feat: support batch repetition and selective case import

mcp_server/tools/automation.py

@@ -225,13 +225,19 @@ async def mobile_batch(
     reasoning_effort?,device_serial?,verification_level?,explorer_mode?,
     locked_app_package?,record_video?,analyze_video?,request_timeout_seconds?,
     max_retries?,retry_interval_seconds?,timeout_seconds?}}],profile?:flash|pro,
-    formats?:[docx,xlsx],stop_on_failure?:false,timeout_seconds?:1800}. Required device
+    formats?:[docx,xlsx],stop_on_failure?:false,timeout_seconds?:1800,repeat_count?:1}.
+    repeat_count is a positive integer: execute all selected cases in order for each
+    round, with independent session IDs, statuses and reports. The default total limit
+    (cases * repeat_count) is 10000, configurable via ARTEMIS_BATCH_MAX_EXECUTIONS.
+    Only include user-selected cases; get returns iteration/repeat_count per job.
+    Required device
     must be user-selected. Creation validates and saves a DRAFT; start executes it.
     Reuse the same request_id and exact payload after a connection failure; never invent
     a new ID for the same submission. lookup(request_id) resolves an uncertain outcome.
     get returns per-case status. pause stops future dispatch, not the active task;
     use mobile_manage_task(stop) to stop that task. resume never repeats finished cases.
-    retry_failed creates a new draft only after an explicit rerun request; it is not
+    retry_failed copies each failed execution once into a new draft (repeat_count=1)
+    only after an explicit rerun request; it is not
     transport-idempotent, so after an uncertain response use list instead of retrying.
     delete removes a non-active batch and its task sessions, reports and files after
     an explicit user request. Confirm the batch ID with get first; deletion is irreversible.