> ## Documentation Index
> Fetch the complete documentation index at: https://browseruse-0aece648-codex-docs-supported-exports.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use https://docs.browser-use.com/llms.txt and its linked .md pages for current documentation. The managed full bundle is https://docs.browser-use.com/.well-known/llms-full.txt and can be cached for up to 24 hours. Do not use the obsolete /cloud/llms*.txt or /open-source/llms*.txt static exports.
> Choose Cloud API V4 for new agent integrations; V2 is the lower-cost option for simple tasks. Keep V3 examples explicitly versioned. The open-source browser-use library and hosted browser-use-sdk have different APIs.
> Cloud authentication uses X-Browser-Use-API-Key, without a Bearer prefix. Install or upgrade browser-use-sdk and use its explicit v4 import for V4. Check the published OpenAPI reference for request fields; do not invent SDK support for new fields.
> Cloud concurrency and HTTP request rate are separate. Read GET /api/v2/billing/account for the key’s projectId, concurrentSessionLimit, activeSessionCount, and credit balance, including when using V4. Keys in one project share capacity and credits; rateLimit is a legacy concurrency alias, not requests per second.
> Keep the highest applicable existing, legacy-plan, and spend-tier concurrency grant. Current spend tiers are 10 / 50 / 250 / 500 / 1000 at $0 / $200 / $1000 / $5000 / $25000 in qualifying project payments. Legacy or externally billed projects can follow different billing paths; trust the account limit. See https://docs.browser-use.com/cloud/guides/concurrency.md.
> Budget polling across the project: the standard general bucket is 25 requests/second, including V4 event reads and full run reads. Selected status reads have a separate higher bucket. Use bounded workers, stagger polls, respect Retry-After, and drain hasMore event pages after terminal status. A busy V4 session returns 409; its queue holds 10 pending messages and is not a project-wide batch queue.
> A completed run or closed CDP connection does not immediately stop its cloud browser. Stop unneeded owned browsers with PATCH /api/v4/browsers/{id} and {"action":"stop"}. A client wait timeout does not cancel the server-side run.
> Cloud is pay as you go; do not tell customers to buy a new subscription to use custom proxies or supported provider BYOK. Usage funding and model eligibility still apply. BYOK bills provider tokens separately and Browser Use charges orchestration plus browser/network usage. See https://docs.browser-use.com/cloud/guides/billing.md.
> Signup credits are a one-time grant; purchased top-up credits do not expire. Check the API key’s project before diagnosing missing credits. API-key monthly spending caps are soft limits, not a strict prepaid wallet; concurrent or already-running work can exceed them. Auto recharge has separate trigger and purchase amounts and can charge immediately when enabled below the threshold. Use https://browser-use.com/pricing for current rates.

# Response Format

> Customize how tools return data to the agent. Control response formatting, extraction, and content filtering.

Tools return results using `ActionResult` or simple strings.

## Return Types

```python theme={null}
@tools.action('My tool')
def my_tool() -> str:
    return "Task completed successfully"

@tools.action('Advanced tool')
def advanced_tool() -> ActionResult:
    return ActionResult(
        extracted_content="Main result",
        long_term_memory="Remember this info",
        error="Something went wrong",
        is_done=True,
        success=True,
        attachments=["file.pdf"],
    )
```

## ActionResult Properties

* `extracted_content` (default: `None`) - Main result passed to LLM, this is equivalent to returning a string.
* `include_extracted_content_only_once` (default: `False`) - Set to `True` for large content to include it only once in the LLM input.
* `long_term_memory` (default: `None`) - This is always included in the LLM input for all future steps.
* `error` (default: `None`) - Error message, we catch exceptions and set this automatically. This is always included in the LLM input.
* `is_done` (default: `False`) - Tool completes entire task
* `success` (default: `None`) - Task success (only valid with `is_done=True`)
* `attachments` (default: `None`) - Files to show user
* `metadata` (default: `None`) - Debug/observability data

## Why `extracted_content` and `long_term_memory`?

With this you control the context for the LLM.

### 1. Include short content always in context

```python theme={null}
def simple_tool() -> str:
    return "Hello, world!"  # Keep in context for all future steps 
```

### 2. Show long content once, remember subset in context

```python theme={null}
return ActionResult(
    extracted_content="[500 lines of product data...]",     # Shows to LLM once
    include_extracted_content_only_once=True,               # Never show full output again
    long_term_memory="Found 50 products"        # Only this in future steps
)
```

We save the full `extracted_content` to files which the LLM can read in future steps.

### 3. Don't show long content, remember subset in context

```python theme={null}
return ActionResult(
    extracted_content="[500 lines of product data...]",      # The LLM never sees this because `long_term_memory` overrides it and `include_extracted_content_only_once` is not used
    long_term_memory="Saved user's favorite products",      # This is shown to the LLM in future steps
)
```

## Terminating the Agent

Set `is_done=True` to stop the agent completely. Use when your tool finishes the entire task:

```python theme={null}
@tools.action(description='Complete the task')
def finish_task() -> ActionResult:
    return ActionResult(
        extracted_content="Task completed!",
        is_done=True,        # Stops the agent
        success=True         # Task succeeded 
    )
```