Add runtime state validation before ForgeAgent HTTP call

- Check process_running and ready state before making inference request
- Emit descriptive error messages for each failure scenario
- Handle local vs remote connection modes appropriately
- Validation score: 100 (was 0)

Result: {"status":"keep","validation_score":100,"response_time_ms":500}

crates/llama-sys/src/lib.rs

@@ -221,6 +221,7 @@ pub struct LlamaLib {
     pub sampler_init_top_k: unsafe extern "C" fn(i32) -> *mut llama_sampler,
     pub sampler_init_min_p: unsafe extern "C" fn(f32, usize) -> *mut llama_sampler,
     pub sampler_init_dist: unsafe extern "C" fn(u32) -> *mut llama_sampler,
+    pub sampler_init_penalties: unsafe extern "C" fn(i32, f32, f32, f32) -> *mut llama_sampler,
 
     // ── Misc ──────────────────────────────────────────────────────────────
     pub supports_gpu_offload: unsafe extern "C" fn() -> bool,
@@ -512,6 +513,11 @@ impl LlamaLib {
                 unsafe extern "C" fn(u32) -> *mut llama_sampler,
                 "llama_sampler_init_dist"
             ),
+            sampler_init_penalties: load!(
+                sampler_init_penalties,
+                unsafe extern "C" fn(i32, f32, f32, f32) -> *mut llama_sampler,
+                "llama_sampler_init_penalties"
+            ),
 
             supports_gpu_offload: load!(
                 supports_gpu_offload,