Enhance Python CI: Add comprehensive formatting and import sorting checks

- Added ruff format checking to python-test.yml workflow
- Created new python-format.yml workflow for dedicated formatting checks
- Added pyproject.toml with comprehensive ruff configuration
- Configured import sorting (isort replacement) and formatting (black replacement)
- Auto-formatted all Python code with ruff format
- Fixed exception chaining issues (B904) in parser files
- Enhanced CI now covers: linting, formatting, import sorting, and type checking

This replaces the need for separate black and isort tools by using ruff's
built-in capabilities, providing faster and more consistent code quality checks.

Author: vinod0m

.github/workflows/python-format.yml

@@ -0,0 +1,44 @@
+# Python Code Formatting
+# This workflow checks and can auto-fix Python code formatting
+name: Python Code Formatting
+permissions:
+  contents: write
+  pull-requests: write
+
+on:
+  push:
+    paths:
+      - '**.py'
+  pull_request:
+    paths:
+      - '**.py'
+  workflow_dispatch:
+
+jobs:
+  format-check:
+    name: Check Python formatting
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Setup Python Environment
+        uses: ./.github/actions/setup-python-env
+        with:
+          python-version: '3.11'
+          install-dev-reqs: 'true'
+      
+      - name: Check import sorting with ruff
+        run: |
+          python -m ruff check src/ --select I --diff
+          echo "Import sorting check completed"
+      
+      - name: Check code formatting with ruff
+        run: |
+          python -m ruff format --check --diff src/
+          echo "Code formatting check completed"
+      
+      - name: Run ruff --fix (dry-run) to show potential fixes
+        continue-on-error: true
+        run: |
+          echo "Preview of potential fixes:"
+          python -m ruff check src/ --fix --diff || true

.github/workflows/python-test.yml

@@ -29,6 +29,9 @@ jobs:
       - name: Run ruff (lint)
         run: |
           python -m ruff check src/
+      - name: Run ruff (format check)
+        run: |
+          python -m ruff format --check src/
       - name: Run unit tests with coverage
         run: |
           PYTHONPATH=. pytest --cov=src/ --cov-report=xml

pyproject.toml

@@ -0,0 +1,47 @@
+# Ruff configuration for unstructuredDataHandler
+[tool.ruff]
+target-version = "py310"
+line-length = 88
+exclude = [
+    ".git",
+    ".mypy_cache",
+    ".pytest_cache",
+    ".ruff_cache",
+    ".venv",
+    ".venv_ci",
+    "__pycache__",
+    "build",
+    "dist",
+]
+
+[tool.ruff.lint]
+# Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.
+select = [
+    "E",  # pycodestyle errors
+    "W",  # pycodestyle warnings
+    "F",  # Pyflakes
+    "I",  # isort
+    "B",  # flake8-bugbear
+    "C4", # flake8-comprehensions
+    "UP", # pyupgrade
+]
+ignore = [
+    "E501", # line too long, handled by black
+    "B008", # do not perform function calls in argument defaults
+    "C901", # too complex
+]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401"]  # Allow unused imports in __init__.py
+"test/**/*.py" = ["B018"] # Allow useless expressions in tests
+
+[tool.ruff.lint.isort]
+known-first-party = ["src"]
+force-single-line = true
+force-sort-within-sections = true
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "auto"

src/agents/deepagent.py

@@ -3,14 +3,16 @@
 import argparse
 import os
 import re
-import yaml
-from typing import Any, Optional, List
+from typing import Any
 
-from langchain.agents import AgentExecutor, create_tool_calling_agent
-from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain.agents import AgentExecutor
+from langchain.agents import create_tool_calling_agent
+from langchain.prompts import ChatPromptTemplate
+from langchain.prompts import MessagesPlaceholder
 from langchain.tools import BaseTool
 from langchain_community.chat_message_histories import ChatMessageHistory
 from langchain_core.runnables.history import RunnableWithMessageHistory
+import yaml
 
 # LLM names declared as Any so mypy accepts fallback to None if imports fail
 GoogleGenerativeAI: Any
@@ -24,12 +26,14 @@
 
 try:
     from langchain_openai import ChatOpenAI  # type: ignore
+
     OpenAI = ChatOpenAI
 except Exception:
     OpenAI = None
 
 try:
     from langchain_ollama import ChatOllama  # type: ignore
+
     Ollama = ChatOllama
 except Exception:
     Ollama = None
@@ -53,12 +57,13 @@ class FlexibleAgent:
     Flexible agent supporting multiple LLM providers (Gemini, OpenAI,
     Ollama, etc.) for unstructuredDataHandler.
     """
+
     def __init__(
         self,
-        provider: Optional[str] = None,
-        api_key: Optional[str] = None,
-        model: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
+        provider: str | None = None,
+        api_key: str | None = None,
+        model: str | None = None,
+        tools: list[Any] | None = None,
         dry_run: bool = False,
         config_path: str = "config/model_config.yaml",
         **kwargs,
@@ -72,15 +77,14 @@ def __init__(
         config_path: Path to the model configuration file.
         kwargs: Additional LLM-specific arguments
         """
-        with open(config_path, 'r', encoding='utf-8') as f:
+        with open(config_path, encoding="utf-8") as f:
             config = yaml.safe_load(f)
 
         # Normalize provider and validate
-        provider = (provider or config.get('default_provider') or "").lower()
+        provider = (provider or config.get("default_provider") or "").lower()
         if not provider:
             raise ValueError(
-                "Provider not specified and no default_provider found in "
-                "config."
+                "Provider not specified and no default_provider found in " "config."
             )
 
         self.dry_run = bool(dry_run)
@@ -94,28 +98,24 @@ def __init__(
             return
 
         # Configure agent from YAML
-        agent_config = config.get('agent', {})
-        verbose = agent_config.get('verbose', True)
+        agent_config = config.get("agent", {})
+        verbose = agent_config.get("verbose", True)
 
         # Configure provider
-        provider_config = config.get('providers', {}).get(provider, {})
-        model = model or provider_config.get('default_model')
+        provider_config = config.get("providers", {}).get(provider, {})
+        model = model or provider_config.get("default_model")
 
         try:
-            if provider == 'gemini':
+            if provider == "gemini":
                 self.llm = GoogleGenerativeAI(
                     google_api_key=api_key, model=model, **kwargs
                 )
-            elif provider == 'openai':
-                self.llm = OpenAI(
-                    openai_api_key=api_key, model=model, **kwargs
-                )
+            elif provider == "openai":
+                self.llm = OpenAI(openai_api_key=api_key, model=model, **kwargs)
             elif provider == "ollama" and Ollama is not None:
                 self.llm = Ollama(model=model, **kwargs)
             else:
-                raise ValueError(
-                    f"Unsupported or unavailable provider: {provider}"
-                )
+                raise ValueError(f"Unsupported or unavailable provider: {provider}")
         except Exception as e:
             raise RuntimeError(
                 f"Failed to initialize LLM provider '{provider}': {e}"
@@ -133,9 +133,7 @@ def __init__(
         )
 
         agent = create_tool_calling_agent(self.llm, self.tools, prompt)
-        agent_executor = AgentExecutor(
-            agent=agent, tools=self.tools, verbose=verbose
-        )
+        agent_executor = AgentExecutor(agent=agent, tools=self.tools, verbose=verbose)
 
         def get_session_history(session_id: str) -> ChatMessageHistory:
             if session_id not in self.store:
@@ -154,15 +152,15 @@ def run(self, input_data: str, session_id: str = "default"):
         Run the agent on the provided input data (prompt).
         """
         result = self.agent.invoke(
-            {"input": input_data},
-            config={"configurable": {"session_id": session_id}}
+            {"input": input_data}, config={"configurable": {"session_id": session_id}}
         )
         return result["output"]
 
 
 class MockAgent:
     """A mock agent for dry-run and CI that can echo or use tools."""
-    def __init__(self, tools: Optional[List[BaseTool]] = None):
+
+    def __init__(self, tools: list[BaseTool] | None = None):
         self.last_input = None
         self.tools = tools or []
 
@@ -188,21 +186,21 @@ def main():
     try:
         from dotenv import load_dotenv  # type: ignore
     except Exception:  # pragma: no cover - fallback if dotenv is unavailable
+
         def load_dotenv(*_args, **_kwargs):  # type: ignore
             return False
+
     parser = argparse.ArgumentParser()
     parser.add_argument(
         "--dry-run", action="store_true", help="Run agent in dry-run mode"
     )
     parser.add_argument("--provider", help="LLM provider to use")
     parser.add_argument("--model", help="Model name to use")
     parser.add_argument(
-        "--prompt", default="What is the capital of France?",
-        help="The prompt to run"
+        "--prompt", default="What is the capital of France?", help="The prompt to run"
     )
     parser.add_argument(
-        "--session-id", default="default",
-        help="The session ID for the conversation"
+        "--session-id", default="default", help="The session ID for the conversation"
     )
     args = parser.parse_args()
 
@@ -212,8 +210,7 @@ def load_dotenv(*_args, **_kwargs):  # type: ignore
     api_key = None
     if not args.dry_run:
         if args.provider and (
-            args.provider.lower() == "gemini" or
-            args.provider.lower() == "google"
+            args.provider.lower() == "gemini" or args.provider.lower() == "google"
         ):
             api_key = os.getenv("GOOGLE_GEMINI_API_KEY")
         elif args.provider and args.provider.lower() == "openai":

src/llm/__init__.py

@@ -5,9 +5,7 @@
 Model providers.
 """
 
-from .base import BaseLLMClient, MockLLMClient
+from .base import BaseLLMClient
+from .base import MockLLMClient
 
-__all__ = [
-    'BaseLLMClient',
-    'MockLLMClient'
-]
+__all__ = ["BaseLLMClient", "MockLLMClient"]