Add macOS LLM model engine support and environment setup

selftest.py

@@ -171,6 +171,13 @@ def check_mlx_whisper(synthesized):
     record("mlx whisper (optional)", matches(heard), f"heard {heard!r}")
 
 
+def check_macos_llm():
+    from apple_llm import probe_apple_llm
+
+    available, reason = probe_apple_llm()
+    record("macos llm", available, reason)
+
+
 async def check_claude():
     from claude_agent_sdk import ClaudeSDKClient, ResultMessage, StreamEvent
 
@@ -199,16 +206,16 @@ async def check_claude():
                     if text:
                         spoken.append(text)
                 elif isinstance(message, ResultMessage) and message.is_error:
-                    record("claude session", False, f"error: {message.result}")
+                    record("claude session (optional)", False, f"error: {message.result}")
                     return
     except Exception as e:
         hint = ""
         if "-9" in str(e):
             hint = " — the CLI was killed applying its own sandbox; run this from a normal terminal"
-        record("claude session", False, f"{e}{hint}")
+        record("claude session (optional)", False, f"{e}{hint}")
         return
     record(
-        "claude session",
+        "claude session (optional)",
         True,
         f"replied {''.join(spoken).strip()!r} using {DEFAULT_CLAUDE_MODEL}",
     )
@@ -223,6 +230,7 @@ async def main():
     synthesized = check_kokoro()
     check_apple_stt(synthesized)
     check_mlx_whisper(synthesized)
+    check_macos_llm()
     await check_claude()
 
     required_failures = [