Refactor access card handling and update CLI output for tunnel operations

- Integrated `print_access_card` functionality into the `up` command for both tunneled and non-tunneled scenarios.
- Removed the deprecated `print_mcp_snippet` function from the session management flow.
- Updated the `tunnel_forwards` function to streamline port handling for LLM runtimes.
- Enhanced test cases to reflect changes in access card printing and MCP snippet logging.

src/gpu_rent/tunnel.py

@@ -15,7 +15,7 @@ from gpu_rent.cloud import (
 )
 from gpu_rent.config import Config
 from gpu_rent.errors import CloudError, GpuRentError
-from gpu_rent.llm_runtime import llm_local_port, llm_remote_port, normalize_runtime
+from gpu_rent.llm_runtime import normalize_runtime
 from gpu_rent.os_client import connect
 from gpu_rent.ssh_ops import wait_ssh
 from gpu_rent.state import load_state, save_state, utc_now
@@ -75,7 +75,6 @@ def tunnel_forwards(cfg: Config) -> list[tuple[int, int]]:
     """List of (local_port, remote_port). SwarmUI always; LLM if configured."""
     pairs = [(cfg.swarmui_local_port, 7801)]
     runtime = normalize_runtime(cfg.llm_runtime)
-    # Prefer state notes if provision recorded a different runtime this session.
     state = load_state()
     noted = (state.notes or {}).get("llm_runtime")
     if noted:
@@ -83,17 +82,10 @@ def tunnel_forwards(cfg: Config) -> list[tuple[int, int]]:
             runtime = normalize_runtime(str(noted))
         except ValueError:
             pass
-    remote = llm_remote_port(runtime)
-    local = llm_local_port(cfg) if runtime != "none" else None
-    # llm_local_port uses cfg.llm_runtime — override by mutating check:
     if runtime == "ollama":
-        local = cfg.ollama_local_port
-        remote = 11434
+        pairs.append((cfg.ollama_local_port, 11434))
     elif runtime == "llamacpp":
-        local = cfg.llamacpp_local_port
-        remote = 8080
-    if local and remote:
-        pairs.append((local, remote))
+        pairs.append((cfg.llamacpp_local_port, 8080))
     return pairs
 
 
@@ -194,23 +186,15 @@ def run_tunnel(
 
     server = _start_forwarder(cfg, current_host, forwards)
     swarm_url = f"http://127.0.0.1:{cfg.swarmui_local_port}"
-    log(f"UI {swarm_url}")
-    log(f"API {swarm_url}/API/")
-    log(f"MCP {swarm_url}/mcp")
-    runtime = normalize_runtime(cfg.llm_runtime)
-    state = load_state()
-    if (state.notes or {}).get("llm_runtime"):
-        try:
-            runtime = normalize_runtime(str(state.notes["llm_runtime"]))
-        except ValueError:
-            pass
-    if runtime == "ollama":
-        log(f"Ollama API http://127.0.0.1:{cfg.ollama_local_port}  (OLLAMA_HOST=…)")
-    elif runtime == "llamacpp":
-        log(f"llama.cpp http://127.0.0.1:{cfg.llamacpp_local_port}")
+
+    from gpu_rent.access_card import print_access_card
+
+    print_access_card(cfg, tunneled=True, host=current_host)
+
     if open_browser:
         webbrowser.open(swarm_url)
 
+    state = load_state()
     state.phase = "ready_tunneled"
     save_state(state)