chore: import upstream snapshot with attribution

examples/integration-docker/code-generation-sandbox/README.md

@@ -0,0 +1,12 @@
+# integration-docker/code-generation-sandbox (Docker Code Generation Sandbox)
+
+You can run this example with:
+
+```bash
+npx promptfoo@latest init --example integration-docker/code-generation-sandbox
+cd integration-docker/code-generation-sandbox
+```
+
+## Usage
+
+See https://promptfoo.dev/docs/guides/sandboxed-code-evals

examples/integration-docker/code-generation-sandbox/code_generation_prompt.txt

@@ -0,0 +1,7 @@
+You are a Python code generator. Write a Python function to solve the following problem:
+
+{{problem}}
+
+Use the following function name: {{function_name}}
+
+Only provide the function code, without any explanations or additional text. Wrap your code in triple backticks.

examples/integration-docker/code-generation-sandbox/promptfooconfig.yaml

@@ -0,0 +1,31 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: 'Generate code with Claude in a Docker sandbox'
+
+prompts:
+  - file://code_generation_prompt.txt
+
+providers:
+  - anthropic:claude-sonnet-4-6
+  # - openai:gpt-4.1
+
+tests:
+  - vars:
+      problem: 'Write a Python function to calculate the factorial of a number'
+      function_name: 'factorial'
+      test_input: '5'
+      expected_output: '120'
+  - vars:
+      problem: 'Write a Python function to check if a string is a palindrome'
+      function_name: 'is_palindrome'
+      test_input: "'racecar'"
+      expected_output: 'True'
+  - vars:
+      problem: 'Write a Python function to find the largest element in a list'
+      function_name: 'find_largest'
+      test_input: '[1, 5, 3, 9, 2]'
+      expected_output: '9'
+
+defaultTest:
+  assert:
+    - type: python
+      value: file://validate_and_run_code.py

examples/integration-docker/code-generation-sandbox/requirements.txt

@@ -0,0 +1,10 @@
+certifi==2025.10.5
+charset-normalizer==3.3.2
+docker==7.1.0
+epicbox==1.1.0
+idna==3.15
+python-dateutil==2.9.0.post0
+requests==2.33.0
+six==1.16.0
+structlog==24.2.0
+urllib3==2.7.0

examples/integration-docker/code-generation-sandbox/validate_and_run_code.py

@@ -0,0 +1,60 @@
+import re
+
+import epicbox
+
+# Replace with your preferred Docker image
+DOCKER_IMAGE = "python:3.9-alpine"
+
+
+def get_assert(output, context):
+    # Extract the Python function from the LLM output
+    function_match = re.search(r"```python\s*\n(def\s+.*?)\n```", output, re.DOTALL)
+    if not function_match:
+        return {"pass": False, "score": 0, "reason": "No function definition found"}
+
+    function_code = function_match.group(1)
+
+    # Configure epicbox
+    epicbox.configure(profiles=[epicbox.Profile("python", DOCKER_IMAGE)])
+
+    # Get the function name, test input, and expected output from the context
+    function_name = context["vars"]["function_name"]
+    test_input = context["vars"]["test_input"]
+    expected_output = context["vars"]["expected_output"]
+
+    # Prepare the code to run in the sandbox
+    test_code = f"""
+{function_code}
+
+# Test the function
+result = {function_name}({test_input})
+print(result)
+"""
+
+    files = [{"name": "main.py", "content": test_code.encode("utf-8")}]
+    limits = {"cputime": 1, "memory": 64}
+
+    # Run the code in the sandbox
+    result = epicbox.run("python", "python main.py", files=files, limits=limits)
+
+    if result["exit_code"] != 0:
+        return {
+            "pass": False,
+            "score": 0,
+            "reason": f"Execution error: {result['stderr'].decode('utf-8')}",
+        }
+
+    # Compare the output with the expected result
+    actual_output = result["stdout"].decode("utf-8").strip()
+    if actual_output == str(expected_output):
+        return {
+            "pass": True,
+            "score": 1,
+            "reason": f"Correct output: got {expected_output}",
+        }
+    else:
+        return {
+            "pass": False,
+            "score": 0,
+            "reason": f"Incorrect output. Expected: {expected_output}, Got: {actual_output}",
+        }