internal/

Package agent provides the agent runner for executing LLM interactions.

Package benchmark provides benchmarking infrastructure for testing LLM tool usage.

Package inbox is the one place a turn picks up anything that arrives while it is running: a line you type, a file dropped in the session's inbox directory by "kvit-coder steer", or an event from a background process.

Package markdown renders the final assistant answer as styled terminal output.

Package mcp implements a Model Context Protocol (MCP) client for kvit-coder.

Package permissions decides whether a shell command may run, from what the command actually is rather than from what its text looks like.

Package procs runs commands that outlive the turn's iterations.

Package prompt provides system prompt generation for the agent.

Package repl provides the exec mode runner for the agent.

Package report holds the structured end-of-turn report: its shape, the checks it must pass before the agent accepts it, and the rendering the agent and the interactive front end both draw it with.

Package session stores a conversation and everything else that outlives one turn: the checkpoint repository, spilled tool output, the steering inbox and the record of background processes.

Package stats provides statistics tracking for agent operations.

Package tui provides the interactive terminal UI for kvit-coder-ui.

Package workspace provides workspace-level utilities including locking.