> ## Documentation Index
> Fetch the complete documentation index at: https://agents.concierca.ch/llms.txt
> Use this file to discover all available pages before exploring further.

# Running & Approvals

> Starting runs, the one-active-run rule, the live view, pause/resume/cancel, the credit budget, and human approval steps.

A **run** is one execution of a mission from the first step to the last. This page covers how to start one, watch it, control it, keep it within budget, and answer the human approval gates it hits along the way.

## Starting a run

Click **Run** on the mission page. To start a run you need write access — you must be the mission's **owner** or a **lead** — and the mission must be **active** (not paused or archived).

<Warning>
  **Only one run can be active per mission at a time.** If a run is already running, paused, or waiting for a human, you can't start a second one — resume or finish the current one first. This is what keeps a mission's history a clean, single timeline.
</Warning>

## The run lifecycle

A run moves through a small set of statuses:

| Status             | Meaning                                                                         |
| ------------------ | ------------------------------------------------------------------------------- |
| **running**        | A step is executing right now.                                                  |
| **paused**         | You paused it. Reversible — resume to continue.                                 |
| **awaiting human** | Blocked on a human approval step, or parked because the budget cap was reached. |
| **success**        | Every step finished successfully.                                               |
| **failed**         | A step failed and the flow stopped.                                             |
| **canceled**       | You canceled it. Terminal.                                                      |

## The live view

**Runs › Live** is the real-time picture of the current run: which step is running or waiting for a human, how many steps are done, and a **credit-budget bar**. Two controls sit here:

* **Stop after current step** — a graceful stop; the running step finishes, then the run halts.
* **Cancel now** — an immediate stop. The step in flight may already have had side effects (an email sent, a record written), so use it knowingly.

Past runs live under **Runs › History**, with a per-step **Trace** (prompt, answer, attempts, cost), the assembled **Prompt**, **Tool calls**, **Logs**, an **Evaluation**, and a per-step **Cost** table. Files produced by runs are collected under **Runs › Artifacts**.

## Pause, resume, cancel

| Action     | Effect                                                                                                                                  |
| ---------- | --------------------------------------------------------------------------------------------------------------------------------------- |
| **Pause**  | Stops the run and blocks new runs. **Reversible.**                                                                                      |
| **Resume** | Continues the run. It always picks up from the **first unfinished step** — resuming is idempotent, so nothing already done is repeated. |
| **Cancel** | Ends the run for good. **Terminal** — a canceled run cannot be resumed.                                                                 |

<Note>
  **Resume is safe to press.** Because it continues from the first non-success step, resuming a paused or interrupted run never re-runs completed work.
</Note>

## The credit budget

Each **agent step costs exactly 1 credit**. A mission can set a **credit budget per run** (in [Settings › Budgets](/guide/mission-triggers)) — the most credits a single run may spend.

When the *next* agent step would push the run over its budget, the run doesn't quietly overspend. It **parks as `awaiting_human`** with a budget-exceeded status and waits.

<Steps>
  <Step title="A run hits its cap">
    The next agent step would exceed the budget, so the run parks instead of running it.
  </Step>

  <Step title="You're asked to raise the budget">
    The mission's **Overview** shows the parked run with an **Increase budget** action.
  </Step>

  <Step title="Add credits and continue">
    Raise the budget and the run resumes from where it parked — no work is lost.
  </Step>
</Steps>

## Human approval steps

A **human** step pauses the run and asks a person to decide before it can move on. It creates an **approval token valid for 7 days** and blocks until someone responds.

Where approvals show up:

* **In-app — always.** They appear in the mission's **Approvals** tab and in the approver's inbox.
* **Telegram — optional.** If configured, the request is pushed to Telegram with real **Approve** and **Reject** buttons.

The decisions available on an approval:

| Decision           | What it does                                              |
| ------------------ | --------------------------------------------------------- |
| **Approve**        | Let the run advance.                                      |
| **Reject**         | Send it back — typically to an earlier step to be redone. |
| **Delegate**       | Hand the decision to another member.                      |
| **Return to step** | Loop the run back to a specific earlier step with a note. |

Who may decide: the step's **designated approver**, the mission **owner**, or a **lead**.

<Warning>
  **Never approve on the AI's behalf.** A human gate exists precisely so a person makes the call. Approvals are recorded in the audit trail against whoever decided.
</Warning>

### How a rejection loops back

Rejecting (or returning to a step) doesn't end the mission — it sends the run **back to an earlier step** to try again. That loop is bounded by the same safety cap as automatic loopbacks: after **3 iterations** it stops going in circles and **auto-escalates to the owner** as a human step, so a person decides what happens next rather than the mission retrying forever.

<Note>
  Resolving approvals from an AI client uses `approval_list` and `approval_resolve`; runtime control uses `mission_run`, `mission_pause`, `mission_resume`, `mission_cancel`, and `mission_budget_increase`. See the [Missions API reference](/for-agents/missions) and [Mission Recipes](/for-agents/ai/mission-recipes).
</Note>