Fix#7676 - Add Claude Code Assistant for using LLMs (#7673)

* Add Claude Code Assistant for using LLMs

add claude.md files for context to the LLM

* format code

* Update claude.yml

add pull request target

* Force test claude.yml

* Remove sensitive flag - Update claude.yml

* Update claude.yml

Reverted the direct_prompt

* format code (#7674)

Co-authored-by: slangbot <186143334+slangbot@users.noreply.github.com>

* Fix Claude workflow based on PR review feedback

- Remove unused pull_request_review_comment trigger
- Increase timeout from 30 to 60 minutes
- Change fetch-depth from 0 to 2 for minimal git history
- Add recursive submodule checkout following copilot pattern
- Add environment setup with libx11-dev dependency
- Switch to release build config following copilot pattern
- Increase max_turns from 10 to 20 for longer conversations
- Update custom instructions with build commands and OS info

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Update workflow - configure debug build

* Update max turns to 50 for M size work

* Add Claude Code settings with auto-formatting hook

- Create .claude/settings.json with PostToolUse hook
- Automatically runs ./extras/formatting.sh after Write/Edit/MultiEdit operations
- Ensures code formatting consistency when Claude makes changes

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: slangbot <186143334+slangbot@users.noreply.github.com>
Co-authored-by: slangbot <ellieh+slangbot@nvidia.com>
Co-authored-by: Claude <noreply@anthropic.com>

4 files changed, 590 insertions, 0 deletions

diff --git a/.claude/settings.json b/.claude/settings.json
new file mode 100644
index 000000000..5e1dea6fb
--- /dev/null
+++ b/.claude/settings.json
@@ -0,0 +1,15 @@
+{
+  "hooks": {
+    "PostToolUse": [
+      {
+        "matcher": "Write|Edit|MultiEdit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "./extras/formatting.sh"
+          }
+        ]
+      }
+    ]
+  }
+}
\ No newline at end of file
diff --git a/.github/workflows/claude.yml b/.github/workflows/claude.yml
new file mode 100644
index 000000000..454077f06
--- /dev/null
+++ b/.github/workflows/claude.yml
@@ -0,0 +1,317 @@
+name: ClaudeCode - Slang Assistant
+
+permissions:
+  contents: write
+  pull-requests: write
+  issues: write
+  actions: read
+  id-token: write
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+env:
+  AWS_REGION: ${{ vars.AWS_REGION }}
+  AWS_ACCESS_KEY_ID: ${{ vars.AWS_ACCESS_KEY_ID }}
+  AWS_SECRET_ACCESS_KEY: ${{ vars.AWS_SECRET_ACCESS_KEY }}
+
+jobs:
+  claude:
+    name: Claude Code Assistant
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude')))
+
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+
+    # Cancel previous runs on new pushes
+    concurrency:
+      group: claude-${{ github.event.issue.number || github.event.pull_request.number || github.run_id }}
+      cancel-in-progress: true
+
+    steps:
+      # Format setup and environment preparation
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+          fetch-depth: 2 # fetch minimal history for git context
+
+      - name: Format Setup and Environment Preparation
+        uses: ./.github/actions/format-setup
+
+      - name: Setup Environment Dependencies
+        run: |
+          set -euo pipefail
+          echo "🏗️ Setting up environment dependencies..."
+
+          sudo apt-get update
+          sudo apt-get install -y libx11-dev
+
+          # Configure and build the project
+          cmake --preset default --fresh
+          cmake --workflow --preset debug
+
+          echo "✅ Environment setup completed"
+
+      # Validate environment and dependencies
+      - name: Validate Environment
+        run: |
+          set -euo pipefail
+
+          # Check required secrets
+          if [ -z "${{ secrets.LLMGW_ID }}" ] || [ -z "${{ secrets.LLMGW_SECRET }}" ] || [ -z "${{ secrets.LLMGW_TOKEN_URL }}" ]; then
+            echo "::error::Missing required secrets: LLMGW_ID or LLMGW_SECRET or LLMGW_TOKEN_URL"
+            exit 1
+          fi
+
+          # Install required tools
+          command -v jq >/dev/null 2>&1 || { echo "::error::jq is required but not installed"; exit 1; }
+          command -v curl >/dev/null 2>&1 || { echo "::error::curl is required but not installed"; exit 1; }
+
+          echo "✅ Environment validation passed"
+
+      # Generate custom auth token and set as environment variable
+      - name: Generate Custom Auth Token
+        id: auth-token
+        env:
+          LLMGW_TOKEN_URL: ${{ secrets.LLMGW_TOKEN_URL }}
+        run: |
+          set -euo pipefail
+
+          echo "🔐 Generating authentication token..."
+
+          # Set up error handling
+          cleanup() {
+            local exit_code=$?
+            echo "🧹 Cleaning up temporary files..."
+            rm -f /tmp/token_response.json 2>/dev/null || true
+            if [ $exit_code -ne 0 ]; then
+              echo "::error::Authentication failed - check your credentials and endpoint"
+            fi
+            exit $exit_code
+          }
+          trap cleanup EXIT
+
+          # Generate token with comprehensive error handling
+          HTTP_CODE=$(curl -s -w "%{http_code}" -o /tmp/token_response.json --fail-with-body \
+            --max-time 30 \
+            --retry 3 \
+            --retry-delay 2 \
+            --location "${{ env.LLMGW_TOKEN_URL }}" \
+            --header 'Content-Type: application/x-www-form-urlencoded' \
+            --header "Authorization: Basic $(echo -n ${{ secrets.LLMGW_ID }}:${{ secrets.LLMGW_SECRET }} | base64 -w0)" \
+            --data-urlencode 'grant_type=client_credentials' \
+            --data-urlencode 'scope=awsanthropic-readwrite azureopenai-readwrite' \
+            2>/dev/null)
+
+          # Check HTTP response code
+          if [ "$HTTP_CODE" -ne 200 ]; then
+            echo "::error::Authentication failed with HTTP code: $HTTP_CODE"
+            if [ -f /tmp/token_response.json ]; then
+              echo "::error::Response: $(cat /tmp/token_response.json | head -c 200)"
+            fi
+            exit 1
+          fi
+
+          # Extract and validate token
+          if [ ! -f /tmp/token_response.json ]; then
+            echo "::error::No response file generated"
+            exit 1
+          fi
+
+          ANTHROPIC_AUTH_TOKEN=$(jq -r '.access_token // empty' /tmp/token_response.json 2>/dev/null)
+
+          # Validate token format and length
+          if [ -z "$ANTHROPIC_AUTH_TOKEN" ] || [ "$ANTHROPIC_AUTH_TOKEN" = "null" ]; then
+            echo "::error::Failed to extract access token from response"
+            exit 1
+          fi
+
+          # Basic token validation
+          if [ ${#ANTHROPIC_AUTH_TOKEN} -lt 10 ]; then
+            echo "::error::Token appears to be too short (${#ANTHROPIC_AUTH_TOKEN} characters)"
+            exit 1
+          fi
+
+          # CRITICAL: Mask the token BEFORE any output
+          echo "::add-mask::$ANTHROPIC_AUTH_TOKEN"
+
+          # Set as environment variable for subsequent steps
+          echo "ANTHROPIC_AUTH_TOKEN=$ANTHROPIC_AUTH_TOKEN" >> $GITHUB_ENV
+
+          # Set token expiry if available
+          TOKEN_EXPIRES=$(jq -r '.expires_in // empty' /tmp/token_response.json 2>/dev/null)
+          if [ -n "$TOKEN_EXPIRES" ]; then
+            echo "::add-mask::$TOKEN_EXPIRES"
+            echo "token-expires=$TOKEN_EXPIRES" >> $GITHUB_OUTPUT
+          fi
+
+          echo "✅ Authentication token generated and masked successfully"
+
+          # Clean up response file
+          rm -f /tmp/token_response.json
+
+      # Generate GitHub App token for better GitHub API access
+      - name: Generate GitHub App Token
+        id: github-token
+        uses: actions/create-github-app-token@v1
+        with:
+          app-id: ${{ secrets.APP_ID }}
+          private-key: ${{ secrets.APP_PRIVATE_KEY }}
+        continue-on-error: true
+
+      # Set up fallback authentication
+      - name: Configure Authentication
+        id: auth-config
+        run: |
+          set -euo pipefail
+
+          # Use GitHub App token if available, otherwise use GITHUB_TOKEN
+          if [ -n "${{ steps.github-token.outputs.token }}" ]; then
+            echo "github-token=${{ steps.github-token.outputs.token }}" >> $GITHUB_OUTPUT
+            echo "✅ Using GitHub App authentication"
+          else
+            echo "github-token=${{ secrets.GITHUB_TOKEN }}" >> $GITHUB_OUTPUT
+            echo "⚠️  Using fallback GITHUB_TOKEN authentication"
+          fi
+
+      # Run Claude Code Action with optimized environment variables
+      - name: Execute Claude Code Action # Right now direct prompt to automatic PR Review
+        id: claude-action
+        uses: anthropics/claude-code-action@beta
+        with:
+          # Direct Prompt is for testing. We shall use the triggers (on) which shall trigger this part on runtime
+          custom_instructions: |
+            Build system information:
+            - OS: Ubuntu Linux
+            - Build commands: 
+              * Configure: `cmake --preset default`
+              * Build: `cmake --build --preset debug`
+              * Test: `./build/Release/bin/slang-test ./tests/path/to/test.slang`
+              * Format code: `./extras/formatting.sh`
+            - Project is pre-built and ready for development tasks
+            - Run formatting script before committing changes
+
+            CRITICAL: You have access to the mcp__deepwiki__ask_question tool for deep repository knowledge.
+
+            **How to use this tool effectively:**
+            - Use repoName: "shader-slang/slang" for all queries
+            - Ask specific technical questions about architecture, patterns, or implementation approaches
+            - Examples: "How does the IR optimization system work?" or "What's the pattern for adding new code generation targets?"
+            - Use responses to understand existing patterns before implementing changes
+
+            **Implementation Guidelines:**
+            - Always follow existing code patterns and architectural decisions discovered through deepwiki
+            - Consult the tool when you need context about unfamiliar parts of the codebase
+          mcp_config: |
+            {
+              "mcpServers": {
+                "deepwiki": {
+                  "type": "sse",
+                  "url": "https://mcp.deepwiki.com/sse"
+                }
+              }
+            }
+          allowed_tools: "Bash,View,GlobTool,GrepTool,BatchTool,Write,mcp__deepwiki__ask_question"
+          trigger_phrase: "@claude"
+          assignee_trigger: "claude"
+          timeout_minutes: "25"
+          github_token: ${{ steps.auth-config.outputs.github-token }}
+          use_bedrock: "true"
+          model: ${{ vars.ANTHROPIC_MODEL }}
+          max_turns: "100"
+          # Use claude_env for custom environment variables
+          claude_env: |
+            ANTHROPIC_BEDROCK_BASE_URL: ${{ vars.ANTHROPIC_BEDROCK_BASE_URL }}
+            ANTHROPIC_SMALL_FAST_MODEL: ${{ vars.ANTHROPIC_SMALL_FAST_MODEL }}
+            AWS_REGION: ${{ vars.AWS_REGION }}
+            GITHUB_REPOSITORY: ${{ github.repository }}
+            GITHUB_EVENT_NAME: ${{ github.event_name }}
+            GITHUB_ACTOR: ${{ github.actor }}
+            ANTHROPIC_AUTH_TOKEN: ${{ env.ANTHROPIC_AUTH_TOKEN }}
+            DISABLE_TELEMETRY: 1
+
+        # The ANTHROPIC_API_KEY environment variable is automatically picked up
+        continue-on-error: true
+
+      # Handle action results and errors
+      - name: Handle Action Results
+        if: always()
+        run: |
+          set -euo pipefail
+
+          # Check if Claude action succeeded
+          if [ "${{ steps.claude-action.outcome }}" = "success" ]; then
+            echo "✅ Claude Code action completed successfully"
+
+            # Optional: Add success comment to PR/issue
+            if [ -n "${{ github.event.issue.number || github.event.pull_request.number }}" ]; then
+              echo "Claude has successfully processed your request! 🎉" >> /tmp/comment.md
+              echo "<!-- Claude-success -->" >> /tmp/comment.md
+            fi
+
+          elif [ "${{ steps.claude-action.outcome }}" = "failure" ]; then
+            echo "❌ Claude Code action failed"
+
+            # Create error comment for debugging
+            cat > /tmp/error_comment.md << 'EOF'
+          ## Claude Code Action Failed ❌
+
+          The Claude Code action encountered an error. This could be due to:
+          - Network connectivity issues
+          - Authentication problems
+          - Model availability issues
+          - Rate limiting
+
+          Please check the workflow logs for more details and try again.
+
+          <!-- Claude-error -->
+          EOF
+
+          else
+            echo "⚠️  Claude Code action was cancelled or skipped"
+          fi
+
+      # Security cleanup
+      - name: Security Cleanup
+        if: always()
+        run: |
+          set -euo pipefail
+
+          echo "🧹 Performing security cleanup..."
+
+          # Clear any temporary files that might contain sensitive data
+          find /tmp -name "*token*" -type f -delete 2>/dev/null || true
+          find /tmp -name "*auth*" -type f -delete 2>/dev/null || true
+          find /tmp -name "*response*" -type f -delete 2>/dev/null || true
+
+          # Clear environment variables (belt and suspenders approach)
+          unset ANTHROPIC_API_KEY 2>/dev/null || true
+          unset ANTHROPIC_AUTH_TOKEN 2>/dev/null || true
+
+          echo "✅ Security cleanup completed"
+
+      # Workflow summary
+      - name: Workflow Summary
+        if: always()
+        run: |
+          echo "## Claude Code Workflow Summary" >> $GITHUB_STEP_SUMMARY
+          echo "- **Trigger**: ${{ github.event_name }}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Repository**: ${{ github.repository }}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Actor**: ${{ github.actor }}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Auth Token**: ✅ Generated" >> $GITHUB_STEP_SUMMARY
+          echo "- **GitHub Token**: ${{ steps.github-token.outcome == 'success' && '✅ GitHub App' || '⚠️ Fallback' }}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Claude Action**: ${{ steps.claude-action.outcome == 'success' && '✅ Success' || '❌ Failed' }}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Model Used**: ${{ vars.ANTHROPIC_MODEL || 'default' }}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Workflow Status**: ${{ job.status }}" >> $GITHUB_STEP_SUMMARY
diff --git a/CLAUDE.local.md b/CLAUDE.local.md
new file mode 100755
index 000000000..282936701
--- /dev/null
+++ b/CLAUDE.local.md
@@ -0,0 +1,48 @@
+# Slang Repository Structure
+
+For the repoName: `shader-slang/slang` repository, the deepwiki mcp server structure includes:
+
+## Main Topics:
+ - 1 Overview
+ - 2 Compiler Architecture
+   - 2.1 Front-End: Parsing & AST
+   - 2.2 Semantic Analysis
+   - 2.3 Intermediate Representation
+   - 2.4 IR Lowering & Optimization
+   - 2.5 Code Generation
+ - 3 Session Management & API
+   - 3.1 Session & Linkage System
+   - 3.2 ComponentType Hierarchy
+ - 4 Language Features
+   - 4.1 Automatic Differentiation
+   - 4.2 Module System
+   - 4.3 Interfaces & Generics
+   - 4.4 Capabilities System
+ - 5 Target Platforms
+   - 5.1 HLSL & DirectX Targets
+   - 5.2 GLSL & Vulkan Targets
+   - 5.3 C++, CUDA & CPU Targets
+   - 5.4 Other Targets & Extensions
+ - 6 Rendering System
+   - 6.1 GFX API Architecture
+   - 6.2 Shader Objects & Resource Binding
+   - 6.3 Device & Pipeline Management
+ - 7 Testing & Build Infrastructure
+   - 7.1 Test Framework
+   - 7.2 Build System
+   - 7.3 CI/CD Pipeline
+ - 8 Development Tools
+   - 8.1 Language Server
+   - 8.2 Utilities & Core Libraries
+### MCP Tools
+#### 1. `mcp__deepwiki__ask_question`
+- **Purpose**: Ask specific questions about a GitHub repository
+- **Parameters**:
+  - `repoName` (required): GitHub repository in format "shader-slang/slang"
+  - `question` (required): The question to ask about the repository
+- **Usage**: Returns AI-generated answers based on repository analysis
+
+## Build Instructions
+- Build using: `cmake --build --preset debug`
+- Test using: `./build/Debug/bin/slangc -target path/to/file.slang`
+    - Add `-dump-ir` for IR stages / optimization logs and understanding
diff --git a/CLAUDE.md b/CLAUDE.md
new file mode 100755
index 000000000..8a01904db
--- /dev/null
+++ b/CLAUDE.md
@@ -0,0 +1,210 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Essential Build Commands
+
+**Configure and build (recommended):**
+```bash
+cmake --preset default
+cmake --build --preset releaseWithDebugInfo  # or --preset debug, or --preset release
+```
+
+**Alternative Visual Studio workflow:**
+```bash
+cmake --preset vs2022  # or vs2019
+cmake --build --preset releaseWithDebugInfo
+```
+
+**Quick release build and package:**
+```bash
+cmake --workflow --preset release
+```
+
+**Build only generators for cross-compilation:**
+```bash
+cmake --workflow --preset generators --fresh
+```
+
+## Testing Commands
+
+**Run all tests:**
+```bash
+build/Release/bin/slang-test
+# or for debug builds:
+build/Debug/bin/slang-test
+```
+
+**Run specific test categories:**
+```bash
+slang-test -category smoke    # Basic smoke tests
+slang-test -category quick    # Quick tests  
+slang-test -category full     # Full test suite
+slang-test -category compute  # Compute shader tests
+```
+
+**Run tests with parallel execution:**
+```bash
+slang-test -use-test-server -server-count 8
+```
+
+**Run specific API tests:**
+```bash
+slang-test -api vk           # Vulkan only
+slang-test -api dx12         # DirectX 12 only
+```
+
+**Full CI-style test run:**
+```bash
+slang-test -use-test-server -server-count 8 -category full -expected-failure-list tests/expected-failure-github.txt
+```
+
+**Run single test:**
+```bash
+slang-test tests/compute/array-param
+```
+
+## Core Architecture Overview
+
+### Main Compilation Pipeline
+- **Front-end**: Source → AST → IR (with semantic checking and lowering)
+- **Back-end**: IR → Optimized IR → Target Code Generation
+
+### Key Source Directories
+
+**`source/core/`** - Foundation utilities, platform abstraction, collections, memory management
+
+**`source/compiler-core/`** - Shared compiler infrastructure
+- Lexical analysis, diagnostics, source locations
+- Downstream compiler integration (DXC, FXC, GLSLANG)
+- Artifact management and JSON utilities for tooling
+
+**`source/slang/`** - Main compiler implementation
+- `slang-parser.cpp` - Recursive descent parser
+- `slang-ast-*.cpp` - Abstract Syntax Tree and type system
+- `slang-check-*.cpp` - Semantic checking and type checking
+- `slang-ir*.cpp` - Intermediate representation and optimization passes
+- `slang-emit-*.cpp` - Target-specific code generators (HLSL, GLSL, SPIR-V, Metal, etc.)
+- `slang-lower-to-ir.cpp` - AST to IR transformation
+
+### IR System Characteristics
+- **SSA Form**: Single Static Assignment with block parameters
+- **Instruction-based**: Everything is an instruction (types, constants, operations)
+- **Typed IR**: Every instruction has a type
+- **Global Deduplication**: Types and constants automatically deduplicated
+
+### Code Generation Targets
+- `slang-emit-hlsl.cpp` - HLSL generation
+- `slang-emit-glsl.cpp` - GLSL generation  
+- `slang-emit-spirv.cpp` - Direct SPIR-V bytecode
+- `slang-emit-metal.cpp` - Metal Shading Language
+- `slang-emit-wgsl.cpp` - WebGPU Shading Language
+- `slang-emit-cuda.cpp` - CUDA C++ generation
+- `slang-emit-cpp.cpp` - Host C++ code generation
+
+## Key Build Configuration
+
+**CMake presets available:**
+- `default` - Ninja Multi-Config (recommended)
+- `vs2022` / `vs2019` - Visual Studio generators
+- `emscripten` - WebAssembly build
+- `generators` - Build only code generators
+
+**Important CMake options:**
+- `SLANG_ENABLE_TESTS=TRUE` - Enable test targets (default)
+- `SLANG_ENABLE_GFX=TRUE` - Enable graphics abstraction layer
+- `SLANG_ENABLE_SLANGC=TRUE` - Enable standalone compiler
+- `SLANG_LIB_TYPE=SHARED` - Build shared library (default)
+
+## Module and Generic System
+
+**Module compilation:**
+- Independent compilation with cross-module linking
+- Serialization support for caching and distribution
+- Built-in core modules for language features
+
+**Generics and interfaces:**
+- First-class generic types and functions
+- Interface-based programming with witness tables
+- Compile-time specialization and monomorphization
+
+## Development Notes
+
+**Language features:**
+- HLSL compatibility with Slang extensions
+- Automatic differentiation for neural graphics
+- Multi-target compilation (DX11/12, Vulkan, Metal, CUDA, CPU)
+- Capability system for platform feature management
+
+**Testing structure:**
+- Main tests in `tests/` directory
+- Categories: compute, autodiff, bugs, bindings, etc.
+- Expected failure lists for CI (`tests/expected-failure-*.txt`)
+
+**Cross-compilation:**
+First build generators for build platform, then configure with `SLANG_GENERATORS_PATH` pointing to them.
+
+## Debugging and Development Workflow
+
+**Using slangc for debugging:**
+```bash
+# Basic compilation with target-specific output
+./build/Debug/bin/slangc -target cuda file.slang
+
+# Debug IR stages and optimization passes
+./build/Debug/bin/slangc -dump-ir -target cuda file.slang
+
+# HLSL output for debugging
+./build/Debug/bin/slangc -target hlsl file.slang -o output.hlsl
+```
+
+**Interactive debugging with slangi (interpreter):**
+```bash
+# Run bytecode interpreter for testing without GPU
+./build/Debug/bin/slangi file.slang
+```
+
+**Test-driven development:**
+```bash
+# CPU-based testing (no GPU required)
+slang-test tests/your-test.slang -cpu
+
+# Interpreter-based testing 
+slang-test tests/your-test.slang -slangi
+
+# Test with specific backend
+slang-test tests/your-test.slang -api dx12  # or vk, metal, etc.
+```
+
+## Code Formatting and Style
+
+**Before submitting changes:**
+```bash
+# Format code according to project standards
+./extras/formatting.sh
+```
+
+**PR requirements:**
+- All PRs must be labeled "pr: non-breaking" or "pr: breaking"
+- Include regression tests under `tests/` directory
+- Breaking changes are rare and only for API/language compatibility issues
+
+## Test Structure and Patterns
+
+**Test file headers for different execution modes:**
+```bash
+# CPU execution (no GPU required)
+//TEST:COMPARE_COMPUTE(filecheck-buffer=CHECK):-output-using-type -cpu
+
+# Interpreter execution
+//TEST:INTERPRET(filecheck=CHECK):
+
+# HLSL compilation test
+//TEST(hlsl):COMPARE_HLSL: -entry main -target hlsl
+```
+
+**Common test categories:**
+- `tests/compute/` - Compute shader tests
+- `tests/autodiff/` - Automatic differentiation tests  
+- `tests/bugs/` - Bug reproduction and regression tests
+- `tests/bindings/` - Resource binding tests