> For the complete documentation index, see [llms.txt](https://agpt.co/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agpt.co/docs/integrations/block-integrations/manage_session.md).

# Conductor Manage Session

Renames, cancels or archives a Conductor agent session. Requires your own Conductor API key, created at [app.conductor.build/users/api-keys](https://app.conductor.build/users/api-keys) and added through AutoGPT’s credentials UI. Select that credential for each Conductor block; no server-wide default key is used.

## Conductor Manage Session

### What it is

Rename, cancel or archive a Conductor agent session. Cancel stops the running turn and drops queued prompts.

### How it works

One `action` per run: `rename` posts `{name}` to `/rename`; `cancel` posts `{}` to `/cancel`, stopping the current turn and dropping queued prompts; `archive` posts `{}` to `/archive`. Cancel and archive report `canceled_queued_messages`. The `status` output is Conductor's immediate response: cancellation can still report `working` while the agent stops. Use Get Session to confirm that it reaches `idle`.

### Inputs

| Input       | Description                                                               | Type                              | Required |
| ----------- | ------------------------------------------------------------------------- | --------------------------------- | -------- |
| session\_id | Session ID                                                                | str                               | Yes      |
| action      | rename, cancel (stop the current turn and drop queued prompts) or archive | "rename" \| "cancel" \| "archive" | No       |
| name        | New session name (rename)                                                 | str                               | No       |

### Outputs

| Output                     | Description                                     | Type            |
| -------------------------- | ----------------------------------------------- | --------------- |
| error                      | Error message if the operation failed           | str             |
| session\_id                | Session ID                                      | str             |
| workspace\_id              | Workspace the session belongs to, when reported | str             |
| status                     | Session status after the action, when reported  | str             |
| canceled\_queued\_messages | Queued prompts dropped by cancel or archive     | int             |
| result                     | Raw API response                                | Dict\[str, Any] |

### Possible use case

**Stop a runaway agent**: Cancel a session whose `status` has been `working` past a deadline.

**Housekeeping**: Archive finished sessions so Get Workspace lists only active chats.

***


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://agpt.co/docs/integrations/block-integrations/manage_session.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.