fix: Update Penguin tests to use renamed resource server (#1540)

Signed-off-by: Shashank Verma <[email protected]>

Author: shashank3959

tests/unit/environments/penguin_test_data/test_penguin_sanity.json

@@ -80,18 +80,18 @@ def penguin_vllm_generation(cluster, penguin_tokenizer):  # noqa: F811
 def penguin(penguin_vllm_generation):
     """Create a Penguin actor for testing."""
 
-    yaml_str = r"""multineedle_resources_server:
+    yaml_str = r"""example_multi_step_resources_server:
   resources_servers:
-    multineedle:
+    example_multi_step:
       entrypoint: app.py
       domain: instruction_following
-multineedle_simple_agent:
+example_multi_step_simple_agent:
   responses_api_agents:
     simple_agent:
       entrypoint: app.py
       resources_server:
         type: resources_servers
-        name: multineedle_resources_server
+        name: example_multi_step_resources_server
       model_server:
         type: responses_api_models
         name: openai_model

tests/unit/environments/test_penguin.py

@@ -818,37 +818,37 @@ def test_run_async_penguin_rollout(
             "natural_termination_rate": None,
             "truncation_rate": None,
             # per agent metrics
-            "multineedle_simple_agent/full_result": None,
-            "multineedle_simple_agent/accuracy/histogram": None,
-            "multineedle_simple_agent/accuracy/max": 0.0,
-            "multineedle_simple_agent/accuracy/mean": 0.0,
-            "multineedle_simple_agent/accuracy/median": 0.0,
-            "multineedle_simple_agent/accuracy/min": 0.0,
-            "multineedle_simple_agent/accuracy/stddev": 0.0,
-            "multineedle_simple_agent/order_instruction_following_failure/histogram": None,
-            "multineedle_simple_agent/order_instruction_following_failure/max": 0.0,
-            "multineedle_simple_agent/order_instruction_following_failure/mean": 0.0,
-            "multineedle_simple_agent/order_instruction_following_failure/median": 0.0,
-            "multineedle_simple_agent/order_instruction_following_failure/min": 0.0,
-            "multineedle_simple_agent/order_instruction_following_failure/stddev": 0.0,
-            "multineedle_simple_agent/original_term_minefield_hit/histogram": None,
-            "multineedle_simple_agent/original_term_minefield_hit/max": 0.0,
-            "multineedle_simple_agent/original_term_minefield_hit/mean": 0.0,
-            "multineedle_simple_agent/original_term_minefield_hit/median": 0.0,
-            "multineedle_simple_agent/original_term_minefield_hit/min": 0.0,
-            "multineedle_simple_agent/original_term_minefield_hit/stddev": 0.0,
-            "multineedle_simple_agent/reward/histogram": None,
-            "multineedle_simple_agent/reward/max": 0.0,
-            "multineedle_simple_agent/reward/mean": 0.0,
-            "multineedle_simple_agent/reward/median": 0.0,
-            "multineedle_simple_agent/reward/min": 0.0,
-            "multineedle_simple_agent/reward/stddev": 0.0,
-            "multineedle_simple_agent/set_overlap/histogram": None,
-            "multineedle_simple_agent/set_overlap/max": 0.0,
-            "multineedle_simple_agent/set_overlap/mean": 0.0,
-            "multineedle_simple_agent/set_overlap/median": 0.0,
-            "multineedle_simple_agent/set_overlap/min": 0.0,
-            "multineedle_simple_agent/set_overlap/stddev": 0.0,
+            "example_multi_step_simple_agent/full_result": None,
+            "example_multi_step_simple_agent/accuracy/histogram": None,
+            "example_multi_step_simple_agent/accuracy/max": 0.0,
+            "example_multi_step_simple_agent/accuracy/mean": 0.0,
+            "example_multi_step_simple_agent/accuracy/median": 0.0,
+            "example_multi_step_simple_agent/accuracy/min": 0.0,
+            "example_multi_step_simple_agent/accuracy/stddev": 0.0,
+            "example_multi_step_simple_agent/order_instruction_following_failure/histogram": None,
+            "example_multi_step_simple_agent/order_instruction_following_failure/max": 0.0,
+            "example_multi_step_simple_agent/order_instruction_following_failure/mean": 0.0,
+            "example_multi_step_simple_agent/order_instruction_following_failure/median": 0.0,
+            "example_multi_step_simple_agent/order_instruction_following_failure/min": 0.0,
+            "example_multi_step_simple_agent/order_instruction_following_failure/stddev": 0.0,
+            "example_multi_step_simple_agent/original_term_minefield_hit/histogram": None,
+            "example_multi_step_simple_agent/original_term_minefield_hit/max": 0.0,
+            "example_multi_step_simple_agent/original_term_minefield_hit/mean": 0.0,
+            "example_multi_step_simple_agent/original_term_minefield_hit/median": 0.0,
+            "example_multi_step_simple_agent/original_term_minefield_hit/min": 0.0,
+            "example_multi_step_simple_agent/original_term_minefield_hit/stddev": 0.0,
+            "example_multi_step_simple_agent/reward/histogram": None,
+            "example_multi_step_simple_agent/reward/max": 0.0,
+            "example_multi_step_simple_agent/reward/mean": 0.0,
+            "example_multi_step_simple_agent/reward/median": 0.0,
+            "example_multi_step_simple_agent/reward/min": 0.0,
+            "example_multi_step_simple_agent/reward/stddev": 0.0,
+            "example_multi_step_simple_agent/set_overlap/histogram": None,
+            "example_multi_step_simple_agent/set_overlap/max": 0.0,
+            "example_multi_step_simple_agent/set_overlap/mean": 0.0,
+            "example_multi_step_simple_agent/set_overlap/median": 0.0,
+            "example_multi_step_simple_agent/set_overlap/min": 0.0,
+            "example_multi_step_simple_agent/set_overlap/stddev": 0.0,
         },
     }