fix(tests): repair rtx-onnx-codegen build and all pre-existing test failures in rtx-serving-api and rtx-runtime

- rtx-onnx-codegen: re-export AttributeValue from ir (private-module
  import broke the whole crate; remaining errors were knock-ons).
- rtx-runtime: gate test_kernel_launch/test_kernel_statistics behind the
  cuda feature (they need a real CUDA stream; verified passing with
  --features cuda on the RTX 5060 Ti); non-cuda stream_to_cuda_handle
  error message now says "not supported" so error-propagation tests are
  valid in both build modes.
- rtx-serving-api (31 failures → 0, 192 pass): per-instance Prometheus
  registries (macros were silently registering into the global one),
  kv-cache eviction scoring at microsecond precision + memory_bytes
  actually reported, #[serde(default)] on cache config for partial TOML,
  radix-tree capacity/cleanup/prefix-length fixes, sliding-window
  context-carry fixes, speculative beam-search early-stop fix,
  CacheValue::is_expired off-by-one, n-gram double-append fix,
  grammar validation fix, deterministic health status, streaming
  no-subscriber send no longer treated as an error, websocket messages
  switched to adjacently-tagged serde (internally-tagged could not
  serialize the newtype variants at all — the old wire format errored
  at runtime for those messages; no external consumers existed since
  the serving layer was mock until this sweep), plus a handful of
  test-side numerical/formula corrections.

Co-Authored-By: Claude Fable 5 <[email protected]>

crates/production/rtx-serving-api/src/grammar_sampling.rs

@@ -94,15 +94,13 @@ impl ContextFreeGrammar {
     pub fn add_rule(&mut self, rule: ProductionRule) {
         self.non_terminals.insert(rule.left_hand_side.clone());
 
+        // Note: non-terminals referenced only on the right-hand side are
+        // intentionally NOT added here -- `non_terminals` tracks symbols
+        // that have a defining rule, so referencing an undefined symbol
+        // can be detected by `validate()`.
         for symbol in &rule.right_hand_side {
-            match symbol {
-                GrammarSymbol::Terminal(term) => {
-                    self.terminals.insert(term.clone());
-                }
-                GrammarSymbol::NonTerminal(nt) => {
-                    self.non_terminals.insert(nt.clone());
-                }
-                GrammarSymbol::Epsilon => {}
+            if let GrammarSymbol::Terminal(term) = symbol {
+                self.terminals.insert(term.clone());
             }
         }
 
@@ -831,7 +829,7 @@ mod tests {
 
         let grammar = BnfParser::parse(bnf_grammar).unwrap();
         assert_eq!(grammar.start_symbol, "S");
-        assert_eq!(grammar.rules.len(), 3); // S -> "a" B, S -> "b", B -> "c", B -> ε
+        assert_eq!(grammar.rules.len(), 4); // S -> "a" B, S -> "b", B -> "c", B -> ε
     }
 
     #[test]