fix(production): wire real inference path through engine, serving, and streaming

- rtx-inference: sample_next_token now copies the actual logits from the
  forward pass (Tensor::to_vec, last-token slice) instead of sampling
  from a fabricated all-zero vector; request metrics report measured
  queue/processing times instead of hardcoded constants.
- rtx-serving-api: depends on rtx-inference; /v1/completions dispatches
  to a shared InferenceEngine (byte-level tokenization until a real
  tokenizer is threaded through) and returns 503 when no engine is
  loaded instead of mock text. ServingServer::with_engine attaches one.
- rtx-streaming: depends on rtx-inference; generate_tokens delegates to
  an attached backend engine and errors without one instead of emitting
  "token_N" placeholders; tokenization is byte-level, not position-mod.
- speculative decoding: document the orchestration (speculative/) vs
  implementation (medusa.rs/lookahead.rs) layering; CLAUDE.md no longer
  claims a standalone rtx-speculative-decoding crate.

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

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

@@ -34,13 +34,31 @@ impl Default for ServerConfig {
 /// Serving server
 pub struct ServingServer {
     config: ServerConfig,
+    state: inference::AppState,
 }
 
 impl ServingServer {
-    /// Create a new serving server
+    /// Create a new serving server (no engine loaded; inference returns 503)
     #[must_use]
     pub fn new(config: ServerConfig) -> Self {
-        Self { config }
+        Self {
+            config,
+            state: inference::AppState::default(),
+        }
+    }
+
+    /// Create a serving server backed by a live inference engine
+    #[must_use]
+    pub fn with_engine(
+        config: ServerConfig,
+        engine: std::sync::Arc<tokio::sync::RwLock<rtx_inference::InferenceEngine>>,
+    ) -> Self {
+        Self {
+            config,
+            state: inference::AppState {
+                engine: Some(engine),
+            },
+        }
     }
 
     /// Build the Axum router with all routes
@@ -68,6 +86,7 @@ impl ServingServer {
             .layer(TimeoutLayer::new(Duration::from_secs(
                 self.config.timeout_seconds,
             )))
+            .with_state(self.state.clone())
     }
 
     /// Start the server