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/core/interactor.py

@@ -0,0 +1,26 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from trace import Trace
+from typing import TYPE_CHECKING, Generic
+
+from rdagent.core.experiment import ASpecificExp
+
+if TYPE_CHECKING:
+    from rdagent.core.scenario import Scenario
+
+
+class Interactor(ABC, Generic[ASpecificExp]):
+    def __init__(self, scen: Scenario) -> None:
+        self.scen: Scenario = scen
+
+    @abstractmethod
+    def interact(self, exp: ASpecificExp, trace: Trace | None = None) -> ASpecificExp:
+        """
+        Interact with the experiment to get feedback or confirmation.
+
+        Responsibilities:
+        - Present the current state of the experiment.
+        - Collect input to guide the next steps in the experiment.
+        - Rewrite the experiment based on feedback.
+        """