SolarOS

SolarOS 4.17.7 manual · app

agent

Native Responses/Chat-Completions LLM client and SolarOS agent control plane. It streams model text directly to the active shell and exposes typed system-status, storage-listing, job-listing, display-discovery, and optional Python/Lua execution tools. agent tools shows risk, policy, and runtime availability.

Configure the full endpoint and model, then ask a question:

agent config endpoint https://api.openai.com/v1/responses
agent config model gpt-model
agent config key api-key
agent config reasoning medium
agent config tools confirm
agent config max-tools 16
agent
job start speechd /voices/en-US
agent --tts
agent list
agent resume SLOT
agent ask How much memory is free on this device?
agent script python -c "print(6 * 7)"
agent script lua /script.lua argument

Bare agent and agent new open a new foreground prompt loop. Completed turns are saved, and agent list plus agent resume SLOT restore a selected transcript after leaving the app or rebooting. agent delete SLOT removes one conversation without changing provider credentials. Responses uses its saved provider continuation ID; Chat Completions uses bounded local history. Slots are 1 to 3 on internal flash or 1 to 8 on SD; the oldest is reused when full. agent ask performs one unsaved request but likewise waits for Esc or the app-exit key after completion, so display-shell output is not immediately replaced by the shell screen.

agent --tts, agent --tts new, agent --tts resume SLOT, and agent --tts ask PROMPT keep the written answer and also queue the successful final model response through the running local PicoTTS speechd. Start speechd with a voice directory first. Status and retry messages, tool calls, tool results, confirmations, and intermediate text before a tool call are not spoken.

Use agent config key clear for an endpoint that does not require bearer authentication. agent status shows configuration, request counters, HTTP status, reasoning effort, duration, traffic, and internal-RAM/PSRAM measurements from the last request. The API key itself is never printed. A Chat-Completions-compatible endpoint can still be configured explicitly.

The agent allows 16 tool calls per request by default. Set a limit from 1 to 32 with agent config max-tools COUNT. When the budget is used, it gives a final answer from the results already collected. Answers are limited to 16 KiB.

agent script supports Python or Lua with a 30-second deadline and up to 4095 output bytes. Model-generated scripts are limited to 640 source bytes and 383 output bytes. Esc or the app-exit key cancels execution.

The storage registry includes bounded listing, sensitive text-file reads, and text-file replacement. Reads and writes are capped at 3072 bytes and paths below .ssh are unavailable to protect SSH identity files.

The default confirm policy runs read-only tools automatically and shows the exact arguments of sensitive, mutating, disruptive, and script calls before waiting for a local y/N decision. off disables tools, readonly excludes all protected risk classes, and explicit all allows every available tool without prompting. See Native Agent Service for the provider contract and current limits.

Controls: