Design compare workflow for many-to-many analysis

## Summary
Design a compare workflow that can run many-to-many comparisons, optionally through an external app service, and send results into a new chat.

## User Value
Tracking this as a GitHub issue moves the backlog item out of a private markdown file and gives the team a clear place to prioritize, design, implement, and validate the work.

## Proposed Behavior
Define input selection, batch size limits, artifact storage, resumability, comparison output schema, and how users open or continue from generated results.

## Acceptance Criteria
- [ ] The requested behavior is designed or implemented for the relevant SimpleChat surfaces.
- [ ] Permission, configuration, and existing-feature interactions are accounted for.
- [ ] Tests, documentation, or validation notes are added as appropriate.

## Notes
- Source backlog entry: Compare Workflow / Many-To-Many Analysis
- Source file: priv-simplechat-2/grouped_feature_fix_backlog.md
- Backlog status: Research / New
- Current anchors: personal/group workflows, generated analysis artifacts, document comparison docs
- Proposed roadmap priority: P2
- Proposed roadmap size: L
- Related: #941 covers assigned-knowledge agents choosing search/analyze/compare by intent; #212 covered basic document comparison.