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

# Runs & Observability

> Every agent session, recorded — tool calls, tokens, cost, and the diff it produced

A **run** is one agent session in a workspace: a goal, the turns that followed, every tool the agent called, and the changes it left behind. Runs are recorded as they happen, so nothing about a session is reconstructed after the fact.

Each run opens as a tab in the workspace. Multiple runs can be open at once -- see [multiple sessions](/multi-session).

## **What A Run Records**

| **Recorded**         | **Detail**                                                                   |
| -------------------- | ---------------------------------------------------------------------------- |
| **Goal**             | The prompt that started the run                                              |
| **Provider & model** | Snapshotted at start, so a later settings change never rewrites history      |
| **Status**           | `queued` → `running` → `succeeded` / `failed` / `canceled`                   |
| **Turns**            | Each exchange, with its own token counts and cost                            |
| **Tool calls**       | Every invocation with arguments, output, and status -- nested calls included |
| **Artifacts**        | Files and outputs the agent produced                                         |
| **Diff**             | The working-tree change the run produced, captured against the run's start   |

The system prompt, config, and tool policy in force are snapshotted too, so an old run stays reproducible.

## **Reading The Transcript**

### Turn rail

Once a run has more than a few exchanges, a rail of ticks appears down the left edge -- one per user message. It's a map of the whole conversation, not a scrollbar: hovering a tick previews what was asked and how the answer opened, and clicking scrolls the transcript there.

### Context usage ring

A circular indicator shows how much of the model's context window the session has consumed. Hovering breaks it down. It turns amber as the auto-compact threshold approaches and red once the window is nearly full.

### Usage tooltip

Each response is stamped with how long it took. Hovering that duration shows the turn's input, output, cache-read, and cache-write tokens, plus its cost.

### Run detail level

**Settings → General → Run Detail** controls how much of this the transcript shows -- collapse tool calls and their outputs down to a summary, or expand everything.

## **Resuming And Forking**

| **Action**   | **What happens**                                                                                             |
| ------------ | ------------------------------------------------------------------------------------------------------------ |
| **Continue** | Send another message -- Mains resumes the provider session by its session id, so the agent keeps its context |
| **Fork**     | Branch a new run from any response in the transcript                                                         |

Fork is the ⑂ button next to a response. It starts a fresh run seeded from that point, leaving the original untouched -- useful for trying a second approach without losing the first.

<Note>
  Fork is available for Claude, Codex, and Cursor. Copilot runs don't support it.
</Note>

## **Beyond A Single Run**

| **Surface**                           | **Scope**                                                  |
| ------------------------------------- | ---------------------------------------------------------- |
| [Changes / diff viewer](/diff-viewer) | What the run wrote, per file                               |
| [Reviews](/reviews)                   | Findings raised against the workspace                      |
| [Pulse](/pulse)                       | Runs on a schedule you define                              |
| [Dashboard](/stats)                   | Runs, cost, tool usage, and success rate across workspaces |

Runs can be **archived** when you're done with them -- they leave the tab strip but stay queryable.