chore: add a rdagent server with UI

.gitignore

@@ -175,3 +175,7 @@ mlruns/
 /*.sh
 .aider*
 rdagent/app/benchmark/factor/example.json
+
+# UI Server resources
+videos/
+static/

Makefile

@@ -92,7 +92,7 @@ isort:
 # First deal with the core folder, and then gradually increase the scope of detection,
 # and eventually realize the detection of the complete project.
 mypy:
-	$(PIPRUN) python -m mypy rdagent/core   #  --exclude rdagent/scripts,git_ignore_folder
+	$(PIPRUN) python -m mypy rdagent/core
 
 # Check lint with ruff.
 # First deal with the core folder, and then gradually increase the scope of detection,

rdagent/app/cli.py

@@ -45,6 +45,13 @@ def ui(port=19899, log_dir="", debug=False):
         subprocess.run(cmds)
 
 
+def server_ui(port=19899):
+    """
+    start web app to show the log traces in real time
+    """
+    subprocess.run(["python", "rdagent/log/server/app.py", f"--port={port}"])
+
+
 def app():
     fire.Fire(
         {
@@ -58,5 +65,6 @@ def app():
             "health_check": health_check,
             "collect_info": collect_info,
             "kaggle": kaggle,
+            "server_ui": server_ui,
         }
     )

rdagent/app/data_mining/model.py

@@ -9,7 +9,7 @@ class ModelRDLoop(RDLoop):
     skip_loop_error = (ModelEmptyError,)
 
 
-def main(path=None, step_n=None):
+def main(path=None, step_n=None, loop_n=None, all_duration=None, checkout=True):
     """
     Auto R&D Evolving loop for models in a medical scenario.
 
@@ -23,8 +23,8 @@ def main(path=None, step_n=None):
     if path is None:
         model_loop = ModelRDLoop(MED_PROP_SETTING)
     else:
-        model_loop = ModelRDLoop.load(path)
-    model_loop.run(step_n=step_n)
+        model_loop = ModelRDLoop.load(path, checkout=checkout)
+    model_loop.run(step_n=step_n, loop_n=loop_n, all_duration=all_duration)
 
 
 if __name__ == "__main__":

rdagent/app/data_science/loop.py

@@ -1,3 +1,5 @@
+from pathlib import Path
+
 import fire
 
 from rdagent.app.data_science.conf import DS_RD_SETTING
@@ -7,12 +9,11 @@
 
 
 def main(
-    path=None,
-    output_path=None,
-    step_n=None,
-    loop_n=None,
+    path: str | None = None,
+    checkout: bool | str | Path = True,
+    step_n: int | None = None,
+    loop_n: int | None = None,
     competition="bms-molecular-translation",
-    do_truncate=True,
     timeout=None,
     replace_timer=True,
     exp_gen_cls: str | None = None,
@@ -22,29 +23,33 @@ def main(
     Parameters
     ----------
     path :
-        path like `$LOG_PATH/__session__/1/0_propose`. It indicates that we restore the state that after finish the step 0 in loop 1
-    output_path :
-        path like `$LOG_PATH`. It indicates that where we want to save our session and log information.
+        A path like `$LOG_PATH/__session__/1/0_propose`. This indicates that we restore the state after finishing step 0 in loop 1.
+    checkout :
+        Used only when a path is provided.
+        Can be True, False, or a path.
+        Default is True.
+        - If True, the new loop will use the existing folder and clear logs for sessions after the one corresponding to the given path.
+        - If False, the new loop will use the existing folder but keep the logs for sessions after the one corresponding to the given path.
+        - If a path (or a str like Path) is provided, the new loop will be saved to that path, leaving the original path unchanged.
     step_n :
-        How many steps to run; if None, it will run forever until error or KeyboardInterrupt
+        Number of steps to run; if None, the process will run indefinitely until an error or KeyboardInterrupt occurs.
     loop_n :
-        How many loops to run; if None, it will run forever until error or KeyboardInterrupt
-        - if current loop is incomplete, it will be counted as the first loop for completion.
-        - if both step_n and loop_n are provided, the process will stop as soon as either condition is met.
+        Number of loops to run; if None, the process will run indefinitely until an error or KeyboardInterrupt occurs.
+        - If the current loop is incomplete, it will be counted as the first loop for completion.
+        - If both step_n and loop_n are provided, the process will stop as soon as either condition is met.
     competition :
-    do_truncate :
-        If set to True, the logger will truncate the future log messages by calling `logger.storage.truncate`.
+        Competition name.
     replace_timer :
-        If session is loaded, should we replace the timer with session.timer
+        If a session is loaded, determines whether to replace the timer with session.timer.
     exp_gen_cls :
-        When we have different stages, we can replace the exp_gen with the new proposal
+        When there are different stages, the exp_gen can be replaced with the new proposal.
 
 
     Auto R&D Evolving loop for models in a Kaggle scenario.
-    You can continue running session by
+    You can continue running a session by using the command:
     .. code-block:: bash
-        dotenv run -- python rdagent/app/data_science/loop.py [--competition titanic] $LOG_PATH/__session__/1/0_propose  --step_n 1   # `step_n` is a optional parameter
-        rdagent kaggle --competition playground-series-s4e8  # You are encouraged to use this one.
+        dotenv run -- python rdagent/app/data_science/loop.py [--competition titanic] $LOG_PATH/__session__/1/0_propose  --step_n 1   # `step_n` is an optional parameter
+        rdagent kaggle --competition playground-series-s4e8  # This command is recommended.
     """
     if competition is not None:
         DS_RD_SETTING.competition = competition
@@ -55,7 +60,7 @@ def main(
     if path is None:
         kaggle_loop = DataScienceRDLoop(DS_RD_SETTING)
     else:
-        kaggle_loop = DataScienceRDLoop.load(path, output_path, do_truncate, replace_timer)
+        kaggle_loop: DataScienceRDLoop = DataScienceRDLoop.load(path, checkout=checkout, replace_timer=replace_timer)
 
     # replace exp_gen if we have new class
     if exp_gen_cls is not None:

rdagent/app/qlib_rd_loop/factor.py

@@ -25,7 +25,7 @@ def running(self, prev_out: dict[str, Any]):
         return exp
 
 
-def main(path=None, step_n=None):
+def main(path=None, step_n=None, loop_n=None, all_duration=None, checkout=True):
     """
     Auto R&D Evolving loop for fintech factors.
 
@@ -39,8 +39,8 @@ def main(path=None, step_n=None):
     if path is None:
         model_loop = FactorRDLoop(FACTOR_PROP_SETTING)
     else:
-        model_loop = FactorRDLoop.load(path)
-    model_loop.run(step_n=step_n)
+        model_loop = FactorRDLoop.load(path, checkout=checkout)
+    model_loop.run(step_n=step_n, loop_n=loop_n, all_duration=all_duration)
 
 
 if __name__ == "__main__":

rdagent/app/qlib_rd_loop/factor_from_report.py

@@ -146,7 +146,7 @@ def coding(self, prev_out: dict[str, Any]):
         return exp
 
 
-def main(report_folder=None, path=None, step_n=None):
+def main(report_folder=None, path=None, step_n=None, loop_n=None, all_duration=None, checkout=True):
     """
     Auto R&D Evolving loop for fintech factors (the factors are extracted from finance reports).
 
@@ -158,11 +158,11 @@ def main(report_folder=None, path=None, step_n=None):
     if path is None and report_folder is None:
         model_loop = FactorReportLoop()
     elif path is not None:
-        model_loop = FactorReportLoop.load(path)
+        model_loop = FactorReportLoop.load(path, checkout=checkout)
     else:
         model_loop = FactorReportLoop(report_folder=report_folder)
 
-    model_loop.run(step_n=step_n)
+    model_loop.run(step_n=step_n, loop_n=loop_n, all_duration=all_duration)
 
 
 if __name__ == "__main__":

rdagent/app/qlib_rd_loop/model.py

@@ -13,7 +13,7 @@ class ModelRDLoop(RDLoop):
     skip_loop_error = (ModelEmptyError,)
 
 
-def main(path=None, step_n=None):
+def main(path=None, step_n=None, loop_n=None, all_duration=None, checkout=True):
     """
     Auto R&D Evolving loop for fintech models
 
@@ -27,8 +27,8 @@ def main(path=None, step_n=None):
     if path is None:
         model_loop = ModelRDLoop(MODEL_PROP_SETTING)
     else:
-        model_loop = ModelRDLoop.load(path)
-    model_loop.run(step_n=step_n)
+        model_loop = ModelRDLoop.load(path, checkout=checkout)
+    model_loop.run(step_n=step_n, loop_n=loop_n, all_duration=all_duration)
 
 
 if __name__ == "__main__":

rdagent/app/qlib_rd_loop/quant.py

@@ -119,7 +119,7 @@ def feedback(self, prev_out: dict[str, Any]):
             self.trace.hist.append((prev_out["running"], feedback))
 
 
-def main(path=None, step_n=None):
+def main(path=None, step_n=None, loop_n=None, all_duration=None, checkout=True):
     """
     Auto R&D Evolving loop for fintech factors.
     You can continue running session by
@@ -129,8 +129,8 @@ def main(path=None, step_n=None):
     if path is None:
         quant_loop = QuantRDLoop(QUANT_PROP_SETTING)
     else:
-        quant_loop = QuantRDLoop.load(path)
-    quant_loop.run(step_n=step_n)
+        quant_loop = QuantRDLoop.load(path, checkout=checkout)
+    quant_loop.run(step_n=step_n, loop_n=loop_n, all_duration=all_duration)
 
 
 if __name__ == "__main__":

rdagent/app/utils/ape.py

@@ -5,7 +5,7 @@
 import pickle
 from pathlib import Path
 
-from rdagent.core.conf import RD_AGENT_SETTINGS
+from rdagent.log.conf import LOG_SETTINGS
 
 
 def get_llm_qa(file_path):
@@ -21,7 +21,7 @@ def get_llm_qa(file_path):
 
 # Example usage
 # use
-file_path = Path(RD_AGENT_SETTINGS.log_trace_path) / "debug_llm.pkl"
+file_path = Path(LOG_SETTINGS.trace_path) / "debug_llm.pkl"
 llm_qa = get_llm_qa(file_path)
 print(len(llm_qa))
 

rdagent/core/conf.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-# TODO: use pydantic for other modules in Qlib
 from pathlib import Path
 from typing import cast
 
@@ -45,11 +44,6 @@ def base_iter(settings_cls: type[ExtendedBaseSettings]) -> list[type[ExtendedBas
 
 
 class RDAgentSettings(ExtendedBaseSettings):
-    # TODO: (xiao) I think LLMSetting may be a better name.
-    # TODO: (xiao) I think most of the config should be in oai.config
-    # Log configs
-    # TODO: (xiao) think it can be a separate config.
-    log_trace_path: str | None = None
 
     # azure document intelligence configs
     azure_document_intelligence_key: str = ""

rdagent/log/base.py

@@ -5,7 +5,7 @@
 from dataclasses import dataclass
 from datetime import datetime
 from pathlib import Path
-from typing import Literal, Optional, Union
+from typing import Literal, Optional
 
 
 @dataclass
@@ -43,10 +43,8 @@ class Storage:
     def log(
         self,
         obj: object,
-        name: str = "",
-        save_type: Literal["json", "text", "pkl"] = "text",
+        tag: str = "",
         timestamp: datetime | None = None,
-        **kwargs: dict,
     ) -> str | Path:
         """
 
@@ -72,6 +70,16 @@ def iter_msg(self) -> Generator[Message, None, None]:
         """
         ...
 
+    @abstractmethod
+    def truncate(self, time: datetime) -> None:
+        """
+        Remove all log entries after the specified time.
+        """
+        ...
+
+    def __str__(self) -> str:
+        return self.__class__.__name__
+
 
 class View:
     """

rdagent/log/conf.py

@@ -0,0 +1,24 @@
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+from pydantic_settings import SettingsConfigDict
+
+from rdagent.core.conf import ExtendedBaseSettings
+
+
+class LogSettings(ExtendedBaseSettings):
+    model_config = SettingsConfigDict(env_prefix="LOG_", protected_namespaces=())
+
+    trace_path: str = str(Path.cwd() / "log" / datetime.now(timezone.utc).strftime("%Y-%m-%d_%H-%M-%S-%f"))
+
+    ui_server_port: int | None = None
+
+    storages: dict[str, list[int | str]] = {}
+
+    def model_post_init(self, _context: Any, /) -> None:
+        if self.ui_server_port is not None:
+            self.storages["rdagent.log.ui.storage.WebStorage"] = [self.ui_server_port, self.trace_path]
+
+
+LOG_SETTINGS = LogSettings()