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
fix(agent): use Opus 4.6/4.5 computer-use beta (#1090)
asaf-genie3030c46b17b5
diff --git a/.github/workflows/ci-test-models.yml b/.github/workflows/ci-test-models.ymlindex 36898140a1..45d577ffaf 100644--- a/.github/workflows/ci-test-models.yml+++ b/.github/workflows/ci-test-models.yml@@ -25,8 +25,11 @@ jobs:matrix:model:# Claude Sonnet/Haiku+ - anthropic/claude-sonnet-4-6- anthropic/claude-sonnet-4-5-20250929- anthropic/claude-haiku-4-5-20251001+ - anthropic/claude-opus-4-6+ - anthropic/claude-opus-4-5-20251101- anthropic/claude-opus-4-1-20250805# OpenAI CU Previewdiff --git a/libs/python/agent/agent/loops/anthropic.py b/libs/python/agent/agent/loops/anthropic.pyindex 4da1f77f05..9f532c04e1 100644--- a/libs/python/agent/agent/loops/anthropic.py+++ b/libs/python/agent/agent/loops/anthropic.py@@ -34,6 +34,12 @@ from ..types import AgentCapability, AgentResponse, Messages, Tools# Model version mapping to tool version and beta flagMODEL_TOOL_MAPPING = [+ # Claude Opus 4.6/4.5 and Sonnet 4.6 require the 2025-11-24 computer-use beta+ {+ "pattern": r"claude-opus-4-6|claude-opus-4-5|claude-sonnet-4-6",+ "tool_version": "computer_20251124",+ "beta_flag": "computer-use-2025-11-24",+ },# Claude 4 models{"pattern": r"claude-4|claude-opus-4|claude-sonnet-4|claude-haiku-4",