File size: 12,586 Bytes
0c85e62 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 | """Integration tests for cursor-based pagination on GET /api/assets.
These tests exercise the handler/service/query path end-to-end;
cursor-encoding-level tests live in
tests-unit/assets_test/services/test_cursor.py.
"""
import pytest
import requests
def _seed(asset_factory, make_asset_bytes, count: int, tag: str) -> list[str]:
names = [f"cursor_{i:02d}.safetensors" for i in range(count)]
for n in names:
asset_factory(
n,
["models", "model_type:checkpoints", "unit-tests", tag],
{},
make_asset_bytes(n, size=2048),
)
return sorted(names)
def test_cursor_pages_all_items_in_order(http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
names = _seed(asset_factory, make_asset_bytes, count=5, tag="cursor-walk")
params = {
"include_tags": "unit-tests,cursor-walk",
"sort": "name",
"order": "asc",
"limit": "2",
}
seen: list[str] = []
after: str | None = None
pages = 0
while True:
page_params = dict(params)
if after is not None:
page_params["after"] = after
r = http.get(api_base + "/api/assets", params=page_params, timeout=120)
assert r.status_code == 200, r.text
body = r.json()
seen.extend(a["name"] for a in body["assets"])
pages += 1
after = body.get("next_cursor")
if after is None:
break
assert body["has_more"] is True
assert pages < 10, "guard against runaway cursor loop"
assert seen == names, f"expected {names}, got {seen}"
# Last page should have has_more False
assert body["has_more"] is False
assert "next_cursor" not in body
def test_cursor_invalid_returns_400(http: requests.Session, api_base: str):
r = http.get(
api_base + "/api/assets",
params={"after": "not-a-real-cursor", "sort": "created_at"},
timeout=120,
)
assert r.status_code == 400, r.text
body = r.json()
assert body["error"]["code"] == "INVALID_CURSOR"
def test_cursor_sort_mismatch_returns_400(http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
_seed(asset_factory, make_asset_bytes, count=2, tag="cursor-mismatch")
# Take a real cursor minted for sort=name.
r = http.get(
api_base + "/api/assets",
params={
"include_tags": "unit-tests,cursor-mismatch",
"sort": "name",
"order": "asc",
"limit": "1",
},
timeout=120,
)
assert r.status_code == 200
cursor = r.json()["next_cursor"]
assert cursor is not None
# Replay against sort=created_at — should fail with INVALID_CURSOR.
r2 = http.get(
api_base + "/api/assets",
params={"after": cursor, "sort": "created_at"},
timeout=120,
)
assert r2.status_code == 400, r2.text
assert r2.json()["error"]["code"] == "INVALID_CURSOR"
def test_cursor_wins_over_offset(http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
names = _seed(asset_factory, make_asset_bytes, count=4, tag="cursor-vs-offset")
# Take a cursor that points past the first item.
r = http.get(
api_base + "/api/assets",
params={
"include_tags": "unit-tests,cursor-vs-offset",
"sort": "name",
"order": "asc",
"limit": "1",
},
timeout=120,
)
assert r.status_code == 200, r.text
cursor = r.json()["next_cursor"]
assert cursor is not None
# Pass both 'after' and a large offset. Cursor must win; offset is ignored.
r2 = http.get(
api_base + "/api/assets",
params={
"include_tags": "unit-tests,cursor-vs-offset",
"sort": "name",
"order": "asc",
"limit": "1",
"after": cursor,
"offset": "999",
},
timeout=120,
)
assert r2.status_code == 200
body = r2.json()
# Should land on the second name in sorted order — not skip ahead by 999.
assert [a["name"] for a in body["assets"]] == [names[1]]
def test_next_cursor_absent_when_no_more_results(http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
_seed(asset_factory, make_asset_bytes, count=2, tag="cursor-exhaust")
r = http.get(
api_base + "/api/assets",
params={
"include_tags": "unit-tests,cursor-exhaust",
"sort": "name",
"order": "asc",
"limit": "50",
},
timeout=120,
)
assert r.status_code == 200, r.text
body = r.json()
assert body["has_more"] is False
assert "next_cursor" not in body
def test_cursor_pagination_first_page_mints_cursor(http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
"""First-page request (no `after`) must still return `next_cursor` when
more rows exist, or pagination is unreachable from a cold start.
"""
_seed(asset_factory, make_asset_bytes, count=3, tag="cursor-first-page")
r = http.get(
api_base + "/api/assets",
params={"include_tags": "unit-tests,cursor-first-page", "sort": "name", "order": "asc", "limit": "2"},
timeout=120,
)
assert r.status_code == 200, r.text
body = r.json()
assert body["has_more"] is True
assert body.get("next_cursor"), "first page must mint a cursor when more rows exist"
def test_cursor_no_spurious_cursor_when_page_size_equals_remainder(http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
"""When `total` is an exact multiple of `limit`, the final page must
NOT carry a next_cursor — there is nothing past it.
"""
_seed(asset_factory, make_asset_bytes, count=4, tag="cursor-exact-multiple")
# Page 1
r = http.get(
api_base + "/api/assets",
params={"include_tags": "unit-tests,cursor-exact-multiple", "sort": "name", "order": "asc", "limit": "2"},
timeout=120,
)
assert r.status_code == 200, r.text
cursor = r.json()["next_cursor"]
assert cursor is not None
# Page 2 — should exhaust the set with no cursor for a phantom page 3
r2 = http.get(
api_base + "/api/assets",
params={"include_tags": "unit-tests,cursor-exact-multiple", "sort": "name", "order": "asc", "limit": "2", "after": cursor},
timeout=120,
)
assert r2.status_code == 200, r2.text
body = r2.json()
assert len(body["assets"]) == 2
assert body["has_more"] is False
assert "next_cursor" not in body
@pytest.mark.parametrize("sort_field", ["created_at", "updated_at", "size"])
def test_cursor_walks_for_non_name_sorts(sort_field, http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
"""Cursor pagination must work for every sort field the contract claims.
Without this, the `created_at` / `updated_at` (time-encoded micros) and
`size` (int-encoded) cursor paths go entirely unexercised end-to-end.
"""
# Sizes increase strictly by index, so `size desc` has a deterministic
# expected order. Time-based sorts (created_at / updated_at) can tie when
# rows are inserted faster than the DB's timestamp resolution; for those
# we check coverage and no-duplicates and let the keyset tiebreaker do
# the rest, instead of sleeping between inserts and asserting an order
# that depends on clock granularity.
names = []
for i in range(4):
n = f"cursor_{sort_field}_{i:02d}.safetensors"
asset_factory(n, ["models", "model_type:checkpoints", "unit-tests", f"cursor-{sort_field}"], {}, make_asset_bytes(n, size=2048 + i))
names.append(n)
params = {
"include_tags": f"unit-tests,cursor-{sort_field}",
"sort": sort_field,
"order": "desc",
"limit": "2",
}
seen: list[str] = []
after: str | None = None
pages = 0
while True:
page_params = dict(params)
if after is not None:
page_params["after"] = after
r = http.get(api_base + "/api/assets", params=page_params, timeout=120)
assert r.status_code == 200, r.text
body = r.json()
seen.extend(a["name"] for a in body["assets"])
after = body.get("next_cursor")
pages += 1
if after is None:
break
assert pages < 10, "guard against runaway cursor loop"
# No duplicates: a faulty keyset boundary that returns the same row across
# two pages must fail this check.
assert len(seen) == len(set(seen)), (
f"cursor walk repeated rows for sort={sort_field}: {seen}"
)
# Full coverage: every seeded asset reached exactly once.
assert set(seen) == set(names), (
f"missing items for sort={sort_field}: expected {set(names)}, got {set(seen)}"
)
# Strict order check for the only field with a clock-independent ordering.
if sort_field == "size":
assert seen == list(reversed(names)), (
f"size cursor walked out of order: got {seen}, expected {list(reversed(names))}"
)
def test_cursor_order_mismatch_returns_400(http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
"""A cursor minted under desc order replayed against asc must 400, not
silently walk the wrong direction."""
_seed(asset_factory, make_asset_bytes, count=3, tag="cursor-order-flip")
r = http.get(
api_base + "/api/assets",
params={
"include_tags": "unit-tests,cursor-order-flip",
"sort": "name",
"order": "desc",
"limit": "1",
},
timeout=120,
)
assert r.status_code == 200, r.text
cursor = r.json()["next_cursor"]
assert cursor is not None
# Replay with order flipped to asc — server must reject the cursor.
r2 = http.get(
api_base + "/api/assets",
params={
"include_tags": "unit-tests,cursor-order-flip",
"sort": "name",
"order": "asc",
"limit": "1",
"after": cursor,
},
timeout=120,
)
assert r2.status_code == 400, r2.text
assert r2.json()["error"]["code"] == "INVALID_CURSOR"
def test_cursor_invalid_cursor_at_microsecond_boundary(http: requests.Session, api_base: str):
"""A cursor carrying an out-of-range microsecond timestamp must map to
400 INVALID_CURSOR, not 500."""
import base64
import json
# 10^18 microseconds ≈ year 33658, well past datetime.MAX_YEAR.
# `o` and `order=` must be set; otherwise decode fails earlier on the
# missing-order branch and the µs-overflow path is never exercised.
payload = {"s": "created_at", "o": "desc", "v": "999999999999999999999", "id": "asset-x"}
raw = json.dumps(payload, separators=(",", ":")).encode("utf-8")
cursor = base64.urlsafe_b64encode(raw).rstrip(b"=").decode("ascii")
r = http.get(
api_base + "/api/assets",
params={"after": cursor, "sort": "created_at", "order": "desc"},
timeout=120,
)
assert r.status_code == 400, r.text
assert r.json()["error"]["code"] == "INVALID_CURSOR"
def test_cursor_pagination_stable_after_delete(http: requests.Session, api_base: str, asset_factory, make_asset_bytes):
names = _seed(asset_factory, make_asset_bytes, count=4, tag="cursor-delete")
# Page 1.
r = http.get(
api_base + "/api/assets",
params={
"include_tags": "unit-tests,cursor-delete",
"sort": "name",
"order": "asc",
"limit": "2",
},
timeout=120,
)
assert r.status_code == 200
body = r.json()
page1_names = [a["name"] for a in body["assets"]]
cursor = body["next_cursor"]
assert cursor is not None
assert page1_names == names[:2]
# Delete an item from page 1 (already returned) — cursor should still
# locate the next page from where it was minted, not re-index.
target_id = body["assets"][0]["id"]
d = http.delete(api_base + f"/api/assets/{target_id}", timeout=120)
assert d.status_code in (200, 204), d.text
# Page 2 via cursor.
r2 = http.get(
api_base + "/api/assets",
params={
"include_tags": "unit-tests,cursor-delete",
"sort": "name",
"order": "asc",
"limit": "2",
"after": cursor,
},
timeout=120,
)
assert r2.status_code == 200, r2.text
body2 = r2.json()
assert [a["name"] for a in body2["assets"]] == names[2:]
|