M6 + M0: hardening, deploy docs, PoC scripts

- Pipeline-down fallback: dialplan plays gogo-fallback after a failed
  AudioSocket (§15) + script to synthesize the Bosnian prompt via TTS
- Voice heartbeat file → /health/voice endpoint + live status in admin panel
- Retention job also purges stale call registrations; chat sessions metered;
  100%-usage super-admin alert email (GOGO_ADMIN_ALERT_EMAIL)
- .env.example, docs/DEPLOY.md (compose stack, GPU node, backups pg_dump,
  update procedure, security notes)
- §16 Definition of Done as an automated test: softphone-style call → fake
  partner availability → request pushed → webhook confirm → console SMS
- M0 PoC scripts: STT accuracy harness (CER/WER + spoken-digit check; dry-run
  verified with espeak-ng samples + faster-whisper small on CPU — phone number
  extracted exactly), TTS bake-off (Azure vs ElevenLabs, latency+cost), and
  end-to-end latency smoke test speaking real AudioSocket to the live pipeline

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tests/test_definition_of_done.py

@@ -0,0 +1,117 @@
+"""§16 Definition of Done, software phase:
+
+'a demo where a softphone call books a request end-to-end (agent conversation →
+availability from fake partner API → request pushed → webhook outcome →
+console-SMS logged) … all without any hardware present.'
+
+(The chat-widget + mock-tenant half lives in tests/test_chat_widget.py.)
+"""
+
+from sqlalchemy import select
+
+from gogo.agent.llm import LLMResponse, ScriptedLLM, ToolUse, set_llm
+from gogo.domain import BookingStatus
+from gogo.models import BookingRequest, Call, CallRegistration, Service
+from gogo.voice.call import CallLimits, CallSession
+from tests.fake_partner import staff_resolve
+from tests.test_voice import UTTERANCE, FakeCallerTransport, frames, voice_fakes  # noqa: F401
+
+SLOT = {"start": "2026-07-15T17:00:00+02:00", "end": "2026-07-15T17:45:00+02:00"}
+
+
+async def test_definition_of_done_voice_partner_flow(
+    session, partner_tenant, wire_fake_partner, gogo_client, emails, sms, voice_fakes  # noqa: F811
+):
+    stt, tts = voice_fakes
+    wire_fake_partner.slots["SRV-12"] = [SLOT]
+
+    svc = (
+        await session.execute(select(Service).where(Service.tenant_id == partner_tenant.id))
+    ).scalar_one()
+
+    # the "softphone caller" asks for a manicure; the agent checks availability
+    # against the partner API and pushes the booking request into it
+    stt.texts = ["Htjela bih manikir u srijedu, Amra Hodžić, broj s kojeg zovem."]
+    set_llm(
+        ScriptedLLM(
+            [
+                LLMResponse(
+                    text="",
+                    tool_uses=[
+                        ToolUse(
+                            id="t1",
+                            name="check_availability",
+                            input={
+                                "service_id": str(svc.id),
+                                "date_from": "2026-07-15",
+                                "date_to": "2026-07-15",
+                            },
+                        )
+                    ],
+                    stop_reason="tool_use",
+                ),
+                LLMResponse(
+                    text="",
+                    tool_uses=[
+                        ToolUse(
+                            id="t2",
+                            name="submit_booking_request",
+                            input={
+                                "service_id": str(svc.id),
+                                "service_name_raw": "manikir",
+                                "client_name": "Amra Hodžić",
+                                "client_phone": "+38765123456",
+                                "slots": [SLOT],
+                                "summary": "Manikir, srijeda u 17.",
+                            },
+                        )
+                    ],
+                    stop_reason="tool_use",
+                ),
+                LLMResponse(
+                    text="Prosljeđujem zahtjev salonu — kontaktiraće vas. Hvala i prijatno!"
+                ),
+            ]
+        )
+    )
+
+    reg = CallRegistration(tenant_id=partner_tenant.id, caller_msisdn="+38765123456")
+    session.add(reg)
+    await session.commit()
+    reg_id = reg.id
+
+    transport = FakeCallerTransport(UTTERANCE)
+    await CallSession(
+        transport, reg_id, pace=0, limits=CallLimits(inactivity_s=5, max_call_s=60)
+    ).run()
+    set_llm(None)
+
+    # 1) availability came from the fake partner, request was PUSHED into it
+    assert "REQ-0001" in wire_fake_partner.requests
+    pushed = wire_fake_partner.requests["REQ-0001"]
+    assert pushed["client"]["name"] == "Amra Hodžić"
+    assert pushed["service_id"] == "SRV-12"
+    assert pushed["source"] == "voice"
+    # partner tenants get no owner email by default (§8.2)
+    assert emails == []
+
+    # 2) salon staff confirm in their own software → webhook → Gogo closes + SMS
+    resp = await staff_resolve(
+        gogo_client, str(partner_tenant.id), "REQ-0001", "confirmed", confirmed_slot=SLOT
+    )
+    assert resp.status_code == 200
+
+    session.expire_all()
+    req = (await session.execute(select(BookingRequest))).scalar_one()
+    assert req.status == BookingStatus.confirmed.value
+
+    # 3) console-SMS logged to the client
+    assert len(sms) == 1
+    to, body = sms[0]
+    assert to == "+38765123456"
+    assert "Potvrđen termin" in body and "srijeda" in body
+
+    # 4) the call itself is fully accounted for
+    call = (await session.execute(select(Call))).scalar_one()
+    assert call.outcome == "request_created"
+    assert call.transcript and call.recording_path