arbiter-cli 0.1.0__py3-none-any.whl

arbiter/core/swe/sandbox.py

@@ -0,0 +1,111 @@
+"""Self-contained Python sandbox -- no Docker required.
+
+Runs model-generated code in a subprocess with:
+  - Strict timeout (kills after N seconds)
+  - Temp directory isolation (code can't see the host filesystem)
+  - Memory limit via resource module (Unix only)
+
+This is the default execution mode. Docker is optional for full isolation.
+"""
+
+from __future__ import annotations
+
+import os
+import shutil
+import subprocess
+import sys
+import tempfile
+import time
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Optional
+
+from arbiter.core.swe.container import ContainerResult, _parse_pytest_output
+
+
+def run_in_sandbox(
+    fix_code: str,
+    test_code: str,
+    timeout: int = 30,
+) -> ContainerResult:
+    """Run model's fix + test suite in an isolated subprocess.
+
+    1. Creates a temp directory
+    2. Writes fix.py and test_fix.py
+    3. Runs pytest in a subprocess with restricted PYTHONPATH
+    4. Parses results
+    5. Cleans up
+
+    No Docker needed. Ships with Arbiter.
+    """
+    tmpdir = tempfile.mkdtemp(prefix="arbiter-sandbox-")
+    fix_path = Path(tmpdir) / "fix.py"
+    test_path = Path(tmpdir) / "test_fix.py"
+
+    try:
+        fix_path.write_text(fix_code)
+        test_path.write_text(test_code)
+
+        start = time.perf_counter()
+
+        env = os.environ.copy()
+        env["PYTHONDONTWRITEBYTECODE"] = "1"
+        env["PYTHONPATH"] = tmpdir
+
+        cmd = [
+            sys.executable, "-m", "pytest",
+            str(test_path),
+            "-v", "--tb=short",
+        ]
+
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            timeout=timeout,
+            cwd=tmpdir,
+            env=env,
+        )
+
+        elapsed = time.perf_counter() - start
+        stdout = result.stdout
+        stderr = result.stderr
+
+        passed, failed, total = _parse_pytest_output(stdout + stderr)
+
+        return ContainerResult(
+            exit_code=result.returncode,
+            stdout=stdout[-2000:],
+            stderr=stderr[-1000:],
+            tests_passed=passed,
+            tests_failed=failed,
+            tests_total=total,
+            duration_s=elapsed,
+        )
+
+    except subprocess.TimeoutExpired:
+        return ContainerResult(
+            exit_code=-1, stdout="", stderr=f"Timeout after {timeout}s",
+            tests_passed=0, tests_failed=0, tests_total=0,
+            duration_s=timeout,
+        )
+    except Exception as e:
+        return ContainerResult(
+            exit_code=-1, stdout="", stderr=str(e),
+            tests_passed=0, tests_failed=0, tests_total=0,
+            duration_s=0,
+        )
+    finally:
+        shutil.rmtree(tmpdir, ignore_errors=True)
+
+
+def check_sandbox() -> bool:
+    """Check if the sandbox can run (just needs Python + pytest)."""
+    try:
+        result = subprocess.run(
+            [sys.executable, "-m", "pytest", "--version"],
+            capture_output=True, text=True, timeout=5,
+        )
+        return result.returncode == 0
+    except (subprocess.TimeoutExpired, FileNotFoundError):
+        return False

arbiter/core/swe/test_packs.py

@@ -0,0 +1,548 @@
+"""Built-in SWE test packs -- real bugs with real test suites.
+
+Each test case contains:
+  - Buggy source code
+  - A bug report (what the model sees)
+  - A test suite (what verifies the fix)
+  - The correct fix (for reference scoring)
+
+These run inside Docker containers with pytest.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+
+
+@dataclass
+class TestCase:
+    """A single SWE-bench style test case."""
+    name: str
+    category: str
+    filename: str
+    issue: str              # bug report the model sees
+    buggy_code: str         # the broken code
+    test_code: str          # pytest test suite that validates the fix
+    solution_code: str      # correct fix (for reference)
+    expected_tests: int     # how many tests should pass
+    docker_image: str = "arbiter-swe-python"
+    test_command: str = "python -m pytest /workspace/test_fix.py -v --tb=short"
+    timeout: int = 30
+
+
+@dataclass
+class TestPack:
+    """A collection of related test cases."""
+    name: str
+    description: str
+    language: str
+    cases: list[TestCase] = field(default_factory=list)
+
+
+# ══════════════════════════════════════════════════════════════════════
+# Python Bug Fixes
+# ══════════════════════════════════════════════════════════════════════
+
+PYTHON_BUGS = TestPack(
+    name="python-bugs",
+    description="Real Python bugs: off-by-one errors, logic flaws, edge cases",
+    language="python",
+    cases=[
+        TestCase(
+            name="Binary Search Off-by-One",
+            category="bug_fix",
+            filename="search.py",
+            issue=(
+                "binary_search returns -1 for elements that exist in the list. "
+                "For example, binary_search([1, 3, 5, 7, 9], 7) returns -1 "
+                "instead of 3. The function enters an infinite loop for some inputs."
+            ),
+            buggy_code="""\
+def binary_search(arr, target):
+    low, high = 0, len(arr)
+    while low < high:
+        mid = (low + high) // 2
+        if arr[mid] == target:
+            return mid
+        elif arr[mid] < target:
+            low = mid
+        else:
+            high = mid
+    return -1
+""",
+            test_code="""\
+from fix import binary_search
+
+def test_find_existing():
+    assert binary_search([1, 3, 5, 7, 9], 7) == 3
+
+def test_find_first():
+    assert binary_search([1, 3, 5, 7, 9], 1) == 0
+
+def test_find_last():
+    assert binary_search([1, 3, 5, 7, 9], 9) == 4
+
+def test_not_found():
+    assert binary_search([1, 3, 5, 7, 9], 4) == -1
+
+def test_empty():
+    assert binary_search([], 1) == -1
+
+def test_single_element_found():
+    assert binary_search([5], 5) == 0
+
+def test_single_element_not_found():
+    assert binary_search([5], 3) == -1
+""",
+            solution_code="""\
+def binary_search(arr, target):
+    low, high = 0, len(arr) - 1
+    while low <= high:
+        mid = (low + high) // 2
+        if arr[mid] == target:
+            return mid
+        elif arr[mid] < target:
+            low = mid + 1
+        else:
+            high = mid - 1
+    return -1
+""",
+            expected_tests=7,
+        ),
+
+        TestCase(
+            name="LRU Cache Eviction Bug",
+            category="bug_fix",
+            filename="cache.py",
+            issue=(
+                "The LRU cache does not evict the least recently used item when full. "
+                "After inserting 3 items into a cache with capacity 2, all 3 items "
+                "remain. The cache should only hold the 2 most recently accessed items."
+            ),
+            buggy_code="""\
+class LRUCache:
+    def __init__(self, capacity):
+        self.capacity = capacity
+        self.cache = {}
+        self.order = []
+
+    def get(self, key):
+        if key in self.cache:
+            return self.cache[key]
+        return -1
+
+    def put(self, key, value):
+        if key in self.cache:
+            self.cache[key] = value
+        else:
+            self.cache[key] = value
+            self.order.append(key)
+""",
+            test_code="""\
+from fix import LRUCache
+
+def test_basic_put_get():
+    c = LRUCache(2)
+    c.put("a", 1)
+    c.put("b", 2)
+    assert c.get("a") == 1
+    assert c.get("b") == 2
+
+def test_eviction():
+    c = LRUCache(2)
+    c.put("a", 1)
+    c.put("b", 2)
+    c.put("c", 3)  # should evict "a"
+    assert c.get("a") == -1
+    assert c.get("c") == 3
+
+def test_access_refreshes():
+    c = LRUCache(2)
+    c.put("a", 1)
+    c.put("b", 2)
+    c.get("a")      # refresh "a"
+    c.put("c", 3)   # should evict "b" not "a"
+    assert c.get("a") == 1
+    assert c.get("b") == -1
+
+def test_update_existing():
+    c = LRUCache(2)
+    c.put("a", 1)
+    c.put("a", 10)
+    assert c.get("a") == 10
+
+def test_capacity_one():
+    c = LRUCache(1)
+    c.put("a", 1)
+    c.put("b", 2)
+    assert c.get("a") == -1
+    assert c.get("b") == 2
+""",
+            solution_code="""\
+from collections import OrderedDict
+
+class LRUCache:
+    def __init__(self, capacity):
+        self.capacity = capacity
+        self.cache = OrderedDict()
+
+    def get(self, key):
+        if key in self.cache:
+            self.cache.move_to_end(key)
+            return self.cache[key]
+        return -1
+
+    def put(self, key, value):
+        if key in self.cache:
+            self.cache.move_to_end(key)
+        self.cache[key] = value
+        if len(self.cache) > self.capacity:
+            self.cache.popitem(last=False)
+""",
+            expected_tests=5,
+        ),
+
+        TestCase(
+            name="Flatten Nested List Bug",
+            category="bug_fix",
+            filename="flatten.py",
+            issue=(
+                "flatten([[1, [2, 3]], [4, [5, [6]]]]) returns [1, [2, 3], 4, [5, [6]]] "
+                "instead of [1, 2, 3, 4, 5, 6]. It only flattens one level deep "
+                "instead of recursively flattening all nested lists."
+            ),
+            buggy_code="""\
+def flatten(lst):
+    result = []
+    for item in lst:
+        if isinstance(item, list):
+            result.extend(item)
+        else:
+            result.append(item)
+    return result
+""",
+            test_code="""\
+from fix import flatten
+
+def test_already_flat():
+    assert flatten([1, 2, 3]) == [1, 2, 3]
+
+def test_one_level():
+    assert flatten([[1, 2], [3, 4]]) == [1, 2, 3, 4]
+
+def test_deep_nested():
+    assert flatten([[1, [2, 3]], [4, [5, [6]]]]) == [1, 2, 3, 4, 5, 6]
+
+def test_empty():
+    assert flatten([]) == []
+
+def test_mixed():
+    assert flatten([1, [2, [3]], 4]) == [1, 2, 3, 4]
+
+def test_all_nested():
+    assert flatten([[[1]], [[2]], [[3]]]) == [1, 2, 3]
+""",
+            solution_code="""\
+def flatten(lst):
+    result = []
+    for item in lst:
+        if isinstance(item, list):
+            result.extend(flatten(item))
+        else:
+            result.append(item)
+    return result
+""",
+            expected_tests=6,
+        ),
+
+        TestCase(
+            name="Rate Limiter Time Window",
+            category="implementation",
+            filename="rate_limiter.py",
+            issue=(
+                "Implement a rate limiter. The current implementation counts all calls "
+                "ever made instead of using a sliding time window. After max_calls "
+                "have been made, it blocks forever instead of allowing calls once "
+                "the window has passed."
+            ),
+            buggy_code="""\
+import time
+
+class RateLimiter:
+    def __init__(self, max_calls, period_seconds):
+        self.max_calls = max_calls
+        self.period = period_seconds
+        self.call_count = 0
+
+    def allow(self):
+        if self.call_count < self.max_calls:
+            self.call_count += 1
+            return True
+        return False
+""",
+            test_code="""\
+import time
+from fix import RateLimiter
+
+def test_allows_under_limit():
+    rl = RateLimiter(3, 1.0)
+    assert rl.allow() == True
+    assert rl.allow() == True
+    assert rl.allow() == True
+
+def test_blocks_over_limit():
+    rl = RateLimiter(2, 1.0)
+    assert rl.allow() == True
+    assert rl.allow() == True
+    assert rl.allow() == False
+
+def test_allows_after_window():
+    rl = RateLimiter(1, 0.1)
+    assert rl.allow() == True
+    assert rl.allow() == False
+    time.sleep(0.15)
+    assert rl.allow() == True
+
+def test_sliding_window():
+    rl = RateLimiter(2, 0.2)
+    assert rl.allow() == True
+    time.sleep(0.1)
+    assert rl.allow() == True
+    assert rl.allow() == False
+    time.sleep(0.15)
+    assert rl.allow() == True
+""",
+            solution_code="""\
+import time
+
+class RateLimiter:
+    def __init__(self, max_calls, period_seconds):
+        self.max_calls = max_calls
+        self.period = period_seconds
+        self.calls = []
+
+    def allow(self):
+        now = time.time()
+        self.calls = [t for t in self.calls if now - t < self.period]
+        if len(self.calls) < self.max_calls:
+            self.calls.append(now)
+            return True
+        return False
+""",
+            expected_tests=4,
+        ),
+
+        TestCase(
+            name="Linked List Cycle Detection",
+            category="implementation",
+            filename="linked_list.py",
+            issue=(
+                "Implement Floyd's cycle detection for a linked list. "
+                "The current has_cycle function uses a set to track visited nodes, "
+                "which works but uses O(n) memory. Rewrite it to use O(1) memory "
+                "with the tortoise and hare algorithm."
+            ),
+            buggy_code="""\
+class Node:
+    def __init__(self, val, next=None):
+        self.val = val
+        self.next = next
+
+def has_cycle(head):
+    visited = set()
+    current = head
+    while current:
+        if id(current) in visited:
+            return True
+        visited.add(id(current))
+        current = current.next
+    return False
+""",
+            test_code="""\
+from fix import Node, has_cycle
+
+def test_no_cycle():
+    head = Node(1, Node(2, Node(3)))
+    assert has_cycle(head) == False
+
+def test_with_cycle():
+    a = Node(1)
+    b = Node(2)
+    c = Node(3)
+    a.next = b
+    b.next = c
+    c.next = a
+    assert has_cycle(a) == True
+
+def test_empty():
+    assert has_cycle(None) == False
+
+def test_single_no_cycle():
+    assert has_cycle(Node(1)) == False
+
+def test_single_self_cycle():
+    a = Node(1)
+    a.next = a
+    assert has_cycle(a) == True
+
+def test_uses_constant_memory():
+    # The function should NOT use a set/dict
+    import inspect
+    source = inspect.getsource(has_cycle)
+    assert 'set()' not in source, "Should use O(1) memory, not a set"
+    assert 'dict()' not in source, "Should use O(1) memory, not a dict"
+    assert '{}' not in source, "Should use O(1) memory"
+""",
+            solution_code="""\
+class Node:
+    def __init__(self, val, next=None):
+        self.val = val
+        self.next = next
+
+def has_cycle(head):
+    slow = head
+    fast = head
+    while fast and fast.next:
+        slow = slow.next
+        fast = fast.next.next
+        if slow is fast:
+            return True
+    return False
+""",
+            expected_tests=6,
+        ),
+    ],
+)
+
+
+# ══════════════════════════════════════════════════════════════════════
+# Algorithm Challenges
+# ══════════════════════════════════════════════════════════════════════
+
+ALGORITHMS = TestPack(
+    name="algorithms",
+    description="Classic algorithm problems with edge cases",
+    language="python",
+    cases=[
+        TestCase(
+            name="Two Sum",
+            category="algorithms",
+            filename="two_sum.py",
+            issue=(
+                "Implement two_sum(nums, target) that returns indices of two numbers "
+                "that add up to target. Must run in O(n) time, not O(n^2). "
+                "The current brute force solution is too slow for large inputs."
+            ),
+            buggy_code="""\
+def two_sum(nums, target):
+    for i in range(len(nums)):
+        for j in range(len(nums)):
+            if i != j and nums[i] + nums[j] == target:
+                return [i, j]
+    return []
+""",
+            test_code="""\
+from fix import two_sum
+
+def test_basic():
+    result = two_sum([2, 7, 11, 15], 9)
+    assert sorted(result) == [0, 1]
+
+def test_middle():
+    result = two_sum([3, 2, 4], 6)
+    assert sorted(result) == [1, 2]
+
+def test_negative():
+    result = two_sum([-1, -2, -3, -4, -5], -8)
+    assert sorted(result) == [2, 4]
+
+def test_not_found():
+    assert two_sum([1, 2, 3], 100) == []
+
+def test_uses_hash_map():
+    import inspect
+    source = inspect.getsource(two_sum)
+    has_dict = 'dict' in source or '{}' in source or 'hash' in source.lower()
+    no_nested_loop = source.count('for ') <= 1
+    assert has_dict or no_nested_loop, "Should use O(n) approach with hash map"
+""",
+            solution_code="""\
+def two_sum(nums, target):
+    seen = {}
+    for i, num in enumerate(nums):
+        complement = target - num
+        if complement in seen:
+            return [seen[complement], i]
+        seen[num] = i
+    return []
+""",
+            expected_tests=5,
+        ),
+
+        TestCase(
+            name="Merge Intervals",
+            category="algorithms",
+            filename="intervals.py",
+            issue=(
+                "merge_intervals([[1,3],[2,6],[8,10],[15,18]]) should return "
+                "[[1,6],[8,10],[15,18]] but currently returns the input unchanged. "
+                "The function doesn't actually merge overlapping intervals."
+            ),
+            buggy_code="""\
+def merge_intervals(intervals):
+    if not intervals:
+        return []
+    intervals.sort(key=lambda x: x[0])
+    merged = [intervals[0]]
+    for i in range(1, len(intervals)):
+        merged.append(intervals[i])
+    return merged
+""",
+            test_code="""\
+from fix import merge_intervals
+
+def test_overlapping():
+    assert merge_intervals([[1,3],[2,6],[8,10],[15,18]]) == [[1,6],[8,10],[15,18]]
+
+def test_no_overlap():
+    assert merge_intervals([[1,2],[3,4],[5,6]]) == [[1,2],[3,4],[5,6]]
+
+def test_all_overlap():
+    assert merge_intervals([[1,4],[2,3]]) == [[1,4]]
+
+def test_empty():
+    assert merge_intervals([]) == []
+
+def test_single():
+    assert merge_intervals([[1,5]]) == [[1,5]]
+
+def test_touching():
+    assert merge_intervals([[1,2],[2,3]]) == [[1,3]]
+""",
+            solution_code="""\
+def merge_intervals(intervals):
+    if not intervals:
+        return []
+    intervals.sort(key=lambda x: x[0])
+    merged = [intervals[0]]
+    for start, end in intervals[1:]:
+        if start <= merged[-1][1]:
+            merged[-1][1] = max(merged[-1][1], end)
+        else:
+            merged.append([start, end])
+    return merged
+""",
+            expected_tests=6,
+        ),
+    ],
+)
+
+
+# ══════════════════════════════════════════════════════════════════════
+# All built-in packs
+# ══════════════════════════════════════════════════════════════════════
+
+BUILT_IN_PACKS = [PYTHON_BUGS, ALGORITHMS]
+
+# Total test count
+TOTAL_SWE_TESTS = sum(len(p.cases) for p in BUILT_IN_PACKS)

arbiter/dashboard/frontend/dist/assets/index-1tkxJouQ.css

@@ -0,0 +1 @@
+*,:before,:after{--tw-border-spacing-x: 0;--tw-border-spacing-y: 0;--tw-translate-x: 0;--tw-translate-y: 0;--tw-rotate: 0;--tw-skew-x: 0;--tw-skew-y: 0;--tw-scale-x: 1;--tw-scale-y: 1;--tw-pan-x: ;--tw-pan-y: ;--tw-pinch-zoom: ;--tw-scroll-snap-strictness: proximity;--tw-gradient-from-position: ;--tw-gradient-via-position: ;--tw-gradient-to-position: ;--tw-ordinal: ;--tw-slashed-zero: ;--tw-numeric-figure: ;--tw-numeric-spacing: ;--tw-numeric-fraction: ;--tw-ring-inset: ;--tw-ring-offset-width: 0px;--tw-ring-offset-color: #fff;--tw-ring-color: rgb(59 130 246 / .5);--tw-ring-offset-shadow: 0 0 #0000;--tw-ring-shadow: 0 0 #0000;--tw-shadow: 0 0 #0000;--tw-shadow-colored: 0 0 #0000;--tw-blur: ;--tw-brightness: ;--tw-contrast: ;--tw-grayscale: ;--tw-hue-rotate: ;--tw-invert: ;--tw-saturate: ;--tw-sepia: ;--tw-drop-shadow: ;--tw-backdrop-blur: ;--tw-backdrop-brightness: ;--tw-backdrop-contrast: ;--tw-backdrop-grayscale: ;--tw-backdrop-hue-rotate: ;--tw-backdrop-invert: ;--tw-backdrop-opacity: ;--tw-backdrop-saturate: ;--tw-backdrop-sepia: ;--tw-contain-size: ;--tw-contain-layout: ;--tw-contain-paint: ;--tw-contain-style: }::backdrop{--tw-border-spacing-x: 0;--tw-border-spacing-y: 0;--tw-translate-x: 0;--tw-translate-y: 0;--tw-rotate: 0;--tw-skew-x: 0;--tw-skew-y: 0;--tw-scale-x: 1;--tw-scale-y: 1;--tw-pan-x: ;--tw-pan-y: ;--tw-pinch-zoom: ;--tw-scroll-snap-strictness: proximity;--tw-gradient-from-position: ;--tw-gradient-via-position: ;--tw-gradient-to-position: ;--tw-ordinal: ;--tw-slashed-zero: ;--tw-numeric-figure: ;--tw-numeric-spacing: ;--tw-numeric-fraction: ;--tw-ring-inset: ;--tw-ring-offset-width: 0px;--tw-ring-offset-color: #fff;--tw-ring-color: rgb(59 130 246 / .5);--tw-ring-offset-shadow: 0 0 #0000;--tw-ring-shadow: 0 0 #0000;--tw-shadow: 0 0 #0000;--tw-shadow-colored: 0 0 #0000;--tw-blur: ;--tw-brightness: ;--tw-contrast: ;--tw-grayscale: ;--tw-hue-rotate: ;--tw-invert: ;--tw-saturate: ;--tw-sepia: ;--tw-drop-shadow: ;--tw-backdrop-blur: ;--tw-backdrop-brightness: ;--tw-backdrop-contrast: ;--tw-backdrop-grayscale: ;--tw-backdrop-hue-rotate: ;--tw-backdrop-invert: ;--tw-backdrop-opacity: ;--tw-backdrop-saturate: ;--tw-backdrop-sepia: ;--tw-contain-size: ;--tw-contain-layout: ;--tw-contain-paint: ;--tw-contain-style: }*,:before,:after{box-sizing:border-box;border-width:0;border-style:solid;border-color:#e5e7eb}:before,:after{--tw-content: ""}html,:host{line-height:1.5;-webkit-text-size-adjust:100%;-moz-tab-size:4;-o-tab-size:4;tab-size:4;font-family:ui-sans-serif,system-ui,sans-serif,"Apple Color Emoji","Segoe UI Emoji",Segoe UI Symbol,"Noto Color Emoji";font-feature-settings:normal;font-variation-settings:normal;-webkit-tap-highlight-color:transparent}body{margin:0;line-height:inherit}hr{height:0;color:inherit;border-top-width:1px}abbr:where([title]){-webkit-text-decoration:underline dotted;text-decoration:underline dotted}h1,h2,h3,h4,h5,h6{font-size:inherit;font-weight:inherit}a{color:inherit;text-decoration:inherit}b,strong{font-weight:bolder}code,kbd,samp,pre{font-family:JetBrains Mono,Fira Code,monospace;font-feature-settings:normal;font-variation-settings:normal;font-size:1em}small{font-size:80%}sub,sup{font-size:75%;line-height:0;position:relative;vertical-align:baseline}sub{bottom:-.25em}sup{top:-.5em}table{text-indent:0;border-color:inherit;border-collapse:collapse}button,input,optgroup,select,textarea{font-family:inherit;font-feature-settings:inherit;font-variation-settings:inherit;font-size:100%;font-weight:inherit;line-height:inherit;letter-spacing:inherit;color:inherit;margin:0;padding:0}button,select{text-transform:none}button,input:where([type=button]),input:where([type=reset]),input:where([type=submit]){-webkit-appearance:button;background-color:transparent;background-image:none}:-moz-focusring{outline:auto}:-moz-ui-invalid{box-shadow:none}progress{vertical-align:baseline}::-webkit-inner-spin-button,::-webkit-outer-spin-button{height:auto}[type=search]{-webkit-appearance:textfield;outline-offset:-2px}::-webkit-search-decoration{-webkit-appearance:none}::-webkit-file-upload-button{-webkit-appearance:button;font:inherit}summary{display:list-item}blockquote,dl,dd,h1,h2,h3,h4,h5,h6,hr,figure,p,pre{margin:0}fieldset{margin:0;padding:0}legend{padding:0}ol,ul,menu{list-style:none;margin:0;padding:0}dialog{padding:0}textarea{resize:vertical}input::-moz-placeholder,textarea::-moz-placeholder{opacity:1;color:#9ca3af}input::placeholder,textarea::placeholder{opacity:1;color:#9ca3af}button,[role=button]{cursor:pointer}:disabled{cursor:default}img,svg,video,canvas,audio,iframe,embed,object{display:block;vertical-align:middle}img,video{max-width:100%;height:auto}[hidden]:where(:not([hidden=until-found])){display:none}.pointer-events-none{pointer-events:none}.absolute{position:absolute}.relative{position:relative}.sticky{position:sticky}.inset-0{top:0;right:0;bottom:0;left:0}.inset-y-0{top:0;bottom:0}.left-0{left:0}.right-2{right:.5rem}.right-3{right:.75rem}.top-0{top:0}.top-0\.5{top:.125rem}.top-1\/2{top:50%}.top-2{top:.5rem}.z-10{z-index:10}.z-50{z-index:50}.mx-auto{margin-left:auto;margin-right:auto}.mb-1{margin-bottom:.25rem}.mb-2{margin-bottom:.5rem}.mb-3{margin-bottom:.75rem}.mb-4{margin-bottom:1rem}.mb-5{margin-bottom:1.25rem}.ml-2{margin-left:.5rem}.ml-auto{margin-left:auto}.mt-0\.5{margin-top:.125rem}.mt-1{margin-top:.25rem}.mt-1\.5{margin-top:.375rem}.mt-12{margin-top:3rem}.mt-2{margin-top:.5rem}.mt-2\.5{margin-top:.625rem}.mt-3{margin-top:.75rem}.mt-4{margin-top:1rem}.block{display:block}.flex{display:flex}.inline-flex{display:inline-flex}.table{display:table}.grid{display:grid}.hidden{display:none}.h-1{height:.25rem}.h-1\.5{height:.375rem}.h-10{height:2.5rem}.h-12{height:3rem}.h-14{height:3.5rem}.h-2{height:.5rem}.h-2\.5{height:.625rem}.h-3{height:.75rem}.h-4{height:1rem}.h-6{height:1.5rem}.h-8{height:2rem}.h-9{height:2.25rem}.h-full{height:100%}.max-h-80{max-height:20rem}.min-h-\[400px\]{min-height:400px}.min-h-\[480px\]{min-height:480px}.min-h-screen{min-height:100vh}.w-1\.5{width:.375rem}.w-10{width:2.5rem}.w-12{width:3rem}.w-2{width:.5rem}.w-2\.5{width:.625rem}.w-28{width:7rem}.w-3{width:.75rem}.w-32{width:8rem}.w-4{width:1rem}.w-6{width:1.5rem}.w-7{width:1.75rem}.w-8{width:2rem}.w-9{width:2.25rem}.w-full{width:100%}.max-w-7xl{max-width:80rem}.flex-1{flex:1 1 0%}.shrink-0{flex-shrink:0}.-translate-y-1\/2{--tw-translate-y: -50%;transform:translate(var(--tw-translate-x),var(--tw-translate-y)) rotate(var(--tw-rotate)) skew(var(--tw-skew-x)) skewY(var(--tw-skew-y)) scaleX(var(--tw-scale-x)) scaleY(var(--tw-scale-y))}@keyframes pulse{50%{opacity:.5}}.animate-pulse{animation:pulse 2s cubic-bezier(.4,0,.6,1) infinite}@keyframes spin{to{transform:rotate(360deg)}}.animate-spin{animation:spin 1s linear infinite}.resize-none{resize:none}.grid-cols-1{grid-template-columns:repeat(1,minmax(0,1fr))}.grid-cols-2{grid-template-columns:repeat(2,minmax(0,1fr))}.grid-cols-3{grid-template-columns:repeat(3,minmax(0,1fr))}.grid-cols-5{grid-template-columns:repeat(5,minmax(0,1fr))}.flex-col{flex-direction:column}.flex-wrap{flex-wrap:wrap}.items-start{align-items:flex-start}.items-center{align-items:center}.justify-end{justify-content:flex-end}.justify-center{justify-content:center}.justify-between{justify-content:space-between}.gap-0\.5{gap:.125rem}.gap-1{gap:.25rem}.gap-1\.5{gap:.375rem}.gap-2{gap:.5rem}.gap-2\.5{gap:.625rem}.gap-3{gap:.75rem}.gap-4{gap:1rem}.gap-5{gap:1.25rem}.space-y-1>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(.25rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(.25rem * var(--tw-space-y-reverse))}.space-y-1\.5>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(.375rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(.375rem * var(--tw-space-y-reverse))}.space-y-2>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(.5rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(.5rem * var(--tw-space-y-reverse))}.space-y-3>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(.75rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(.75rem * var(--tw-space-y-reverse))}.space-y-4>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(1rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(1rem * var(--tw-space-y-reverse))}.space-y-5>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(1.25rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(1.25rem * var(--tw-space-y-reverse))}.space-y-6>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(1.5rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(1.5rem * var(--tw-space-y-reverse))}.space-y-8>:not([hidden])~:not([hidden]){--tw-space-y-reverse: 0;margin-top:calc(2rem * calc(1 - var(--tw-space-y-reverse)));margin-bottom:calc(2rem * var(--tw-space-y-reverse))}.overflow-auto{overflow:auto}.overflow-hidden{overflow:hidden}.overflow-x-auto{overflow-x:auto}.truncate{overflow:hidden;text-overflow:ellipsis;white-space:nowrap}.whitespace-pre-line{white-space:pre-line}.whitespace-pre-wrap{white-space:pre-wrap}.rounded{border-radius:.25rem}.rounded-2xl{border-radius:1rem}.rounded-full{border-radius:9999px}.rounded-lg{border-radius:.5rem}.rounded-md{border-radius:.375rem}.rounded-xl{border-radius:.75rem}.border{border-width:1px}.border-2{border-width:2px}.border-y{border-top-width:1px;border-bottom-width:1px}.border-b{border-bottom-width:1px}.border-r{border-right-width:1px}.border-t{border-top-width:1px}.border-\[var\(--border\)\]{border-color:var(--border)}.border-\[var\(--primary\)\]{border-color:var(--primary)}.border-\[var\(--secondary\)\]{border-color:var(--secondary)}.border-emerald-500\/15{border-color:#10b98126}.border-emerald-500\/20{border-color:#10b98133}.border-emerald-500\/30{border-color:#10b9814d}.border-red-500\/20{border-color:#ef444433}.border-white\/\[0\.02\]{border-color:#ffffff05}.border-t-transparent{border-top-color:transparent}.border-opacity-50{--tw-border-opacity: .5}.bg-\[var\(--bg\)\]{background-color:var(--bg)}.bg-\[var\(--primary\)\]{background-color:var(--primary)}.bg-\[var\(--surface\)\]{background-color:var(--surface)}.bg-\[var\(--surface-2\)\]{background-color:var(--surface-2)}.bg-\[var\(--surface-3\)\]{background-color:var(--surface-3)}.bg-amber-400{--tw-bg-opacity: 1;background-color:rgb(251 191 36 / var(--tw-bg-opacity, 1))}.bg-arbiter-bg{--tw-bg-opacity: 1;background-color:rgb(10 10 15 / var(--tw-bg-opacity, 1))}.bg-emerald-400{--tw-bg-opacity: 1;background-color:rgb(52 211 153 / var(--tw-bg-opacity, 1))}.bg-emerald-500\/10{background-color:#10b9811a}.bg-emerald-500\/15{background-color:#10b98126}.bg-emerald-500\/5{background-color:#10b9810d}.bg-red-400{--tw-bg-opacity: 1;background-color:rgb(248 113 113 / var(--tw-bg-opacity, 1))}.bg-white{--tw-bg-opacity: 1;background-color:rgb(255 255 255 / var(--tw-bg-opacity, 1))}.bg-opacity-10{--tw-bg-opacity: .1}.bg-gradient-to-br{background-image:linear-gradient(to bottom right,var(--tw-gradient-stops))}.bg-gradient-to-r{background-image:linear-gradient(to right,var(--tw-gradient-stops))}.from-\[var\(--primary\)\]{--tw-gradient-from: var(--primary) var(--tw-gradient-from-position);--tw-gradient-to: rgb(255 255 255 / 0) var(--tw-gradient-to-position);--tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to)}.from-\[var\(--secondary\)\]{--tw-gradient-from: var(--secondary) var(--tw-gradient-from-position);--tw-gradient-to: rgb(255 255 255 / 0) var(--tw-gradient-to-position);--tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to)}.from-emerald-500\/20{--tw-gradient-from: rgb(16 185 129 / .2) var(--tw-gradient-from-position);--tw-gradient-to: rgb(16 185 129 / 0) var(--tw-gradient-to-position);--tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to)}.via-transparent{--tw-gradient-to: rgb(0 0 0 / 0) var(--tw-gradient-to-position);--tw-gradient-stops: var(--tw-gradient-from), transparent var(--tw-gradient-via-position), var(--tw-gradient-to)}.to-\[var\(--primary\)\]{--tw-gradient-to: var(--primary) var(--tw-gradient-to-position)}.to-\[var\(--secondary\)\]{--tw-gradient-to: var(--secondary) var(--tw-gradient-to-position)}.to-emerald-500\/20{--tw-gradient-to: rgb(16 185 129 / .2) var(--tw-gradient-to-position)}.p-1{padding:.25rem}.p-12{padding:3rem}.p-16{padding:4rem}.p-3{padding:.75rem}.p-4{padding:1rem}.p-6{padding:1.5rem}.p-8{padding:2rem}.px-1\.5{padding-left:.375rem;padding-right:.375rem}.px-2{padding-left:.5rem;padding-right:.5rem}.px-3{padding-left:.75rem;padding-right:.75rem}.px-4{padding-left:1rem;padding-right:1rem}.px-5{padding-left:1.25rem;padding-right:1.25rem}.px-6{padding-left:1.5rem;padding-right:1.5rem}.py-0\.5{padding-top:.125rem;padding-bottom:.125rem}.py-1{padding-top:.25rem;padding-bottom:.25rem}.py-1\.5{padding-top:.375rem;padding-bottom:.375rem}.py-2{padding-top:.5rem;padding-bottom:.5rem}.py-2\.5{padding-top:.625rem;padding-bottom:.625rem}.py-3{padding-top:.75rem;padding-bottom:.75rem}.py-3\.5{padding-top:.875rem;padding-bottom:.875rem}.py-5{padding-top:1.25rem;padding-bottom:1.25rem}.py-6{padding-top:1.5rem;padding-bottom:1.5rem}.py-8{padding-top:2rem;padding-bottom:2rem}.pb-2{padding-bottom:.5rem}.pb-3{padding-bottom:.75rem}.pb-4{padding-bottom:1rem}.pb-5{padding-bottom:1.25rem}.pl-7{padding-left:1.75rem}.pr-4{padding-right:1rem}.pt-2\.5{padding-top:.625rem}.pt-4{padding-top:1rem}.pt-5{padding-top:1.25rem}.text-left{text-align:left}.text-center{text-align:center}.text-right{text-align:right}.font-mono{font-family:JetBrains Mono,Fira Code,monospace}.font-sans{font-family:ui-sans-serif,system-ui,sans-serif,"Apple Color Emoji","Segoe UI Emoji",Segoe UI Symbol,"Noto Color Emoji"}.text-2xl{font-size:1.5rem;line-height:2rem}.text-\[10px\]{font-size:10px}.text-\[11px\]{font-size:11px}.text-\[8px\]{font-size:8px}.text-\[9px\]{font-size:9px}.text-base{font-size:1rem;line-height:1.5rem}.text-lg{font-size:1.125rem;line-height:1.75rem}.text-sm{font-size:.875rem;line-height:1.25rem}.text-xs{font-size:.75rem;line-height:1rem}.font-bold{font-weight:700}.font-medium{font-weight:500}.font-normal{font-weight:400}.font-semibold{font-weight:600}.uppercase{text-transform:uppercase}.capitalize{text-transform:capitalize}.leading-relaxed{line-height:1.625}.tracking-tight{letter-spacing:-.025em}.tracking-wider{letter-spacing:.05em}.tracking-widest{letter-spacing:.1em}.text-\[var\(--primary\)\]{color:var(--primary)}.text-\[var\(--secondary\)\]{color:var(--secondary)}.text-\[var\(--text\)\]{color:var(--text)}.text-\[var\(--text-dim\)\]{color:var(--text-dim)}.text-\[var\(--text-muted\)\]{color:var(--text-muted)}.text-\[var\(--warning\)\]{color:var(--warning)}.text-amber-400{--tw-text-opacity: 1;color:rgb(251 191 36 / var(--tw-text-opacity, 1))}.text-emerald-400{--tw-text-opacity: 1;color:rgb(52 211 153 / var(--tw-text-opacity, 1))}.text-red-400{--tw-text-opacity: 1;color:rgb(248 113 113 / var(--tw-text-opacity, 1))}.text-white{--tw-text-opacity: 1;color:rgb(255 255 255 / var(--tw-text-opacity, 1))}.antialiased{-webkit-font-smoothing:antialiased;-moz-osx-font-smoothing:grayscale}.opacity-50{opacity:.5}.shadow-2xl{--tw-shadow: 0 25px 50px -12px rgb(0 0 0 / .25);--tw-shadow-colored: 0 25px 50px -12px var(--tw-shadow-color);box-shadow:var(--tw-ring-offset-shadow, 0 0 #0000),var(--tw-ring-shadow, 0 0 #0000),var(--tw-shadow)}.shadow-lg{--tw-shadow: 0 10px 15px -3px rgb(0 0 0 / .1), 0 4px 6px -4px rgb(0 0 0 / .1);--tw-shadow-colored: 0 10px 15px -3px var(--tw-shadow-color), 0 4px 6px -4px var(--tw-shadow-color);box-shadow:var(--tw-ring-offset-shadow, 0 0 #0000),var(--tw-ring-shadow, 0 0 #0000),var(--tw-shadow)}.filter{filter:var(--tw-blur) var(--tw-brightness) var(--tw-contrast) var(--tw-grayscale) var(--tw-hue-rotate) var(--tw-invert) var(--tw-saturate) var(--tw-sepia) var(--tw-drop-shadow)}.transition{transition-property:color,background-color,border-color,text-decoration-color,fill,stroke,opacity,box-shadow,transform,filter,backdrop-filter;transition-timing-function:cubic-bezier(.4,0,.2,1);transition-duration:.15s}.transition-all{transition-property:all;transition-timing-function:cubic-bezier(.4,0,.2,1);transition-duration:.15s}.transition-colors{transition-property:color,background-color,border-color,text-decoration-color,fill,stroke;transition-timing-function:cubic-bezier(.4,0,.2,1);transition-duration:.15s}:root{--bg: #06060c;--surface: #0f0f1a;--surface-2: #181828;--surface-3: #222238;--border: #1e1e35;--primary: #00d4ff;--secondary: #7c3aed;--accent: #10b981;--warning: #f59e0b;--error: #ef4444;--text: #e2e2f0;--text-dim: #6b6b8a;--text-muted: #3d3d5c}body{font-family:Inter,system-ui,-apple-system,sans-serif;background:var(--bg);color:var(--text);min-height:100vh;overflow-x:hidden}code,pre,.font-mono{font-family:JetBrains Mono,Fira Code,monospace}::-webkit-scrollbar{width:5px;height:5px}::-webkit-scrollbar-track{background:transparent}::-webkit-scrollbar-thumb{background:var(--border);border-radius:10px}::-webkit-scrollbar-thumb:hover{background:var(--text-muted)}.glass{background:#0f0f1ab3;-webkit-backdrop-filter:blur(12px);backdrop-filter:blur(12px);border:1px solid var(--border)}.glow-primary{box-shadow:0 0 20px #00d4ff26,0 0 40px #00d4ff0d}.glow-accent{box-shadow:0 0 20px #10b98126,0 0 40px #10b9810d}.glow-winner{box-shadow:0 0 30px #10b98133,0 0 60px #10b98114}@keyframes shimmer{0%{background-position:-200% 0}to{background-position:200% 0}}.shimmer{background:linear-gradient(90deg,var(--surface) 25%,var(--surface-2) 50%,var(--surface) 75%);background-size:200% 100%;animation:shimmer 2s ease-in-out infinite}.gradient-text{background:linear-gradient(135deg,var(--primary),var(--secondary));-webkit-background-clip:text;-webkit-text-fill-color:transparent;background-clip:text}.ambient-glow{position:fixed;width:600px;height:600px;border-radius:50%;filter:blur(150px);opacity:.03;pointer-events:none;z-index:0}.placeholder\:text-\[var\(--text-muted\)\]::-moz-placeholder{color:var(--text-muted)}.placeholder\:text-\[var\(--text-muted\)\]::placeholder{color:var(--text-muted)}.first\:text-right:first-child{text-align:right}.last\:border-0:last-child{border-width:0px}.last\:text-right:last-child{text-align:right}.hover\:bg-\[var\(--surface-2\)\]:hover{background-color:var(--surface-2)}.hover\:bg-white\/\[0\.01\]:hover{background-color:#ffffff03}.hover\:bg-white\/\[0\.02\]:hover{background-color:#ffffff05}.hover\:text-\[var\(--text\)\]:hover{color:var(--text)}.hover\:text-\[var\(--text-dim\)\]:hover{color:var(--text-dim)}.hover\:underline:hover{text-decoration-line:underline}.focus\:outline-none:focus{outline:2px solid transparent;outline-offset:2px}.disabled\:cursor-not-allowed:disabled{cursor:not-allowed}.disabled\:opacity-30:disabled{opacity:.3}@media(min-width:640px){.sm\:grid-cols-3{grid-template-columns:repeat(3,minmax(0,1fr))}.sm\:grid-cols-4{grid-template-columns:repeat(4,minmax(0,1fr))}}@media(min-width:1024px){.lg\:grid-cols-2{grid-template-columns:repeat(2,minmax(0,1fr))}.lg\:grid-cols-4{grid-template-columns:repeat(4,minmax(0,1fr))}}