feat(benchmark): add hook mode with baseline cache for pre-push checks

- Fix lint errors and LSP issues in benchmark.py
- Add --hook mode to compare against saved baseline
- Add --baseline flag to save results as baseline
- Add --threshold to configure degradation threshold (default 20%)
- Add benchmark step to pre-push hook in hk.pkl
- Update AGENTS.md with hk documentation links and benchmark runner docs

hk.pkl

@@ -22,6 +22,9 @@ hooks {
                 prefix = "uv run"
                 check = "ruff check engine/ tests/"
             }
+            ["benchmark"] {
+                check = "uv run python -m engine.benchmark --hook --displays null --iterations 20"
+            }
         }
     }
 }