perf(run_agent): accumulate length-continuation prefix via list+join

Replace O(n²) string concatenation of truncated_response_prefix in the
length-continuation retry loop with a list + ''.join(). Functionally
equivalent: same partial response on early return, same prepend on
final assembly. The legacy retry path is capped at 3 iterations, so
the practical wall-clock win is small, but the new idiom matches the
rest of the codebase and removes a needless repeated allocation.

Salvaged from PR #2717 (the run_conversation portion only — trajectory
refactor dropped because it silently rewrote </tool_response> to </think>).

Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>

tests/run_agent/test_anthropic_truncation_continuation.py

@@ -59,7 +59,7 @@ class TestTruncatedAnthropicResponseNormalization:
         nr = get_transport("anthropic_messages").normalize_response(response)
 
         # The continuation block checks these two attributes:
-        #   assistant_message.content  → appended to truncated_response_prefix
+        #   assistant_message.content  → appended to truncated_response_parts
         #   assistant_message.tool_calls → guards the text-retry branch
         assert nr.content is not None
         assert "partial response" in nr.content