feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier

Replace MTP with draft-dflash and a separate DFlash2 drafter GGUF.
Remove the qwen-classifier backend to free VRAM (GPU was at 100%).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

CONTEXT.md

@@ -17,7 +17,7 @@ _Avoid_: using it as a synonym for Server
 ### Serving models
 
 **Backend**:
-A model server process that serves one model to the gateway (`llama-server`, `qwen-classifier`).
+A model server process that serves one model to the gateway (`llama-server`).
 _Avoid_: provider, model server
 
 **Slot**:
@@ -28,9 +28,9 @@ _Avoid_: parallel request, lane
 The large model that does the actual work for workloads.
 _Avoid_: chat model
 
-**Classifier model**:
-The small model that judges a coding CLI's tool calls before they run.
-_Avoid_: fast model (`fastModel` only when quoting qwen-code's config key)
+**Draft model**:
+The small speculative-decoding drafter that runs beside the main model inside `llama-server` (DFlash2).
+_Avoid_: classifier model (the separate classifier backend was removed)
 
 ### Reaching the models