Enables main agents to delegate memory retrieval, web research, and multi-step tasks to internal sub-agents, returning concise conclusions while keeping detailed tool calls and raw content out of the main context.
Implements Chain of Thought methodology for extended sequential thinking on complex reasoning tasks. Enables AI clients to break down and solve problems that require deep, step-by-step logical analysis.
Adds a deep_reasoning tool that consults stronger reasoning models (e.g., DeepSeek R1) to produce full reasoning traces for complex problems, helping the agent shape and cross-check its answers.
Provides a 'think' tool that allows Claude and other LLMs to add dedicated thinking steps during complex tool use scenarios, creating space for structured reasoning and improving problem-solving capabilities.