feat(assets): cursor-based pagination on GET /api/assets

app/assets/api/routes.py

@@ -39,6 +39,7 @@
     update_asset_metadata,
     upload_from_temp_path,
 )
+from app.assets.services.cursor import InvalidCursorError
 from app.assets.services.tagging import list_tag_histogram
 
 ROUTES = web.RouteTableDef()
@@ -172,7 +173,7 @@ def _build_asset_response(result: schemas.AssetDetailResult | schemas.UploadResu
         user_metadata=result.ref.user_metadata or {},
         metadata=result.ref.system_metadata,
         job_id=result.ref.job_id,
-        prompt_id=result.ref.job_id,  # deprecated: mirrors job_id for cloud compat
+        prompt_id=result.ref.job_id,  # deprecated alias of job_id, kept for compatibility
         created_at=result.ref.created_at,
         updated_at=result.ref.updated_at,
         last_access_time=result.ref.last_access_time,
@@ -209,24 +210,37 @@ async def list_assets_route(request: web.Request) -> web.Response:
     order_candidate = (q.order or "desc").lower()
     order = order_candidate if order_candidate in {"asc", "desc"} else "desc"
 
-    result = list_assets_page(
-        owner_id=USER_MANAGER.get_request_user_id(request),
-        include_tags=q.include_tags,
-        exclude_tags=q.exclude_tags,
-        name_contains=q.name_contains,
-        metadata_filter=q.metadata_filter,
-        limit=q.limit,
-        offset=q.offset,
-        sort=sort,
-        order=order,
-    )
+    try:
+        result = list_assets_page(
+            owner_id=USER_MANAGER.get_request_user_id(request),
+            include_tags=q.include_tags,
+            exclude_tags=q.exclude_tags,
+            name_contains=q.name_contains,
+            metadata_filter=q.metadata_filter,
+            limit=q.limit,
+            offset=q.offset,
+            sort=sort,
+            order=order,
+            after=q.after,
+        )
+    except InvalidCursorError as e:
+        return _build_error_response(400, "INVALID_CURSOR", str(e))
 
     summaries = [_build_asset_response(item) for item in result.items]
 
+    # has_more semantics differ by mode:
+    #   - cursor mode: a non-empty next_cursor means there are more results.
+    #   - offset mode: derived from total - (offset + page size).
+    if q.after is not None:
+        has_more = result.next_cursor is not None
+    else:
+        has_more = (q.offset + len(summaries)) < result.total
+
     payload = schemas_out.AssetsList(
         assets=summaries,
         total=result.total,
-        has_more=(q.offset + len(summaries)) < result.total,
+        has_more=has_more,
+        next_cursor=result.next_cursor,
     )
     return web.json_response(payload.model_dump(mode="json", exclude_none=True))
 

app/assets/api/schemas_in.py

@@ -59,6 +59,11 @@ class ListAssetsQuery(BaseModel):
 
     limit: conint(ge=1, le=500) = 20
     offset: conint(ge=0) = 0
+    # Opaque keyset cursor. When supplied, `offset` is ignored. Cursor pagination
+    # is supported for sort values `created_at`, `updated_at`, `name`, `size`.
+    # Supplying `after` together with `sort=last_access_time` returns
+    # 400 INVALID_CURSOR; that sort only supports offset/limit.
+    after: str | None = None
 
     sort: Literal["name", "created_at", "updated_at", "size", "last_access_time"] = (
         "created_at"

app/assets/api/schemas_out.py

@@ -40,6 +40,8 @@ class AssetsList(BaseModel):
     assets: list[Asset]
     total: int
     has_more: bool
+    # Opaque cursor for the next page. Omitted when there are no more results.
+    next_cursor: str | None = None
 
 
 class TagUsage(BaseModel):

app/assets/database/queries/asset_reference.py

@@ -266,9 +266,18 @@ def list_references_page(
     metadata_filter: dict | None = None,
     sort: str | None = None,
     order: str | None = None,
+    after_cursor_value: object | None = None,
+    after_cursor_id: str | None = None,
 ) -> tuple[list[AssetReference], dict[str, list[str]], int]:
     """List references with pagination, filtering, and sorting.
 
+    When ``after_cursor_value``/``after_cursor_id`` are supplied the query uses
+    keyset pagination — ``offset`` is ignored and a WHERE clause selects rows
+    strictly after the given ``(sort_col, id)`` position in the active sort
+    direction. The cursor value must already be typed for the column
+    (datetime for time sorts, int for size, str for name); the caller decodes
+    the opaque cursor string and resolves to the typed value.
+
     Returns (references, tag_map, total_count).
     """
     base = (
@@ -297,9 +306,31 @@ def list_references_page(
         "size": Asset.size_bytes,
     }
     sort_col = sort_map.get(sort, AssetReference.created_at)
-    sort_exp = sort_col.desc() if order == "desc" else sort_col.asc()
+    descending = order == "desc"
+
+    # Keyset WHERE: (sort_col, id) strictly less-than / greater-than the cursor.
+    # Equivalent to: sort_col <op> v  OR  (sort_col = v AND id <op> cursor_id).
+    if after_cursor_value is not None and after_cursor_id is not None:
+        if descending:
+            keyset = sa.or_(
+                sort_col < after_cursor_value,
+                sa.and_(sort_col == after_cursor_value, AssetReference.id < after_cursor_id),
+            )
+        else:
+            keyset = sa.or_(
+                sort_col > after_cursor_value,
+                sa.and_(sort_col == after_cursor_value, AssetReference.id > after_cursor_id),
+            )
+        base = base.where(keyset)
+
+    # Secondary ORDER BY id (matching the primary direction) gives the keyset
+    # comparison a deterministic tiebreaker on duplicate sort_col values.
+    id_exp = AssetReference.id.desc() if descending else AssetReference.id.asc()
+    sort_exp = sort_col.desc() if descending else sort_col.asc()
 
-    base = base.order_by(sort_exp).limit(limit).offset(offset)
+    base = base.order_by(sort_exp, id_exp).limit(limit)
+    if after_cursor_id is None:
+        base = base.offset(offset)
 
     count_stmt = (
         select(sa.func.count())

app/assets/services/asset_management.py

@@ -1,8 +1,19 @@
 import contextlib
 import mimetypes
 import os
+from datetime import timezone
 from typing import Sequence
 
+from app.assets.services.cursor import (
+    CursorPayload,
+    InvalidCursorError,
+    decode_cursor,
+    decode_cursor_int,
+    decode_cursor_time,
+    encode_cursor,
+    encode_cursor_from_time,
+)
+
 
 from app.assets.database.models import Asset
 from app.assets.database.queries import (
@@ -242,6 +253,11 @@ def get_asset_by_hash(asset_hash: str) -> AssetData | None:
         return extract_asset_data(asset)
 
 
+# Sort fields that support cursor pagination. `last_access_time` is not
+# in this list — it falls back to offset/limit.
+_CURSOR_SORT_FIELDS = ("created_at", "updated_at", "name", "size")
+
+
 def list_assets_page(
     owner_id: str = "",
     include_tags: Sequence[str] | None = None,
@@ -252,7 +268,39 @@ def list_assets_page(
     offset: int = 0,
     sort: str = "created_at",
     order: str = "desc",
+    after: str | None = None,
 ) -> ListAssetsResult:
+    """List assets with optional cursor pagination.
+
+    When ``after`` is supplied it overrides ``offset``. The cursor's sort field
+    must match ``sort`` and be in the cursor-supported allowlist; mismatches
+    raise InvalidCursorError so the handler can map to 400 INVALID_CURSOR.
+    """
+    cursor_value: object | None = None
+    cursor_id: str | None = None
+    # Mint next_cursor on every page where the sort is cursor-supported, not
+    # only when the request itself arrived with a cursor. Otherwise a first
+    # request (no `after`) returns next_cursor=None and the client can never
+    # enter cursor mode.
+    mint_cursor = sort in _CURSOR_SORT_FIELDS
+
+    if after is not None:
+        if sort not in _CURSOR_SORT_FIELDS:
+            raise InvalidCursorError(
+                f"cursor pagination is not supported for sort={sort!r}"
+            )
+        payload = decode_cursor(after, _CURSOR_SORT_FIELDS, expected_order=order)
+        if payload.sort_field != sort:
+            raise InvalidCursorError(
+                f"cursor sort field {payload.sort_field!r} does not match request sort {sort!r}"
+            )
+        cursor_value, cursor_id = _resolve_cursor_value(payload), payload.id
+
+    # Over-fetch by one row so we can distinguish "exactly `limit` rows total
+    # remaining" from "more rows past this page" without a second query. Drop
+    # the sentinel before returning.
+    fetch_limit = limit + 1 if mint_cursor else limit
+
     with create_session() as session:
         refs, tag_map, total = list_references_page(
             session,
@@ -261,12 +309,22 @@ def list_assets_page(
             exclude_tags=exclude_tags,
             name_contains=name_contains,
             metadata_filter=metadata_filter,
-            limit=limit,
+            limit=fetch_limit,
             offset=offset,
             sort=sort,
             order=order,
+            after_cursor_value=cursor_value,
+            after_cursor_id=cursor_id,
         )
 
+        next_cursor: str | None = None
+        if mint_cursor and len(refs) > limit:
+            # There's at least one more row past this page — mint a cursor from
+            # the last row of the page (i.e. index `limit - 1`, since we
+            # over-fetched), and drop the sentinel.
+            next_cursor = _encode_next_cursor(refs[limit - 1], sort, order)
+            refs = refs[:limit]
+
         items: list[AssetSummaryData] = []
         for ref in refs:
             items.append(
@@ -277,7 +335,39 @@ def list_assets_page(
                 )
             )
 
-        return ListAssetsResult(items=items, total=total)
+        return ListAssetsResult(items=items, total=total, next_cursor=next_cursor)
+
+
+def _resolve_cursor_value(payload: CursorPayload) -> object:
+    """Map a decoded cursor payload to a column-typed Python value."""
+    if payload.sort_field in ("created_at", "updated_at"):
+        # DB stores naive UTC; strip tzinfo so the comparison binds against a
+        # `TIMESTAMP WITHOUT TIME ZONE` column without an offset shift.
+        return decode_cursor_time(payload).replace(tzinfo=None)
+    if payload.sort_field == "size":
+        return decode_cursor_int(payload)
+    return payload.value  # name, str-typed
+
+
+def _encode_next_cursor(ref, sort: str, order: str) -> str | None:
+    """Mint a cursor pointing at *ref* for the given sort dimension.
+
+    Returns None when the boundary row carries a NULL sort value (e.g. an asset
+    record whose size_bytes hasn't been backfilled). Continuing pagination
+    across a NULL boundary is undefined under keyset ordering — better to
+    truncate cleanly here than to mint a cursor that mis-positions.
+    """
+    if sort == "name":
+        return encode_cursor("name", ref.name, ref.id, order=order)
+    if sort == "size":
+        if ref.asset is None or ref.asset.size_bytes is None:
+            return None
+        return encode_cursor("size", str(ref.asset.size_bytes), ref.id, order=order)
+    # created_at / updated_at — DB datetimes are naive UTC; attach tz before encoding.
+    value = ref.created_at if sort == "created_at" else ref.updated_at
+    if value is None:
+        return None
+    return encode_cursor_from_time(sort, value.replace(tzinfo=timezone.utc), ref.id, order=order)
 
 
 def resolve_hash_to_path(