fix(ai-gateway): Update A2A docs

[tomek-labuk]

Description

Fixes broken currency agent.

NOTE: This PR is to be retested before final reviews.

Preview Links

https://deploy-preview-4895--kongdeveloper.netlify.app/how-to/proxy-a2a-agents/
https://deploy-preview-4895--kongdeveloper.netlify.app/how-to/secure-a2a-endpoints/
https://deploy-preview-4895--kongdeveloper.netlify.app/how-to/secure-a2a-endpoints-with-oidc/
https://deploy-preview-4895--kongdeveloper.netlify.app/how-to/rate-limit-a2a-traffic/
https://deploy-preview-4895--kongdeveloper.netlify.app/how-to/limit-a2a-request-size/

Checklist

• Tested how-to docs. If not, note why here.
• All pages contain metadata.
• Any new docs link to existing docs.
• All autogenerated instructions render correctly (API, decK, Konnect, Kong Manager).
• Style guide (capitalized gateway entities, placeholder URLs) implemented correctly.
• Every page has a description entry in frontmatter.
• Add new pages to the product documentation index (if applicable).

[netlify]

✅ Deploy Preview for kongdeveloper ready!

Name	Link
🔨 Latest commit	c77ed40
🔍 Latest deploy log	https://app.netlify.com/projects/kongdeveloper/deploys/69e9be8a31266e00080a7f87
😎 Deploy Preview	https://deploy-preview-4895--kongdeveloper.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[Copilot]

Pull request overview

Updates the AI Gateway A2A how-tos to use a KongAir sample A2A agent (instead of the currency conversion sample), aligning prerequisites, entity examples, and request examples across the docs.

Changes:

• Added a new prereq include for running the KongAir A2A agent via Docker Compose.
• Added new Gateway entity examples for the KongAir A2A Service and Route.
• Updated multiple A2A how-tos to reference the new Service/Route and use KongAir-focused request examples.

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
app/_includes/prereqs/a2a-kongair-agent.md	New prereq instructions for running the KongAir A2A agent container.
app/_how-tos/ai-gateway/secure-a2a-with-oidc.md	Switches prereqs/examples to the KongAir agent and updates sample requests.
app/_how-tos/ai-gateway/secure-a2a-traffic.md	Switches prereqs/examples to the KongAir agent and updates validation samples.
app/_how-tos/ai-gateway/rate-limit-a2a-traffic.md	Switches prereqs and rate-limiting namespace to the KongAir agent.
app/_how-tos/ai-gateway/proxy-a2a-agents.md	Switches prereqs and sample outputs/requests to the KongAir agent.
app/_how-tos/ai-gateway/limit-a2a-body-size.md	Switches prereqs/examples to the KongAir agent and updates sample request text.
app/_data/entity_examples/gateway/services/a2a-kongair-agent.yaml	New Service entity example targeting the agent on port 10000.
app/_data/entity_examples/gateway/routes/a2a-kongair-route.yaml	New Route entity example for /a2a pointing to the new Service.

Comments suppressed due to low confidence (2)

app/_how-tos/ai-gateway/secure-a2a-with-oidc.md:199

• This section updates the example request to flights, but the concluding sentence still says the successful response contains a currency conversion result; update that description to match the KongAir agent/flight query example.

          text: "What flights are available on route KA-123?"
{% endvalidation %}
<!-- vale on -->

{{site.base_gateway}} validates the bearer token via Okta's JWKS endpoint, then proxies the request to the upstream A2A agent. A successful response contains a completed task with the currency conversion result.

app/_how-tos/ai-gateway/rate-limit-a2a-traffic.md:107

• The guide still claims Rate Limiting Advanced is per-consumer and uses an apikey header in examples, but it no longer enables Key Auth (or creates a Consumer), so readers won’t actually get per-consumer limits; either re-add the Key Auth + Consumer steps or adjust the text/examples to rate limit by IP instead.

## Enable the Rate Limiting Advanced plugin

The [Rate Limiting Advanced plugin](/plugins/rate-limiting-advanced/) counts requests per consumer and rejects requests that exceed the configured limit. This configuration allows 5 requests per 30 seconds, intentionally low to make it easy to trigger during testing.