Cache stable investigation case context with versioned deterministic aliases

config/llm.gemini-cache.example.toml

@@ -19,9 +19,12 @@ max_output_tokens = 16384
 reasoning_effort = "medium"
 entity_resolution_reasoning_effort = "low"
 
-# Enabled by default on this adapter. Instruction/schema prefix only;
+# Enabled by default on this adapter. Stable case context plus instructions/schema;
 # live evidence is always complete. Explicit false is an operational override.
 context_cache = true
+cache_context_version = "stable_case_v1"
+# For replay with the previous instruction/schema-only config snapshot:
+# cache_context_version = "instructions_v1"
 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.