Starts a local opencode server if needed (or attaches to a running one) and reports its version and the current settings.

Lists the agents configured in opencode with their mode and description, for use as the 'agent' parameter of a dispatch.

Lists the providers and models configured in opencode as 'provider/model' IDs. Use 'filter' to narrow the list. Never returns API keys.

Persists which model, agent and permission mode future opencode tasks use. Every field is optional; only the fields you pass are changed.

Creates a temporary opencode session and hands it the task. Returns IMMEDIATELY with a runId, without waiting for the result. Afterwards call 'opencode_wait' with the runId until the run is finished. The task must be described completely and self-contained, because the session knows nothing about this conversation.

Sends a follow-up instruction into the session of an earlier run, so the subagent keeps everything it already worked out. Requires that the earlier run was dispatched with keepSession: true. Returns a new runId to wait on.

Waits up to 'maxSeconds' for a run to finish. If it is done, the full result comes back. If it is still running, a progress report comes back — then simply call again. Never blocks indefinitely, and never shortens the run itself: the task keeps going between calls no matter how long it takes. Returns the moment opencode reports the session idle — there is no polling delay. While waiting it emits notifications/progress with the live tool activity, so a client that sets resetTimeoutOnProgress can raise maxSeconds well past its own default timeout. Pass 'runIds' instead of 'runId' to wait for whichever of several parallel runs finishes first.

Answers the question a run is parked on. Only reachable when autoAnswerQuestions is disabled in the configuration; otherwise questions are rejected automatically so a headless run can never hang. 'answers' holds one array of chosen labels per question, in order.

Returns the complete conversation of a run's session — every message with its tool calls. Use this to audit what the subagent actually did when the summary is not enough.

Returns the actual patch per file for a run, not just the file names. Relies on opencode's workspace snapshots, so it is empty outside a git repository — opencode_result still lists the touched files in that case.

Returns the subagent's own todo list for a run — the most informative view of a long task while it is still working.

Returns the current state of a run immediately, without waiting.

Returns the final result of a finished run (reply text, changed files, cost).

Aborts a running opencode run and cleans up the temporary session.

Lists every run of this MCP session with its status and duration.