Modules
Typed LLM provider abstraction built on top of req_llm.
Translates between Planck's types and req_llm's call interface.
Converts model configuration into Planck.AI.Model structs.
Everything sent to the LLM in a single request: system prompt, conversation history, and available tools.
A single conversation turn with a role and a list of typed content parts.
Represents an LLM model and its metadata.
Behaviour for modules that supply a list of Planck.AI.Model structs.
Model catalog for Anthropic's Claude family, sourced from LLMDB.
Model catalog for Google's Gemini family, sourced from LLMDB.
Factory for llama.cpp models via its OpenAI-compatible HTTP server.
Factory for Ollama models via its OpenAI-compatible HTTP server.
Model catalog for OpenAI's GPT family, sourced from LLMDB.
Behaviour wrapping the req_llm streaming call.
Streaming event types and normalization from req_llm chunks.
Defines a tool that can be called by the model during a conversation.