Phase 6.4.25: point vllm-eval at v2-bf16 and record gate 2/5-holdout results

Gate 2 on v2-bf16: PASS, 192/200 = 96.0% (penpot 60/60 = 100.0%).
Gate 5 holdout mode (60 prompts, fallback trigger): FAIL, forbidden-API
rate 15.0% (9/60) vs threshold <=5% -- model still occasionally invents
penpot.importImage(...) for photo/URL prompts.

docker-compose.eval.yml

@@ -7,10 +7,13 @@ services:
     ports:
       - "8001:8000"
     volumes:
-      - /home/aleleba/ft-models/Qwen3.6-35B-A3B-mcp-bf16:/model:ro
+      # Fase 6.4.25: apunta al candidato v2-bf16 (base + LoRA #1 + LoRA #2), no al
+      # bf16 de Fase 4 (que solo tiene el LoRA #1). Es el checkpoint contra el que
+      # corren las puertas 5 y 2 del disparador de fallback antes de cuantizar.
+      - /home/aleleba/ft-models/Qwen3.6-35B-A3B-mcp-v2-bf16:/model:ro
     command:
       - "--model=/model"
-      - "--served-model-name=qwen3.6-35b-a3b-mcp-bf16"
+      - "--served-model-name=qwen3.6-35b-a3b-mcp-v2-bf16"
       - "--tensor-parallel-size=1"
       - "--max-model-len=32768"
       - "--enable-auto-tool-choice"