feat: update default backend to AirLLM and optimize for Mac M3 36GB

src/config.py

@@ -41,12 +41,13 @@ class Settings(BaseSettings):
     # "airllm"  — always use AirLLM (requires pip install ".[bigbrain]")
     # "auto"    — use AirLLM on Apple Silicon if airllm is installed,
     #             fall back to Ollama otherwise
-    timmy_model_backend: Literal["ollama", "airllm", "grok", "claude", "auto"] = "ollama"
+    timmy_model_backend: Literal["ollama", "airllm", "grok", "claude", "auto"] = "airllm"
 
     # AirLLM model size when backend is airllm or auto.
     # Larger = smarter, but needs more RAM / disk.
     # 8b  ~16 GB  |  70b  ~140 GB  |  405b  ~810 GB
-    airllm_model_size: Literal["8b", "70b", "405b"] = "70b"
+    # Optimization: Llama-3.3-70B-Instruct-MLX is recommended for Mac M3 36GB.
+    airllm_model_size: str = "70b"
 
     # ── Grok (xAI) — opt-in premium cloud backend ────────────────────────
     # Grok is a premium augmentation layer — local-first ethos preserved.

src/timmy/backends.py

@@ -23,9 +23,10 @@ from timmy.prompts import SYSTEM_PROMPT
 logger = logging.getLogger(__name__)
 
 # HuggingFace model IDs for each supported size.
+# 70b is optimized for Mac M3 36GB using Llama-3.3-70B-Instruct-MLX.
 _AIRLLM_MODELS: dict[str, str] = {
     "8b": "meta-llama/Meta-Llama-3.1-8B-Instruct",
-    "70b": "meta-llama/Meta-Llama-3.1-70B-Instruct",
+    "70b": "meta-llama/Llama-3.3-70B-Instruct-MLX",
     "405b": "meta-llama/Meta-Llama-3.1-405B-Instruct",
 }
 
@@ -128,7 +129,10 @@ class TimmyAirLLMAgent:
     # ── private helpers ──────────────────────────────────────────────────────
 
     def _build_prompt(self, message: str) -> str:
-        context = SYSTEM_PROMPT + "\n\n"
+        from timmy.prompts import get_system_prompt
+        # AirLLM uses 70b by default which is tool-capable
+        system_prompt = get_system_prompt(tools_enabled=True)
+        context = system_prompt + "\n\n"
         # Include the last 10 turns (5 exchanges) for continuity.
         if self._history:
             context += "\n".join(self._history[-10:]) + "\n\n"