fix coder bug (#868)

Co-authored-by: Xu <v-xuminrui@microsoft.com>

rdagent/components/coder/data_science/pipeline/prompts.yaml

@@ -115,9 +115,9 @@ pipeline_eval:
     {% if is_sub_enabled %}
     ## Evaluation Scope
     Your focus is to check whether the workflow code:
-    Step 1: Executes successfully, correctly generating a final submission.
+    Step 1: Executes successfully without any errors. Please distinguish between the errors and warnings.
 
-    Step 2: Generates predictions in the correct format, ensuring: they align with the submission structure, the index and column names should match the sample, and the content should not be empty or apparently incorrect.
+    Step 2: Correctly generates a final submission in the correct format, ensuring: they align with the submission structure, the index names and column names should match the sample, and the items should not be empty or apparently incorrect.
     
     Step 3: Aligns with the competition requirements. This includes:
     - CAREFULLY ANALYZE WHETHER THE EXPERIMENTAL SETUP AND CODE MAY CAUSE MISALIGNMENT BETWEEN VALIDATION AND TEST PERFORMANCE.

rdagent/scenarios/data_science/share.yaml

@@ -258,8 +258,9 @@ component_spec:
       {% endraw %}
     
   Pipeline: |-
-    0. Program Running:
-      - The program will be runned using python main.py **without any parameters**. Ensure no optional parameters are used in main.py.
+    0. Program Execution:
+      - The workflow will be executed by running `python main.py` with no command-line arguments. Ensure that `main.py` does not require or expect any parameters.
+      - The working directory will only contain `main.py`. Any additional files required for execution must be downloaded or generated by `main.py` itself.
       
     1. File Handling:
       - Handle file encoding and delimiters appropriately.