feat: add CLI history baseline and regression ergonomics

[salim4n]

Summary

• Add CLI history commands: eval history list and eval history show.
• Add eval run --history ... --record-history for local JSONL history.
• Add baseline selection with --baseline latest|entry-id and regression checks with thresholds.
• Add optional regression Markdown output and docs for local/CI loops.

Out of scope

• Database or hosted history
• SaaS dashboard
• Remote execution
• Provider calls
• New reward algorithms
• PPO or policy optimization

Validation

• bun test packages/cli/src/index.test.ts
• bun run lint
• bun run typecheck
• bun run test
• bun run build
• bun run pack:check
• CLI smoke: record history, baseline latest regression, list, show
• git diff --check