice).
+PUBLIC_HOST=voip.activeblue.net
+PORT=8200
+# App bind address. Default 127.0.0.1 (nginx proxies in locally) — not exposed on LAN.
+BIND_HOST=127.0.0.1
+
+# ── Twilio ───────────────────────────────────────────────────────────────────
+# From console.twilio.com. Account SID + a Standard API Key (scoped to this app,
+# revocable independently). The Auth Token stays in the Twilio console only — never on
+# this server. Create the key under Account → API Keys → Create Standard key, name it
+# avc-phone-agent-prod; the Secret is shown once. Used to auto-hang-up the carrier leg
+# and validate inbound webhook signatures.
+TWILIO_ACCOUNT_SID=ACxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+TWILIO_API_KEY_SID=SKxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+TWILIO_API_KEY_SECRET=your_api_key_secret_here
+# Inbound webhook signature validation is ON whenever TWILIO_API_KEY_SECRET is set.
+# Set to false only for local testing without real Twilio requests.
+TWILIO_VALIDATE=true
+# Shared secret embedded in the Media Stream wss URL to gate /ws. Set a stable random
+# value (e.g. `openssl rand -base64 24`); if blank, one is generated per process start.
+STREAM_TOKEN=
+
+# ── Odoo appointment integration ─────────────────────────────────────────────
+# Leave ODOO_USER/ODOO_API_KEY blank to disable Odoo and log requests to JSONL only.
+# Same creds the activeblue-agent container uses (docker inspect activeblue-agent).
+# Verified working against db1 with ODOO_TARGET=crm.
+ODOO_URL=http://localhost:8069
+ODOO_DB=db1
+ODOO_USER=mr.garcia09@gmail.com
+ODOO_API_KEY=
+ODOO_TARGET=crm          # crm = callback lead (recommended) | calendar = tentative event
+
+# ── Capacity ─────────────────────────────────────────────────────────────────
+# Max simultaneous calls (each uses GPU; Ollama serializes generation). Over-cap
+# callers hear BUSY_MESSAGE and are hung up. Tune to your GPU headroom (2-3 typical).
+MAX_CONCURRENT_CALLS=2
+# BUSY_MESSAGE=Thank you for calling Advanced Vision Care. All of our lines are busy right now. Please call back in a few minutes. Goodbye.
+
+# ── Models (defaults are fine) ───────────────────────────────────────────────
+OLLAMA_MODEL=llama3.1:8b
+OLLAMA_URL=http://127.0.0.1:11434/v1
+# LLM provider: ollama (local, default) | anthropic (Claude API). Flip to A/B test Claude.
+LLM_PROVIDER=ollama
+ANTHROPIC_API_KEY=
+# Default is the most capable model; for low-latency phone voice prefer claude-haiku-4-5
+# (fastest) or claude-sonnet-4-6 (balance).
+ANTHROPIC_MODEL=claude-opus-4-8
+# ── STT: Deepgram (real-time, in-call only) ──────────────────────────────────
+# Nova-2 delivers end-of-utterance in <300ms (vs Whisper's 1-3s buffering). Key from
+# console.deepgram.com. Model is fixed to nova-2 in code; DEEPGRAM_MODEL is informational.
+DEEPGRAM_API_KEY=
+DEEPGRAM_MODEL=nova-2
+# Whisper is retained for POST-CALL transcription only (Phase 3), not the live pipeline.
+WHISPER_MODEL=base
+WHISPER_DEVICE=cuda
+WHISPER_COMPUTE=float16
+KOKORO_VOICE=af_heart
+KOKORO_MODEL_DIR=/home/tocmo0nlord/pipecat-run/models