fix: address PR review feedback

- Remove quotes from asyncio.Task return type in Evaluator.evaluate()
- Update ModelResponse.evaluations type to asyncio.Task[List[JudgeResult]]
- Forward default_ai_provider to __evaluate_agent in create_agent

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: jsonbailey

packages/sdk/server-ai/src/ldai/client.py

@@ -459,7 +459,7 @@ async def create_agent(
         """
         self._client.track(_TRACK_USAGE_CREATE_AGENT, context, key, 1)
         log.debug(f"Creating managed agent for key: {key}")
-        config = self.__evaluate_agent(key, context, default or _DISABLED_AGENT_DEFAULT, variables)
+        config = self.__evaluate_agent(key, context, default or _DISABLED_AGENT_DEFAULT, variables, default_ai_provider=default_ai_provider)
 
         if not config.enabled:
             return None

packages/sdk/server-ai/src/ldai/evaluator.py

@@ -36,7 +36,7 @@ def evaluate(
         self,
         input_text: str,
         output_text: str,
-    ) -> 'asyncio.Task[List[JudgeResult]]':
+    ) -> asyncio.Task[List[JudgeResult]]:
         """
         Run all configured judges against the given input/output pair.
 

packages/sdk/server-ai/src/ldai/managed_model.py

@@ -3,7 +3,7 @@
 
 from ldai.models import AICompletionConfig, LDMessage
 from ldai.providers.model_runner import ModelRunner
-from ldai.providers.types import ModelResponse
+from ldai.providers.types import JudgeResult, ModelResponse
 from ldai.tracker import LDAIConfigTracker
 
 
@@ -58,7 +58,7 @@ async def invoke(self, prompt: str) -> ModelResponse:
         self._messages.append(response.message)
         return response
 
-    def _track_judge_results(self, tracker: LDAIConfigTracker, eval_task: 'asyncio.Task') -> None:
+    def _track_judge_results(self, tracker: LDAIConfigTracker, eval_task: asyncio.Task[List[JudgeResult]]) -> None:
         async def _run() -> None:
             results = await eval_task
             for r in results:

packages/sdk/server-ai/src/ldai/providers/types.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import asyncio
 from dataclasses import dataclass
 from typing import Any, Callable, Dict, List, Optional
 
@@ -44,7 +45,7 @@ class ModelResponse:
     """
     message: LDMessage
     metrics: LDAIMetrics
-    evaluations: Optional[List[JudgeResult]] = None
+    evaluations: Optional[asyncio.Task[List[JudgeResult]]] = None
 
 
 @dataclass