> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/technical-reference/workflow-execution/timeouts-and-execution-limits.md).

# Timeouts and Execution Limits

Timeouts limit waiting at different stages of a request. A client timeout, a provider timeout, and a workflow execution limit do not mean the same thing.

![Follow the existing run after a client timeout](https://1957915746-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FLe7Lu37b7n1qw0ftG93m%2Ftimeouts-and-execution-limits.png?alt=media)

A client deadline does not cancel the workflow. Follow the existing run and reconcile any external writes before repeating the request. These are operation excerpts; authenticate each request.

<details>

<summary>Copy the example</summary>

```http
# Keep the run ID returned when execution started.
GET /v2/runs/{run_id}

# Inspect the state before submitting another run.
# running / queued: execution is still in progress
# paused: a human response is required
# succeeded / failed / cancelled: terminal states

# Explicitly request a stop when necessary.
POST /v2/runs/{run_id}/cancel
```

</details>

## Before you begin

The run ID, error details, and configuration of the failing node or client.

## Key concepts

| Term                 | Definition                                                                                                                                                |
| -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Cancellation request | A request to stop an execution. Acceptance is not confirmation that all work has stopped.                                                                 |
| Side effect          | A change outside the returned answer, such as creating a record or sending email. Cancellation or release rollback does not undo a completed side effect. |

## Configuration options

| Option          | Purpose                                                                      | Behavior                                                                  |
| --------------- | ---------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
| Timeout         | A limit on how long a particular client or operation waits.                  | It does not always establish that execution or an external write stopped. |
| Execution limit | A cap on a run, model response, tool sequence, or other processing resource. | Identify which limit was reached before adjusting another setting.        |

## Set execution limits

1. Identify which component stopped waiting.
2. Read the current run state before starting another execution.
3. Adjust the relevant node, provider, or client setting only after identifying the cause.

You can distinguish a slow response from a stopped or failed execution.

## Behavior and limitations

An application deadline does not cancel a workflow. A tool’s network timeout does not establish whether the provider completed a write. There is no single timeout value that applies to every model, action, and execution path. Preserve run IDs and use explicit cancellation when stopping supported runs.

## Related resources

[Execution Order and Node Dependencies](https://docs.stackai.com/technical-reference/workflow-execution/execution-order-and-node-dependencies.md)


---

# 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://docs.stackai.com/technical-reference/workflow-execution/timeouts-and-execution-limits.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.
