Keyboard shortcuts

Press ← or → to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Core concepts

The vocabulary for how Veyyon runs: sessions, permissions, and the boundary between the harness and the model provider. For commands see Using Veyyon; for feature guides see Features.

Pages

The CLI is veyyon. It calls a configured model endpoint with your credentials and runs a tool loop: read, edit, verify, stop.

PageWhat it defines
Sessions, turns, and threadsThe runtime units. A session is the persisted run, a turn is one request plus the agent loop, and a thread is the active path through the session tree.
Permission modelThe approval-mode boundary. tools.approvalMode (plan, ask, ask-command, auto, yolo) sets which tool tiers run automatically and when Veyyon prompts you first. There is no operating-system command sandbox.
Model contractThe bring-your-own-key boundary: endpoint, model, and key. The split between harness and provider responsibilities, Freeform versus Function tools, and how system prompts and tool schemas are presented.

Foundations that pair with these pages

How the pieces fit

  you ──► veyyon (TUI or a one-shot prompt)
            │
            ├─ session / thread / turn   (concepts/sessions-turns-threads)
            ├─ approval mode             (concepts/permission-model)
            └─ model call                (concepts/model-contract)
                  │
                  ├─ system prompt + tool schemas (harness)
                  ├─ endpoint + key               (your provider)
                  └─ model id                     (discovered or pinned)

Changing providers changes the endpoint, the credentials, and the model id. Tool repair, edit verification, approvals, and context compaction stay the same, because they are harness behavior. See Configuring providers and Models and providers.

  • Permission model and Approvals cover the approval modes.
  • The default auto runs every tier; the per-tool policies, the working-directory boundary, credential use, and a tool’s own critical commands still prompt. A headless run has no terminal to answer a prompt, so under a rung that prompts, a tool call fails instead of pausing.
  • Non-interactive mode covers scripted veyyon launch patterns.