Galaris

Missions and plans

Give an agent a clear deliverable, follow its steps and inspect the result. Tasks retain progress, waiting states and recovery evidence.

Before execution: define the result

Give the mission a deliverable, authorised sources and success criteria. The request becomes a self-contained Task instruction. The Dispatcher selects the supported execution mode; a Planner can turn steps into actual subtasks with dependencies.

Choose direct execution or a plan

Depending on the harness, the Dispatcher selects EXEC, EXEC high or PLAN. One coherent outcome can stay in direct execution even when demanding. A plan suits deliverables that need to be verified and resumed independently, including sequential work.

The internal harness turns steps into real Tasks. Depth and final-task count are configurable: three levels and 200 leaves by default, with no separate cap on the total node count. Each contribution retains its criteria and results.

Process a collection while keeping successful work

For an inventory discovered during the work, a plan can use a progressive collection. Galaris validates a JSON Dataset, freezes its revision and creates a Task for each substantial item in waves respecting plan limits. A collection accepts up to 1,000 items; execution remains sequential.

Progress includes known items awaiting their Task. Retry keeps successful results and the frozen inventory while resuming failed items. An incomplete inventory is reported rather than silently collapsed into one oversized Task.

During execution: understand the state

Inspect routing, execution, waiting, pause and completion in the task list. Open details to see the plan and its progress. A request for clarification needs an answer; waiting for a colleague is different from a failed attempt.

Task history — Agents’ work, dates and actual statuses in the dedicated instance.
Task history — Agents’ work, dates and actual statuses in the dedicated instance.C05
A task’s request and result — Albert’s lesson creation, with the requested objective and final feedback.
A task’s request and result — Albert’s lesson creation, with the requested objective and final feedback.C06

A specialist receives a child task linked to the parent. Its result feeds the parent’s synthesis. Follow responsibilities and waiting states rather than interpreting every tool call as a separate mission.

After execution: inspect the result

Read the output together with sources, tools, costs and events. Decide whether the deliverable meets the request, requires a correction or leaves a decision for a person. A completed model call alone does not prove that a file was delivered.

Execution details — Information and traces from a task actually completed by Albert.
Execution details — Information and traces from a task actually completed by Albert.C07

Recover according to the evidence

Durable state keeps a failed worker from erasing a task. The internal harness journals effects around tool calls. An uncertain external action can block automatic replay; recovery uses the evidence available instead of assuming it never happened.

Recover activity after closing the page

Task details and the chat panel recover the latest attempt, requested or effective pause, waiting state and next retry. New tasks retain the original request, provenance and a preview of progress messages. Late events do not replace terminal results.

The Working Set links inputs, produced files and deliverables. If a file exists but was not sent, delivery recovery can call the authorised transport directly without generating it again.

Bound the resources used

Optional limits cover tokens, cost and time across a task tree. Goal cycles can share consumption. The view distinguishes recorded usage, reservations and estimated remaining budget. Limits govern admission of new phases; a phase already running can exceed its reservation.

Find mission resources

Amend, replace or verify before repeating

A clarification can amend work when the deliverable stays the same. A definition conflict does not create a second Task. An explicit replacement retains the link to the previous Task and waits for evidence of stopping; situations such as an active child or external wait prevent replacement.

A tool error returns to the agent with its outcome: rejected or unknown effect. It can correct the request or verify the effect. Recovery reuses recorded results and errors without making the call again; an uncertain operation does not automatically become safe to replay.

Your original request remains a reference

When a mission is created from a conversation, the server preserves the triggering messages and files. Supplementary context clarifies references and earlier constraints; it does not replace the original instruction with a summary.

Independent work leaves previous missions running or waiting. A rejected amendment does not silently replace a mission or stop unrelated work. Whether a mission can be changed depends on its state and the recovery capabilities of its engine.