fix(llm): handle empty completions + missing usage (nemotron-friendly)

EmptyCompletionError ora retryable. resp.usage può essere None su
provider :free (es. nemotron-3-super-120b-a12b:free) → no assert.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/multi_swarm/llm/client.py

@@ -21,11 +21,16 @@ MODEL_TIER_C = "qwen/qwen-2.5-72b-instruct"
 MODEL_TIER_D = "meta-llama/llama-3.3-70b-instruct"
 OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
 
+class EmptyCompletionError(RuntimeError):
+    pass
+
+
 # Errori transient: retry. RateLimit/Auth/InvalidRequest: NO retry.
 _RETRYABLE_EXCEPTIONS: tuple[type[BaseException], ...] = (
     openai.APIConnectionError,
     openai.APITimeoutError,
     openai.InternalServerError,
+    EmptyCompletionError,
 )
 
 
@@ -88,12 +93,13 @@ class LLMClient:
             top_p=genome.top_p,
             max_tokens=max_tokens,
         )
+        if not resp.choices or resp.choices[0].message.content is None:
+            raise EmptyCompletionError(f"empty response from {model}")
         usage = resp.usage
-        assert usage is not None
         return CompletionResult(
-            text=resp.choices[0].message.content or "",
+            text=resp.choices[0].message.content,
-            input_tokens=usage.prompt_tokens,
+            input_tokens=usage.prompt_tokens if usage else 0,
-            output_tokens=usage.completion_tokens,
+            output_tokens=usage.completion_tokens if usage else 0,
             tier=genome.model_tier,
             model=model,
         )