Convert compression middleware to route-specific

[shenald-dev]

Converted the global compression() middleware to a route-specific middleware on the /v1/chat/completions endpoint. This prevents unhandled routes (404s) and lightweight responses from incurring unnecessary CPU overhead and memory allocation for compression. Bumped version to 1.1.32 and updated CHANGELOG.md and ledger files.

---

PR created automatically by Jules for task 16502635405221466179 started by @shenald-dev

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[shenald-dev]

Looks good. Ensure there is test coverage verifying that compression is applied only to the /v1/chat/completions endpoint and not to other routes.

Reviewed — quality: high

[shenald-dev]

Looks good, merging this in. CI is green and everything checks out 👍

Move compression middleware to be route-specific for /v1/chat/completions to reduce unnecessary CPU and memory overhead.

[google-labs-jules]

Looks good. Ensure there is test coverage verifying that compression is applied only to the /v1/chat/completions endpoint and not to other routes.

Reviewed — quality: high

Added explicit tests to verify that compression() is attached to the /v1/chat/completions endpoint and that the /health endpoint is not compressed. Instead of altering the payload size or framework defaults to assert on Content-Encoding, the test cleanly asserts on the Vary header behavior (Accept-Encoding) that the middleware introduces when attached, even if the payload doesn't exceed the threshold.

[google-labs-jules]

Looks good, merging this in. CI is green and everything checks out 👍

Move compression middleware to be route-specific for /v1/chat/completions to reduce unnecessary CPU and memory overhead.

Acknowledged.