Detect if code is running in an AI agent or automated development environment

Model-facing filesystem tools (read, write, edit) over the DeepSeek Harness filesystem seam (ctx.fs)

The **[Groq provider](https://ai-sdk.dev/providers/ai-sdk-providers/groq)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Groq chat and completion APIs, transcription support, and browser search tool.

Model-facing fresh-agent Ralph loop over the workflow and subagent seams

Replay-safe model-free head/middle/tail pruning for tool-result surface nodes

Generic bash tool for AI agents, compatible with AI SDK

Model-facing ask_user_question tool over the ctx.userInteraction seam

Tool-call timeout policy: a tools/execute wrapper that arms a per-tool deadline on exec.signal and returns TOOL_TIMEOUT when it wins

Unified LLM API with automatic model discovery and provider configuration

Globally named send_message, interrupt_agent, and list_agents tools over ctx.subagents continuations

Sandbox-consuming implementation of the DeepSeek Harness PowerShell executor seam (confines every command via ctx.sandbox, reports denial/enforcement result facts)

Model-facing workflow tool: run a JavaScript orchestration script over ctx.workflows

Model-facing subagent delegation tool over the ctx.subagents seam

Token-meter-driven compaction policy and LLM summarization backend for the DeepSeek Harness

Model-facing pwsh tool over the bash executor seam

Repeat-tool-call guard plugin: advisory reminders when an agent loops on identical tool calls

MCP client bridge: connects to MCP servers and registers their tools on ctx.tools

Model-facing bash tool with optional generic background-task and sandbox-escalation support

Model-facing todo_write tool over the DeepSeek Harness event-sourced session log

Core types and classes for Google services.