feat(tiktok): tiktok.scrape capability + billing wire-up

surfsense_backend/tests/unit/capabilities/tiktok/scrape/test_executor.py

@@ -0,0 +1,79 @@
+"""``tiktok.scrape`` executor: verb input → actor input mapping → typed items.
+
+Boundary mocked: the proprietary scraper (injected fake). NOT mocked: the verb's
+own payload→TikTokScrapeInput mapping and the dict→TikTokVideoItem wrapping.
+"""
+
+from __future__ import annotations
+
+import pytest
+
+from app.capabilities.tiktok.scrape.executor import build_scrape_executor
+from app.capabilities.tiktok.scrape.schemas import ScrapeInput, ScrapeOutput
+from app.exceptions import ForbiddenError
+from app.proprietary.platforms.tiktok import TikTokAccessBlockedError, TikTokScrapeInput
+
+pytestmark = pytest.mark.unit
+
+
+class _FakeScraper:
+    """Records the actor input + limit it was called with; returns canned items."""
+
+    def __init__(self, items: list[dict]):
+        self._items = items
+        self.calls: list[tuple[TikTokScrapeInput, int | None]] = []
+
+    async def __call__(
+        self, actor_input: TikTokScrapeInput, *, limit: int | None = None
+    ) -> list[dict]:
+        self.calls.append((actor_input, limit))
+        return self._items
+
+
+async def test_maps_urls_to_start_urls_and_wraps_items():
+    scraper = _FakeScraper([{"id": "123", "text": "hello"}])
+    execute = build_scrape_executor(scrape_fn=scraper)
+
+    out = await execute(ScrapeInput(urls=["https://www.tiktok.com/@nasa/video/123"]))
+
+    assert isinstance(out, ScrapeOutput)
+    assert len(out.items) == 1
+    assert out.items[0].id == "123"
+
+    (actor_input, _limit) = scraper.calls[0]
+    assert [u.url for u in actor_input.startUrls] == [
+        "https://www.tiktok.com/@nasa/video/123"
+    ]
+
+
+async def test_forwards_typed_sources_and_limit():
+    scraper = _FakeScraper([])
+    execute = build_scrape_executor(scrape_fn=scraper)
+
+    await execute(
+        ScrapeInput(
+            profiles=["nasa"],
+            hashtags=["food"],
+            search_queries=["cats"],
+            results_per_page=7,
+            max_items=25,
+        )
+    )
+
+    (actor_input, limit) = scraper.calls[0]
+    assert actor_input.profiles == ["nasa"]
+    assert actor_input.hashtags == ["food"]
+    assert actor_input.searchQueries == ["cats"]
+    assert actor_input.resultsPerPage == 7
+    # The outer collection limit is the caller's total-item cap.
+    assert limit == 25
+
+
+async def test_access_blocked_maps_to_forbidden():
+    async def _blocked(actor_input: TikTokScrapeInput, *, limit: int | None = None):
+        raise TikTokAccessBlockedError("all IPs refused")
+
+    execute = build_scrape_executor(scrape_fn=_blocked)
+
+    with pytest.raises(ForbiddenError):
+        await execute(ScrapeInput(hashtags=["food"]))

surfsense_backend/tests/unit/capabilities/tiktok/scrape/test_schemas.py

@@ -0,0 +1,45 @@
+"""``tiktok.scrape`` input guards: a source is required and the batch is bounded."""
+
+from __future__ import annotations
+
+import pytest
+from pydantic import ValidationError
+
+from app.capabilities.tiktok.scrape.schemas import (
+    MAX_TIKTOK_ITEMS,
+    MAX_TIKTOK_SOURCES,
+    ScrapeInput,
+)
+
+pytestmark = pytest.mark.unit
+
+
+def test_rejects_input_with_no_source():
+    with pytest.raises(ValidationError):
+        ScrapeInput()
+
+
+def test_accepts_urls_only():
+    payload = ScrapeInput(urls=["https://www.tiktok.com/@nasa"])
+    assert payload.profiles == []
+
+
+def test_accepts_hashtags_only():
+    payload = ScrapeInput(hashtags=["food"])
+    assert payload.hashtags == ["food"]
+
+
+def test_defaults_and_bounds():
+    payload = ScrapeInput(hashtags=["food"])
+    assert payload.max_items == 10
+    assert payload.results_per_page == 10
+    with pytest.raises(ValidationError):
+        ScrapeInput(hashtags=["food"], max_items=0)
+    with pytest.raises(ValidationError):
+        ScrapeInput(hashtags=["food"], max_items=MAX_TIKTOK_ITEMS + 1)
+
+
+def test_rejects_more_sources_than_the_cap():
+    too_many = [f"tag{i}" for i in range(MAX_TIKTOK_SOURCES + 1)]
+    with pytest.raises(ValidationError):
+        ScrapeInput(hashtags=too_many)

surfsense_backend/tests/unit/capabilities/tiktok/test_registry.py

@@ -0,0 +1,23 @@
+"""The tiktok namespace registers its verb as one Capability the doors/agent read."""
+
+from __future__ import annotations
+
+import pytest
+
+from app.capabilities import (
+    tiktok,  # noqa: F401  — importing the namespace registers its verbs
+)
+from app.capabilities.core import BillingUnit
+from app.capabilities.core.store import get_capability
+from app.capabilities.tiktok.scrape.schemas import ScrapeInput, ScrapeOutput
+
+pytestmark = pytest.mark.unit
+
+
+def test_tiktok_scrape_is_registered_and_billed_per_video():
+    cap = get_capability("tiktok.scrape")
+
+    assert cap.name == "tiktok.scrape"
+    assert cap.input_schema is ScrapeInput
+    assert cap.output_schema is ScrapeOutput
+    assert cap.billing_unit is BillingUnit.TIKTOK_VIDEO