CI checks that can be automatically repaired

.github/workflows/ci.yml

@@ -20,16 +20,17 @@ jobs:
       - run: env | sort
       - run: make dev
       - env:
+          # Two environment variables here can cause sphinx to fail to build in ci.
+          # CHAT_MAX_TOKENS: ${{ secrets.CHAT_MAX_TOKENS }}
+          # CHAT_TEMPERATURE: ${{ secrets.CHAT_TEMPERATURE }}
           CHAT_AZURE_API_BASE: ${{ secrets.CHAT_AZURE_API_BASE }}
           CHAT_AZURE_API_VERSION: ${{ secrets.CHAT_AZURE_API_VERSION }}
-          CHAT_MAX_TOKENS: ${{ secrets.CHAT_MAX_TOKENS }}
           CHAT_MODEL: ${{ secrets.CHAT_MODEL }}
-          CHAT_TEMPERATURE: ${{ secrets.CHAT_TEMPERATURE }}
           EMBEDDING_AZURE_API_BASE: ${{ secrets.CHAT_AZURE_API_BASE }}
           EMBEDDING_AZURE_API_VERSION: ${{ secrets.CHAT_AZURE_API_VERSION }}
           EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
         name: lint test docs and build
-        run: make lint # test docs build sphinx
+        run: make lint docs-gen # test docs build
     strategy:
       matrix:
         python-version:

Makefile

@@ -81,10 +81,7 @@ constraints: deepclean
 
 # Check lint with black.
 black:
-	$(PIPRUN) python -m black --check . --extend-exclude test/scripts --extend-exclude git_ignore_folder -l 120
-
-sphinx:
-	$(PIPRUN) sphinx-build -W --keep-going -b html ./docs _build
+	$(PIPRUN) python -m black --check --diff . --extend-exclude test/scripts --extend-exclude git_ignore_folder -l 120
 
 # Check lint with isort.
 isort:
@@ -107,13 +104,33 @@ toml-sort:
 	$(PIPRUN) toml-sort --check pyproject.toml
 
 # Check lint with all linters.
-# lint: black isort mypy ruff toml-sort
-lint: mypy ruff
+# Prioritize fixing isort, then black, otherwise you'll get weird and unfixable black errors.
+# lint: mypy ruff
+lint: mypy ruff isort black toml-sort
 
 # Run pre-commit with autofix against all files.
 pre-commit:
 	pre-commit run --all-files
 
+########################################################################################
+# Auto Lint
+########################################################################################
+
+# Auto lint with black.
+auto-black:
+	$(PIPRUN) python -m black . --extend-exclude test/scripts --extend-exclude git_ignore_folder -l 120
+
+# Auto lint with isort.
+auto-isort:
+	$(PIPRUN) python -m isort . -s git_ignore_folder -s test/scripts
+
+# Auto lint with toml-sort.
+auto-toml-sort:
+	$(PIPRUN) toml-sort pyproject.toml
+
+# Auto lint with all linters.
+auto-lint: auto-isort auto-black auto-toml-sort
+
 ########################################################################################
 # Test
 ########################################################################################

docs/conf.py

@@ -16,7 +16,7 @@
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
 extensions = [
-    'sphinx.ext.autodoc',
+    "sphinx.ext.autodoc",
 ]
 
 autodoc_member_order = "bysource"

docs/development.rst

@@ -11,12 +11,18 @@ For Development
    make dev
    ```
 
-- Run linting and formatting.
+- Run linting and checking.
 
    ```bash
    make lint
    ```
 
+- Some linting issues can be fixed automatically. We have added a command in the Makefile for easy use.
+
+  ```bash
+  make auto-lint
+  ```
+
 
 Code Structure
 =========================

docs/index.rst

@@ -17,6 +17,7 @@ Welcome to RDAgent's documentation!
    development
    api_reference
    policy
+   test_dropdown/test1
 
 .. test_dropdown/test1
 

docs/installation.rst

@@ -27,13 +27,16 @@ USE_AZURE_TOKEN_PROVIDER
 
 ### ☁️ Azure Configuration
 - Install Azure CLI:
-  ```sh
-  curl -L https://aka.ms/InstallAzureCli | bash
-  ```
+
+   ```sh
+   curl -L https://aka.ms/InstallAzureCli | bash
+   ```
+
 - Log in to Azure:
-  ```sh
-  az login --use-device-code
-  ```
+
+   ```sh
+   az login --use-device-code
+   ```
 
 - `exit` and re-login to your environment (this step may not be necessary).
 

docs/scenarios_and_quickstart.rst

@@ -23,7 +23,7 @@ Scenario lists
      - 
 
 Scnarios' demo & quick start
-=========================
+============================
 
 Scen1
 -----
@@ -69,7 +69,7 @@ TODO: Show some examples:
 
 
 Scen2: 
------
+------
 📄 Research Report-Based Factor Extraction
 
 Scen2 Intro

pyproject.toml

@@ -4,7 +4,7 @@ requires = [
   "setuptools",
   "setuptools-scm",
 ]
-root= "rdagent"
+root = "rdagent"
 
 [project]
 authors = [
@@ -27,14 +27,13 @@ dynamic = [
 ]
 keywords = [
   "Autonomous Agents",
-  "Research and Development",
   "Large Language Models",
+  "Research and Development",
 ]
 name = "rdagent"
 readme = "README.md"
 requires-python = ">=3.8"
 
-
 [project.urls]
 homepage = "https://github.com/microsoft/RD-Agent/"
 issue = "https://github.com/microsoft/RD-Agent/issues"
@@ -52,13 +51,13 @@ color_output = true
 profile = "black"
 
 [tool.mypy]
-explicit_package_bases = true
 check_untyped_defs = true
 disallow_any_unimported = true
 disallow_untyped_defs = true
 enable_error_code = [
   "ignore-without-code",
 ]
+explicit_package_bases = true
 warn_return_any = true
 warn_unused_ignores = true
 

rdagent/app/data_mining/conf.py

@@ -1,6 +1,5 @@
 from pathlib import Path
 
-
 from rdagent.components.workflow.conf import BasePropSetting
 
 
@@ -19,11 +18,11 @@ class Config:
 
     evolving_n: int = 10
 
-    # 2) Extra config for the scenario 
+    # 2) Extra config for the scenario
     # physionet account
     # NOTE: You should apply the account in https://physionet.org/
-    username: str = ''
-    password: str = ''
+    username: str = ""
+    password: str = ""
 
 
 PROP_SETTING = PropSetting()

rdagent/app/data_mining/model.py

@@ -1,8 +1,10 @@
 import fire
+
 from rdagent.app.data_mining.conf import PROP_SETTING
 from rdagent.components.workflow.rd_loop import RDLoop
 from rdagent.core.exception import ModelEmptyError
 
+
 class ModelRDLoop(RDLoop):
     skip_loop_error = (ModelEmptyError,)
 

rdagent/app/qlib_rd_loop/RDAgent.py

@@ -1,4 +1,5 @@
 import pickle
+
 from rdagent.app.qlib_rd_loop.conf import PROP_SETTING
 from rdagent.core.developer import Developer
 from rdagent.core.exception import ModelEmptyError
@@ -12,6 +13,7 @@
 from rdagent.core.utils import import_class
 from rdagent.log import rdagent_logger as logger
 
+
 # TODO: we can design a workflow that can automatically save session and traceback in the future
 class Model_RD_Agent:
     def __init__(self):
@@ -20,50 +22,55 @@ def __init__(self):
         self.hypothesis2experiment: Hypothesis2Experiment = import_class(PROP_SETTING.model_hypothesis2experiment)()
         self.qlib_model_coder: Developer = import_class(PROP_SETTING.model_coder)(self.scen)
         self.qlib_model_runner: Developer = import_class(PROP_SETTING.model_runner)(self.scen)
-        self.qlib_model_summarizer: HypothesisExperiment2Feedback = import_class(PROP_SETTING.model_summarizer)(self.scen)
+        self.qlib_model_summarizer: HypothesisExperiment2Feedback = import_class(PROP_SETTING.model_summarizer)(
+            self.scen
+        )
         self.trace = Trace(scen=self.scen)
 
     def generate_hypothesis(self):
         hypothesis = self.hypothesis_gen.gen(self.trace)
-        self.dump_objects(hypothesis=hypothesis, trace=self.trace, filename='step_hypothesis.pkl')
+        self.dump_objects(hypothesis=hypothesis, trace=self.trace, filename="step_hypothesis.pkl")
         return hypothesis
 
     def convert_hypothesis(self, hypothesis):
         exp = self.hypothesis2experiment.convert(hypothesis, self.trace)
-        self.dump_objects(exp=exp, hypothesis=hypothesis, trace=self.trace, filename='step_experiment.pkl')
+        self.dump_objects(exp=exp, hypothesis=hypothesis, trace=self.trace, filename="step_experiment.pkl")
         return exp
 
     def generate_code(self, exp):
         exp = self.qlib_model_coder.develop(exp)
-        self.dump_objects(exp=exp, trace=self.trace, filename='step_code.pkl')
+        self.dump_objects(exp=exp, trace=self.trace, filename="step_code.pkl")
         return exp
 
     def run_experiment(self, exp):
         exp = self.qlib_model_runner.develop(exp)
-        self.dump_objects(exp=exp, trace=self.trace, filename='step_run.pkl')
+        self.dump_objects(exp=exp, trace=self.trace, filename="step_run.pkl")
         return exp
 
     def generate_feedback(self, exp, hypothesis):
         feedback = self.qlib_model_summarizer.generate_feedback(exp, hypothesis, self.trace)
-        self.dump_objects(exp=exp, hypothesis=hypothesis, feedback=feedback, trace=self.trace, filename='step_feedback.pkl')
+        self.dump_objects(
+            exp=exp, hypothesis=hypothesis, feedback=feedback, trace=self.trace, filename="step_feedback.pkl"
+        )
         return feedback
 
     def append_to_trace(self, hypothesis, exp, feedback):
         self.trace.hist.append((hypothesis, exp, feedback))
-        self.dump_objects(trace=self.trace, filename='step_trace.pkl')
+        self.dump_objects(trace=self.trace, filename="step_trace.pkl")
 
-    def dump_objects(self, exp=None, hypothesis=None, feedback=None, trace=None, filename='dumped_objects.pkl'):
-        with open(filename, 'wb') as f:
+    def dump_objects(self, exp=None, hypothesis=None, feedback=None, trace=None, filename="dumped_objects.pkl"):
+        with open(filename, "wb") as f:
             pickle.dump((exp, hypothesis, feedback, trace or self.trace), f)
 
     def load_objects(self, filename):
-        with open(filename, 'rb') as f:
+        with open(filename, "rb") as f:
             return pickle.load(f)
 
+
 def process_steps(agent):
     # Load trace if available
     try:
-        _, _, _, trace = agent.load_objects('step_trace.pkl')
+        _, _, _, trace = agent.load_objects("step_trace.pkl")
         agent.trace = trace
         print(trace.get_sota_hypothesis_and_experiment())
     except FileNotFoundError:
@@ -99,6 +106,7 @@ def process_steps(agent):
     # # Step 6: Append to trace
     # agent.append_to_trace(hypothesis, exp, feedback)
 
+
 if __name__ == "__main__":
     agent = Model_RD_Agent()
     process_steps(agent)