feat: per-model max_rounds for Gemini orchestrator engine

Mirrors the pattern already in openai_orchestrator.py. The Gemini engine
was still hardcoded to the global orchestrator_max_rounds setting.

- orchestrator_engine.py: max_rounds param on run() and _run_from_contents();
  effective_limit = min(per_model_limit, global_limit); stored in checkpoint
  so resume() respects it across confirmation gates
- routers/orchestrator.py: passes orch_model.get("max_rounds") to run()
- tools/agents.py: passes model_cfg.get("max_rounds") for gemini_api spawns

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

cortex/routers/orchestrator.py

@@ -247,6 +247,7 @@ async def _run_job(job_id: str, req: OrchestrateRequest, user: str) -> None:
                 tool_list=tool_list,
                 confirm_allow=confirm_allow,
                 confirm_deny=confirm_deny,
+                max_rounds=orch_model.get("max_rounds") if orch_model else None,
             )
 
         if result.checkpoint: