feat: add lazy actor indexing for contribution lookups

4 files changed, 73 insertions, 3 deletions

diff --git a/tests/test_contributions_api.py b/tests/test_contributions_api.py
index e221602..22d0af3 100644
--- a/tests/test_contributions_api.py
+++ b/tests/test_contributions_api.py
@@ -1,9 +1,10 @@
 from datetime import UTC, datetime
 
 from fastapi.testclient import TestClient
+from sqlalchemy import select
 
 from srht_contrib.main import create_app
-from srht_contrib.models import ContributionEvent
+from srht_contrib.models import ContributionEvent, TrackedActor
 
 
 def test_read_only_contribution_routes_are_public_and_write_routes_require_api_key(settings, db_engine, session_factory) -> None:
@@ -45,6 +46,8 @@ def test_contributions_api_returns_zero_filled_range(client: TestClient, db_sess
     response = client.get("/api/contributions/~ccleberg?from=2026-03-28&to=2026-03-30")
 
     assert response.status_code == 200
+    assert response.json()["is_indexed"] is True
+    assert response.json()["indexing_state"] == "indexed"
     assert response.json()["days"] == [
         {"date": "2026-03-28", "count": 0, "score": 0.0},
         {"date": "2026-03-29", "count": 0, "score": 0.0},
@@ -52,6 +55,20 @@ def test_contributions_api_returns_zero_filled_range(client: TestClient, db_sess
     ]
 
 
+def test_public_read_registers_actor_for_lazy_indexing(client: TestClient, db_session) -> None:
+    response = client.get("/api/contributions/~ccleberg?from=2026-03-28&to=2026-03-30")
+
+    tracked_actor = db_session.scalar(select(TrackedActor).where(TrackedActor.actor == "~ccleberg"))
+
+    assert response.status_code == 200
+    assert response.json()["is_indexed"] is False
+    assert response.json()["indexing_state"] == "pending"
+    assert response.json()["last_polled_at"] is None
+    assert tracked_actor is not None
+    assert tracked_actor.is_active is True
+    assert tracked_actor.last_requested_at is not None
+
+
 def test_contribution_stats_api(client: TestClient, db_session) -> None:
     db_session.add_all(
         [
@@ -88,6 +105,8 @@ def test_contribution_stats_api(client: TestClient, db_session) -> None:
     assert response.json()["total_score"] == 1.5
     assert response.json()["longest_streak"] == 2
     assert response.json()["current_streak"] == 2
+    assert response.json()["is_indexed"] is True
+    assert response.json()["indexing_state"] == "indexed"
 
 
 def test_invalid_date_input_returns_400(client: TestClient) -> None:
diff --git a/tests/test_ingestion.py b/tests/test_ingestion.py
index 2322b4a..788ec81 100644
--- a/tests/test_ingestion.py
+++ b/tests/test_ingestion.py
@@ -4,7 +4,7 @@ from sqlalchemy import select
 
 from srht_contrib.config import Settings
 from srht_contrib.jobs.poller import PollerService
-from srht_contrib.models import SyncState, TrackedRepository
+from srht_contrib.models import SyncState, TrackedActor, TrackedRepository
 from srht_contrib.schemas import NormalizedEvent
 from srht_contrib.services.git import GitIngestionService, GitPollResult
 from srht_contrib.services.todo import TodoIngestionService, TodoPollResult
@@ -335,3 +335,31 @@ def test_sync_overlap_reuses_cursor_window_and_suppresses_duplicates(db_session)
     assert state is not None
     assert len(todo_service.calls) == 2
     assert todo_service.calls[1].isoformat() == "2026-03-30T00:00:00+00:00"
+
+
+def test_scheduled_poll_polls_known_actors_and_seeds_default_actor(db_session) -> None:
+    event = NormalizedEvent(
+        service="todo",
+        event_type="ticket_created",
+        actor="~known",
+        repo_name="todo",
+        resource_id="123",
+        external_uid="todo:event:known:created:123",
+        occurred_at=datetime(2026, 3, 30, 10, 0, tzinfo=UTC),
+        weight=1.0,
+        raw_payload_json=None,
+    )
+    todo_service = RecordingTodoService(events_by_call=[[], [event]])
+    poller = PollerService(todo_service=todo_service, git_service=EmptyGitService())
+
+    db_session.add(TrackedActor(actor="~known", is_active=True))
+    db_session.commit()
+
+    results = poller.poll_tracked_actors(db_session, default_actor="~default")
+
+    tracked_actors = db_session.scalars(select(TrackedActor).order_by(TrackedActor.actor)).all()
+
+    assert results == {"~default": 0, "~known": 1}
+    assert [actor.actor for actor in tracked_actors] == ["~default", "~known"]
+    assert all(actor.last_poll_status == "indexed" for actor in tracked_actors)
+    assert all(actor.last_polled_at is not None for actor in tracked_actors)
diff --git a/tests/test_migrations.py b/tests/test_migrations.py
index d572af2..505ddb3 100644
--- a/tests/test_migrations.py
+++ b/tests/test_migrations.py
@@ -22,6 +22,7 @@ def test_alembic_upgrade_creates_schema(tmp_path) -> None:
         "alembic_version",
         "contribution_events",
         "sync_states",
+        "tracked_actors",
         "tracked_repositories",
     ]
 
@@ -115,6 +116,7 @@ def test_alembic_upgrade_adopts_legacy_schema(tmp_path) -> None:
     assert columns["actor"]["nullable"] is False
     assert "uq_tracked_repository_service_actor_name" in unique_constraints
     assert actor == Settings().default_actor
+    assert "tracked_actors" in inspector.get_table_names()
 
 
 def test_alembic_prefers_database_url_from_environment(tmp_path, monkeypatch) -> None:
@@ -128,3 +130,4 @@ def test_alembic_prefers_database_url_from_environment(tmp_path, monkeypatch) ->
 
     inspector = inspect(create_engine(database_url))
     assert "actor_aliases" in inspector.get_table_names()
+    assert "tracked_actors" in inspector.get_table_names()
diff --git a/tests/test_polling_api.py b/tests/test_polling_api.py
index b07b877..75270e0 100644
--- a/tests/test_polling_api.py
+++ b/tests/test_polling_api.py
@@ -1,10 +1,11 @@
 from datetime import UTC, datetime
 
 from fastapi.testclient import TestClient
+from sqlalchemy import select
 
 from srht_contrib.config import Settings
 from srht_contrib.main import create_app
-from srht_contrib.models import ContributionEvent
+from srht_contrib.models import ContributionEvent, TrackedActor
 from srht_contrib.services.srht_client import SourceHutClientError
 
 
@@ -19,6 +20,16 @@ class InsertingPoller:
         self.todo_service = service
         self.git_service = service
 
+    def track_actor_request(self, db, actor: str, *, update_last_requested: bool = True):
+        tracked_actor = db.scalar(select(TrackedActor).where(TrackedActor.actor == actor))
+        if tracked_actor is None:
+            tracked_actor = TrackedActor(actor=actor, is_active=True)
+            db.add(tracked_actor)
+        if update_last_requested:
+            tracked_actor.last_requested_at = datetime(2026, 3, 30, 9, 0, tzinfo=UTC)
+        db.flush()
+        return tracked_actor
+
     def poll_all(self, db, actor: str) -> int:
         db.add(
             ContributionEvent(
@@ -43,6 +54,14 @@ class FailingPoller:
         self.todo_service = service
         self.git_service = service
 
+    def track_actor_request(self, db, actor: str, *, update_last_requested: bool = True):
+        tracked_actor = db.scalar(select(TrackedActor).where(TrackedActor.actor == actor))
+        if tracked_actor is None:
+            tracked_actor = TrackedActor(actor=actor, is_active=True)
+            db.add(tracked_actor)
+        db.flush()
+        return tracked_actor
+
     def poll_all(self, db, actor: str) -> int:
         raise SourceHutClientError("boom")
 
@@ -58,6 +77,7 @@ def test_manual_poll_uses_same_database_session(settings: Settings, db_engine, s
     assert poll_response.status_code == 200
     assert poll_response.json()["inserted_events"] == 1
     assert calendar_response.status_code == 200
+    assert calendar_response.json()["is_indexed"] is True
     assert calendar_response.json()["days"] == [{"date": "2026-03-30", "count": 1, "score": 1.0}]