Missions

Missions pair a durable project plan with native OpenCode conversations. The coordinator plans and delegates; the task tree records dependencies and results. A saved plan, an admitted input and observed execution are different facts.

Create, then explicitly start

1. Open Missions in the right panel and choose Create mission.
2. Fill What should the mission do? and check Title, prefilled from the first sentence (up to 60 characters).
3. Under When, select Once or Every day at. For daily work, verify the displayed time zone; Change allows an IANA zone.
4. Expand Options for Playbook, Notes, Agents and models, Task sessions, saved briefs and optional followed conversations. With Compare two models, the Model A and Model B selectors appear in the main form.
5. Choose Create. Select the new entry, then use its separate ▶ action when ready: Start mission for one-time work, or Play schedule {id} for a daily schedule.

Create never starts work. A one-time mission is prepared; a daily schedule is paused. Neither creation nor saving a brief arms a timer. Creation is scoped to the selected project/Location and freezes the requested profiles and task-session policy. Validation is beside the affected field; a refusal that says nothing was sent leaves the draft available for correction. The coordinator of a one-time mission can also prepare a separate mission for you, such as a follow-up: it appears in the list as Prepared and, like any mission, starts only from its ▶ action.

Playbooks

For Compare two models, both models are required and must differ; a different Thinking level alone is not a different model. Unless you choose one, the judge uses the coordinator's model; the form warns when it matches A or B, which may bias the comparison. The overview shows the verdict, both model names and the scores by criterion.

The playbook guides coordination; it does not bypass native permissions or guarantee success. Answer Exploration's decision questions through CodeNomad's interruption dock so an explicit UI answer is recorded, rather than asking an agent to impersonate approval.

Follow the tree and read results

1. Select the mission title. The leading chevron keeps its list open; the title field opens a temporary picker.
2. Choose Summary (eye) for the central overview, or select a task node for its exact result, brief and evidence.
3. Follow dependency links and Reports; use Open conversation for the coordinator when you need its transcript.
4. Under Needs you, choose Answer to open the requesting actor's conversation and interruption dock.

The graph includes completed and retired work. Retiring a task does not itself stop its conversation. In a one-time mission, the coordinator can separately stop the conversations of a retired task it launched as a native subagent, without touching other tasks. In progress is the mission's lifecycle state, not proof that its coordinator is currently running. Full prose belongs in the central reader, not the panel's task list; Technical details folds identifiers and requested execution information.

Briefings and update requests

The coordinator is instructed to publish a project briefing after its initial plan, after task settlements, when waiting for a human and before the final report. This is an authored assessment, not a live activity counter or guaranteed periodic heartbeat. A notice identifies when the map has changed since the briefing.

Use Request an update below the toolbar for a fresh coordinator assessment, then read Summary. Update requested… means the request is pending, not answered. Delivery unconfirmed does not authorize automatic resending: open the coordinator conversation before making a separate new request. This is an ordinary native input, not a read-only sandbox; the coordinator retains its normal permissions.

Profiles, delegation and depth

1. Use the Missions gear or Settings → Missions to edit New mission defaults.
2. Under Apply to, choose All missions or one playbook, then set Task sessions and, under Agents and models, one row per role (coordinator, then the playbook's roles). Each choice is saved immediately; there is no Save button.
3. In a playbook scope, rows show the global values marked Global. Changing a field customizes that role starting from them; its revert icon uses the global values again. Reset (after confirmation) clears only the agents and models of the shown scope.
4. In creation, use Options → Agents and models for specific requested profiles; Use saved defaults restores the saved ones.
5. For native recursion limits, edit Subsession nesting depth → Depth override for the project. Pressing Enter or leaving the field saves a changed valid value; Inherit saves at once; Escape discards an unsaved value.

Native default and Global are different: the former requests OpenCode's own defaults, the latter inherits the global choice; choosing native defaults in a playbook scope remains an explicit exception. Catalog availability is checked; a requested profile is not proof of the profile a conversation currently uses. Native permissions and configured depth still govern internal helper calls in either task mode.

A refused or unconfirmed choice is never resent: the stored values are shown again, and Reload appears only when they cannot be read. If a depth change is unconfirmed, your value is kept; use Refresh project depth before another change. Do not interpret OpenCode effective depth unknown as zero or disabled.

Reuse a saved brief

1. In creation, expand Options → Start from a brief and select the saved brief.
2. Review the copied objective, notes, playbook, profiles and delegation before Create.
3. Use Save as brief to name a reusable draft. A selected one-time mission, including a finished one, also offers Save as brief.

Briefs store instructions and requested choices, not task plans, results, conversations, schedule clocks or execution authority. Loading one fills an ordinary creation draft; it does not start or schedule anything. Removing a brief keeps existing missions/conversations. Settings → Missions → Saved briefs manages the library; if the library becomes unreadable, Reset the saved library (after confirmation) removes saved briefs, not executions. Schedules themselves have no save-as-brief action.

Daily time, catch-up and followed conversations

Daily schedules use the saved IANA time zone and civil time, not an elapsed 24-hour interval. Times are shown in the schedule's zone, labelled when different from the viewer's. Each run gets its own coordinator and isolated mission map; the selected schedule shows the current task tree and date/outcome history. Select a past run to read it centrally. History is bounded to 30 results.

Creation time also bounds eligible daily work; starting a new schedule is not permission to process dates before it existed. Run now starts a separate manual run when offered; it does not replace the daily clock or bypass a pending run. A displayed next time is a projection, not a guarantee of exact-time execution.

Followed conversations (optional) adds bounded context from chosen conversations. Only a completed run advances their processed-message cursors; a failed/interrupted run does not silently consume that context. If instructions plus context exceed capacity, shorten instructions or remove followed conversations rather than assuming unlimited history is read.

Lifetime and service restarts

After a restart, inspect the pending run and choose Resume when ready. Resume reconciles the existing run without sending its coordinator input twice; it does not promise continuation of an interrupted native turn. A turn cut off by restart can settle as ended without a report, with Interrupted by a restart. Do not use restarting as a way to retry tool side effects.

Missions work with the desktop apps and with a standalone CodeNomad server. When the panel shows Mission Control is unavailable, its message names the cause:

Pause, Stop and uncertain outcomes

1. Select the entry and inspect its current state and conversation before acting.
2. Use the pause icon for a resumable hold, or the stop icon and confirmation for a terminal stop. One-time tooltips are Pause mission and Stop mission permanently; schedule tooltips name the schedule.
3. If the result is unconfirmed, use Check status / Check control status to read the existing outcome. Do not issue a replacement action to bypass uncertainty.
4. For one-time actions, the header's Refresh and resend the unconfirmed action first checks state and resends only that still-unconfirmed exact action from your explicit click.

One-time Pause interrupts the mission's native family and parks coordination; Stop also cancels queued family inputs/deliveries and is terminal. These are bounded operations: Some sub-agents may still be running. means the stop is incomplete. Inspect the retained result and use its explicit retry rather than assuming all shell/tool effects were cancelled. Resume tells the coordinator about interrupted descendants; it must decide how to continue the work.

Daily Pause/Stop cancel scheduling and request interruption of registered root actors, including the coordinator and independent specialists, but do not prove that those conversations or their descendants have stopped. Inspect the native families. Stop is terminal: a stopped schedule cannot Play, Resume or Run now. Check passage reconciles a pending run without sending it again. Transient scheduled-check failures display their last failure and retry automatically; a lost user-control reply does not cause automatic control resending.

For a one-time coordinator that is idle without its report, the primary ▶ action can verify and recover it; tasks have targeted missing-report recovery when eligible. Recovery checks native activity, descendants and waits first; unknown activity refuses admission. It does not replay assignments or replace the plan. Open conversations to resolve outstanding questions, permissions, shells or background work.

If Create is unconfirmed, the window retains the submitted request and disables further creation for that project; worktree deletion can remain held. Refresh only reads state. Closing/reopening the editor does not repair it. Before reloading the window, inspect the mission list: reload clears the local lock, not proof that creation failed. Do not blindly create a duplicate after a reload or restart.

Edit, delete and clean up conversations

Use Edit selected mission on an editable one-time mission; on a conflict, close/reopen the editor to load the current revision rather than overwrite it. Daily schedules do not offer edit/delete controls.

1. For a one-time mission you no longer need, choose Delete selected mission… and review the confirmation.
2. Optionally select Also delete specialist conversations created for this mission before confirming.
3. Check Conversation cleanup for removed/kept/pending counts. Retry only the remaining recorded cleanup if offered.

Deleting a mission is not the same as stopping it; use Stop and inspect remaining work first. Coordinators and reused conversations are kept. Shared, moved, child-bearing or unverifiably owned specialists may also be retained. Partial cleanup is not rolled back and is not silently completed in the background. Completed cleanup history remains available in the overview reader.

See Permissions, Conversations and OpenCode setup for native work and service controls.