refactor: remove inference redundancy and fix cache leaks

- drop Executor unused tokenizer field, _head_dim, stale metrics docstring
- unify greedy sampling via SamplingPipeline.sample, drop top-level duplicate
- drop Task.flush_remaining no-op and unreachable prompt-length branch
- drop ProtocolHandler redundant chunks list (reuse body)
- fix page_size=1 token-slot leak on task_free
- clear _task_pages/_task_slots on alloc-failure paths
- reset _bind_state on task_free to avoid stale steady-state reuse
- remove unreachable contiguous branches in paged-only helpers

astrai/inference/api/protocol.py

@@ -181,12 +181,10 @@ class ProtocolHandler:
         self, agen: AsyncGenerator, ctx: GenContext, stop_sequences: List[str]
     ) -> Dict[str, Any]:
         checker = StopChecker(stop_sequences)
-        chunks: List[str] = []
         body = ""
         matched = None
 
         async for token in agen:
-            chunks.append(token)
             body += token
 
             matched = checker.check(body)
@@ -195,6 +193,5 @@ class ProtocolHandler:
 
             ctx.completion_tokens += 1
 
-        content = "".join(chunks)
         stop = StopInfo(matched=matched, body=body)
-        return self.builder.format_response(ctx, content, stop)
+        return self.builder.format_response(ctx, body, stop)