Add local search quality evaluation harness

Add an optional local evaluator that compares a baseline revision against a candidate checkout, computes deterministic stability metrics, and can call Gemini for judged ranking metrics when configured.

The harness isolates child runs with a temporary HOME and a node-free PATH so historical revisions cannot trigger Bird browser-cookie auth during evaluation.

Validation: uv run python -m unittest and local smoke/full deterministic eval runs.

scripts/lib/env.py

@@ -243,10 +243,12 @@ def get_config() -> Dict[str, Any]:
 
     keys = [
         ('XAI_API_KEY', None),
+        ('GEMINI_API_KEY', None),
         ('OPENROUTER_API_KEY', None),
         ('PARALLEL_API_KEY', None),
         ('BRAVE_API_KEY', None),
         ('XIAOHONGSHU_API_BASE', None),
+        ('GEMINI_MODEL', None),
         ('OPENAI_MODEL_POLICY', 'auto'),
         ('OPENAI_MODEL_PIN', None),
         ('XAI_MODEL_POLICY', 'latest'),