Enable explicit caching by default on capable Gemini adapter

config/llm.gemini-cache.example.toml

@@ -1,4 +1,4 @@
-# Optional separate configuration. Copy to an ignored *.local.toml file.
+# Native Gemini configuration. Copy to an ignored *.local.toml file.
 # This does not replace the existing OpenAI-compatible configuration.
 [llm]
 privacy_profile = "cloud_allowed"
@@ -19,7 +19,8 @@ max_output_tokens = 16384
 reasoning_effort = "medium"
 entity_resolution_reasoning_effort = "low"
 
-# Opt-in. Instruction/schema prefix only; live evidence is always complete.
+# Enabled by default on this adapter. Instruction/schema prefix only;
+# live evidence is always complete. Explicit false is an operational override.
 context_cache = true
 cache_ttl_seconds = 300
 # A character heuristic, not a tokenizer or a format limit. Provider minimums