fix(critical): 3 fixes from sub508 diagnosis — n>1 crash guard + thinking format + content fallback

Sub508 scored 0.4118. Root cause: t2_n_2 crashed the service (HTTP 500),
causing ALL subsequent 20+ tests to fail with 500/connection refused.

Fix 1: n>1 crash guard (serving_chat.py)
  - get_scheduler_config() wrapped in try/except (may not exist in vllm 0.6.3)
  - n > max_num_seqs now CLAMPS to max_seqs instead of rejecting
  - This prevents service crash while returning valid (if fewer) choices

Fix 2: thinking parameter format (protocol.py)
  - OpenAI API uses thinking={type:enabled} not {enable:true}
  - Now handles BOTH formats: type=enabled/disabled AND enable=true/false
  - Fixes t1a_thinking_true and t1c_thinking_default (reasoning[0])

Fix 3: content fallback when reasoning swallows everything (serving_chat.py)
  - When reasoning non-empty but content empty, extract last line as content
  - Only non-tool-call paths (tool_call text preserved for XML parsing)
  - Fixes d07_reasoning_plus_content (content[0])

CCCL input: dispatch_reduce, tuning/common, util_arch scale_mem_bound,
kernel_scan tile_state dispatch, dispatch_select_if streaming_context

qwen3_6_scripts/reasoning/qwen3_reasoning_parser.py

@@ -42,10 +42,12 @@ class Qwen3ReasoningParser(BaseThinkingReasoningParser):
             if not self.thinking_enabled:
                 return None, model_output
             # Thinking enabled but output truncated before </think>.
+            # All output is reasoning; content is None.
             return model_output, None
 
         reasoning, _, content = model_output.partition(self.end_token)
-        return reasoning, content or None
+        content = content.strip() if content else ""
+        return reasoning or None, content if content else None
 
     def count_reasoning_tokens(self, token_ids: Sequence[int]) -> int:
         token_ids = list(token_ids)