Update samplingMode preset documentation and WebIDL enum

[isaacahouma]

Proposal: Add intermediate sampling modes (slightly-predictable and slightly-creative)

This PR expands the Prompt API's LanguageModelSamplingMode enum with two intermediate presets to cover the gaps in the preset spectrum:

• slightly-predictable: For focused outputs with a bit more variation than predictable.
• slightly-creative: For creative outputs that are slightly more focused than creative.

Spec & Explainer Changes:

• Expose slightly-predictable and slightly-creative in the LanguageModelSamplingMode WebIDL enum in index.bs.
• Document the new modes and their descriptions in the README.md explainer.

---

💥 Error: 422 Unprocessable Entity 💥

PR Preview failed to build. (Last tried on Jul 28, 2026, 8:56 PM UTC).

More

PR Preview relies on a number of web services to run. There seems to be an issue with the following one:

🚨 Spec Generator - Spec Generator is the web service used to build bikeshed/ReSpec specs

🔗 Related URL

Error output:

[
    {
        "lineNum": "329:44",
        "messageType": "link",
        "text": "Multiple possible 'getting the language availabilities partition' dfn refs.\nArbitrarily chose https://webmachinelearning.github.io/proofreader-api/#get-the-language-availabilities-partition\nTo auto-select one of the following refs, insert one of these lines into a <pre class=link-defaults> block:\nspec:proofreader-api; type:dfn; text:get the language availabilities partition\nspec:writing-assistance-apis; type:dfn; text:get the language availabilities partition"
    },
    {
        "lineNum": "331:45",
        "messageType": "link",
        "text": "Multiple possible 'getting the language availabilities partition' dfn refs.\nArbitrarily chose https://webmachinelearning.github.io/proofreader-api/#get-the-language-availabilities-partition\nTo auto-select one of the following refs, insert one of these lines into a <pre class=link-defaults> block:\nspec:proofreader-api; type:dfn; text:get the language availabilities partition\nspec:writing-assistance-apis; type:dfn; text:get the language availabilities partition"
    },
    {
        "lineNum": "335:59",
        "messageType": "link",
        "text": "Multiple possible 'computing language availability' dfn refs.\nArbitrarily chose https://webmachinelearning.github.io/proofreader-api/#compute-language-availability\nTo auto-select one of the following refs, insert one of these lines into a <pre class=link-defaults> block:\nspec:proofreader-api; type:dfn; text:compute language availability\nspec:writing-assistance-apis; type:dfn; text:compute language availability"
    },
    {
        "lineNum": "342:60",
        "messageType": "link",
        "text": "Multiple possible 'computing language availability' dfn refs.\nArbitrarily chose https://webmachinelearning.github.io/proofreader-api/#compute-language-availability\nTo auto-select one of the following refs, insert one of these lines into a <pre class=link-defaults> block:\nspec:proofreader-api; type:dfn; text:compute language availability\nspec:writing-assistance-apis; type:dfn; text:compute language availability"
    },
    {
        "lineNum": null,
        "messageType": "failure",
        "text": "Did not generate, due to errors exceeding the allowed error level."
    }
]

This seems to be an issue with the Spec Generator service. PR Preview doesn't manage this service and so has no control over it. If you've identified an issue with it, you can report the issue to the maintainers of Spec Generator directly. Please be courteous. Thank you!

If you don't have enough information above to solve the error by yourself or if the issue doesn't seem related to Spec Generator, you can file an issue with PR Preview.