Fix codeql alert + modularize pytorch codegen

.github/workflows/codeql.yml

@@ -0,0 +1,100 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL Advanced"
+
+on:
+  push:
+    branches: [ "main", "deploy" ]
+  pull_request:
+    branches: [ "main", "deploy" ]
+  workflow_dispatch:
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+        - language: javascript-typescript
+          build-mode: none
+        - language: python
+          build-mode: none
+        # CodeQL supports the following values keywords for 'language': 'actions', 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'rust', 'swift'
+        # Use `c-cpp` to analyze code written in C, C++ or both
+        # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
+        # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
+        # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
+        # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    # Add any setup steps before running the `github/codeql-action/init` action.
+    # This includes steps like installing compilers or runtimes (`actions/setup-node`
+    # or others). This is typically only required for manual builds.
+    # - name: Setup runtime (example)
+    #   uses: actions/setup-example@v1
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v4
+      with:
+        languages: ${{ matrix.language }}
+        build-mode: ${{ matrix.build-mode }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+    # If the analyze step fails for one of the languages you are analyzing with
+    # "We were unable to automatically build your code", modify the matrix above
+    # to set the build mode to "manual" for that language. Then modify this step
+    # to build your code.
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+    - name: Run manual build steps
+      if: matrix.build-mode == 'manual'
+      shell: bash
+      run: |
+        echo 'If you are using a "manual" build mode for one or more of the' \
+          'languages you are analyzing, replace this with the commands to build' \
+          'your code, for example:'
+        echo '  make bootstrap'
+        echo '  make release'
+        exit 1
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v4
+      with:
+        category: "/language:${{matrix.language}}"

project/block_manager/services/codegen/__init__.py

@@ -0,0 +1,6 @@
+"""Code generation orchestration package"""
+
+from .pytorch_orchestrator import PyTorchCodeOrchestrator
+from .tensorflow_orchestrator import TensorFlowCodeOrchestrator
+
+__all__ = ['PyTorchCodeOrchestrator', 'TensorFlowCodeOrchestrator']

project/block_manager/services/codegen/base.py

@@ -0,0 +1,79 @@
+"""
+Base utilities for code generation
+Shared functions for both PyTorch and TensorFlow code generation
+"""
+
+from collections import deque
+from typing import List, Dict, Any
+
+
+def topological_sort(nodes: List[Dict], edges: List[Dict]) -> List[Dict]:
+    """
+    Sort nodes in topological order based on edges using Kahn's algorithm.
+
+    Args:
+        nodes: List of node definitions
+        edges: List of edge definitions
+
+    Returns:
+        List of nodes in topological order
+    """
+    node_map = {node['id']: node for node in nodes}
+
+    # Build adjacency list and in-degree count
+    graph = {node['id']: [] for node in nodes}
+    in_degree = {node['id']: 0 for node in nodes}
+
+    for edge in edges:
+        source = edge.get('source')
+        target = edge.get('target')
+        if source in graph and target in graph:
+            graph[source].append(target)
+            in_degree[target] += 1
+
+    # Kahn's algorithm
+    queue = deque([node_id for node_id, degree in in_degree.items() if degree == 0])
+    sorted_ids = []
+
+    while queue:
+        node_id = queue.popleft()
+        sorted_ids.append(node_id)
+
+        for neighbor in graph[node_id]:
+            in_degree[neighbor] -= 1
+            if in_degree[neighbor] == 0:
+                queue.append(neighbor)
+
+    # Return nodes in sorted order
+    return [node_map[node_id] for node_id in sorted_ids if node_id in node_map]
+
+
+def get_input_variable(incoming: List[str], var_map: Dict[str, str]) -> str:
+    """
+    Determine input variable name based on incoming connections.
+
+    Args:
+        incoming: List of incoming node IDs
+        var_map: Map of node ID to variable name
+
+    Returns:
+        Variable name or list of variable names for multiple inputs
+    """
+    if not incoming:
+        return 'x'
+    elif len(incoming) == 1:
+        return var_map.get(incoming[0], 'x')
+    else:
+        # Multiple inputs (for concat, add, etc.)
+        input_vars = [var_map.get(src, 'x') for src in incoming]
+        return f"[{', '.join(input_vars)}]"
+
+
+def get_node_type(node: Dict[str, Any]) -> str:
+    """Extract node type from node definition"""
+    return node.get('data', {}).get('blockType', 'unknown')
+
+
+def get_node_config(node: Dict[str, Any]) -> Dict[str, Any]:
+    """Extract configuration from node definition"""
+    return node.get('data', {}).get('config', {})