feat: add user interaction in data science scenario (#1251)

* feat: add interactor classes and user interaction handling for experiments

* update code

* use fragment retry mechanism instead of rerun()

* fix a bug

* integrate user instructions into proposal and coder

* fix CI

* fix CI

* feat: add approval option for user instructions submission

* feat: enhance user instructions handling in Task and DSExperiment classes

* fix CI

* add user instructions into hypothesis rewrite

* add interface to command line

---------

Co-authored-by: Bowen Xian <xianbowen@outlook.com>

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

@@ -169,7 +169,8 @@ pipeline_coder:
     8. **Try-except blocks are ONLY allowed when reading files. If no files are successfully read, it indicates incorrect file paths or reading methods, not a try-except issue. Try-except is PROHIBITED elsewhere in the code. Assert statements are PROHIBITED throughout the entire code.**
     9. ATTENTION: ALWAYS use the best saved model (not necessarily final epoch) for predictions. **NEVER create dummy/placeholder submissions (e.g., all 1s, random values)**. If training fails, report failure honestly rather than generating fake submission files.
     10. You should ALWAYS generate the complete code rather than partial code.
-    11. Strictly follow all specifications and general guidelines described above.
+    11. If the task contains any user instructions, you must strictly follow them. User instructions have the highest priority and should be followed even if they conflict with other specifications or guidelines.
+    12. Strictly follow all specifications and general guidelines described above.
 
     ### Output Format
     {% if out_spec %}

rdagent/components/interactor/__init__.py

@@ -0,0 +1,17 @@
+from rdagent.core.experiment import ASpecificExp
+from rdagent.core.interactor import Interactor
+from rdagent.core.proposal import Trace
+
+
+class SkipInteractor(Interactor[ASpecificExp]):
+
+    def interact(self, exp: ASpecificExp, trace: Trace) -> ASpecificExp:
+        """
+        Interact with the user to get feedback or confirmation.
+
+        Responsibilities:
+        - Present the current state of the experiment to the user.
+        - Collect user input to guide the next steps in the experiment.
+        - Rewrite the experiment based on user feedback.
+        """
+        return exp

rdagent/components/workflow/conf.py

@@ -11,6 +11,7 @@ class BasePropSetting(ExtendedBaseSettings):
     knowledge_base: str = ""
     knowledge_base_path: str = ""
     hypothesis_gen: str = ""
+    interactor: str = ""
     hypothesis2experiment: str = ""
     coder: str = ""
     runner: str = ""