opentui(phase3): launcher integration — HERMES_TUI_ENGINE dual-engine

hermes --tui launches the native OpenTUI engine (Bun) when
HERMES_TUI_ENGINE=opentui (env) or display.tui_engine=opentui (config);
Ink stays the default and the shipping path is untouched.

- _resolve_tui_engine() (env > config > ink); refuses opentui on
  Windows/Termux (no Bun) -> falls back to ink with a notice.
- _make_opentui_argv() -> [bun, src/entry.real.tsx] (no build step).
- _bun_bin() with HERMES_BUN override.
- Branch at top of _make_tui_argv BEFORE _ensure_tui_node (Bun-only host
  must not bootstrap Node).
- Gate _launch_tui NODE_OPTIONS/--max-old-space-size on engine==ink (Bun
  is JSC; the V8 flag errors/ignores).

Verified end-to-end via tmux: real hermes --tui -> Bun -> OpenTUI ->
real Python gateway streamed a real reply. No-flag default still ink.

tests/agent/test_usage_pricing.py

@@ -192,32 +192,6 @@ def test_custom_endpoint_models_api_pricing_is_supported(monkeypatch):
     assert float(entry.output_cost_per_million) == 2.0
 
 
-def test_nous_portal_pricing_preserves_vendor_prefixed_model_ids(monkeypatch):
-    seen = {}
-
-    def _fake_fetch_endpoint_model_metadata(base_url, api_key=None):
-        seen["base_url"] = base_url
-        return {
-            "openai/gpt-5.5-pro": {
-                "pricing": {
-                    "prompt": "0.000025",
-                    "completion": "0.000125",
-                }
-            }
-        }
-
-    monkeypatch.setattr(
-        "agent.usage_pricing.fetch_endpoint_model_metadata",
-        _fake_fetch_endpoint_model_metadata,
-    )
-
-    entry = get_pricing_entry("openai/gpt-5.5-pro", provider="nous")
-
-    assert seen["base_url"] == "https://inference-api.nousresearch.com/v1"
-    assert float(entry.input_cost_per_million) == 25.0
-    assert float(entry.output_cost_per_million) == 125.0
-
-
 def test_deepseek_v4_pro_pricing_entry_exists():
     """Regression test: deepseek-v4-pro must have a pricing entry.