Parses task list from document when the response is continue output. Requires ## Goals / summary and ## Tasks; ignores ## Original prompt and ## Follow-up prompts if present. Sets runner.pending.goals_summary_md directly (same as parse_task_list). Caller must set runner.pending to a fresh List before calling. Caller appends the prompt-box message to runner.user_prompts on success.
Appends to issues on each failure. Used by Runner after session continue. Step.register_slugs and task validation on step 0 only (same rule as parse_task_list and parse_task_list_iteration).