Stage 5: Alembic migrations, durable call rows, one transcript truth

Alembic replaces create_all as the schema authority: async env.py
against Base.metadata (CLI and in-app entry paths share it via
config.attributes["connection"]), an autogenerated baseline of the
create_all-era schema, and init_db now runs upgrade head — stamping
the baseline first on a pre-Alembic database so existing deployments
adopt cleanly. create_all remains for tests only.

Calls are durable from the start: CallManager gains an
on_call_created hook (wired to persist_call_on_create) that inserts
an in_progress CallRecord the moment a call is created;
persist_call_on_end finalizes that same row. A SIGKILL mid-call now
leaves an in_progress row instead of erasing the call from history
(verified live against the dev database).

One transcript representation: ActiveCall.transcript_chunks holds
TranscriptEntry (t_offset_ms, speaker, text) — add_transcript stamps
real offsets from connect time, receptionist passes speaker instead
of encoding it into "caller: ..." strings, persisted chunks carry
real seek offsets, and the dead CallRecord.transcript Text column is
dropped by migration. Device.is_online migrates String → Boolean
(with a USING cast for existing rows).

Model de-triplication: CallResponse/CallStatusResponse build via
from_call classmethods (one ActiveCall→response mapping);
DeviceStatus deleted — can_receive_call is a computed field on
Device and the list endpoint returns the domain model; all row↔dict
and row↔domain mapping now lives in call_persistence.py
(record_summary/record_detail/chunk_to_dict + device row functions).

New tests/test_data_layer.py: upgrade-head-matches-models,
pre-Alembic adoption, durable in_progress rows, end-without-create
fallback, transcript offsets, consolidated response models.

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

tests/test_data_layer.py

@@ -0,0 +1,187 @@
+"""
+Data-layer tests.
+
+Alembic migrations produce the schema the ORM models declare (and
+adopt a pre-Alembic database); a call gets a durable in_progress row
+the moment it starts; transcript entries carry real offsets; the
+consolidated response models map from the domain in one place.
+"""
+
+import asyncio
+
+import pytest
+from sqlalchemy import Boolean, inspect, text
+from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
+from sqlalchemy.pool import StaticPool
+
+import db.database as dbmod
+from core.call_manager import CallManager
+from core.event_bus import EventBus
+from db.database import Base
+from models.call import ActiveCall, CallStatus, CallStatusResponse
+from models.device import Device, DeviceType
+from services import call_persistence as store
+
+# ================================================================
+# Alembic migrations
+# ================================================================
+
+def _run_alembic(connection, revision: str) -> None:
+    from alembic import command
+    from alembic.config import Config
+
+    cfg = Config("alembic.ini")
+    cfg.attributes["connection"] = connection
+    command.upgrade(cfg, revision)
+
+
+def _schema_info(sync_conn) -> dict:
+    inspector = inspect(sync_conn)
+    return {
+        "tables": set(inspector.get_table_names()) - {"alembic_version"},
+        "call_record_cols": {c["name"] for c in inspector.get_columns("call_records")},
+        "is_online_type": next(
+            c["type"] for c in inspector.get_columns("devices")
+            if c["name"] == "is_online"
+        ),
+    }
+
+
+class TestMigrations:
+    async def test_upgrade_head_matches_models(self, tmp_path):
+        engine = create_async_engine(f"sqlite+aiosqlite:///{tmp_path}/mig.db")
+        async with engine.begin() as conn:
+            await conn.run_sync(dbmod._upgrade_to_head)
+        async with engine.connect() as conn:
+            info = await conn.run_sync(_schema_info)
+        await engine.dispose()
+
+        assert info["tables"] == set(Base.metadata.tables)
+        assert "transcript" not in info["call_record_cols"]
+        assert isinstance(info["is_online_type"], Boolean)
+
+    async def test_adopts_pre_alembic_schema(self, tmp_path):
+        """A create_all-era database (baseline schema, no alembic_version)
+        is stamped and migrated forward instead of failing."""
+        engine = create_async_engine(f"sqlite+aiosqlite:///{tmp_path}/legacy.db")
+        async with engine.begin() as conn:
+            await conn.run_sync(
+                lambda c: _run_alembic(c, dbmod._BASELINE_REVISION)
+            )
+            await conn.execute(text("DROP TABLE alembic_version"))
+
+        async with engine.begin() as conn:
+            await conn.run_sync(dbmod._upgrade_to_head)
+        async with engine.connect() as conn:
+            info = await conn.run_sync(_schema_info)
+        await engine.dispose()
+
+        assert "transcript" not in info["call_record_cols"]
+        assert isinstance(info["is_online_type"], Boolean)
+
+
+# ================================================================
+# Durable call rows
+# ================================================================
+
+@pytest.fixture
+async def mem_db(monkeypatch):
+    engine = create_async_engine(
+        "sqlite+aiosqlite:///:memory:",
+        poolclass=StaticPool,
+        connect_args={"check_same_thread": False},
+    )
+    async with engine.begin() as conn:
+        await conn.run_sync(Base.metadata.create_all)
+    factory = async_sessionmaker(engine, expire_on_commit=False)
+    monkeypatch.setattr(dbmod, "_engine", engine)
+    monkeypatch.setattr(dbmod, "_session_factory", factory)
+    yield factory
+    await engine.dispose()
+
+
+class TestDurableCallRows:
+    async def test_in_progress_row_from_the_start(self, mem_db):
+        cm = CallManager(
+            EventBus(),
+            on_call_created=store.persist_call_on_create,
+            on_call_ended=store.persist_call_on_end,
+        )
+        call = await cm.create_call("+15551230000", intent="dispute a charge")
+
+        async with mem_db() as session:
+            row = await store.get_record(session, call.id)
+        assert row is not None
+        assert row.status == "in_progress"
+        assert row.ended_at is None
+        assert row.intent == "dispute a charge"
+
+        await cm.add_transcript(call.id, "hello, billing please", speaker="caller")
+        await cm.end_call(call.id, CallStatus.COMPLETED)
+
+        async with mem_db() as session:
+            row = await store.get_record(session, call.id)
+            chunks = await store.get_transcript_chunks(session, call.id)
+        assert row.status == "completed"
+        assert row.ended_at is not None
+        assert [(c.seq, c.speaker, c.text) for c in chunks] == [
+            (0, "caller", "hello, billing please")
+        ]
+
+    async def test_end_without_create_still_writes_row(self, mem_db):
+        """If the create-time insert never happened, finalize inserts."""
+        cm = CallManager(EventBus(), on_call_ended=store.persist_call_on_end)
+        call = await cm.create_call("+15551230001")
+        await cm.end_call(call.id, CallStatus.FAILED)
+
+        async with mem_db() as session:
+            row = await store.get_record(session, call.id)
+        assert row is not None
+        assert row.status == "failed"
+
+
+# ================================================================
+# Transcript offsets
+# ================================================================
+
+class TestTranscriptOffsets:
+    async def test_entries_carry_offset_and_speaker(self):
+        cm = CallManager(EventBus())
+        call = await cm.create_call("+15551230002")
+
+        await cm.add_transcript(call.id, "one")
+        await asyncio.sleep(0.02)
+        await cm.add_transcript(call.id, "two", speaker="agent")
+
+        first, second = call.transcript_chunks
+        assert first.t_offset_ms >= 0
+        assert second.t_offset_ms > first.t_offset_ms
+        assert first.speaker == "unknown"
+        assert second.speaker == "agent"
+        assert call.transcript == "one\ntwo"
+
+
+# ================================================================
+# Consolidated response models
+# ================================================================
+
+class TestResponseModels:
+    def test_status_response_from_call(self):
+        call = ActiveCall(id="call_x", remote_number="+15550000000", intent="pay bill")
+        resp = CallStatusResponse.from_call(call)
+        assert resp.call_id == "call_x"
+        assert resp.status == "initiating"
+        assert resp.remote_number == "+15550000000"
+        assert resp.intent == "pay bill"
+
+    def test_device_serializes_routability(self):
+        device = Device(
+            id="dev_1",
+            name="Desk Phone",
+            type=DeviceType.SIP_PHONE,
+            sip_uri="sip:desk@gw",
+            is_online=True,
+        )
+        assert device.model_dump()["can_receive_call"] is True
+        device.dnd = True
+        assert device.model_dump()["can_receive_call"] is False