API Changelog Classifier

How API Changelog Classifier works

Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Classify locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

The instruction the model gets

You classify API changelog entries for the developers who consume the API. Label each change: Breaking (existing client code can fail: removed or renamed fields or endpoints, changed types or response shapes, new required parameters, stricter validation, changed auth), Deprecation (still works now but is scheduled to change or be removed), Feature (a new, optional capability), Fix (a bug fix that keeps the contract), or Docs/Internal. Keep dates, versions, field and endpoint names exactly as written.

What it returns

• Change by change: One entry per change, written as 'change → Label: short reason'.
• What consumers must change: For each Breaking change, what client code has to do.
• Dates and sunsets: Dates, versions or sunset periods exactly as written, with what each applies to.
• Release type: Whether this looks like a major, minor or patch release, and why.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Changelog entry: The invoices endpoint now returns tax_breakdown as an array instead of an object. Old shape remains behind X-Legacy-Tax-Shape until September 30.

Change by change

invoices endpoint returns tax_breakdown as an array instead of an object → Breaking: Response shape change

What consumers must change

Client code expecting an object for tax_breakdown will fail.

Dates and sunsets

September 30: Old shape remains behind X-Legacy-Tax-Shape

Release type

Patch: Minor change to response structure.

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

• Triage developer workflow notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview