Google Antigravity Python SDK — v0.1.13 Release Notes

[NTaylorMullen]

This release introduces pre-tool argument modification capabilities in lifecycle hooks, adds native support for synchronous hook functions, and establishes structured command execution configuration with configurable execution timeouts. It also improves tool execution observability with step correlation IDs, and enhances connection resilience during client disconnects.

🌟 Key Highlights

🚀 Bringing Antigravity SDK powered agents to IntelliJ and Zed IDEs..

1. Antigravity in your IDE: Antigravity SDK powers IDE Extensions available across the Jetbrains family of IDEs and Zed. Use it for high-performance, agentic editing within your native workflow. 
   • IntelliJ - Open Jetbrains AI > Settings > Agents > Search for Antigravity > Click install
   • Zed - Ctrl/Cmd+Shift+P > agent: open settings > External Agents > Add > Install from Registry > Search for Antigravity > Click install 
   • How to get started: https://antigravity.google/blog/antigravity-ide-extensions

• Pre-Tool Hook Argument Modification: Pre-tool lifecycle hooks can now sanitize, transform, or override tool input arguments before tool execution begins.

  @pre_tool
  def sanitize_args(event: PreToolHookEvent) -> PreToolHookDecision:
      return PreToolHookDecision(allow=True, modified_args={"query": event.args["query"].strip()})

• Synchronous Hook Function Support: Lifecycle hook decorators now accept standard synchronous functions alongside asynchronous coroutines without raising runtime await errors.

  @pre_turn
  def log_turn(event: PreTurnHookEvent) -> None:
      print(f"Executing turn for session: {event.session_id}")

• Structured Command Execution Configuration: Command execution settings are now consolidated under RunCommandConfig, introducing configurable timeouts that default to 10 minutes (600 seconds) alongside daemon execution controls.

  capabilities = CapabilitiesConfig(
      run_command_config=RunCommandConfig(timeout_seconds=300, enable_daemons=True)
  )

• Tool Lifecycle Step Correlation: ToolResult and ToolExecutionError event payloads now include step_id, enabling end-to-end tracking and correlation of tool invocations across trajectory steps.

  @post_tool
  def trace_tool_execution(event: ToolResult) -> None:
      print(f"Step {event.step_id}: {event.tool_name} returned {event.result}")

---

📋 Detailed Changes

Features & Enhancements

• Pre-Tool Hook Argument Modification: Added the ability for @pre_tool hooks to return updated tool arguments that are sequentially chained across registered hooks prior to tool execution.
• Tool Step Correlation: Added step_id to ToolResult and ToolExecutionError hook event models, allowing developers to correlate tool completions and failures with their originating tool call step.
• VS Code Debugging Configuration: Updated setup_vscode_debugging.sh to target the canonical getting_started/hello_world starter example and explicitly configure Gemini Developer API defaults.

Model & Default Changes

• Command Timeout and Daemon Configuration: CapabilitiesConfig now has a RunCommandConfig allowing configuration of execution timeouts and daemon commands. Timeouts default to 10 minutes (600 seconds) to prevent unresponsive command tasks. Run commands can have daemons enabled via a boolean flag..

Bug Fixes

• Synchronous Hook Decorator Execution: Fixed a runtime TypeError when decorating synchronous functions with @pre_turn, @post_tool_call, and other lifecycle hooks by verifying awaitability before awaiting hook responses.
• LiteRT Early Client Disconnects: Suppressed unhandled ConnectionResetError, ConnectionAbortedError, and BrokenPipeError exceptions when clients disconnect early from local LiteRT server connections.