Model-facing background job control tools (job_output, job_list, job_kill) over the ctx.jobs registry

Durable workflow-run Conversation Node and nested member disclosure for dsh web

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

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

Race-fenced same-session goal-round driver

Client Tool call-tree renderer and keyed per-tool presentation slot

Zero-dependency bounded-retention primitive: ItemRetainer/TextRetainer + neutral notice helpers (what did we keep, what did we omit)

Code Mode: use LLMs to generate executable code that performs tool calls

Model-facing skill loading tool for the DeepSeek Harness

Web ask_user_question feature: host tool mount plus composer-takeover question UI

CLI tool for Size Limit

Streaming utilities for AI assistants

Shared OpenAI SDK base adapters for TanStack AI providers using Chat Completions and Responses APIs.

Core types and classes for Google services.

Use Ollama with the Vercel AI SDK, implementing the official Ollama API. This provider has minimal dependencies and is web-compatible out of the box.

In-process fork subagent backend: runs a child agent seeded with a prefix of the parent's log

Web skill references and the dedicated skill tool row

The Gateway provider for the [AI SDK](https://ai-sdk.dev/docs) allows the use of a wide variety of AI models and providers.

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

Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.