feat(vllm): lfm2.5 reasoning-parser (deepseek_r1) — scoreable JSON for brokkr's bake-off

LFM2.5 is </think>-delimited (opening tag in prompt); deepseek_r1 splits
reasoning into reasoning_content so content is the clean post-</think>
answer. Re-smoke: content valid JSON + reasoning_content populated. License
production-cleared (operator <$10M ruling), still out of routing per the
measurement gate.

stacks/vllm/compose.yaml

@@ -385,6 +385,12 @@ services:
       - --kv-cache-dtype
       - ${LFM25_KV_CACHE_DTYPE}
       - --enable-prefix-caching
+      # Split the <think> reasoning (delimited by </think>; the opening tag is
+      # injected by the chat template into the prompt) into reasoning_content, so
+      # `content` is the clean post-</think> answer — scoreable JSON for brokkr's
+      # structured-extraction bake-off (raw-served, reasoning prepended, is not).
+      - --reasoning-parser
+      - deepseek_r1
     deploy:
       resources:
         reservations: