Parses task list from document when the response is tasks-only (iteration output). Requires only ## Tasks and task sections; does not require or set Original prompt or Goals / summary. Caller must preserve goals_summary_md from the existing list.
Creates a new List, assigns to runner.pending at start, then builds into it. Step uses this.runner.pending (this.list) during register_slugs. On validation/parse failure do NOT clear runner.pending — leave the parsed list so Runner can capture the failed proposal and restore this.pending = existing_proposed.
Appends to issues on each failure. Used by Runner after task list iteration.