fix(moa): propagate api_mode from slot runtime to call_llm

Slot_runtime resolved the provider's real API surface (including api_mode)
but only forwarded base_url and api_key to call_llm, dropping api_mode.
This caused Copilot GPT-5.x reference slots to hit /chat/completions
instead of the Responses API, returning 400 unsupported_api_for_model.

- _slot_runtime: forward api_mode from resolve_runtime_provider
- call_llm: accept explicit api_mode param, override task config
- 4 regression tests for propagation, omission, and signature

agent/moa_loop.py

@@ -109,6 +109,8 @@ def _slot_runtime(slot: dict[str, str]) -> dict[str, Any]:
             out["base_url"] = rt["base_url"]
         if rt.get("api_key"):
             out["api_key"] = rt["api_key"]
+        if rt.get("api_mode"):
+            out["api_mode"] = rt["api_mode"]
     except Exception as exc:  # pragma: no cover - defensive
         logger.debug("MoA slot runtime resolution failed for %s: %s", _slot_label(slot), exc)
     return out