Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
Change --task-id to --variant-id
Dillon DuPont384c7ec5e197
diff --git a/docs/content/docs/cuabench/guide/advanced/creating-private-tasks.mdx b/docs/content/docs/cuabench/guide/advanced/creating-private-tasks.mdxindex 7cd4780318..c614fa1726 100644--- a/docs/content/docs/cuabench/guide/advanced/creating-private-tasks.mdx+++ b/docs/content/docs/cuabench/guide/advanced/creating-private-tasks.mdx@@ -113,7 +113,7 @@ if __name__ == "__main__":cb interact tasks/my_custom_task# Run specific task variant-cb interact tasks/my_custom_task --task-id 0+cb interact tasks/my_custom_task --variant-id 0# Run oracle solutioncb interact tasks/my_custom_task --oraclediff --git a/docs/content/docs/cuabench/guide/examples/genai-task-generation.mdx b/docs/content/docs/cuabench/guide/examples/genai-task-generation.mdxindex a173aec9e8..373cc017ff 100644--- a/docs/content/docs/cuabench/guide/examples/genai-task-generation.mdx+++ b/docs/content/docs/cuabench/guide/examples/genai-task-generation.mdx@@ -219,7 +219,7 @@ async def solve(task_cfg: cb.Task, session: cb.DesktopSession):### Run Interactively```bash-cb interact tasks/color-picker-env --task-id 0+cb interact tasks/color-picker-env --variant-id 0```Try clicking different colors and see how the UI responds.@@ -238,7 +238,7 @@ cb interact tasks/color-picker-env --oracle --no-wait### Run with Agent```bash-cb interact tasks/color-picker-env --task-id 0+cb interact tasks/color-picker-env --variant-id 0# Agent will be prompted interactively```@@ -363,14 +363,14 @@ cb task generate "Create a calculator"cb task generate "Create a simple quiz with 3 multiple choice questions about Python"# 2. Test interactively-cb interact tasks/python-quiz-env --task-id 0+cb interact tasks/python-quiz-env --variant-id 0# 3. Verify oracle workscb interact tasks/python-quiz-env --oracle --no-wait# On headless servers: xvfb-run -a cb interact tasks/python-quiz-env --oracle --no-wait# 4. Test with agent-cb interact tasks/python-quiz-env --task-id 0+cb interact tasks/python-quiz-env --variant-id 0# 5. Manually refine if needed# Edit tasks/python-quiz-env/main.pydiff --git a/docs/content/docs/cuabench/guide/examples/universal-task.mdx b/docs/content/docs/cuabench/guide/examples/universal-task.mdxindex 3839bb1dcd..1d603cc7f8 100644--- a/docs/content/docs/cuabench/guide/examples/universal-task.mdx+++ b/docs/content/docs/cuabench/guide/examples/universal-task.mdx@@ -355,7 +355,7 @@ Create `gui/index.html` with the Minesweeper game:### Preview Interactively```bash-cb interact tasks/minesweeper --task-id 0+cb interact tasks/minesweeper --variant-id 0```A browser window will open showing the Minesweeper game in a simulated desktop environment.@@ -363,7 +363,7 @@ A browser window will open showing the Minesweeper game in a simulated desktop e### Run with Oracle```bash-cb interact tasks/minesweeper --oracle --task-id 0+cb interact tasks/minesweeper --oracle --variant-id 0```### Run with Agentdiff --git a/docs/content/docs/cuabench/guide/fundamentals/simulated-desktop.mdx b/docs/content/docs/cuabench/guide/fundamentals/simulated-desktop.mdxindex 017af20e0d..bd72227f85 100644--- a/docs/content/docs/cuabench/guide/fundamentals/simulated-desktop.mdx+++ b/docs/content/docs/cuabench/guide/fundamentals/simulated-desktop.mdx@@ -44,7 +44,7 @@ def load():Then preview:```bash-cb interact tasks/my_task --task-id 0+cb interact tasks/my_task --variant-id 0```## Multiple Theme Variantsdiff --git a/docs/content/docs/cuabench/guide/fundamentals/tasks.mdx b/docs/content/docs/cuabench/guide/fundamentals/tasks.mdxindex f0f64e4112..1b17fce318 100644--- a/docs/content/docs/cuabench/guide/fundamentals/tasks.mdx+++ b/docs/content/docs/cuabench/guide/fundamentals/tasks.mdx@@ -210,7 +210,7 @@ def start(task_cfg: cb.Task, env: cb.DesktopSession | cb.MobileSession):```bash# Run interactively-cb interact tasks/my_task --task-id 0+cb interact tasks/my_task --variant-id 0# Run evaluationscb run task tasks/my_task --model anthropic/claude-opus-4-5 --agent cua-agentdiff --git a/docs/content/docs/cuabench/guide/fundamentals/universal-gui.mdx b/docs/content/docs/cuabench/guide/fundamentals/universal-gui.mdxindex 86a8e9a91c..4742359ecf 100644--- a/docs/content/docs/cuabench/guide/fundamentals/universal-gui.mdx+++ b/docs/content/docs/cuabench/guide/fundamentals/universal-gui.mdx@@ -61,7 +61,7 @@ computer={Then preview with:```bash-cb interact tasks/my_game --task-id 0+cb interact tasks/my_game --variant-id 0```The [Simulated Desktop](/cuabench/guide/fundamentals/simulated-desktop) renders your GUI in a themed desktop environment (Linux/Windows/macOS) without requiring Docker.diff --git a/docs/content/docs/cuabench/reference/cli-reference.mdx b/docs/content/docs/cuabench/reference/cli-reference.mdxindex fee3f20485..62f2592628 100644--- a/docs/content/docs/cuabench/reference/cli-reference.mdx+++ b/docs/content/docs/cuabench/reference/cli-reference.mdx@@ -201,7 +201,7 @@ cb interact <task> [options]| Option | Description ||--------|-------------|-| `--task-id <id>` | Task ID to run (default: 0) |+| `--variant-id <id>` | Task variant index (default: 0) || `--dataset <name>` | Dataset name to resolve task from registry || `--dataset-path <path>` | Path to dataset directory containing multiple tasks || `--oracle` | Run the solution after setup |