Add optional Gemini context caching and cache usage accounting

config/llm.gemini-cache.example.toml

@@ -0,0 +1,35 @@
+# Optional separate configuration. Copy to an ignored *.local.toml file.
+# This does not replace the existing OpenAI-compatible configuration.
+[llm]
+privacy_profile = "cloud_allowed"
+max_attempts = 10
+retry_delay_seconds = 60
+blocked_retry_seconds = 3600
+
+[[llm.providers]]
+id = "gemini-native"
+adapter = "gemini"
+privacy = "cloud"
+base_url = "https://generativelanguage.googleapis.com/v1beta"
+model = "gemini-3.8-flash"
+api_key_env = "GEMINI_API_KEY"
+timeout_seconds = 300
+response_format = "json_object"
+max_output_tokens = 16384
+reasoning_effort = "medium"
+entity_resolution_reasoning_effort = "low"
+
+# Opt-in. Instruction/schema prefix only; live evidence is always complete.
+context_cache = true
+cache_ttl_seconds = 300
+# A character heuristic, not a tokenizer or a format limit. Provider minimums
+# still apply; rejected/too-small cache requests fall back to the full input.
+cache_min_prefix_chars = 16000
+
+# Optional estimates in USD per million tokens; verify your model/tariff/date.
+# These illustrative standard-tier rates are from 2026-10-16, valid through
+# 2026-12-31 for the model above, not universal/default prices.
+input_cost_per_million = 0.75
+cached_input_cost_per_million = 0.075
+output_cost_per_million = 3.75
+cache_storage_cost_per_million_hour = 0.50