Fix(llm): complete response cache — set_model invalidation, stats logging, sync mutex (#290)

* fix(llm): complete response cache — set_model invalidation, stats logging, sync mutex

# Conflicts:
#	src/llm/response_cache.rs

* fix(llm): address response cache review comments

- Add total_hit_count AtomicU64 that is never decremented on eviction;
  maybe_log_stats now uses this counter so hit_rate_pct stays accurate
  under high eviction pressure
- Log cache stats before returning on provider error so milestone
  intervals (every 100 requests) are never silently skipped
- Add tracing-test dev-dep and three new tests: total_hits_survives_eviction,
  stats_logged_at_request_100, stats_logged_on_provider_error_at_interval
- Update PR description to reflect actual set_model() behavior (key
  isolation, not cache clear)

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

---------

Co-authored-by: Claude Sonnet 4.6 <[email protected]>

Cargo.lock

@@ -2902,6 +2902,7 @@ dependencies = [
  "tower-http 0.6.8",
  "tracing",
  "tracing-subscriber",
+ "tracing-test",
  "url",
  "urlencoding",
  "uuid",
@@ -6229,6 +6230,27 @@ dependencies = [
  "tracing-serde",
 ]
 
+[[package]]
+name = "tracing-test"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "19a4c448db514d4f24c5ddb9f73f2ee71bfb24c526cf0c570ba142d1119e0051"
+dependencies = [
+ "tracing-core",
+ "tracing-subscriber",
+ "tracing-test-macro",
+]
+
+[[package]]
+name = "tracing-test-macro"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ad06847b7afb65c7866a36664b75c40b895e318cea4f71299f013fb22965329d"
+dependencies = [
+ "quote",
+ "syn 2.0.114",
+]
+
 [[package]]
 name = "try-lock"
 version = "0.2.5"