P2: V0 commit

.idea/.gitignore

@@ -0,0 +1,5 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,15 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyCompatibilityInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ourVersions">
+        <value>
+          <list size="2">
+            <item index="0" class="java.lang.String" itemvalue="2.7" />
+            <item index="1" class="java.lang.String" itemvalue="3.14" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/meta-rl-dsa-solver.iml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="JAVA_MODULE" version="4">
+  <component name="NewModuleRootManager" inherit-compiler-output="true">
+    <exclude-output />
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/misc.xml

@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.9" />
+  </component>
+  <component name="ProjectRootManager" version="2" languageLevel="JDK_24" default="true" project-jdk-name="Python 3.9" project-jdk-type="Python SDK">
+    <output url="file://$PROJECT_DIR$/out" />
+  </component>
+  <component name="PythonCompatibilityInspectionAdvertiser">
+    <option name="version" value="3" />
+  </component>
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/meta-rl-dsa-solver.iml" filepath="$PROJECT_DIR$/.idea/meta-rl-dsa-solver.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

scripts/test_verifier.py

@@ -0,0 +1,16 @@
+from verifier.verifier import verify
+test_cases = [
+    ("5\n", "10"),
+    ("0\n", "0"),
+    ("-3\n", "-6"),
+]
+
+code = """
+n = int(input())
+print(n * 2)
+"""
+
+reward, info = verify(code, test_cases)
+
+print("Reward:", reward)
+print(info)

verifier/metrics.py

@@ -0,0 +1,12 @@
+def compute_pass_rate(results):
+    total = len(results)
+    passed = sum(1 for r in results if r["passed"])
+
+    pass_rate = passed / total if total > 0 else 0.0
+    reward = 1.0 if pass_rate == 1.0 else 0.0
+
+    return reward, {
+        "passed": passed,
+        "total": total,
+        "pass_rate": pass_rate,
+    }

verifier/sandbox.py

@@ -0,0 +1,31 @@
+import subprocess
+import tempfile
+import os
+
+
+def run_code(code: str, stdin: str, timeout: int = 2):
+    try:
+        with tempfile.NamedTemporaryFile("w", suffix=".py", delete=False) as f:
+            f.write(code)
+            path = f.name
+
+        result = subprocess.run(
+            ["python3", path],
+            input=stdin,
+            text=True,
+            capture_output=True,
+            timeout=timeout,
+        )
+
+        os.remove(path)
+
+        if result.returncode != 0:
+            return False, result.stderr.strip()
+
+        return True, result.stdout.strip()
+
+    except subprocess.TimeoutExpired:
+        return False, "TIMEOUT"
+
+    except Exception as e:
+        return False, f"ERROR: {e}"

verifier/verifier.py

@@ -0,0 +1,23 @@
+from verifier.sandbox import run_code
+from verifier.metrics import compute_pass_rate
+
+def verify(code: str, test_cases):
+    results = []
+
+    for stdin, expected in test_cases:
+        ok, output = run_code(code, stdin)
+        passed = ok and output.strip() == expected.strip()
+
+        results.append({
+            "input": stdin.strip(),
+            "expected": expected.strip(),
+            "output": output.strip(),
+            "passed": passed,
+        })
+
+    reward, metrics = compute_pass_rate(results)
+
+    return reward, {
+        **metrics,
+        "results": results,
+    }