In `@src/sentry/api/endpoints/organization_auditlogs.py` around lines 68 - 83, The
OptimizedCursorPaginator will raise TypeError when used with
order_by="-datetime" because get_item_key attempts math.floor on datetime
objects; fix by either switching the paginator used in this branch to
DateTimePaginator when order_by references "datetime" (i.e., detect
order_by.endswith("datetime") and call self.paginate with
paginator_cls=DateTimePaginator) or by making OptimizedCursorPaginator inherit
from DateTimePaginator and implement the same datetime-to-millisecond conversion
in its get_item_key/parse_key methods so datetime values are converted to
millisecond timestamps before floor/ceil operations.

In `@src/sentry/api/paginator.py` around lines 179 - 184, The current logic sets
start_offset = offset when cursor.is_prev is True which allows negative offsets
and will cause Django QuerySet slicing (queryset[start_offset:stop]) to raise an
error; change this to either (a) clamp the offset to non‑negative with
start_offset = max(0, offset) regardless of cursor.is_prev, or (b) validate and
raise/reject negative offsets consistent with the other paginator classes —
update the start_offset assignment and any related validation so
queryset[start_offset:stop] never receives a negative start index (refer to
start_offset, cursor.is_prev, offset, and the queryset slice).

In `@src/sentry/api/paginator.py` around lines 838 - 843, get_item_key and
value_from_cursor currently assume numeric values and break for datetime fields;
update get_item_key (in the paginator class) to detect datetime values
(isinstance(value, datetime)) and convert them to a numeric epoch (e.g.,
milliseconds since epoch) before applying math.floor/math.ceil so both asc/desc
branches work, and update value_from_cursor to return the appropriate datetime
or numeric epoch expected by the queryset filter (convert cursor.value back to a
datetime when the paginator is used for datetime-ordered queries), or
alternatively make this paginator subclass DateTimePaginator so datetime-aware
behavior is inherited; reference get_item_key, value_from_cursor, and consider
organization_auditlogs.py usage with order_by="-datetime" when implementing the
conversion.

In `@src/sentry/api/paginator.py` around lines 877 - 882, The current branch in
paginator.py that checks enable_advanced_features and uses a negative
cursor.offset then does queryset[start_offset:stop] is invalid because Django
QuerySets do not support negative slicing; remove this unsupported
negative-slice path or replace it with a supported approach: when cursor.offset
< 0 either raise a clear error/ValidationError or implement reverse-pagination
by calling queryset.reverse() and converting the negative offset into a positive
slice (e.g., compute positive_start = max(0, -cursor.offset - (limit+extra)) and
positive_stop accordingly) before slicing; update references to
enable_advanced_features, cursor.offset, start_offset and results to use the
chosen supported strategy.

In `@src/sentry/api/paginator.py` around lines 883 - 886, The else branch in
paginator where `start_offset` is set uses `start_offset = max(0, offset) if not
cursor.is_prev else offset`, which leaves a negative `offset` unchecked when
`cursor.is_prev` is True and can break Django QuerySet slicing; change the logic
in the paginator (the code that computes `start_offset` near `cursor.is_prev`,
`start_offset`, and `stop` used for `queryset[start_offset:stop]`) to always
clamp `offset` to a non-negative value (e.g., use `start_offset = max(0,
offset)` for both branches or ensure `offset` is bounded before assignment) so
`queryset` slicing never receives a negative start index.

In `@src/sentry/api/paginator.py` around lines 888 - 892, The code trims results
using len(results) == offset + limit + extra but the slice logic uses
start_offset; change the comparison to use start_offset so the trimming
condition matches the actual slice calculation. Update the block that checks
cursor.is_prev and cursor.value (and the branch referencing results,
get_item_key(..., for_prev=True), offset, limit, extra) to compare against
start_offset instead of offset to ensure correct row trimming when offset was
clamped or modified.