feat(core): GPU-offload clamp with per-workload floor

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

crates/core/src/tuning.rs

@@ -59,7 +59,13 @@ pub fn inference_thread_count(workload: Workload, gpu_offloaded: bool) -> usize
     if power::probe_power_state() == PowerState::OnBattery {
         chosen /= 2;
     }
-    let _ = (workload, gpu_offloaded); // GPU clamp added in next task
+    if gpu_offloaded {
+        let floor = match workload {
+            Workload::Llm => GPU_FLOOR_LLM,
+            Workload::Whisper => GPU_FLOOR_WHISPER,
+        };
+        chosen = chosen.min(floor);
+    }
     chosen.clamp(MIN_INFERENCE_THREADS, MAX_INFERENCE_THREADS)
 }
 
@@ -128,4 +134,52 @@ mod tests {
             }
         });
     }
+
+    #[test]
+    fn gpu_offload_clamps_llm_to_floor() {
+        with_thread_env_lock(|| {
+            std::env::remove_var("MAGNOTIA_INFERENCE_THREADS");
+            crate::power::with_override(Some(PowerState::OnAc), || {
+                let n = inference_thread_count(Workload::Llm, true);
+                assert!(n <= GPU_FLOOR_LLM.max(MIN_INFERENCE_THREADS),
+                        "Llm with GPU offload should clamp to {GPU_FLOOR_LLM}, got {n}");
+                assert!(n >= MIN_INFERENCE_THREADS);
+            });
+        });
+    }
+
+    #[test]
+    fn gpu_offload_clamps_whisper_to_floor() {
+        with_thread_env_lock(|| {
+            std::env::remove_var("MAGNOTIA_INFERENCE_THREADS");
+            crate::power::with_override(Some(PowerState::OnAc), || {
+                let n = inference_thread_count(Workload::Whisper, true);
+                // Whisper floor is 4 on machines with >=4 physical cores;
+                // can't go lower than physical so on a 2c host we stay at 2.
+                assert!(n <= GPU_FLOOR_WHISPER, "got {n}");
+                assert!(n >= MIN_INFERENCE_THREADS);
+            });
+        });
+    }
+
+    #[test]
+    fn whisper_gpu_floor_is_at_least_llm_gpu_floor() {
+        // Architectural invariant: whisper retains CPU work even when
+        // GPU-offloaded; its floor must not be lower than the LLM's.
+        assert!(GPU_FLOOR_WHISPER >= GPU_FLOOR_LLM);
+    }
+
+    #[test]
+    fn gpu_offload_off_does_not_clamp_below_battery_calc() {
+        with_thread_env_lock(|| {
+            std::env::remove_var("MAGNOTIA_INFERENCE_THREADS");
+            // Sequential measurements; with_override is non-reentrant.
+            crate::power::with_override(Some(PowerState::OnAc), || {
+                let no_gpu = inference_thread_count(Workload::Llm, false);
+                let with_gpu = inference_thread_count(Workload::Llm, true);
+                // GPU-offloaded should be <= non-offloaded.
+                assert!(with_gpu <= no_gpu);
+            });
+        });
+    }
 }