class OnlineEvaluatorsAPIResourceDelete multiple evaluators by their IDs. Returns per-item success/failure.
Add RUN or THREAD items to a single annotation queue. RUN items require run_id unless they are created from a suggested example. THREAD items require thread_id and project_id.
List RUN and THREAD items in a single annotation queue for one review status section, with opaque cursor pagination. Optional item_type=RUN|THREAD filters the page. direction=backward returns items before the supplied cursor. The response contains item metadata only, not expanded run or thread payloads. status=archived returns items whose queue review requirements have been satisfied, not merely items the caller personally marked completed.
Alpha: The request and response contract may change; Returns one run within the trace identified by the share token. The request supplies only the run ID and that run's exact start_time coordinate.
Returns per-day LLM evaluator spend for the requested 7-day period, grouped by evaluator, resource, or run rule. Exactly one of group_by, evaluator_id, session_id, or dataset_id is required. resource_id, type, and feedback_key may be supplied with group_by to narrow listing aggregations.
Partially update mutable timestamps (added_at, last_reviewed_time) for a RUN or THREAD annotation queue item. Omit a field, or pass JSON null, to leave it unchanged.