add example [online judge programming]

examples/online_judge_programming/.kattisrc

@@ -0,0 +1,14 @@
+# Please save this file as .kattisrc in your home directory.
+# This file includes a secret token that allows you to log in.
+# DO NOT SHARE IT WITH ANYONE ELSE.
+# If someone gets access to this token, please revoke it by changing your KATTIS password.
+
+[user]
+username: YOUR_USERNAME
+token: YOUR_TOKEN
+
+[kattis]
+hostname: open.kattis.com
+loginurl: https://open.kattis.com/login
+submissionurl: https://open.kattis.com/submit
+submissionsurl: https://open.kattis.com/submissions

examples/online_judge_programming/README.md

@@ -0,0 +1,83 @@
+# Online Judge Programming Example
+
+This example demonstrates how OpenEvolve can solve programming problems and pass all test cases on [Kattis online judge](https://open.kattis.com/) starting from scratch.
+
+## Problem Description
+
+We take the [Alphabet](https://open.kattis.com/problems/alphabet) problem from [Kattis](https://open.kattis.com/) as following:
+```markdown
+A string of lowercase letters is called **alphabetical** if some of the letters can be deleted so that the only letters that remain are the letters from 'a' to 'z' in order. Given a string s, determine the minimum number of letters to add anywhere in the string to make it alphabetical.
+
+Input:
+Each input will consist of a single test case. Note that your program may be run multiple times on different inputs. The only line of input contains a string s (1 ≤ |s| ≤ 50) which contains only lowercase letters.
+
+Output:
+Output a single integer, which is the smallest number of letters needed to add to `s` to make it alphabetical.
+
+Sample Input 1:
+xyzabcdefghijklmnopqrstuvw
+
+Sample Output 1:
+3
+
+Sample Input 2:
+aiemckgobjfndlhp
+
+Sample Output 2:
+20
+```
+
+## Getting Started
+
+First, download your personal configuration file (must be logged in) from [Kattis](https://open.kattis.com/download/kattisrc) and save it as `.kittisrc`.
+
+Then, to run this example:
+
+```bash
+cd examples/online_judge_programming
+python ../../openevolve-run.py initial_program.py evaluator.py --config config.yaml
+```
+
+## Algorithm Evolution
+
+### Initial Algorithm (dummy output)
+
+The initial implementation was a simple dummy output that returned 0 directly.
+
+```python
+import sys
+for line in sys.stdin:
+    s = line.strip()
+
+ans = 0
+print(ans)
+```
+
+### Evolved Algorithm (Dynamic Programming)
+
+After running OpenEvolve for just 4 iterations, it discovered a dynamic programming algorithm that passes all test cases on Kattis:
+
+```python
+import sys
+
+for line in sys.stdin:
+    s = line.strip()
+
+n = len(s)
+dp = [1] * n
+
+for i in range(1, n):
+    for j in range(i):
+        if s[i] > s[j]:
+            dp[i] = max(dp[i], dp[j] + 1)
+
+longest_alphabetical_subsequence_length = max(dp)
+ans = 26 - longest_alphabetical_subsequence_length
+print(ans)
+```
+
+## Next Steps
+
+Try modifying the config.yaml file to:
+- Change the programming problem in system prompt
+- Change the LLM model configuration

examples/online_judge_programming/config.yaml

@@ -0,0 +1,71 @@
+# Configuration for function minimization example
+max_iterations: 20
+checkpoint_interval: 1
+log_level: "INFO"
+
+# LLM configuration
+llm:
+  primary_model: "gemini-2.0-flash"
+  primary_model_weight: 0.6
+  secondary_model: "gemini-2.5-flash-preview-05-20"
+  secondary_model_weight: 0.4
+  api_base: "https://generativelanguage.googleapis.com/v1beta/openai/"
+  api_key: YOUR_API_KEY
+  temperature: 0.7
+  top_p: 0.95
+  max_tokens: 4096
+
+# Prompt configuration
+prompt:
+  system_message: |
+    You are an expert programmer. Your task is to implement an algorithm in Python to pass all the test cases. The problem is as follows:
+
+    A string of lowercase letters is called alphabetical if some of the letters can be deleted so that the only letters that remain are the letters from a to z in order. Given a string s, determine the minimum number of letters to add anywhere in the string to make it alphabetical.
+
+    Input:
+    Each input will consist of a single test case. Note that your program may be run multiple times on different inputs. The only line of input contains a string s (1 ≤ |s| ≤ 50) which contains only lowercase letters.
+    Output:
+    Output a single integer, which is the smallest number of letters needed to add to s to make it alphabetical.
+
+    Sample Input 1:
+    xyzabcdefghijklmnopqrstuvw
+    Sample Output 1:
+    3
+
+    Sample Input 2:
+    aiemckgobjfndlhp
+    Sample Output 2:
+    20
+
+    Your program should always read/write to STDIN/STDOUT. For example, to handle integer input, use the following format:
+    ```
+    import sys
+    for line in sys.stdin:
+        data = int(line)
+    ```
+    Use print() for output. For example:
+    ```
+    print("Hello, World!")
+    ```
+  num_top_programs: 3
+  use_template_stochasticity: true
+
+# Database configuration
+database:
+  population_size: 50
+  archive_size: 20
+  num_islands: 3
+  elite_selection_ratio: 0.2
+  exploitation_ratio: 0.7
+
+# Evaluator configuration
+evaluator:
+  timeout: 60
+  cascade_evaluation: false
+  cascade_thresholds: [1.0]
+  parallel_evaluations: 4
+  use_llm_feedback: false
+
+# Evolution settings
+diff_based_evolution: true
+allow_full_rewrites: false

examples/online_judge_programming/evaluator.py

@@ -0,0 +1,102 @@
+"""
+Evaluator for the function minimization example
+"""
+
+import re
+import subprocess
+import time
+import traceback
+
+
+def run_with_timeout(program_path, timeout_seconds=60):
+    """
+    Run a function with a timeout using subprocess.
+
+    Args:
+        func: Function to run
+        args: Arguments to pass to the function
+        kwargs: Keyword arguments to pass to the function
+        timeout_seconds: Timeout in seconds
+
+    Returns:
+        Result of the function or raises TimeoutError
+    """
+    cmd = ["python", "submit.py", program_path, "-p", "alphabet", "-l", "Python 3", "-f"]
+
+    try:
+        # Run the command and grab its output using subprocess.Popen
+        proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+        stdout, stderr = proc.communicate(timeout=timeout_seconds)
+        exit_code = proc.returncode
+        if exit_code != 0:
+            print(stderr)  # Print the error output if the command failed
+            raise RuntimeError(f"Process exited with code {exit_code}")
+    except subprocess.TimeoutExpired:
+        # Kill the process if it times out
+        proc.kill()
+        raise TimeoutError(f"Process timed out after {timeout_seconds} seconds")
+
+    pattern = (
+        r"Score:\s*(\d+)\s*"
+        r"Test cases done:\s*(\d+)\s*"
+        r"Test cases correct:\s*(\d+)\s*"
+        r"Test cases total:\s*(\d+)"
+    )
+    match = re.search(pattern, stdout)
+    if not match:
+        raise ValueError("Expected summary lines not found")
+
+    score, done, correct, total = map(int, match.groups())
+    return score, done, correct, total
+
+
+def evaluate(program_path):
+    """
+    Evaluate the program by submitting it to OJ and fetching metrics based on how well it performs.
+
+    Args:
+        program_path: Path to the program file
+
+    Returns:
+        Dictionary of metrics
+    """
+    try:
+        # For constructor-based approaches, a single evaluation is sufficient
+        # since the result is deterministic
+        start_time = time.time()
+
+        # Use subprocess to run with timeout
+        score, done, correct, total = run_with_timeout(
+            program_path, timeout_seconds=60  # Single timeout
+        )
+
+        end_time = time.time()
+        eval_time = end_time - start_time
+
+        # Combined score - higher is better
+        combined_score = correct / total if total > 0 else 0.0
+
+        print(
+            f"Evaluation: Score={score}, Done={done}, Correct={correct}, Total={total}, Combined={combined_score:.2f}"
+        )
+
+        return {
+            "score": score,
+            "done": done,
+            "correct": correct,
+            "total": total,
+            "eval_time": eval_time,
+            "combined_score": float(combined_score),
+        }
+
+    except Exception as e:
+        print(f"Evaluation failed completely: {str(e)}")
+        traceback.print_exc()
+        return {
+            "score": 0,
+            "done": 0,
+            "correct": 0,
+            "total": 0,
+            "eval_time": 0.0,
+            "combined_score": 0.0,
+        }

examples/online_judge_programming/initial_program.py

@@ -0,0 +1,12 @@
+"""Online judge programming example for OpenEvolve"""
+
+# EVOLVE-BLOCK-START
+import sys
+
+for line in sys.stdin:
+    s = line.strip()
+
+ans = 0
+print(ans)
+
+# EVOLVE-BLOCK-END

examples/online_judge_programming/requirements.txt

@@ -0,0 +1,2 @@
+lxml
+requests