Skip to content

For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.

Page as Markdown

Transformations

Mutate and transform requests and responses before forwarding them to the destination.

Templating language

Inject response headers

Extract values from a request header and inject it as a header to your response.

Generate request tracing headers

Use uuid() and random() CEL functions to inject a unique request ID and a random sampling value into …

Encode base64 headers

Automatically encode and decode base64 values in request headers.

Rewrite dynamic path segments

Use CEL functions to rewrite request paths in a header.

Forward request URLs

Use CEL expressions to construct a full request URL from context variables and forward it upstream …

Change request path and method

Use pseudo headers to conditionally rewrite the request path and HTTP method based on a request …

Promote query parameters to request headers

Read a query parameter from the request URI and inject it as a request header using a CEL …

Inject LLM model headers

Detect model fallback by injecting the requested and actual LLM model names as response headers …

Remove headers

Remove sensitive or internal headers from requests before they reach the upstream.

Inject response bodies

Learn how to return a customized response body and how to replace specific values in the body.

Change response bodies

Update the response status based on the headers in a response.

Filter and merge request body fields

Use filterKeys() and merge() CEL functions to strip unwanted fields from a JSON request body and …

Validate and set request body defaults

Use default() and fail() CEL functions to enforce required fields and apply default values on a JSON …

Enrich access logs

Log CEL context variables to access logs to inspect and debug transformation expressions at runtime.

Was this page helpful?
Agentgateway assistant

Ask me anything about agentgateway configuration, features, or usage.

Note: AI-generated content might contain errors; please verify and test all returned information.

Tip: one topic per conversation gives the best results. Use the + button in the chat header to start a new conversation.

Switching topics? Starting a new conversation improves accuracy.
↑↓ navigate select esc dismiss

What could be improved?

Your feedback helps us improve assistant answers and identify docs gaps we should fix.

Need more help? Join us on Discord: https://discord.gg/y9efgEmppm

Want to use your own agent? Add the Solo MCP server to query our docs directly. Get started here: https://search.solo.io/.